Industrial system design and use

Abstract

An industrial process design system is presented that includes a process constraint retriever that receives a parameter constraint indication for an industrial process. The system also includes a parameter selector that retrieves potential process design parameters for the industrial process. A parameter selector analyzes the parameter constraint indication and selects a next parameter of interest based on the set of potential process design parameters and the constraint indication analysis. The parameter selector also generates a constraint query for the selected next parameter. A parameter selector iteratively analyzes the received parameter constraint information, selects a new parameter of interest, and generates a new constraint query. The system also includes a process design generator that generates a set of process design parameters based on the constraint query generated by the parameter selector.

Description

Background Art

[0001] Many industrial systems have multiple interdependent parameters. Determining effective parameter settings to achieve acceptable process outcomes presents an ongoing challenge in many industries. Summary of the invention

[0002] An industrial process design system is proposed, the industrial process design system including a process constraint retriever that receives a parameter constraint indication for an industrial process. The system also includes a parameter selector that retrieves potential process design parameters for the industrial process. The parameter selector analyzes the parameter constraint indication and selects a next parameter of interest based on a set of potential process design parameters and the constraint indication analysis. The parameter selector also generates a constraint query for the next parameter selected. The parameter selector iteratively analyzes the received parameter constraint information, selects a new parameter of interest, and generates a new constraint query. The system also includes a process design generator that generates a set of process design parameters based on the constraint query generated by the parameter selector. BRIEF DESCRIPTION OF THE DRAWINGS

[0003] Figure 1 An adhesive dispenser is shown in which example embodiments may be implemented.

[0004] Figure 2 A schematic diagram showing different variables of interest in an example adhesive dispensing operation.

[0005] Figure 3 A process design cycle according to embodiments herein is shown.

[0006] Figure 4 A method of designing an industrial process according to embodiments herein is shown.

[0007] Figure 5 A method of evaluating an industrial process according to embodiments herein is shown.

[0008] Figure 6 A method of dynamically generating a parameter constraint request according to an embodiment of the present invention is shown.

[0009] Figure 7 A process design system architecture according to embodiments herein is shown.

[0010] Figures 8 to 9 An example user interface that may be presented to a process designer according to embodiments herein is shown.

[0011] Fig.10 A process design system architecture is shown in which example embodiments may be implemented.

[0012] Figures 11 to 13 An example apparatus is shown that may be used in embodiments herein. DETAILED DESCRIPTION

[0013] Many industrial processes use liquid materials such as adhesives, liquid food ingredients, coolants or reaction products, for example. Certain properties of these liquids change during process operation - adhesives may solidify, viscosity may change with increasing temperature, coolants may age and have a lower heat capacity than when they were originally purchased or installed.

[0014] Designing a new industrial process requires consideration of each of these properties and how they can be altered by adjusting process parameters. The design process is further complicated by the fact that the components themselves are also variables when designing an industrial process - for example, a variety of adhesives may be theoretically suitable for joining a metal part to a plastic substrate. The choice of which adhesive to use requires consideration of many factors - the conditions of use of the final product, the desired service life, etc. - in addition to the selection of dispensing operating parameters for the adhesive and / or its components.

[0015] The systems and methods herein are intended to solve or provide insight into multivariate analysis problems for industrial process design. While a question such as which adhesive is best for bonding a sprayed metal surface to a plastic surface may seem simple, many interdependent variables are at play. For example, if the joint is on an aircraft, it may need to have good adhesion over a wide temperature range. Similarly, the type or finish of the coating may also affect the adhesion of the adhesive to the surface.

[0016] While the adhesive dispensing example is described throughout as an industrial process in which the systems and methods described herein may be particularly useful, it is expressly contemplated that other industrial processes may also benefit from the systems and methods herein.

[0017] In addition, when referring to the dispensing system, the term "fluid" is widely used in this article to refer to flowable materials. Flowable materials can be liquid or solid particle streams, etc. In certain embodiments, the fluid is an adhesive. The adhesive can be a curable fluid adhesive. In some embodiments, the fluid is a curable two-part fluid adhesive. "Two-part" refers to that the adhesive is composed of a first component and a second component, and the first component and the second component are mixed to form an adhesive, for example, in a static or dynamic mixer.

[0018] In other embodiments, the fluid is a void filler, a sealant, a dielectric fluid (such as 3M Novec TMEngineered fluids), thermally conductive interface materials (such as thermally conductive gap fillers), or fluid chemical compositions for producing any of the aforementioned fluids. However, other suitable fluid dispensing operations may also benefit from the systems and methods herein.

[0019] Fluids have many important properties that may be considered in industrial process design: for example, viscosity, density, color, volatile component content, moisture content, chemical composition, boiling point, and aging state, solidification state, or mixing ratio in the case where the fluid is a curable composition, or the fluid is a mixture. Some of these properties are interdependent. For example, viscosity varies with temperature. Some of these properties are independent, such as the color of the fluid can be set and cannot be adjusted, such as by the use of additives. Although many of the examples herein contemplate liquids, it should also be clearly contemplated that in some systems there may be flowable solids, solid material flows (e.g., particles, microparticles, etc.), or gases.

[0020] Figure 1 An adhesive dispenser is shown in which example embodiments herein may be particularly useful. Figure 1 1 is a side view of a dispenser and mixing system 1 for viscous two-component adhesives. A first component A and a second component B are pushed out from respective cartridges 100, 110 into and through a static mixer 120. In the illustrated system 1, at the output 170 of the static mixer, the mixed adhesive flows through a sensing region 50 before being dispensed at an output 190. The sensing region 50 may house a sensor that senses the mixing ratio, temperature, viscosity, or other variables of interest of the components A and B in the mixed adhesive. Feedback from the sensing region 50 may be important in verifying preferred process parameters.

[0021] The cartridges 100 and 110 contain viscous components A and B, respectively. The corresponding pistons 130 are further moved into the cartridges 100 and 110 and push out components A and B. The pistons 130 are driven by the corresponding motors 140 and 150, which can be independently controlled, and the pressure generated by the pistons 130 moves the unmixed components and, after mixing, moves the mixed viscous adhesive 10 through the static mixer 120 and the channel 20 of the system 1. The motors 140 and 150 can be part of a feedback loop: if the sensed mixing ratio is outside the acceptable range of the desired mixing ratio, the motors 140 and 150 can be independently controlled so that more component A and / or less component B (or vice versa) are pushed into the static mixer 120 to adjust the mixing ratio toward the desired mixing ratio. Both motors 140 and 150 can be individually controlled to obtain a desired total throughput of mixed adhesive to be dispensed per second.

[0022] The static mixer 120 receives unmixed component A and component B of a two-component adhesive at an input end 160. Lamellae inside the static mixer 120 redirect the flow of the input material multiple times and introduce shear forces that help component A and component B mix with each other. The output end 170 of the static mixer 120 is connected to an inlet 180 of a conduit member 190 that includes a channel 20 and a sensing area 50. The mixed adhesive 10 can therefore leave the static mixer 120 and enter the conduit member 190. At the outlet 190 of the conduit member 190, the mixed adhesive 10 is dispensed.

[0023] The sensing area 50 may include one or more different sensors that detect one or more of the components A and B and the properties of the resulting mixture. For example, mixing ratio, temperature, viscosity, flow rate, etc. However, it should be clearly envisioned that the sensor can be positioned elsewhere in the system and that other sensors can be important. The sensed parameter information can be provided to the control system 20. The control system 20 can be specific to the distribution system 1, for example, in that it changes the flow rate, temperature, etc. for the distribution system. However, it should be clearly envisioned that the control system 20 can also be used in the embodiments of this article. The control system 20 may include an internal memory 30, such as calibration data, etc.

[0024] Precisely dispensing a multi-part adhesive onto a surface such as substrate 111 is a challenge in itself, ensuring proper mix ratios, temperatures, speed of movement of the dispenser relative to surface 111, etc. This problem is compounded when an industrial process is first designed. For example, an adhesive may be dispensed onto substrate 111 so that substrate 111 may then be joined to a second material (not shown). In addition to the dispensing parameters, the composition of substrate 111, the second material, and the use of the two materials are important in determining which adhesive the dispensing system should dispense.

[0025] Figure 2 A non-exhaustive schematic diagram of parameters that may need to be considered when designing the parameters of a dispensing system is shown. For example, a dispensing system may have dispenser parameters 210, such as state operating temperature, possible flow rates, sensitivity detection relative to mixing ratio, etc. The substrate may also have parameters of interest 220, such as the material composition of the first material and the second material being joined. The adhesive or other post-dispensing fluid may also have fluid parameters 230, such as thickness and adhesion to the first material, adhesion to the second material, viscosity when dispensed, etc.

[0026] The parameters of interest are divided into constraints 240 and preferences 250. Constraints 240 refer to parameters that are restricted based on the specified design problem. For example, a customer may only be able to use a specific dispenser, which may have a maximum and / or minimum flow rate. In addition, the characteristics of the substrate may also be appropriately set based on the substrate selected by the customer. However, the customer may also have multiple preferences 250, such as for industrial processes, such as dispensing speed, curing rate, the final color of the fluid after dispensing, the smoothness of the fluid on the first material or the second material, whether the fluid is visible after dispensing, etc.

[0027] In addition, a third set of parameters of interest relates to the final product obtained, Figure 2 categorized as results 270. For example, the dispensed adhesive must be effective for the application of interest, typically have a maximum cost, and be dispensed and cured within a suitable time frame.

[0028] Currently, selecting adhesives for use in industrial processes often requires consultation with application engineers or other experts in the field. Figure 2 Many of the parameters shown are interdependent, e.g. a particular adhesive may perform well on metal, perform well on glass, and may bond metal to glass indoors, but if used outdoors will fail due to differences in thermal expansion of flexibility and relaxation properties. Attempts have been made to reduce the cost of designing industrial processes by providing automated assistance to the customer. However, it is difficult to capture the intricacies in the interdependence of parameters without presenting or requesting so much information that the customer is frustrated.

[0029] The systems and methods described herein rely on a machine learning training model driven by a data set of known adhesive parameters and substrate interactions (such as the glass-metal example provided above). Using the systems and methods described herein, an algorithm selectively queries the customer for information about the desired end product and provides recommended industrial process parameters.

[0030] An important limitation of standard multivariate algorithms (regression, nearest neighbor, etc.) is that they treat each variable with equal importance. This can be done by normalization or principal component dimensionality reduction, where the individual factor priorities are lost to a greater extent. An improvement to these models is to add factor prioritization. This can be done in a variety of ways, such as weighted factors and ordered problems.

[0031] For example, for some processes, price and speed are more important than final product color and may be worth reducing possible adhesion. For other processes, the ability to withstand extreme temperature changes will override the cost constraint. While color may be of interest to the customer, it may not even be offered as a constraint query because other parameter requirements will override and dictate the final product color.

[0032] Even when application engineers are involved in the design of an industrial process, it is often important to actually produce a test adhesive or fluid of interest to test efficacy and ensure that constraints are met.

[0033] Figure 3 The process design cycle according to the embodiment of this paper is shown.It should be clearly envisioned that for many industrial processes, it is necessary to iterate to determine all suitable process conditions.Therefore, parameter selection model 300 can provide the initial selection of process parameters---such as the adhesive N of the selection composed of component A and component B with a mixing ratio of X:Y.This information can be provided to controller 320, and this controller specifies the setting of distributor 340 and actuates this distributor.Distributor 340 then operates with the designed specification to produce the fluid after distribution on substrate.Analyzer 360, this analyzer can provide the indication of whether the fluid after distribution is suitable, which constraints are not satisfied, etc. based on manual input, sensor input or their mixing.This information is then provided to parameter selection model 300, and this model can then change one or more process parameters.For example, the adhesive selected can remain the same, but the mixing ratio can be adjusted, or the distribution temperature can be adjusted so that the desired viscosity is achieved.

[0034] In some embodiments herein, parameter selection model 300 is a machine learning driven algorithm, which accesses and uses a database to determine a constrained parameter of interest, and interacts with a client to set the value of the parameter of interest. The model is limited by the data set behind it, which includes a combination of database restrictions (such as a key-value database and an object-oriented database), and the need to carefully assign feature values ​​to attributes. For many current databases, once these feature values ​​are set, if changes are needed, these feature values ​​must be manually changed. And, depending on the complexity of the model, adjusting a value may require adjusting other values ​​to maintain model output quality.

[0035] It would be desirable to have a feedback loop with an automatic tuning algorithm that eliminates the need for explicitly setting and changing each weighted value. Given the limitations of multivariate algorithms, a decision tree model can be considered. Depending on the complexity of the inputs and outputs, such a model may work well, especially if there are a small number of linearly independent variables. However, as the number of variables increases, and the number of output options increases, it becomes difficult to keep the tree properly updated. This task becomes even more difficult if there are any interactions between the variables. Typically, any change such as adding a new product to the database (e.g., a new potential adhesive), or removing a value (e.g., the heater broke and the temperature can no longer be changed) will result in the need to completely rebuild the decision tree. Using machine learning techniques, a decision tree can be designed that is trained with expert knowledge of the inputs and outputs so that the model can automatically update the algorithm connections as new data is provided. For example, each time a new product is added to the database, the model will automatically update the algorithm connections. Figure 3 During the loop, new data can be added to the database, which can then be used to improve the model.

[0036] In some embodiments, the parameter selection model can be communicatively coupled to the automated adhesive compounding system so that samples of a specified adhesive composition can be automatically created with little to no interaction from the user. However, it is also expressly contemplated that the model can also output process conditions that the customer may then have to implement manually or set in a semi-automatic manner.

[0037] Similarly, as discussed herein, analyzer 360 can be automated so that the amount of the adhesive after sensor detection distribution, the thickness of adhesive, the outward appearance of adhesive, the smoothness of adhesive, and the performance information about adhesive, such as whether two materials are actually fully adhered together. However, it should be clearly envisioned that at least some feedback in this feedback provided may need to be manually input by the user. Therefore, in some embodiments, analyzer 360 also includes the I / O components for obtaining feedback with the user interaction. The feedback received (whether it is manually input by the user or the feedback received by automatic sensing) can then be incorporated into the model to improve future suggestions. The model can be expanded to include use suggestions at any level, and the suggestions can include the automated system of suggestion for adhesive or distribution operation.

[0038] In the model training phase, input can be taken from various sources including structured or unstructured data. Structured data can include, for example, databases of physical properties or experimental results, spreadsheet files, flow charts, decision trees, etc. Unstructured data can include written or verbal explanations / notes, Q&A type discussions, or data pieces that have not yet been placed in a structured format (similar to a data table PDF stating that the maximum operating temperature is X in a sentence). This type of data will be unstructured in its current form, but the same information in a database or chart can be considered structured data. Similarly, conditional statements, such as using instructions that say "For wood, prepare the surface like this; For metal, prepare the surface like this", etc., will also be classified as unstructured data. However, these examples are provided as illustrative examples of structured data and unstructured data, and are not intended to limit these terms.

[0039] The system will understand this data in the context of any input given to further enhance capabilities. In some embodiments, in addition to or instead of sending a sample with suggested process conditions, the model can integrate information about the user's input and existing records, both public and internal. For example, based on salesforce.com information, the model may be able to make an assessment as to whether a human intervention (e.g., a sales representative, technical assistance, or an application engineer) should be sent to the user.

[0040] The system and method of this article provide customers with recommended process conditions in order to obtain the desired results. For example, a proposed adhesive can be specified, which can be formed by one or more specified components in a specified mixing ratio, distributed at a specific flow rate and temperature, etc. A finite element analysis (FEA) based on a material data card can be performed and iterated until satisfactory results are provided. Because it is difficult to measure and estimate quality, the system and method of this article can be used as a first step to suggest potential adhesive products for modeling using FEA software. However, it should be clearly envisioned that MDC can estimate adhesion as well as body strain.

[0041] In some instances, the constraints provided by the client may not provide the model to think that a feasible option. The model can then suggest the properties present in the adhesive, if it exists. This can then be used to start a new product introduction program to create this type of adhesive. In some embodiments, the system and method herein can suggest the formula of a specific adhesive based on a known formula. This can include inserting existing adhesives and adhesive technology. In some embodiments, the system and method herein can be extrapolated to outside the current existing product to suggest a new adhesive formula for testing.

[0042] In some embodiments herein, the model may enter training mode and receive new information and new constraint query possibilities, such as from subject matter experts. For example, a new adhesive formulation that may be useful for a new substrate may be added, which may result in a new constraint query. For example, the model may have never been used for a substrate exposed to extreme cold, yet this may be an important feature of a new project.

[0043] In some embodiments herein, the model is able to converse with the user using natural language input. This can improve model training because the expert may be able to converse with the model rather than having to sit down and reprogram it. For example, the expert might convey "This is a good product suggestion, but you didn't ask about price constraints. If you consider the price constraints of the market, the best option is product X." The model can then incorporate new constraint queries about pricing. The pricing constraints can then be related to previous inputs, particularly the market of interest. The newly introduced product X can then be designated by the model as the best option given the constraints going forward.

[0044] However, while natural language input may be preferred, it is expressly contemplated that the model may also be programmable using another suitable I / O component, such as a keyboard, mouse, touch screen, buttons, or other suitable system.

[0045] It is also contemplated that in some embodiments, the model may incorporate a variety of different data types, such as categorical, numerical, Boolean, etc. The model may be able to recognize the data type and the specialized processing required by the model.

[0046] Particularly in the area of ​​adhesive formulation selection, there may not be a "right" answer. For example, not all information is available for the model to make the best choice among a suitable set of choices. Consider the difficulty of bonding a material to ABS, which has a wide range of adhesion issues. The systems and methods of this article can represent an improvement over decision trees for such scenarios. Especially when there is conflicting information, such as a customer wants a product to be black and it must adhere to ABS. There may be an excellent product that adheres to ABS, but there is no black adhesive suitable for ABS. The method can go back to the customer and ask if gray is appropriate, or it may simply focus more on the substrate, because adhesion is almost always more important than aesthetics.

[0047] like Figure 2As shown, some parameters (e.g., constraints) may be weighted differently than other parameters (e.g., preferences). For example, adhesion will almost always take precedence over color and desired thickness. It is also contemplated that the model may learn that different parameters should be weighted differently in different contexts, based on, for example, the use of the final product. For example, the smoothness of the adhesive after dispensing may not be important, except in products where aesthetics are a concern. In another example, thickness may not be of particular concern, with adhesion being a higher priority, except perhaps in situations where the final weight, height, etc. must be precise. However, it is expressly contemplated that the model may determine that for a particular process, a preference (e.g., speed or cost) should be prioritized.

[0048] The model can classify different parameters in different ways. For example, an adhesive can be transparent or black, but not both. In another example, an adhesive can have a first viscosity at one temperature, a second viscosity at a second temperature, but not the second viscosity at the first temperature. Parameters can be classified into categories, such as belonging to multiple options such as gray, black, or transparent. Parameters can also be classified as numerical values, such as thickness or temperature represented as a number, such as 1.2 or 70℉. Parameters can also be classified as Boolean parameters, where there are only two options, such as true or false, etc. A non-exhaustive list of some example classifications is provided below in Table 1.

[0049] Table 1: Example constraint classification

[0050]

[0051] It should be explicitly envisaged that some of the products under consideration may require categorical processing, while others may be processed numerically. All of these can be incorporated into the appropriate algorithm.

[0052] Figure 4 A method of designing an industrial process according to embodiments of the present invention is shown. The steps of method 400 may be performed locally, such as by a controller of an adhesive formulation machine. However, it is clearly contemplated that at least some steps of method 400 may be performed remotely.

[0053] At block 410, the model receives constraint parameter information. For example, the constraint parameters may relate to adhesive 402, substrate 404, dispenser 406, or final product result 408. For example, the adhesive constraint may relate to the type of substrate 404, or the use conditions that adhesive 402 needs to withstand. For example, adhesive 402 may be used in high heat, may need to withstand low temperatures, may need to withstand a range of temperatures without significant thermal expansion, etc. The constraint parameter information may include values, such as a maximum or minimum flow rate for dispenser 406, and other information, such as whether component X is in stock, etc.

[0054] As described herein, it should be clearly envisioned that the model can select the constraint query to be presented to the user based on information previously received from the user or another source. Therefore, the operation in box 410 can be regarded as a series of constraint queries presented to the user by the model. The model can start with the use conditions of, for example, the final product, the substrate material, and then can continue to select queries based on the received information. For example, if all black adhesives are eliminated based on the use conditions, then the constraint query based on color will not be presented to the user. Similarly, if the dispenser 406 does not have a heating element, then any constraint query about high temperature or low temperature process conditions will not be presented to the user.

[0055] Similarly, constraints may be received from the sample generation machine during the operation of block 420. For example, if the sample generation machine is not in component A, the method 400 may proceed to block 480 and obtain additional parameter constraints to find a set of process conditions that do not require component A.

[0056] In the operation of block 430 , samples are generated based on process conditions selected by the model. The process conditions may include, for example, adhesive composition 432 , dispensing conditions 434 (such as temperature, flow rate, mixing ratio, speed, etc.). The process conditions may also include other conditions 438 .

[0057] In the operation of frame 440, check the quality of the sample generated.For example, adhesive can be distributed on the substrate of interest, and adhesion can be tested.In frame 440, quality inspection can also include the quality inspection of the distribution of adhesive itself, for the consistency, gap, consistent thickness, smoothness etc. of flow.Quality inspection can be carried out in original position (in situ) 442, or 444 is carried out after the distribution operation is completed.In addition, in at least some embodiments, user feedback 446 is provided to the model.User feedback 446 can include the feedback that is transmitted to the model in any suitable manner, such as natural language input, I / O input device or by any other suitable mechanism.User feedback can include whether the sample performs as expected, whether the sample is suitable for operation or needs to change what parameter.For example, it may be necessary to increase the adhesion to the substrate, and the adhesive needs to have less viscosity etc. at the distribution temperature.

[0058] Based on the results of the sample testing, the method 400 may return to block 430 to generate a new sample based on the identifiable changes, or may continue to block 410 to obtain additional constraint information from the user, as shown in the operation of block 480. For example, in some embodiments, adjustments to process conditions may be compensated by changes in dispense conditions (such as increases in flow rate or temperature). However, in other embodiments, it may be necessary to restart the constraint query process.

[0059] The system and method of this article have been described with respect to the problem of generating process conditions for adhesive dispensing operations. However, it should be clearly envisioned that the system and method of this article can also be used for other suitable industrial processes with interdependent parameters. Any industrial process that requires multivariate analysis to generate process conditions can benefit from method 400. For example, the abrasive product selected for use on a specific substrate may involve consideration of multiple factors. In addition to which hand tool is used with which abrasive product, it is also necessary to consider whether the abrasive product should be used dry, whether it is polished, whether it is used with water, etc. Similarly, the process of generating other materials (such as adhesive tapes (e.g., tapes) with or without pads) can also benefit from the system and method of this article.

[0060] Figure 5 A method of evaluating an industrial process according to embodiments herein is shown. Method 500 shows how a model can interact with a user.

[0061] At block 510 , constraint information for the process is received. The constraint information may be received in a natural language format 502 , as input through an I / O device 504 , through sensor feedback 506 , or any other suitable mechanism 508 .

[0062] At block 520, constraint information is requested from the user. The constraint information may be queried using a natural language interface 522 (such as a smartphone assistant) or other interface, or may use another suitable I / O device 524 (such as a touch screen, keyboard, mouse, etc.). However, other suitable methods 528 for sending and receiving constraint queries and responses are also contemplated. For example, a series of constraint information queries may be sent via text messaging, an instant messaging applet, or another suitable communication method. The operations in blocks 510 and 520 may occur simultaneously or in parallel. Figure 5 The reverse order shown occurs, for example at least one query may be generated before any constraint information is retrieved.

[0063] The constraint query may be generated based on the constraints identified by the model 512. For example, the model may determine that multiple adhesives may be suitable, and a constraint request may be generated to determine which adhesive may be the best fit. The best fit may be based on price constraints, substrates, use temperature ranges, temperature ranges during distribution, or any other suitable constraints.

[0064] The queries may also be generated by the model following at least in part the decision tree 514. For example, a first query may ask about a first substrate material, and the decision tree may then indicate that the next query should be for a second substrate material. The queries may also be generated by following a flow chart 516, such as first obtaining the substrate material, then obtaining the process conditions, etc. However, it is expressly contemplated that the queries may be generated in other suitable ways 518. As described herein, the model may select constraints 512 based at least in part on machine learning-based training, such that generating the queries in block 520 is at least in part dynamic, such that the user does not have to answer exactly the same series of queries each time a process is designed.

[0065] At block 530, a sample for testing is generated. The sample may be generated automatically, such as by sending instructions to an automatic sample generator, the instructions including the process conditions selected by the model. However, at the other end of the spectrum, generating the sample for testing in block 530 includes instructions for a user to set up an industrial process to generate the sample for testing. The sample may be generated locally by a device in direct communication with the model, as indicated by block 532. However, it is also contemplated that in some embodiments, the model is run on a processing device remote from the sample generation system.

[0066] At block 540, an assessment is received, for example based on testing of the generated samples. The assessment may be received in any suitable manner including, but not limited to, a natural language interface 542 and an I / O device 544, sensor feedback 546, or another suitable option 548.

[0067] At block 550, the process is repeated until an appropriate set of process conditions is identified that achieves the user's desired properties. Iterations may include returning to block 530 to generate new samples for testing, and / or may include returning to block 510 to obtain new constraint information. For example, in some embodiments, the user's desired specifications may change based on the results of the sample testing.

[0068] Figure 6The method for dynamically generating parameter constraint requests according to the embodiments of this paper is shown. This paper describes a system and method including a model based on machine learning, and a user can interact with the model to select process conditions for an industrial process. It should be clearly envisioned that in the embodiments of this paper, the model can dynamically generate requests or constraint requests for information based on information provided by the user, so as to effectively reach a set of process conditions. For many industrial processes, such as adhesive distribution discussed herein, there is not always a one-to-one association between process conditions and desired outputs. Therefore, it should be envisioned that in the embodiments of this paper, the model will dynamically generate constraint queries based on a current known data point set to try to find the best fit for process conditions. Method 600 can be used by the systems and methods of this paper to dynamically generate constraint requests.

[0069] At block 610, constraint inputs are received by the model. The constraint inputs may be received by a natural language interface 602, as well as an I / O device or other user input device 604, sensor feedback 606, or in another suitable manner 608. For example, in some embodiments, some constraint inputs may be retrieved from a data storage device based on known process information (e.g., a known dispenser model may dictate a maximum flow rate) and temperature constraint information.

[0070] In box 620, the next parameter of interest is selected. Based on known information, the next parameter of interest is dynamically selected. Determining the next process variable can be carried out in conjunction with box 630 discussed below, before box 630, or after box 630. The next variable of interest can be directly requested to the user, or provided as one of several options for the user to select from, or can be specified by one or more constraint selection algorithms. For example, if the system restrictions 612 for one or more parts of the industrial process are unknown, these restrictions may be required to determine that the process condition set belongs to an acceptable range. In some embodiments, the model can consult a decision tree 614 to determine what the next parameter of interest is. For example, if cost information has not yet been determined, the decision tree can indicate that the cost information should be requested, for example, before the final product color preference. Similarly, in some embodiments, a flowchart 616 can indicate the initial importance order for different parameters of interest. However, it should be clearly envisioned that the initial order can be changed based on the constraint information received from the user.

[0071] At frame 630, one or more parameters can be removed from consideration.For example, based on known constraints, only the adhesive of interest can be all a color, so color parameters can be removed from consideration.In some embodiments, fixed parameters may not be presented to the user.But, it should also be clearly envisioned that fixed parameters may be presented to the user so that the user learns that these parameters are specified by the previously received constraint information.Another example of fixed parameters may be a temperature threshold value based on the input of the dispenser without a heater element.Therefore, it is impossible to adjust the distribution temperature, and it is also impossible to use temperature to change viscosity.This model may be based on the information about system 622 received, based on one or more steps of decision tree 624, based on the steps in flow chart 626, or use other suitable technologies 628 to classify one or more parameters as fixed parameters.

[0072] At block 640, a constraint request is generated. The model may determine that the best fit has not yet been selected based on the remaining parameters of interest. The constraint request may be generated based on the next parameter of interest. For example, if the next parameter of interest is cure time, the constraint request generated at block 640 may be a natural language query 642 asking if the customer has a maximum cure time allocated. The constraint request may also be transmitted in another suitable manner, such as using an I / O user input device 644, by querying and receiving sensor feedback 646, or using another suitable alternative 648.

[0073] When a response to the constraint request is received, the model may then return to block 610 , as indicated by iterative operation 650 .

[0074] Figure 7 The process design system architecture according to the embodiments of this paper is shown. The industrial process 700 can be any suitable process with multiple interdependent parameters. For example, the grinding operation can involve a consumable abrasive article that contacts and grinds the substrate surface. In addition, as described herein, the adhesive dispenser can distribute the prepared adhesive composition onto the substrate. Other industrial processes should also be envisioned.

[0075] The industrial process 700 includes an industrial process unit 710. The process unit 710 can be any unit operation that causes a consumable to contact a substrate; for example, a dispenser of an adhesive, a robotic arm coupled to an abrasive article, etc. The industrial process unit 710 can include one or more sensors 702 that provide information about any of the following: the industrial process unit 710, the substrate, the consumable, the surrounding environment, the status of one or more components of the industrial process unit 710, or other information that can be relevant to the process design system 720. For example, the sensor 702 can include a position sensor that provides a detected distance between a dispenser tip and a substrate.

[0076] In another example, the sensor 702 can be in communication with a first control unit of the robotic polishing system and can provide an indication of the force applied to the substrate surface, the speed of rotation, etc.

[0077] The industrial process unit 710 can be a fixed unit, or can have one or more movement mechanisms 706. For example, in the context of fluid dispensing, the movement mechanism 706 can move the dispenser relative to a fixed substrate, or move the substrate relative to a fixed dispenser. In addition, the movement mechanism 706 can move the dispenser closer to or further away from the surface of the substrate.

[0078] The industrial process unit 710 includes a controller 708 that controls one or more actuators 704. The actuators 704 as described herein are intended to broadly cover any part of the industrial process unit 710 that can take action. For example, an adhesive dispenser can dispense any of a first component A, a second component B, an additive, or a combination thereof, each of which can have a separate actuator 704 associated with dispensing and controlling the flow rate.

[0079] A user of industrial process unit 710 may need to select parameter values ​​for a new process. For example, a dispensing line may need to be reconfigured to dispense a different adhesive. Or one or more components of the adhesive may be out of stock, and a new adhesive formulation may need to be selected to address the shortage. Process design system 720 may interact with the user, for example, via user device 750. User device 750 may have a configuration such as Figure 7 A display 754 is shown, however, it is expressly contemplated that a display is not required for every embodiment, and that a user may use a natural language feed interface or another suitable I / O device 756 .

[0080] The process design system 720 utilizes information from a data store 760 (which may be populated from prior experiments and / or application engineer knowledge) or another suitable data source to select operating parameter values ​​for implementation by the controller 708. The process design system 720 is a dynamic system that generates queries for a user to select a set of process parameters for the industrial process unit 710 based on information retrieved from the data store 760 or other source.

[0081] The constraint selection model 730 is a machine learning capable algorithm that generates queries for a user of the industrial process unit 710. The constraint receiver 732 receives information about operations to be performed by the industrial process unit 710. The information may be received from the sensor 702, such as from the data store 760, or by direct communication with the user, such as using the user device 750. The received constraints may include, for example, the current position of the robot arm relative to the substrate, the current component A and component B loaded into the adhesive dispensing unit, the ambient temperature, etc.

[0082] The constraint selection model 730 analyzes the constraint information received by the constraint retriever 734 and determines the next parameter of interest to design the process for the unit 710. For example, based on the constraint information received, the adhesive composition can be set, but the flow rate and temperature may still be uncertain. Therefore, the model 730 can ask the customer for the process rate (e.g., how fast should the adhesive be dispensed / how many adhesive operations should be completed during the conversion?) to obtain the constraint information required to set these parameter values.

[0083] In some embodiments, the process design system 720 may also include a substrate identifier 722 and / or an actuator identifier 724. The substrate identifier 722 may detect the substrate on which the process unit 710 will act. For example, the one or more sensors 702 may include an optical unit that images and identifies the substrate. However, the substrate identifier 722 may identify the substrate, for example, by accessing the data store 760. Once the substrate is known, the substrate parameters 774 for the industrial process unit 710 may be retrieved. Similarly, in some embodiments, the actuator identifier 724 may communicate with the controller 708 of the industrial process unit 710 to identify the industrial process unit 710.

[0084] Identifying the process unit 710 may include identifying the type of process unit 710, such as a robot arm to a distribution unit, and the make and / or model, in order to retrieve parameter constraint information, such as temperature range, motion speed range, etc. However, although the substrate identifier 722 and the actuator identifier 724 are Figure 7 7 is shown as a portion of the process design system 720 that automatically identifies the substrate and process unit 710 , but it is expressly contemplated that in some embodiments, a user may have to manually transfer this information to the process design system 720 .

[0085] In some embodiments, the process design system 720 also includes a sensor signal receiver 726 that can receive information from the sensor 702. However, the sensor signal receiver 726 can also receive sensor information from the data store 760. The sensor signal can be received in real time, delayed, or just from a previous operation of the process element 710.

[0086] Constraint hint selector 734 selects a hint or query to be presented to a user, such as using user device 750, based on the analysis performed by constraint selection model 730. For example, if viscosity is determined to be a parameter of interest, constraint hint selector 734 may retrieve constraint options 776 from data store 760, such as a minimum viscosity, a maximum viscosity, and an acceptable viscosity range.

[0087] The process design system 720 may also have other components 728. For example, in an embodiment where the process design system 720 communicates with a user device 750 that includes a display 754, the GUI generator 752 may generate a GUI for presentation on the display 754.

[0088] The process design system 720 may also include a model trainer 736 that adjusts the constraint selection model 730 based on user feedback. As described herein, in some embodiments, the constraint selection model 730 may interact with application engineers or other experts in the space during a training phase so that the model 730 may learn which parameters are of greater interest in different scenarios.

[0089] In some embodiments, the constraint selection model outputs the process parameters for the industrial process unit 710, but additional experiments may be useful for industrial processes where the interdependence of parameters is difficult to predict. For example, in the adhesive space, there may not be enough to fully ensure that a specific process parameter set will achieve the desired performance, aesthetics or other customer needs in the data storage 760. Therefore, in some embodiments, the experimental design device 740 can generate a process parameter set for testing, such as on the industrial process unit 710 or on different systems. The experimental feedback collector 742 can collect results. For example, the experimental design device 740 can communicate directly with the industrial process unit 710 to implement the process control parameter value selected by the constraint selection model 730. However, it should be clearly envisioned that the experimental design device 740 can also communicate with the GUI builder 752 to present instructions for the user to experiment on the display 754.

[0090] The data store 760 may include any information related to the constraint selection model 730. The consumable properties 762 may include any properties about the consumables used by the industrial process unit 710. For example, a robotic grinding system may benefit from a data store 760 that includes consumable properties 762 for a plurality of abrasive articles (e.g., bonded abrasive articles, nonwoven abrasive articles, coded discs, or other suitable abrasive articles), such as a cut rate and useful life for each abrasive article.

[0091] For individual consumables, the data store 760 may include data about performance 764, such as the adhesion of an adhesive or the cutting rate of an abrasive article. The data store 760 may also include aesthetic data 766, such as the color of the adhesive when cured, the smoothness of the adhesive when cured, etc. In addition, the data store 760 may include availability information 768, which may include pricing information and whether the consumable is currently in stock. In some embodiments, if the user indicates that there is time to order new components or consumables, the process design system 720 may ignore the availability data 768. The process needs to be implemented quickly, and the availability data 768 can allow the constraint selection model to ignore any out-of-stock or low-stock consumables when selecting process control parameters.

[0092] In some embodiments, the data store 760 also includes parameters associated with the industrial process unit 710, such as, in particular, actuator parameters 772 and substrate parameters 774. For example, the substrate parameters 774 may include whether a particular substrate has good adhesion to a given adhesive composition. The data store 760 may also include other suitable information 778.

[0093] For example, the model 730 can take into account a computer aided drawing (CAD) file from the user. The file can carry information related to the substrate type and the joint design. The user can upload the CAD file, and the model will then take into account the information first before asking subsequent questions. This will greatly improve the output quality and reduce the user's workload. In addition, in some embodiments, the process design system 710 is incorporated into the CAD software.

[0094] Some products have "simple" rules of thumb that can eliminate them from selection. For example, based on the CAD model, the surface area of ​​the bonding area can be calculated, and the force or stress will be applied. Some CAD models also take into account the substrate material. The 3D model can also show the allowed movements and constraints, so the direction of the stress can be known.

[0095] Additionally, the term "CAD" is used broadly herein and may refer to a 3D model, or a 3D model with additional information. For example, a finite element analysis (FEA) model may be built on top of a 3D model of a structure, which may allow for better predictions of stresses / strains / applied forces, etc.

[0096] The data store 760 may also include a material data card (MDC) of the consumable properties 762 in a file that can be imported into finite element analysis (FEA) software. The FEA software takes the base CAD model and applies a mesh to the design so that strains and stresses can be calculated numerically. In some embodiments, the model 730 is integrated into the FEA software along with the MDC as a plug-in and / or material library.

[0097] In some embodiments, a user may construct a typical CAD model and provide it with the stored MDC, FEA software, and model 730 providing process parameter values ​​and / or additional constraint requests.

[0098] It is expressly contemplated that in embodiments herein, the selection of which consumable to use is a parameter of interest for the constraint selection model 730. For example, a user of an adhesive dispenser is not required to select a specific adhesive, but rather the constraint selection model 730 selects the adhesive as part of a set of process control variables for the user.

[0099] Figures 8 to 9 An example user interface that can be presented to a process designer according to embodiments of the present invention is shown. However, it should be clearly contemplated that user interfaces 800 and 900 are presented for exemplary purposes only. In some embodiments, the user device does not include a display, or a different user interface can be presented.

[0100] like Figure 8 As shown in FIG. 8 , two different types of constraint queries are shown. Constraint query 810 may be a query actually presented to a user, which may be Figure 8 The display format shown may also be presented through other suitable mechanisms (such as natural language, etc.). Figure 8 The fixed constraint query 820 is shown as being grayed out so that the user cannot interact with it in some embodiments. The fixed constraint query 820 may be shown on the user interface 800, but in a manner that conveys to the user that they cannot be changed, or set based on other higher level (e.g., more important) parameters of interest. However, it is expressly contemplated that such queries are not shown, or presented to the user.

[0101] User interface 900 shows information that can be presented to a user when performing an experiment using a set of process parameters selected by a model according to embodiments herein. As shown, multiple sensed parameter values ​​and parameter values ​​selected by the model and information about the substrate are shown. Based on the deviation of the actual parameter values ​​from the modeled parameter values, corrective actions 910 are shown. In some embodiments, corrective actions 910 are taken automatically and may or may not be presented to the user.

[0102] Fig.10 A process design system architecture is shown in which example embodiments may be implemented. Fig.10 1 is a process design system architecture 1000, which illustrates one embodiment of a specific implementation of a process design system 1010. As an example, the system 1000 can provide computing, software, data access, and storage services without requiring the end user to know the physical location or configuration of the system delivering these services. In various embodiments, a remote server can deliver these services over a wide area network (such as the Internet) using an appropriate protocol. For example, a remote server can deliver applications over a wide area network, and they can be accessed through a web browser or any other computing component. Figures 1 to 9 The software or components shown or described and the corresponding data may be stored on a server at a remote location. The computing resources in a remote server environment may be consolidated at a remote data center location, or they may be dispersed. The remote server infrastructure may deliver services through a shared data center, even though they appear as a single access point for users. Therefore, the components and functions described herein may be provided from a remote server at a remote location using a remote server architecture. Alternatively, they may be provided by a conventional server installed directly on a client device, or otherwise provided.

[0103] exist Fig.10 In the example shown, some items are similar to those shown in previous figures. Fig.10 It is specifically shown that the systems 1010 can be located at a remote server location 1002. Thus, the computing device 1020 accesses those systems through the remote server location 1002. The operator 1050 can also use the computing device 1020 to access the user interface 1022.

[0104] Fig.10 It is shown that it should also be envisioned that some elements of the system described herein are arranged at the remote server location 1002, while other elements are not arranged at the remote server location. By way of example, storage device 1030, 1040 or 1060, or processing unit 1070 can be arranged at a location separated from position 1002, and accessed by a remote server at position 1002. No matter where they are located, they can be directly accessed by computing device 1020 using system 1010 through a network (wide area network or local area network), hosted at a remote site by a service, provided as a service, or accessed by a connection service residing in a remote location. In addition, data can be stored in any location basically, and can be intermittently accessed by interested parties or forwarded to interested parties. For example, a physical carrier can be used to replace an electromagnetic wave carrier, or a physical carrier can also be used in addition to an electromagnetic wave carrier.

[0105] It will also be noted that the elements of the systems described herein or portions thereof may be disposed on a variety of different devices. Some of these devices include servers, desktop computers, laptop computers, embedded computers, industrial controllers, tablet computers, or other mobile devices such as handheld computers, cellular phones, smart phones, multimedia players, personal digital assistants, etc.

[0106] Figures 11 to 13 An example device is shown that may be used in the embodiments shown in the previous figures. Fig.11 An example mobile device is shown that may be used in the embodiments shown in the previous figures. Fig.11 11 is a simplified block diagram of an illustrative example of a handheld computing device or mobile computing device that can be used by a user of the systems and methods discussed herein. For example, the system (or portions thereof) can be deployed locally on device 1116, or applications 1133 can use communication link 1113 to access the system or initiate the methods described herein. For example, the mobile device can be deployed in an operator compartment of a computing device for generating, processing, or displaying data.

[0107] Fig.11 A general block diagram of the components of a mobile cellular device 1116 that can run some of the components shown and described herein is provided. The mobile cellular device 1116 interacts with these components, or runs some components and interacts with some components. In the device 1116, a communication link 1113 is provided, which allows the handheld device to communicate with other computing devices, and in some embodiments provides a channel for automatically receiving information (such as by scanning). Examples of communication links 1113 include allowing communication through one or more communication protocols, such as wireless services for providing cellular access to a network, and protocols for providing local wireless connections to a network.

[0108] In other examples, the application may be received on a removable secure digital (SD) card connected to the interface 1115. The interface 1115 and the communication link 1113 communicate with the processor 1117 (which may also embody a processor) along a bus 1119, which is also connected to a memory 1121 and input / output (I / O) components 1123, as well as a clock 1125 and a position system 1127.

[0109] In one embodiment, I / O components 1123 are provided to facilitate input and output operations, and the device 1116 may include input components such as buttons, touch sensors, optical sensors, microphones, touch screens, proximity sensors, accelerometers, orientation sensors, and output components such as display devices, speakers, and / or printer ports. Other I / O components 1123 may also be used.

[0110] The clock 1125 illustratively includes a real-time clock component that outputs time and date. The clock can also provide a timing function for the processor 1117.

[0111] Illustratively, the location system 1127 includes components for outputting the current geographic location of the device 1116. The location system may include, for example, a global positioning system (GPS) receiver, a LORAN system, a dead reckoning system, a cellular triangulation system, or other positioning system. The location system may also include, for example, mapping software or navigation software that generates desired maps, navigation routes, and other geographic functions.

[0112] Memory 1121 stores operating system 1129, network settings 1131, applications 1133, application configuration settings 1135, data storage 1137, communication drivers 1139, and communication configuration settings 1141. Memory 1121 may include all types of tangible volatile and non-volatile computer-readable memory devices. The memory may also include computer storage media (described below). Memory 1121 stores computer-readable instructions that, when executed by processor 1117, cause the processor to perform computer-implemented steps or functions according to the instructions. Processor 1117 may also be activated by other components to facilitate its functionality. It should be clearly contemplated that although physical memory storage device 1121 is shown as part of the device, cloud computing options are available, where some data and / or processing are completed using remote services.

[0113] Fig.12 It is shown that the device may also be a smartphone 1271. The smartphone 1271 has a touch-sensitive display 1273 that displays icons or tiles or other user input mechanisms 1275. The mechanisms 1275 may be used by the user to run applications, make calls, perform data transfer operations, etc. In general, the smartphone 1271 is built on a mobile operating system and provides more advanced computing capabilities and connectivity than a non-smartphone. Note that other forms of devices are possible.

[0114] However, although Fig.12 An embodiment is shown in which the device 1200 is a smartphone 1271, but it is expressly contemplated that the display may be presented on another computing device as well.

[0115] Fig.13 is an example of a computing environment in which elements or portions thereof of the systems and methods described herein may be deployed, for example. Fig.13, an example system for implementing some embodiments includes a general purpose computing device in the form of a computer 1310. Components of the computer 1310 may include, but are not limited to, a processing unit 1320 (which may include a processor), a system memory 1330, and a system bus 1321 that couples various system components including the system memory to the processing unit 1320. The system bus 1321 may be any of a variety of types of bus structures including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures. The memories and programs described with respect to the systems and methods described herein may be deployed in Fig.10 in the corresponding part of .

[0116] Computer 1310 typically includes various computer-readable media. Computer-readable media can be any available media that can be accessed by computer 1310, and includes both volatile / non-volatile media and removable / non-removable media. By way of example and not limitation, computer-readable media can include computer storage media and communication media. Computer storage media is different from modulated data signals or carrier waves, and does not include modulated data signals or carrier waves. Computer storage media include hardware storage media, which include volatile / non-volatile and removable / non-removable media implemented in any method or technology to store information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage devices, cassettes, tapes, magnetic disk storage devices or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by computer 1310. Communication media can embody computer-readable instructions, data structures, program modules or other data in a transmission mechanism, and include any information delivery media. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.

[0117] The system memory 1330 includes computer storage media in the form of volatile and / or nonvolatile memory, such as read-only memory (ROM) 1331 and random access memory (RAM) 1332. A basic input / output system 1333 (BIOS), containing the basic routines that help to transfer information between elements within the computer 1310 (such as during startup), is typically stored in ROM 1331. RAM 1332 typically contains data and / or program modules that are immediately accessible to and / or currently being operated on by the processing unit 1320. By way of example and not limitation, Fig.13Operating system 1334 , application programs 1335 , other program modules 1336 , and program data 1337 are shown.

[0118] The computer 1310 may also include other removable / non-removable and volatile / non-volatile computer storage media. By way of example only, Fig.13 A hard disk drive 1341 is shown that reads from and writes to a non-removable, non-volatile magnetic medium, a non-volatile magnetic disk 1352, an optical drive 1355, and a non-volatile optical disk 1956. The hard disk drive 1341 is typically connected to the system bus 1321 through a non-removable memory interface, such as interface 1340, and the optical drive 1355 is typically connected to the system bus 1321 through a removable memory interface, such as interface 1350.

[0119] Alternatively or additionally, the functionality described herein may be at least partially performed by one or more hardware logic components. For example, but not limited to, exemplary types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (e.g., ASICs), application specific standard products (e.g., ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0120] The above discussed and Fig.13 The illustrated drives and their associated computer storage media provide storage of computer readable instructions, data structures, program modules and other data for the computer 1310. Fig.13 1344, application programs 1345, other program modules 1346, and program data 1347. Note that these components may be the same as or different from operating system 1334, application programs 1335, other program modules 1336, and program data 1337.

[0121] A user can enter commands and information into the computer 1310 through input devices such as a keyboard 1362, a microphone 1363, and a pointing device 1361, such as a mouse, trackball, or touch pad. Other input devices (not shown) may include a joystick, a game pad, a satellite dish, a scanner, or the like. These and other input devices are typically connected to the processing unit 1320 through a user input interface 1360 that is coupled to the system bus, but may be connected by other interface and bus structures. A visual display 1391 or other type of display device is also connected to the system bus 1321 via an interface, such as a video interface 1390. In addition to the monitor, the computer may also include other peripheral output devices such as speakers 1397 and a printer 1396, which may be connected through an output peripheral interface 1395.

[0122] The computer 1310 operates in a networked environment using logical connections, such as a local area network (LAN) or a wide area network (WAN), to one or more remote computers, such as remote computer 1380 .

[0123] When used in a LAN networking environment, the computer 1310 is connected to the LAN 1371 through a network interface or adapter 1370. When used in a WAN networking environment, the computer 1310 typically includes a modem 1372 or other means for establishing communications over the WAN 1373 (such as the Internet). In a networking environment, program modules may be stored in the remote memory storage device. Fig.13 It is shown that, for example, remote applications 1385 can reside on remote computer 1380 .

[0124] In the specific description of the preferred embodiment, reference is made to the accompanying drawings, which illustrate specific embodiments in which the present invention may be put into practice. Illustrative embodiments are not intended to be exhaustive of all embodiments according to the present invention. It should be understood that other embodiments may be utilized without departing from the scope of the present invention, and structural or logical changes may be made. Therefore, the following detailed description should not be considered to have a limiting meaning, and the scope of the present invention is limited by the appended claims.

[0125] Unless otherwise indicated, all numbers expressing feature sizes, amounts, and physical properties used in the specification and claims are to be understood in all instances as modified by the term “about.” Accordingly, unless indicated to the contrary, the numerical parameters set forth in the foregoing specification and the appended claims are approximations that may vary depending upon the desired properties sought to be obtained by one skilled in the art utilizing the teachings disclosed herein.

[0126] Unless the content clearly dictates otherwise, as used in the specification and the appended claims, the singular forms "a / kind", and "the" encompass embodiments having plural referents. Unless the content clearly dictates otherwise, as used in the specification and the appended claims, the term "or" is generally employed in its sense including "and / or".

[0127] If spatially relative terms are used herein, including but not limited to "proximal," "distal," "lower," "upper," "below," "below," "above," and "on top," they are used for convenience in describing the spatial relationship of one or more elements relative to another element. In addition to the specific orientations depicted in the drawings and described herein, such spatially relative terms encompass different orientations of the device when in use or operation. For example, if the object depicted in the figure is flipped or inverted, parts previously described as being below or under other elements should be above or on top of these other elements.

[0128] As used herein, for example, when an element, component or layer is described as forming a "consistent interface" with another element, component or layer, or "on it", "connected to it", "coupled to it", "stacked on it" or "in contact with it", it may be directly on it, directly connected to it, directly coupled to it, directly stacked on it or directly in contact with it, or for example, an intermediate element, component or layer may be on a specific element, component or layer, or connected to it, coupled to it or in contact with it. For example, when an element, component or layer is, for example, referred to as "directly on" another element, "directly connected to" another element, "directly coupled to" another element or "directly in contact with" another element, there is no intermediate element, component or layer. The technology disclosed herein can be implemented in a variety of computer devices, such as servers, laptop computers, desktop computers, notebook computers, tablet computers, handheld computers, smart phones and the like. Any component, module or unit is described as emphasizing functional aspects, and does not necessarily need to be implemented by different hardware units. The technology described herein can also be implemented in hardware, software, firmware or any combination thereof. Any features described as modules, units or components may be implemented together in an integrated logic device or may be implemented independently as discrete but cooperating logic devices. In some cases, various features may be implemented as integrated circuit devices (such as integrated circuit chips or chipsets). In addition, although a variety of different modules are described throughout this specification, many of which perform unique functions, all functions of all modules may be combined into a single module, or even split into additional modules. The modules described herein are exemplary only and are described in this manner for ease of understanding.

[0129] If implemented in software, the technology may be implemented at least in part by a computer-readable medium including instructions that, when executed in a processor, perform one or more of the methods described above. A computer-readable medium may include a tangible computer-readable storage medium and may form part of a computer program product, which may include packaging materials. A computer-readable storage medium may include a random access memory (RAM), such as a synchronous dynamic random access memory (SDRAM), a read-only memory (ROM), a non-volatile random access memory (NVRAM), an electrically erasable programmable read-only memory (EEPROM), a FLASH memory, a magnetic or optical data storage medium, or the like. A computer-readable storage medium may also include a non-volatile storage device, such as a hard disk, a magnetic tape, a compact disk (CD), a digital versatile disk (DVD), a Blu-ray disc, a holographic data storage medium, or other non-volatile storage device.

[0130] The term "processor" as used herein may refer to any of the aforementioned structures or any other structures suitable for implementing the embodiments of the technology described herein. In addition, in some respects, the functionality described herein may be provided in a dedicated software module or hardware module configured to perform the technology disclosed herein. Even if implemented in software, the technology may also use hardware (such as a processor) for executing software and a memory for storing software. In any such case, the computer described herein may define a specific machine capable of performing the specific functions described herein. In addition, the technology may be fully implemented in one or more circuits or logic elements (which may also be considered as processors).

[0131] An industrial process design system is proposed, which includes: a process constraint retriever, which receives parameter constraint indications for an industrial process. The system also includes: a parameter selector, which retrieves potential process design parameters for the industrial process. The parameter selector analyzes the parameter constraint indications. Based on the potential process design parameter set and the constraint indication analysis, the parameter selector selects the next parameter of interest. The parameter selector generates a constraint query for the selected next parameter. The parameter selector iteratively analyzes the received parameter constraint information, selects a new parameter of interest, and generates a new constraint query. The system also includes: a process design generator, which generates a process design parameter set based on the constraint query generated by the parameter selector.

[0132] The system according to claim 1 may be implemented such that the system comprises a query communicator which transmits the generated query.

[0133] The system may be implemented such that the query communicator includes a graphical user interface generator that generates a graphical user interface including the generated query.

[0134] The system may be implemented such that the query communicator includes a natural language generator.

[0135] The system may be implemented such that the process constraint retriever receives a constraint indication from a sensor.

[0136] The system may be implemented such that the sensor is a temperature sensor, a pressure sensor, a flow rate sensor, a mixing ratio sensor, a position sensor, a distance sensor, or a reflectivity sensor.

[0137] The system may be implemented such that the sensor is part of an industrial process.

[0138] The system may be implemented such that the sensor sends a sensor signal to a data store that is accessed by a process constraint retriever.

[0139] The system may be implemented such that the parameter constraint indicates a substrate.

[0140] The system may be implemented such that the parameter constraint indicates a condition of use of a product for an industrial process.

[0141] The system may be implemented such that the industrial process is an adhesive dispensing process and wherein the use condition is a temperature range.

[0142] The industrial process is an adhesive dispensing process, and wherein the parameter constraint information is an adhesive for coupling a second substrate to a first substrate using a substrate composition.

[0143] The system may be implemented such that the parameter selector designates at least one of the set of potential design process parameters as a constrained parameter based on the received indication. Based on the constrained parameter, the parameter selector selects a new parameter of interest.

[0144] The system may be implemented such that the parameter selector designates at least one of the set of potential design process parameters as a constrained parameter based on the received indication. Based on the constrained parameter, the parameter selector changes a weight of a second one of the set of potential process design parameters.

[0145] A method for generating a process design parameter set for an industrial process is provided, the method comprising: iteratively receiving a constraint indication for a first parameter in the process design parameter set; selecting a second parameter in the process design parameter set based on the received constraint indication; and generating a constraint query for the second parameter. The steps of receiving, selecting, and generating are repeated until the process design parameter set is fully constrained. The method also comprises: generating a process design test command including the process design parameter set.

[0146] The method may be implemented such that the method includes transmitting a process design test command to an industrial process such that the industrial process implements the set of process design parameters.

[0147] The method may be implemented such that the method includes transmitting a process design test command to a graphical user interface.

[0148] The method may be implemented such that generating a constrained query includes generating a natural language based query.

[0149] The method may be implemented such that the constraint indication is received by a microphone.

[0150] The method may be implemented such that selecting the second parameter includes designating the third parameter as a constrained parameter.

[0151] The method may be implemented such that selecting the second parameter comprises varying a weight of the second parameter relative to the third parameter.

[0152] The method may be implemented such that the third parameter is adhesive color, and the adhesive color is set based on the received substrate material.

[0153] The method may be implemented such that the received constraint indication is an operating temperature.

[0154] The method may be implemented such that the industrial process is an adhesive dispensing operation and the process design test commands are transmitted to an adhesive compounding unit.

[0155] The method may be implemented such that the received constraint indication is based on feedback from an adhesive compounding attempt.

[0156] An industrial process design system is presented, the industrial process design system including an industrial process unit having a set of configurable parameters. The system also includes a communication component configured to receive a parameter constraint indication for a first parameter in the set of configurable parameters. The system also includes a parameter selection module, which adjusts the set of configurable parameters based on the received parameter constraint indication by performing the following for a second parameter: changing a weight associated with a second parameter in the set; designating the second parameter as a fully constrained parameter; or generating a query related to the second parameter, wherein the query is transmitted using the communication component. The parameter selection module repeatedly adjusts the set of configurable parameters until a constrained parameter set for the industrial process is generated. The system also includes a controller that transmits the constrained parameter set to a device.

[0157] The system may be implemented such that the device is an industrial process unit.

[0158] The system may be implemented such that the device is a computing device having a display.

[0159] The system may be implemented such that the parameter constraint indication is received from an I / O device.

[0160] The system may be implemented such that the parameter constraint indication is a natural language signal received from a microphone.

[0161] The system may be implemented such that the parameter constraint indication is received from a sensor.

[0162] The system may be implemented such that the sensor is associated with an industrial process unit.

[0163] The system may be implemented such that the sensor is an ambient environment sensor.

[0164] The system may be implemented such that if a received constraint indication indicates that a first parameter has a higher priority than a second parameter, the parameter decreases a weight associated with the second parameter.

[0165] The system may be implemented such that if only one option remains, the second parameter is designated as the constrained parameter.

[0166] The system may be implemented such that if the parameter selection module detects that there are no options remaining for the second parameter, the parameter selection module overrides the received constraint input.

[0167] The system may be implemented such that the industrial process unit is an adhesive dispensing unit.

[0168] The system may be implemented such that the received constraint information is a product usage specification, the product usage specification comprising: usage temperature, substrate, or minimum adhesion.

[0169] The system may be implemented such that the constraint information received is a dispenser limitation including: a maximum flow rate, a mixing ratio limitation, or an operating temperature.

[0170] The system may be implemented such that the second parameter is a user preference including: adhesive thickness, adhesive color, or adhesive cost.

[0171] The system may be implemented such that the first parameter is a numerically expressed parameter and the second parameter is a non-numerically expressed parameter.

[0172] An adhesive dispensing design system is presented, the adhesive dispensing design system including an adhesive dispensing unit having a set of configurable parameters. The system also includes a communication component configured to receive a parameter constraint indication for a first parameter in the set of configurable parameters. The system also includes a parameter selection module that adjusts the set of configurable parameters based on the received parameter constraint indication by performing the following for a second parameter: changing a weight associated with a second parameter in the set; designating the second parameter as a fully constrained parameter; or generating a query related to the second parameter, wherein the query is transmitted using the communication component. The parameter selection module repeatedly adjusts the set of configurable parameters until a constrained set of parameters for an industrial process is generated. The system also includes a controller that transmits the constrained set of parameters to a device.

[0173] The system may be implemented such that the device is an adhesive dispensing unit.

[0174] The system may be implemented such that the device is a computing device having a display.

[0175] The system may be implemented such that the parameter constraint indication is received from an I / O device.

[0176] The system may be implemented such that the parameter constraint indication comprises a natural language signal received from a microphone.

[0177] The system may be implemented such that the parameter constraint indication is received from a sensor.

[0178] The system may be implemented such that the sensor is associated with an adhesive dispensing unit.

[0179] The system may be implemented such that the sensor is an ambient environment sensor.

[0180] The system may be implemented such that if a received constraint indication indicates that a first parameter has a higher priority than a second parameter, the parameter decreases a weight associated with the second parameter.

[0181] The system may be implemented such that if only one option remains, the second parameter is designated as the constrained parameter.

[0182] The system may be implemented such that if the parameter selection module detects that there are no options remaining for the second parameter, the parameter selection module overrides the received constraint input.

[0183] The system may be implemented such that the received constraint information is a product usage specification, the product usage specification comprising: usage temperature, substrate, or minimum adhesion.

[0184] The system may be implemented such that the constraint information received is a dispenser limitation including: a maximum flow rate, a mixing ratio limitation, or an operating temperature.

[0185] The system may be implemented such that the second parameter is a user preference including: adhesive thickness, adhesive color, or adhesive cost.

[0186] The system may be implemented such that the first parameter is a numerically expressed parameter and the second parameter is a non-numerically expressed parameter.

[0187] Example

[0188] These embodiments are for illustrative purposes only and are not meant to unduly limit the scope of the appended claims. Although the numerical ranges and parameters setting forth the broad scope of the present disclosure are approximate, the numerical values ​​set forth in the specific examples are recorded as accurately as possible. However, any numerical value inherently contains certain errors that are inevitably caused by the standard deviation found in the corresponding test measurements. At a minimum, and without attempting to limit the application of the doctrine of equivalents to the scope of the claims, each numerical parameter should at least be interpreted as taking into account the reported significant digits and by applying ordinary rounding.

[0189] Adhesives offer many benefits over traditional mechanical fasteners when joining two substrates together. However, the use of adhesives in industrial processes can also be more complex due to material properties, process conditions, and even the effects of process conditions on material properties. Each joining process has unique characteristics that make it difficult to fully optimize the process. In many cases, it is not possible to fully maximize all aspects of the process because shifting one process parameter will affect the optimal settings of other process parameters. Traditional systems and methods that attempt to address the complexity of optimizing parameters are often too rigid in their approach or limited in their effectiveness.

[0190] Take the example of an engineer trying to join ABS plastic to steel. ABS plastic is a class of materials that contains acrylonitrile, butadiene, and styrene. The definition of ABS does not include the ratios of these components, so ABS can mean many different things from both a mechanical and chemical perspective. Additionally, ABS is often molded with release agents that remain on the surface after production, which is important from a surface science perspective. Finally, ABS is a commodity material, which in many cases means that an end user who orders the material through their channel can receive a different material with each order. These differences illustrate the complexity of optimizing the adhesive bonding process, as these factors can greatly affect how a given adhesive performs on ABS and how to best process an adhesive for use on ABS.

[0191] In this example, the engineer types the substrates "Steel" and "ABS" into a graphical user interface (GUI), which is sent as the first process constraint. The system understands the complexity behind ABS, so it prioritizes the next parameter as whether the ABS is molded. The engineer responds that it is molded, so the system then chooses to collect the next parameter constraint, asking if solvents can be used in their facility. The engineer then confirms that their EHS does not allow the use of solvents, and this further limits the potential adhesive materials that may be suitable for this application. The system may request additional parameters, such as the processing open time for the adhesive, the color of the adhesive, or other parameters.

[0192] Conventional systems are likely to fail for a number of reasons. One reason may be that if certain key information is not collected, the recommendations will result in incorrect recommendations (e.g., a recommendation that solvent cleaning is required before use if solvent usage is not prompted as a parameter constraint). Conventional systems may also fail because they collect conflicting constraints, where no solution satisfies all constraints given, or they may tend to not allow the user to give all the required constraints, resulting in solutions that do not meet the end-use requirements.

[0193] The system treats each parameter constraint as a conditional constraint so that it can take conflicting constraints and then decide how to best proceed and how to optimize within the given constraints. For example, an engineer can specify that the material should be black and that it needs to join ABS to steel without solvent cleaning. If there is no black material that will perform, but a clear material that otherwise meets the constraints is available, then this clear material can be provided with details of why it was chosen. The system also knows that ABS is a variable material, so it will communicate this to the engineer by giving a confidence level in the solution that further helps the engineer design the process.

[0194] In addition, once the candidate adhesive material is selected, the system initiates the delivery of the material to the engineer using instructions on how to set, use and test the adhesive. In this example, the user has an adhesive dispenser, so the system also provides instructions for calibrating and testing using the dispenser. In view of the rheological properties of the two-part adhesive, only two static mixer nozzles will fully mix the adhesive and produce appropriate solidification. The system notifies the engineer that these parts will be needed. Once the engineer has tested the sample, they will input the result into the system, and the system recommends the optimal distribution flow rate range in view of the input. If there is a temperature sensor on the dispenser, the system can take this information into account, because the temperature can affect the dispensability of the adhesive and the resulting processability range.

[0195] In another example, the system first loads a computer-aided design (CAD) file into the system. The system extracts parameter constraints for the geometry and substrate material from the file. In view of the surface area of ​​the substrate, the system decides that double-sided tape may be a candidate for this application. To further constrain the problem, the system asks the user verbally, "What is the maximum temperature that the joint will experience?" The user answers verbally, "400F." The system similarly obtains constraints on the time spent at this temperature and whether the joint needs to be flexible or rigid. In view of the results, the system no longer needs any more information and therefore recommends a specific double-sided tape to be tested. Double-sided tapes are pressure-sensitive adhesives (PSAs) and therefore need to be activated by pressing them firmly against the substrate-contacting the substrate alone is not enough to form a strong bond.

[0196] This PSA requires a minimum pressure of 15 psi between the tape and the substrate. This is complicated by the fact that the production process equipment is set to deliver force rather than pressure. In addition, when the tape is between two substrates, the pressure generated on the top of the interlayer may be different from the pressure applied to the PSA because the geometry of the bonding area is usually different from the shape of the entire substrate. Given that the system has a CAD model, it is able to calculate the required pressure and convert it into a force setting that can be used with automatic processing equipment. Each PSA has a temperature use range and a preferred duration for pressure application. These parameters are set as process parameters that affect the range of use conditions and process settings, such as application rate and dwell time before force application after pressure is applied. Engineers use these process parameters and provide feedback to the system, which is further used to improve the process.

Claims

1. An industrial process design system, the industrial process design system comprising: a process constraint retriever that receives an indication of a parameter constraint for an industrial process; a parameter selector that retrieves a set of potential process design parameters for the industrial process, wherein the parameter selector: analyzing the parameter constraint indication; selecting a next parameter of interest based on the set of potential process design parameters and the constraint-indicative analysis; generating a constraint query for the next parameter of the selection; and wherein the parameter selector iteratively analyzes received parameter constraint information, selects new parameters of interest, and generates new constraint queries; and A process design generator generates a set of process design parameters based on the constraint query generated by the parameter selector.

2. The system according to claim 1, further comprising: A query communicator transmits the generated query.

3. The system according to claim 2, wherein: The query communicator includes a graphical user interface generator that generates a graphical user interface including the generated query.

4. The system according to any one of claims 1 to 3, wherein: The process constraint retriever receives constraint indications from sensors.

5. The system according to claim 4, wherein: The sensor is a temperature sensor, a pressure sensor, a flow rate sensor, a mixing ratio sensor, a position sensor, a distance sensor, or a reflectivity sensor.

6. The system according to any one of claims 1 to 5, wherein: The parameter constraint indicates the substrate composition.

7. A system according to any one of claims 1 to 6, wherein: The parameter constraints indicate usage conditions of a product for the industrial process.

8. The system according to claim 7, wherein: The industrial process is an adhesive dispensing process and wherein the use condition is a temperature range.

9. The system according to claim 6, wherein: The industrial process is an adhesive dispensing process, and wherein the parameter constraint information is a first substrate material.

10. The system according to any one of claims 1 to 9, wherein: The parameter selector designates at least one of the set of potential design process parameters as a constrained parameter based on the received indication, and wherein the parameter selector selects the new parameter of interest based on the constrained parameter.

11. The system according to any one of claims 1 to 10, wherein: The parameter selector designates at least one of the set of potential design process parameters as a constrained parameter based on the received indication, and wherein the parameter selector changes a weight of a second one of the set of potential process design parameters based on the constrained parameter.

12. A method of generating a set of process design parameters for an industrial process, the method comprising: Iteratively: receiving an indication of a constraint for a first parameter of the set of process design parameters; selecting a second parameter from the set of process design parameters based on the received constraint indication; generating a constraint query for the second parameter; and wherein the steps of receiving, selecting and generating are repeated until the set of process design parameters is fully constrained; as well as A process design test command including the process design parameter set is generated.

13. The method according to claim 12, further comprising: The process design test commands are transmitted to the industrial process so that the industrial process implements the set of process design parameters.

14. The method according to claim 12 or 13, further comprising: The process design test commands are transmitted to a graphical user interface.

15. The method according to any one of claims 1 to 14, wherein: The constraint indication is received by a microphone.

16. The method according to any one of claims 12 to 15, wherein: Selecting the second parameter includes designating the third parameter as a constrained parameter.

17. The method according to claim 1, wherein: Selecting the second parameter includes changing a weight of the second parameter relative to a third parameter.

18. The method according to claim 16, wherein: The third parameter is adhesive color, and wherein the adhesive color is set based on a received substrate material.

19. The method according to claim 17, wherein: The received constraint indication is an operating temperature.

20. The method according to claim 13, wherein: The industrial process is an adhesive dispensing operation and wherein the process design test commands are transmitted to an adhesive compounding unit.

21. An industrial process design system, the industrial process design system comprising: An industrial process unit having a set of configurable parameters; a communication component configured to receive a parameter constraint indication for a first parameter in the set of configurable parameters; A parameter selection module, wherein the parameter selection module adjusts the set of configurable parameters based on the received parameter constraint indication by performing the following for the second parameter: changing a weight associated with the second parameter in the set; designate the second parameter as a fully constrained parameter; or generating a query related to the second parameter, wherein the query is transmitted using the communication component; and wherein the parameter selection module repeatedly adjusts the set of configurable parameters until a constrained set of parameters for the industrial process is generated; and A controller transmits the constrained set of parameters to a device.

22. The system of claim 21, wherein: The device is the industrial process unit.

23. The system according to claim 21 or 22, wherein: The parameter constraint indication is received from a sensor.

24. The system of claim 23, wherein: The sensor is associated with the industrial process unit.

25. The system of claim 23, wherein: The sensor is an ambient environment sensor.

26. A system according to any one of claims 21 to 25, wherein: If the received constraint indication indicates that the first parameter has a higher priority than the second parameter, the parameter decreases a weight associated with the second parameter.

27. A system according to any one of claims 21 to 26, wherein: When only one option remains, the second parameter is designated as a constrained parameter.

28. A system according to any one of claims 21 to 27, and further wherein: If the parameter selection module detects that there are no remaining options for the second parameter, the parameter selection module overrides the received constraint input.

29. A system according to any one of claims 21 to 28, wherein: The industrial process unit is an adhesive dispensing unit.

30. The system of claim 29, wherein: The received constraint information includes: product usage specifications, including: usage temperature, substrate, or minimum adhesion; dispenser limitations, including: maximum flow rate, mixing ratio limitation, or operating temperature.

31. An adhesive dispensing design system, the adhesive dispensing design system comprising: an adhesive dispensing unit having a set of configurable parameters; a communication component configured to receive a parameter constraint indication for a first parameter in the set of configurable parameters; A parameter selection module, wherein the parameter selection module adjusts the set of configurable parameters based on the received parameter constraint indication by performing the following for a second parameter: changing a weight associated with the second parameter in the set; designate the second parameter as a fully constrained parameter; or generating a query related to the second parameter, wherein the query is transmitted using the communication component; and wherein the parameter selection module repeatedly adjusts the set of configurable parameters, until a constrained set of parameters for the industrial process is generated; and A controller transmits the constrained set of parameters to a device.

32. The system of claim 31, wherein: The device is an adhesive dispensing unit.

33. The system of claim 31, wherein: The device is a computing device having a display.

34. The system of claim 31, wherein: The parameter constraint indication is received from a sensor associated with the adhesive dispensing unit. The system of claim 34, wherein the sensor is an ambient environment sensor.

35. A system according to any one of claims 31 to 34, wherein: If the received constraint indication indicates that the first parameter has a higher priority than the second parameter, the parameter decreases a weight associated with the second parameter.

36. The system of claim 1, wherein: The received constraint information is a product usage specification, and the product usage specification includes: usage temperature, substrate, or minimum adhesion.

37. The system of claim 1, wherein: The first parameter is a parameter expressed numerically, and the second parameter is a parameter expressed non-numerically.

Images