Methods and systems to detect process equipment issues

Abstract

There is provided a method for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine. Each article includes one or more article sensors configured to generate article sensor data indicating processing of that article by the machine. The method includes: receiving, at a processor, the article sensor data from the one or more article sensors; determining, by the processor, at least one process signature based on the received article sensor data, the at least one process signature including process and / or timing information associated with processing an article of the one or more articles; detecting, by the processor, the process issue based on a comparison of the at least one process signature with one or more reference process signatures; and generating, by the processor, an output recommending a corrective action to address the detected process issue.

Description

Title: METHODS AND SYSTEMS TO DETECT PROCESS EQUIPMENT ISSUESFIELD

[0001] The embodiments described herein generally relate to methods and systems to detect process equipment issues, and in particular to detect process equipment issues that impact processing of an article during a production process.BACKGROUND

[0002] The following is not an admission that anything discussed below is part of the prior art or part of the common general knowledge of a person skilled in the art.

[0003] A production line generally involves conveying articles to different equipment or machines that perform processing operations on the articles. An article may undergo multiple processing operations during the production process. Process equipment issues can impact the processing of an article during the production process, for example, faulty processing being performed by a machine resulting in the article not meeting product specifications. Undetected process equipment issues can result in article quality reduction, production efficiency reduction and / or production cost increases.SUMMARY

[0004] This summary is intended to introduce the reader to the more detailed description that follows and not to limit or define any claimed or as yet unclaimed invention. One or more inventions may reside in any combination or sub-combination of the elements or process steps disclosed in any part of this document including its claims and figures.

[0005] The various embodiments described herein generally relate to methods and systems to detect process equipment issues. The process equipment issues may be detected during a production process of the article. Further, the disclosed methods and systems can generate an output recommending a corrective action to address the detectedprocess issue. This can enable article quality improvement, production efficiency improvement and / or production cost reduction.

[0006] In accordance with an aspect of this disclosure, there is provided a system for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine. The system includes the one or more articles and at least one processor. Each article includes one or more article sensors configured to generate article sensor data indicating processing of that article by the machine. The at least one processor is configured to: receive the article sensor data from the one or more article sensors; determine at least one process signature based on the received article sensor data, the at least one process signature including process and / or timing information associated with processing an article of the one or more articles; detect the process issue based on a comparison of the at least one process signature with one or more reference process signatures; and generate an output recommending a corrective action to address the detected process issue.

[0007] In accordance with another aspect of this disclosure, there is provided a method for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine. Each article includes one or more article sensors configured to generate article sensor data indicating processing of that article by the machine. The method includes: receiving, at a processor, the article sensor data from the one or more article sensors; determining, by the processor, at least one process signature based on the received article sensor data, the at least one process signature including process and / or timing information associated with processing an article of the one or more articles; detecting, by the processor, the process issue based on a comparison of the at least one process signature with one or more reference process signatures; and generating, by the processor, an output recommending a corrective action to address the detected process issue.

[0008] In accordance with another aspect of this disclosure, there is provided a non-transitory computer readable medium storing thereon program instructions that are executable by a processor for performing a method for detecting a process issue associatedwith a machine that is configured to process one or more articles introduced into the machine. Each article includes one or more article sensors configured to generate article sensor data indicating processing of that article by the machine. The method includes: receiving, at the processor, the article sensor data from the one or more article sensors; determining, by the processor, at least one process signature based on the received article sensor data, the at least one process signature including process and / or timing information associated with processing an article of the one or more articles; determining, by the processor, the process issue based on a comparison of the at least one process signature with one or more reference process signatures; and generating, by the processor, an output recommending a corrective action to address the detected process issue.

[0009] It will be appreciated that the aspects and embodiments may be used in any combination or sub-combination. Further aspects and advantages of the embodiments described herein will appear from the following description taken together with the accompanying drawings.BRIEF DESCRIPTION OF THE DRAWINGS

[0010] For a better understanding of the embodiments described herein and to show more clearly how they may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings which show at least one exemplary embodiment, and in which:

[0011] FIG. 1 is a schematic top view of an example embodiment of a system for tracking processing of one or more articles by multiple processing heads of a machine;

[0012] FIG. 2A is an example graph of sealing force measured by article sensors of the system of FIG. 1 versus time during processing of articles by processing heads of a rail capper;

[0013] FIG. 2B is an example graph of sealing force measured by article sensors of the system of FIG. 1 versus time during processing of articles by processing heads of a capping machine with multiple spinning rollers;

[0014] FIG. 2C is an example graph of sealing force measured by an article sensor of the system of FIG. 1 versus time during processing of an article by a processing head of a rotary capper;

[0015] FIG. 3 is a block diagram of an example control system of the system of FIG.1;

[0016] FIG. 4 is a flowchart of an example method for tracking processing of one or more articles by multiple processing heads of the machine of FIG. 1 ;

[0017] FIG. 5A is a perspective view of an example embodiment of an article of the system of FIG. 1;

[0018] FIG. 5B is a perspective view of another example embodiment of an article of the system of FIG. 1 ; and

[0019] FIG. 6 is a flowchart of an example method for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine.

[0020] The skilled person in the art will understand that the drawings, described below, are for illustration purposes only. The drawings are not intended to limit the scope of the applicants' teachings in any way. Also, it will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Further, where considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements.DESCRIPTION OF VARIOUS EMBODIMENTS

[0021] It will be appreciated that numerous specific details are set forth in order to provide a thorough understanding of the exemplary embodiments described herein. However, it will be understood by those of ordinary skill in the art that the embodiments described herein may be practiced without these specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not toobscure the embodiments described herein. Furthermore, this description is not to be considered as limiting the scope of the embodiments described herein in anyway, but rather as merely describing the implementation of the various embodiments described herein.

[0022] It should be noted that terms of degree such as "substantially", "about" and "approximately" when used herein mean a reasonable amount of deviation of the modified term such that the end result is not significantly changed. These terms of degree should be construed as including a deviation of the modified term if this deviation would not negate the meaning of the term it modifies.

[0023] In addition, as used herein, the wording “and / or” is intended to represent an inclusive-or. That is, “X and / or Y” is intended to mean X or Y or both, for example. As a further example, “X, Y, and / or Z” is intended to mean X or Y or Z or any combination thereof.

[0024] The terms "including," "comprising" and variations thereof mean "including but not limited to," unless expressly specified otherwise. A listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a," "an" and "the" mean "one or more," unless expressly specified otherwise.

[0025] As used herein and in the claims, two or more elements are said to be “coupled”, “connected”, “attached”, or “fastened” where the parts are joined or operate together either directly or indirectly (i.e. , through one or more intermediate parts), so long as a link occurs. As used herein and in the claims, two or more elements are said to be “directly coupled”, “directly connected”, “directly attached”, or “directly fastened” where the element are connected in physical contact with each other. None of the terms “coupled”, “connected”, “attached”, and “fastened” distinguish the manner in which two or more elements are joined together.

[0026] The terms "an embodiment," "embodiment," "embodiments," "the embodiment," "the embodiments," "one or more embodiments," "some embodiments," and "one embodiment" mean "one or more (but not all) embodiments of the present invention(s)," unless expressly specified otherwise.

[0027] The embodiments of the systems and methods described herein may be implemented in hardware or software, or a combination of both. These embodiments maybe implemented in computer programs executing on programmable computers, each computer including at least one processor, a data storage system (including volatile memory or non-volatile memory or other data storage elements or a combination thereof), and at least one communication interface. For example and without limitation, the programmable computers may be a server, network appliance, embedded device, computer expansion module, a personal computer, laptop, personal data assistant, cellular telephone, smartphone device, tablet computer, a wireless device or any other computing device capable of being configured to carry out the methods described herein.

[0028] In some embodiments, the communication interface may be a network communication interface. In embodiments in which elements are combined, the communication interface may be a software communication interface, such as those for interprocess communication (IPC). In still other embodiments, there may be a combination of communication interfaces implemented as hardware, software, and combination thereof.

[0029] Program code may be applied to input data to perform the functions described herein and to generate output information. The output information is applied to one or more output devices, in known fashion.

[0030] Each program may be implemented in a high-level procedural or object oriented programming and / or scripting language, or both, to communicate with a computer system. However, the programs may be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Each such computer program may be stored on a storage media or a device (e.g. , ROM, magnetic disk, optical disc) readable by a general or special purpose programmable computer, for configuring and operating the computer when the storage media or device is read by the computer to perform the procedures described herein. Embodiments of the system may also be considered to be implemented as a non-transitory computer-readable storage medium, configured with a computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner to perform the functions described herein.

[0031] Furthermore, the system, processes and methods of the described embodiments are capable of being distributed in a computer program product comprising a computer readable medium that bears computer usable instructions for one or more processors. The medium may be provided in various forms, including one or more diskettes, compact disks, tapes, chips, wireline transmissions, satellite transmissions, internet transmission or downloadings, magnetic and electronic storage media, digital and analog signals, and the like. The computer useable instructions may also be in various forms, including compiled and non-compiled code.

[0032] In the description herein, the term “article” is used to refer to an object that is being manufactured, produced, packaged, transported, and / or distributed etc. As used herein, the term “article” may refer to a product and / or a package containing a product. An “article” may refer to (i) a product that is intended to be received / used by a retailer, distributor and / or end-user, and / or (ii) the entire package that may be received by a retailer, distributor and / or end-user including external packaging and / or containers and the goods / products contained therein. Some non-limiting examples of articles include pharmaceutical vials, drink bottles, food cans and other containers, etc. In the description herein, an “article” may refer to an actual package and / or product and / or a replica of the actual package and / or product. A replica article can be a test article that is used to monitor the processing performance of the machines. A replica article may include one or more article sensors that generate sensor data indicating the processing performance of the machines.

[0033] In the various embodiments disclosed herein, during a production process, an article is conveyed to a machine that performs a processing operation on the article. The machine may include multiple processing heads and each article may be processed by any one of the multiple processing heads. The article includes one or more article sensors that generate article sensor data indicating processing of the article. The article sensor data can be used to determine, for example, whether the article has been correctly processed according to target process criteria. If it is determined that an issue arose with the processing of an article, corrective action may be performed. The corrective action may be performed with higher efficiency and / or lower cost if it can be identified which of the multiple processing heads processed the article resulting in the issue.

[0034] In the various embodiments illustrated herein, the machine may have a large number of processing heads. The articles and / or processing heads may move at large relative speeds. This may create challenges for a human operator to manually track processing of articles by the machine and to accurately identify the specific processing head that processed a given article. The tracking accuracy may be improved by reducing the processing throughput, but this may also reduce production efficiency and / or increase production cost.

[0035] The disclosed systems and methods can enable automatic tracking of the processing of the article and thereby enable automatic and accurate identification of the specific processing head that processed a given article. The disclosed systems and methods can determine a process time for each article based on the article sensor data. For example, a process time may be determined for twelve articles processed by a machine with twelve processing heads. The disclosed systems and methods can receive position sensor data from a position sensor system indicating position of the multiple processing heads at a position capture time. For example, the position sensor data may indicate the position of each of the twelve processing heads at a position capture time. Based on a timing relationship between the process time and the position capture time, the disclosed systems and methods can determine the processing head that processed each article and generate a corresponding process tracking output.

[0036] In some embodiments, article sensor data may be collected from multiple processed articles. The article sensor data of any given article may be compared with the article sensor data of the other articles to detect an issue / problem related to processing of the article. If an issue / problem is detected, the process tracking output may be used to identify the processing head that processed the article having the issue / problem. This can enable corrective action to be performed for that processing head. The disclosed systems and methods can thereby improve production efficiency and / or reduce production cost by identifying specific processing heads that require corrective action. In some embodiments, the comparison of article sensor data collected from multiple processed articles may be further used to identify a root cause for the detected issue. The root cause identification may be used to recommend a specific correction action to address the issue.

[0037] Referring now to FIG. 1 , shown therein is a schematic top view of an example embodiment of a system 100 for tracking processing of one or more articles by multiple processing heads of a machine 10. In the illustrated example, system 100 includes multiple articles 110a-110h (also collectively referred to herein as article 110), a position sensor system 120, and a control system 130.

[0038] Machine 10 can be any suitable processing machine. For example, machine 10 may be a capping machine, a filling machine, a labeling machine, etc. Machine 10 may include any suitable number of processing heads. For example, in one example, machine 10 may have 8 to 16 processing heads. In other examples, machine 10 may have fewer than 8 processing heads or may have greater than 16 processing heads. In the illustrated example, machine 10 includes 8 processing heads 20a-20h (also collectively referred to herein as processing heads 20). Each processing head 20a-20h may process an article that enters machine 10. For example, in a capping machine, each article entering machine 10 may be capped by any one of the processing heads 20a-20h.

[0039] Machine 10 may have any suitable design to enable articles 110 to enter and exit machine 10. In the illustrated example, machine 10 includes an entry conveyor 30 and an exit conveyor 40. Machine 10 may include a moveable portion 50 that includes processing heads 20a-20h. Moveable portion 50 may rotate relative to the stationary portion of machine 10 to move processing heads 20a-20h to receive incoming articles 110 from entry conveyor 30, and further move processing heads 20a-20h towards exit conveyor 40. Processing heads 20a-20h may process received articles 110 during movement between entry and exit.

[0040] Machine 10 may have any suitable design for processing multiple articles 110 using multiple processing heads 20. For an example capping processing, machine 10 may be a rotary capper or a rail capper where the article is rotated during processing or machine 10 may include spinning rollers where the article is not rotated during capping.

[0041] Reference is now made to FIGS. 5A and 5B showing perspective views of example embodiments of articles 110. Each article 110 may include one or more sensors 160 configured to generate article sensor data indicating processing of that article by the machine. Any suitable article sensors may be used based on the processing performed onthe article. For example, the article sensors may include force sensors, fill sensors etc. In some embodiments, an article sensor may include a combination of multiple sensors.

[0042] FIG. 5A shows an example embodiment of article 110 that is a pharmaceutical vial. In the illustrated example, article 110 includes a device housing section 502a, and a flange 550 to which a cap, such as a crimp cap, may be applied. The flange 550 may be defined by the combination of a closing member 552 and a capping section 520. The device housing section 502a can be configured to house a force measurement sensor 160a configured to measure forces applied to the flange 550 of article 110.

[0043] FIG. 5B shows an example embodiment of article 110 that is a drink bottle. In the illustrated example, article 110 includes a device housing section 502b. The device housing section 502b can be configured to house a fill sensor 160b configured to detect fill level of article 110.

[0044] Referring back to FIG. 1 , each article 110 may include an integrated processor (not shown in FIG. 1). In some embodiments, the integrated processor may process the article sensor data to determine process times and transmit the processed article sensor data and / or determined process times to control system 130. In some embodiments, the integrated processor may perform pre-processing of the article sensor data. For example, the integrated processor may pre-process the article sensor data to filter noise and transmit the pre-processed data to control system 130. In other embodiments, the integrated processor may transmit unprocessed article sensor data generated by article sensors 160 to control system 130.

[0045] Reference is now made to FIGS. 2A and 2B. FIG. 2A shows an example graph 200a of sealing force measured by article sensors versus time during processing of articles by processing heads of a rail capper. FIG. 2B shows an example graph 200b of sealing force measured by article sensors versus time during processing of articles by processing heads of a capping machine with multiple spinning rollers. In the illustrated example, the measured data is related to sealing force. In other examples, the measured data can include any suitable measurements, e.g., a pressure measurement, an impact / shock measurement, a liquid fill value, a weight, a position / orientation etc.

[0046] Graphs 200a and 200b each include multiple sealing force curves, each sealing force curve including the measured sealing force values versus time for at least a portion of time between the article entering the machine (for being processed) and the article exiting the machine (after being processed). Graphs 200a and 200b may each be generated by aligning multiple sealing force curves along a common time axis. For example, each sealing force curve in example graphs 200a and 200b may be generated by plotting measured sealing force starting at a time t = 0 when the measured sealing force exceeds a threshold sealing force. In the illustrated example, graphs 200a and 200b are generated using a threshold sealing force of 10 lbs. In other examples, different threshold sealing forces may be used. For example, the threshold sealing force may be selected to be sufficiently large to filter out noise and / or pre-processing handling of the article. As another example, the threshold sealing force may be selected to be sufficiently small to capture a larger portion of the processing of the articles by the machine. As shown in graphs 200a and 200b, the sealing force may vary as the article is processed. In other examples, a different criterion may be used to align multiple sealing force curves along the common time axis. For example, the multiple sealing force curves may be aligned at a process end time when the measured sealing force drops below a threshold sealing force.

[0047] During processing of articles 110, each article may enter machine 10 at entry conveyor 30 and be picked up by one of multiple processing heads 20. For example, article 110d may be picked up and processed by processing head 20b. Initially, the sealing force measured by the article sensors of article 110d may be in a range between 0 and the threshold sealing force. The sealing force may reach the threshold sealing force (e.g., 10lbs) when the moving processing head 20b is at a position 60 and the article sensor may begin recording the measured sealing force. The corresponding time may be recorded as the process time by the article sensor, i.e. , the process time may correspond to the time instant when the measured force exceeds the threshold sealing force. In other examples, a different criterion may be used to define the process time. The process time may be defined as any time associated with the processing of the article by the machine, for example, corresponding to an initial time, an intermediate time or an end time of the processing. For example, reference is now made to FIG. 20 showing an example graph 200c of sealing forcemeasured by an article sensor versus time during processing of an article by a processing head of a rotary capper. In the illustrated example, the process time may be defined as an initial time 210a, an intermediate time 21 Ob, or an end time 210c. Time 210a may correspond to an earliest time at which the measured sealing force exceeds threshold sealing force of 10lbs. Time 210b may correspond to a first detected peak in the measured sealing force. Time 210c may correspond to the latest time at which the measured sealing force is at least 20lbs.

[0048] In some embodiments, the process time may be defined based on the type of machine and / or article sensor data. For example, the machine may be a capping machine, and the article sensor data includes measured sealing force values for articles capped by the capping machine. A processing head of the capping machine may have a processing issue / problem causing insufficient sealing force to be applied. For example, with reference to example graph 200c shown in FIG. 20, the processing issue / problem may cause a delay of 500ms before the applied sealing force reaches the 10lbF sealing force value. In such cases, using an initial time 210a as the process time may cause errors in determining the processing head that processed each article. To mitigate this problem, the process time may be defined based on the measured sealing force value falling below a threshold value indicating completion of processing and / or the article being dropped off by the processing head. This may improve the accuracy of determining the processing head that processed each article because the process times for all processing heads (including the processing head applying insufficient sealing force) can be better synchronized.

[0049] The position 60 for different articles, processing heads and process runs may fall within a range of positions shown in FIG. 1. The range of positions may correspond to process reproducibility and to process variability for different processing heads and / or different articles.

[0050] The article sensors may continue recording the sealing force during subsequent processing of the article by machine 10. In some embodiments, the article sensors may continue recording the sealing force after the article exits machine 10. For example, the sealing force data after the article exits machine 10 may be used to determinea post-process sealing force value that indicates the quality of the applied seal. The postprocess sealing force value may be used to detect issues during processing of the article by machine 10. For example, the post-process sealing force value may indicate that insufficient sealing force was applied during processing of one or more articles. In response, corrective action may be performed on the processing head(s) corresponding to the insufficient sealing force.

[0051] The disclosed systems and methods can further enhance detection of processing issues / problems because article sensor data can be continuously collected during processing of the article (in addition to the post-process sensor data). For example, the article sensors may generate sensor data at a 120Hz frequency to provide 120 sensor measurement data points per second. The measured data (e.g., the sealing force curves shown in graphs 200a and 200b) may be used to detect issues during processing of articles by machine 10.

[0052] In some embodiments, a process signature may be determined for each processing head based on the article sensor data for that processing head. The process signature can include any suitable combination of process and timing information associated with processing an article. For example, a process signature determined based on the sealing force data shown in graphs 200a and 200b may include data describing initial timing when the applied force exceeds a specific value, a final timing at which the applied force drops below a specific value, a rate of change of the applied force, average applied force, peak applied force etc. The process signature of the given processing head relative to other processing heads can indicate if there are any processing issues / problems associated with the given processing head. For example, the process signature of a given processing head may indicate a lower peak applied force compared with other processing heads.

[0053] In some embodiments, the process signature may further indicate a root cause of a processing issue / problem (if any). The root cause may be related, for example, to a machine misconfiguration or a malfunctioning machine component. As one example of a machine misconfiguration, a capping machine may include a top spring and a bottom spring, each having adjustable tensions. The determined process signature may indicate a machinemisconfiguration in the tension adjustment of the top (and / or bottom) spring. The combination of issue detection and root cause identification can enable targeted corrective actions to be performed. With reference to the above example, the disclosed systems and methods can automatically generate an output indicating that the tension on the top spring of the processing head needs to be adjusted.

[0054] The disclosed systems and methods can use any suitable technique for determining the process signature. For example, the disclosed systems and methods may implement automated statistical analysis of the article sensor data for article processed by a given processing head to determine the process signature forthat processing head. In some embodiments, the disclosed systems and methods may input the article sensor data for a given processing head into a machine learning model that is trained to generate an output including the process signature for that processing head.

[0055] In some embodiments, data from different sensors may be combined to detect issues and / or identify root cause. For example, the article sensors may include gyroscopes and / or accelerometers in addition to force sensors. The additional sensors may generate sensor data indicating, for example, a number of rotations of the article while the processing head applies the sealing force during a capping / crimping process. A mismatch in the number of rotations for articles processed by a given processing head relative to other articles can enable root cause identification for an associated processing issue.

[0056] Referring back to FIG. 1, position sensor system 120 may be any suitable sensor system that generates position sensor data indicating position of one or more of the multiple processing heads at a position capture time. For example, a sensor may detect the position of any one of the multiple processing heads at a position capture time. The position of the remaining processing heads at the position capture time may be determined based on the relative positioning of the multiple processing heads. In some embodiments, multiple position sensor systems may be used. For example, a separate position sensor system may be used to detect the position of each of the multiple processing heads at the position capture time.

[0057] In the illustrated example, position sensor system 120 includes a proximity sensor 140 and a marker 150. Proximity sensor 140 may be positioned on a stationary portion of machine 10. Marker 150 may be positioned on the moveable portion 50 of machine 10. Any suitable technique may be used for the proximity detection. For example, marker 150 may be a magnetic device and proximity sensor 140 may include an inductive sensor.

[0058] During processing, the moveable portion 50 moves in relation to the stationary portion, and proximity sensor 140 may detect each time marker 150 moves within detectable proximity of proximity sensor 140. Proximity sensor 140 may detect marker 150 once during each rotation of moveable portion 50. The timing corresponding each proximity detection may be defined as a position capture time. The time period between two consecutive position capture times may correspond to one rotation of the moveable portion 50 and may be defined as one run of machine 10.

[0059] Each position capture time may correspond to a specific position of the multiple processing heads. For the example illustrated in FIG. 1, processing head 20b may be at position 60 at each position capture time. The position of the remaining processing heads 20a and 20c-20h at each position capture time may be determined based on their relative positioning with respect to processing head 20b. The process time for each article may correspond to the time when the processing head that processed the article is at position 60. For an example run where articles 110a-110h are processed by processing heads 20g, 20h, 20a, 20b, 20c, 20d, 20e and 20f respectively, the process time of the article processed by processing head 20b may correspond most closely (smallest time difference) with the position capture time. This can enable identification of the article processed by processing head 20b. Based on a sequence of introduction of the articles into the machine and the known sequence and direction of rotation (clockwise / counter-clockwise) of the processing heads, the identification of the remaining articles processed by the processing heads can be performed.

[0060] In other examples, any other suitable technology may be used to implement position sensor system 120. For example, position sensor system 120 may include an imaging device (e.g., a camera) that is used to optically determine the positions of processingheads 20. The timing of the image capture may be defined as the position capture time. As another example, machine 10 may include a programmable logic controller (PLC). The PLC may provide position sensor data indicating the positions of the multiple processing heads at any suitable position capture time.

[0061] In some embodiments, position sensor system 120 includes an integrated processor. In some embodiments, the integrated processor may pre-process and / or process the position sensor data. The integrated process may transmit processed, pre-processed or unprocessed position sensor data to control system 130.

[0062] Control system 130 may be implemented using any suitable device. Reference is now made to FIG. 3 showing a block diagram of an example device implementation of control system 130. For example, control system 130 may be implemented using a tablet device, a smartphone, a workstation, a personal computer, a server device in combination with any suitable client device etc.

[0063] For the embodiment shown in FIG. 3, control system 130 includes a communication unit 305, a display 310, a processor unit 315, a memory unit 320, an I / O unit 325, a user interface engine 330 and a power unit 335. One or more components of control system 130 may be located at machine 10. In some embodiments, one or more components of control system 130 may be located at a remote location and communicate with machine 10 using a communication network.

[0064] Communication unit 305 can include wired or wireless connection capabilities. Communication unit 305 can be used by control system 130 to communicate with other devices or computers. For example, control system 130 may use communication unit 205 to receive article sensor data from the article sensors and / or receive position sensor data from position sensor system.

[0065] Processor unit 315 can control the operation of control system 130. Processor unit 315 can be any suitable processor, controller or digital signal processor that can provide sufficient processing power depending on the configuration, purposes and requirements of control system 130 as is known by those skilled in the art. For example, processor unit 315 may be a high-performance general processor. For example, processor unit 315 may includea standard processor, such as an Intel® processor, or an AMD® processor. Alternatively, processor unit 315 can include more than one processor with each processor being configured to perform different dedicated tasks. Alternatively, specialized hardware (e.g., graphical processing units (GPUs)) can be used provide some of the functions provided by processor unit 315. In some embodiments, processor unit 315 may include additional processors located remote from control system 130, for example, at articles 110 or machine 10.

[0066] Processor unit 315 can execute a user interface engine 330 that may be used to generate various user interfaces. User interface engine 330 may be configured to provide a user interface on display 310. Optionally, control system 130 may be in communication with external displays. User interface engine 330 may also generate user interface data for the external displays that are in communication with control system 130.

[0067] User interface engine 330 can be configured to provide a user interface to enable set-up and initialization of articles 110. User interface engine 330 can also be configured to provide a user interface to provide a process tracking output indicating processing head that processed each article.

[0068] Display 310 may be a LED or LCD based display and may be a touch sensitive user input device that supports gestures. Display 310 may be integrated into control system 130. Alternatively, display 310 may be located physically remote from control system 130 and communicate with control system 130 using a communication network. In some embodiments, control system 130 may not include a dedicated display 310 and may provide output displays using external displays.

[0069] I / O unit 325 can include at least one of a mouse, a keyboard, a touch screen, a thumbwheel, a trackpad, a trackball, a card-reader, voice recognition software and the like, depending on the particular implementation of control system 130. In some cases, some of these components can be integrated with one another. I / O unit 325 may enable a user, an operator and / or an administrator of control system 130 to interact with the user interfaces provided by user interface engine 330.

[0070] Power unit 335 can be any suitable power source that provides power to control system 130 such as a power adaptor or a rechargeable battery pack depending on the implementation of control system 130 as is known by those skilled in the art.

[0071] Memory unit 320 can include software code for implementing an operating system 340, programs 345, and database 350.

[0072] Memory unit 320 can include RAM, ROM, one or more hard drives, one or more flash drives or some other suitable data storage elements such as disk drives, etc. Memory unit 320 can be used to store an operating system 340 and programs 345 as is commonly known by those skilled in the art. For instance, operating system 340 provides various basic operational processes for control system 130. For example, the operating system 340 may be an operating system such as Windows® Server operating system, or Red Hat® Enterprise Linux (RHEL) operating system, or another operating system.

[0073] Database 350 may include a Structured Query Language (SQL) database such as PostgreSQL or MySQL or a not only SQL (NoSQL) database such as MongoDB, or Graph Databases, etc. Database 350 may be integrated with control system 130. Alternatively, database 350 may run independently on a database server in network communication with control system 130.

[0074] Database 350 may store the received article sensor data and / or the received position sensor data. In some embodiments, database 350 may store the process tracking outputs indicating processing head that processed each article.

[0075] Programs 245 can include various programs so that system 100 can perform various functions such as, but not limited to, receiving article sensor data and / or position sensor data, determining processing head that processed each article, generating process tracking output etc.

[0076] Reference is now made to FIG. 4, which shows a flowchart of an example method 400 for tracking processing of one or more articles by multiple processing heads of a machine when the one or more articles are introduced into the machine, each article being processed by any one of the multiple processing heads. Each article may exit the machine after being processed. Method 400 may be executed, for example, in response to acquiredprocess signatures indicating a processing issue for one or more articles. Method 400 can enable tracking of the processing head(s) that processed the one or more articles having the processing issue.

[0077] Each article may include one or more article sensors configured to generate article sensor data indicating processing of that article by the machine. In some embodiments, the article sensors may be initialized at the beginning of method 400. In other embodiments, the article sensors may be pre-initialized, and no additional initialization is performed at the beginning of method 400.

[0078] The initialization may include one or more settings including a threshold setting for the sensor data. The article sensor may begin recording and / or transmitting article sensor data when the sensed data meets the threshold setting. For example, the threshold setting may be 10lbs force and the article sensor may begin recording article sensor data when the sensed force exceeds 10lbs. The initialization settings may include a frequency of recording / transmitting the article sensor data.

[0079] The initialization may include a timing synchronization between multiple article sensors. Any suitable synchronization method may be used, for example, the timing synchronization may be performed using handshake signals between the article sensors. In some embodiments, each article sensor may include a visual indicator, e.g., a LED. The LEDs of the multiple article sensors may blink in synchronization when the article sensors are synchronized indicating to an operator or a user that the article sensors are synchronized. In some embodiments, the initialization may include a timing synchronization between the article sensors and the position sensor system.

[0080] The initialization may include determining a timing relationship between the position capture time and the process time. For the example illustrated in FIG. 1, each proximity detection of marker 150 by proximity sensor 140 may correspond to processing head 20b being at position 60 and the process time closest to the position capture time is that of an article processed by processing head 20b.

[0081] Method 400 may be implemented using system 100 for machine 10 and concurrent reference is now made to FIG. 1. Multiple article 110 may be introduced intomachine 10 and method 400 may be implemented to determine processing head 20 that processed each article 110. The number of articles 110 may be the same, greater, or smaller than the number of processing heads 20. In some embodiments, method 400 may be implemented using other systems and / or for other machines.

[0082] The article sensors of each article may generate article sensor data as the article is processed by machine 10. In some embodiments, the article sensor may record the generated article sensor data in internal memory. The stored article sensor data may be subsequently accessed by control system 130. In some embodiments, the article sensor may transmit the generated article sensor data in real-time to control system 130.

[0083] At act 405, method 400 includes receiving the article sensor data from the one or more article sensors. For example, control system 130 may receive the article sensor data from articles 110a-110h.

[0084] At act 410, method 400 includes determining a process time for each article based on the received article sensor data. For example, control system 130 may determine a process time for each article 110a-110h based on the received article sensor data. For an example scenario where articles 110a-110h are introduced sequentially into machine 10, the articles 110a-110h may be processed sequentially by processing heads 20g, 20h, 20a, 20b, 20c, 20d, 20e and 20f respectively. The article sensor of each article 110a-110h may record a process time a when the measured sensor data meets the threshold setting. For example, the article sensor of each article may record a process time when the sensed force exceeds 10lbs. The recorded process times ci-cs indicate the timing and order of processing of articles 110a-110h.

[0085] At act 415, method 400 includes receiving position sensor data from a position sensor system. For example, control system 130 may receive position sensor data from position sensor system 120. For the example illustrated in FIG. 1, marker 150 may be detected by proximity sensor 140 at a position capture time for each rotation of moveable portion 50 of machine 10. The position sensor data may include the corresponding position capture times pi, p2,...pmfor m rotations of moveable portion 50.

[0086] At act 420, method 400 includes determining processing head that processed each article based on the process time, the position of the multiple processing heads at the position capture time, and the timing relationship between the process time and the position capture time. For example, control system 130 may determine processing head that processed each article by determining a process time a that most closely corresponds to a position capture time, i.e. , by determining mintj |cf- p7|.

[0087] During an example execution of method 400, the process times for articles 110a-110h may be as follows (relayed as unix timestamps to the millisecond) - Article ID Process Time110a 1687880650100 (Tuesday, June 27, 202312:44:10.100 PM GMT-03:00 DST) 110b 1687880650849 (Tuesday, June 27, 202312:44:10.849 PM GMT-03:00 DST) 110c 1687880651597 (Tuesday, June 27, 202312:44:11.597 PM GMT-03:00 DST) 110d 1687880652374 (Tuesday, June 27, 202312:44:12.374 PM GMT-03:00 DST) 110e 1687880653125 (Tuesday, June 27, 202312:44:13.125 PM GMT-03:00 DST) 110f 1687880653906 (...)110g 1687880654631 (...)110h 1687880655384 (...)The position captures times for two consecutive runs may be as follows - Run 1 - 1687880649788 (Tuesday, June 27, 2023 12:44:09.788 PM GMT-03:00 DST) Run 2 - 1687880652574 (Tuesday, June 27, 2023 12:44:12.574 PM GMT-03:00 DST)

[0088] For run 2, control system 130 may determine that the minimum difference between a process time and a position capture time, mintj |cf- p7|, is met for the 4thprocess time (a difference of 200 milliseconds). Based on the timing relationship determined during initialization, control system 130 may determine that the article that was processed 4th(110d)was processed by processing head 20b. Based on the sequencing of process times of articles 110a-110h and the relative positioning of processing heads 20a-20h, control system 130 may determine that articles 110a-110h were processed sequentially by processing heads 20g, 20h, 20a, 20b, 20c, 20d, 20e and 20f respectively.

[0089] In cases where articles are introduced intermittently into machine 10 or where the total number of articles is smaller than the total number of processing heads, the tracking of processing by articles by the multiple processing heads may be further based on a rotation speed of the moveable portion 50. A pre-determined offset (e.g., determined during initialization) and the proximity detection at the position capture time may be used to identify the processing head corresponding to position 60 at the position capture time. Further, the rotation speed may be used in combination with the time interval between process times to determine one or more processing heads that did not process an article. For example, the rotation speed and the process times may be used to determine that a first article was processed by processing head 20c and the next article was processed by processing head 20f, i.e. , no articles were introduced into processing heads 20d and 20e.

[0090] At act 425, method 400 includes generating a process tracking output indicating processing head that processed each article. For example, control system 130 may generate a process tracking output indicating processing head that processed each article. In some embodiments, the process tracking output may be provided to a user via a user interface generated by control system 130. In some embodiments, the process tracking output may be stored, e.g., stored in database 350 (FIG. 3) of control system 130. The process tracking output may enable corrective actions to be performed for any processing heads that do not meet processing criteria.

[0091] Reference is now made to FIG. 6, which shows a flowchart of an example method 600 for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine. Each article may include one or more article sensors configured to generate article sensor data indicating processing of that article by the machine. Method 600 may be implemented using any suitable processor to process the article sensor data.

[0092] Method 600 may be implemented for any suitable machine that is configured to process articles. In some embodiments, method 600 may be implemented for a machine having a single processing unit / head. In such examples, every article processed by the machine is processed by the same processing unit / head. In some embodiments, method 600 may be implemented for a machine having multiple processing heads, for example, machine 100 shown in FIG. 1. In such examples, articles processed by machine 100 may be processed by different processing units / heads. Concurrent reference is made herein below to components shown in FIG. 1.

[0093] At act 605, method 600 includes receiving the article sensor data from the one or more article sensors. For example, a processor may receive article sensor data indicating processing of the articles by the machine.

[0094] At act 610, method 600 includes determining at least one process signature based on the received article sensor data. For the example embodiment of the machine having a single processing unit / head, the processor may determine a single process signature for the machine. For the example embodiment of the machine having multiple processing units / heads, the processor may determine multiple process signatures. Each process signature may be associated with one of the multiple processing heads. The determined process signature may include process and / or timing information associated with processing an article of the one or more articles.

[0095] At act 615, method 600 includes detecting the process issue based on a comparison of the at least one process signature with one or more reference process signatures. The reference process signatures may be associated with processing heads / machines that are known to not have a process equipment issue. For the example embodiment of the machine having a single processing unit / head, the reference process signatures may be associated with other similar machines. For the example embodiment of the machine having multiple processing units / heads, the reference process signatures may be associated with the other processing heads of the same machine and / or other machines.

[0096] At act 620, method 600 includes generating an output recommending a corrective action to address the detected process issue. For example, the processor maygenerate an output that includes any suitable combination of the determined process signature, the detected process issue, a root cause attributed to the detected process issue and a recommended corrective action to address the root cause.

[0097] Numerous specific details are set forth herein in order to provide a thorough understanding of the exemplary embodiments described herein. However, it will be understood by those of ordinary skill in the art that these embodiments may be practiced without these specific details. In other instances, well-known methods, procedures and components have not been described in detail so as not to obscure the description of the embodiments. Furthermore, this description is not to be considered as limiting the scope of these embodiments in any way, but rather as merely describing the implementation of these various embodiments.

Claims

CLAIMS1. A system for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine, the system comprising:the one or more articles, wherein each article comprises one or more article sensors configured to generate article sensor data indicating processing of that article by the machine; andat least one processor configured to:receive the article sensor data from the one or more article sensors; determine at least one process signature based on the received article sensor data, the at least one process signature comprising process and / or timing information associated with processing an article of the one or more articles; detect the process issue based on a comparison of the at least one process signature with one or more reference process signatures; andgenerate an output recommending a corrective action to address the detected process issue.

2. The system of claim 1 , wherein the one or more article sensors comprise at least one of: a force sensor, a fill sensor, a pressure sensor, an accelerometer, or a gyroscope.

3. The system of claim 1 , wherein the at least one processor is configured to filter noise in the article sensor data prior to determining the at least one process signature.

4. The system of claim 1, wherein the at least one processor is further configured to determine a process signature comprising at least one of:- a predetermined force-threshold crossing time,- a peak measured force,- a rate of change in measured force, or- a process end time.

5. The system of claim 1, wherein the one or more reference process signatures are generated based on article sensor data from multiple processing heads of the machine.

6. The system of claim 1, wherein detecting the process issue comprises determining a deviation of the at least one process signature from a statistical distribution of the one or more reference process signatures.

7. The system of claim 1 , wherein the machine comprises at least one of: a capping machine, a filling machine or a labeling machine.

8. The system of claim 7, wherein when the machine comprises the capping machine, the process issue comprises a misconfiguration of a spring tension of a capping head of the capping machine.

9. The system of claim 1, wherein the output recommending a corrective action comprises recommending adjustment of a physical component of the machine.

10. The system of claim 1, wherein the machine comprises a plurality of processing heads, and the at least one processor is further configured to identify at least one processing head associated with the detected process issue.

11. The system of claim 1 , wherein the at least one processor is configured to determine the at least one process signature using a machine learning model trained on article sensor data.

12. The system of claim 1, wherein the article sensor data comprises data captured at a sampling frequency of at least 100 Hz.

13. The system of claim 10, further comprising a position sensor system configured to provide position data associated with the plurality of processing heads of the machine, theat least one processor being configured to correlate the position data with the article sensor data.

14. The system of claim 10, wherein the corrective action comprises routing a specific processing head for maintenance.

15. The system of claim 1, wherein the one or more articles comprise a replica article configured to simulate processing conditions for the machine.

16. A method for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine, each article comprising one or more article sensors configured to generate article sensor data indicating processing of that article by the machine, the method comprising:receiving, at a processor, the article sensor data from the one or more article sensors; determining, by the processor, at least one process signature based on the received article sensor data, the at least one process signature comprising process and / or timing information associated with processing an article of the one or more articles; detecting, by the processor, the process issue based on a comparison of the at least one process signature with one or more reference process signatures; and generating, by the processor, an output recommending a corrective action to address the detected process issue.

17. The method of claim 16, further comprising pre-processing the article sensor data, at the processor, to remove noise prior to determining the at least one process signature.

18. The method of claim 16, wherein determining the at least one process signature comprises calculating a time at which a predetermined force threshold is exceeded.

19. The method of claim 16, wherein detecting the process issue comprises identifying a deviation exceeding a predefined tolerance.

20. The method of claim 16, further comprising identifying a machine component associated with the detected process issue.

21. The method of claim 16, wherein identifying the machine component comprises determining a processing head that processed the article associated with the process signature.

22. The method of claim 16, wherein the one or more reference process signatures are generated from sensor data of multiple articles previously processed by the machine.

23. The method of claim 16, wherein generating the output comprises providing a user interface display indicating the corrective action.

24. The method of claim 16, wherein the corrective action includes an adjustment to a spring tension of a capping head.

25. The method of claim 16, wherein determining the at least one process signature comprises applying a statistical or machine learning analysis to the article sensor data.

26. The method of claim 16, further comprising detecting a number of rotations of an article during processing and incorporating the detected rotations into the process signature.

27. A non-transitory computer readable medium storing thereon program instructions that are executable by a processor for performing a method for detecting a process issue associated with a machine that is configured to process one or more articles introduced into the machine, each article comprising one or more article sensors configured to generatearticle sensor data indicating processing of that article by the machine, wherein the method comprises:receiving, at the processor, the article sensor data from the one or more article sensors;determining, by the processor, at least one process signature based on the received article sensor data, the at least one process signature comprising process and / or timing information associated with processing an article of the one or more articles; determining, by the processor, the process issue based on a comparison of the at least one process signature with one or more reference process signatures; and generating, by the processor, an output recommending a corrective action to address the detected process issue.

28. The non-transitory computer readable medium of claim 27, wherein the processor is further configured to perform the method of claims 17 to 26.

Images