Production plan optimization method and device and electronic equipment

Abstract

The invention discloses a production plan optimization method and device and electronic equipment. The method comprises the following steps: acquiring basic data of a production process flow; constructing a plurality of business models according to the basic data; a target business model to be measured and calculated is determined from the multiple business models, sub-case models of the target business model are determined, and the target business model comprises at least one sub-case model; according to the initial value of the sub-case model and a condition satisfied by a parameter in the sub-case model, determining an optimal solution of the sub-case model, the optimal solution being used for representing an optimal value required by each device for maximizing the benefit under a constraint condition and a target function; and determining a production plan according to the optimal solution. The technical problem that the overall calculation speed is affected due to the fact that the model construction efficiency of the large-scale plan optimization problem in the related technology is low is solved.

Description

Technical Field

[0001] The present application relates to the technical field of production management, and in particular to a method, device and electronic equipment for optimizing a production plan. Background Art

[0002] In the field of manufacturing, the formulation of production plans is inseparable from the establishment of various models. For large-scale planning optimization problems, the model building efficiency of related technologies is low, which affects the overall calculation speed.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a production plan optimization method, device and electronic device to at least solve the technical problem in the related art that the model construction efficiency of large-scale planning optimization problems is low, which affects the overall calculation speed.

[0005] According to one aspect of an embodiment of the present application, a method for optimizing a production plan is provided, comprising: obtaining basic data of a production process; constructing multiple business models based on the basic data; determining a target business model to be measured from the multiple business models, and determining a sub-case model of the target business model, wherein the target business model includes at least one sub-case model; determining an optimal solution of the sub-case model based on initial values ​​of the sub-case model and conditions satisfied by parameters in the sub-case model, wherein the optimal solution is used to represent the optimal value required for each device to maximize the benefit under constraints and objective functions; and determining a production plan based on the optimal solution.

[0006] In some embodiments of the present application, determining a sub-case model of a target business model includes: determining sub-case data corresponding to the target business model by determining a parameter set of the target business model; and determining the sub-case model based on the parameter set and the sub-case data.

[0007] In some embodiments of the present application, the parameter set is determined by one of the following methods: determining the parameter set by a first method, wherein the first method includes determining a starting value of a measurement variable, an ending value of a measurement variable, and a step size; determining the parameter set by a second method, wherein the second method includes determining a starting value of a measurement variable, an ending value of a measurement variable, and a specified number of values; determining the parameter set by a third method, wherein the third method includes specifying a measurement variable or constraint.

[0008] In some embodiments of the present application, a sub-case model is determined based on a parameter set and sub-case data, including: determining a measured value corresponding to a measured variable in the parameter set; and determining the sub-case model based on conditions satisfied by the measured value and the parameters in the sub-case model.

[0009] In some embodiments of the present application, the method also includes: obtaining a structure tree to which multiple business models belong, wherein the root node of the structure tree is a basic model, and the basic model includes multiple business models; determining a target business model from the structure tree; determining sub-cases of the target business model under different measurement values ​​of different measurement variables, wherein the sub-cases are leaf nodes of the structure tree; and updating the structure tree based on the sub-cases.

[0010] In some embodiments of the present application, the initial value of the sub-case model is determined in the following manner: obtaining a set of constraint variables corresponding to all sub-case models, wherein each constraint variable in the constraint variable set includes an upper limit and a lower limit of the variable; determining a first initial value of the sub-case model based on the upper limit, the lower limit and the initial value coefficient, wherein the first initial value is the initial value of any first variable in the sub-case model; determining a second initial value based on the first initial value and the transfer coefficient, wherein the second initial value is the initial value of any second variable in the sub-case model, and the first variable is obtained after the constraint is transferred.

[0011] In some embodiments of the present application, the method further includes: using multi-threading to perform parallel computing solutions on the sub-case model to obtain an optimal solution.

[0012] In some embodiments of the present application, determining a production plan based on an optimal solution includes: obtaining an optimal solution; determining a target benefit value curve graph based on the optimal solution, and determining a production plan based on the target benefit value curve graph.

[0013] According to another aspect of an embodiment of the present application, a production plan optimization device is also provided, including: an acquisition module for acquiring basic data of a production process; a construction module for constructing multiple business models based on the basic data; a first determination module for determining a target business model to be measured from multiple business models, and determining a sub-case model of the target business model, wherein the target business model includes at least one sub-case model; a solution module for determining an optimal solution of the sub-case model based on the initial values ​​of the sub-case model and the conditions satisfied by the parameters in the sub-case model, wherein the optimal solution is used to represent the optimal values ​​required for each device to maximize the benefit under constraints and objective functions; a second determination module for determining a production plan based on the optimal solution.

[0014] According to another aspect of the embodiment of the present application, there is also provided an electronic device, including: a memory and a processor, the memory being used to store program instructions; the processor being connected to the memory and being used to execute an optimization method for realizing the above-mentioned production plan.

[0015] In an embodiment of the present application, by constructing a sub-case model based on the business model and determining the optimal solution of the sub-case model to determine the production plan, the purpose of finding a production plan that maximizes the benefits under constraints and objective functions is achieved, thereby achieving the technical effect of significantly improving the efficiency of production plan formulation and optimization effects, and further solving the technical problem of low model construction efficiency for large-scale planning optimization problems in related technologies, which affects the overall calculation speed. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 It is a hardware structure block diagram of a computer terminal of a production plan optimization method according to an embodiment of the present application;

[0018] Figure 2 is a flow chart of a method for optimizing a production plan according to an embodiment of the present application;

[0019] Figure 3 It is a basic data schematic diagram of a production process flow of a production plan optimization method according to an embodiment of the present application;

[0020] Figure 4 This is a schematic diagram of multi-scheme calculation data of a production plan optimization method according to an embodiment of the present application;

[0021] Figure 5 It is a schematic diagram of a calculation flow of a production plan optimization method according to an embodiment of the present application;

[0022] Figure 6 is a structural diagram of a production plan optimization method according to an embodiment of the present application;

[0023] Figure 7 It is a structural schematic diagram of a production plan optimization device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0026] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0027] Multi-threaded Parallel Computing (MPC): In computer programming, multiple threads are used to execute computing tasks simultaneously to improve computing efficiency and response speed.

[0028] Planning Optimization Matrix: A method of organizing the constraints and variables in planning optimization into a matrix form to facilitate solving using linear or nonlinear programming algorithms.

[0029] In the field of manufacturing, the formulation of production plans is inseparable from the establishment of various models. The establishment of models and their solution process require a large amount of data input. Due to the differences in data and the complexity of the production plan itself, the formulation of production plans often consumes a lot of time, energy and resources, and even fails to obtain the optimal solution. The relevant technology has high requirements for modeling personnel. Multiple scheme calculations require repeated modeling, which consumes a lot of manpower and material resources. In addition, for large-scale planning optimization problems, the efficiency of constructing models is too low. In addition, the search method used in the relevant technology relies heavily on the initial value problem, and the solution result depends largely on the quality of the initial value.

[0030] In order to solve the above technical problems, the embodiments of the present application provide corresponding solutions, which are described in detail below.

[0031] The production plan optimization method embodiment provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a method for optimizing a production plan. Figure 1As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions connected via a wired and / or wireless network. In addition, it may also include: a display, a keyboard, a cursor control device, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, and a BUS bus. Those skilled in the art can understand that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0032] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0033] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the method for optimizing the production plan in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned method for optimizing the production plan. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0034] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .

[0036] It should be noted that, in some optional embodiments, the above Figure 1 The computer terminal shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the computer terminal described above.

[0037] In the above-mentioned operating environment, an embodiment of the present application provides an embodiment of a method for optimizing a production plan. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0038] Figure 2 is a flow chart of a method for optimizing a production plan according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0039] Step S202, obtaining basic data of the production process flow.

[0040] In the above step S202, the production process refers to the sequence of all conversion steps and production operations from raw materials to final products, including the input, processing, conversion, output of materials and any auxiliary processes such as mixing, separation or refining. For example, in the field of oil refining and chemical industry, the production process covers the whole process from crude oil cracking to final product synthesis.

[0041] Basic data refers to the original information set that constitutes the production process model, including but not limited to device capabilities, material properties, market supply and demand information, operating conditions, product quality indicators, cost data, etc. Basic data can be obtained by consulting the factory's technical manuals, historical operation records, or directly reading from the on-site equipment control system. It can also come from laboratory test results, specifications provided by suppliers, or industry databases. For example, taking device capability data as an example, it can be based on the device's engineering design data and historical operation data. The engineering design data provides the maximum and minimum production capacity of the device, while the historical operation data reflects the actual performance of the device under different conditions.

[0042] In some embodiments of the present application, a property transfer flow diagram can be established based on basic data to show the flow path and property changes of materials between different devices. For example, the property transfer flow diagram can record in detail the entire process of materials from feed to each device and then to the final product, as well as the changes in material properties at each stage. Through this diagram, you can intuitively understand how materials flow on the production line and how process operations affect the quality of the final product.

[0043] Step S204, constructing multiple business models based on the basic data.

[0044] In the above step S204, the business model refers to a mathematical model constructed based on the production process and basic data, which is used to describe and predict the production activities of a refinery or chemical plant. The business model covers key elements such as equipment, materials, properties, supply and demand relationships, and is used to evaluate the economy and feasibility of different production plans. For example, the equipment model can describe the operating characteristics and material handling capacity of a single processing unit (such as a normal and low pressure distillation tower, a catalytic cracking reactor), including its maximum processing volume, minimum processing volume, and how to convert input materials into output materials under specific conditions; the property model can describe the physical and chemical properties of the material, such as density, viscosity, sulfur content, etc., and changes in these properties will affect the quality and value of the final product; the supply and demand model can describe the market demand for specific products and the supply capacity of the refinery, and is used to predict the market adaptability and potential profits under different production plans.

[0045] In some embodiments of the present application, for the device model, the device model can be established by collecting the design parameters and historical operation data of the device, using linear or nonlinear programming techniques, that is, based on the capacity data and operating conditions of the device, using mathematical equations to describe the material balance and conversion process of the device. For example, for the atmospheric and vacuum distillation unit, the model will consider the feed amount of crude oil, the output ratio of each fraction, and energy consumption, etc.; for the property model, the model can be trained based on historical data by a data-driven method (such as a machine learning algorithm) to predict the changes in material properties under future conditions, that is, using historical data and material properties to establish a prediction model to evaluate the impact of changes in material properties on production costs and benefits. For example, by analyzing historical data on the cracking product yields of different types of crude oil, a neural network data model can be constructed to predict the cracking yield to optimize the raw material selection and processing scheme. It should be noted that the construction of the business model is not limited to the above two types, and each business model can be constructed according to the basic data obtained according to its own characteristics.

[0046] Step S206, determining a target business model to be measured from the multiple business models, and determining a sub-case model of the target business model, wherein the target business model includes at least one sub-case model.

[0047] In the above step S206, by comparing different business models, based on the current production and market conditions, a model that best reflects the current business objectives can be selected as the target business model. For example, if the goal is to evaluate the impact of different crude oil purchase volumes on production efficiency, then the selected business model can include data and constraints of all relevant production processes such as crude oil procurement, cracking, processing and sales.

[0048] A sub-case model refers to a specific solution or scenario model under a target business model. Each sub-case model is generated by making partial adjustments or parameter modifications to the target business model, and is used to evaluate the impact of different operating conditions, raw material procurement strategies, or product structures on production benefits. In some embodiments of the present application, a sub-case model can be generated by changing specific parameters or constraints of the target business model. For example, the crude oil purchase volume, the processing capacity of a specific device, or the sales ceiling of a certain product can be modified. The generation of the sub-case model is based on business objectives and parameters that need to be evaluated, and each sub-case model represents a possible production scenario.

[0049] In order to more accurately simulate various possible situations in the production process and provide more comprehensive data support for formulating production plans, the sub-case model of the target business model can be determined in the following ways: by determining the parameter set of the target business model, determine the sub-case data corresponding to the target business model; determine the sub-case model based on the parameter set and the sub-case data.

[0050] The parameter set refers to a variable parameter set used to generate a sub-case model in the target business model, such as raw material purchase quantity, product sales price, device processing capacity, material property standard, etc. In some embodiments of the present application, a series of key parameters can be selected according to the business scenario and optimization goal, and these parameters will serve as the basis for generating the sub-case model. For example, if the goal is to evaluate the impact of different crude oil purchase quantities on production efficiency, the parameter set may include the purchase quantity, purchase price, and yield prediction of cracking products of various crude oils.

[0051] Sub-case data refers to a specific numerical data set for multi-scheme calculations defined based on a parameter set of a target business model. Each sub-case data set represents a specific change in a parameter or a group of parameters in a business model, and is used to generate a corresponding sub-case model to evaluate the benefits under different production strategies. In some embodiments of the present application, a specific numerical range or fixed value can be defined based on a selected parameter set to generate multiple sub-case data sets. The selection of parameter sets can be based on an in-depth analysis of factors affecting production, for example, considering multiple indicators such as market, cost, technology, and quality, to ensure that the generated sub-case model can fully cover the key changes in the business scenario.

[0052] By setting different parameter set definition methods, it is possible to adapt to production processes of different complexities. Whether it is simple linear production or complex multi-stage production, a suitable parameter set can be found. Specifically: the parameter set is determined by a first method, wherein the first method includes determining the starting value of the measured variable, the ending value of the measured variable and the step size; the parameter set is determined by a second method, wherein the second method includes determining the starting value of the measured variable, the ending value of the measured variable and the specified number of values; the parameter set is determined by a third method, wherein the third method includes specifying the measured variable or constraint.

[0053] Measured variables refer to variable parameters used for adjustment and testing in plan optimization or multi-scheme measurement. Measured variables can be raw material purchase volume, product sales price, device processing capacity, material property standards, etc.

[0054] The first method is to determine the parameter set by defining the starting value, ending value and step size of the measured variable. This method is suitable for parameters that need to change continuously to evaluate their continuous impact on production benefits. For example, if the goal is to evaluate the impact of different crude oil purchase volumes on benefits, the starting value of the crude oil purchase volume can be set to 10 million tons, the ending value to 12 million tons, and the step size to 500,000 tons. This means that 21 sub-case models will be generated, and the crude oil purchase volume of each model will increase by 500,000 tons until it reaches 12 million tons. This method can systematically evaluate the changing trend of parameters within a certain range.

[0055] The second method is to determine the parameter set by defining the starting value, ending value, and number of specified values ​​of the measured variable. It is similar to the first method, but is more suitable for situations where multiple discrete points need to be compared within a specific value range. For example, when evaluating the impact of changes in the processing capacity of a device, you can set the starting value to 80%, the ending value to 100%, and the number of specified values ​​to 5. This will generate 5 sub-case models, with the device processing capacity adjusted to 80%, 85%, 90%, 95%, and 100%, respectively, so as to compare the impact of different processing capacities on production benefits within the specified range.

[0056] The third method is to directly specify the parameters or constraints that need to be tested. This method is suitable for situations where fixed value comparison is required, such as selecting several specific raw materials for cost-effectiveness analysis. For example, in the business scenario of crude oil cost-effectiveness measurement, the goal is to evaluate the procurement effect of 21 different crude oils, and a fixed procurement volume of 1 million tons can be specified for each crude oil. In this way, each sub-case model focuses on the changes in a single parameter or constraint, which facilitates direct comparison of its benefits.

[0057] The generation of sub-case models depends on the structure and data of the target business model. By locally updating the variable values ​​in the parameter set, multiple sub-models can be quickly generated, each of which corresponds to a specific scenario or assumption in the business model. In some embodiments of the present application, based on the target business model, the constraints or objective functions in the business model can be locally updated according to the parameter values ​​in the sub-case data to generate a specific sub-case model. For example, when evaluating the impact of changes in the sales ceiling of a product on production efficiency, each sub-case model will change the sales ceiling of the product while keeping other parameters unchanged to simulate production situations under different sales strategies.

[0058] In some embodiments of the present application, the sub-case model can be determined by the following steps: determining the measured values ​​corresponding to the measured variables in the parameter set; and determining the sub-case model based on the conditions satisfied by the measured values ​​and the parameters in the sub-case model.

[0059] The measured value refers to the specific value defined for the selected measured variable. The measured value will be used to create a subcase model to evaluate the benefits under a specific production strategy. The setting of the measured value can be determined by gradient (corresponding to the first method), specified value range (corresponding to the second method) or fixed value (corresponding to the third method), depending on the business scenario to be tested.

[0060] After the measured values ​​are determined, it is necessary to construct or update the sub-case model based on these measured values ​​and the set constraints to reflect the production environment under a specific production strategy. In some embodiments of the present application, for each sub-case, only the measured variables need to be partially modified based on the target business model, while other model structures and parameters remain unchanged. For example, when evaluating the impact of changes in the processing capacity of multiple devices on production benefits, only the processing capacity parameters of each device can be changed, while keeping other device parameters unchanged, so that multiple sub-case models can be quickly generated, each model represents a different device processing capacity strategy. In an optional embodiment, when generating a sub-case model, it is also possible to check whether the model parameters meet all the set constraints. For example, if the processing capacity of a device is set to exceed its design capacity in a sub-case, such a sub-case model needs to be readjusted or excluded to ensure the feasibility of the model solution, to ensure the rationality of the sub-case model and the validity of the calculation results.

[0061] By constructing and updating the structure tree, the optimization process and results of the production plan can be clearly displayed, which is convenient for enterprises to make production decisions. Specifically: obtain the structure tree to which multiple business models belong, where the root node of the structure tree is the basic model, and the basic model includes multiple business models; determine the target business model from the structure tree; determine the sub-cases of the target business model under different measurement values ​​of different measurement variables, where the sub-cases are the leaf nodes of the structure tree; update the structure tree according to the sub-cases.

[0062] The structure tree refers to a tree structure used to organize and manage multiple business models, in which the root node is the basic model and the leaf nodes represent sub-case models under specific conditions (i.e., under different measurement values). The design of the structure tree makes model updates and multi-threaded processing more efficient, reduces repeated calculations, and can quickly locate and adjust specific business models. The root node refers to the top-level node of the structure tree, which represents the basic model of the entire system. The basic model contains the common parameters and constraints of all devices, materials, properties, utilities, and process flows, and is the basis for generating all sub-case models. The leaf node refers to the end node of the structure tree, and each leaf node corresponds to a specific sub-case model. These models are generated on the basis of the basic model by changing the values ​​of specific measurement variables (such as device processing capacity, raw material procurement volume, etc.), and are used to evaluate the benefits under different production strategies.

[0063] In the structure tree, a specific business model can be selected as the target business model according to the current business objectives or market conditions of the enterprise. For example, if the goal is to optimize the raw material structure, a business model containing all raw material sources and processing equipment can be selected as the goal to perform multi-scheme calculations. In some embodiments of the present application, a label or index can be added to each business model in the node of the structure tree to achieve rapid positioning of the target business model in the model tree. The label or index can be set based on the type, function or specific parameters of the model to facilitate subsequent sub-case generation and model updating.

[0064] In some embodiments of the present application, templates or predefined rules can also be used to generate sub-cases, that is, to improve the efficiency of sub-case generation, templates or rules can be predefined for specific types of measured variables and measured values. After determining the target business model, sub-case models that meet the requirements can be quickly generated according to these templates or rules, reducing the time for model construction.

[0065] When a sub-case model is generated, only the parameter set of the corresponding leaf node in the structure tree needs to be updated, while the parameters and constraints of other nodes (including the root node) remain unchanged, which avoids the overhead of repeatedly building the model and improves the computing efficiency. In some embodiments of the present application, sub-cases can be calculated in parallel, for example, using a multi-threaded or distributed computing framework to simultaneously process multiple leaf nodes (i.e., multiple sub-case models) in the structure tree to speed up the computing process, ensure full utilization of computing resources, and improve the efficiency of the entire computing process.

[0066] Step S208, determining the optimal solution of the sub-case model based on the initial value of the sub-case model and the conditions satisfied by the parameters in the sub-case model, wherein the optimal solution is used to represent the optimal value required for each device to maximize the benefit under the constraints and the objective function.

[0067] In the above step S208, the initial value refers to the initial value set for each parameter in the model before determining the optimal solution of the sub-case model. In some embodiments of the present application, an optimization algorithm based on the branch and bound method can be used, combined with the characteristics of multi-scheme measurement, to generate an initial value for each parameter in the sub-case model. The initial value strategy can simultaneously consider the constraints of all sub-cases to ensure the validity and applicability of the initial value. For example, for the processing volume parameter of a certain equipment, in all sub-cases, its initial value can be dynamically adjusted according to the change of the processing capacity of the equipment under different schemes. In addition, historical data and model prediction technology can also be used to generate a reasonable initial value according to the change trend of specific parameters (such as raw material procurement volume, product sales price, etc.) in the sub-case model. This initial value strategy can quickly converge to the optimal solution because the initial value has taken into account the correlation in actual production.

[0068] In order to ensure the rationality and accuracy of the initial value of the model, thereby improving the optimization effect of the production plan, the initial value of the sub-case model can be determined in the following way: obtain the constraint variable set corresponding to all sub-case models, wherein each constraint variable in the constraint variable set includes an upper limit and a lower limit of the variable; determine the first initial value of the sub-case model based on the upper limit, the lower limit and the initial value coefficient, wherein the first initial value is the initial value of any first variable in the sub-case model; determine the second initial value based on the first initial value and the transfer coefficient, wherein the second initial value is the initial value of any second variable in the sub-case model, and the first variable is obtained after the constraint is transferred.

[0069] Each variable in the set of constraint variables has a set of upper and lower limits, which come from the actual physical limitations, process requirements and economic factors of production to ensure the feasibility of the model solution. The initial value coefficient refers to the weight factor used to determine the initial value position, which determines the relative position of the initial value between the upper and lower limits of the variable. A reasonable initial value coefficient can help the model converge to the optimal solution faster.

[0070] The first initial value refers to the initial value determined based on the upper limit, lower limit and initial value coefficient of the variable before constraint transfer; the second initial value is the result of the first initial value after constraint transfer, taking into account the interaction and dependency between different variables, which helps to build a more accurate model initial value.

[0071] In some embodiments of the present application, the first initial value may be determined based on the initial value coefficient, and the calculation formula is:

[0072] x i =βmin(LB i )+(1-β)max(UB i ) (Formula 1)

[0073] LB i ≤x i ≤UB i (Formula 2)

[0074] Among them, x i is the first initial value of the first variable x in case i, β is the initial value coefficient, LB i is the lower limit of the variable x in case i, UB i is the upper limit of the constraint variable x in case i.

[0075] It should be noted that in addition to the above method, the company's historical production data can also be used to set a first initial value based on actual production conditions for each constraint variable. This method takes into account the fluctuations and trends in the actual production process, and can provide initial values ​​close to reality, thereby improving the accuracy of the model solution.

[0076] After determining the first initial value, considering the interaction between different variables, such as the change in the processing volume of one device may affect the material supply of other devices, the first initial value can be adjusted through the transfer coefficient to generate the second initial value. The transfer coefficient reflects the strength of this interaction and ensures that the model initial value is still valid and reasonable after the constraint transfer.

[0077] Specifically, the second initial value can be calculated by the following formula:

[0078] y=cx (Formula 3)

[0079] y=c(βmin(LB i )+(1-β)max(UB i )) (Formula 4)

[0080] Among them, x is the first variable before transfer, c is the transfer coefficient, and y is the second initial value of the second variable after transfer.

[0081] Through the transfer mechanism, the first initial value is transferred and adjusted between multiple sub-case models to generate the corresponding second initial value, ensuring that the initial value is valid in all sub-cases, avoiding the solution failure or falling into the local optimal solution due to unreasonable initial value.

[0082] Constraints refer to a series of rules and restrictions that model parameters need to meet during the optimization process. Constraints are derived from the physical, chemical, economic and safety requirements of actual production to ensure that the optimization results are feasible in actual production. For example, the device feed and discharge balance constraint, that is, during the optimization process, ensure that the feed volume of the equipment is equal to the discharge volume, which not only complies with the physical law of material conservation, but also ensures the continuity and stability of the production process. Another example is the property constraint and material balance constraint, that is, in the process of generating the optimal solution, it is necessary to ensure that the properties of the material (such as density, sulfur content, etc.) meet the upper and lower limit requirements, and that the purchase and sale volume of the material and the device usage are balanced.

[0083] The objective function refers to the criterion used to quantify and evaluate the pros and cons of different solutions in an optimization model. For example, in a planning optimization scenario for petroleum refining and chemical engineering, the objective function can be a benefit value, and the optimization process aims to find a combination of equipment parameters that can maximize the benefit.

[0084] In some embodiments of the present application, the optimal solution can be finally found by continuously branching and narrowing the search range based on the improved branch and bound algorithm. In the improved branch and bound algorithm, the search in the constraint model space can be more effectively performed according to the characteristics of multi-scheme measurement to avoid falling into the local optimal solution. For example, starting from the initial value of the model, the search range of the parameters can be determined by setting boundary conditions; the model can be branched, that is, multiple sub-problems are created, and the parameter range of each sub-problem is further refined to exclude those branches that will not produce the optimal solution; each sub-problem is solved, and those solutions that meet the constraints and have higher benefit values ​​are screened out to construct a smaller search space and further optimize the solution; by continuously iterating the branch and bound process, the search space is gradually narrowed, and an optimal solution is finally determined. The optimal solution has the highest benefit value among the solutions of all sub-problems and meets all constraints.

[0085] In order to improve the efficiency of production plan optimization and shorten the optimization cycle, the following steps can also be performed: use multi-threading to perform parallel calculations on the sub-case model to obtain the optimal solution. In some embodiments of the present application, the optimal solution can be obtained based on the multi-threaded model task segmentation. Specifically, the sub-case model generated in the multi-scheme measurement can be divided into several independent computing tasks, each task containing the optimization solution of a sub-case model. According to the number of computing resources (such as the number of processor cores), these tasks are processed in parallel using the same number of threads, and each thread is responsible for the solution of a sub-case model. In the above process, the solution process of each sub-case model is independent, which means that they can be processed in parallel without affecting each other. Multi-threading technology assigns the optimization solution task to different threads, and each thread is responsible for the solution of a sub-case model, which can reduce the total solution time and improve computing efficiency.

[0086] In order to avoid data inconsistency problems in parallel computing, an effective synchronization mechanism can also be established between multiple threads to ensure that each thread uses the latest model data. At the same time, threads need to be able to communicate with each other so that necessary information can be exchanged during the solution process, such as the update of the optimal solution. For example, global variables can be set or inter-thread communication mechanisms such as semaphores or mutexes can be used to ensure that the model data accessed by all threads is the latest. At the same time, when a thread finds the current optimal solution for a subcase model, it can send it to other threads so that they can use it in subsequent calculations, thereby improving the overall optimization effect.

[0087] Step S210, determining a production plan based on the optimal solution.

[0088] In the above step S210, the production plan refers to the strategy and arrangement for guiding the actual production activities of the enterprise determined based on the optimal solution. The production plan may include the procurement, processing, distribution and sales strategies of materials, the operating status and parameter settings of the device, and the reasonable allocation of resources, etc. In some embodiments of the present application, the optimal solution parameters of the optimization model can be interpreted as actual production parameters, such as the processing volume of the equipment, the distribution volume of the material, the feed temperature and pressure, etc., and a detailed production schedule is formulated based on these parameters.

[0089] In order to intuitively display the changes in benefits under different production strategies and help enterprises quickly identify the optimal production plan, the following steps can be performed: obtain the optimal solution; determine the target benefit value curve based on the optimal solution, and determine the production plan based on the target benefit value curve.

[0090] The target benefit value curve is used to show the changes in benefit values ​​under different production strategies (i.e., sub-case models). The target benefit value curve can be drawn with different parameter settings in the multi-scheme measurement (such as the value of the measurement variable) as the horizontal axis and the benefit value of the corresponding scheme as the vertical axis.

[0091] Through the above steps S202 to S210, by constructing a sub-case model based on the business model and determining the optimal solution of the sub-case model to determine the production plan, the purpose of finding a production plan that maximizes the benefits under the constraints and objective functions is achieved, thereby achieving the technical effect of significantly improving the efficiency of production plan formulation and optimization effect, and further solving the technical problem of low model construction efficiency of large-scale planning optimization problems in related technologies, which affects the overall calculation speed.

[0092] Figure 3 is a basic data schematic diagram of a production process flow of a production plan optimization method according to an embodiment of the present application, such as Figure 3 As shown, in some embodiments of the present application, the basic case data (ie, basic data) may include four parts: material data, device data, process data, and utility engineering data.

[0093] (1) Material data: Material data is the basic information of all raw materials, intermediate products and final products involved in the production process. It can include the name, properties (such as density, viscosity, sulfur content, etc.), source (purchase, internal production), upper and lower limits of consumption and production, as well as market sales price and purchase price. Material data is the key to building a production model. It is directly related to the construction of material balance constraints and is the basis for material flow and economic benefit analysis in planning optimization.

[0094] (2) Equipment data: Equipment data includes detailed information of all equipment in the production process (such as reactors, distillation towers, compressors, etc.), including the name, type, processing capacity (maximum and minimum processing volume), operating status (startup, shutdown, maintenance, etc.), energy consumption, product yield, etc. Equipment data is used to build equipment models, reflecting the material processing capacity of the equipment and its impact on the output and quality of the final product. It is an important source of equipment input and output balance constraints and property constraints in the optimization model.

[0095] (3) Process data: Process data describes the operating parameters and process flow in the production process, which may include specific process routes, process parameters (such as temperature, pressure, flow), material transfer paths between different devices, and the law of material property changes. Process data is used to build property models and blending models, reflecting how materials are transformed in the process flow under certain conditions, and how different materials are combined to meet product quality requirements. It is the key to considering production efficiency and cost in production plan optimization.

[0096] (4) Utility data: Utility data involves the supply and consumption data of utilities such as water, electricity, and steam used in the production process, and may include information such as the type, supply capacity, consumption, and price of utilities. Utility data is used to build supply and demand models and property transfer flow diagrams to ensure that the efficient use of energy and resources, as well as cost control issues, are considered during the optimization process, and is an important reference for maximizing economic benefits.

[0097] Figure 4 is a schematic diagram of multi-scheme calculation data of a production plan optimization method according to an embodiment of the present application, such as Figure 4 As shown, in some embodiments of the present application, multi-scheme calculation data mainly involves three parts: basic case data, calculation scheme data and selection report data.

[0098] (1) Basic case data: Basic case data is the basic reference point in the planning optimization method, which can include complete information such as all material data, equipment data, process data and utility data under normal production conditions. Basic case data serves as the starting point for multi-scheme calculations and provides a unified comparison benchmark for different calculation schemes.

[0099] (2) Calculation scheme data: The calculation scheme data is a series of variable parameters defined by the user, which is used to generate multiple sub-cases to evaluate the benefits and performance under different production strategies. It can include information such as the test scheme name, description, parameter adjustment range (starting value, ending value and step size, or specified multiple values). The calculation scheme data is partially modified based on the basic case data to generate sub-case models under specific conditions for further benefit analysis and optimization.

[0100] (3) Select report data: Select report data is the optimization result information selected by the user according to specific needs. It is used to generate customized reports and can include indicators such as benefit value, key production parameters, material flow, and other user-defined focus points. The definition of selected report data can help decision makers quickly locate and analyze optimization results related to specific production strategies and improve decision-making efficiency.

[0101] Figure 5 is a schematic diagram of a calculation flow of a production plan optimization method according to an embodiment of the present application, such as Figure 5 As shown, in some embodiments of the present application, the optimization of the production plan may include the following steps:

[0102] Step S502: Start, i.e. start the production plan optimization system or call the optimization algorithm, and the program starts running. This step is the starting point of the process, it marks the beginning of the entire multi-scheme calculation process, and provides a start signal for subsequent steps.

[0103] Step S504: Load model data, i.e. read material data, device data, process data and utility data from the database or file to build the basic information of the production model. In this step, the system can obtain all production-related data to provide necessary information for the subsequent generation of the optimization model. Loading model data is a prerequisite for generating the optimization model to ensure that the model can reflect the actual production environment.

[0104] Step S506: Generate an optimization model, that is, build an optimization model that maximizes benefits based on the data loaded in step S504, including objective functions and constraints. After the model data is loaded, the system uses these data to build a mathematical model, which will include the objective function of multi-objective optimization and the constraints to ensure production feasibility, providing a model framework for the subsequent creation of a multi-scheme model structure.

[0105] Step S508: Multi-scheme model structure creation, that is, based on the multi-scheme calculation data definition, using tree structure or sub-model generation technology to build the overall structure of the multi-scheme model, and taking each sub-case model as part of the structure. After the optimization model is generated, in order to adapt to the multi-scheme calculation, the system can create a model structure containing all sub-cases. This step ensures that the multi-scheme data loaded later can correspond to the correct sub-model, which is convenient for the subsequent optimization solution.

[0106] Step S510: Loading multi-scheme data, i.e. reading multi-scheme calculation data, including scheme name, description, parameter variation range and other information. Loading multi-scheme data is a key step to apply user-defined calculation parameters and ranges to the model structure, providing specific parameters and calculation ranges for the generation of each sub-case model, and is closely linked to the creation of the multi-scheme model structure, providing specific data support for the generation of sub-models.

[0107] Step S512: Add sub-scheme models, that is, according to the multi-scheme data loaded in step S510, the basic model is partially updated, the optimization model of each sub-case is generated, and it is added to the multi-scheme model structure. This step is to generate a specific model for each sub-case based on the creation of the multi-scheme model structure to ensure that the model parameters and constraints of each sub-case can correctly reflect the user-defined measurement variables and are directly related to the loaded multi-scheme data.

[0108] Step S514: Generate constraint model, that is, generate specific constraint model for each sub-scheme model, including material balance, property constraint, planning optimization objective function, etc., and convert it into standard mathematical problem for optimization solution. After the sub-scheme model is generated, the constraint conditions can be further refined to construct the constraint model. This step ensures that all sub-case models can run under the framework of mathematical solution, and prepares mathematical expression for subsequent multi-scheme initial value generation and solution.

[0109] Step S516: Generate initial values ​​for multiple scenarios, that is, generate an initial solution for each sub-case model and ensure that the initial value can meet the constraints of all models. Initial value generation is the starting point of optimization solution, which is crucial to ensure the stability and efficiency of the solution. This step can comprehensively consider the characteristics of all sub-case models and generate a reasonable initial value, providing a good foundation for the subsequent planning optimization model solution.

[0110] Step S518: Multi-threaded sub-scheme solution, that is, using multi-threaded parallel computing technology to simultaneously perform optimization solutions for multiple sub-schemes to speed up the solution process. After the initial value is generated, the system can use multi-threaded technology to solve multiple sub-case models in parallel, significantly improving the calculation efficiency. This step fully utilizes the multi-core processing power of modern computers, is closely linked to the initial value generation, and helps to improve the efficiency of multi-scheme calculations.

[0111] Step S520: Result output, that is, summarizing and analyzing the optimization results of each sub-scheme to generate the final multi-scheme calculation report, including benefit value curves, etc. After all sub-case models are solved, the system can process and analyze the results to form an easy-to-understand report. This step provides a platform for evaluating and comparing different production strategies, helping decision makers to choose the best solution, thus forming a closed loop with the previous multi-threaded solution step and completing the entire multi-scheme calculation process.

[0112] Figure 6 is a schematic diagram of a structure tree of a production plan optimization method according to an embodiment of the present application, which shows how a model is organized into a tree structure in a specific embodiment to effectively support multi-scheme calculation. Figure 6 As shown in the figure, the root node is the starting point of the entire structure tree, which represents the collection of basic models, including all basic models used for production planning optimization. These models cover all aspects of the production process, such as device model, atmospheric and vacuum model, supply and demand model, property model, blending model and global model.

[0113] exist Figure 6 Under the root node of , the device model nodes specify the devices in the production process, such as "normal pressure 1" and "normal pressure 2". These device model nodes represent different devices in the production process. Each device model contains information such as the processing capacity, material inflow and outflow balance, and property constraints related to it. The device model node is a key component for processing material flow and production capacity in the optimization model. The "Base" node represents the base case. It is the starting point of all sub-schemes and contains the original parameters and constraints of all device models, supply and demand models, etc. The base case is a fixed reference point in the optimization model. All multi-scheme calculations are based on the "Base" case. By comparing the "Base" case, the changes in production benefits under different sub-cases can be evaluated. Sub-scheme model nodes, such as "Case1" and "Case2", are nodes representing different scenarios in multi-scheme calculations. These sub-scheme model nodes are partially modified based on some parameters and constraints of the "Base" node to reflect specific production strategies or parameter changes. For example, "Case1" corresponding to "normal pressure 1" can represent a production strategy after the capacity or operating parameters of the "normal pressure 1" device are adjusted.

[0114] exist Figure 6Under the root node of , the supply and demand model nodes include nodes such as "Purchase 1" and "Sales 1", which represent the material procurement and sales activities in the production process. The models in these supply and demand model nodes take into account the market supply and demand relationship and price fluctuations, which are crucial to the benefit analysis of production plan optimization. For example, "Purchase 1" can involve the purchase volume and price changes of raw materials, while "Sales 1" can reflect the adjustment of product sales prices and market capacity. Similarly, the "Base" node represents the base case, which is the starting point of all sub-schemes and contains the original parameters and constraints of all device models, supply and demand models, etc. "Case1" and "Case2" are also sub-scheme model nodes, which are nodes representing different scenarios in multi-scheme calculations. The existence of nodes such as "Case1" and "Case2" enables the optimization model to flexibly adapt to various production scenarios and perform multi-scheme benefit calculations.

[0115] Figure 6 The tree-structured organization method in makes full use of the similarities and differences between models, avoiding the repeated construction of complete models in each multi-scheme calculation. By partially updating the parameters and constraints in the "Base" case to generate sub-scheme models such as "Case1" and "Case2", the time for model construction can be significantly reduced and the efficiency of multi-scheme calculation can be improved. At the same time, this structure helps to more clearly manage and understand the relationship between models, facilitate tracking and comparison of optimization results under different schemes, and thus assist enterprises in making more informed production planning decisions.

[0116] To facilitate understanding of the above content, a refinery is used as an example to further illustrate the above content.

[0117] (1) Business scenario 1 setting:

[0118]

[0119] (2) Example of inputting data: You can select and enter one of the step size and the number of specified values.

[0120] Variable encoding variable Variable Types start Finish Step Length Specify the number of values 123 A product Upper limit 290 230 10 7

[0121] (3) The data converted into mathematical model are as follows:

[0122]

[0123] (4) The results of the multi-scheme calculation 1 are as follows:

[0124]

[0125] It should be noted that a target benefit diagram can be drawn based on the above results, including a curve diagram, a bar chart, etc., which will not be described in detail here.

[0126] (1) Business scenario 2 setting:

[0127]

[0128]

[0129] (2) Input data example:

[0130] / / Solution 1 Solution 2 Solution 3 Solution 4 ...... Crude1 Crude oil 1 100 0 0 0 0 Crude2 Crude Oil 2 0 100 0 0 0 Crude3 Crude Oil 3 0 0 100 0 0 Crude4 Crude oil 4 0 0 0 100 0 ...... ....... ....... ....... ....... ....... ......

[0131] In business scenario 2, a parameter set determination method different from that in business scenario 1 is adopted. Subsequently, multiple scheme calculation results can also be generated based on the defined data, which will not be repeated here.

[0132] The multi-scheme calculation method adopted in this application can significantly improve the efficiency of calculation and evaluation. Compared with the method of building models multiple times and running them one by one, multi-threaded parallel computing can process a large amount of data and schemes at the same time, reducing duplication of work and time cost, and is very useful in processing large-scale models, batch calculations, and applications that require rapid solutions. By testing and comparing multiple schemes together, the use of resources is effectively saved, and multiple schemes can be run at one time, reducing computing resources and manpower investment. In addition, by considering the comprehensive effects and influencing factors of multiple schemes at the same time, a more comprehensive perspective can be provided for decision makers. For example, after systematically comparing and analyzing different schemes, it is possible to gain insight into the differences in crude oil cost performance, raw material or product structure optimization, and other measurement parameters of different schemes, which helps to find the best solution, identify feasible improvement space, and provide guidance and suggestions for the optimization of petrochemical production plans, so as to make more informed decisions.

[0133] Figure 7 is a structural diagram of a production plan optimization device according to an embodiment of the present application, such as Figure 7 As shown, the device comprises:

[0134] The acquisition module 702 is used to acquire basic data of the production process;

[0135] A construction module 704 is used to construct multiple business models based on basic data;

[0136] A first determination module 706 is used to determine a target business model to be measured from a plurality of business models, and determine a sub-case model of the target business model, wherein the target business model includes at least one sub-case model;

[0137] A solution module 708, used to determine the optimal solution of the sub-case model according to the initial value of the sub-case model and the conditions satisfied by the parameters in the sub-case model, wherein the optimal solution is used to represent the optimal value required for each device to maximize the benefit under the constraint conditions and the objective function;

[0138] The second determination module 710 is used to determine a production plan according to the optimal solution.

[0139] It should be noted that Figure 7 The production plan optimization device shown is used to execute Figure 2 The optimization method of production planning shown is therefore Figure 2 The explanations in the optimization method of production planning in also apply to Figure 7 The optimization device of the production plan shown will not be described in detail here.

[0140] An embodiment of the present application also provides an electronic device, which includes a memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the steps of the production plan optimization method in each embodiment of the present application.

[0141] For example, the processor performs the following functions by executing program instructions stored in the memory:

[0142] Obtain basic data of the production process; construct multiple business models based on the basic data; determine the target business model to be measured from the multiple business models, and determine the sub-case model of the target business model, wherein the target business model includes at least one sub-case model; determine the optimal solution of the sub-case model based on the initial value of the sub-case model and the conditions satisfied by the parameters in the sub-case model, wherein the optimal solution is used to represent the optimal value required for each device to maximize the benefit under the constraints and the objective function; determine the production plan based on the optimal solution.

[0143] An embodiment of the present application further provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the steps of the production plan optimization method in each embodiment of the present application by running the computer program.

[0144] An embodiment of the present application also provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of the production plan optimization method in each embodiment of the present application.

[0145] The embodiments of the present application also provide a computer program, which, when executed by a processor, implements the steps of the production plan optimization method in each embodiment of the present application.

[0146] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0147] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0148] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0149] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0151] 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 technical solution of the present application can be essentially or partly or all or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc., which can store program code.

[0152] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for optimizing a production plan, characterized in that: include: Obtain basic data of production process; Building multiple business models based on the basic data; Determining a target business model to be measured from the multiple business models, and determining a sub-case model of the target business model, wherein the target business model includes at least one sub-case model; Determining an optimal solution of the sub-case model according to the initial value of the sub-case model and the conditions satisfied by the parameters in the sub-case model, wherein the optimal solution is used to represent the optimal value required for each device to maximize the benefit under the constraint conditions and the objective function; A production plan is determined according to the optimal solution.

2. The method according to claim 1, characterized in that Determine a sub-case model of the target business model, including: Determine sub-case data corresponding to the target business model by determining a parameter set of the target business model; A sub-case model is determined according to the parameter set and the sub-case data.

3. The method according to claim 2, characterized in that The parameter set is determined by one of the following methods: Determining the parameter set by a first method, wherein the first method includes determining a starting value of a measured variable, an ending value of a measured variable, and a step size; Determining the parameter set by a second method, wherein the second method includes determining a starting value of a measured variable, an ending value of a measured variable, and a specified number of values; The parameter set is determined by a third method, wherein the third method includes specifying measured variables or constraints.

4. The method according to claim 2, characterized in that: Determining a sub-case model according to the parameter set and the sub-case data includes: Determining a measured value corresponding to a measured variable in the parameter set; The sub-case model is determined according to the conditions satisfied by the measured value and the parameters in the sub-case model.

5. The method according to claim 1, characterized in that The method further comprises: Acquire a structure tree to which the multiple business models belong, wherein a root node of the structure tree is a basic model, and the basic model includes the multiple business models; Determining the target business model from the structure tree; Determine sub-cases of the target business model under different measured values ​​of different measured variables, wherein the sub-cases are leaf nodes of the structure tree; The structure tree is updated according to the subcase.

6. The method according to claim 1, characterized in that The initial value of the subcase model is determined in the following way: Obtaining a set of constraint variables corresponding to all sub-case models, wherein each constraint variable in the set of constraint variables includes an upper limit of a variable and a lower limit of a variable; Determine a first initial value of the sub-case model according to the variable upper limit, the variable lower limit and the initial value coefficient, wherein the first initial value is an initial value of any first variable in the sub-case model; A second initial value is determined according to the first initial value and the transfer coefficient, wherein the second initial value is the initial value of any second variable in the sub-case model, and the second variable is obtained after the first variable is constrained and transferred.

7. The method according to claim 1, characterized in that The method further comprises: The sub-case model is solved by parallel computing using multi-threading to obtain the optimal solution.

8. The method according to claim 1, characterized in that Determining a production plan according to the optimal solution includes: Obtaining the optimal solution; A target benefit value curve graph is determined based on the optimal solution, and the production plan is determined based on the target benefit value curve graph.

9. A production plan optimization device, characterized in that: include: Acquisition module, used to obtain basic data of production process; A construction module, used to construct multiple business models based on the basic data; A first determination module, configured to determine a target business model to be measured from the multiple business models, and determine a sub-case model of the target business model, wherein the target business model includes at least one sub-case model; A solution module, used for determining an optimal solution of the sub-case model according to the initial value of the sub-case model and the conditions satisfied by the parameters in the sub-case model, wherein the optimal solution is used to represent the optimal value required for each device to maximize the benefit under the constraint conditions and the objective function; The second determination module is used to determine the production plan according to the optimal solution.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory is used to store program instructions; the processor is connected to the memory and is used to execute the optimization method for implementing the production plan described in any one of claims 1 to 8.

Images