Regulation and control method for production system, production system, electronic device, and storage medium

Abstract

The present application provides a regulation and control method for a production system, a production system, an electronic device, and a storage medium. The regulation and control method for a production system comprises: acquiring a mathematical model of a production system; optimizing the mathematical model on the basis of historical data of the production system, to obtain optimization data of the production system; and regulating and controlling the production system on the basis of the optimization data of the production system. By means of the method, prediction and determination can be carried out before the takt time of the production system is unbalanced, and corresponding decisions are made to adjust the takt time, so that the takt time is balanced and rational, thereby improving production efficiency.

Description

Production system control method, production system, electronic equipment and storage medium

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on July 27, 2023, with application number 202310929558.7 and invention name “Production system control method, production system, electronic device and storage medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of production control, and in particular to a production system control method, a production system, an electronic device, and a storage medium. Background Art

[0003] Pull-based production lines are driven by actual customer demand orders. Replenishment requests are initiated based on sales orders, and manufacturers then rapidly produce and replenish inventory. Pull-based production management often presents the following challenges: When upstream processing units complete production or demand is low, downstream processing units fail to respond promptly, leading to material congestion; and when upstream processing units begin production or demand is high, downstream processing units fail to meet supply requirements, leading to material shortages. These issues can easily lead to uneven production rhythms, thus impacting production efficiency. Technical issues

[0004] One of the purposes of the embodiments of the present application is to provide a production system control method, a production system, an electronic device and a storage medium, which solve the problems of uneven production rhythm and low production efficiency in the prior art. Technical Solutions

[0005] To solve the above technical problems, the technical solutions adopted in the embodiments of the present application are:

[0006] In a first aspect, a method for controlling a production system is provided, comprising:

[0007] obtaining a mathematical model of the production system;

[0008] Optimizing the mathematical model according to historical data of the production system to obtain optimized data of the production system;

[0009] The production system is regulated according to the optimization data of the production system.

[0010] In the embodiment of the present application, the production system to be regulated is converted into a mathematical model, and the production system is regulated using a mathematical optimization method. This allows prediction and judgment before the production rhythm of the production system becomes unbalanced, and corresponding decisions are made to adjust the production rhythm, thereby balancing and rationalizing the production rhythm and improving production efficiency. In addition, using the historical data of the production system for optimization processing is equivalent to optimizing the mathematical model based on real production data. The optimized data obtained in this way is closer to the actual production status, making the final regulation result more reliable; and optimizing based on historical data is equivalent to optimizing using offline data, without the need for iterative calculations, which helps to improve the stability of the optimization results.

[0011] In an implementation of the first aspect, obtaining the mathematical model of the production system includes:

[0012] Obtaining system parameters of the production system;

[0013] A mathematical model of the production system is generated according to the system parameters of the production system.

[0014] In the embodiment of the present application, the mathematical model of the production system is determined based on the system parameters of the production system, so that the established mathematical model can more accurately reflect the production status of the production system and provide a reliable model basis for subsequent optimization processing and regulation.

[0015] In an implementation of the first aspect, generating a mathematical model of the production system according to system parameters of the production system includes:

[0016] determining a dependent variable of the mathematical model;

[0017] determining a decision variable related to the dependent variable according to system parameters of the production system;

[0018] A mathematical model of the production system is generated according to the dependent variables and the decision variables.

[0019] In the embodiment of the present application, the decision variables of the mathematical model of the production system are determined according to the system parameters of the production system, so that the established mathematical model can more accurately reflect the production status of the production system, providing a reliable model basis for subsequent optimization processing and regulation.

[0020] In an implementation of the first aspect, generating the mathematical model of the production system according to the dependent variable and the decision variable includes:

[0021] determining constraints on the decision variables;

[0022] A mathematical model of the production system is generated according to the dependent variables, the decision variables and the constraints of the decision variables.

[0023] To ensure optimal results, the decision variables can theoretically be adjusted without restriction, but this approach may affect the production efficiency and capacity of the production system. In the embodiments of the present application, by setting constraints on the decision variables, this can effectively prevent the occurrence of such a situation. By limiting the decision variables to a reasonable range, this helps ensure the production efficiency of the production system after adjustment.

[0024] In an implementation of the first aspect, generating the mathematical model of the production system according to the dependent variable, the decision variable, and the constraint conditions of the decision variable includes:

[0025] generating an objective function based on the dependent variable and the decision variable;

[0026] A mathematical model of the production system is generated according to the constraint conditions of the decision variables and the objective function.

[0027] In the embodiment of the present application, the production status of the production system is reflected by the objective function, and the adjustment range of the decision variable is limited by the constraint conditions, so that the generated mathematical model can not only reflect the production status of the production system, but also constrain the production status of the production system. In the subsequent optimization process, it is equivalent to adjusting the production status of the production system within a reasonable range, so that the final control result is more in line with practical applications and is conducive to achieving production balance.

[0028] In an implementation of the first aspect, when the dependent variable is a line balance rate, determining a decision variable related to the dependent variable according to a system parameter of the production system includes:

[0029] determining a first process time of a processing unit in the production system according to system parameters of the production system;

[0030] determining a second process time of a bottleneck process in the production system according to system parameters of the production system;

[0031] The decision variable is determined according to the first process time and the second process time.

[0032] Typically, bottleneck processes have longer process times than non-bottleneck processes, and thus bottleneck processes are a significant factor influencing production efficiency. In the present embodiment, the process of determining decision variables takes into account the process times of both bottleneck and non-bottleneck processes. This is equivalent to considering every process that affects the production efficiency of the production system, which helps to obtain an optimization result that is more suitable for practical applications.

[0033] In an implementation of the first aspect, the system parameters of the production system include the machine processing time of the processing unit and the logistics delay time of the scheduling unit;

[0034] Determining the first process time of the processing unit in the production system according to the system parameters of the production system includes:

[0035] The first process time of the processing unit in the production system is determined according to the machine processing time of the processing unit and the logistics delay time of the scheduling unit.

[0036] In a pull-mode production system, the processing unit and the scheduling unit jointly affect the production efficiency. At present, usually only the impact of the processing unit on production efficiency is considered, while the impact of the scheduling unit on production efficiency is ignored, resulting in unsatisfactory control results. In the embodiment of the present application, the reason why the processing unit stops waiting for materials is logistics. In this case, the process time of the processing unit is determined according to the machine processing time of the processing unit and the logistics delay time of the scheduling unit, which is equivalent to taking the logistics factors of the scheduling unit into account in the process of establishing a mathematical model. Through the above method, the reliability of the production system control can be improved, thereby achieving more accurate balanced production and improving production efficiency.

[0037] In an implementation of the first aspect, when the processing unit is a bottleneck process, determining the first process time of the processing unit in the production system according to the system parameters of the production system includes:

[0038] The first process time of the processing unit in the production system is determined according to the bottleneck process time of the processing unit.

[0039] In the embodiment of the present application, the reason for the processing unit's downtime due to waiting for material is not logistics, but the processing unit itself is the bottleneck process. In this case, the processing unit's process time is determined based on the bottleneck process time of the processing unit. This is equivalent to taking the bottleneck process's downtime factor into account when establishing the mathematical model. This approach can improve the reliability of production system control, thereby more accurately achieving balanced production and improving production efficiency.

[0040] In an implementation of the first aspect, the system parameters of the production system include a machine processing time of the processing unit;

[0041] Determining the first process time of the processing unit in the production system according to the system parameters of the production system includes:

[0042] The first process time of the processing unit in the production system is determined according to the machine processing time of the processing unit.

[0043] In the present embodiment, the processing unit does not stop waiting for material and is operating normally. In this case, the processing unit's process time is determined based on the processing time of the processing unit's machine. Combining the above two situations, various possible situations in the processing unit's production process are taken into account, making the established mathematical model more closely aligned with actual production conditions, thereby ensuring the reliability of the control.

[0044] In an implementation of the first aspect, determining the constraint conditions of the decision variables includes:

[0045] determining a time interval of a first process time of a processing unit in the production system;

[0046] The constraint conditions of the decision variables are determined according to the time interval.

[0047] In the embodiment of the present application, by limiting the time interval of the process time of the processing unit, it is possible to effectively prevent the situation where the processing time is increased unlimitedly to ensure production balance, thereby helping to improve the production efficiency of the production system.

[0048] In an implementation of the first aspect, optimizing the mathematical model based on historical data of the production system to obtain optimized data of the production system includes:

[0049] Obtaining historical data of the decision variables in the production system;

[0050] The data of the dependent variable in the mathematical model is predicted according to the historical data of the decision variable to obtain the optimized data.

[0051] In the embodiment of the present application, the actual historical data of the production system is used for optimization processing, which is equivalent to optimizing the mathematical model based on real production data. The optimization data obtained in this way is closer to the actual production status, making the final control result more reliable.

[0052] In an implementation of the first aspect, regulating the production system according to the optimization data of the production system includes:

[0053] determining a control variable related to the dependent variable from system parameters of the production system;

[0054] The control variable is adjusted according to the optimization data to obtain the adjusted control variable, and the adjusted control variable is used to adjust the production state of the production system.

[0055] The dependent variable can be directly affected by some variables or indirectly affected by some variables. Optionally, the control variable can be a variable that directly affects the dependent variable (such as a decision variable) or a variable that indirectly affects the dependent variable. In the embodiments of the present application, by adjusting the control variables related to the dependent variable, the dependent variable is directly or indirectly affected, thereby achieving regulation and control of the production system.

[0056] In an implementation of the first aspect, adjusting the control variable according to the optimization data to obtain the adjusted control variable includes:

[0057] Obtaining a target value of a regulating parameter of the control variable;

[0058] The controlled variable is adjusted according to the target value of the adjustment parameter and the optimization data to obtain the adjusted controlled variable.

[0059] In the embodiment of the present application, adjustment parameters are added during the adjustment process of the control variables, which can effectively prevent large-scale adjustments and facilitate stable adjustment.

[0060] In an implementation of the first aspect, obtaining a target value of a regulating parameter of the control variable includes:

[0061] Obtaining multiple groups of first candidate values ​​of adjustment parameters of the control variable;

[0062] Calculating an evaluation score corresponding to each group of the first candidate values, respectively, the evaluation score representing a value of the dependent variable obtained when the adjustment parameter of the control variable is the first candidate value;

[0063] A group of target values ​​is determined from multiple groups of first candidate values ​​according to the evaluation scores corresponding to each group of first candidate values.

[0064] In the embodiment of the present application, target values ​​of the adjustment parameters are screened based on the influence of each of the multiple sets of first candidate values ​​on the dependent variable. In this way, an optimal set of adjustment parameters can be selected, which is conducive to achieving optimal control of the production system.

[0065] In an implementation of the first aspect, determining a set of target values ​​from multiple sets of first candidate values ​​according to the evaluation scores corresponding to each set of first candidate values ​​includes:

[0066] Deleting candidate values ​​having evaluation scores less than a preset value from the multiple groups of first candidate values ​​to obtain at least one remaining group of first candidate values;

[0067] A set of target values ​​is determined from the remaining at least one set of the first candidate values.

[0068] In the embodiment of the present application, this is equivalent to performing two rounds of screening: a first round of screening based on the evaluation scores, and a second round of screening of the remaining at least one set of first candidate values. This double screening can improve the optimality of the adjustment parameters, thereby facilitating optimal control of the production system.

[0069] In an implementation of the first aspect, the adjustment parameter includes a proportional parameter, a differential parameter, and an integral parameter, and each group of the first candidate values ​​includes a first parameter value of a proportional parameter, a second parameter value of a differential parameter, and a third parameter value of an integral parameter;

[0070] The step of determining a set of target values ​​from the remaining at least one set of the first candidate values ​​comprises:

[0071] Arrange and combine the first parameter value, the second parameter value, and the third parameter value in the remaining at least one group of the first candidate values ​​to obtain multiple groups of second candidate values;

[0072] Calculate the evaluation score corresponding to each group of the second candidate values ​​respectively;

[0073] According to the evaluation scores corresponding to each group of the second candidate values, a group of the target values ​​is determined from multiple groups of the second candidate values.

[0074] In this embodiment of the present application, during the second round of screening of at least one remaining set of first candidate values, permutations and combinations of parameter values ​​across different groups are considered, equivalent to considering multiple possible scenarios for adjusting the parameters. Compared to the first screening, this second round of screening is more granular, which helps improve the optimality of the adjustment parameters.

[0075] In an implementation of the first aspect, adjusting the control variable according to the target value of the adjustment parameter and the optimization data to obtain the adjusted control variable includes:

[0076] In one iteration, the error value between the value of the dependent variable corresponding to the current control variable and the optimized data is calculated;

[0077] When the error value is greater than a preset error, calculating an adjustment amount according to the error value and a target value of the adjustment parameter;

[0078] The controlled variable is adjusted according to the adjustment amount to obtain the adjusted controlled variable.

[0079] In an implementation of the first aspect, when the error value is greater than a preset error, calculating the adjustment amount according to the error value and a target value of the adjustment parameter includes:

[0080] When the error value is greater than a preset error, calculating a proportional value according to the error value and a first parameter value in the target value of the adjustment parameter;

[0081] Calculating a differential value according to the error value and a second parameter value in the target value of the adjustment parameter;

[0082] Calculating an integral value according to the error value and a third parameter value in the target value of the adjustment parameter;

[0083] The adjustment amount is calculated according to the proportional value, the differential value, and the integral value.

[0084] In the embodiments of the present application, the adjustment amount is calculated using three steps: proportional, differential, and integral. The proportional step facilitates timely response to errors, the differential step facilitates overcoming oscillations and reducing adjustment time, and the integral step facilitates error elimination. The adjustment amount calculated using these three steps can promptly eliminate errors and reduce adjustment time, thereby improving adjustment efficiency and sensitivity.

[0085] In an implementation of the first aspect, the control variable includes at least one of the following: a scheduling speed, a scheduling displacement, a scheduling flow of the scheduling unit, and a processing speed of the processing unit, wherein the scheduling flow is used to represent the allocation amount of the scheduling resources and the allocation amount of the scheduling tasks;

[0086] The step of adjusting the control variable according to the optimization data to obtain the adjusted control variable includes:

[0087] Adjust the dispatching speed according to the optimization data to obtain the adjusted dispatching speed;

[0088] Adjust the scheduling displacement according to the optimization data to obtain the adjusted scheduling displacement;

[0089] Adjust the scheduling flow according to the optimization data to obtain the adjusted scheduling flow;

[0090] The processing speed is adjusted according to the optimization data to obtain the adjusted processing speed.

[0091] In the embodiment of the present application, multiple control variables related to the dependent variable are taken into consideration. By adjusting the multiple control variables separately, it is equivalent to adjusting multiple factors affecting the production efficiency of the production system, thereby achieving balanced regulation of the production system.

[0092] In an implementation of the first aspect, the method further includes:

[0093] updating the mathematical model of the production system at predetermined intervals to obtain an updated mathematical model;

[0094] Optimizing the updated mathematical model to obtain updated optimization data;

[0095] The production system is regulated according to the updated optimization data.

[0096] In the embodiment of the present application, by regularly remodeling the production system, the mathematical model changes with the state of the production system and is closer to the actual situation of the production system. This can effectively avoid the situation where poor control effects are caused by inaccuracies in the mathematical model, and is conducive to improving the reliability of production system control.

[0097] In an implementation of the first aspect, regulating the production system according to the optimization data includes:

[0098] Establishing a simulation environment for the production system;

[0099] Regulating the simulation environment according to the optimization data to obtain simulation results;

[0100] If the simulation result meets the preset conditions, the production system is regulated according to the optimization data.

[0101] In the embodiment of the present application, the feasibility of the optimized data is verified in a simulation environment, and if the optimized data is feasible, it is applied to the actual production system. In this way, the reliability of the production system control can be further improved.

[0102] In some implementations, if the simulation results do not meet the preset conditions, a mathematical model of the production system to be regulated is regenerated based on the system parameters of the production system; the mathematical model is optimized to obtain optimized data for the mathematical model; and the production system is regulated based on the optimized data for the mathematical model. Alternatively, if the simulation results do not meet the preset conditions, the mathematical model is optimized to obtain optimized data for the mathematical model; and the production system is regulated based on the optimized data for the mathematical model.

[0103] In a second aspect, a production system is provided, comprising a central control unit, at least one processing unit, and at least one scheduling unit;

[0104] The central control unit is used to control the processing unit and the scheduling unit according to the method described in any one of the first aspects;

[0105] The processing unit is used to process the production material to obtain the processed material;

[0106] The dispatching unit is used to transport the processing materials.

[0107] In the embodiment of the present application, the central control unit can not only control the processing unit, but also the scheduling unit. Since the production efficiency of the production system is jointly determined by the processing unit and the scheduling unit, the central control unit in the embodiment of the present application can achieve balanced adjustment of the processing unit and the scheduling unit, thereby ensuring balanced production of the production system and improving production efficiency.

[0108] In an implementation of the second aspect, the central control unit includes a decision layer and a control layer;

[0109] The decision layer is used to obtain a mathematical model of the production system; optimize the mathematical model according to the historical data of the production system to obtain optimized data of the production system;

[0110] The control layer is used to regulate the production system according to the optimization data of the production system.

[0111] In the embodiment of the present application, the central control unit is divided into two layers, one layer is used to generate optimization data, and the other layer is used for regulation. The two layers divide the work and process, which is conducive to improving the regulation efficiency.

[0112] In a third aspect, an embodiment of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for controlling a production system as described in any one of the first aspects above is implemented.

[0113] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the production system control method as described in any one of the above-mentioned first aspects is implemented.

[0114] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute the production system control method described in any one of the above-mentioned first aspects.

[0115] It can be understood that the beneficial effects of the third to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0116] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0117] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present application. The same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0118] FIG1 is a schematic diagram of a production system provided in an embodiment of the present application;

[0119] FIG2 is a schematic diagram of a production system provided by another embodiment of the present application;

[0120] FIG3 is a schematic flow chart of a control method for a production system provided in an embodiment of the present application;

[0121] FIG4 is a flow chart of a mathematical model generation method provided in an embodiment of the present application;

[0122] FIG5 is a schematic flow chart of the control method provided in an embodiment of the present application;

[0123] FIG6 is a schematic diagram of a parameter adjustment process provided in an embodiment of the present application;

[0124] FIG7 is a schematic flow chart of a control method provided in another embodiment of the present application;

[0125] FIG8 is a schematic diagram of the effect of the control method provided in an embodiment of the present application on a production system;

[0126] FIG9 is a schematic structural diagram of an electronic device provided in an embodiment of the present application. Modes for Carrying Out the Invention

[0127] The following embodiments of the technical solution of the present application will be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present application and are therefore only examples and are not intended to limit the scope of protection of the present application.

[0128] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned figure descriptions are intended to cover non-exclusive inclusions.

[0129] In the description of the embodiments of this application, the technical terms "first" and "second" are used only to distinguish different objects and should not be understood to indicate or imply relative importance or implicitly specify the quantity, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, the meaning of "plurality" is more than two, unless otherwise clearly and specifically defined.

[0130] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0131] In the description of the embodiments of this application, the term "and / or" is simply a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent the following three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0132] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0133] Pull-based production lines are driven by actual customer demand orders. Replenishment requests are initiated based on sales orders, and manufacturers then rapidly produce and replenish inventory. Pull-based production management often presents the following challenges: When upstream processing units complete production or demand is low, downstream processing units fail to respond promptly, leading to material congestion; and when upstream processing units begin production or demand is high, downstream processing units fail to meet supply requirements, leading to material shortages. These issues can easily lead to uneven production rhythms, thus impacting production efficiency.

[0134] To address the above-mentioned issues, an embodiment of the present application provides a method for regulating a production system. In this embodiment, the production system to be regulated is converted into a mathematical model, and the production system is regulated using mathematical optimization methods. This method enables prediction and determination before the production rhythm of the production system becomes unbalanced, and appropriate decisions can be made to adjust the production rhythm, thereby balancing and rationalizing the production rhythm and improving production efficiency.

[0135] The following is an introduction to the control method of the production system provided in the embodiments of the present application with reference to specific examples.

[0136] First, the production system involved in the embodiments of the present application is introduced.

[0137] FIG1 is a schematic diagram of a production system according to an embodiment of the present application. As shown in FIG1 , by way of example and not limitation, the production system may include a central control unit 11, at least one processing unit 12 (only two processing units are shown in FIG1 ), and at least one scheduling unit 13 (only two scheduling units are shown in FIG1 ).

[0138] The central control unit 11 is used to control the processing unit 12 and the scheduling unit 13 according to the control method of the production system provided in the embodiment of the present application. The processing unit 12 is used to process the production materials to obtain the processed materials. The scheduling unit 13 is used to transport the processed materials.

[0139] To address production management issues under the pull model, related technologies typically add buffer areas or shelves between processing units to alleviate material congestion or shortages. However, current solutions increase the workload of scheduling units and the complexity of task management, transforming the original point-to-point material transportation from downstream to upstream into two modes: downstream to buffer and then to upstream, and downstream directly to upstream. Furthermore, the addition of a large number of buffer areas takes up remaining space in the production area, hindering subsequent upgrades and expansions of the production line. This also increases investment in work-in-progress.

[0140] In the embodiment of the present application, the central control unit can not only control the processing unit, but also the scheduling unit. Since the production efficiency of the production system is jointly determined by the processing unit and the scheduling unit, the central control unit in the embodiment of the present application can achieve balanced regulation of the processing unit and the scheduling unit while reducing the buffer area, thereby ensuring balanced production of the production system and improving production efficiency.

[0141] In some embodiments, referring to FIG2 , which is a schematic diagram of a production system provided by another embodiment of the present application, as shown in FIG2 , the central control unit 11 includes a decision layer 111 and a control layer 112 .

[0142] The decision layer 111 is used to optimize the production system and obtain the optimization data of the production system. The control layer 112 is used to control the production system according to the optimization data of the production system.

[0143] In the embodiment of the present application, the central control unit is divided into two layers, one layer is used to generate optimization data, and the other layer is used for regulation. The two layers divide the work and process, which is conducive to improving the regulation efficiency.

[0144] Based on the above system, the control method of the production system is introduced below.

[0145] FIG3 is a flow chart of a control method for a production system according to an embodiment of the present application. As an example and not a limitation, as shown in FIG1 , the method may include the following steps:

[0146] S301: Acquire a mathematical model of the production system.

[0147] In the embodiment of the present application, the mathematical model can reflect the operating status of the production system. Using the mathematical model to regulate the production system is equivalent to converting the actual regulation problem into a mathematical problem.

[0148] In the embodiment of the present application, the mathematical model may include dependent variables and decision variables, wherein the decision variables are the influencing factors of the dependent variables.

[0149] S302: Optimize the mathematical model according to historical data of the production system to obtain optimized data of the production system.

[0150] As shown in the embodiment of Figure 1, the production system may include a processing unit and a scheduling unit. Accordingly, the optimization of the production system includes but is not limited to optimizing the process time of the processing unit and optimizing the logistics transportation time of the scheduling unit.

[0151] Mathematical models can reflect the operating status of the production system. Optimizing the mathematical model is equivalent to optimizing the production system.

[0152] In the embodiment of the present application, the optimization data of the mathematical model includes the data of each decision variable in the mathematical model when the dependent variable of the mathematical model reaches the target value.

[0153] In the embodiments of the present application, the production system to be regulated is converted into a mathematical model and regulated using mathematical optimization methods. This method enables prediction and determination before the production rhythm of the production system becomes unbalanced, and appropriate decisions are made to adjust the production rhythm, thereby balancing and rationalizing the production rhythm and improving production efficiency.

[0154] S303: regulating the production system according to the optimization data of the production system.

[0155] Among them, the regulation process is equivalent to adjusting the system parameters related to the dependent variables in the production system so that the dependent variables of the production system reach their target values.

[0156] For example, system parameters related to the dependent variable include decision variables and parameters that indirectly affect the dependent variable. For decision variables, their data can be adjusted to be consistent with the optimization data. For parameters that indirectly affect the dependent variable, these parameters can be adjusted to bring the dependent variable to its target value.

[0157] In the embodiments of the present application, the production system is first optimized and then regulated based on the optimization data. Optimization enables prediction and determination before the production rhythm of the production system becomes unbalanced, and appropriate decisions are made to adjust the production rhythm, thereby balancing and rationalizing the production rhythm and improving production efficiency.

[0158] In some embodiments, referring to FIG4 , which is a flow chart of a mathematical model generation method provided in an embodiment of the present application, as shown in FIG4 , S301 may include:

[0159] S401: Obtain system parameters of the production system.

[0160] System parameters refer to parameters related to the production efficiency and production management of the production system. For example, system parameters may include the process time of a processing unit, the bottleneck process time, logistics transportation time, logistics delay time, etc., which are not specifically limited here.

[0161] In the embodiment of the present application, the mathematical model may include dependent variables and decision variables, wherein the decision variables are the influencing factors of the dependent variables.

[0162] The steps of generating a mathematical model according to the system parameters of the production system are described in the following S4011-S4013 embodiments.

[0163] S402: Generate a mathematical model of the production system according to system parameters of the production system.

[0164] In the embodiment of the present application, the mathematical model of the production system is determined based on the system parameters of the production system, so that the established mathematical model can more accurately reflect the production status of the production system and provide a reliable model basis for subsequent optimization processing and regulation.

[0165] In some embodiments, S402 may include the following steps:

[0166] S4011, determining the dependent variable of the mathematical model.

[0167] S4012: Determine a decision variable related to the dependent variable according to system parameters of the production system.

[0168] In this embodiment of the present application, the dependent variable may be an evaluation index of the production status of the production system, and the decision variable is a parameter that affects the evaluation index. The dependent variable may be a system parameter of the production system or other parameters. The decision variable is a parameter of the production system that affects the dependent variable.

[0169] For example, the dependent variable is the line balance rate (not a system parameter of the production system), and the decision variables include the process time of the processing unit and the bottleneck process time, etc.

[0170] Line balancing involves analyzing the load of all production processes and adjusting the load distribution between them to achieve capacity balance (keeping operating times as close as possible). This eliminates any wasted waiting time and improves overall production line efficiency. The line balance rate is a metric used to evaluate the effectiveness of line balancing.

[0171] The bottleneck process is the step or process that limits the overall production line's output. Typically, the bottleneck process takes longer than other processes. In other words, the bottleneck process is a significant factor affecting line balance.

[0172] S4013: Generate a mathematical model of the production system according to the dependent variables and the decision variables.

[0173] The mathematical model here is used to represent the relationship between the dependent variable and the decision variable. For example, the mathematical model can include a function that represents the functional relationship between the dependent variable and the decision variable.

[0174] In the S4011-S4013 embodiments, the decision variables of the mathematical model of the production system are determined according to the system parameters of the production system, so that the established mathematical model can more accurately reflect the production status of the production system, providing a reliable model basis for subsequent optimization processing and regulation.

[0175] For the convenience of description, the following explanation is given by taking the dependent variable as the line balance rate as an example.

[0176] When the dependent variable is the line balance rate, step S4012 may include:

[0177] 1-1. Determine a first process time of a processing unit in the production system according to system parameters of the production system.

[0178] 1-2. Determine a second process time of a bottleneck process in the production system according to system parameters of the production system.

[0179] 1-3. Determine the decision variable according to the first process time and the second process time.

[0180] Usually, each processing unit corresponds to a production process, and the process time of a processing unit refers to the time required to complete a job or a process.

[0181] In the embodiments of this application, a processing unit includes a bottleneck process. For example, a production system includes three processing units, a, b, and c, with processing unit a being the bottleneck process. The process times for processing units a, b, and c are referred to as the first process time, while the process time for processing unit a is also referred to as the second process time.

[0182] In one implementation of step I-3, each first process time can be used as a decision variable, and each second process time can be used as a decision variable. In another implementation, the sum of the first process times can be used as a decision variable, and the sum of the second process times can be used as a decision variable.

[0183] Typically, bottleneck processes have longer process times than non-bottleneck processes, and thus bottleneck processes are a significant factor influencing production efficiency. In the present embodiment, the process of determining decision variables takes into account the process times of both bottleneck and non-bottleneck processes. This is equivalent to considering every process that affects the production efficiency of the production system, which helps to obtain an optimization result that is more suitable for practical applications.

[0184] In some application scenarios, the logistics delay of the scheduling unit leads to the processing delay of the processing unit. In this case, the system parameters of the production system include the machine processing time of the processing unit and the logistics delay time of the scheduling unit. Accordingly, step 1-1 may include:

[0185] The first process time of the processing unit in the production system is determined according to the machine processing time of the processing unit and the logistics delay time of the scheduling unit.

[0186] For example, for a processing unit d with a processing delay, its first process time = the machine processing time of the processing unit d + the logistics delay time of the scheduling unit for the processing unit d.

[0187] In a pull-mode production system, the processing unit and the scheduling unit jointly affect the production efficiency. At present, usually only the impact of the processing unit on production efficiency is considered, while the impact of the scheduling unit on production efficiency is ignored, resulting in unsatisfactory control results. In the embodiment of the present application, the reason why the processing unit stops waiting for materials is logistics. In this case, the process time of the processing unit is determined according to the machine processing time of the processing unit and the logistics delay time of the scheduling unit, which is equivalent to taking the logistics factors of the scheduling unit into account in the process of establishing a mathematical model. Through the above method, the reliability of the production system control can be improved, thereby achieving more accurate balanced production and improving production efficiency.

[0188] In other application scenarios, the processing unit itself is the bottleneck process. In this case, step 1-1 may include:

[0189] The first process time of the processing unit in the production system is determined according to the bottleneck process time of the processing unit.

[0190] For example, for processing unit e, its first process time = the bottleneck process time corresponding to processing unit e.

[0191] In the embodiment of the present application, the reason for the processing unit's downtime due to waiting for material is not logistics, but the processing unit itself is the bottleneck process. In this case, the processing unit's process time is determined based on the bottleneck process time of the processing unit. This is equivalent to taking the bottleneck process's downtime factor into account when establishing the mathematical model. This approach can improve the reliability of production system control, thereby more accurately achieving balanced production and improving production efficiency.

[0192] In other application scenarios, the processing unit is operating normally, that is, there is no processing delay due to logistics delays of the scheduling unit, and it is not a bottleneck process. In this case, the system parameters of the production system include the machine processing time of the processing unit. Accordingly, step 1-1 may include:

[0193] The first process time of the processing unit in the production system is determined according to the machine processing time of the processing unit.

[0194] For example, for processing unit f, the first process time = the machine processing time of processing unit f.

[0195] In the embodiment of the present application, the processing unit does not stop waiting for materials and produces normally. In this case, the process time of the processing unit is determined according to the machine processing time of the processing unit.

[0196] Combining the above three application scenarios, various possible situations in the production process of the processing unit are taken into account, making the established mathematical model closer to the actual production status, thereby ensuring the reliability of regulation.

[0197] During the optimization of the mathematical model, to ensure that the target line balance rate is achieved, the process time of the processing unit can theoretically be extended indefinitely. However, in practice, the process time of the processing unit cannot be unlimited, which will affect production capacity and production efficiency. To ensure the rationality of the optimization results, in some embodiments, step S4013 may include:

[0198] Determine the constraints of the decision variables; and generate a mathematical model of the production system based on the dependent variable, the decision variables, and the constraints of the decision variables.

[0199] In the embodiment of the present application, by setting constraints on the decision variables, the above situation can be effectively prevented. By limiting the decision variables to a reasonable range, it is beneficial to ensure the production efficiency of the production system after regulation.

[0200] In some embodiments, the determination of the constraint conditions of the decision variables may include:

[0201] determining a time interval of a first process time of a processing unit in the production system;

[0202] The constraint conditions of the decision variables are determined according to the time interval.

[0203] As described above, the processing unit in the embodiment of the present application includes a bottleneck process. Therefore, determining the time interval of the first process time of the processing unit here is equivalent to determining the process time of each processing process in the production system including the bottleneck process.

[0204] The time interval may include a maximum time value and a minimum time value. This time interval may be set according to actual production conditions. In subsequent applications, the time interval may also be adaptively adjusted according to actual production conditions.

[0205] In the embodiment of the present application, by limiting the time interval of the process time of the processing unit, it is possible to effectively prevent the situation where the processing time is increased unlimitedly to ensure production balance, thereby helping to improve the production efficiency of the production system.

[0206] In some embodiments, generating the mathematical model of the production system according to the dependent variable, the decision variable, and the constraints of the decision variable includes:

[0207] generating an objective function based on the dependent variable and the decision variable;

[0208] A mathematical model of the production system is generated according to the constraint conditions of the decision variables and the objective function.

[0209] The objective function represents the functional relationship between the dependent variable and the decision variable. In practical terms, the objective function is the performance standard of the production system.

[0210] For example, the dependent variable is the line balance rate, and the decision variables include the sum of the first process time of the processing units in the production system and the second process time of the bottleneck process. The constraint condition of the decision variables is the time interval of the first process time of the processing units. Accordingly, the mathematical model of the production system is: Y(t) = (X(t) / (n*P(t)))*100%;

[0211] Where Y represents the line balance rate, X represents the sum of the first process time of the processing units in the production system, X = x1 + x2 + ….. + xn, xn represents the first process time of the nth processing unit, P represents the second process time, n represents the total number of processing units, and t represents the tth sampling time.

[0212] In the embodiment of the present application, the production status of the production system is reflected by the objective function, and the adjustment range of the decision variable is limited by the constraint conditions, so that the generated mathematical model can not only reflect the production status of the production system, but also constrain the production status of the production system. In the subsequent optimization process, it is equivalent to adjusting the production status of the production system within a reasonable range, so that the final control result is more in line with practical applications and is conducive to achieving production balance.

[0213] It is understandable that the above embodiment is described by taking the line balance rate as the dependent variable. In actual applications, other parameters may also be selected as the dependent variables.

[0214] In some optimization methods, a target value for the dependent variable can be set, the decision variables in the mathematical model can be initialized, and then the mathematical model can be iteratively processed based on the collected real-time data of the dependent variable and the target value of the dependent variable. When the value of the dependent variable after iterative processing is consistent with the target value, the value of the decision variable in the mathematical model at this time is determined as the optimization data. For example, the least squares method can be used to establish an objective function that represents the error between the iterative value and the target value of the dependent variable, and then iterative processing can be performed based on the objective function. However, the above-mentioned iterative processing method using real-time data can easily lead to unstable optimization results, thereby affecting the control reliability of the production system.

[0215] To solve the above problem, in some embodiments, step S302 may include:

[0216] Historical data of the decision variables in the production system are obtained.

[0217] The data of the dependent variable in the mathematical model is predicted according to the historical data of the decision variable to obtain the optimized data of the production system.

[0218] The historical data of decision variables refers to the data of decision variables that have been monitored during the production process. In other words, the historical data of decision variables is actual production data. To improve the optimization accuracy of the mathematical model, a large amount of historical data can be collected and used to optimize the mathematical model. In this way, the optimization process is equivalent to the process of predicting the mathematical model based on big data.

[0219] In the embodiment of the present application, the optimization process is performed using the actual historical data of the production system, which is equivalent to the optimization of the mathematical model based on the real production data. The optimization data obtained in this way is closer to the actual production status, making the final control result more reliable. In addition, the method of processing based on real-time data can only obtain the current real-time data and cannot obtain the data at the next moment. Therefore, it is usually necessary to perform iterative calculations to obtain the optimization result. This method easily leads to unstable optimization results. In the embodiment of the present application, the optimization process is performed based on historical data, which is equivalent to optimizing using offline data. It does not require iterative calculations, which is conducive to improving the stability and reliability of the optimization results.

[0220] In some embodiments, step S303 may include:

[0221] Establishing a simulation environment for the production system;

[0222] Regulating the simulation environment according to the optimization data to obtain simulation results;

[0223] If the simulation result meets the preset conditions, the production system is regulated according to the optimization data.

[0224] In one implementation, simulation software may be used to establish a simulation environment for the production system, such as a simulation environment including the logic of a scheduling unit and a factory layout diagram, to simulate the factory layout and production status of a real production system.

[0225] In the embodiment of the present application, the feasibility of the optimized data is verified in a simulation environment, and if the optimized data is feasible, it is applied to the actual production system. In this way, the reliability of the production system control can be further improved.

[0226] In some embodiments, referring to FIG5 , which is a flow chart of the control method provided in an embodiment of the present application. As an example and not a limitation, as shown in FIG5 , step S303 may include:

[0227] S501: Determine a control variable related to the dependent variable from system parameters of the production system.

[0228] In a production system, there is usually more than one parameter that can affect the dependent variable. The dependent variable can be directly affected by some variables, and can also be indirectly affected by some variables. In an embodiment of the present application, the control variable can be a variable that directly affects the dependent variable (such as a decision variable), or a variable that indirectly affects the dependent variable. For example, the control variables may include the process time of the processing unit, the scheduling speed of the scheduling unit (such as the speed of an unmanned guided vehicle (AGV)), the displacement of the scheduling unit (such as the displacement between the AGV pickup point and the delivery point), and the scheduling flow, etc., wherein the scheduling flow is used to represent the allocation of scheduling resources and the allocation of scheduling tasks.

[0229] S502: Adjust the control variable according to the optimization data to obtain the adjusted control variable, and use the adjusted control variable to adjust the production state of the production system.

[0230] For decision variables among the control variables, the data of the decision variables can be adjusted to be consistent with the optimization data. For parameters among the control variables that indirectly affect the dependent variable, these parameters can be adjusted to bring the dependent variable to its target value. Specific control methods can be referred to the description in the following embodiments.

[0231] As described in S501, the line balance rate is affected by multiple factors in the production system. Optionally, the control variable includes at least one of the following: the scheduling speed, scheduling displacement, and scheduling flow of the scheduling unit, and the processing speed of the processing unit. The scheduling flow is used to represent the allocation of scheduling resources and the allocation of scheduling tasks.

[0232] In one implementation, only one control variable can be adjusted. Although this approach is simple, the final control result may not be ideal due to the presence of other control variables that can affect the dependent variable.

[0233] In another implementation, step S502 includes:

[0234] Adjust the dispatching speed according to the optimization data to obtain the adjusted dispatching speed;

[0235] Adjust the scheduling displacement according to the optimization data to obtain the adjusted scheduling displacement;

[0236] Adjust the scheduling flow according to the optimization data to obtain the adjusted scheduling flow;

[0237] The processing speed is adjusted according to the optimization data to obtain the adjusted processing speed.

[0238] In the embodiment of the present application, multiple control variables related to the dependent variable are taken into consideration. By adjusting the multiple control variables separately, it is equivalent to adjusting multiple factors affecting the production efficiency of the production system, thereby achieving balanced regulation of the production system.

[0239] In the embodiment of FIG5 , the production system is regulated by adjusting the control variables related to the dependent variables to directly or indirectly affect the dependent variables.

[0240] In theory, the adjusted control variables can bring the objective function to its ideal value. However, in practice, because the production system's operating conditions are affected by multiple factors, it may not be possible to achieve the ideal value. This means there is a certain error between the actual and ideal values ​​of the objective function. Furthermore, during the adjustment process, the objective function data may fluctuate significantly, which is detrimental to the stability of the production system.

[0241] To solve the above problem, in some embodiments, step S502 may include:

[0242] 2-1. Obtain the target value of the adjustment parameter of the control variable.

[0243] 2-2. Adjust the control variable according to the target value of the adjustment parameter and the optimization data to obtain the adjusted control variable.

[0244] In the embodiment of the present application, adjustment parameters are added during the adjustment process of the control variables, which can effectively prevent large-scale adjustments and facilitate stable adjustment.

[0245] In some implementations, the target values ​​of the adjustment parameters can be pre-set fixed values, such as those set by technicians based on experience. However, because production systems are complex systems, the control objectives (objective functions) are nonlinear, making it difficult to translate the control process into a simple linear problem. Therefore, setting the target values ​​of the adjustment parameters is particularly important. However, in the above-mentioned approach, the target values ​​of the adjustment parameters may not achieve optimal control.

[0246] To solve the above problem, in some embodiments, step 2-1 may include:

[0247] 3-1. Obtain multiple groups of first candidate values ​​of the adjustment parameters of the control variables.

[0248] 3-2 Calculate the evaluation score corresponding to each group of the first candidate values ​​respectively, where the evaluation score represents the value of the dependent variable obtained when the adjustment parameter of the control variable is the first candidate value.

[0249] 3-3 Determine a group of target values ​​from multiple groups of first candidate values ​​based on the evaluation scores corresponding to each group of first candidate values.

[0250] In the embodiment shown in steps 3-1 to 3-3, target values ​​of the adjustment parameters are screened based on the impact of each of the multiple sets of first candidate values ​​on the dependent variable. In this way, an optimal set of adjustment parameters can be selected, which is conducive to achieving optimal control of the production system.

[0251] In one implementation of step 3-1, a simulation model of the production system (eg, including the logic of the scheduling unit and the factory layout diagram, etc.) may be established in a simulation environment, and multiple groups of first candidate values ​​may be generated based on the simulation model.

[0252] For example, a parameter range of the adjustment parameter may be obtained according to a simulation model, and then a plurality of first candidate values ​​may be randomly selected within a numerical range between the parameter ranges.

[0253] It should be noted that, in the embodiment of the present application, there can be multiple adjustment parameters, and accordingly, multiple first candidate values ​​corresponding to each adjustment parameter are obtained. In one implementation method of calculating the evaluation score in 3-2, a first candidate value can be randomly selected from the multiple first candidate values ​​of each adjustment parameter, and the simulation model can be adjusted according to the selected first candidate value to obtain the numerical value of the dependent variable corresponding to this group of first candidate values; and then another first candidate value can be randomly selected from the remaining first candidate values ​​of each adjustment parameter, and the simulation model can be adjusted according to the currently selected first candidate value to obtain the numerical value of the dependent variable corresponding to the current group of first candidate values.

[0254] One implementation of step 3-2 may include determining the target value as the candidate value with the lowest evaluation score among the multiple sets of first candidate values. Although this approach is simple, it is prone to the following problems: because the selection of the first candidate values ​​is random, if the quality of the selected first candidate values ​​is poor, it is impossible to obtain a more ideal target value.

[0255] To solve the above problem, one implementation of step 3-2 may include:

[0256] Deleting candidate values ​​with evaluation scores less than a preset value from multiple groups of first candidate values ​​to obtain at least one remaining group of first candidate values; and determining a group of target values ​​from the at least one remaining group of first candidate values.

[0257] In the embodiment of the present application, this is equivalent to performing two rounds of screening: a first round of screening based on the evaluation scores, and a second round of screening of the remaining at least one set of first candidate values. This double screening can improve the optimality of the adjustment parameters, thereby facilitating optimal control of the production system.

[0258] Optionally, the adjustment parameters include a proportional parameter, a differential parameter and an integral parameter, and each group of the first candidate values ​​includes a first parameter value of a proportional parameter, a second parameter value of a differential parameter and a third parameter value of an integral parameter.

[0259] Accordingly, one implementation of determining a set of target values ​​from the remaining at least one set of first candidate values ​​includes:

[0260] Arrange and combine the first parameter value, the second parameter value, and the third parameter value in the remaining at least one group of the first candidate values ​​to obtain multiple groups of second candidate values;

[0261] Calculate the evaluation score corresponding to each group of the second candidate values ​​respectively;

[0262] According to the evaluation scores corresponding to each group of second candidate values, a group of target values ​​is determined from multiple groups of second candidate values.

[0263] Exemplarily, the parameter ranges of the proportional parameter [Pmin, Pmax], the differential parameter [Dmin, Dmax], and the integral parameter [Imin, Imax] are first determined. Then, n first candidate values ​​[P1, ..., Pn] are randomly selected within the parameter range [Pmin, Pmax], n first candidate values ​​[D1, ..., Dn] are randomly selected within the parameter range [Dmin, Dmax], and n first candidate values ​​[I1, ..., In] are randomly selected within the parameter range [Imin, Imax]. Optionally, [P1, D1, I1], ..., [Pn, Dn, In] can be used as a set of first candidate values. The values ​​of the dependent variables corresponding to [P1, D1, I1], ..., [Pn, Dn, In] are calculated, respectively. Then, the set of first candidate values ​​corresponding to the values ​​of the calculated dependent variables that are less than a preset value is deleted. Assume that the remaining two groups of first candidate values ​​are [P1, D1, I1] and [P2, D2, I2]. Permutate and combine the parameter values ​​in these two groups of first candidate values ​​to obtain the following eight groups of second candidate values: [P1, D1, I1], [P1, D2, I1], [P1, D2, I2], [P1, D1, I2], [P2, D1, I1], [P2, D2, I1], [P2, D2, I2], [P1, D1, I2]. Calculate the values ​​of the dependent variables corresponding to each of these eight groups of second candidate values, and determine the group of second candidate values ​​corresponding to the maximum value among the calculated values ​​of the dependent variables as a group of target values.

[0264] In this embodiment of the present application, during the second round of screening of at least one remaining set of first candidate values, permutations and combinations of parameter values ​​across different groups are considered, equivalent to considering multiple possible scenarios for adjusting the parameters. Compared to the first screening, this second round of screening is more granular, which helps improve the optimality of the adjustment parameters.

[0265] In some embodiments, adjusting the control variable according to the target value of the adjustment parameter and the optimization data in step 2-2 to obtain the adjusted control variable may include:

[0266] In one iteration, the error value between the value of the dependent variable corresponding to the current control variable and the optimized data is calculated;

[0267] When the error value is greater than a preset error, calculating an adjustment amount according to the error value and a target value of the adjustment parameter;

[0268] The controlled variable is adjusted according to the adjustment amount to obtain the adjusted controlled variable.

[0269] In the embodiment of the present application, the optimization data includes the optimization data of the dependent variable and the optimization data of the decision variable. Accordingly, the error value between the value of the dependent variable and the optimization data of the dependent variable is calculated.

[0270] When the error value is greater than a preset error, calculating the adjustment amount according to the error value and the target value of the adjustment parameter may include:

[0271] When the error value is greater than a preset error, calculating a proportional value according to the error value and a first parameter value in the target value of the adjustment parameter;

[0272] Calculating a differential value according to the error value and a second parameter value in the target value of the adjustment parameter;

[0273] Calculating an integral value according to the error value and a third parameter value in the target value of the adjustment parameter;

[0274] The adjustment amount is calculated according to the proportional value, the differential value, and the integral value.

[0275] For example, see Figure 6, which is a schematic diagram of the parameter adjustment process provided by an embodiment of the present application. As shown in Figure 6, the error value between the optimized data of the line balance rate (optimized data of the dependent variable) and the adjustment data (the numerical value of the line balance rate calculated based on the control amount) is respectively adjusted by proportional adjustment (such as multiplying by the first parameter value of the proportional parameter), integral adjustment (such as multiplying by the third parameter value of the integral parameter) and differential adjustment (such as multiplying by the second parameter value of the differential parameter). The adjusted proportional value, differential value and integral value are weighted and calculated to obtain the adjustment amount; the adjustment amount is applied to the production system (including the processing unit and the scheduling unit) to obtain the new numerical value of the line balance rate (calculated data of the dependent variable). Continue to adjust according to the error value between the newly calculated numerical value of the line balance rate and the optimized data, and so on, until the error value between the calculated numerical value of the line balance rate and the optimized data is less than the preset error.

[0276] In the embodiments of the present application, the adjustment amount is calculated using three steps: proportional, differential, and integral. The proportional step facilitates timely response to errors, the differential step facilitates overcoming oscillations and reducing adjustment time, and the integral step facilitates error elimination. The adjustment amount calculated using these three steps can promptly eliminate errors and reduce adjustment time, thereby improving adjustment efficiency and sensitivity.

[0277] As described in the embodiment of S502, there are multiple control variables that affect the dependent variable. Accordingly, each control variable corresponds to a set of target values ​​of the adjustment parameters. For example, see the following table:

[0278] As shown in the table above, each control parameter may affect the line balance rate, and each control parameter corresponds to a set of target values ​​for the adjustment parameters. Different control parameters correspond to different target values ​​for the adjustment parameters.

[0279] For example, see Figure 7, which is a flow chart of the control method provided by the embodiment of the present application. As shown in Figure 7, the control process in S502 may include the following steps:

[0280] S701: Obtain target values ​​of adjustment parameters of control variables.

[0281] The target value includes a first parameter value of the proportional parameter, a second parameter value of the differential parameter, and a third parameter value of the integral parameter.

[0282] S702: Obtain optimization data of dependent variables, such as optimization data of line balance rate.

[0283] S703, calculating the error, that is, calculating the error value between the data of the dependent variable corresponding to the current control variable and the optimized data of the dependent variable.

[0284] S704 , calculating a proportional value, that is, calculating the proportional value according to the first parameter value of the proportional parameter in the target value of the adjustment parameter and the error value.

[0285] S705 , calculating a differential value, that is, calculating the differential value according to the second parameter value of the differential parameter in the target value of the adjustment parameter and the error value.

[0286] S706 , calculating the integral value, that is, calculating the integral value according to the third parameter value of the integral parameter in the target value of the adjustment parameter and the error value.

[0287] S707 , performing weighted summation to obtain the adjustment amount, that is, performing weighted summation on the proportional value, the differential value, and the integral value.

[0288] S708: Apply the adjustment amount to the production system and collect actual data of the production system.

[0289] Jump to S703, if the error value is greater than the preset error, continue to execute S704-S708; if the error value is less than or equal to the preset error, execute S709.

[0290] S709: Optimize the mathematical model to obtain optimized data of new dependent variables.

[0291] Jump to S702 and execute the loop.

[0292] For the relevant content of step S709, please refer to the description in the embodiment of S302, which will not be repeated here.

[0293] Referring to Figure 8, it is a schematic diagram of the impact of the control method provided in an embodiment of the present application on the production system. As shown in Figure 8, the controllable variables of the processing unit 12 include the downtime waiting for materials, the processing speed and the line balance rate. The controllable variables of the scheduling unit 13 include the scheduling delay. The above-mentioned control method can regulate both the scheduling unit 13 in the production system and the processing unit 12 in the production system. Among them, the adjustment of the scheduling delay of the scheduling unit 13 can affect the downtime waiting for materials of the processing unit 12, and the downtime waiting for materials of the processing unit 12 will affect the production capacity. The adjustment of the scheduling delay of the scheduling unit 13 can also affect the line balance rate of the production line, thereby affecting the processing speed of the processing unit 12, and the processing speed of the processing unit 12 will affect the production quality and production capacity. In addition, the parameters that directly affect the line balance rate can be controlled by the adjustment method, and the line balance rate can reversely affect the scheduling unit 13 and the processing unit 12, thereby affecting the production capacity and quality of the production system. Through the control method in the embodiment of the present application, the scheduling unit and the processing unit in the production system can be controlled simultaneously to achieve dynamic control of the production system, thereby ensuring the production efficiency and production quality of the production system at the same time.

[0294] In some embodiments, the production system control method may further include:

[0295] updating the mathematical model of the production system at predetermined intervals to obtain an updated mathematical model;

[0296] Optimizing the updated mathematical model to obtain updated optimization data;

[0297] The production system is regulated according to the updated optimization data.

[0298] The steps of updating the mathematical model of the production system are the same as the steps of generating the mathematical model described in the embodiment of FIG. 4 . For details, please refer to the description in the embodiment of FIG. 4 , which will not be repeated here.

[0299] In the embodiment of the present application, by regularly remodeling the production system, the mathematical model changes with the state of the production system and is closer to the actual situation of the production system. This can effectively avoid the situation where poor control effects are caused by inaccuracies in the mathematical model, and is conducive to improving the reliability of production system control.

[0300] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0301] Figure 9 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. As shown in Figure 9, the electronic device 9 of this embodiment includes: at least one processor 90 (only one is shown in Figure 9), a memory 91, and a computer program 92 stored in the memory 91 and executable on the at least one processor 90. When the processor 90 executes the computer program 92, it implements the steps of any of the above-mentioned production system control method embodiments.

[0302] The electronic device may be a computing device such as a desktop computer, a notebook computer, a PDA, or a cloud server. The electronic device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that FIG9 is merely an example of an electronic device 9 and does not limit the electronic device 9. The electronic device may include more or fewer components than shown, or a combination of certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0303] The processor 90 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0304] In some embodiments, the memory 91 may be an internal storage unit of the electronic device 9, such as a hard disk or memory of the electronic device 9. In other embodiments, the memory 91 may also be an external storage device of the electronic device 9, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 9. Furthermore, the memory 91 may also include both an internal storage unit of the electronic device 9 and an external storage device. The memory 91 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program. The memory 91 may also be used to temporarily store data that has been output or is about to be output.

[0305] An embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the production system control method described in each of the above embodiments is implemented.

[0306] An embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the production system control method according to the above embodiments is implemented.

[0307] This embodiment also provides a computer program product, in which a computer-readable storage medium stores program code. When the computer program product runs on a computer, the computer executes the above-mentioned related steps to implement the production system control method in the above-mentioned embodiment.

[0308] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, it can implement the steps of the above-mentioned various method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0309] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0310] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

Claims

1. A method for controlling a production system, characterized in that: include: obtaining a mathematical model of the production system; Optimizing the mathematical model according to historical data of the production system to obtain optimized data of the production system; The production system is regulated according to the optimization data of the production system.

2. The method according to claim 1, characterized in that The step of obtaining the mathematical model of the production system comprises: Obtaining system parameters of the production system; A mathematical model of the production system is generated according to the system parameters of the production system.

3. The method according to claim 2, characterized in that Generating a mathematical model of the production system according to the system parameters of the production system comprises: determining a dependent variable of the mathematical model; Determining a decision variable related to the dependent variable according to a system parameter of the production system; A mathematical model of the production system is generated according to the dependent variables and the decision variables.

4. The method according to claim 3, characterized in that The step of generating the mathematical model of the production system according to the dependent variable and the decision variable comprises: determining constraints on the decision variables; A mathematical model of the production system is generated according to the dependent variable, the decision variable and the constraints of the decision variable.

5. The method according to claim 4, characterized in that The step of generating a mathematical model of the production system according to the dependent variable, the decision variable and the constraint conditions of the decision variable comprises: generating an objective function according to the dependent variable and the decision variable; A mathematical model of the production system is generated according to the constraint conditions of the decision variables and the objective function.

6. The method according to claim 3, characterized in that In the case where the dependent variable is a line balance rate, determining a decision variable related to the dependent variable according to a system parameter of the production system includes: Determining a first process time of a processing unit in the production system according to a system parameter of the production system; Determining a second process time of a bottleneck process in the production system according to system parameters of the production system; The decision variable is determined according to the first process time and the second process time.

7. The method according to claim 6, characterized in that The system parameters of the production system include the machine processing time of the processing unit and the logistics delay time of the scheduling unit; Determining the first process time of the processing unit in the production system according to the system parameters of the production system includes: The first process time of the processing unit in the production system is determined according to the machine processing time of the processing unit and the logistics delay time of the scheduling unit.

8. The method according to claim 6, characterized in that In the case where the processing unit is a bottleneck process, determining the first process time of the processing unit in the production system according to the system parameters of the production system includes: The first process time of the processing unit in the production system is determined according to the bottleneck process time of the processing unit.

9. The method according to claim 6, characterized in that The system parameters of the production system include the machine processing time of the processing unit; Determining the first process time of the processing unit in the production system according to the system parameters of the production system includes: The first process time of the processing unit in the production system is determined according to the machine processing time of the processing unit.

10. The method according to claim 6, characterized in that The determining of the constraint conditions of the decision variables includes: Determine a time interval of a first process time of a processing unit in the production system; The constraint conditions of the decision variables are determined according to the time interval.

11. The method according to any one of claims 3 to 10, characterized in that: The step of optimizing the mathematical model according to the historical data of the production system to obtain the optimized data of the production system includes: Acquire historical data of the decision variables in the production system; The data of the dependent variable in the mathematical model is predicted according to the historical data of the decision variable to obtain the optimized data.

12. The method according to any one of claims 3 to 10, characterized in that: The step of regulating the production system according to the optimization data of the production system comprises: Determining a control variable related to the dependent variable from system parameters of the production system; The control variable is adjusted according to the optimization data to obtain the adjusted control variable, and the adjusted control variable is used to adjust the production state of the production system.

13. The method according to claim 12, characterized in that The step of adjusting the control variable according to the optimization data to obtain the adjusted control variable includes: Obtaining a target value of a regulating parameter of the control variable; The control variable is adjusted according to the target value of the adjustment parameter and the optimization data to obtain the adjusted control variable.

14. The method according to claim 13, characterized in that The step of obtaining a target value of a regulating parameter of the control variable comprises: Acquire multiple groups of first candidate values ​​of adjustment parameters of the control variables; Calculating respectively an evaluation score corresponding to each group of the first candidate values, the evaluation score representing the value of the dependent variable obtained when the adjustment parameter of the control variable is the first candidate value; A group of the target values ​​is determined from multiple groups of the first candidate values ​​according to the evaluation scores corresponding to each group of the first candidate values.

15. The method according to claim 14, characterized in that The step of determining a set of target values ​​from a plurality of sets of the first candidate values ​​according to the evaluation scores corresponding to each set of the first candidate values ​​comprises: Deleting candidate values ​​whose evaluation scores are less than a preset value from the multiple groups of the first candidate values, to obtain at least one remaining group of the first candidate values; A set of the target values ​​is determined from the remaining at least one set of the first candidate values.

16. The method according to claim 15, characterized in that The adjustment parameters include a proportional parameter, a differential parameter and an integral parameter, and each group of the first candidate values ​​includes a first parameter value of a proportional parameter, a second parameter value of a differential parameter and a third parameter value of an integral parameter; The step of determining a set of the target values ​​from the remaining at least one set of the first candidate values ​​comprises: Sort the first parameter value, the second parameter value and the third parameter value in the remaining at least one set of the first candidate values. Column combination, to obtain multiple groups of second candidate values; Calculate the evaluation score corresponding to each group of the second candidate values ​​respectively; According to the evaluation score corresponding to each group of the second candidate values, a group of the target values ​​is determined from multiple groups of the second candidate values.

17. The method according to claim 16, characterized in that The step of adjusting the control variable according to the target value of the adjustment parameter and the optimization data to obtain the adjusted control variable includes: In one iteration process, the error value between the value of the dependent variable corresponding to the current control variable and the optimization data is calculated; When the error value is greater than a preset error, calculating an adjustment amount according to the error value and a target value of the adjustment parameter; The controlled variable is adjusted according to the adjustment amount to obtain the adjusted controlled variable.

18. The method according to claim 17, characterized in that When the error value is greater than the preset error, calculating the adjustment amount according to the error value and the target value of the adjustment parameter includes: When the error value is greater than a preset error, a proportional value is calculated according to the error value and a first parameter value in the target value of the adjustment parameter; Calculating a differential value according to the error value and a second parameter value in the target value of the adjustment parameter; Calculating an integral value according to the error value and a third parameter value in the target value of the adjustment parameter; The adjustment amount is calculated according to the proportional value, the differential value and the integral value.

19. The method according to claim 12, characterized in that The control variable includes at least one of the following: a scheduling speed, a scheduling displacement, a scheduling flow of a scheduling unit, and a processing speed of a processing unit, wherein the scheduling flow is used to represent the allocation amount of scheduling resources and the allocation amount of scheduling tasks; The step of adjusting the control variable according to the optimization data to obtain the adjusted control variable includes: Adjust the dispatching speed according to the optimization data to obtain the adjusted dispatching speed; Adjust the scheduling displacement according to the optimization data to obtain the adjusted scheduling displacement; Adjust the scheduling flow according to the optimization data to obtain the adjusted scheduling flow; The processing speed is adjusted according to the optimization data to obtain the adjusted processing speed.

20. The method according to claim 1, characterized in that The method further comprises: Updating the mathematical model of the production system at every preset period to obtain the updated mathematical model; Optimizing the updated mathematical model to obtain updated optimization data; The production system is regulated according to the updated optimization data.

21. The method according to claim 1, characterized in that The step of regulating the production system according to the optimization data comprises: Establishing a simulation environment for the production system; Regulating the simulation environment according to the optimization data to obtain a simulation result; If the simulation result meets the preset conditions, the production system is regulated according to the optimization data.

22. A production system, characterized in that: It includes a central control unit, at least one processing unit and at least one scheduling unit; The central control unit is used to control the processing unit and the scheduling unit according to the method according to any one of claims 1 to 21; The processing unit is used to process the production material to obtain the processed material; The dispatching unit is used to transport the processing material.

23. The production system according to claim 22, characterized in that The central control unit includes a decision-making layer and a control layer; The decision layer is used to obtain the mathematical model of the production system; optimize the mathematical model according to the historical data of the production system to obtain the optimized data of the production system; The control layer is used to regulate the production system according to the optimization data of the production system.

24. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the control method of the production system according to any one of claims 1 to 21 is implemented.

25. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the control method of the production system according to any one of claims 1 to 21 is implemented.

Images