Feedback control system and method for glass tube conversion process

Abstract

A method of providing feedback control of a converter for converting glass tubes into glass articles includes a model predictive control framework. The method includes operating a converter, providing a target value for a property of the glass article or glass tube, measuring the property of the glass article and glass tube, adjusting the measurement data to remove abnormal data points and calculating a statistical value representative of the measured property, and determining updated settings for the one or more process parameters from the previous settings, the statistical characteristic, and the target value, wherein the updated settings are those that minimize a target control function of the converter. The method further includes adjusting the process parameter to an updated setting. The model predictive control framework is capable of feedback control of the converter to compensate for disturbances acting on the process.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of priority to U.S. application serial number 17 / 746,396, filed on May 17, 2022, and the benefit of priority to U.S. provisional application serial number 63 / 344,851, filed on May 22, 2023, under 35 U.S.C. §120, the contents of which are based and are incorporated herein by reference in their entirety. Technical Field

[0002] The present specification relates generally to systems and methods for producing glass articles from glass tubes and, more particularly, to systems and methods for feedback control of a glass tube conversion process. Background Art

[0003] Historically, glass has been used as a preferred material for packaging pharmaceuticals due to its airtightness, optical clarity, and excellent chemical durability relative to other materials. Specifically, glass used in pharmaceutical packaging must have sufficient chemical durability to prevent affecting the stability of the pharmaceutical formulation contained therein. Glasses with suitable chemical durability include those within the ASTM standard "Type IA" and "Type IB" glass compositions, which have a history of proven chemical durability.

[0004] Glass tubes can be converted into other glass products, such as various glass containers for pharmaceutical applications, including but not limited to vials, syringes, ampoules, cartridges and other glass products. Glass tubes can, for example, be converted in a "conversion machine". Conversion machines have been used for more than 75 years and are currently manufactured by various commercial and in-house equipment suppliers. These conversion machines typically use steps including flame processing, rotating and fixed tool shaping, thermal separation or scratching and impact cutting steps to reshape long glass tubes into multiple glass products. Various burners and forming tools are typically used to shape one or more products from the glass tube and separate the products from the glass tube. Summary of the invention

[0005] During the conversion of a glass tube into a glass product using a conversion machine (i.e., a converter), a heating element (such as a burner) heats the glass of the glass tube to a temperature at which the viscosity of the glass allows the glass to form one or more features of the glass product. The forming station includes a forming tool, such as a pin and wheel assembly, to contact the heated glass tube and form the internal and external dimensions of the features of the finished glass product. Conventional conversion machines use simple needle valves to adjust the burner output in the heating station. The position of the forming tool on a conventional conversion machine is adjusted by a mechanical linkage, which is typically connected to a cam drive shaft. Burner output, burner positioning, forming tool position, and forming tool contact timing can affect the dimensional yield and defect rate of the converter. In addition, hundreds of other process settings and inputs on a typical conversion machine can affect the dimensional yield and defect rate that can be achieved by the conversion machine.

[0006] Historically, the control strategies used to manage the hundreds of process settings and inputs of traditional conversion machines have relied on human operators. In particular, these human operators of various experience levels have been relied upon to change the burner parameters, forming unit parameters, and overall machine timing for vials of different geometries. Human operators manage the normal day-to-day variations that occur in this process by adjusting these same parameters. The extent to which producers are able to consistently produce high yields and high-quality glass products from conversion machines is highly dependent on the skill level and experience of the machine operators operating the conversion machines. Differences in operator experience levels from line to line and from shift to shift can result in significant variations in the yield and quality of vials produced by the process. Despite advances in "add-on" control settings and automation (such as mass flow control valves, servo motors, and / or PLC controllers), the current state of the art is that human operators still make decisions and ultimately drive all input parameters of the converter.

[0007] Therefore, a need exists for a system and method to provide feedback control for a converter that converts glass tubing into glass articles, such as pharmaceutical packaging, to reduce variability in operation and to increase yield and reduce defect rates.

[0008] In a first aspect of the present disclosure, a method for controlling a converter for producing glass products from glass tubes may include operating the converter to produce a plurality of glass products from a plurality of glass tubes, wherein the converter includes a plurality of processing stations, and operating the converter may include translating the glass tube to sequentially pass through each of the plurality of processing stations. The method may further include providing a target value for at least one property of the plurality of glass products or the plurality of glass tubes during or after the conversion, measuring at least one property of the plurality of glass products or the plurality of glass tubes during or after the conversion, recording a setting of at least one process parameter of the converter associated with the at least one property to generate a data set including the measured values ​​of the at least one property and the setting of the at least one process parameter of the converter, processing the data set to generate a statistical characteristic of a distribution of the measured values ​​of the at least one property, and determining an updated setting for each of the at least one process parameter based on the statistical characteristic of the distribution of the measured at least one property, the target value of the at least one property, and the setting of the at least one process parameter. The updated setting of the at least one process parameter may be a value of the setting that minimizes the target control function of the at least one property. The method may further include adjusting each of the at least one process parameter of the converter to the updated setting.

[0009] A second aspect of the present disclosure may include the first aspect, further comprising repeatedly measuring at least one attribute, recording a setting of each of at least one process parameter, processing a data set, determining an updated setting of each of at least one process parameter, and adjusting each of at least one process parameter until the updated setting of each of at least one process parameter converges.

[0010] A third aspect of the present disclosure may include any one of the first aspect or the second aspect, wherein processing a data set may include removing abnormal data points from a data set of measurement values ​​of at least one attribute, and after removing the abnormal data points, calculating statistical characteristics of the distribution of the measurement values ​​of at least one attribute from the data set.

[0011] A fourth aspect of the present disclosure may include the third aspect, wherein the statistical property of the distribution of the data set may be a mean, a median, a range, a standard deviation, a variance, or a combination of these.

[0012] A fifth aspect of the present disclosure may include any one of the first to fourth aspects, further comprising providing a specification range for each of the at least one attribute. The specification range of the attribute may include a minimum value of the attribute and a maximum value of the attribute, below which the glass product is considered to be out of specification and above which the glass product is considered to be out of specification. The method may further include applying an attribute weighting factor to each of the at least one attribute in the objective control function based on a spread of the specification range for each of the at least one attribute.

[0013] A sixth aspect of the present disclosure may include the fifth aspect, further comprising determining an attribute weighting factor according to a specification range of each attribute of at least one attribute.

[0014] A seventh aspect of the present disclosure may include the sixth aspect, comprising determining a process capability index C for each of at least one attribute from a specification range. pk , and a process capability index C based on each of at least one of the attributes pk An attribute weighting factor is determined for each of the at least one attribute.

[0015] An eighth aspect of the present disclosure may include any one of the first to seventh aspects, further comprising constructing a penalty factor for each of at least one process parameter and applying the penalty factor to each of at least one process parameter in the target control function, wherein the penalty factor is operated to reduce the magnitude of changes in process parameters that have a greater impact on one or more of at least one attribute.

[0016] A ninth aspect of the present disclosure may include the eighth aspect, further comprising repeating the method of the eighth aspect for a plurality of iterations, identifying a divergence or oscillation of an updated setting of one or more of the at least one process parameter that indicates a reduction in the ability to control one or more aspects of the converter, and adjusting a penalty factor of one or more of the at least one process parameter. Adjusting the penalty factor may reduce the magnitude of changes made to the one or more process parameters in each iteration of the method, thereby tending to reduce the divergence or oscillation of the updated setting.

[0017] A tenth aspect of the present disclosure may include the ninth aspect, wherein divergence may be indicated by an oscillation or a continuous increase in the objective control function at each iteration of the method.

[0018] The eleventh aspect of the present disclosure may include any one of the first to tenth aspects, further including providing a maximum setting and a minimum setting for each of at least one process parameter, and maintaining an updated setting of each of at least one process parameter within a range between the minimum setting and the maximum setting of the process parameter.

[0019] A twelfth aspect of the present disclosure may include any one of the first to eleventh aspects, wherein the objective control function may include a mean square error cost function according to the following equation: Therefore, there is a need for a system and method for providing feedback control for a converter that converts a glass tube into a glass product (such as a pharmaceutical package) to reduce variability in operation and improve yield and reduce defect rate. J(k)=(G*Act[k)+Attrib measured(k)-G*Act(k-1)-Attrib targ ) T Q T Q(G*Act(k)+Attrib measured (k)-(G*Act(k-1))-Attrib tArg )+(Act(k)-Act(k-1)) T R T R(Act(k)-Act(k-1)); where: J(k) is the mean square error cost function that varies with k, k is an integer indicating the current number of iterations to minimize the mean square error cost function, G is a sensitivity factor matrix representing the degree to which a change in each of at least one process parameter produces a change in each of at least one attribute, Attrib measured (k) is a vector of statistical characteristics of the distribution of the measured values ​​of at least one attribute during iteration k, Act(k) is the setting of the process parameters at iteration k, Act(k-1) is the setting of the process parameters for process parameter iteration k-1, Attrib targ is a vector of target values ​​for each of at least one attribute, Q T Q is a symmetric weighting matrix of attribute weighting factors for errors of attribute measurement values ​​from attribute target values, and RTR is a symmetric weighting matrix of penalty factors for variations of at least one process parameter.

[0020] A thirteenth aspect of the present disclosure may include the twelfth aspect, further comprising constructing a target control function.

[0021] The fourteenth aspect of the present disclosure may include the thirteenth aspect, wherein constructing the target control function may include constructing at least one model associated with the predicted value of at least one attribute for each setting of at least one process parameter. At least one model may include an expression, wherein the predicted value of at least one attribute may be the sum of at least one item depending on the setting of at least one process parameter and an offset constant. Constructing the target control function may further include providing an initial mean square error cost function, which is a function of the predicted value of each of the at least one attribute, the target value of each of the at least one attribute, and the setting of each of the at least one process parameter; substituting at least one model into the initial mean square error cost function of the predicted value of the at least one attribute; and solving at least one model of the offset constant to generate an offset constant function. Solving at least one model of the offset constant may include replacing the predicted value of each of the at least one attribute with the statistical characteristics of the measured value of each of the at least one attribute. Constructing the target control function may further include replacing the offset constant in the initial mean square error cost function with the offset constant function to generate the target control function.

[0022] A fifteenth aspect of the present disclosure may include the fourteenth aspect, wherein constructing at least one model may include conducting a "design of experiments" process, deriving at least one model from first principles, or a combination of these to produce at least one model.

[0023] A sixteenth aspect of the present disclosure may include any of the fourteenth or fifteenth aspects, further comprising periodically reconstructing at least one model to account for process variations over time or in response to known variations in the operation of the converter.

[0024] A seventeenth aspect of the present disclosure may include any one of the fourteenth to sixteenth aspects, further comprising applying a weighting factor for each of the at least one attribute to one or more terms of the objective control function.

[0025] An eighteenth aspect of the present disclosure may include any one of the fourteenth to seventeenth aspects, further comprising applying a penalty factor for each of at least one process parameter to one or more terms of the objective control function.

[0026] A nineteenth aspect of the present disclosure may include any one of the first to eighteenth aspects, wherein determining an updated setting for each of at least one process parameter may further include subjecting at least one process parameter to constraints including a maximum value and a minimum value of the at least one process parameter.

[0027] The twentieth aspect of the present disclosure may include any one of the first to nineteenth aspects, including providing target values ​​for multiple properties of multiple glass products, multiple glass tubes, or both; measuring multiple properties of multiple glass products, multiple glass tubes, or both for multiple glass products; and recording settings of multiple process parameters of the converter related to the multiple properties to generate multiple data sets. Each of the multiple data sets may include a measured value of each of the multiple properties of the converter during the time period and a setting of each of the multiple process parameters. The method may further include processing each of the multiple data sets to generate a statistical characteristic of the distribution of each of the multiple properties; determining an updated setting of each of the multiple process parameters based on the statistical characteristic of the distribution of each of the multiple properties, the target value of each of the multiple properties, and the setting of each of the multiple process parameters; and adjusting each of the multiple process parameters of the converter to the updated setting of each of the multiple process parameters. The updated settings of the multiple process parameters may be the values ​​of the updated settings that minimize the objective control function.

[0028] A twenty-first aspect of the present disclosure may include any one of the first to twentieth aspects, further comprising displaying a user interface on a display.

[0029] A twenty-second aspect of the present disclosure may include the twenty-first aspect, further comprising receiving one or more user inputs from a user interface, and changing an updated setting of at least one process parameter based on the one or more user inputs.

[0030] A twenty-third aspect of the present disclosure may include any one of aspects one to twenty-second, wherein at least one property may include one or more properties of the converted glass article, one or more properties of one or more features of the partially formed glass article at the working end of the glass tube, one or more properties of the glass tube, one or more properties of the preform at the working end of the glass tube, or a combination of these.

[0031] A twenty-fourth aspect of the present disclosure may relate to a system for producing a plurality of glass products from a plurality of glass tubes. The system may include a converter, including: a plurality of holders, each holder operable to hold a glass tube and rotate the glass tube around a central axis of the glass tube; a plurality of processing stations, including at least one heating station, at least one forming station, and at least one separation station; and at least one measuring device, at least one measuring device operable to measure one or more properties of a glass product produced by the glass tube, each of the glass tubes, or both. The converter is operable to translate the glass tube through each of the plurality of processing stations in sequence to produce a plurality of glass products. The system may further include a control system communicatively coupled to the converter, the control system including one or more processors, one or more memory modules communicatively coupled to the one or more processors, and machine-readable and executable instructions stored on the one or more memory modules. When executed by one or more processors, the machine-readable and executable instructions may cause a control system to automatically measure at least one property of the glass article, the glass tube, or both with at least one measuring device; record settings of at least one process parameter of the converter associated with the at least one property to generate a data set including measured values ​​of the at least one property of the converter and settings of each of the at least one process parameter; process the data set to generate statistical characteristics of a distribution of measured values ​​of the at least one property; determine an updated setting of the at least one process parameter based on the statistical characteristics of the distribution of measured values ​​of the at least one property, a target value of the at least one property, and the settings of each of the at least one process parameter; and adjust the at least one process parameter of the converter to the updated setting. The updated setting of each of the at least one process parameter may be a value of the setting that minimizes a target control function of the at least one property.

[0032] It should be understood that both the above general description and the following detailed description describe various embodiments, and that they are intended to provide an overview or framework for understanding the nature and character of the claimed subject matter. The accompanying drawings are included to provide a further understanding of the various embodiments, and are incorporated into and constitute a part of this specification. The accompanying drawings illustrate various embodiments described herein, and together with the description, serve to explain the principles and operation of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 schematically depicts a front view of an embodiment of a system including a converter for producing a glass article from a glass tube according to one or more embodiments shown and described herein;

[0034] Figure 2 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 A top view of the main turret, secondary turret and feed turret of the converter;

[0035] Figure 3 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 Heating station for the converter;

[0036] Figure 4 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 An embodiment of a forming station of a converter;

[0037] Figure 5 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 Another embodiment of the forming station of the converter;

[0038] Figure 6 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 Cooling station for converters;

[0039] Figure 7 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 Separation station for converters;

[0040] Figure 8 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 The piercing station of the converter;

[0041] Fig. 9 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 Measuring station for converters;

[0042] Fig.10 Schematically depicts a schematic diagram of a system according to one or more embodiments shown and described herein. Figure 1 A perspective view of a segment of a glass tube in a converter before conversion;

[0043] Fig.11 schematically depicts another embodiment of a system including a converter for converting a glass tube to produce a glass article according to one or more embodiments shown and described herein;

[0044] Fig.12 Schematically depicts a method for providing a Fig.11 The control sequence of the feedback control of the converter;

[0045] Fig.13 graphically depicting a size of a glass article (y-axis) as a function of a unique identifier of the glass article (x-axis) for a plurality of condition sets according to one or more embodiments shown and described herein;

[0046] Fig.14 A diagrammatic representation of a Fig.13 Multiple operation models constructed based on the dimensional data and condition sets;

[0047] Fig.15 graphically depicting a size of a glass article (y-axis) as a function of a unique identifier of the glass article (x-axis) for a plurality of condition sets according to one or more embodiments shown and described herein;

[0048] Fig.16 A diagrammatic representation of a Fig.15 Multiple operation models constructed based on the dimensional data and condition sets;

[0049] Fig.17 A graph graphically depicting normalized measured values ​​of various properties of a glass vial as a function of normalized predicted values ​​of those properties using the operational model constructed in Example 2 in accordance with one or more embodiments shown and described herein;

[0050] Fig.18 A graph of the sum of squared errors (eg, target control function values) as a function of the number of iterations of the control methods of Example 2 and Example 3 is graphically depicted according to one or more embodiments shown and described herein;

[0051] Fig.19graphically depicting normalized measurements of 13 properties of glass vials produced in Example 2 at different iterations of the control method of Example 2 according to one or more embodiments shown and described herein;

[0052] Fig. 20 graphically depicting normalized measurements of maximum and minimum values ​​of each of flange outer diameter, flange inner diameter, flange height, and top height of a glass vial as a function of time in four iterations of the control method in Example 2 according to one or more embodiments shown and described herein; and

[0053] Fig.21 Normalized measurements of each of the bottom flange angle, top flange angle, shoulder angle, and shoulder radius of a glass vial as a function of time in four iterations of the control method in Example 2 are graphically depicted according to one or more embodiments shown and described herein. DETAILED DESCRIPTION

[0054] Reference will now be made in detail to embodiments of the disclosed system and method for controlling the operation of a glass tube conversion process for producing glass products, examples of which are illustrated in the accompanying drawings. Where possible, the same reference numerals will be used throughout the drawings to indicate the same or similar components. A method for controlling a converter for converting a glass tube into a glass product is disclosed herein, the method may include operating the converter to produce a plurality of glass products from a plurality of glass tubes, wherein the converter includes a plurality of processing stations, and operating the converter includes sequentially passing through each of the plurality of processing stations. The method may further include providing a target value for at least one property of the plurality of glass products or the plurality of glass tubes during or after the conversion, measuring at least one property of the plurality of glass products or the plurality of glass tubes during or after the conversion, and recording a setting of at least one process parameter of the converter related to the at least one property to generate a data set including measured values ​​of the at least one property and the setting of the at least one process parameter of the converter. The method may further include processing the data set to generate a statistical characteristic of a distribution of measured values ​​of the at least one property, and determining an updated setting for each of the at least one process parameter from the statistical characteristic of the distribution of the measured at least one property, the target value of the at least one property, and the setting of the at least one process parameter. The updated setting of the at least one process parameter may be a value of the setting that minimizes the target control function of the at least one property. In an embodiment, the objective control function may be derived from a cost function of the converter, such as but not limited to a mean square error cost function.The method may further include adjusting each of at least one process parameter of the converter to an updated setting.

[0055] Directional terms (eg, up, down, right, left, front, back, top, bottom) as used herein are made solely with reference to the drawings as drawn and the coordinate axes provided therein and are not intended to imply an absolute orientation.

[0056] Unless otherwise expressly stated, any method described herein is not to be construed as requiring that its steps be performed in a particular order, nor requiring a particular orientation of any apparatus. Thus, in the absence of a method claim actually reciting an order to be followed in its steps, or any apparatus claim actually reciting an order or orientation of individual components, or otherwise specifically stating in the claim or description that the steps are to be limited to a particular order, or reciting a particular order or orientation of components of an apparatus, no order or orientation is intended to be inferred in any respect. This applies to any possible non-explicit basis for interpretation, including: matters of logic with respect to the arrangement of steps, flow of operations, order of components, or orientation of components; ordinary meaning derived from grammatical organization or punctuation; and the number or type of embodiments described in the specification.

[0057] As used herein, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Thus, for example, reference to an (a) component includes aspects having two or more such components unless the context clearly dictates otherwise.

[0058] As used herein, the "working end" of the glass tube is the end of the glass tube oriented toward the processing station of the main turret of the converter relative to the holder, and the "non-working end" of the glass tube is the end of the glass tube oriented away from the processing station of the main turret.

[0059] As used herein, the "residence time" of a converter refers to the duration of time that a glass tube spends in a particular processing station before being passed to the next subsequent processing station.

[0060] As used herein, the term "active time" refers to the duration of time that a glass tube remains engaged with at least one heating element or at least one forming tool in a particular processing station.

[0061] As used herein, the term "indexing time" refers to the duration of time it takes to index a glass tube from one processing station to the next when used in connection with an indexing converter. "Dwell time," "active time," and "indexing time" are all measured in units of time.

[0062] "Engagement" of the burner with the glass tube refers to placing the burner in a position where the flame from the burner extends to or contacts the glass tube to heat the glass tube when used in connection with the heating station. Conversely, when the burner is disengaged from the glass tube, the burner is placed in a position where the flame from the burner is directed away from the glass tube or moved far enough away from the glass tube that the flame does not contact or directly heat the glass tube.

[0063] When used in relation to a forming tool in a forming station, the term "engaged" means that the forming tool contacts the glass tube. When the forming tool is disengaged from the glass tube, the forming tool does not contact the glass tube.

[0064] As used herein, the term "parts rate" refers to the production rate or throughput rate of a converter in terms of number of glass articles per unit time.

[0065] As used herein, the term "circumference" of a glass tube refers to a set of points at a constant radius r of the glass tube over 360 degrees from a central axis D of the glass tube at a specific Z position (i.e., a position on the + / -Z axis of the drawing). For example, the circumference of the glass tube may coincide with the outer surface of the glass tube at a specific Z position or the inner surface of the glass tube at a specific Z position.

[0066] As used herein, the term "operation" refers to normal steady-state operation of the converter. Thus, as used herein, "operation settings" refer to settings of the converter for normal steady-state operation of the converter.

[0067] As used herein, the terms "upstream" and "downstream" refer to the location of the converter's processing stations relative to each other. A first processing station is considered "downstream" of a second processing station if the glass tube encounters the second processing station before encountering the first processing station. Likewise, a first processing station is considered "upstream" of a second processing station if the glass tube encounters the first processing station before encountering the second processing station.

[0068] Glass tubes can be converted into glass products, especially glass products for pharmaceutical applications, which may include but are not limited to vials, syringes, ampoules, cartridges and other glass products. A converter (i.e., a conversion machine) including multiple processing stations can be used to convert glass tubes into these glass products. The processing station may include a heating station, a forming station, a thermal separation station and a piercing station, as well as other types of processing stations. The conversion machine typically uses steps including but not limited to flame processing, rotating and fixed tool forming, separation (such as thermal separation or scoring and impact cutting steps), piercing, cooling, measuring or other processing steps to reshape the long glass tube into a variety of glass products. Therefore, the glass products produced by the conversion process on the conversion machine are subjected to a series of flame burners or other heating elements and forming tools to shape the glass tube into a specific shape and size, and the shaped glass products are separated from the glass tube.

[0069] Reference now Figure 1 , schematically depicts one embodiment of a converter 100 for producing glass products from a glass tube 102. The converter 100 can be used to convert the glass tube 102 into a plurality of glass products. The converter 100 can include a base 104 having a plurality of processing stations 106 and a main turret 108 located above the base 104 and rotating relative to the base 104 about a central axis A. The converter 100 can further include a glass tube loading turret 110 located above the main turret 108 for feeding the glass tube 102 to the main turret 108. The converter 100 can also include a plurality of secondary processing stations 112 on the base 104 and a secondary turret 114 that can rotate relative to the base 104.

[0070] like Figure 1 , the base 104 of the converter 100 can be fixed, and the processing stations 106 can be coupled to the upper portion 105 of the base 104. The plurality of processing stations 106 can be spaced apart from each other and arranged in a main loop 116. In an embodiment, the main loop 116 can be circular so that the main turret 108 can be rotated about the central axis A by the main turret 108 to index or continuously move the glass tube 102 through the plurality of processing stations 106. Alternatively, in other embodiments, the main loop 116 can be a linear arrangement of processing stations 106. Although the description herein refers to a circular layout of processing stations 106, it should be understood that the subject matter disclosed herein can be equally well applied to converters having other arrangements of processing stations 106, such as linear, curved, or irregularly shaped arrangements of processing stations 106.

[0071] The type and / or shape of the glass article manufactured from the glass tube 102 may affect the total number of processing stations 106 of the converter 100. The number of processing stations 106 of the main turret 108 may be 14 to 32 processing stations 106. Although the converter 100 and the conversion process are described herein in the context of a converter 100 having sixteen processing stations 106 in the main loop 116, it should be understood that the converter 100 may have more or less than sixteen processing stations 106 in the main loop 116. By way of example and not limitation, the processing stations 106 may include one or more heating, forming, polishing, cooling, separating, piercing, measuring, feeding, unloading stations, other processing stations, or combinations thereof for producing glass articles from the glass tube 102. The type and / or shape of the article manufactured from the glass tube 102 may also affect the type of processing stations 106 of the converter 100 and / or the order of the processing stations 106.

[0072] The main turret 108 may be positioned above the base 104 and may be rotatably coupled to the base 104 such that the main turret 108 may rotate relative to the base 104 about a central axis A. The main turret 108 may be rotated relative to the base 104 using a drive motor (not shown). The main turret 108 may include a plurality of holders 130 configured to removably secure each glass tube 102 to the main turret 108. The holder 130 may be a clamp, a chuck, or other holding device, or a combination of holding devices. The holder 130 may orient each glass tube 102 such that the glass tube 102 is approximately parallel to the central axis A of the main turret 108 and approximately perpendicular to the upper portion 105 of the base 104. Although the converter 100 is described herein in the context of a vertically oriented converter 100, it should be understood that the converter 100 may be horizontally oriented or oriented at an angle such that the glass tube 102 is non-vertical during processing. Each of the holders 130 can be moved from the bottom portion 109 of the main turret 108 in the direction of the base 104 (i.e., in a direction relative to the base 104). Figure 1 Each holder 130 can be oriented to position the glass tube 102 at or near each successive processing station 106 of the main loop 116 of the base 104 as the main turret 108 indexes about the central axis A. The vertical orientation of the glass tubes 102 allows the working end 150 of each glass tube 102 to move or index incrementally through the processing stations 106.

[0073] In an embodiment, the converter 100 may be operable to index each of the plurality of holders 130 progressively through the plurality of processing stations 106. Indexing may refer to a stepwise process of moving the glass tube 102 to a processing station 106, holding the glass tube 102 at a stationary position XYZ position in the processing station 106 for a dwell time, and then indexing the glass tube 102 to the next processing station 106. Alternatively, in an embodiment, the converter 100 may be operable to continuously translate the plurality of holders 130 in a conversion process. In an embodiment, the processing station 106 may translate with the glass tube 102 in the processing station during the active time of the glass tube 102.

[0074] Each holder 130 can be individually rotated relative to the main turret 108 to rotate the glass tube 102 about a central axis D of the glass tube 102, which can be parallel to a central axis A of the main turret 108. Each of the holders 130 can be operably coupled to a motor (not shown), a continuous drive belt, or other drive mechanism for rotating each holder 130 about the central axis D of the glass tube 102 relative to the main turret 108. Rotation of the holders 130 allows the glass tube 102 to rotate about the central axis D of the glass tube 102 relative to a fixed burner, forming tool, cooling nozzle, or other feature of the processing station 106. The heating element or forming tool in the processing station 106 can be held in a fixed position relative to the glass tube 102, and the rotation of the glass tube 102 about the central axis D can be able to expose the entire circumference of the glass tube 102 to the heating element or forming tool.

[0075] refer to Figure 1 and Figure 2 , the converter 100 may include a plurality of secondary processing stations 112, which may also be spaced and arranged in a secondary loop 118 ( Figure 2 ). The converter 100 may include a secondary turret 114 ( Figure 1 ) for separating the product 103 ( Figure 1 ) indexed or continuously moved through the plurality of secondary processing stations 112. The secondary turret 114 can rotate relative to the base 104 about the second axis B. The second axis B can be substantially parallel to the central axis A of the primary turret 108. The secondary turret 114 can also include a plurality of holders 130 to hold the glass articles 103 and position the glass articles 103 to sequentially engage each of the secondary processing stations 112. The secondary turret 114 can be separated from the separation station 206 ( Figure 2 ) receives the glass product 103, indexes or continuously moves the product 103 through a plurality of secondary processing stations 112 by the rotation of a secondary turret 114, and discharges the finished product from the converter 100. Although shown in a circular pattern, it should be understood that the secondary processing stations 112 can be arranged in a linear, curved or irregular arrangement. The secondary processing stations 112 can be referred to as bottom formers. For vials, the secondary processing stations 112 are operable to form the bottom of the vial.

[0076] The converter 100 may include a device for loading a new length of glass tube 102 into the holder 130. In an embodiment, the converter 100 may include a glass tube loading turret 110 located adjacent to the main turret 108 from which the glass tube loading turret 110 is capable of loading a new length of glass tube 102 into the holder 130 of the main turret 108 in at least one processing station 106. In an embodiment, the glass tube loading turret 110 may be offset from the central axis A of the main turret 108. The glass tube loading turret 110 may be rotatable about an axis C, which may be substantially parallel to the central axis A of the main turret 108. The glass tube loading turret 110 may be independently supported in a fixed position relative to the main turret 108, and the rotation of the glass tube loading turret 110 may be independent of the rotation of the main turret 108. In an embodiment, the processing station 106 aligned with the glass tube loading turret 110 may be a tube loading station 214 ( Figure 2 When the converter 100 has converted all or most of the glass tubes 102 at a particular holder position 136 into one or more articles, the glass tube loading turret 110 may be indexed at the holder position 136 to align with the tube loading station 214 ( Figure 2 ), the new length of glass tube 102 is delivered to the holder 130 at the holder position 136 through the top of the main turret 108. Alternatively or additionally, in an embodiment, the converter 100 may include an arm (not shown) movable between the main turret 108 and the glass tube loading turret 110. When the converter 100 has converted all or a portion of the glass tubes 102 at a particular holder position 136, the arm may grab the new length of glass tube 102 from the glass tube loading turret 110 or other glass tube temporary storage device and deliver the new length of glass tube 102 to the main turret 108 at the particular holder position 136. Other methods and devices for delivering the new length of glass tube 102 to the main turret 108 are contemplated.

[0077] Reference now Figure 2 As previously described, the multiple processing stations 106 of the converter 100 may include one or more heating stations 202, forming stations 204, separation stations 206, cooling stations 210, piercing stations 212, tube loading stations 214, unloading stations 216, measuring stations 218, tube length unloading stations 220 or other stations and / or combinations of these stations. Figure 2 Schematically depicted is an arrangement of the processing stations 106 of a converter 100 having a primary loop 116 of sixteen processing stations 106 and a secondary loop 118 of eight secondary processing stations 112. As previously described, the processing stations 106 of the primary loop 116 may be evenly spaced and evenly distributed around the circular loop, and the secondary processing stations 112 of the secondary loop 118 may also be evenly spaced and evenly distributed around the circular loop. Figure 2A glass tube loading turret 110 having a plurality of loading channels 132 is also schematically depicted.

[0078] Figure 2 The main circuit 116 of the converter schematically depicted in FIG. 1 may include one or more heating stations 202, a separation station 206, a piercing station 212, one or more forming stations 204, one or more cooling stations 210, a measuring station 218, a tube length unloading station 220, and a tube loading station 214. Figure 2 The main loop 116 is depicted as having a circular arrangement of processing stations 106, as previously described, the main loop 116 may have processing stations 106 located in other non-circular arrangements, such as linear, curvilinear, irregularly shaped, or other arrangements. The heating station 202 may be positioned in front of each of the forming station 204 and the separation station 206 relative to the indexing direction 222 of the main turret 108 to preheat a target area of ​​the glass tube 102 to a viscosity that causes the glass to become deformable and can be effectively formed or stretched and separated. At the separation station 206, the formed glass article 103 ( Figure 1 ) can be used in conjunction with the glass tube 102 ( Figure 1 ) is separated and the bottom is formed at the same time. The separation station 206 can also be a processing station 106, where the partially formed glass products 103 are once separated and transferred to the secondary turret 114 ( Figure 1 ), in indexing through the secondary loop 118 of the secondary processing station 112. The piercing station 212 can be positioned on the primary loop 116 downstream of the separation station 206 in the indexing direction 222 of the main turret 108. At the piercing station 212, the meniscus 350 ( Figure 8 ) is pierced, thereby reopening the working end 150 of the glass tube 102.

[0079] Reference again Figure 2 , the forming station 204 of the main turret 108 can be positioned downstream of the piercing station 212 and the one or more heating stations 202 in the indexing direction 222. The one or more forming stations 204 can iteratively shape the glass tube 102 to form one or more features of the finished glass product. As described above, the one or more heating stations 202 can be positioned before each forming station 204 to preheat the target area of ​​the glass tube 102 to a temperature at which the glass tube 102 can be shaped and formed into the desired features. The forming station 204 of the main turret 108 can shape the working end 150 ( Figure 3A) to form a feature at one end of the glass article 103, and after the glass article 103 has been separated from the glass tube 102, the forming station 204 of the secondary turret 114 can shape the other end of the glass article 103. In an embodiment, the converter 100 can be used to produce vials from the glass tube 102, and the forming stations 204 of the converter 100 can include one or more shoulder forming stations, flange forming stations; flange finishing stations, or a combination of these, wherein one or more heating stations 202 are located before and between each of the forming stations 204.

[0080] The main loop 116 may further include a measuring station 218 at which at least one measuring device may be used to measure one or more attributes of the glass tube 102 (such as, for example, diameter and thickness), or one or more dimensions of features of the glass article 103 formed by the forming station 204. Feature dimensions may include, but are not limited to, flange thickness, flange length, neck length, neck thickness, overall article length, flange inner diameter, flange outer diameter, flange height, top height, bottom flange angle, top flange angle, eccentricity, article inner and outer diameters, shoulder thickness, shoulder angle, shoulder radius, other feature dimensions, or combinations thereof. One or more appearance attributes of the glass tube 102 or glass article 103 may also be evaluated in the measuring station 218. Appearance attributes may include, but are not limited to, defects in one or more features of the glass article 103 (e.g., defects in the flange, neck, etc.), overall desirability, or a combination thereof. Overall desirability may be a composite attribute based on a plurality of other dimensions or appearance attributes measured for the glass article 103. In an embodiment, the measuring station 218 can be positioned directly after the last forming station 204 so that the dimensions are measured while the glass tube 102 is still at an elevated temperature. Alternatively, the measuring station 218 can be positioned after one or more cooling stations 210 to measure the dimensions of the glass tube 102 and / or glass article 103 at a lower temperature. In an embodiment, the secondary loop 118 of the converter 100 can include the measuring station 218.

[0081] Still reference Figure 2 , one or more cooling stations 210 may be positioned after the forming station 204 in the indexing direction 222 of the main turret 108. A tube length unloading station 220 may be positioned after the forming station 204 and between the forming station 204 and the separation station 206 to drop the partially formed glass tube 102, thereby positioning the glass tube 102 for separation of the glass product 103 from the glass tube 102 at the separation station 206. The main loop 116 may also include a tube loading turret 110 for loading new lengths of glass tube 102 raw material into the main turret 108 ( Figure 1) of the tube loading station 214. In an embodiment, the tube loading station 214 can be incorporated into the cooling station 210. The tube loading station 214 can be positioned between the last forming station 204 and the separation station 206.

[0082] The forming station 204 of the main turret 108 can form features at the first end of the glass article 103. For example, the forming station 204 can form a shoulder 142 and a flange 144 at the top (first end) of the glass article 103, where the glass article 103 is a vial or a cartridge, such as Figure 4 As shown. Refer again Figure 2 Once the glass article 103 is separated from the glass tube 102 at the separation station 206, the glass article 103 can be transferred to the secondary processing station 112 of the secondary turret 114. The secondary processing station 112 can include one or more forming stations 204 for forming a second end of the glass article 103, the second end being opposite to the first end of the glass article 103. For example, the forming station 204 of the secondary processing station 112 can form one or more features at the bottom (second end) of the glass article 103. The secondary turret 114 can rotate about the axis B in a direction 224 opposite to the primary turret 108. In an embodiment, the secondary turret 114 can rotate in the same direction as the primary turret 108.

[0083] The secondary processing stations of the secondary loop may include one or more heating stations 202, forming stations 204, polishing stations 208, cooling stations 210, unloading stations 216, or other stations or combinations of secondary processing stations 112. Figure 2 The secondary loop is depicted as a circular arrangement with secondary processing stations 112, as previously described, the secondary loop can have secondary processing stations 112 located in other non-circular arrangements, such as linear, curved, irregular shapes, or other arrangements. In embodiments, the secondary processing stations 112 of the secondary loop 118 can be used to form one or more features of a glass article 103 (such as a vial, ampoule, cartridge, or syringe), for example, at an end of the glass article 103 opposite the end formed by the main turret 108. For example, in some embodiments, the glass article 103 is a vial, and the forming station 204 of the secondary loop 118 can form the bottom of the vial. Other features are also contemplated, such as features of an ampoule, cartridge, syringe, etc. The secondary loop 118 can include one or more polishing stations 208 to finish the surface of the glass article. The secondary loop 118 can further include a plurality of cooling stations 210 and a discharge station 216, where the finished glass article 103 can be discharged from the converter 100.

[0084] The previous description of the processing stations 106 of the primary loop 116 and the secondary processing stations 112 of the secondary loop 118 may represent a typical converter 100 for producing vials from the glass tube 102. However, it should be understood that more or fewer processing stations 106 and secondary processing stations 112 may be utilized to produce vials or other glass products having different shapes or features, such as cartridges, syringes, ampoules, or other pharmaceutical glass products. In addition, it should be understood that the processing stations 106 and secondary processing stations 112 may be arranged in any of a variety of different orders and / or configurations to produce glass products of different shapes.

[0085] Reference now Figure 3 , schematically depicts a heating station 202 of a converter 100. Each heating station 202 may include one or more heating elements 301. Figure 3 As shown, in an embodiment, the heating element 301 may include one or more burners 302, which are used to heat the forming station 204 ( Figure 2 ) or at the separation station 206 ( Figure 2 ) before the separation operation performed at ). Figure 3 A single burner 302 is depicted, it being understood that multiple burners 302 may be employed in a single heating station 202. Each burner 302 may be fluidly coupled to a fuel gas supply 304, an oxygen supply 306, and optionally, an air supply 308. Examples of fuel gases for the burners 302 may include, but are not limited to, hydrogen, hydrocarbon fuel gases (e.g., methane, propane, and butane), other fuel gases, or combinations of these.

[0086] Each burner 302 may include a fuel control valve 310 to control the flow rate of the fuel gas to the burner 302. Each burner 302 may also include an oxygen control valve 312 to control the mass flow rate of oxygen to the burner 302. Each burner 302 may further include an air control valve 314 for optionally controlling the air flow rate to the burner 302. The burners 302 combust the fuel gas in the presence of oxygen and / or air to produce a flame that heats at least a target area of ​​the glass tube 102. Although the heating station 202 of the converter 100 is described herein as using a burner to heat the glass tube 102, it should be understood that other heating elements or methods other than burners may be used to heat the glass tube 102. Other heating elements may include, but are not limited to, lasers, such as, for example, CO2 lasers, induction heaters, other heating devices, or combinations of these.

[0087] The heating station 202 can further include a burner positioner 318 coupled to the burner 302. The burner positioner 318 can be operated to vertically (e.g., at a position) the glass tube 102 in the heating station 202. Figure 3in the + / -Z direction of the coordinate axis in ), horizontally (for example, in the Figure 3 ) or a combination of these directions. In an embodiment, each burner positioner 318 may include one or more servo motors operable to automatically and / or incrementally adjust the position of the burner 302 in one or more directions. Any other type of positioner that is or will be commercially available may be used for the burner positioner 318. The burner positioner 318, the fuel control valve 310, the oxygen control valve 312, the air control valve 314, or a combination of these may be communicatively coupled to the control system 402 to enable the control system 402 to control the vertical position, horizontal position, heat output, or a combination thereof of the burner 302.

[0088] Reference now Figure 4 and Figure 5 , schematically depicts an example of a forming station 204 of a converter 100. Each forming station 204 may include one or more forming tools 324, which may be relative to the base 104 ( Figure 1 ) is rotated about the processing axis E. When entering the forming station 204, the glass tube 102 that has been heated in the previous heating station 202 is rotated by the holder 130. The forming tool 324 can engage with the glass tube 102 while the glass tube 102 is rotating. When engaged, the contact of the forming tool 324 with the heated glass tube 102 can form the glass tube 102 into a desired shape. The forming tool 324 can contact the glass tube 102 during the active time of the forming tool 324. When the active time expires, the forming tool actuator 326 can disengage the forming tool 324 from the engagement with the glass tube 102. Figure 4 An embodiment of a forming station 204 for forming a shoulder 142 of a glass bottle is schematically shown. Figure 5 An exemplary embodiment of a forming station 204' for forming a flange 144 of a glass bottle is schematically depicted. The forming station 204' for forming the flange 144 includes three forming tools 324a, 324b, and 324c. Other types of forming tools 324 may be employed in the forming station 204 depending on the desired characteristics of the glass article 103.

[0089] Reference again Figure 4, the forming tool actuator 326 is operable to move the forming tool 324 into or out of engagement with the glass tube 102. Moving the forming tool 324 into and out of engagement with the glass tube 102 can control the contact timing of the forming tool 324 with the glass tube 102. The contact timing of the forming tool 324 with the glass tube 102 refers to the time when each forming tool 324 in the forming station 204 engages and disengages with the glass tube 102. Adjusting the contact timing of the forming tool 324 can adjust the overall contact timing of each of the forming tools 324 in contact with the glass tube 102. The contact time refers to the duration of time that the forming tool 324 is engaged or in contact with the glass tube 102.

[0090] The burner positioner 326 can further be operable to vertically (e.g., at Figure 3 in the + / -Z direction of the coordinate axis in ), horizontally (for example, in the Figure 4 The forming tool 324 is changed in the XY plane (in the XY plane indicated by the coordinate axes in the figure) or in a combination of these directions. The forming position of the forming tool 324 refers to the forming tool position when the forming tool 324 is engaged with the glass tube 102. In an embodiment, each forming tool actuator 326 may include one or more servo motors that are operable to automatically and / or incrementally adjust the position of the forming tool 324 in one or more directions. Figure 4 . Any other type of positioner that is or will be commercially available may be used as at least a portion of the forming tool actuator 326. The forming tool actuator 326 may be communicatively coupled to the control system 402 to enable the control system 402 to change the vertical position, horizontal position, or both of the forming tool 324 when in the forming position. The vertical and / or horizontal position of the forming tool 324 refers to the position of the forming tool 324 when the forming tool 324 is engaged with the glass tube 102.

[0091] Reference now Figure 6, schematically depicting a cooling station 210. The cooling station 210 may include one or more cooling nozzles 340 configured to direct a cooling fluid 342 (such as, for example, cold air or an inert gas) to the glass tube 102. One or more of the cooling nozzles 340 may be positioned to direct the cooling fluid 342 to a specific area of ​​the glass tube 102. One or more cooling fluid control valves 344 may be fluidly coupled to the cooling nozzles 340 to control a mass flow rate of the cooling fluid 342 to the cooling nozzles 340, such that a cooling rate of the glass tube 102 as well as a temperature of the glass tube 102 and a temperature gradient in the glass tube 102 can be controlled. The cooling station 210 may further include a cooling nozzle positioner (not shown) coupled to the cooling nozzle 340 and operable to position the cooling nozzle 340 relative to the glass tube 102. The cooling nozzle positioner, the cooling fluid control valve 344, or both may be communicatively coupled to the control system 402 ( Figure 1 ) so that the control system 402 can control the vertical and / or horizontal position of the cooling nozzle 340, the flow rate of the cooling fluid 342, or a combination of these.

[0092] Reference now Figure 7 , a separation station 206 of the converter 100 is schematically depicted. Figure 7 The separation station 206 depicted in FIG. 1 is a hot separation station and can be positioned after one or more heating stations 202 in the indexing direction 222 of the main turret 108. The heating station 202 located before the separation station 206 can heat the glass tube 102 to make the glass viscous. The separation station 206 can include a separation burner 348. The separation burner 348 can have any of the features previously described for the burner 302, including but not limited to the fuel gas control valve 310, the oxygen control valve 312 and / or the air control valve 314. When the deformable glass tube 102 made by the previous heating station 202 is rotated about the central axis D of the glass tube 102 by the holder 130, the separation burner 348 can engage with the outer surface 140 of the glass tube 102 to heat the glass tube 102 to a temperature at which the viscosity of the glass causes the partially formed glass product to separate from the glass tube 102. Once separated from the glass tube 102, the partially formed product can be transferred to the secondary turret 114 ( Figure 1 ) or unloaded from the converter 100. Figure 7 2. Although shown as a thermal separation station, the separation station 206 may also be a non-thermal separation station, such as a separation station using a scratch and break technique, which may be used, for example, for syringes and cartridges.

[0093] Similar to the heating station 202, the separation station 206 may also include a burner positioner 318 coupled to the separation burner 348. The burner positioner 318 may be operable to vertically (e.g., at a position between 102 and 206) the glass tube 102 in the heating station 206. Figure 3 in the + / -Z direction of the coordinate axis in ), horizontally (for example, in the Figure 7 The burner positioner 318, the fuel control valve 310, the oxygen control valve 312, the air control valve 314, or a combination of these can be communicatively coupled to the control system 402 ( Figure 3 ), so that the control system 402 can control the vertical position, horizontal position, heat output, or a combination of these of the separation burner 348. When the separation station 206 is a scoring and fracturing separation station, the separation station 206 may include one or more scoring tools and / or fracturing tools, and may further include a tool actuator operable to change the positioning of the scoring tool and / or fracturing tool.

[0094] Reference now Figure 8 , schematically depicts one embodiment of a piercing station 212 of the converter 100. The piercing station 212 may be positioned after the separation station 206 in the indexing direction 222 of the main turret 108. As previously described, the thermal separation of the article 103 from the glass tube 102 in the separation station 206 may cause a meniscus 350 of the glass to be formed across the working end 150 of the glass tube 102. In the piercing station, the meniscus 350 is pierced in preparation for forming the next article at the working end 150 of the glass tube 102.

[0095] In an embodiment, the piercing station 212 may include a piercing burner 352. The piercing burner 352 may be positioned below the working end 150 of the glass tube 102 and may be oriented toward the working end 150 of the glass tube 102. The piercing burner 352 may be fluidly coupled to one or more of the fuel gas supply 304, the oxygen supply 306, the air supply 308, or a combination thereof. Figure 3The piercing station 212 may further include a fuel gas control valve 310, an oxygen control valve 312, and / or an air control valve 314 for controlling the heat output from the piercing burner 352. When the main turret 108 indexes the glass tube 102 into the piercing station 212, the flame from the piercing burner 352 heats the meniscus 350 of the glass and melts the meniscus 350 to pierce the meniscus 350 and reopen the working end 150 of the glass tube 102. In an embodiment, the meniscus 350 may be pierced by directing a gas flow (such as compressed air, nitrogen, argon, or other gas) at or through the meniscus 350. In an embodiment, mechanical means or other methods may be used to pierce the meniscus 350 instead of using a piercing burner 352.In U.S. Patent No. 10,968,133 (issued on April 6, 2021, entitled “METHODS FOR MINIMIZING SHR IN GLASS ARTICLES BY PRODUCING A GAS FLOW DURING PHARMACEUTICAL PART CONVERTING”), co-pending U.S. Application No. 16 / 197,187 (filed on November 20, 2018, entitled “SYSTEMS AND METHODS FOR MINIMIZING SHR FROM PIERCING DURING PHARMACEUTICAL PART CONVERTING USING AGAS FLOW”), FLOW), co-pending U.S. Application No. 16 / 197,971, filed on November 21, 2018, entitled “SYSTEMS AND METHODS FOR MINIMIZING SHR FROM PIERCING DURING PHARMACEUTICAL PART CONVERTING USING NEGATIVE PRESSURE EVACUATION”, and co-pending U.S. Application No. 16 / 198,041, filed on November 21, 2018, entitled “SYSTEMS AND METHODS FOR MINIMIZING SHR FROM PIERCING FROM PHARMACEUTICAL PART CONVERTING USING A variety of methods for piercing the meniscus 350 are disclosed in the piercing station 212, all of which are incorporated herein by reference in their entirety. Positioners, control valves, and other control devices may be incorporated into the piercing station 212 and communicatively coupled to the control system (). Figure 1 ) to control various operating parameters of the puncture station 212.

[0096] Reference now Fig. 9, schematically depicting a measuring station 218. The measuring station 218 may include one or more measuring devices 360 configured to measure one or more properties of the glass tube 102 and the glass article 103, or both. The properties may include one or more physical dimensions, one or more appearance characteristics, or both of the glass tube 102, the glass article 103, or both. The measuring device 360 ​​in the measuring station 218 may be any measuring device described herein. The measuring device 360 ​​may be communicatively coupled to the control system 402 to transmit information related to one or more properties of the glass tube 102, the glass article 103, or both to the control system 402. In an embodiment, the measuring device 360 ​​may be a thermal imaging device. An example of a thermal imaging device for measuring properties and characteristics of a feature formed at the working end 150 of the glass tube 102 or the glass tube 102 may be found in U.S. Patent No. 10,773,989, issued on September 15, 2020, the entire contents of which are incorporated herein by reference.

[0097] Figure 3-Figure 9 Schematic diagrams of several different examples of processing stations 106 that may be utilized in converter 100. However, it should be understood that other processing stations 106 having different structures, combinations of structures, or functions may be utilized to achieve the desired conversion of glass tube 102 into one or more glass articles.

[0098] Reference now Fig.10 , the glass tube 102 may be an elongated hollow cylindrical tube made of glass. The glass tube 102 may have a circular cross-sectional shape and may have an outer surface 140, an inner surface 146, and a thickness t. The thickness t of the glass tube 102 may be the radial distance between the inner surface 146 and the outer surface 140 of the glass tube 102. The glass tube 102 can be Fig.10 The glass tube 102 may have a length L in the + / -Z direction of the coordinate axis. Fig.10 As previously mentioned, during the entire conversion process, the glass tube 102 can rotate about the central axis D of the glass tube 102. The working end 150 of the glass tube 102 is when the glass tube 102 is fixed in the holder 130 of the converter 100. Fig.10 The non-working end of the glass tube 102 is the end opposite to the working end 150 (i.e., the glass tube 102 is oriented in the -Z direction of the coordinate axis in FIG. Fig.10 The end in the +Z direction of the coordinate axis).

[0099] Reference again Figure 1 and Figure 2In operation, the main turret 108 can index or move the glass tube 102 fixed in the holder 130 into the processing station 106. Specific operations such as heating, forming, piercing, separating, cooling, dripping, feeding, measuring, etc. can be performed on the glass tube 102 at each processing station 106. The converter 100 can be adjusted so that all processing stations 106 complete their operations within the dwell time. At the end of the dwell time, the main turret 108 can index the glass tube 102 to the next processing station 106 during the indexing time. For the indexing converter, as used in this disclosure, the total time per part per station is the sum of the dwell time and the indexing time.

[0100] In an embodiment, the converter 100 may be a continuous converter operable to continuously move the glass tube 102 and the holder 130 through a plurality of processing stations 106. In an embodiment, heating elements, burners, forming tools, measurement equipment, and other elements of the conversion process may move with the glass tube 102 as the glass tube 102 passes through the processing stations 106. For both indexed converters and continuous converters, the "active time" of a processing station is the duration that the glass tube 102 remains engaged with at least one heating element, at least one forming tool, at least one cooling nozzle, or other equipment while in the processing station 106.

[0101] Examples of converters 100 for converting glass tubes 102 into glass vials include the "RP16 Bottle Forming Machine" or "RP18 Bottle Forming Machine" with "Automatic Tube Feeder" manufactured by Ambeg Dr. J. Dichter GmbH, which include 16 processing stations 106 and 8 secondary processing stations 112 in the main loop 116. Other examples include the "RP32 Vial Forming Machine" manufactured by Ambeg Dr. J. Dichter GmbH, which has 32 processing stations 106 in the main loop 116 and two secondary loops 118, wherein there are 8 secondary processing stations 112 in each secondary loop 118, and the "Zeta 098 Vial Forming Machine" manufactured by Euromatic SRL, which has 36 processing stations. Another example may include the "Zeta 103 Cartridge Forming Machine" manufactured by Euromatic SRL, which is a converter for converting glass tubes into glass cartridges. The cartridge converter has similar features to the previously described vial converter 100, but is utilized to produce glass articles having a cartridge form factor rather than a vial.

[0102] Although described in the context of a converter for producing glass vials from glass tubes 102, it should be understood that the converter 100 can be configured to produce one or more other articles, such as other types of pharmaceutical containers or articles, by changing the order or configuration of the forming tools 324 and / or the processing stations 106 in the primary loop 116 or the secondary processing stations 112 in one or more secondary loops 118. Pharmaceutical articles can include, but are not limited to, vials, cartridges, syringes, ampoules, jars, or other glass pharmaceutical articles.

[0103] During operation of the converter 100, the burner output of the burner 302 and the positioning of the burner 302 can have a significant impact on the dimensional yield and defect rate of the converter 100. The position of the forming tool 324 relative to the glass tube 102 can also have a significant impact on the dimensional yield and defect rate of the converter 100. In addition, the contact timing of the forming tool 324 in contact with the glass tube 102 can greatly affect the dimensional tolerances and defects in the glass product 103 made from the glass tube 102. The overall contact timing in conventional converters is already inherently linked to the machine indexing rate, which further complicates and limits the process window of conventional converters for producing high yield and high quality products. In addition, the converter 100 can have hundreds of other inputs and processing settings across all processing stations 106 that need to be properly and continuously managed to produce high manufacturing yields and high quality products.

[0104] Historically, on conventional conversion machines, the burner output required to heat the glass tube 102 to sufficient viscosity for forming has been controlled by simple needle valves fluidly coupled to manifolds for fuel gas, oxygen, and air. In the forming station of a conventional conversion machine, the position of the forming tool (usually including a forming pin and a forming wheel) has been set by a simple mechanical linkage connected to a cam drive shaft. In recent years, some modern automation technologies have been developed and have become an "add-on" feature for some glass tube converters. In particular, mass flow control valves have been incorporated to replace manual needle valves to set the gas and oxygen flows to the various burners. Servomotors have replaced the adjustable linkages used to position the forming tools in the forming station. More advanced PLCs allow timing and speed profiles to be applied to each servo-driven device, significantly improving the control of the forming station compared to previous cam drive shaft machines. However, even with the current state of the art, decisions about the selection and adjustment of process parameters are made through interaction with more complex software and technology, but these decisions are still made by human operators.

[0105] The efficiency of operation of the converter 100 for producing the glass product 103 from the glass tube 102 depends heavily on timely compensation for disturbances in the process that may cause one or more properties of the glass product 103 to deviate from target values ​​and / or increase the variance of these properties. Continuously adjusting the numerous properties of the glass product or glass tube by managing and adjusting the hundreds of inputs and process parameter settings of the glass tube converter 100 is difficult.

[0106] In addition, normal changes in the conversion process or changes in external inputs to the conversion process may also require adjustment of the converter. Variability may occur with input materials or fuel gases, thermal growth of the turret over time, tool wear that gradually changes tool size, burner degradation over time, or other factors. This variability manifests itself as changes or trends in measured glass properties over time. Even after the nominal set point is determined, changes in input materials or input fuel gases, equipment wear, changes in the environment surrounding the converter, and many other disturbances require real-time adjustment of the actuator set point itself to compensate for the process. The source of the disturbance is usually unknown, and even if known, it is economically unfeasible to remove some disturbances compared to the construction and application of feedback control. Among the many possible actuator set point values, most can be fixed, of which 10 to 20 may be considered for adjustment, of which 10 to about 30 properties of the glass product or glass tube are mainly considered. Since the actuator setting is usually less than the property to be controlled, and has the maximum and minimum limits of the actuator, some form of optimization or compromise may be required. Furthermore, the actuators controlling the various burners and forming tools can have complex interactions and due to the actuator variations the sensitivity is often variable and poorly understood.

[0107] For conventional glass tube conversion machines, the control strategy for managing all process inputs and process settings has historically used human operators to make changes to the process parameters of the converter 100 based on human intuition and experience. These human operators with various experience levels have been relied upon to change burner parameters, forming unit parameters, and overall machine timing for glass products of different geometries (e.g., vials, syringes, ampoules, cartridges, etc.). Human operators are also relied upon to manage and account for the normal day-to-day variations that occur in the conversion process by adjusting these same parameters. Through experience and understanding of basic first principles, some experienced operators have learned to adjust many actuator set points in an attempt to maintain the property values ​​of the glass products within specification targets. However, the way the operator reacts to these changing properties can significantly affect the yield and quality of the glass products in the steady state. Therefore, the extent to which a producer can consistently produce high-yield, high-quality glass products from a conversion machine is highly dependent on the skill level and experience of the human operators who use the conversion machine. Variations in experience levels between operators, machines, production lines, and shifts can result in significant variability in the yield and quality of glass products produced by the conversion process.

[0108] The task of controlling the glass tube converter 100 is multidimensional. The human ability to consider more than about 3 actuators and 3 attributes simultaneously is difficult and often impossible. In addition, some flange dimensions have been shown to have some degree of heteroscedasticity. Therefore, it is important to consider not only attributes that are meant to be at or near target, but also to balance attribute variances, since it is ultimately desirable to maximize process capability C pk Finally, the in-loop approach is fairly manual and requires frequent operator attention if and when process drift becomes excessive or a step change in converter 100 performance has occurred.

[0109] Therefore, there is a continuing need for systems and methods for controlling operation of a converter 100 and a conversion process for producing a glass product 103 from a glass tube 102. The systems and methods disclosed herein address the problems in the prior art by providing automatic or semi-automatic feedback control based on a model predictive control framework to effectively control a converter 100 for producing a glass product 103 from a glass tube 102. The feedback control methods disclosed herein can effectively control multiple process parameters of the converter 100 to produce a glass product having properties within specification during steady-state operation of the converter 100.

[0110] The model predictive control framework includes constructing one or more operating models for the converter 100, each operating model relating at least one process parameter of the converter 100 to at least one property of the glass product 103, the glass tube 102, or both. The operating model included in the controller can be determined by a "design of experiments" technique, by first principles construction, or a combination of both methods. The operating model for the converter 100 can be substituted into a target control function. In an embodiment, the target control function can be a mean square error cost function of the converter 100. Although described herein in the context of a mean square error cost function, it should be understood that the target control function can be based on other types of cost functions or any other suitable control function. The target control function can further include attribute weighting factors and penalty factors for adjusting process parameters. Updated settings for multiple process parameters for the converter can be determined by solving the target control function for minimizing the process parameter values ​​of the target control function. The solution to minimize the target control function can further consider the maximum and minimum values ​​of each process parameter.

[0111] The model predictive control framework can be used to provide feedback control of the converter 100. The feedback control method disclosed herein for controlling the operation of the converter 100 can include executing one or several iterations of a control sequence. The control sequence can include providing a target value for a property of the glass product 103 or glass tube 102 during or after the conversion. The feedback control method can further include operating the converter 100 to produce the glass product 103 from the glass tube 102 by translating the glass tube 102 through a plurality of processing stations 106 in sequence, measuring the property of the glass product or glass tube for a statistically relevant number of glass tubes, and recording the settings of the process parameters of the converter related to the property to attribute to the production of one or more data sets including the measured values ​​of the property and the settings of the process parameters. The data sets can be processed to remove abnormal data points and generate statistical characteristics of the distribution of the measured values ​​of the property (e.g., mean, median, range, standard deviation, variance, etc.). The method further includes determining an update setting from the objective control function by substituting the statistical characteristics of the distribution of each measured property, the target value of the property, and the setting of the process parameter into the objective control function, and then finding the update setting that minimizes the value of the objective control function. The method can further adjust the process settings to determine updated settings from the minimization of the objective control function. The control sequence can be repeated until the updated settings of the process parameters converge.

[0112] Over time, the operating conditions of the converter 100 may change, and the difference between the operating model and the actual performance of the converter 100 may become significant. The model predictive control framework disclosed herein uses feedback control to compensate for such mismatches between the operating model and the actual converter performance, so that the operation of the converter produces glass products that remain within acceptable specifications, despite the potential significant inaccuracies in the initial operating model. Therefore, the initial operating model may generally have errors with respect to nonlinearity, offset, and sensitivity errors. The model predictive control framework disclosed herein compensates for process changes over time, such as changes in glass composition, wear of forming tools and burners, changes in the environment surrounding the converter (e.g., temperature, humidity, atmospheric pressure, etc.), or other process changes. The feedback control process disclosed herein can also be more continuous and reliable performance, reducing reliance on human operators controlling the converter 100. The feedback control method can also be able to adjust the operation of the converter 100 so as to explain normal process variability in a continuous and data-driven manner rather than through guesses and models based on human intuition and experience.

[0113] It should also be noted that some abnormal behaviors of the converter 100 may be difficult to capture by the algorithm, but may be observed and noticed by a human operator. The feedback control methods disclosed herein may be adapted to allow varying degrees of human interaction, which may provide an opportunity to observe these abnormal behaviors and account for them in controlling the conversion process.

[0114] The feedback control method disclosed herein may be at least partially or completely executed by a control system communicatively coupled to the converter. Figure 1 , a system 400 for producing a plurality of glass products from a glass tube 102 may include a converter 100 having a plurality of processing stations 106, such as but not limited to at least one heating station 202, at least one forming station 204, and a separation station 206. As previously described, the converter 100 is operable to move or pass the glass tube 102 through each of the plurality of processing stations 106. The converter 100 may include a plurality of holders 130. Each of the plurality of holders 130 is operable to hold the glass tube 102 and rotate the glass tube 102 about a central axis D of the glass tube 102. The converter 100 may further include at least one measuring device 360, which is operable to measure one or more properties of each of the glass products 103 produced from the glass tube 102. The converter 100 may further include a control system 402 communicatively coupled to the converter 100 and the at least one measuring device 360. It should be understood and appreciated that the converter 100 may include any of the features, processing stations, or operating parameters previously described herein for the converter 100.

[0115] Reference again Fig. 9As previously described, the system 400 may include one or more measuring devices 360. The measuring devices 360 may be capable of 100% online inspection of various dimensional and appearance attributes of the glass tube 102, the glass article 103, or both to provide real-time feedback to the system 400. The measuring devices 360 may be disposed in one or more measuring stations 218, which may be in the primary loop, the secondary loop, or both. Additionally or alternatively, in an embodiment, the converter 100 may include one or more measuring devices 360 located at one or more processing stations 106 that are not measuring stations 218, such as, but not limited to, a heating station 202, a forming station 204, a separation station 206, a cooling station, a piercing station, or other types of processing stations. Additionally or alternatively, one or more of the measuring devices 360 may be coupled to one of the plurality of holders 130 and may be translated with the holder 130 through the plurality of processing stations 106. In an embodiment, the converter 100 may include a plurality of measurement devices 360, each of which may be coupled to a processing station 106 and / or to one of the plurality of holders 130 for translation with the holder 130 and the glass tube 102 through the plurality of processing stations 106. Additionally or alternatively, the measurement devices 360 may be configured downstream of the converter 100, such as at a quality control station downstream of the converter 100.

[0116] The measurement device 360 ​​is operable to measure one or more properties of the glass tube 102, one or more properties of the characteristics of the partially formed glass article at the working end 150 of the glass tube 102, one or more properties of each glass article 103 produced by the glass tube 102, or a combination thereof. The properties of the plurality of glass tubes 102, glass articles 103, partially formed glass articles 103, or a combination thereof may include one or more temperatures of the glass tube 102, one or more dimensions of the glass tube 102, one or more dimensions of the plurality of glass articles 103 or characteristics of the partially formed glass articles 103 formed at the working end 150 of the glass tube 102, one or more appearance properties of the plurality of glass articles 103, or a combination thereof. In an embodiment, the measurement device 360 ​​may be positioned and operable to measure one or more properties of a glass preform at the working end 150 of the glass tube 102. The glass preform refers to the heated portion of the glass tube 102 at the working end 150 of the glass tube 102 after the heating station 202 and before the forming station 204. In other words, a glass preform refers to the working end 150 of the glass tube 102 being in suitable conditions for forming (e.g., glass viscosity). Because the glass preform is part of the glass tube 102 during conversion, references herein to properties of the glass tube 102 are also intended to include properties of the glass preform. Properties of the glass preform may include glass temperature, dimensions of the preform, other properties of the preform, or combinations of these. Other properties of the glass tube 102, the glass article 103, or both may be measured and are contemplated by the present disclosure.

[0117] The one or more measuring devices 360 may include any measuring device capable of measuring one or more dimensions, temperatures, or appearance attributes of the glass tube 102 and / or the glass product 103 made therefrom. The measuring device 360 ​​may include, but is not limited to, an optical measuring system, a laser measuring device, a measuring device using sound waves or other electromagnetic waves, or other measuring techniques. In an embodiment, the measuring device 360 ​​may include a thermal imaging system, such as the thermal imaging system disclosed in U.S. Patent No. 10,773,989, entitled “SYSTEMS AND METHODS FOR MEASURING THETEMPERATURE OF GLASSDURING TUBE CONVERSION” filed on March 22, 2018, the entire contents of which are incorporated herein by reference in their entirety. The thermal imaging system is operable to measure one or more temperatures or dimensions of the glass tube 102, the glass product 103, or both during or after heating the glass tube 102 and forming the glass tube 102 into the glass product 103. Additionally or alternatively, the measurement device 360 ​​can include one or more dimensional measurement systems, such as one or more of a visual imaging system, a laser reflectometer, a laser micrometer, an optical micrometer, or other measurement devices operable to measure one or more dimensions of the glass tube 102, a feature of the partially formed glass article, the finished glass article 103, or a combination of these. Other useful measurement devices 360 for determining one or more temperatures, dimensions, appearance attributes, or combinations of these of the glass tube 102, the glass article 103, or both are contemplated.

[0118] Reference again Figure 1 , the system 400 for producing a plurality of glass articles from a glass tube 102 may further include a control system 402 communicatively coupled to the converter 100. In particular, the control system 402 may be communicatively coupled to the measurement device 360 ​​and various control devices in the processing stations 106 of the converter 100. The control devices of the converter 100 that may be communicatively coupled to the control system 402 may include, but are not limited to, a burner positioner 318, a fuel gas control valve 310, an oxygen control valve 312, an air control valve 314, a forming tool actuator 326, a cooling fluid control valve 344, a main turret drive motor, a drive motor(s) operably coupled to the holder 130 for rotation of the glass tube 102, a timer, a ventilation system, other control devices, or a combination of these. The number and type of control devices may depend on the particular converter 100 used and the number and type of processing stations 106 employed by the converter 100.

[0119] The control system 402 may include one or more processors 404, one or more memory modules 406 communicatively coupled to the processors 404, and machine-readable and executable instructions 408 stored on the one or more memory modules 406. When executed by the processor(s) 404, the machine-readable and executable instructions 408 may cause the system to automatically perform any actions and / or method steps further described in greater detail herein, even if not explicitly described in the context of the machine-readable and executable instructions 408.

[0120] Reference now Fig.11 In an embodiment, the system 400 may further include a display 430 operable to display a graphical user interface 432. The display 430 may be directly communicatively coupled to the control system 402, or may be in electronic communication with the control system 402 via the network 410. The display 430 may be a touch screen or may include one or more input devices (not shown) that enable a user to input information into the graphical user interface 432. The graphical user interface 432 may be operable to display information about the control system 402 and the control sequence. The graphical user interface 432 may also be operable to receive input from a user and transmit the user input to the control system 402.

[0121] The control system 402 may include machine-readable and executable instructions 408 that, when executed by the processor(s) 404, may cause the system 400 to automatically perform one or more steps in a control sequence for controlling the converter 100 according to the model predictive control framework described herein. The control system 402 may provide feedback control of the converter 100.

[0122] As previously discussed, the model predictive control framework disclosed herein includes one or more models that relate process parameters of the converter 100 to properties of the glass product 103, the glass tube 102, or both to predict the value of the property from the settings of various process parameters. A model for the converter 100 is constructed and then incorporated into a target control function for providing feedback control of the converter. During operation of the converter 100, the control system 402, by executing one or more computer-readable and executable instructions, can measure properties of the glass product 103, the glass tube 102, or both, adjust the measured data, and then use the target control function to adjust the process parameters of the converter 100 to maintain the properties of the glass product 103 within an acceptable target. In particular, the control system 402 can minimize the target control function, which takes into account the target value of the property and the difference between the measured value of the property and the predicted value of the property obtained from the model.

[0123] As previously described, the first action in providing feedback control of the converter 100 through a model predictive control framework is to construct one or more models that relate the values ​​of one or more process parameters of the converter 100 to one or more properties of the glass article 103, the glass tube 102, or both. The model of the converter can be constructed by considering first principles, by conducting a "design of experiments" process, a combination of these two methods, or by other methods. Typically, first principles can suggest a model structure, and "design or experiment" can be used to determine model coefficients and confirm the model structure or suggest modifications to the model structure. In an embodiment, the model structure of the operating model can be linear, which can result in better computational efficiency of the model predictive control framework. However, it should be understood that the model structure of the operating model can be nonlinear.

[0124] In an embodiment, the model of the converter 100 can be constructed entirely or at least partially through a "design of experiments" process. The "design of experiments" process can automatically construct an operational model of the converter 100 using 100% real-time online measurements of various properties of the glass tube 102 and / or glass product 103 and statistical data analysis tools. In particular, the "design of experiments" process for determining the operational model of the present disclosure can include constructing multiple condition sets for the converter 100, each of which includes settings for multiple process parameters. The converter 100 can then be operated under each of the set conditions to produce the glass product 103. When the glass product 103 is produced, various properties of the glass product 103, the glass tube 102, or both can be measured in real time by the measurement device 360 ​​of the converter 100. Each glass product 103 can be assigned a unique identifier, which can be associated with the condition set used to make the glass product 103 and the properties measured for the glass product. Once all condition sets are run, one or more operational models can be constructed using data about the condition sets and the measured properties, and the operational model associates one or more process settings on the converter 100 with the measured properties. The operating model may be used to automatically determine initial operating settings for each of a plurality of process parameters of the converter 100. Additionally or alternatively, the operating model may be incorporated into a target control function for providing feedback control of the converter 100.

[0125] The plurality of condition sets of the converter 100 may each include a plurality of settings for a plurality of process parameters of the converter 100. Each of the plurality of condition sets of the converter 100 may be different from the other condition sets. Thus, each condition set may represent a unique group of settings for process parameters of the converter 100. In some instances, such as after a forming tool change, many of the process parameters may remain the same, and only a subset of the condition sets may be needed to reconstruct an operational model for the forming station 204 of the converter 100, wherein the subset of condition sets includes a number of condition sets that is less than the total number of possible condition sets for the converter 100.

[0126] The plurality of process parameters for each condition set may include, but are not limited to, total part rate, holder 130 rotation rate, burner position in one or more heating stations 202, burner heat output in one or more heating stations 202, position of forming tools 324 in one or more forming stations 204, contact timing between forming tools 324 in one or more forming stations 204 and glass tube 102, other process parameters, or combinations thereof. Figure 3 The burner position of the burner 302 in the heating station 202 may include the vertical position of the burner 302 relative to the glass tube 102 (e.g., Figure 3 + / -Z direction of the coordinate axis in ), horizontal position (for example, in Figure 3 The burner heat output of the burner 302 in the heating station 202 may include the position of one or more of the fuel gas control valve 310, the oxygen control valve 312, the air control valve 314, or a combination thereof that can control the burner heat output of the burner 302.

[0127] Reference Figure 4 The forming tool position of the forming tool 324 in the forming station 204 may include the vertical position of the burner 302 relative to the glass tube 102 (e.g., Figure 3 + / -Z direction of the coordinate axis in ), horizontal position (for example, in Figure 3 The horizontal position of the forming tool 324 may refer to the horizontal position of the forming tool 324 relative to the glass tube 102 when the forming tool 324 is in the engaged position. The horizontal position of the forming tool 324 may determine the pressure of the forming tool 324 on the glass tube 102 when in the engaged position. The contact timing between the forming tool 324 and the glass tube 102 may be controlled by controlling the operation of the forming tool actuator 326 to adjust the time when the forming tool 324 is moved into and out of engagement with the glass tube 102 in the forming station 204. As previously described, the contact timing may be adjusted to control the overall contact timing in the forming station 204.

[0128] The discussion herein of certain process parameters associated with the heating station 202 and the forming station 204 is provided for the purpose of illustrating the subject matter of the present disclosure and is not intended to limit the process parameters that may be used. It should be understood that other process parameters associated with the separation station 206, piercing station, cooling station, or other processing stations 106 of the converter 100 may also be included in the condition set. The number and type of process parameters for each condition set of the converter 100 may depend on the type of converter 100, such as the number and type of processing stations 106 on the converter 100, the configuration of each processing station 106, the process control equipment (e.g., control valves, trim regulators, speed regulators, etc.) present on each processing station 106, or other factors.

[0129] Each process parameter of the converter 100 may have a setting range. The setting range for each of the process parameters may represent the full range of control of the process parameter, or may be a narrower setting range within which the converter 100 may be expected to produce glass products with acceptable quality and yield. Each of the process parameters may have a maximum value and a minimum value. The maximum and minimum values ​​for each of the process parameters may be based on the total capability or range of motion of an actuator or control device that includes the process parameter, or may be based on values ​​of the process parameter that are known to produce off-specification glass products or other problem conditions on the converter 100.

[0130] The setting range of each process parameter can be used to construct multiple condition sets for the converter 100. In an embodiment, the setting range of each process parameter of the converter 100 can be input into a "design of experiments" statistical software program, which can be operable to process the setting range of each process parameter of the converter 100 to construct multiple condition sets. An example of a "design of experiments" statistical software program can be the SAS developed Other commercially available statistical software packages or custom software and / or algorithms may also be used to construct the plurality of condition sets. The plurality of condition sets provide a set of "recipes" for the operation of the converter 100. Illustrative examples of subsets of condition sets are provided in Tables 2 and 3 of the examples.

[0131] In an embodiment, a starting recipe may be provided or stored in one or more memory modules of the control system 402 of the converter 100. The starting recipe may be associated with a particular type or size of the glass article 103 and may include preset values ​​for each process parameter of the converter 100. A condition set may be constructed from the starting recipe by selecting settings for each process parameter, each process parameter centered around the preset value of the starting recipe, or distributed within a range that includes the preset value of the starting recipe. In other words, a condition set may include preset values ​​from the starting recipe for a particular process parameter and values ​​of the process parameter on either side of the preset value.

[0132] Once a set of conditions is constructed for the converter 100, the converter 100 can be operated under each of the plurality of condition sets. A fixed number of glass products 103 can be produced under the process parameters of each condition set. As few as 60 glass products, or even 50 glass products, can show statistical significance between the condition sets. The control system 402 can be operated to produce greater than or equal to 50 or greater than or equal to 60 glass products 103 under the process parameters of each condition set of the converter 100. In embodiments, the converter 100 can be operated to produce 50 to 200, 50 to 100, 60 to 200, or 60 to 100 glass products 103 for each condition set.

[0133] When operating the converter 100 to produce the glass product 103 under the process parameters in each condition set, the measurement device 360 ​​can be used to measure one or more properties of the plurality of glass tubes 102, the glass product 103, or both. As previously described, the measurement device 360 ​​is operable to measure one or more properties of the plurality of glass tubes 102, the glass product 103, or both. The properties may include, but are not limited to, one or more temperatures or dimensions of the glass tube 102 or the glass preform, one or more dimensions of the glass product 103, one or more appearance features of the glass product 103, or a combination of these. The properties may also include intermediate dimensions of the partially formed glass product during or after one or more forming stations. The measurement device 360 ​​may be communicatively coupled to the control system 402. The measurement device 360 ​​may be operable to transmit one or more signals to the control system 402, the signals indicating the properties of the glass tube 102, the glass product 103, or both measured by the measurement device 360.

[0134] Once all condition sets have been run on the converter 100, one or more operating models can be built for the converter 100 based on the measured one or more properties and the multiple condition sets. The operating models can relate various process settings to one or more properties of the glass article 103.

[0135] The operating model may be generated from statistical analysis of data collected on measured properties of the glass article 103 and process parameters used to produce the glass article 103. In an embodiment, the operating model may be constructed externally from the converter 100 or the control system 402. Referring again to Fig.11, the data collected about the measured properties of the glass product 103 and the process parameters used to produce the glass product 103 can be exported from the control system 402 to the external computing device 420. The data can be exported from the control system 402 to the external computing device 420 via the network 410, which can be a wired or wireless network. The external computing device 420 can include statistical analysis software capable of processing the data received from the control system 402 and building an operational model therefrom. Examples of statistical analysis software can include the SAS developed However, other statistical analysis software packages may be used.Once constructed, the operational model may be transferred from the external computing device 420 to the control system 402 for use in the operation of the converter 100 and / or construction of a target control function.

[0136] After constructing the operating model, the operating model can be used to determine the initial operating settings for each process parameter, and then the converter 100 is operated with the initial operating settings. In an embodiment, the operating model can be input into the control system 402, and the control system 402 can be operable to determine the initial operating settings for each process parameter from the operating model. The term "initial operating settings" refers to the values ​​of the process parameters initially set by the converter 100 before feedback control using the model predictive control framework disclosed herein. In the model below, the initial operating settings can correspond to the settings of the process parameters at k=0, where k is an integer indicating an iteration of the control sequence, as described below. Therefore, for the first iteration of the control sequence (k=1), the vector value at iteration k-1 indicated by the term Act(k-1) will be equal to the initial operating settings of the converter.

[0137] The control system 402 may be operable to receive specifications for the glass product 103 to be produced, wherein the specifications may include target values ​​for one or more properties of the glass product 103, the glass tube 102, or both. The target values ​​may be one or more target dimensions, one or more target appearance properties, or a combination of these for the glass product 103 or the glass tube 102 to be produced during different transformation stages. For example, the target values ​​for the properties of the glass product 103 may include one or more specification values ​​from an international standard for glass products 103, such as, but not limited to, ISO 8362-1, "Injection Containers and Accessories—Part 1: Injection Vials Made of Glass Tubing", Third Edition, 2009-12-15, the entire contents of which are incorporated herein by reference. Table 1 below provides an exemplary specification from ISO 8362-1, which provides dimensions for injection vials made of glass tubes, including a neck treatment without blow-back (i.e., Type A). Table 1 : Specifications from ISO 8362-1 for 2R, 4R, 6R, 8R, 10R and 15R injection bottles with finish without blowback - Table 1 (20R, 25R, 30R, overflow capacity and mass omitted, no bias).

[0138] When executed by the processor 404, the machine-readable and executable instructions 408 may cause the control system 402 to automatically receive specifications for the glass article 103 to be produced and determine initial operating settings for each process parameter of the converter 100 from the specifications and the operating model constructed by the converter 100. The control system 402 may receive the specifications for the glass article 103 from a user input device or an external computing device 420 communicatively coupled to the control system 402 via a network 410. The initial operating settings for the process parameters may be determined by inputting values ​​for properties of the glass article 103 from the specifications into the operating model and calculating the initial operating settings therefrom. Operating the converter 100 at the initial operating settings may include adjusting each process parameter to the initial operating setting determined from the operating model.

[0139] The control system 402 is operable to construct an operational model of the converter 100. In particular, the control system 402 may include machine-readable and executable instructions 408 that, when executed by the processor(s) 404, may cause the system to automatically operate the converter 100 to convert the glass tube 102 into a plurality of glass products 103; measure one or more properties of the plurality of glass tubes 102, glass products 103, or both using at least one measurement device 360; adjust a plurality of process parameters of the converter 100 to operate the converter 100 under each of a plurality of condition sets; associate each of the plurality of glass products 103 with one of a plurality of condition sets for producing the glass products 103 and one or more properties of the glass tube 102, glass product 103, or both measured by the measurement device 360; and construct one or more operational models based on the measured properties and condition sets. Each operational model may relate one or more process parameters of the plurality of process parameters to one or more measured properties of the glass tube 102, glass product 103, or both. When executed by the one or more processors 404, the machine-readable and executable instructions 408 may further cause the control system 402 to automatically determine an initial operating setting for each process parameter based on the operating model and to operate the converter 100 with each process parameter set to the initial operating setting determined from the operating model.

[0140] After constructing the operating model for the converter 100, the operating model can then be integrated into a model predictive control framework for providing feedback control of the converter 100. In particular, the operating model can be integrated into a target control function that provides an algorithm for feedback control of the converter 100. The target control function can be based on a cost function for the converter 100. In an embodiment, the target control function can be based on a weighted mean square error cost function for the converter 100. Other control algorithms for constructing the target control function can be conceived. When based on the weighted mean square error cost function, the target control function penalizes the deviation of the attribute measurement value from the attribute target value, the attribute variance level (whether directly considered or indirectly addressed), and the actuator movement amplitude. The actuator movement amplitude refers to the amplitude of the position change of the actuator or control valve used to control the process parameters of the converter 100. During the feedback control sequence of controlling the converter, the target control function for the converter 100 is minimized. If the model is linear, this is achieved by a standard quadratic programming method with constraints. A solution to the optimization problem is applied, and the difference between what is expected to happen and what actually happens is taken into account when building the solution, and the entire optimization step is repeated again. Thus, the control sequence and the minimization of the target control function are repeated in an interactive process to provide robust performance in the presence of significant modeling errors. Each iteration of the control sequence includes measuring the properties of samples of glass products and / or glass tubes produced on the converter, recording the settings of the process parameters used to manufacture the glass products, processing the data set including the measured values ​​and settings of the process parameters to produce a statistical property matrix representing the measured values ​​of the properties, substituting the settings of the process parameters and the statistical property matrix representing the measured values ​​of the properties into the target control function, determining the updated settings of the process parameters by minimizing the target control function, and then adjusting the process parameters to the updated settings. The control sequence can then be repeated multiple times until the updated settings converge.

[0141] The objective control function may be derived by first constructing an operational model that provides an expression for the settings of the process parameters related to the estimated value of the property of the glass article or glass tube. As previously described herein, the operational model may be constructed by first principles, a "design of experiments" approach, or a combination of both. The operational model may express an expression where the estimated value of the property is the sum of an offset constant and at least one term that depends on the settings of the process parameters.

[0142] Second, a target control function may be constructed using the operational model and various terms and constants from the operational model to substitute into an initial control function for the converter, such as, but not limited to, a mean square error cost function. The initial control function may depend on an estimated value for each property of the glass article 103, the glass tube 102, or both; a target value for each property; and a setting for each process parameter. The operational model constructed for the converter 100 may be substituted into the initial control function for the estimated values ​​of the properties. Subsequently, the operational model is solved for offset constants to produce an offset constant function. Solving the operational model for the offset constants may include replacing the measured values ​​of the properties or a statistical property representing a distribution of the measured values ​​with the estimated values ​​for each property. The offset constant function may then be substituted into a control function modified for the offset constants to produce a target control function.

[0143] The derivation of an exemplary target control function according to the present disclosure will now be described in further detail. In an embodiment, the operating model of the converter 100 may be a linear model, such as the operating model provided in Equation 1 (EQU. 1).

[0144] In equation 1, is an nx1 vector of estimated values ​​of the properties in iteration k+1 of the control sequence, where n is an integer equal to the number of properties of the glass article and / or glass tube considered in the model predictive control framework, and k is an integer indicating the current iteration of the control sequence. The term G is a sensitivity matrix, where the sensitivities are obtained from the construction of the operating model (e.g., from a design of "experimental procedures"). Each sensitivity in the sensitivity matrix indicates the degree to which the property value changes in response to a change in a particular process parameter. The term Act(k) is an nx1 vector of settings of process parameters (e.g., settings of various actuators and control valves) for iteration k of the control sequence. The term α is a vector of offset constants.

[0145] Although the context of the operating model as a linear function is described herein, it should be understood that a more complex operating model can be constructed and substituted into the initial control function to derive the target control function. As previously described, the present model predictive control framework can compensate for significant errors between the operating model and the actual performance of the converter. Thus, it has been found that any errors in the operating model due to simplification of the operating model to a linear model are easily compensated by the model predictive control framework and feedback control of the converter 100 disclosed herein.

[0146] As previously discussed, depending on the estimated value of the attribute, the target value of the attribute, and the process settings (e.g., actuator settings), the initial control function can be a mean square error cost function. The initial control function can also include a weighting factor and a penalty factor for the attribute difference to penalize or reduce the magnitude of the change in the process parameter in each iteration. In an embodiment, the initial control function can be an expression for the mean square error cost function provided in Equation 2.

[0147] In Equation 2, the term Attrib targ is a vector of target values ​​for properties of the glass article and / or glass tube. is a vector of estimated values ​​of properties of the glass article and / or glass tube used for iteration k+1 of the control sequence. T Q is a symmetric and usually diagonal weighting matrix that includes attribute weighting factors for the differences between the measured values ​​of the attributes and the target values ​​of the attributes. Note that it is common to express this weighting factor matrix as the transpose of a matrix multiplied by itself. This is not required, but simplifies the expression. The term R T R is a symmetric and usually diagonal weighting matrix that is a weighting matrix of penalty factors for changes in process parameters (i.e., changes in actuator settings) from one iteration of the control sequence to the next. R may be required when there is significant model inaccuracy. T R acts as a closed-loop robustness adjustment lever. This article further discusses the adjustment of the penalty factor for changes in process parameters to tune the target control function. The operating model of Equation 1 can be substituted into the terms of Equation 2 above. to obtain the intermediate expression of Equation 3.

[0148] The offset constant α can be estimated by solving Equation 1 for the offset constant (one time step in the past, so the resulting attribute value is known rather than estimated), and then replacing the attribute's estimated value with the measured value of the attribute in the current iteration of the control sequence. Thus, at iteration k, we can obtain from Equation 1 that α = AttriB measured (k) - G*Act(k-1). This is an estimate obtained by measuring the property at time k. This estimate of the offset constant is actually a means of introducing feedback into the control sequence and is used as a form of integral control (similar to a standard PID proportional, integral, derivative controller) to eliminate steady-state errors. The equation for estimating the offset constant can be substituted into Equation 3 to produce the target control function of Equation 4 (Equation 4).

[0149] In Equation 4, the only unknown in the above equation is Act(k). As previously described, Act(k) is an nx1 vector of settings of process parameters (e.g., settings of various actuators and control valves) for iteration k of the control sequence. The control system 402 is operable to solve Equation 4 for values ​​of Act(k), which can minimize the target control function J(k) for iteration k of the control sequence. Minimizing the solution of Act(k) of the target control function of Equation 4 can be constrained by the maximum and minimum values ​​of each setting of the process parameters. In other words, when determining the solution of Act(k) that minimizes the target control function of Equation 4, the following expression in Equation 5 (Equation 5) must also be satisfied for all values ​​of k (e.g., k and k-1, where k=1, 2, 3, 4, ...). Ac tmin <Act(k)<Act max Equation 5

[0150] In Equation 5, Act min is the minimum value matrix of each process parameter setting, and Act max is the maximum value matrix of each process parameter setting. The solution of this constrained optimization problem is solved by standard quadratic programming method.

[0151] Vector Attrib targ and Attrib measured It can be any property of the glass article 103 and / or glass tube 102 that can be manipulated by changing one or more process parameters, which can achieve an adequate operating model. targ and Attrib measured can be any of the properties of the glass article 103 and / or glass tube 102 discussed previously herein. In an embodiment, the vector Attrib targ and Attrib measured The attributes of the glass article 103 and / or glass tube 102 may include, but are not limited to, one or more dimensions of the glass article 103 and / or glass tube 102, one or more appearance attributes of the glass article 103, one or more chemical attributes of the glass, ranges of any of these attributes, or combinations of these. The range of an attribute may include the standard deviation or variance of the attribute value(s). The variance of one or more attributes of the glass article and / or glass tube may be included in the AttriB by one of the following: targ and Attrib measured Either: (1) directly model the variance response in a “design of experiments” procedure; or (2) model the maximum and minimum attribute values ​​and control them to the desired set points.

[0152] As previously discussed, the objective control function may include attribute weighting factors, such as the weighting factor matrix Q in Equation 4T Q. The attribute weighting factors may be used to weight the relative importance of various attributes of the glass article and / or glass tube in the objective control function. Thus, deriving the objective control function may further include constructing an attribute weighting factor for each of the attributes of the glass article, the glass tube, or both, and applying the attribute weighting factors to one or more terms of the objective control function based on the mean square error cost function. In an embodiment, the attribute weighting factor may be applied to a term in the objective control function that represents the error between the target value and the estimated value of the attribute from the original mean square error cost function (i.e., (AttriB in Equation 2) est (k+1)–Attrib targ )).

[0153] In an embodiment, the process capability index C can be calculated by considering one or more properties of the glass article and the glass tube. pk To determine the attribute weighting factor. The process capability index C of the attribute pk The process capability index C can be determined based on known calculation methods, the distribution of the attribute within the specification range, the estimated mean of the attribute value, and the estimated variability of the attribute (e.g., standard deviation, variance, etc.). pk The properties of the glass product and / or glass tube may have a property weighting factor, and the property weighting factor is related to the property having the larger process capability index C pk The attributes with greater relative importance in the objective control function are weighted more heavily than the attributes with greater process capability index C. pk The properties of the glass article and / or glass tube may have property weighting factors that weight properties that have relatively less importance in the objective control function.

[0154] As previously discussed, the objective control function may include a penalty factor, such as the penalty factor matrix R in Equation 4 T R. Penalty factors may be used to penalize the magnitude of change in one or more process parameters in the objective control function for each iteration of the control sequence. Each penalty factor may indicate the amount of effect that a change in a particular process parameter has on the control response. In some instances, large changes in one or more process parameters may have a significant effect on one or more attributes, which may cause the updated settings of one or more process parameters to diverge or oscillate. Penalty factors may be used to reduce the magnitude of change in one or more process parameters in any one iteration of the control sequence. Thus, penalty factors may be used to reduce the response rate of feedback control by reducing the magnitude of change produced in each iteration of the control sequence. Penalty factors may reduce or prevent the probability that the control response diverges or oscillates outside of normal expected changes, but at the cost of a slower response time of the control method to changing operating conditions.

[0155] A penalty factor may be constructed for one or more process parameters and may be applied to a term in a target control function that represents a change in the process parameter. The penalty factor may be constructed based on simulation, trial and error, operator intuition and experience, or other considerations. Process parameters with large penalty factors R will be penalized to a greater extent in the target control function, resulting in smaller allowed changes in process parameters with high R for each iteration of the control sequence. Similarly, process parameters with small penalty factors R will be penalized to a lesser extent in the target control function, which may allow larger allowed changes in process parameters with low R in each iteration of the control sequence. Thus, the penalty factor may be used as a tuning feature to tune the feedback control provided by the model predictive control framework.

[0156] Reference again Fig.11 , the target control function may be used in a method for providing feedback control of a converter 100 for producing a glass product 103 from a glass tube 102. The control method for feedback control of the converter 100 may include providing a target value for one or more properties of the glass tube 102, the glass product 103, or both during or after conversion. The control method may include operating the converter 100 to produce a plurality of glass products 103 from a plurality of glass tubes 102 and measuring the properties of the plurality of glass products 103 and / or the plurality of glass tubes 102. The control method may include recording settings of operating parameters of the converter 100 associated with the properties to generate a data set including measured values ​​of the properties and settings of process parameters. The control method may further include processing the data set to generate statistical characteristics of the distribution of measured values ​​of each property, and determining an updated setting for each operating parameter based on the statistical characteristics of the distribution of measured values ​​of each property, target values ​​of each property, and settings of the operating parameters. The updated setting of the operating parameter may be a setting value that minimizes the target control function constructed by the converter. The control method may further include adjusting each operating parameter of the converter 100 to the updated setting.

[0157] The control method may further include the steps of repeatedly measuring the attribute, recording the setting of each process parameter, processing the data set, determining an updated setting for each process parameter, and adjusting each process parameter to the updated setting. In an embodiment, the control method may be repeated continuously while the converter 100 is operating. In an embodiment, the control method may be repeated at least until the updated settings of the process parameters converge. Convergence of a process parameter refers to the process parameter being adjusted to a range within which further changes in the process parameter are within the normal expected variability of the process.

[0158] Reference now Fig.12, graphically depicts a control sequence 500 for feedback control of a converter 100 representing the methods described herein. During one iteration of the control sequence 500 for feedback control of the converter 100, a conversion process 510 for producing glass products from a glass tube using the converter 100 is operated. During the conversion process 510, one or more properties of the glass tube, the glass products, or both are measured for a plurality of glass products. A measured value 512 for each of the properties and settings 514 of the process parameters is output from the conversion process 510 and received in the control system 402. The measured value 512 for each property is processed in a data processing module 520 to remove anomalous data points and to calculate one or more statistical characteristics 522 of the distribution of the measured values ​​512.

[0159] After processing the data including the measured values ​​512 of the attributes, the settings 514 of the process parameters and at least one statistical characteristic 522 representing the measured values ​​512 of the attributes are passed to the control module 530 along with the target value 524 of the attributes. The control module 530 may include a target control function, which in an embodiment may be based on a mean square error cost function for the converter. The control module 530 receives the settings 514 of the process parameters, the statistical characteristics 522 representing the measured values ​​512 of the plurality of attributes, and the target value 524 of the attributes. The control module 530 then finds the value of the updated settings of the process parameters that minimizes the target control function 530. The updated settings 532 are then output from the control system 402 to the conversion process 510 and the converter 100, where the process parameters are adjusted to the updated settings 532. The control sequence 500 may be repeated for multiple iterations.

[0160] The control methods disclosed herein can control a single property by considering one or more process parameters, or can control multiple properties by considering multiple process parameters. The control methods can be implemented in whole or in part by the control system 402. In an embodiment, the control methods and control sequences can be fully automated by the control system 402. For example, the control system 402 can be communicatively coupled to each of the actuators and control devices that control the process parameters, and the control system 402 can be adjusted to fully automatically change the process parameters to the updated settings at the end of each iteration of the control sequence.

[0161] In other embodiments, the control methods and control sequences may include some interaction with an operator of the converter 100 while performing other actions using the control system 402. In embodiments, the control system 402 may be operable to receive measured values ​​of properties and settings of process parameters from the converter 100, process data including the measured values ​​of properties and settings of process parameters, and determine updated values ​​of operating parameters by minimizing an objective control function. After determining the updated settings of the operating parameters, the control system 402 may transmit the updated settings of the process parameters to the operator, who may then decide to adjust the process parameters of the converter 100 to the updated settings. As previously discussed, it is difficult for a human operator to consider more than a maximum of approximately 3 different operating parameters and 3 different properties simultaneously. Therefore, for converters that must consider multiple operating conditions and properties in a control strategy, the control system 402 must be capable of performing the necessary trial and error solution approach to minimize the complex objective control function for multiple properties of the glass product to determine the updated settings of the operating parameters. Reference Fig.11 In an embodiment, the control system 402 may include a display 430 including a graphical user interface 432 operable to facilitate interaction between the control system 402 and an operator of the converter 100. The control system 402 may enable an operator to input parameters (such as attribute weighting factors, penalty factors, target values ​​for attributes, operating model information, or other information) into the control system 402 for use in a model predictive control framework.

[0162] The target value of the property of the glass product 103 and / or the glass tube 102 can be provided as a single target value, a range of target values ​​(e.g., by providing a maximum and minimum value of the specification of the property or by providing a single target value and a tolerance), or both. Examples of a single target value may include a target mean, a target median, a target maximum, a target minimum, a target spread, or other single target values. The range of target values ​​may be characterized by a target minimum and a target maximum or by a combination of a single target value and a tolerance. The target value may refer to a dimensional or appearance characteristic of the finished glass product 103, such as, but not limited to, those in Table 1 from ISO 8362-1. The target value may also include a target value for an intermediate condition of the glass product 103, such as a temperature, a dimensional or appearance characteristic of the glass tube 102, a glass preform at the working end 150 of the glass tube 102, a characteristic of a partially formed glass product at the working end 150 of the glass tube 102, or a combination of these. The target value for each property may be manually input into the control system 402 by an operator, for example, by using the graphical user interface 432, or may be automatically obtained by the control system 402 from an external system via the network 410, where the external system may be a business management system or other system capable of storing specifications for glass products and / or glass tubing. In an embodiment, the control system 402 is operable to save the target value for the property in the memory module 406 of the control system 402.

[0163] Reference again Fig. 9 and Fig.11 As previously described, each of the plurality of properties of the glass tube 102, the glass article 103, or both may be measured during operation of the converter 100 using one or more measuring devices 360. The measured values ​​of the properties and the settings of the process parameters may be stored in one or more memory modules 406 of the control system 402, such as a relational database stored on the memory module 406 of the control system 402. In an embodiment, the control system 402 may include machine-readable and executable instructions 408 that, when executed by the processor 404, may cause the control system 402 to automatically measure each of the properties of the glass tube 102, the glass article 103, or both, and record the settings of the process parameters to generate a data set including the measured values ​​of each property and the settings of the process parameters. When executed by the processor 404, the machine-readable and executable instructions 408 may cause the control system 402 to automatically save the data set to the memory module 406 or export the data set to the external computing device 420.

[0164] For each iteration of the control sequence, the properties of the glass tube 102 and / or the glass product 103 can be measured for a plurality of glass products 103 produced on the converter 100 to generate a data set including a plurality of measured values ​​for each property under the process parameter settings. The number of glass products 103 measured in each iteration of the control sequence can be a statistically relevant number of glass products 103. The statistically relevant number of glass products 103 can be large enough to generate a plurality of glass products 103 representing a distribution of measured values ​​of a true underlying distribution (i.e., the distribution of measured values ​​of all glass products produced under the process parameters when the converter is operated indefinitely under these process parameters). The number of glass products 103 constituting the statistically relevant number can depend on the number of different process parameters incorporated into the model predictive control framework. In general, the greater the number of glass products measured, the higher the accuracy of the data set, and the higher the accuracy of the statistical characteristics of the distribution of measured values ​​of each property. Determining the number of glass products required to generate a statistically relevant data set is within the skill of a person of ordinary skill in the art who understands natural process variations through properties.

[0165] The number of glass products measured can also be balanced by the desired response time of the control sequence. Increasing the number of glass products 103 measured increases the response time of the feedback control by increasing the time allocated to measure the properties to generate a data set. Likewise, reducing the number of glass products measured can reduce the response time of the feedback control sequence used to control the converter 100, however, there is a risk of reduced accuracy. Therefore, the number of products 103 for which the properties of the glass products 103 or glass tubes are measured can be selected to balance the accuracy and response rate of the feedback control. In some embodiments where multiple properties and multiple process parameters are considered in a model predictive control framework, each iteration of the control sequence or method can include measuring the properties of the glass products for at least one full tube length of glass tubes for all holders 130 of the converter 100. For example, for a converter 100 with sixteen processing stations in the main turret, and for a glass tube long enough to produce 20 to 30 glass products 103 from each glass tube 102, the number of glass products measured may be at least between 320 and 480 glass products 103 at each iteration of the control sequence. However, it should be understood that the number of glass articles 103 measured may be greater or lesser depending on the level of inherent property variation.

[0166] Once the measured values ​​of the attributes and the settings of the process parameters of the converter are obtained, the data set can be processed to produce one or more statistical characteristics representing the distribution of the measured values. The data set obtained from the converter 100 may include the measured values ​​of each attribute and the settings of each process parameter. The method disclosed herein may include removing abnormal data points from the data set of measured values ​​of at least one attribute. After removing the abnormal data points, the control method may include calculating the statistical characteristics of the distribution of the measured values ​​of the attributes from the data set. The statistical characteristic of each attribute is a calculated value representing the measured values ​​of the attribute. The statistical characteristic of the distribution of the data set may be a mean, a median, a range, a standard deviation, a variance, or a combination of these. In an embodiment, the statistical characteristic may be the mean or median of the distribution of the measured values. The control system 402, in particular the data processing module 520 of the control system, may include computer readable and executable instructions 406, which, when executed by the processor 404, cause the control system 402 to automatically process the measured value 512 data to remove abnormal data points and calculate one or more statistical characteristics of the distribution of the measured values ​​for each attribute. Reference Fig.11 Processing the data set may be performed using the control system 402, or the processed data set may be exported to an external computing device 420 that processes the data set and returns the statistical attributes.

[0167] refer to Fig.12 Once the data set is processed to produce the statistical characteristics of the distribution of the measured values ​​of each attribute, the control method may then include determining updated settings for the process parameters based on the target control function. Determining the updated settings from the target control function may include passing the settings of the target values ​​of the attributes, the settings of the process parameters used to generate the measured values ​​of the attributes, and the statistical characteristics representing the distribution of the measured values ​​of each attribute to the control module and substituting these values ​​into the target control function. In an embodiment, the target control function may be a function of Equation 4 provided herein. In the target control function in Equation 4, the target value of the attribute may replace Attrib targ , indicating the statistical characteristics of the measured values ​​of the attribute can be substituted into the vector Attrib measured (k), and the process parameter settings can be substituted into the vector Act(k-1).

[0168] Determining updated settings for process parameters may further include solving a target cost function that minimizes the value of the process parameter of the target control function. The control system 402 is operable to determine the value of the process setting of the target control function that minimizes the target control function. Updated settings for process parameters are those settings that minimize the target control function. In an embodiment, the control system 402 may include computer-readable and executable instructions 406, which, when executed by the processor 404, may cause the control system 402 to automatically substitute the target value of the attribute, the statistical characteristics of the measured values ​​representing the attribute, and the settings of the process parameters into the target control function, and determine the updated settings for the process parameters by finding the setting values ​​that minimize the target control function. The updated settings may be determined using the control system 402, or the control system 402 may be operable to export the statistical characteristics, the target value, the settings of the process parameters, or a combination of these to an external computing device 420, which may be operable to determine the updated settings and send the updated settings back to the control system 402.

[0169] As previously discussed, each process parameter may have a maximum value and a minimum value based on an operable range of an actuator, control valve, servo motor, or other control device, or based on values ​​of the process parameter that are known to produce off-specification glass products. The solution to the minimized objective control function may be further constrained by the maximum value and the minimum value of each process parameter, as discussed previously herein with respect to Equations 4 and 5. In an embodiment, determining updated settings for the process parameters may include subjecting the objective control function to constraints including the maximum value and the minimum value of each process parameter. In an embodiment, the control method may include providing a maximum setting and a minimum setting for each process parameter, and maintaining the updated setting for each process parameter within a range between the minimum setting and the maximum setting of the process parameter.

[0170] Once the updated settings for the process parameters are determined, the control method may include adjusting the process parameters of the converter 100 to the updated settings. In an embodiment, the control system 402 may include machine-readable and executable instructions 408 that, when executed by the processor 404, may cause the control system 402 to automatically transmit a control signal indicating the updated setting for each process parameter to one or more control devices on the converter 100, wherein the control signal causes the control device to adjust the process parameter to the updated setting. The control signal may indicate the updated setting or a change in the process parameter setting relative to the previous setting at k-1. In an embodiment, the machine-readable and executable instructions 406, when executed by the processor 404, may cause the control system 402 to automatically display the updated settings on the display 430. In an embodiment, an operator may view the updated settings and make changes to the process parameters, rather than using the control system 402 to automatically change the process parameters.

[0171] As previously discussed, the control method may include repeating the control sequence one or more times. In an embodiment, the control sequence may be repeated continuously while the converter 100 is operated to produce the glass product 103. In such an instance, the model predictive control framework and the control system 402 provide constant feedback control of the converter 100 during operation. In an embodiment, the control sequence may be repeated multiple times, the number of repetitions being sufficient to converge the update settings to a value within an acceptable range. The acceptable range of the update settings refers to the range of process parameters representing the normal expected variability in the process. Once the repetition of the control sequence results in the convergence of the update settings, the final update settings may be maintained and the repetition of the control sequence may be stopped. In an embodiment, the control method may be performed on a periodic control basis throughout the operation of the converter 100, wherein the "periodic control basis" refers to operating the converter 100 in alternating cycles of control and non-control. The non-control period is a period during which the control method is not executed during the operation of the converter 100. In an embodiment, the non-control period may have a duration greater than or equal to the duration of a single iteration of the control sequence. In an embodiment, the non-control period may be at least as long as the length required to consume a set of glass tubes loaded into the converter 100.

[0172] As previously discussed, the model predictive control framework disclosed herein can compensate for some errors in the operating model or mismatches between the operating model built for the converter 100 and the actual operation of the converter caused by changes in the conversion process, materials, or operating environment. In some instances, such as but not limited to process changes, tool wear, changes in input materials, or process drift over time, the mismatch between the operating model integrated into the target control function and the actual operation of the converter 100 may become significant enough to cause a lack of control over the conversion process. The lack of control can manifest as the updated settings of the process parameters diverging with each iteration of the control sequence, or the oscillations of the updated settings exceeding the effects of the normally expected variability in the conversion process.

[0173] As previously discussed, in some cases, the objective control function may be adapted to correct for a mismatch that results in a reduction in the ability to control the converter. For example, in some cases, control may be restored by changing the penalty factors in a penalty factor matrix (RTR) for one or more process parameters. Modifying the penalty factors for changes in one or more process parameters, such as modifying so as to penalize changes in process parameters to a greater extent, may reduce the magnitude of any changes to those process parameters in each iteration of the control sequence, which may reduce the probability of overshoot resulting in divergence or oscillation. However, changing the penalty factors to reduce the magnitude of changes made to the process parameters may slow the control response, which may increase the time required to compensate for any further changes in the process.

[0174] In an embodiment, the method disclosed herein may include a repetitive control method (i.e., a control sequence) for multiple iterations, and identifying a condition indicating a reduction in the ability to control one or more aspects of the converter. The condition indicating a reduction in the ability to control the converter may include diverging or oscillating updated settings for one or more process parameters through multiple iterations of the control sequence. After identifying the condition indicating a reduction in the ability to control the converter, the method may include adjusting a penalty factor for the one or more process parameters. Adjusting the penalty factor may reduce the magnitude of the changes made to the one or more process parameters in each iteration of the method, thereby reducing the divergence or oscillation of the updated settings and restoring control of the converter.

[0175] At some point during the operation of the converter 100, whether due to gradual changes in the conversion process over time or due to an expected step change in the conversion process, the mismatch between the operating model of the converter and the actual operation of the converter may become large enough to require reconstructing one or more operating models of the converter 100. In some cases, gradual changes in the process, such as equipment wear or other gradual changes, may eventually lead to a mismatch between the operating model and actual converter performance, which requires reconstructing the operating model. The need to reconstruct the model may be indicated by a reduction in the ability of the model predictive control framework to control the converter, such as an indication of divergent settings of process variables, oscillations of process variables beyond the expected natural variability in the process, or excessive time required to converge updated settings of process parameters (e.g., an uneconomical number of iterations for the control sequence). The operating model may also be reconstructed in anticipation of or in response to an expected change in the operation of the converter 100, such as, but not limited to, an expected change in the size, shape, or type of glass product produced, a change in product specifications and target values, a known change in glass composition or quality, an expected change in fuel gas composition, a planned replacement of worn equipment (e.g., worn forming tools, burners, control valves, actuators, etc.), other planned maintenance activities, or other expected changes. In an embodiment, reconstruction of the operating model of the converter may be performed according to a regular periodic schedule, which may help remedy mismatches between the operating model and actual converter performance before a degradation in the ability to control the converter is experienced.

[0176] The operating model of the converter 100 may be reconstructed by considering first principles or by engaging in the "experimental design" process previously described herein for constructing the operating model. After reconstructing the operating model by first principles, the "experimental design" process, or both, the objective control function may be modified to incorporate the new operating model, such as by incorporating an updated sensitivity matrix G into Equation 4. In some embodiments, updating the objective control function may also include updating the attribute weighting factor matrix (Q T Q), penalty factor matrix (R TR) or a combination of these. The attribute weighting factor matrix and the penalty factor matrix can be updated in the event of an expected change involving the process, such as but not limited to a change in the size, shape or type of glass product being produced, replacement of wear equipment, change in glass composition, or other expected changes. Once the operating model and target control function are updated, the control method can be resumed.

[0177] The construction and / or reconstruction of an operating model in response to gradual or anticipated changes in the operation of the converter 100 will now be described in further detail. The "Design of Experiments" process previously described herein may be used to construct and / or reconstruct an operating model of the converter 100 to quickly and efficiently achieve steady-state operation of the converter 100 during startup of a new converter 100, startup of an existing converter 100 with a new type, size, or shape of glass product 103, transition from one type or size of glass product 103 to another type or size of glass product 103, or a combination of these. The "Design of Experiments" process disclosed herein may also be used to construct or reconstruct an operating model to readjust the operation of the converter 100 after a change in one or more components of the converter 100 (such as a forming tool 324 or a burner 302; a change in fuel gas composition 1; a change in one or more external inputs to the converter 100; or a combination of these).

[0178] Converter startup and / or switching

[0179] Reference again Figure 1 , the system 400 and method of the present disclosure may be used to quickly and efficiently determine the initial operating settings of the converter 100 to achieve steady-state operation at converter startup or after a converter 100 switchover. Startup refers to the first time a new converter 100 is started to operate or an existing converter 100 is started to operate to produce a new type or size of glass product 103 that was not previously produced on the existing converter 100. Switchover may refer to changing the size, shape, or type of glass product 103 from one size, shape, or type of previously produced glass product 103 to another size, shape, or type of previously produced glass product 103. Switchover may also include a change in the size of the glass tube 102, a change in the glass composition of the glass tube 102, a change in the coefficient of thermal expansion (CTE) of the glass tube 102, or other changes in the physical or chemical properties of the input glass tube 102. As previously discussed, a change in the type, shape, or size of glass product 103 being produced or a change in the type or size of the glass tube 102 typically involves a significant amount of lost production time due to setting and adjusting hundreds of process parameters on the converter 100 for the new type or size of glass product.

[0180] Building a setup for a new converter 100 or for a new glass product 103 that has not been previously produced can be a relatively long and iterative process that relies heavily on human operators to perform. Setup for a new converter 100 or for a new glass product 103 that has not been previously produced can include a two-step process: (1) burner setup; and (2) forming station setup. In particular, burner setup of the converter 100 is first performed to produce the appropriate preform at the working end 150 of the glass tube 102, and then the forming station 204 is set up to produce the final glass product 103. During the burner setup stage, the part rate of the converter 100, the position of the burner 302, and the heat output of the burner 302 can be adjusted in sequence before forming, moving around the converter 100 from the separation station 206 to the final heating station 202. These adjustments during burner setup can be based on general guidelines and targets for various sizes of glass tubes 102, which can help measure the effects of these individual burner 102 parameters and their interaction with each other. However, in most cases, burner settings involve an iterative process to create a suitable glass preform for shaping.

[0181] Once the glass preform shape is constructed, the settings for the forming station 204 are constructed. The relative vertical and horizontal positioning of the forming tool 324 affects the shape of the features of the glass product 103. For glass bottles, these features can include any of the properties described in Table 1 for ISO 8362-1, such as but not limited to flange height, neck outer diameter, flange inner diameter, flange outer diameter, shoulder radius, or other features. The features and shapes depend on the type of glass product 103 being produced. General guidelines and goals for these different shapes and sizes exist; however, in order to meet the stringent dimensional tolerances of pharmaceutical glass products, it may take a lot of iteration time to find the right forming settings, which may often include going back in the process to make further modifications to the burner settings.

[0182] As previously discussed, the system 400 and method of the present disclosure may include systematically operating the converter 100 under multiple condition sets and building an operating model based on the condition sets and measured properties of the glass tube 102, glass product 103, or both produced using the condition sets. The operating model built for the converter 100 for the specific glass product 103 being produced can then be used to determine the initial operating settings of the converter 100 in order to produce a glass product 103 with desired properties. This provides a systematic and automated setup process that reduces or eliminates reliance on machine operator decisions and speeds up the setup and switching process of the converter 100. The operating model built for the converter can then be integrated into the objective control function of the model predictive control framework for providing feedback control for the converter 100.

[0183] In an embodiment, the system 400 may receive an input indicating a change in the type of glass product 103 produced by the converter 100 from a first glass product to a second glass product. The change in the type of glass product 103 may include a change in the size, shape, or both of the glass product 103, the glass tube 102, or both. In an embodiment, the second glass product may be a new type or size of glass product 103 that has not been previously produced on the converter 100. The input indicating the change in type of glass product 103 may be a manual input, or may be an electronic signal received from an external system (such as a business management system) via the network 410. In an embodiment, the electronic signal may include a starting recipe for the second glass product, where a plurality of condition sets may be constructed starting from the starting recipe. The system 400 can operate the converter 100 to convert the glass tube 102 into a plurality of second glass products, measure one or more properties of the plurality of second glass products using the measurement device 360, adjust a plurality of process parameters to operate the converter 100 under each of a plurality of condition sets, associate each of the plurality of second glass products with the condition set and the measured properties for producing the second glass products, and construct one or more operating models of the second glass products based on the one or more measured properties and the plurality of condition sets for each of the plurality of second glass products. The system 400 can further determine an initial operating setting for each of the plurality of process parameters based on the one or more second operating models, and operate the converter 100 with each of the plurality of process parameters set to the initial operating setting determined according to the one or more second operating models. Although described in the context of switching from a first glass product to a second glass product or from one type or size of glass tube to another type or size of glass tube, the system 400 and method of this paragraph can be equally applied to the startup of a new converter 100 (e.g., setting up a first glass product on a new machine).

[0184] In an embodiment, the converter 100 may be set up in stages. The first stage of the set up may be a burner set up to determine an initial operating set up of process parameters for the heating station 202 to produce a glass preform having target properties (such as temperature, viscosity, size, or a combination of these). Once the converter 100 has been set up to produce an appropriate glass preform at the working end 150 of the glass tube 102, the second stage of the set up may be a forming set up to determine an initial operating set up of process parameters for the forming station 214 to form the glass preform into the features of the glass article 103.

[0185] The method of the present disclosure may include the following steps, which may be implemented by the system through the processor 404 executing the machine-readable and executable instructions 408. The method may include preparing a first subset of a set of conditions, which may include process parameters related to producing a glass preform at the working end 150 of the glass tube 102 in one or more heating stations 202. The method may further include preparing a second subset of the set of conditions, which may include process parameters related to forming the glass preform at the working end 150 of the glass tube 102 into one or more features of the glass article 103 in one or more forming stations 204. The condition sets may be constructed according to any method disclosed herein, such as but not limited to inputting various process parameters into a "design of experiments" statistical software program. In an embodiment, the first subset of the condition set and the second subset of the condition set may be constructed externally to the system 400 and then uploaded as a "recipe" to the control system 402, which may then be automatically run on the converter 100.

[0186] The method may further include operating the converter 100 under each of the first subset of the condition sets, measuring one or more preform properties of the glass preform at the working end 150 of the glass tube 102, and constructing one or more preform operation models based on the measured one or more preform properties and the first subset of the condition sets. The preform operation model may be constructed according to any method disclosed herein for constructing an operation model. The preform operation model may describe the relationship of various burner input parameters (burner flow, position, and holder 130 rotation rate) to the properties of the glass preform (such as one or more dimensions and / or temperature distribution of the glass preform). The method may further include determining an initial operating setting for each of the plurality of process parameters in the heating station 202 based on the preform operation model, and operating the converter 100 with each of the plurality of process parameters in the heating station 202 set to the initial operating setting determined according to the preform operation model.

[0187] In an embodiment, the preform operation model can be used such as or other statistical software program control system 402 external to the external computing system 420 ( Fig.11). Once constructed by the external computing system 420, the preform operation model may be used to determine optimal initial operating settings for the heating station 202, and the initial operating settings may be uploaded to the control system 402 as a recipe. In an embodiment, the preform operation model may be constructed internally within the control system 402. The control system 402 may include machine-readable and executable instructions that, when executed by the processor 404, may cause the control system 402 to perform a statistical analysis of a set of conditions and measured properties of the glass preform to construct the preform operation model. When executed by the processor 404, the machine-readable and executable instructions may further cause the control system 402 to automatically determine the initial operating settings for the heating station 202 from the preform operation model, and automatically adjust the process parameters of the heating station to the initial operating settings constructed from the preform operation model.

[0188] Once a suitable glass preform is set, a similar process may be performed on the forming setup to determine initial operating settings for the plurality of forming stations 204. The method of the present disclosure may further include operating the converter 100 under each of a second subset of the set of conditions including process parameters associated with the forming stations 204 while operating the converter 100 with the process parameters of the heating station 202 set to the initial operating settings. The method may further include measuring one or more properties of the plurality of glass articles 103 produced, constructing one or more forming operation models based on the properties measured for the plurality of glass articles 103 and the second subset of the set of conditions, determining an initial operating setting for each of the plurality of process parameters in the forming stations 204 based on the forming operation models, and operating the converter 100 with each of the plurality of process parameters in the forming stations 204 set to the initial operating settings determined from the one or more forming operation models. As with the preform operation model, the forming operation model may be constructed on the external computing system 420 or on the internal control system 402.

[0189] The control system 402 may further include machine readable and executable instructions that, when executed by the processor, may cause the control system 402 to automatically update the target control function with information from the operating model built during startup or switchover of the converter 100. In embodiments, switchover of the converter 100 may include changing operation from a first glass product to a second glass product, where the second glass product is a product previously run on the converter 100. In these embodiments, the operating model built for the previous activity may be retrieved and the target control function updated with information from the previously built operating model without having to rebuild the operating model. The ability of the model predictive control framework to compensate for mismatches between the operating model and the actual operation of the converter 100 enables the use of previously built operating models.

[0190] Parts Replacement

[0191] In an embodiment, the control system 402 is operable to reconstruct one or more operating models in response to a change in one of the components of the converter, such as, but not limited to, replacement of a worn forming tool, a burner, an actuator, a control valve, a converter drive motor, a drive train operably coupling the converter drive motor to the main turret, or other components. As previously discussed, replacement of one or more components of the converter 100 or other planned or unplanned maintenance activities may introduce significant errors in the operating model, which may slow down the response time of the model predictive control framework or cause the model predictive control framework to lack control of the converter. After replacing one or more components of the converter 100, the updated operating settings of one or more process parameters calculated according to the minimized objective control function may no longer result in the production of glass products 103 that meet quality specifications. For example, after replacing one or more forming tools 324 in the forming station 204 due to wear or failure of the forming tool 324, the positioning of the new forming tool 324 may need to be adjusted due to the different size of the replacement forming tool 324 compared to the worn forming tool 324. Replacement of the converter drive motor, components of the drive train that operably couples the converter drive motor to the main turret, forming tool actuators, burner actuators, burner control valves, burners, or other components of the converter 100 may also introduce additional mismatches between the actual operation of the converter 100 and the properties predicted from the operating model. These mismatches between the previous operating model and the actual operation of the converter 100 after replacement of one or more components may result in high yield losses.

[0192] In these examples, the systems 400 and methods disclosed herein can automatically reconstruct one or more operational models of the converter 100 after replacing one or more components in the processing station 106 of the converter 100. The following method steps related to automatically reconstructing one or more operational models of the converter 100 after a component change will be described in the context of replacing (multiple) forming tools 324. However, it should be understood that the method steps can be utilized to achieve similar effects when reconstructing one or more operational models of the converter 100 after replacing any other components (such as, but not limited to, the burner 302, the burner positioner 318, the control valve (fuel gas control valve, oxygen control valve, air control valve), the forming tool actuator 326, the retainer 130, the converter drive motor, components of the drive train, or other components).

[0193] The method disclosed herein for automatically rebuilding one or more operating models of the converter 100 after replacing a component of the converter 100 may include identifying one or more defective components in one or more processing stations 106 of the converter 100. Defective components may refer to components that have failed or have worn out so that they no longer produce glass products 103 that meet the size and / or appearance standards of the glass products 103. The method may further include replacing the defective components in the one or more processing stations 106 with one or more replacement components. The defective component may be any component in any processing station 106 previously described herein. In an embodiment, the method may further include identifying one or more defective forming tools in one or more forming stations 204 of the converter 100. The defective forming tool may refer to a forming tool 324 that no longer produces a glass product 103 that meets the size standards of the glass product 103. The defective forming tool may be worn or damaged. The method may further include replacing the defective (multiple) forming tools with one or more replacement forming tools.

[0194] After replacing the defective part with the replacement part, the method may further include preparing a plurality of condition sets for the converter 100, operating the converter 100 to convert the glass tube 102 into a plurality of glass products 103, measuring one or more properties of the plurality of glass products 103, the glass tube 102, or both, adjusting one or more of a plurality of process parameters of the condition set to operate the converter 100 under each of the plurality of condition sets, and associating each of the plurality of glass products 103 with the condition set and the measured one or more properties for producing the glass product 103. The method may further include updating the operating model based on the measured one or more properties and the plurality of condition sets for each of the plurality of glass products 103 to produce an updated set of operating models that takes into account the replacement part. An initial operating setting for each of the plurality of process parameters may be determined from the updated operating model. The process parameters may be adjusted to the initial operating setting, and the converter 100 is operated under the new initial operating setting to produce the glass product 103. The method may further include updating the objective control function with information from the updated operating model, such as, but not limited to, updating the sensitivity matrix G of the objective control function of Equation 4.

[0195] In an embodiment, replacement of a component such as a forming tool 324 may not require adjustment of all process parameters or operating models of the converter 100. For example, replacement of the forming tool 324 may not affect the glass preform, and the operating model and process parameters associated with the upstream heating station 202 may not need to be rebuilt and adjusted. Therefore, automatically rebuilding the operating model of the converter 100 after a component replacement may only require updating a subset of the operating model for the converter 100. In an embodiment, a plurality of condition sets for the converter 100 may include settings for a subset of a plurality of process parameters for the converter 100. The subset of process parameters may include process parameters related to the processing station 106 of the replaced component, and optionally, any processing station 106 downstream thereof. In an embodiment, the component replacement may be a forming tool replacement, and the subset of the plurality of process parameters of the converter 100 may include positioning of one or more replaced forming tools (with respect to all three dimensions of the coordinate axes in the figure), contact timing of one or more replaced forming tools with the glass tube 102, or both. The contact timing may include the overall contact timing of the replacement forming tool in contact with the glass tube 102.

[0196] In an embodiment, a system 400 including a control system 402 may be used to implement a method for automatically rebuilding one or more operating models of a converter 100 after a component replacement or other machine anomaly. The control system 402 may include machine-readable and executable instructions 408, which, when executed by a processor 404, may further cause the control system 402 to automatically receive input indicating a change in one or more components in at least one processing station 106 of the converter and to build a subset of condition sets. The subset of condition sets may include settings of a subset of process parameters of the converter 100 that are related to or affected by the change in the component of the converter 100. In an embodiment, the component change may be a replacement of one or more forming tools 324, and the subset of condition sets may include settings of a subset of process parameters related to the forming station 204 where the forming tools were replaced and / or settings of process parameters related to the processing station 106 downstream of the forming station 204.

[0197] When executed by the processor(s) 404, the machine-readable and executable instructions 408 may further cause the control system 402 to operate the converter 100 to convert the glass tube 102 into a plurality of glass articles 103, measure one or more properties of the plurality of glass articles 103, the glass tube 102, or both using at least one measurement device 360, adjust one or more of the plurality of process parameters to operate the converter 100 under each of the condition sets in the subset of the condition sets, associate each of the plurality of glass articles 103 with the condition set for producing the glass article 103 and the property measured for each of the glass articles 103, and update one or more of the operating models based on the property measured for each of the plurality of glass articles 103 and the subset of the condition set to generate one or more updated operating models for the converter 100. The updated operating models may be used by the control system 402 to determine initial operating settings for the plurality of process parameters after the component replacement. The control system 402 may then operate the converter 100 with the process parameters set to the updated initial operating settings determined by the operating models. The control system 402 may also include machine-readable and executable instructions 408 that, when executed by the processor 404, may cause the control system 402 to automatically update the target control function with information from the updated operating model.

[0198] Identifying abnormal conditions

[0199] In an embodiment, the control system 402 is operable to identify one or more abnormal conditions on the converter 100, such as, but not limited to, a faulty component of the converter 100, a wrong size glass tube 102 loaded into the converter 100, a missing glass tube 102, a burner airflow interruption, a ventilation system operation interruption, other abnormal conditions, or a combination of these. The method disclosed herein may include: for each of a plurality of process parameters, while operating the converter 100 at an operating setting, measuring one or more properties of each of a plurality of glass products 103; determining one or more predicted properties of each of the plurality of glass products 103 based on a plurality of process settings and an operating model; and comparing the one or more properties measured for each of the plurality of glass products 103 with the one or more predicted properties to identify deviations from normal steady-state operation of the converter 100. The method may further include identifying an abnormal condition of the converter 100 based on comparing the one or more properties measured for each of the plurality of glass products 103 with the one or more predicted properties based on the operating model, correcting the abnormal condition of the converter 100, and rebuilding the model after correcting the abnormal condition.

[0200] In any methods disclosed herein, the converter 100 may include a plurality of holders 130, and the methods disclosed herein may include securing one of the plurality of glass tubes 102 in each of the plurality of holders 130, and passing each of the plurality of holders 130 and the glass tube 102 disposed therein through a plurality of processing stations 106.

[0201] In any of the methods disclosed herein, each of the plurality of processing stations 106 of the converter 100 can be in a fixed position, and the method can include passing the glass tube 102 continuously through each processing station 106 in sequence. Alternatively, in an embodiment, in any of the methods disclosed herein, the converter 100 can be a continuous converter, and the method can include passing the glass tube continuously through the plurality of processing stations, wherein each of the plurality of processing stations can move in coordination with the translation of the glass tube 102 during an active time.

[0202] refer to Fig.11 In an embodiment, the system 400 may include a distributed computing environment including the converter 100 and a control system 402, a network 410, and one or more external computing devices 420. The control system 402 may communicate with the external computing device 420 via the network 410. One or more steps in the method disclosed herein may be implemented using the external computing device 420 alone or in combination with the control system 402. Fig.11 4 is shown as being directly communicatively coupled to the converter 100, it should be understood that the control system 402 can also communicate with the converter 100 via a network 410. The network 410 can be a wired or wireless network. In an embodiment, the network 410 can be a cloud network.

[0203] Embodiments of the present disclosure may be embodied in hardware and / or software (including firmware, resident software, microcode, etc.). The control system 402 of the converter 100 and / or other controllers on the converter 100 may include at least one processor and a computer-readable storage medium (i.e., a memory module), as previously described herein. The control system 402 may be communicatively coupled to one or more system components (e.g., the converter 100, the burner positioner 318, the burner control valve, the forming tool actuator 326, the measurement device 360, the converter drive system, etc.) via any wired or wireless communication path. The computer-usable or computer-readable storage medium or memory module 406 may be any medium that can contain, store, communicate, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or apparatus.

[0204] The computer usable or computer readable storage medium or memory module 406 may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared or semiconductor system, device, apparatus or propagation medium. More specific examples (non-exhaustive list) of computer readable storage medium or memory module 406 would include the following: an electrical connection with one or more wires, a portable computer floppy disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, and a portable compact disk read-only memory (CD-ROM). Note that the computer usable or computer readable storage medium or memory module 406 may even be paper or another medium suitable for printing a program thereon, as the program may be electronically captured, for example via optical scanning of the paper or other medium, and then, if necessary, compiled, interpreted or otherwise processed in a suitable manner, and then stored in a computer memory.

[0205] Computer readable storage medium or memory module 406 may include machine readable and executable instructions 408 for performing the operations of the present disclosure. For ease of development, machine readable and executable instructions 408 may include computer program code that can be written in a high-level programming language (such as C or C++). In addition, the computer program code for performing the operations of the present disclosure may also be written in other programming languages, such as but not limited to interpreted languages. Some modules or routines may be written in assembly language or even microcode to enhance performance and / or memory usage. However, the software embodiments of the present disclosure do not rely on the implementation of a specific programming language. It should be further understood that any or all functions in the program modules may also be implemented by discrete hardware components, one or more application specific integrated circuits (ASICs) or programmed digital signal processors or microcontrollers. Example

[0206] The following examples illustrate the operation of the disclosed systems and methods for making a plurality of glass articles from a glass tube in a converter.The following examples are not intended to limit the scope of the present disclosure.

[0207] Example 1: Construction of the converter operation model

[0208] Example 1 below illustrates the disclosed system and method for building an operational model of a converter and preliminarily setting up a converter 100 for converting a glass tube into a glass product. Since hundreds of different process parameters can be adjusted on a typical converter, for purposes of illustration and brevity, the examples herein only involve a subset of these process parameters. The glass tubes in these examples are aluminosilicate glass tubes, such as those manufactured and sold by Corning Incorporated. Glass. The aluminosilicate glass tubes may be further processed after conversion by annealing and / or ion exchanging the glass tubes. Although aluminosilicate glass is used in the examples, the effectiveness of the systems and methods disclosed herein is not dependent on the type or composition of the glass.

[0209] The glass tube is converted into a glass product using a converter. The converter used includes 18 processing stations in the main loop. Each process parameter can have a preset value for a specific type or size of glass product to be produced. The construction of a condition set can start with the preset value as a starting point.

[0210] Burner settings

[0211] The method of the present disclosure is first used to construct an operating setting for three process parameters related to the burner setting of the converter 100. The three process parameters of Example 1 are the burner position in the first heating station upstream of the forming station, the burner position in the second heating station placed between the first heating station and the forming station, and the rotation speed (chuck speed) of the holder 130. The "Design of Experiments" statistical analysis software constructed a subset of 18 condition sets for modeling these three process parameters. Table 2 provides the subset of 18 condition sets. Table 2

[0212] The converter 100 was run in each condition set in Table 2 to produce 60 glass products in each condition set. Five different dimensions / angles were measured for each glass product produced at each condition set. Each glass product was assigned an identifier / part number and the measured dimensions / angles and condition set associated with each glass product in a relational database. Fig.12 , graphically depicts data for one of the dimensions measured for the glass article of Example 1 as a function of part number. Fig.12 As shown, the data points are grouped by the set of conditions used to manufacture the glass article 103.

[0213] Then use The statistical analysis software analyzes the data and condition sets for each glass product's measured dimension / angle to develop multiple operating models relating process parameters to each measured dimension / angle. Fig.14 For ease of illustration, a graphical representation of the operating model constructed from the data in Example 1 is provided. It should be appreciated that the control system 402 uses an empirical mathematical expression of the model rather than a graphical representation to determine the initial operating settings of the converter.

[0214] Forming station settings

[0215] Next, the method of the present disclosure is used to construct an operational model and an initial operating setting for five process parameters related to a forming setting, which involves a third heating station and a forming station immediately downstream of the third heating station. The five process parameters of the forming station setting of Example 1 include the relative burner gas flow rate in the third heating station, the burner position in the third heating station, the position of the first forming tool in the forming station, the end time of contact between the first forming tool and the glass tube, and the end time of contact between the second forming tool in the forming station and the glass tube. In this example, the position of the second forming tool is completely dependent on the position of the first forming tool based on the first principle. Therefore, only the position of the first forming tool is modeled. The relative burner gas flow rate is the fuel gas flow rate delivered to the burner divided by the reference burner gas flow rate. Use The "Design of Experiments" statistical analysis software constructed a subset of 24 condition sets for modeling these five process parameters. The subset of 24 condition sets for the forming station settings of Example 1 is provided in Table 3. Table 3

[0216] The converter 100 was run at each of the condition sets in Table 3 to produce 60 glass products in each condition set. Two dimensions and two appearance attributes were measured for each glass product produced at each condition set. In addition, the overall desirability of each glass product was determined from the measurements of the two dimensions and two appearance attributes. Each glass product was assigned a unique identifier / part number, and the measured attributes and condition set were associated with each glass product in a relational database. Reference Fig.15 , graphically depicts data for a dimension measured for the glass article of Example 1 as a function of part number. Fig.15 As shown, the data points are grouped by the set of conditions used to manufacture the glass article 103.

[0217] Then use Statistical analysis software analyzes the data and condition sets for each glass product's measured dimensions / angles to develop multiple operating models relating process parameters to each measured dimension, measured appearance attributes, and overall expectations. Fig.16 , for ease of illustration, a graphical representation of the operational model constructed from the data in Example 1 is provided.

[0218] Example 2: Feedback Control Based on Model Predictive Control Framework

[0219] In Example 2, an operating model is constructed for the converter and integrated into the target control function of Equation 4, which is then used to provide feedback control of the converter 100. For Example 2, glass vials are produced from glass tubes using the converter having 18 processing stations on the main turret described in Example 1. The glass tubes are the same as those in Example 1.

[0220] In the first step of Example 2, an operational model is constructed through the "Experimental Design" process. Considering the 13 attributes of the glass vial, an operational model is constructed for 9 process parameters. The modeled process parameters include the vertical position of the forming tool in the first forming station, the horizontal position of the forming tool in the first forming station, the airflow of the burner in the first heating station before the first forming station, the vertical position of the burner in the first heating station, the vertical position of the burner in the second heating station after the first forming station, the vertical position of the pin forming tool in the second forming station after the second heating station, the working position of the BB forming tool in the second forming station, the working position of the IB wheel forming tool in the second forming station, and the working position of the OB wheel forming tool in the second forming station. The attributes of the glass tube measured for each condition set include the maximum outer diameter of the flange, the minimum outer diameter of the flange, the maximum inner diameter of the flange, the minimum inner diameter of the flange, the maximum flange height, the minimum flange height, the maximum top height, the minimum top height, the average eccentricity, the average lower flange angle, the average top flange angle, the average shoulder angle, and the average shoulder radius.

[0221] As described in Example 1, the converter is run under each condition set, and the measured attributes and process parameter settings for each vial are associated and stored in a relational database using a unique identifier. Once all condition sets have been run, the converter is then used The statistical analysis software analyzes the data to construct a plurality of operating models that relate the process parameters to each measured attribute of the glass vial. In Example 2, the operating model is a linear operating model of the form of Equation 1 to simplify the integration of the operating model with the target control function. Now referring to Fig.17 , the normalized values ​​of flange outer diameter, flange inner diameter, top height, and shoulder angle of the glass article derived from the measured data are plotted against the predicted values ​​of these properties using the operating model and process parameter settings. Fig.17 As shown, the linear operational model constructed in Example 3 provides good predictions of the attributes, as indicated by the high R value greater than 0.9. 2 values ​​and very low P values ​​less than 0.001.

[0222] As in Example 2, the converter is operated without feedback control for a period of five months, during which time machine wear and other long-term changes result in at least some additional mismatch between the operating model and actual operation of the converter. In step 2 of Example 2, after five months, the original operating model is integrated into the target control function of Equation 4.

[0223] Once the operating model is integrated into the target control function, multiple iterations of the control method of the present disclosure are performed to provide feedback control of the converter. Initially, the process parameters are set to initial operating settings determined according to the operating model. For each iteration of the control method, the converter is operated at the current settings of the nine process parameters previously discussed in Example 2. 13 properties are measured for each glass product produced during operation of the converter. The measured values ​​of the properties and operating settings of the nine process parameters for each of the produced glass products are saved in a database. For each iteration of the control method, the measured values ​​of the properties and settings of the process parameters corresponding to a number of vials that consume the entire length of the glass tube in each holder (e.g., 18 holders) of the converter are recorded.

[0224] The data including the measured values ​​of the attributes and process settings are then processed to remove outliers and calculate the statistical characteristics of the distribution of the measured values ​​of each attribute. In Example 2, the statistical characteristic is the average value of the measured values ​​of each attribute measured. The measured values ​​of the attributes, the target values ​​of the attributes, and the average values ​​of the current settings of the process parameters are then substituted into the target control function of Equation 4 for Attrib measured 、Attrib target During data processing and solving of the target control function, the converter is operated under the previous run settings to maintain a consistent thermal environment for the converter.

[0225] The objective control function is then solved for an updated set of process parameters (e.g., Act(k)) that minimizes the objective control function. The process parameters of the converter are then changed to the updated set of process parameters, and the control method is repeated. In Example 2, the control method is repeated four times.

[0226] Reference now Fig.18 , the sum of squared errors (eg, the value of the minimized objective control function) is plotted as a function of the number of iterations of the control method. Reference numeral 1802 refers to the objective control function value of Example 2. Fig.18 As shown, the largest change occurs in the first iteration. Therefore, the model predictive control framework disclosed herein may be able to compensate for the mismatch between the operating model and the actual operation of the converter in as little as one iteration of the control method. Fig.18 The variation in the target control function values ​​for interactions 2-4 is explained by the natural variability in the conversion process.

[0227] Reference now Fig.19, showing the normalized mean of each of the 13 property values ​​measured in Example 3 as a function of the iteration of the control method. Overall, the property values ​​converged over four iterations of the control method, further indicating the effectiveness of the model predictive control framework disclosed herein.

[0228] Reference now Fig. 20 and Fig.21 , the normalized measurements of the 13 properties considered in Example 2 are plotted as a function of time during 4 iterations of the control method. Fig. 20 In FIG. 1 , normalized values ​​of the minimum flange outer diameter 2002, the maximum flange outer diameter 2004, the minimum flange inner diameter 2012, the maximum flange inner diameter 2014, the minimum flange height 2022, the maximum flange height 2024, the minimum top height 2032, and the maximum top height 2034 are graphically depicted. Fig. 20 As shown, at the beginning of iteration zero (k-0), the maximum flange inner diameter 2014 and the maximum top height 2034 of the glass vial are both greater than the upper specification limit (USL) of these parameters. As time passes in each iteration, the process parameters are adjusted to change the inner diameter and the top height so that the maximum flange inner diameter 2014 and the maximum top height 2034 fall back to the acceptable range between the upper specification limit (USL) and the lower specification limit (LSL). The corresponding adjustments can be seen in the minimum flange outer diameter 2002, the maximum flange outer diameter 2004, the minimum flange inner diameter 2012, and in Fig. 20 The flange height can also be observed in .

[0229] refer to Fig.21 , graphically depicts normalized values ​​of average bottom flange angle 2102, average top flange angle 2104, average shoulder angle 2106, and average shoulder radius 2108. Fig.21 As shown, at the beginning of iteration zero (k-0) period, the average shoulder angle 2106 is below the lower specification limit (LSL) of the average shoulder angle. As time passes in each iteration, the process parameters are adjusted to change the shoulder angle so that the average shoulder angle 2106 remains within an acceptable range between the USL and the LSL. Fig. 20 and 21 It is shown that the model predictive control framework and control method disclosed in this application can provide feedback control to the converter to identify out-of-specification attributes of the glass product and restore those out-of-specification attributes to within acceptable specifications and maintain them within acceptable specifications.

[0230] Example 3: Further introducing feedback control into the mismatched model predictive control framework

[0231] In Example 3, the operating model from Example 2 is incorporated into the target control function of Equation 4. The resulting target control function is then used in a model predictive control framework to provide feedback control to a converter different from the converter used to generate the initial operating model. The resulting target control function is then used in a model predictive control framework to provide feedback control for the converter used to generate the initial operating model. The converter of Example 3 has the same number and arrangement of processing stations as the converter of Example 2. Despite having the same number and arrangement of processing stations, the use of different converters in Example 3 is expected to introduce even more errors and mismatches between the operating model of the converter of Example 2 and the actual operation of the converter of Example 3. As in Example 3, the use of an operating model from one converter in the feedback control of different converters having the same number and configuration of processing stations indicates that the model predictive control framework described herein can compensate for the significant mismatch between the operating model and actual operation of the converter.

[0232] The control method of Example 3 is the same as described in Example 2. Fig.18 , reference numeral 1803 indicates the value of the target control function of Example 3 which varies with the number of iterations of the control method. Fig.18 As shown, the model predictive control framework disclosed herein is able to compensate for the mismatch between the operating model and the actual operation of the converter in as little as one iteration of the control method, even if the operating model is constructed on a completely different conversion machine. Therefore, the model predictive control framework disclosed herein is robust enough to account for significant errors in the operating model without losing the ability to control the conversion process.

[0233] Although various embodiments of converters and systems and methods for providing feedback control of converters for producing a plurality of glass articles from a glass tube have been described herein, it should be understood that each of these embodiments and techniques are contemplated for use alone or in combination with one or more embodiments and techniques.

[0234] It is obvious to those skilled in the art that various modifications and changes can be made to the embodiments described herein without departing from the spirit and scope of the subject matter claimed. Therefore, it is intended that the specification covers various modifications and changes of the embodiments described herein, as long as these modifications and changes fall within the scope of the attached claims and their equivalents.

Claims

1. A method for controlling a converter for producing a glass product from a glass tube, the method comprising: operating a converter to produce a plurality of glass articles from a plurality of glass tubes, wherein the converter includes a plurality of processing stations, and operating the converter includes translating the glass tubes to sequentially pass through each of the plurality of processing stations; providing a target value for at least one property of the plurality of glass articles or the plurality of glass tubes during or after the conversion; measuring the at least one property of the plurality of glass articles or the plurality of glass tubes during or after conversion; recording a setting of at least one process parameter of the converter associated with the at least one property to generate a data set comprising a measured value of the at least one property and the setting of the at least one process parameter of the converter; processing said data set to produce statistical characteristics of a distribution of said measured values ​​of said at least one attribute; determining an updated setting for each of the at least one process parameter based on the statistical characteristic of the distribution of the at least one property measured, the target value for the at least one property, and the setting of the at least one process parameter, wherein the updated setting for the at least one process parameter is a value of the setting that minimizes an objective control function for the at least one property; as well as Each of the at least one process parameter of the converter is adjusted to the updated setting.

2. The method of claim 1 , further comprising repeatedly measuring the at least one property, recording the setting of each of the at least one process parameter, processing the data set, determining the updated setting of each of the at least one process parameter, and adjusting each of the at least one process parameter until the updated setting of each of the at least one process parameter converges.

3. The method of claim 1 , wherein processing the data set comprises: removing anomalous data points from said data set of said measured values ​​of said at least one attribute; After removing the anomalous data points, the statistical characteristic of the distribution of the measured values ​​of the at least one attribute from the data set is calculated.

4. The method of claim 3, wherein: The statistical property of the distribution of the data set is the mean, median, range, standard deviation, variance, or a combination of these.

5. The method of claim 1, further comprising: Providing a specification range for each of the at least one attribute, wherein the specification range for an attribute comprises: a minimum value for a property below which the glass article is considered non-compliant; and a maximum value for the attribute, above which the glass article is considered to be out of specification; and An attribute weighting factor is applied to each of the at least one attribute in the objective control function based on a spread within the specification range for each of the at least one attribute.

6. The method of claim 5, further comprising determining the attribute weighting factor for each of the at least one attribute from the specification range.

7. The method of claim 6, comprising determining the process capability index C for each of the at least one attribute from the specification range. pk , and the process capability index C based on the at least one attribute pk The attribute weighting factor is determined for each of the at least one attribute.

8. The method of claim 1, further comprising: constructing a penalty factor for each of the at least one process parameter; as well as The penalty factor is applied to the at least one process parameter in the objective control function. for each process parameter in the number, wherein the penalty is operated to reduce the magnitude of the variation of the process parameter having a greater impact on one or more of the at least one attribute.

9. The method of claim 8, further comprising: Repeating the method of claim 8 for multiple iterations; identifying a divergence or oscillation of the updated settings for one or more of the at least one process parameter, the divergence or oscillation indicating a reduction in the ability to control one or more aspects of the converter; as well as The penalty factor of one or more of the at least one process parameter is adjusted, wherein adjusting the penalty factor reduces the magnitude of changes made to the one or more process parameters in each iteration of the method, thereby tending to reduce divergence or oscillation of the update setting.

10. The method of claim 9, wherein: The divergence is indicated by oscillations or a continuous increase in the target control function at each iteration of the method.

11. The method of claim 1, further comprising: providing a maximum setting and a minimum setting for each of the at least one process parameter; as well as The updated setting of each of the at least one process parameter is maintained within a range between the minimum setting and the maximum setting of the process parameter.

12. The method of claim 1, wherein: The objective control function includes the mean square error cost function from the following equation: J(k)=(G*Act(k)+Attrib measured (k)-G*Act(k-1)-Attrib targ ) T Q T Q(G*Act(k)+Attrib measured (k)-(G*Act(k-1))-Attrib targ )+(Act(k)-Act(k-1)) T R T R(Act(k)-Act(k-1)) in: J(k) is the mean square error cost function as a function of k; k is an integer representing the current iteration that minimizes the mean square error cost function; G is a product of the change of each process parameter in the at least one process parameter. The sensitivity factor moment of the degree of change of each attribute in the at least one attribute is Array; Attrib measured (k) is a vector of said statistical characteristics of said distribution of said measured values ​​of said at least one attribute during iteration k; Act(k) is the setting of the process parameters at iteration k; Act(k-1) is the setting of the process parameters at iteration k-1; Attrib targ is a vector of said target values ​​for each of said at least one attribute; Q T Q is a symmetric weighting matrix of attribute weighting factors for the error between the measured value of the attribute and the target value of the attribute; R T R is a symmetric weighted matrix of penalty factors for said variation of said at least one process parameter.

13. The method of claim 12, further comprising constructing the target control function.

14. The method according to claim 13, characterized in that Constructing the target control function includes: constructing at least one model associated with a predicted value of the at least one property for each setting of the at least one process parameter, wherein the at least one model comprises an expression wherein the predicted value of the at least one property is a sum of at least one term dependent on the setting of the at least one process parameter and an offset constant; providing an initial mean squared error cost function that is a function of the predicted value for each of the at least one attribute, the target value for each of the at least one attribute, and the setting for each of the at least one process parameter; substituting the at least one model into the initial mean squared error cost function for the predicted value of the at least one attribute; solving the at least one model of the offset constant to produce an offset constant function, wherein solving the at least one model of the offset constant comprises replacing the statistical characteristics of the measured values ​​of each of the at least one attribute with the predicted values ​​of each of the at least one attribute; and The offset constant function is used to replace the offset constant in the initial mean square error cost function to generate the target control function.

15. The method of claim 14, wherein constructing the at least one model comprises performing a "design of experiments" process, deriving the at least one model from first principles, or a combination of these to produce the at least one model.

16. The method of claim 14, further comprising periodically rebuilding the at least one model to account for process variations over time or in response to known variations in operation of the converter.

17. The method of claim 14, further comprising applying an attribute weighting factor for each of the at least one attribute to one or more terms of the objective control function.

18. The method of claim 14, further comprising applying a penalty factor for each of the at least one process parameter to one or more terms of the objective control function.

19. The method of claim 1, wherein determining updated settings for each of the at least one process parameter further comprises subjecting the at least one process parameter to a constraint comprising a maximum value and a minimum value for the at least one process parameter.

20. The method of claim 1, comprising: providing target values ​​for a plurality of properties of the plurality of glass articles, the plurality of glass tubes, or both; measuring a plurality of properties of the plurality of glass articles, the plurality of glass tubes, or both for a plurality of glass articles; recording settings of a plurality of process parameters of the converter associated with the plurality of properties to generate a plurality of data sets, each of the plurality of data sets comprising a measured value of each of the plurality of properties of the converter and the setting of each of the plurality of process parameters during the time period; processing each of the plurality of data sets to generate statistical characteristics of a distribution of each of the plurality of attributes; determining the updated setting for each of the plurality of process parameters based on the statistical characteristics of the distribution of each of the plurality of attributes, the target value for each of the plurality of attributes, and the setting for each of the plurality of process parameters, wherein the updated setting for the plurality of process parameters is a value of the updated setting that minimizes the objective control function; as well as For each of the plurality of process parameters, each of the plurality of process parameters of the converter is adjusted to the updated setting.

21. The method of claim 1, further comprising displaying a user interface on a display.

22. The method of claim 21, further comprising receiving one or more user inputs from the user interface, and changing the updated setting of the at least one process parameter based on the one or more user inputs.

23. The method of claim 1, wherein the at least one property comprises one or more properties of the converted glass article, one or more properties of one or more features of the partially formed glass article at the working end of the glass tube, one or more properties of the glass tube, one or more properties of the preform at the working end of the glass tube, or a combination of these.

24. A system for producing a plurality of glass articles from a plurality of glass tubes, the system comprising: A converter, comprising: a plurality of holders, each of the holders being operable to hold the glass tube and rotate the glass tube about a central axis of the glass tube; A plurality of processing stations, the plurality of processing stations comprising at least one heating station, at least one forming station and at least one separating station; at least one measuring device operable to measure the or both to produce one or more properties of said glass article; The converter is operable to translate the glass tubes in sequence. passing through each of the plurality of processing stations to produce the plurality of glass articles; and a control system communicatively coupled to the converter, the control system comprising one or more processors, one or more memory modules communicatively coupled to the one or more processors, and machine-readable and executable instructions stored on the one or more memory modules that, when executed by the one or more processors, cause the control system to automatically: measuring at least one property of the glass article, the glass tube, or both with the at least one measuring device; Record the converter associated with the at least one attribute at least one process parameter of the converter to generate a data set including a measured value of the at least one property and the setting of each of the at least one process parameter of the converter; processing said data set to produce statistical characteristics of a distribution of said measured values ​​of said at least one attribute; determining the updated setting for each of the at least one process parameter based on the statistical characteristics of the distribution of measured values ​​of the at least one property, the target value for the at least one property, and the setting of the at least one process parameter, wherein the updated setting for the at least one process parameter is a value of the setting that minimizes an objective control function for the at least one property; and The at least one process parameter of the converter is adjusted to the updated setting.

Images