Process parameter switching method and device for multi-variety production

Abstract

The application discloses a process parameter switching method and device for multi-variety production. The server method comprises the following steps: receiving a process parameter switching request sent by a manufacturing execution system for monitoring product production status, wherein the process parameter switching request carries production demand description information and a product batch model; automatically obtaining corresponding target process parameters according to the production demand description information, wherein the target process parameters are determined by using a preset comparison function, and the preset comparison function comprises a basic comparison term expression and a physical comparison term expression; pre-verifying the target process parameters to obtain a verification result; and in the case that the verification result indicates that the target process parameters pass the verification, binding the target process parameters to the product batch model and issuing the target process parameters to a device control layer. Therefore, by using the embodiment of the application, the time required for searching and inputting the process parameters is avoided, the device can be switched to a new production task more quickly, and therefore the production efficiency and product quality are significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of industrial automation, and in particular to a process parameter switching method and device for multi-variety production. BACKGROUND

[0002] In modern chemical, pharmaceutical, food and beverage industries, production equipment needs to frequently switch between producing different products to meet market diversification and individualization needs. For example, in the fine chemical industry, the same production equipment may need to switch between producing different products in a short period of time, and the production process parameters (such as temperature, pressure, flow, reaction time, feeding sequence, etc.) of each product are different. This multi-variety, small-batch production mode puts high requirements on the flexibility, stability and safety of the equipment.

[0003] In the prior art, the control of production equipment usually relies on the equipment control layer (such as DCS or PLC) and the upper-layer manufacturing execution system (such as MES). The operator manually inputs new process parameters into the equipment control layer according to the production plan. The manual input of process parameters or the selection of process parameters is not only time-consuming, but also prone to errors due to human operation, which affects product quality and production efficiency. Some automatic systems are also affected by model computing power during automatic operation, and the reaction is slow. There is no effective control system verification method for the production of multiple products, multiple processes, multiple devices, and multiple parameter control switching. SUMMARY

[0004] The embodiments of the present application provide a process parameter switching method and device for multi-variety production. In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not a general review, nor does it determine the key / important elements or delineate the protection scope of these embodiments. Its only purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] In a first aspect, the embodiments of the present application provide a process parameter switching method for multi-variety production, applied to a server, the method comprising:

[0006] The server receives a process parameter switching request sent by a manufacturing execution system for monitoring the production state of a product, and the process parameter switching request carries production demand description information and a product batch model;

[0007] The server automatically acquires corresponding target process parameters according to the production demand description information, and the target process parameters are determined by using a preset comparison function, the preset comparison function includes a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the keyword sequence of the production demand, and the physical comparison term expression is used to quantify the correlation between the process flowchart;

[0008] The server pre-verifies the target process parameter, and obtains a verification result.

[0009] The server binds the target process parameter to the product batch model in a case where the verification result indicates that the target process parameter passes the verification, and issues the target process parameter to a device control layer to switch the currently executed process parameter to the target process parameter.

[0010] In a second aspect, an embodiment of the present application provides a process parameter switching device for multi-variety production, and the device comprises:

[0011] The receiving module is configured to receive a process parameter switching request sent by a manufacturing execution system for monitoring a product production state, and the process parameter switching request carries production demand description information and a product batch model.

[0012] The obtaining module is configured to automatically obtain a corresponding target process parameter according to the production demand description information, and the target process parameter is determined by using a preset comparison function.

[0013] The pre-verification module is configured to pre-verify the target process parameter, and obtain a verification result.

[0014] The parameter issuing module is configured to bind the target process parameter to the product batch model in a case where the verification result indicates that the target process parameter passes the verification, and issue the target process parameter to a device control layer to switch the currently executed process parameter to the target process parameter.

[0015] The technical scheme provided by the embodiment of the present application can have the following beneficial effects:

[0016] In the embodiment of the present application, on the one hand, the manufacturing execution system can monitor the product production state in real time, and can issue a process parameter switching request to the server in time when it is necessary to switch the production of the next variety, and the server can automatically obtain a corresponding target process parameter, which does not need manual intervention, avoids the time required for searching and inputting the process parameter, and enables the device to switch to a new production task more quickly, thereby significantly improving the production efficiency and shortening the production cycle. On the other hand, the target process parameter is determined by using a preset comparison function, the preset comparison function comprises a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the production demand keyword sequences, and the physical comparison term expression is used to quantify the correlation between the process flowcharts. By comprehensively considering the correlation of the production demand and the correlation of the process flow, accurate process parameters can be quickly obtained depending on the historical production data of each variety, and the product quality is improved.

[0017] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application, as claimed. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and serve to explain the principles of the application, in which, like reference numerals designate corresponding parts throughout the several views.

[0019] Figure 1 is a method flow diagram of a process parameter switching method for multi-variety production provided by an embodiment of the application;

[0020] Figure 2 is a process flow diagram of a pre-verification process provided by an embodiment of the application;

[0021] Figure 3 is a process flow diagram of a process parameter switching process for multi-variety production provided by an embodiment of the application;

[0022] Figure 4 is a model fine-tuning method flow diagram of a keyword extraction model provided by an embodiment of the application;

[0023] Figure 5 is a structural diagram of a process parameter switching device for multi-variety production provided by an embodiment of the application;

[0024] Figure 6 is a structural diagram of an electronic device provided by an embodiment of the application. DETAILED DESCRIPTION

[0025] The following description and drawings are illustrative of the specific embodiments of the present application and are not intended to limit the generality of the application as set forth in the claims.

[0026] It should be noted that the described embodiments are merely a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0027] The following description refers to the accompanying drawings. Unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in this exemplary description are not meant to represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the application as detailed in the appended claims.

[0028] In the description of the present application, it is understood that the terms "first", "second" and the like are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to the specific circumstances. In addition, in the description of the present application, "a plurality of" means two or more, unless otherwise specified. The association relationship of the associated objects is described, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after it.

[0029] Currently, the control of production equipment usually relies on the equipment control layer (such as DCS or PLC) and the upper layer manufacturing execution system (such as MES). The operator manually inputs new process parameters into the equipment control layer according to the production plan. The way of manually inputting process parameters or selecting process parameters not only consumes time, but also is prone to cause parameter errors due to human operation errors, affecting product quality and production efficiency.

[0030] The applicant of the present application realizes that this way completely depends on the working experience and attention of the operator, and is prone to cause monitoring errors due to fatigue or negligence of the operator. In addition, manual observation is difficult to accurately capture and record key details in the operation process. This monitoring method has low timeliness and accuracy, thereby causing unstable product quality.

[0031] In order to solve the above problems, the present application provides a process parameter switching method and device for multi-variety production to solve the problems existing in the above related technical problems. In the embodiments of the present application, on the one hand, the manufacturing execution system can monitor the product production state in real time, and can timely issue a process parameter switching request to the server when the production of the next variety needs to be switched, and the server can automatically obtain the corresponding target process parameter. This process does not require manual intervention, avoids the time required for searching and inputting process parameters, enables the equipment to be switched to a new production task more quickly, thereby significantly improving production efficiency and shortening the production cycle. On the other hand, the target process parameter is determined by using a preset comparison function, the preset comparison function includes a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the production demand keyword sequence, and the physical comparison term expression is used to quantify the correlation between the process flowchart. By comprehensively considering the correlation of production demand and the correlation of process flow, accurate process parameters can be quickly obtained depending on the historical production data of each variety, thereby improving product quality, which will be described in detail below by exemplary embodiments.

[0032] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which: Figure 1 -Appendix Figure 4The method for switching process parameters for multi-variety production provided by the embodiment of the application is introduced in detail. The method can be realized by relying on a computer program and can be run on a process parameter switching device for multi-variety production based on the Von Neumann system. The computer program can be integrated in an application or can be run as an independent tool application.

[0033] Please refer to Figure 1 A flowchart of a method for switching process parameters for multi-variety production provided by the embodiment of the application is provided, which is applied to a server. As shown in Figure 1 The method of the embodiment of the application includes the following steps:

[0034] S101, the server receives a process parameter switching request sent by a manufacturing execution system for monitoring the production state of a product. The process parameter switching request carries production demand description information and a product batch model.

[0035] In the production system, the server is a software system running on a server and is used for managing and controlling a production process. The manufacturing execution system (MES) is a software system for monitoring and managing a production process. By collecting production data in real time, the state of a production device can be monitored and the smooth progress of a production task can be ensured. The process parameter switching request is a request sent by the MES system to the server and is used for indicating that the current process parameters need to be switched. The production demand description information is a specific description of a current production task and includes the type, specification, quality requirement, production process requirement and the like of a product. The product batch model is a code or name used for identifying different batches of products.

[0036] In one possible implementation manner, the MES system judges that the current production task needs to switch process parameters according to a production plan or real-time monitoring data. At this time, the MES system generates a process parameter switching request, which contains the production demand description information and the product batch model. The server receives the process parameter switching request sent by the MES system through a network interface (such as HTTP, TCP / IP and the like). The server analyzes the request content and can extract the production demand description information and the product batch model.

[0037] A process parameter switching request in JSON format is as follows, for example:

[0038] {"request_id":"REQ123456789","timestamp": "2025-06-17T10:30:00Z","production_demand_info": {"product_name": "Chemical Product A", "product_specification": {"chemical composition": {"component A": "50%", "component B": "30%", "component C": "20%"}, "purity requirement": "≥99.5%", "appearance": "colorless and transparent liquid", "quality requirement": {"heavy metal content": "<10ppm", "moisture content": "<0.1%"}}, "process requirement": {"reaction temperature": "100-120°C", "reaction pressure": "1-2MPa", "reaction time": "4 hours", "stirring speed": "50-100rpm"}}, "batch_model": "Batch_20250617_Chemical Product A", "additional_notes": "This batch of products requires strict control of reaction conditions to ensure product quality meets standards."}

[0039] In some embodiments of the present application, the process of automatically obtaining the target process parameters corresponding to the production demand description information includes: inputting the production demand description information into a pre-tuned keyword extraction model, outputting the production demand keyword sequence corresponding to the production demand description information, and the pre-tuned keyword extraction model is obtained by fine-tuning a large language model using professional knowledge for multi-variety production industry; using a preset comparison function to analyze the overall comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database, the preset multi-variety database is obtained by collecting and preprocessing the historical production data of each variety; extracting the currently executed process parameters from the historical production data of the variety corresponding to the largest non-zero overall comparison value; adjusting the redundant parameters in the currently executed process parameters to obtain the target process parameters corresponding to the production demand description information.

[0040] In some embodiments of the present application, the target process parameters refer to the operating parameters of the production equipment that need to be set to meet the production demand, including temperature, pressure, time, flow, etc., which directly affect the quality of the product.

[0041] In some embodiments of the present application, the process of automatically obtaining the target process parameters corresponding to the production demand description information includes: inputting the production demand description information into a pre-tuned keyword extraction model, outputting the production demand keyword sequence corresponding to the production demand description information, and the pre-tuned keyword extraction model is obtained by fine-tuning a large language model using professional knowledge for multi-variety production industry; using a preset comparison function to analyze the overall comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database, the preset multi-variety database is obtained by collecting and preprocessing the historical production data of each variety; extracting the currently executed process parameters from the historical production data of the variety corresponding to the largest non-zero overall comparison value; adjusting the redundant parameters in the currently executed process parameters to obtain the target process parameters corresponding to the production demand description information.

[0042] The pre-tuned keyword extraction model is a model tuned for extracting keyword sequences from production demand description information. The model is based on a large language model (such as BERT, GPT, etc.) and is tuned using professional knowledge for the multi-variety production industry. The production demand keyword sequence is a keyword sequence extracted from the production demand description information, which represents the core content of the production demand. The pre-set multi-variety database is a database containing historical production data of various varieties, which provides reference for historical production data. The redundant parameters are parameters that are not related or unnecessary for the current production demand.

[0043] In the embodiments of the present application, by inputting the production demand description information into the pre-tuned keyword extraction model, the system can quickly extract the core keyword sequence of the production demand. Using the pre-set comparison function, the system further analyzes the similarity between these keyword sequences and the historical production data in the pre-set multi-variety database, and finds the most matching historical production data. On this basis, the system extracts the process parameters currently executed and adjusts the redundant parameters among them, and finally generates target process parameters that accurately match the current production demand. This process not only improves the accuracy and efficiency of process parameter selection, but also reduces human error, ensures the stability of production and the consistency of product quality, and is very suitable for the case where the product variety is large, the process is multiple, the parameter adjustment is multiple, the equipment control program switching is frequent. The historical production data in the pre-set multi-variety database is shown in Table 1, for example.

[0044] Table 1

[0045]

[0046] The function expression of the pre-set comparison function is:

[0047]

[0048] wherein, is the overall comparison value, is the semantic similarity weight, the value range is , the default value is , is the topological similarity weight, the value range is , the default is , is the basic comparison value, is the physical comparison item value;

[0049] The expression of the basic comparison item is:

[0050]

[0051] wherein, For the basic comparison item values, This is the current vector set of keywords related to production demand. For each variety, there is a historical vector set. The number of keywords required for production needs, The number of historical keywords corresponding to each variety. This represents the number of semantic intersections between production demand keywords and the historical keywords corresponding to each product variety.

[0052] The physical comparison term expression is:

[0053]

[0054] in, For physical comparison terms, This is a directed graph with a topological topology for the first process, where nodes represent different reactors and edges represent material flow directions. A directed graph representing a historical process flow diagram. for The total number of nodes, for The total number of nodes, Let be the graph edit distance between the first process topology directed graph and each of the second process topology directed graphs. The total number of nodes in the directed graph of the process topology with the most nodes or edges.

[0055] It should be noted that, in order to ensure the accuracy of the matching, a system was designed... When the semantics of production demand keywords and historical keywords corresponding to each product variety have no overlap, the value of the basic comparison item is 0. It can be 0, leading to the final When the value is 0, the historical production data of varieties corresponding to zero comparison values ​​can be accurately filtered out, so that the currently executed process parameters can be extracted from the historical production data of varieties corresponding to the largest non-zero overall comparison value.

[0056] In the embodiments of this application, by designing basic comparison term expressions, the parameter generalization problem caused by relying solely on the directed graph of process topology can be prevented.

[0057] In some embodiments of the present application, the specific process of analyzing the comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database includes: obtaining the historical production data of each variety in the preset multi-variety database; inputting the historical production data of each variety into the pre-tuned keyword extraction model to output the historical production demand keyword sequence corresponding to each variety; calculating the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequence corresponding to each variety according to the basic comparison item expression; obtaining the current process flow diagram of the required product variety based on the production demand keyword sequence; calculating the physical comparison item value between the current process flow diagram and the historical process flow diagram of each variety according to the physical comparison item expression; and weighting the product of the basic comparison value and the physical comparison item value to obtain the overall comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database.

[0058] The historical production demand keyword sequence is a keyword sequence extracted from the production data of each variety and used to represent the core content of the historical production demand. The process flow diagram refers to a process flow diagram generated according to the production demand and describes the specific process steps and flow of the production task.

[0059] In some embodiments of the present application, the process of calculating the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequence corresponding to each variety includes: converting the production demand keyword sequence into a vector set to obtain a current vector set; converting the historical production demand keyword sequence corresponding to each variety into a vector set to obtain a historical vector set corresponding to each variety; calculating the semantic similarity between the current vector set and the historical vector set corresponding to each variety; and taking the semantic similarity as the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequence corresponding to each variety.

[0060] For example, the production demand keyword sequence is [granulation, tabletting], and a historical production demand keyword sequence is [granulation, coating]. It can be known that only "granulation" , so .

[0061]

[0062] In some embodiments of the present application, the specific process of calculating the physical comparison value between the current process flow chart and the historical process flow chart of each product variety includes: converting the current process flow chart into a first process topology directed graph composed of nodes and edges; converting the historical process flow chart of each product variety into a second process topology directed graph composed of nodes and edges; calculating the minimum number of required editing operations for adding, deleting or modifying nodes or edges between the first process topology directed graph and each second process topology directed graph to obtain the graph editing distance between the first process topology directed graph and each second process topology directed graph; counting the total number of nodes of the process topology directed graph with the most nodes or edges in the first process topology directed graph and each second process topology directed graph; calculating the difference between the graph editing distance and the total number of nodes to obtain the process topology similarity between the current process flow chart and the historical process flow chart of each product variety; and taking the process topology similarity as the physical comparison value between the current process flow chart and the historical process flow chart of each product variety.

[0063] For example, the first process topology directed graph is: mixing → reaction → drying (3 nodes), and a second process topology directed graph is mixing → reaction → filtration → packaging (4 nodes), and at this time, the GED = 2 (1 node needs to be added + 1 edge needs to be modified).

[0064]

[0065] Further, if the total overall comparison value is 0, it indicates that there is no similar product variety in the preset multi-product variety database at this time, at which time manual operation can be switched to, and prompt information can be generated and sent to the early warning client for early warning and reminding.

[0066] In some embodiments of the present application, the specific process of automatically obtaining the corresponding target process parameter according to the production demand description information includes: loading a pre-established mapping relationship between process parameter version numbers and process parameters; querying the target process parameter version number in the production demand description information; obtaining the target process parameter corresponding to the target process parameter version number from the mapping relationship; and taking the target process parameter as the target process parameter corresponding to the production demand description information.

[0067] In the embodiments of the present application, the pre-established mapping relationship between the process parameter version numbers and the process parameters establishes a one-to-one relationship, so that the corresponding process parameter can be accurately found, and the accuracy is high, but the parameter configuration workload in the early stage is large.

[0068] In some embodiments of the present application, the specific process of automatically obtaining the corresponding target process parameter according to the production demand description information includes: loading a pre-established mapping relationship between process parameter version numbers and process parameters; querying the target process parameter version number in the production demand description information; obtaining the target process parameter corresponding to the target process parameter version number from the mapping relationship; and taking the target process parameter as the target process parameter corresponding to the production demand description information.

[0069] The pre-check ensures that the target process parameter meets the operation requirements of the production equipment, the standards of the production process and the safety specifications, and avoids production failure or equipment damage caused by parameter errors.

[0070] wherein each target process parameter comprises a target process identity and a target attribute value.

[0071] In some embodiments, the specific process of pre-verifying the target process parameter to obtain the verification result comprises: reading, from a configuration file or a database of the device, a plurality of parameter ranges supported by a device control layer, each parameter range comprising a process identity and an attribute value range; determining, from the process identity and the attribute value range included in each parameter range, whether an attribute value range corresponding to a same process identity as the target process identity contains the target attribute value; if yes, generating a verification result indicating that the target process parameter passes the verification; and if no, generating a verification result indicating that the target process parameter fails the verification.

[0072] For example, the target process parameter is:

[0073] Chemical composition: component A: 50%, component B: 30%, component C: 20%, purity requirement: ≥99.5%, appearance: colorless transparent liquid, reaction temperature: 100-120°C, reaction time: 3.8 hours, reaction pressure: 1-2 MPa, stirring speed: 50-100 rpm.

[0074] For example, the partial parameter range is: reaction temperature: must be within the temperature range allowed by the device (such as 80-150°C). Reaction pressure: must be within the pressure range allowed by the device (such as 0.5-3 MPa). Reaction time: must be within a reasonable production cycle range (such as 1-6 hours). Stirring speed: must be within the speed range allowed by the device (such as 30-120 rpm). By comparison, the relevant verification result can be determined.

[0075] For example Figure 2 as shown, Figure 2 is a flowchart of a pre-verification process provided by the present application, which reads a plurality of parameter ranges supported by a device control layer, each parameter range comprising a process identity and an attribute value range, determines whether the process identity and the attribute value range included in each parameter range contain the target process parameter, and if yes, generates a verification result indicating that the target process parameter passes the verification; and if no, generates a verification result indicating that the target process parameter fails the verification.

[0076] S104, in the case where the verification result indicates that the target process parameter passes the verification, the server binds the target process parameter to a product batch model and issues it to the device control layer to switch the currently executed process parameter to the target process parameter.

[0077] wherein the product batch model refers to a code or name used to identify different batches of products. The device control layer refers to a system or software that directly controls the operation of a production device.

[0078] Further, the device control layer receives the process parameters issued by the server and applies them to the production equipment to complete the switching of the process parameters. For example, after the PLC system receives the parameters, it updates the operating parameters of the equipment and starts operating according to the new parameters.

[0079] For example Figure 3 As shown, Figure 3 is a process schematic block diagram of a process parameter switching process for multi-variety production provided by the present application. First, the manufacturing execution system sends a process parameter switching request to the server. The server analyzes the information in the request and the production demand keywords and process flowcharts in the preset multi-variety database based on a preset comparison function to determine the target process parameters and checks them, and then issues them to the device control layer for production process parameter switching.

[0080] In the embodiments of the present application, on the one hand, the manufacturing execution system can monitor the product production state in real time, and when it is necessary to switch to the production of the next variety, it can timely issue a process parameter switching request to the server, and the server can automatically obtain the corresponding target process parameters. This process does not require manual intervention, avoids the time required for searching and inputting process parameters, enables the equipment to switch to a new production task more quickly, and thus significantly improves the production efficiency and shortens the production cycle. On the other hand, the target process parameters are determined by using a preset comparison function, the preset comparison function includes a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the production demand keyword sequence, and the physical comparison term expression is used to quantify the correlation between the process flowcharts. By comprehensively considering the correlation of the production demand and the correlation of the process flow, accurate process parameters can be quickly obtained depending on the historical production data of each variety, and thus the product quality is improved.

[0081] Please refer to Figure 4 is a process schematic diagram of a keyword extraction model fine-tuning method provided by the embodiments of the present application. As shown Figure 4 The method of the embodiments of the present application can include the following steps:

[0082] S201, collect preset professional knowledge for multi-variety production industry;

[0083] The professional knowledge for multi-variety production industry refers to the knowledge related to multi-variety production, such as technology, process, management, etc. These knowledge includes production process parameters, quality control standards, equipment operation requirements, etc.

[0084] In some embodiments of the present application, the types of professional knowledge required for collection include production process parameters (such as temperature, pressure, time, etc.), quality control standards (such as purity requirements, appearance requirements, etc.), equipment operation requirements (such as the temperature range and pressure range allowed by the equipment), production flowcharts, and historical production data (including successful and failed cases). The data sources include internal documents of the enterprise, historical production records, expert experience, industry standards and specifications, and external databases.

[0085] S202, adjusting model parameters of the large language model to obtain a keyword extraction model;

[0086] S203, inputting the preset professional knowledge facing the multi-variety production industry into the keyword extraction model for model fine-tuning to obtain a pre-fine-tuned keyword extraction model.

[0087] In the embodiments of the present application, on the one hand, the manufacturing execution system can monitor the product production state in real time, and when it is necessary to switch the production of the next variety, it can timely issue a process parameter switching request to the server, and the server can automatically obtain the corresponding target process parameter. This process does not require manual intervention, avoids the time required for searching and inputting process parameters, enables the equipment to switch to a new production task more quickly, and thus significantly improves the production efficiency and shortens the production cycle. On the other hand, the target process parameter is determined by using a preset comparison function, the preset comparison function includes a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the production demand keyword sequences, and the physical comparison term expression is used to quantify the correlation between the process flowcharts. By comprehensively considering the correlation of production demand and the correlation of process flow, accurate process parameters can be quickly obtained depending on the historical production data of each variety, and thus the product quality is improved.

[0088] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, please refer to the method embodiments of the present application.

[0089] Please refer to Figure 5 which shows a structure schematic diagram of a process parameter switching device for multi-variety production provided by an example embodiment of the present application. The process parameter switching device for multi-variety production can be realized by software, hardware, or a combination of both to become all or part of an electronic device. The device 1 includes a receiving module 10, an obtaining module 20, a pre-inspection module 30, and a parameter issuing module 40.

[0090] The receiving module 10 is configured to receive a process parameter switching request sent by a manufacturing execution system for monitoring the product production state, the process parameter switching request carrying production demand description information and a product batch model;

[0091] The acquisition module 20 is configured to acquire the target process parameters corresponding to the production demand description information automatically, the target process parameters are determined by using a preset comparison function, the preset comparison function includes a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the production demand keyword sequences, and the physical comparison term expression is used to quantify the correlation between the process flowcharts.

[0092] The pre-inspection module 30 is configured to pre-verify the target process parameters to obtain a verification result.

[0093] The parameter issuing module 40 is configured to bind the target process parameters to a product batch model and issue the target process parameters to a device control layer to switch the currently executed process parameters to the target process parameters when the verification result indicates that the target process parameters pass the verification.

[0094] It should be noted that the process parameter switching device for multi-variety production provided in the above embodiments is used to execute the process parameter switching method for multi-variety production, and only the division of the above functional modules is used as an example for description, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above-described functions. In addition, the process parameter switching device for multi-variety production and the process parameter switching method for multi-variety production provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be described here.

[0095] The serial numbers of the embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.

[0096] In the embodiments of the present application, on the one hand, the manufacturing execution system can monitor the product production state in real time, and can issue a process parameter switching request to the server in time when it is necessary to switch the production of the next variety, and the server can automatically acquire the corresponding target process parameters. This process does not require manual intervention, avoids the time required for searching and inputting process parameters, enables the device to switch to a new production task more quickly, and thus significantly improves the production efficiency and shortens the production cycle. On the other hand, the target process parameters are determined by using a preset comparison function, the preset comparison function includes a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the production demand keyword sequences, and the physical comparison term expression is used to quantify the correlation between the process flowcharts. By comprehensively considering the correlation of the production demand and the correlation of the process flow, accurate process parameters can be quickly acquired depending on the historical production data of each variety, and thus the product quality is improved.

[0097] The application further provides a computer readable medium, which stores program instructions, and the program instructions are executed by a processor to implement the process parameter switching method for multi-variety production provided by each method embodiment.

[0098] The application further provides a computer program product containing instructions, which, when running on a computer, causes the computer to execute the process parameter switching method for multi-variety production of each method embodiment.

[0099] Please refer to Figure 6 A structural schematic diagram of an electronic device is provided for the embodiments of the application. As shown in the figure, the electronic device 1000 can include at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002. Figure 6

[0100] The communication bus 1002 is used to realize the connection and communication between the components.

[0101] The user interface 1003 can include a display screen (Display) and a camera (Camera), and the optional user interface 1003 can further include a standard wired interface and a wireless interface.

[0102] The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0103] ​The processor 1001 can include one or more processing cores. The processor 1001 connects various parts within the entire electronic device 1000 through various interfaces and lines, and performs various functions of the electronic device 1000 and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Alternatively, the processor 1001 can be implemented in at least one of a hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA). The processor 1001 can integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes an operating system, a user interface, and an application program; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; and the modem is used for processing wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 1001, but can be realized by a separate chip.

[0104] The memory 1005 can include a random access memory (RAM) and can also include a read-only memory (ROM). Alternatively, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets, or instruction sets. The memory 1005 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 1005 can alternatively be at least one storage system located away from the aforementioned processor 1001. As shown in the figure, the memory 1005 as a computer storage medium can include an operating system, a network communication module, a user interface module, and a process parameter switching application program for multi-variety production. Figure 6

[0105] In Figure 6 ​In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an interface for user input and obtain data input by the user, and the processor 1001 can be used to call the process parameter switching application for multi-variety production stored in the memory 1005 and specifically perform the following operations:

[0106] receiving a process parameter switching request sent by a manufacturing execution system for monitoring the production status of a product, the process parameter switching request carrying production demand description information and a product batch model;

[0107] automatically obtaining corresponding target process parameters according to the production demand description information, the target process parameters being determined using a preset comparison function, the preset comparison function including a basic comparison term expression and a physical comparison term expression, the basic comparison term expression being used to quantify the correlation between the production demand keyword sequence, and the physical comparison term expression being used to quantify the correlation between the process flowcharts;

[0108] pre-verifying the target process parameters to obtain a verification result;

[0109] in a case where the verification result indicates that the target process parameters pass the verification, binding the target process parameters to the product batch model and issuing the target process parameters to a device control layer to switch the currently executed process parameters to the target process parameters.

[0110] In an embodiment, when the processor 1001 executes the operation of automatically obtaining corresponding target process parameters according to the production demand description information, the processor 1001 specifically performs the following operations:

[0111] inputting the production demand description information into a pre-tuned keyword extraction model to output a production demand keyword sequence corresponding to the production demand description information, the pre-tuned keyword extraction model being obtained by tuning a large language model using professional knowledge in the multi-variety production industry;

[0112] analyzing the overall comparison value between the production demand keyword sequence and the historical production data of each variety in a preset multi-variety database using the preset comparison function, the preset multi-variety database being obtained by collecting and preprocessing the historical production data of each variety;

[0113] extracting the currently executed process parameters from the historical production data of the variety corresponding to the largest non-zero overall comparison value;

[0114] adjusting the redundant parameters in the currently executed process parameters to obtain the target process parameters corresponding to the production demand description information.

[0115] In an embodiment, when the processor 1001 executes the operation of analyzing the comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database, the processor 1001 specifically performs the following operations:

[0116] obtain historical production data of each variety in the preset multi-variety database;

[0117] input the historical production data of each variety into the pre-tuned keyword extraction model, and output a historical production demand keyword sequence corresponding to each variety;

[0118] According to the basic comparison item expression, calculate the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequence corresponding to each variety;

[0119] Based on the production demand keyword sequence, obtain the current process flowchart of the required product variety;

[0120] According to the physical comparison item expression, calculate the physical comparison item value between the current process flowchart and the historical process flowchart of each variety;

[0121] The basic comparison value and the physical comparison item value are weighted and multiplied to obtain the overall comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database.

[0122] In one embodiment, when the processor 1001 performs the calculation of the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequence corresponding to each variety, it specifically performs the following operations:

[0123] Convert the production demand keyword sequence into a vector set to obtain a current vector set;

[0124] Convert the historical production demand keyword sequence corresponding to each variety into a vector set to obtain a historical vector set corresponding to each variety;

[0125] Calculate the semantic similarity between the current vector set and the historical vector set corresponding to each variety;

[0126] The semantic similarity is taken as the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequence corresponding to each variety.

[0127] In one embodiment, when the processor 1001 performs the calculation of the physical comparison item value between the current process flowchart and the historical process flowchart of each variety, it specifically performs the following operations:

[0128] Convert the current process flowchart into a first process topology directed graph composed of nodes and edges;

[0129] Convert the historical process flowchart of each variety into a second process topology directed graph composed of nodes and edges;

[0130] Calculate the minimum number of editing operations required for adding, deleting, or modifying nodes or edges between the first process topology directed graph and each second process topology directed graph to obtain the graph editing distance between the first process topology directed graph and each second process topology directed graph;

[0131] Count the total number of nodes in the process topology directed graph with the most nodes or edges in the first process topology directed graph and each second process topology directed graph;

[0132] Calculate the difference between the ratio of the graph editing distance and the total number of nodes to obtain the process topology similarity between the current process flowchart and the historical process flowchart of each variety;

[0133] The process topology similarity is used as the physical comparison item value between the current process flowchart and the historical process flowchart of each variety.

[0134] In one embodiment, the processor 1001 specifically performs the following operations when generating the pre-tuned keyword extraction model:

[0135] Collecting pre-set professional knowledge facing multi-variety production industries;

[0136] Adjusting the model parameters of the large language model to obtain the keyword extraction model;

[0137] Inputting the pre-set professional knowledge facing multi-variety production industries into the keyword extraction model for model fine-tuning to obtain the pre-tuned keyword extraction model.

[0138] In one embodiment, the processor 1001 specifically performs the following operations when automatically obtaining the corresponding target process parameters according to the production demand description information:

[0139] Loading the mapping relationship between the pre-established process parameter version number and the process parameter;

[0140] In the production demand description information, querying the target process parameter version number;

[0141] From the mapping relationship, obtain the target process parameter corresponding to the target process parameter version number;

[0142] The target process parameter is used as the target process parameter corresponding to the production demand description information.

[0143] In one embodiment, the processor 1001 specifically performs the following operations when pre-verifying the target process parameter to obtain a verification result:

[0144] Reading a plurality of parameter ranges supported by the device control layer from the configuration file or database of the device, each parameter range including a process identifier and an attribute value range;

[0145] determining, from the process identification and attribute value range included in each parameter range, whether the attribute value range corresponding to the same process identification as each target process identification contains the target attribute value;

[0146] if yes, generating a check result indicating that the target process parameter check is passed;

[0147] if no, generating a check result indicating that the target process parameter check is not passed.

[0148] In the embodiments of the present application, on the one hand, the manufacturing execution system can monitor the product production state in real time, and when it is necessary to switch the production of the next variety, it can timely issue a process parameter switching request to the server, and the server can automatically obtain the corresponding target process parameter. This process does not require manual intervention, avoids the time required for searching and inputting process parameters, enables the device to switch to a new production task more quickly, and thus significantly improves the production efficiency and shortens the production cycle. On the other hand, the target process parameter is determined by using a preset comparison function, the preset comparison function includes a basic comparison term expression and a physical comparison term expression, the basic comparison term expression is used to quantify the correlation between the production demand keyword sequences, and the physical comparison term expression is used to quantify the correlation between the process flowcharts. By comprehensively considering the correlation of production demand and the correlation of process flow, accurate process parameters can be quickly obtained depending on the historical production data of each variety, and thus the product quality is improved.

[0149] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware, and the program for process parameter switching for multi-variety production can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. The storage medium of the program for process parameter switching for multi-variety production can be a magnetic disk, an optical disk, a read-only memory or a random access memory, etc.

[0150] The above only describes the preferred embodiments of the present application, and of course cannot limit the scope of the rights of the present application, so equivalent changes made according to the claims of the present application are still within the scope of the present application.

Claims

1. A process parameter switching method for multi-variety production, characterized by, Applied to a server, the method comprises: Receiving a process parameter switching request sent by a manufacturing execution system for monitoring product production status, the process parameter switching request carrying production demand description information and product batch model; According to the production demand description information, automatically obtaining corresponding target process parameters, the target process parameters being determined by using a preset comparison function, the preset comparison function including a basic comparison term expression and a physical comparison term expression; Pre-verifying the target process parameters to obtain a verification result; In the case that the verification result indicates that the target process parameters pass the verification, binding the target process parameters to the product batch model and issuing to a device control layer to switch the currently executed process parameters to the target process parameters; The basic comparison term expression is used to calculate a basic comparison value between a production demand keyword sequence and historical production demand keyword sequences corresponding to each variety, including: Converting the production demand keyword sequence into a vector set to obtain a current vector set; Converting the historical production demand keyword sequences corresponding to each variety into a vector set to obtain historical vector sets corresponding to each variety; Calculating semantic similarity between the current vector set and the historical vector sets corresponding to each variety; Taking the semantic similarity as the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequences corresponding to each variety; The physical comparison term expression is used to calculate a physical comparison term value between a current process flowchart and historical process flowcharts of each variety, including: Based on the production demand keyword sequence, obtaining a current process flowchart of a required product variety; Converting the current process flowchart into a first process topology directed graph composed of nodes and edges, wherein the nodes represent different reaction kettles and the edges represent material flow directions; Converting the historical process flowcharts of each variety into second process topology directed graphs; Calculating the minimum number of editing operations required for adding, deleting or modifying nodes or edges between the first process topology directed graph and each second process topology directed graph to obtain a graph editing distance between the first process topology directed graph and each second process topology directed graph; Counting the total number of nodes of the process topology directed graph with the most nodes or edges among the first process topology directed graph and each second process topology directed graph; Calculating the difference between the graph editing distance and the total number of nodes to obtain a process topology similarity between the current process flowchart and the historical process flowcharts of each variety; Taking the process topology similarity as the physical comparison term value between the current process flowchart and the historical process flowcharts of each variety.

2. The method of claim 1, wherein, The automatically obtaining corresponding target process parameters according to the production demand description information comprises: Inputting the production demand description information into a pre-tuned keyword extraction model to output a production demand keyword sequence corresponding to the production demand description information, the pre-tuned keyword extraction model being obtained by fine-tuning a large language model using professional knowledge for multi-variety production industries. The preset comparison function is used to analyze the overall comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database, and the preset multi-variety database is obtained by collecting and preprocessing the historical production data of each variety; The current executed process parameters are extracted from the historical production data of the variety corresponding to the maximum non-zero overall comparison value; The redundant parameters in the current executed process parameters are adjusted to obtain the target process parameters corresponding to the production demand description information.

3. The method of claim 2, wherein, The analysis of the comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database includes: Obtain the historical production data of each variety in the preset multi-variety database; Input the historical production data of each variety into the pre-tuned keyword extraction model to output the historical production demand keyword sequence corresponding to each variety; According to the basic comparison item expression, the basic comparison value between the production demand keyword sequence and the historical production demand keyword sequence corresponding to each variety is calculated; Based on the production demand keyword sequence, the current process flowchart of the required product variety is obtained; According to the physical comparison item expression, the physical comparison item value between the current process flowchart and the historical process flowchart of each variety is calculated; The basic comparison value and the physical comparison item value are weighted and multiplied to obtain the overall comparison value between the production demand keyword sequence and the historical production data of each variety in the preset multi-variety database.

4. The method of claim 2, wherein, The function expression of the preset comparison function is: wherein, is the total contrast ratio, is the semantic similarity weight, taking a value in the range , by default , is the topological similarity weight, taking a value in the range , by default , is the basic contrast ratio, is the physical contrast item value; The basic comparison item expression is: wherein, is a basic contrast item value, is a current vector set of production demand keywords, is a historical vector set corresponding to each variety, is the number of production demand keywords, is the number of historical keywords corresponding to each variety, is the number of semantic intersection of production demand keywords and historical keywords corresponding to each variety; The physical comparison item expression is: wherein, is a physical contrast item value, is a first process topology directed graph, nodes represent different reactors, and edges represent material flow, is a directed graph of a historical process flow diagram, is a first process topology directed graph, is a total number of nodes of is a total number of nodes of is a total number of nodes of is a graph edit distance between the first process topology directed graph and each second process topology directed graph, is a total number of nodes of the process topology directed graph with the most nodes or edges.

5. The method of claim 2, wherein, The pre-tuned keyword extraction model is generated according to the following steps, including: Collecting preset professional knowledge facing multi-variety production industry; Adjust the model parameters of the large language model to obtain the keyword extraction model; Input the preset professional knowledge facing multi-variety production industry into the keyword extraction model for model fine-tuning to obtain the pre-tuned keyword extraction model.

6. The method of claim 1, wherein, The automatic acquisition of the target process parameters corresponding to the production demand description information includes: Load the mapping relationship between the pre-established process parameter version number and the process parameter; In the production demand description information, query the target process parameter version number; From the mapping relationship, obtain the target process parameter corresponding to the target process parameter version number; The target process parameter is used as the target process parameter corresponding to the production demand description information.

7. The method of claim 1, wherein, Each target process parameter includes a target process identifier and a target attribute value; The pre-verification of the target process parameter includes: Read the multiple parameter ranges supported by the device control layer from the configuration file or database of the device, each parameter range including a process identifier and an attribute value range; From the process identifier and the attribute value range included in each parameter range, determine whether the attribute value range corresponding to the same process identifier as each target process identifier contains the target attribute value; If yes, generate a verification result indicating that the target process parameter passes the verification; If not, generate a verification result indicating that the target process parameter fails the verification.

8. A process parameter switching device for multi-variety production, realized using the method according to any one of claims 1 to 7, characterized in that, The device comprises: a receiving module configured to receive a process parameter switching request sent by a manufacturing execution system for monitoring a product production state, the process parameter switching request carrying production demand description information and a product batch model; an obtaining module configured to automatically obtain corresponding target process parameters according to the production demand description information, the target process parameters being determined by using a preset comparison function, the preset comparison function comprising a basic comparison term expression and a physical comparison term expression, the basic comparison term expression being used to quantify the correlation between a production demand keyword sequence, and the physical comparison term expression being used to quantify the correlation between process flowcharts; a pre-inspection module configured to pre-verify the target process parameters to obtain a verification result; a parameter issuing module configured to bind the target process parameters to the product batch model and issue the target process parameters to a device control layer to switch the currently executed process parameters to the target process parameters if the verification result indicates that the target process parameters pass the verification.

Images