Scheduling optimization method for forming and manufacturing of large aerospace components under time-varying temperature constraints

Abstract

This application discloses a scheduling optimization method for the forming and manufacturing of large aerospace components under time-varying temperature constraints, belonging to the field of hot processing production technology. The method includes: obtaining production data of forgings, the production equipment of forgings includes a heating furnace and a forging press; based on the production data, determining an input vector consisting of the forging temperature, heating time, the heating furnace status of the heating furnace, the forging press status of the forging press, and the number of queued workpieces; inputting the input vector into a scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model for scheduling of production equipment and decision-making on the subsequent processing steps of the forgings. The scheduling optimization model is constructed based on a neural network model. This method can effectively cope with complex production processes where the temperature changes dynamically over time.

Description

Technical Field

[0001] The present application belongs to the field of thermal processing production technology, and in particular relates to a scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components. Background Art

[0002] The manufacturing process for large aerospace components typically involves multiple stages of processing, including high-temperature forging, cooling, and reheating. Due to the large size and complexity of these components, their forming quality and production efficiency are affected by numerous factors, with temperature control being a key factor in ensuring component performance. To ensure component performance, component temperature adjustments are often required multiple times during the manufacturing process, especially when components need to be returned to the reheating furnace. This results in a complex scheduling process with minimal intelligence.

[0003] However, current scheduling methods are mostly based on fixed processes or simple rule-based control, lacking real-time feedback on the dynamic condition of time-varying temperatures. Due to temperature fluctuations, pauses, and rework that can occur during component processing, traditional scheduling methods can easily lead to excessive heating or cooling, increasing energy consumption and even compromising the final component quality. Furthermore, because the forging process requires real-time temperature adjustments, existing scheduling methods and manual experience cannot effectively address these changes.

[0004] While some advanced scheduling optimization methods, such as genetic algorithms and particle swarm optimization, have shown improvement in specific situations, they are primarily applicable to static or quasi-static production environments and lack effective mechanisms for complex production processes where temperatures vary dynamically over time. Therefore, a method that can make intelligent scheduling decisions based on time-varying temperatures is urgently needed. Summary of the Invention

[0005] This application aims to solve at least one of the technical problems existing in the prior art. To this end, this application proposes a scheduling optimization method for forming and manufacturing large aerospace components under time-varying temperature constraints, which can effectively cope with complex production processes where the temperature changes dynamically over time.

[0006] In a first aspect, the present application provides a scheduling optimization method for forming and manufacturing large-scale aerospace components under time-varying temperature constraints, the method comprising:

[0007] Acquiring production data of forgings, wherein the production equipment of the forgings includes a heating furnace and a forging press;

[0008] determining, based on the production data, an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace state of the heating furnace, a forging press state of the forging press, and a number of queued workpieces;

[0009] The input vector is input into a scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model for scheduling the production equipment and deciding the subsequent processing steps of the forgings. The scheduling optimization model is constructed based on a neural network model.

[0010] According to one embodiment of the present application, the neural network model includes an estimation network and a target network, the estimation network is used to output the optimal scheduling strategy according to the input vector, and the target network is used to train the estimation network.

[0011] According to one embodiment of the present application, the estimation network includes an input layer, a first hidden layer, a second hidden layer, and an output layer connected in sequence; inputting the input vector into a scheduling optimization model to obtain an optimal scheduling strategy output by the scheduling optimization model includes:

[0012] receiving the input vector through the input layer and passing it to the first hidden layer;

[0013] Performing feature extraction on the input vector through the first hidden layer to obtain a high-dimensional feature vector;

[0014] compressing the high-dimensional feature vector through the second hidden layer to obtain a compressed feature vector;

[0015] A plurality of feasible actions corresponding to the compressed feature vector are determined through the output layer, and an action combination with the highest Q value among the plurality of feasible actions is determined as the optimal scheduling strategy.

[0016] According to one embodiment of the present application, determining, based on the production data, an input vector consisting of the forging temperature of the forging, the heating time, the heating furnace status of the heating furnace, the forging press status, and the number of queued workpieces includes:

[0017] constructing a forging temperature variation model of the forging based on the temperature data, and obtaining the forging temperature corresponding to the forging temperature variation model;

[0018] Inputting the temperature data into a forging temperature variation model of the forging to obtain the forging temperature output by the forging temperature variation model;

[0019] The forging temperature, the heating time, the heating furnace state, the forging press state and the number of queued workpieces are represented by vectors to obtain the input vector.

[0020] According to one embodiment of the present application, after inputting the input vector into the scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model, the method further includes:

[0021] Calculating a reward value for the optimal scheduling strategy through a reward function;

[0022] Parameters of the scheduling optimization model are optimized using the reward value.

[0023] According to one embodiment of the present application, the reward function R total The overall energy consumption model is constructed based on the temperature time-varying constraint and is used to describe the energy consumption of the forging during the processing, and is expressed as:

[0024] R total =R heat +R temp-error +R forge-temp +R forge-heat-loss +R exposure

[0025] R heat =-α·(c p ·m·(T 目标 -T 初始 )+ΔE 炉 )

[0026] R temp-error =-β·|T 目标 -T 初始 |

[0027]

[0028] R forge-heat-loss =-δ·Q 模具

[0029] R exposure =-λ·Q 环境

[0030] Among them, R heat is the reward function for the heating process, R temp-error is the furnace temperature fluctuation reward function, R forge-temp is the reward function of the forging process, R forge-heat-loss is the heat loss reward function of the forging process, R exposure is the heat exchange reward function of the forging exposed to air, c p is the specific heat capacity of the forging material, m is the mass of the forging, T 目标 is the target temperature after forging heating, T 初始 is the initial temperature of the forging, ΔE 炉 is the fixed energy consumption of the heating furnace, which is proportional to the heating time, T min Is the lowest temperature for forging, T max Is the highest temperature of forging, T 锻件 is the temperature of the forging, Q 模具is the heat dissipation between the forging and the die or hammer, Q 环境 is the heat exchange between the forging and the environment, α, β, γ, δ, and λ are the penalty coefficients of the reward function considering the energy consumption at each stage, T min and T max A time-varying constraint for defining the temperature of the forging.

[0031] According to one embodiment of the present application, the overall energy consumption model is constructed based on the forging temperature change model, and the overall energy consumption model includes a heating energy consumption sub-model in the heating stage, a forging energy consumption sub-model in the forging stage, and a heat dissipation sub-model in the heat dissipation stage.

[0032] In a second aspect, the present application provides an efficient scheduling optimization device for forming and manufacturing large aerospace components under time-varying temperature constraints, the device comprising:

[0033] An acquisition module, configured to acquire production data of forgings, wherein the production equipment of the forgings includes a heating furnace and a forging press;

[0034] a first processing module for determining, based on the production data, an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace state of the heating furnace, a forging press state of the forging press, and a number of queued workpieces;

[0035] The second processing module inputs the input vector into the scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model for scheduling the production equipment and deciding the subsequent processing steps of the forgings. The scheduling optimization model is constructed based on a neural network model.

[0036] In the third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the scheduling optimization method under the time-varying temperature constraint for the forming and manufacturing of large aerospace components as described in the first aspect above is implemented.

[0037] In a fourth aspect, the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it implements the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components as described in the first aspect above.

[0038] In the fifth aspect, the present application provides a chip, which includes a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement the scheduling optimization method under the time-varying temperature constraints of the forming and manufacturing of large aerospace components as described in the first aspect.

[0039] In a sixth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components as described in the first aspect above.

[0040] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become obvious from the description below, or will be learned through practice of the present application.

[0041] The present application provides a scheduling optimization method for forming and manufacturing large aerospace components under time-varying temperature constraints, which has the following beneficial effects compared to the existing technology:

[0042] (1) By predicting the optimal scheduling strategy for the input vector consisting of the forging temperature, heating time, heating furnace status, forging press status and the number of queued workpieces, an intelligent decision is made on whether to perform heating, forging or transfer processes. This can effectively cope with complex production processes where the temperature changes dynamically over time, reduce unnecessary heating times and heating time, reduce the energy consumption of the heating furnace, improve production efficiency, ensure the quality of forgings, solve the problems of excessive energy consumption and low production efficiency caused by temperature changes in the forging forming process, and achieve energy efficiency optimization in the forging forming process.

[0043] (2) It can realize efficient scheduling optimization under the temperature time-varying constraint in the forming and manufacturing of large-scale aerospace components, effectively improve production efficiency, reduce energy consumption, and improve the forming quality of components. It can quickly enter the forging process after heating to avoid the heated forgings cooling too much in the environment and then being reheated. By reducing the exposure time of the forgings from the heating furnace to the forging press and after forging, the heat exchange with the environment is reduced, the heat loss is reduced, and the forgings are ensured to be forged within the appropriate temperature range, avoiding quality problems caused by too low temperature or energy waste caused by too high temperature. Through intelligent scheduling, the connection of each process is optimized, the heat dissipation between the forgings and the forging dies, and between the forgings and the environment is reduced, and the forging temperature is maintained to the maximum extent. It is suitable for large-scale aerospace components, effectively improves production efficiency, reduces energy consumption, and improves the forming quality of components. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0045] Figure 1 This is a flow chart of a scheduling optimization method for forming and manufacturing large-scale aerospace components under time-varying temperature constraints provided by an embodiment of the present application;

[0046] Figure 2 FIG11 is a flow chart of multi-fire processing in the forging manufacturing process provided by an embodiment of the present application;

[0047] Figure 3 This is a flow chart of intelligent scheduling of a forging manufacturing process provided by an embodiment of the present application;

[0048] Figure 4 Schematic diagram of the time-varying temperature constraint in the forging manufacturing process provided by an embodiment of the present application;

[0049] Figure 5 This is a schematic diagram of the structure of an efficient scheduling optimization device under time-varying temperature constraints for forming and manufacturing large-scale aerospace components provided by an embodiment of the present application;

[0050] Figure 6 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are 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 are within the scope of protection of this application.

[0052] The terms "first," "second," and the like in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate, so that the embodiments of this application can be implemented in an order other than that illustrated or described herein, and that the objects distinguished by "first," "second," and the like are generally of the same type, and do not limit the number of objects; for example, the first object can be one or more. In addition, the term "and / or" in the specification and claims refers to at least one of the connected objects, and the character " / " generally indicates that the objects connected are in an "or" relationship.

[0053] In combination with the accompanying drawings, the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components, the efficient scheduling optimization device under the time-varying temperature constraint of the forming and manufacturing of large aerospace components, the electronic device and the readable storage medium provided in the embodiments of the present application are described in detail through specific embodiments and their application scenarios.

[0054] Among them, the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components can be applied to the terminal, and can be specifically executed by the hardware or software in the terminal.

[0055] The terminal includes, but is not limited to, a portable communication device such as a mobile phone or tablet computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad). It should also be understood that, in some embodiments, the terminal may not be a portable communication device, but a desktop computer having a touch-sensitive surface (e.g., a touch screen display and / or a touch pad).

[0056] In the following embodiments, a terminal including a display and a touch-sensitive surface is described. However, it should be understood that the terminal may include one or more other physical user interface devices such as a physical keyboard, a mouse, and a joystick.

[0057] The embodiment of the present application provides a scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components. The execution subject of the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components can be an electronic device or a functional module or functional entity in the electronic device that can implement the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components. The electronic devices mentioned in the embodiment of the present application include but are not limited to mobile phones, tablets, computers, cameras and wearable devices, etc. The scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components provided in the embodiment of the present application is explained below using electronic devices as the execution subject as an example.

[0058] like Figure 1 As shown, the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components includes: steps 110 to 130.

[0059] Step 110: Acquire production data of forgings, where the production equipment of the forgings includes a heating furnace and a forging press;

[0060] Among them, the production data is the actual production data of the forgings, including information such as temperature, heating time, forging time and energy consumption.

[0061] In this step, key data from the actual production of forgings by production equipment in the aerospace large component workshop is collected as production data. This data mainly includes operating data of equipment such as heating furnaces, forging presses, and forgings, such as heating time, heating furnace power, forging mass, specific heat capacity, and other physical parameters, as well as temperature change data of forgings, the environment, and equipment during the heating, forging, and heat dissipation processes. This is shown in the following table:

[0062]

[0063]

[0064] Understandably, forgings are large aerospace components, and they can be made from high-strength steel such as 300M, which is widely used in key aerospace structural components, such as landing gear. The forging and processing of this material requires strict temperature control. Maintaining a high temperature during the forming process ensures the material's mechanical properties. Real-time temperature data from the forgings during the forming and manufacturing process is collected and used to dynamically adjust the scheduling plan.

[0065] In the process of producing forgings in the aerospace large component workshop (hereinafter referred to as the workshop), they need to be heated in a heating furnace and then forged through a forging press.

[0066] Step 120: Determine an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace state of the heating furnace, a forging press state, and a number of queued workpieces based on the production data;

[0067] Among them, the forging temperature is the real-time temperature of the forging, the heating time is the heating time of each forging by the forging press during the forging stage, which will affect the temperature of the forging; the heating furnace status can be idle or working, the forging press status can be idle or working, and the number of queued workpieces is the number of workpieces waiting to be processed in the workshop.

[0068] In this step, data analysis and information extraction are performed on the production data to obtain information such as the forging temperature, heating time, heating furnace status, forging press status, and the number of queued workpieces. This information is represented in the form of a vector to obtain an input vector.

[0069] Step 130: Input the input vector into a scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model for scheduling the production equipment and deciding the subsequent processing steps of the forgings. The scheduling optimization model is constructed based on a neural network model.

[0070] Among them, the optimal scheduling strategy is a method for scheduling production equipment in the workshop. By rationally allocating resources, tasks and time, it can achieve an efficient, flexible and economical production process. It can also decide the next processing step of the forging, such as whether to perform heating, forging or transfer steps.

[0071] For example, the optimal scheduling strategy may include task priority management, resource optimization configuration, time management, and visual scheduling.

[0072] In this step, the input vector is input into the scheduling optimization model, and the input vector is feature extracted by the scheduling optimization model. Based on the mapping relationship between the forging temperature, heating time, heating furnace status, forging press status, and the number of queued workpieces and the control actions, the best performing combination of multiple control actions is obtained, and this combination is output as the optimal scheduling strategy.

[0073] According to the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components provided in the embodiment of the present application, the optimal scheduling strategy is predicted for the input vector consisting of the forging temperature, heating time, heating furnace status, forging press status and number of queued workpieces, and an intelligent decision is made whether to perform heating, forging or transfer processes. This method can effectively cope with complex production processes in which the temperature changes dynamically over time, reduce unnecessary heating times and heating time, reduce the energy consumption of the heating furnace, improve production efficiency, ensure the quality of forging forming, solve the problems of excessive energy consumption and low production efficiency caused by temperature changes in the forging forming process, and achieve energy efficiency optimization in the forging forming process.

[0074] In actual implementation, in order to optimize energy consumption and improve production efficiency, this application uses a scheduling optimization method under temperature time-varying constraints to intelligently schedule the processing process.

[0075] like Figure 2 As shown in the figure, the processing flow of forgings is explained by taking the landing gear as an example. The process flow of the landing gear includes blanking, blank making 5-6 times, heating, pre-forging 2-3 times, die forging 2-3 times and heat treatment. Its characteristics are many times and long process. Taking one of the heating cycles as an example: the forging goes through three steps: heating, forging and returning to the heating furnace for heating.

[0076] The heat loss process includes: heat exchange with the environment during heating, heat exchange with the die during forging, and heat dissipation during transportation from the heating furnace to the forging press.

[0077] In some embodiments, determining, based on the production data, an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace status of the heating furnace, a forging press status, and a number of queued workpieces, comprises:

[0078] Extracting temperature data, the heating time, the heating furnace status, the forging press status and the number of queued workpieces from the production data;

[0079] constructing a forging temperature variation model of the forging based on the temperature data, and obtaining the forging temperature corresponding to the forging temperature variation model;

[0080] The forging temperature, the heating time, the heating furnace state, the forging press state and the number of queued workpieces are represented by vectors to obtain the input vector.

[0081] The forging temperature variation model is used to describe the heat dissipation process of the forging from the heating furnace to the forging press, and the temperature data can be the temperature spatial distribution of the forging at the current moment.

[0082] In actual implementation, a mathematical model of the temperature changes of forgings throughout the production process, known as the forging temperature variation model, is established based on collected production data. This forging temperature variation model accounts for the temperature rise during the heating phase, heat loss due to contact with the forging die during the forging process, and heat exchange with the environment during transportation and exposure. This forging temperature variation model accurately predicts the change in forging temperature over time, thereby determining whether further heating or the next step of forging is necessary.

[0083] The temperature change of forgings can be described by the heat conduction equation (Fourier's heat conduction law). Assuming that the forgings are made of uniform material, the temperature change model of forgings in different forging processes (heating, cooling and forging) is as follows:

[0084]

[0085] Where T(x,t) represents the temperature data of the forging at position x and time t; α = k / ρc is the thermal diffusivity, k is the thermal conductivity of the material, ρ is the material density, and c is the specific heat capacity; represents the spatial gradient of temperature (Laplace operator), and q(x,t) is the power density of the external heat source (such as the heat energy input of a heating furnace).

[0086] The information such as forging temperature, power consumption, remaining processing time and current process is represented by vector to obtain the input vector S t :

[0087] S t ={T t ,P t ,t remaining ,stage t}

[0088] Among them, T t is the forging temperature at the current time t, P t is the power consumption of the current forging, t remaining The remaining processing time is used to characterize the process progress. t It is the current process and is used to characterize the processing stage.

[0089] In this embodiment, the temperature data is processed by the forging temperature change model to obtain the forging temperature that describes the forging temperature change, which can provide a basis for generating the optimal scheduling strategy to improve the yield, production efficiency and material properties of the forgings.

[0090] In some embodiments, the neural network model includes an estimation network and a target network, the estimation network is used to output the optimal scheduling strategy according to the input vector, and the target network is used to train the estimation network.

[0091] The scheduling optimization model is built based on the Double Deep Q-Network (DDQN) algorithm, with the goal of dynamically selecting the best energy-saving scheduling strategy, such as whether to return to the heating furnace.

[0092] The input vectors of the scheduling optimization model include actual data such as production equipment status (heating furnace status, forging press status), forging temperature, heating time, and the number of queued workpieces, and the output is the optimal scheduling strategy for each process.

[0093] The scheduling optimization model built based on the DDQN algorithm consists of two key networks: the Evaluation Network and the Target Network. These networks are used to estimate the value of actions (Q-values) in the current state and provide relatively stable target values, respectively. The Evaluation Network is continuously updated through feedback from the actual scheduling process, while the Target Network is used to generate more robust target values ​​to prevent instability caused by overestimation.

[0094] In some embodiments, the estimation network includes an input layer, a first hidden layer, a second hidden layer, and an output layer connected in sequence; inputting the input vector into a scheduling optimization model to obtain an optimal scheduling strategy output by the scheduling optimization model includes:

[0095] receiving the input vector through the input layer and passing it to the first hidden layer;

[0096] Performing feature extraction on the input vector through the first hidden layer to obtain a high-dimensional feature vector;

[0097] compressing the high-dimensional feature vector through the second hidden layer to obtain a compressed feature vector;

[0098] A plurality of feasible actions corresponding to the compressed feature vector are determined through the output layer, and an action combination with the highest Q value among the plurality of feasible actions is determined as the optimal scheduling strategy.

[0099] like Figure 3 As shown, the input vector S of the state space is obtained during the forging process of aerospace large components (forgings). t ={T t ,P t ,t remaining ,stahe t}.

[0100] In the state space, by input vector S t Defined as information such as current forging temperature, processing stage and process progress.

[0101] The input of the scheduling optimization model is the input vector S t , the output is the optimal scheduling strategy for each process, which mainly solves the following problems:

[0102] 1) Process sequence optimization: Intelligently adjust the order of heating, forging, and heat treatment of forgings to avoid unnecessary repeated heating or waiting time, and reduce heat dissipation;

[0103] 2) Parallel machine selection: When there are multiple production equipment (such as multiple heating furnaces or forging presses) running in parallel, the model selects the most energy-efficient equipment for processing based on the current status of the equipment and historical energy consumption data;

[0104] 3) Real-time dynamic adjustment: During the production process, the model can collect real-time equipment operation data and environmental feedback to dynamically adjust the workpiece processing sequence and equipment selection to ensure the lowest energy consumption and the highest production efficiency.

[0105] For example, when dealing with the scheduling optimization of 300M landing gear forgings, the DDQN neural network structure is set as follows:

[0106] In terms of the dimension of the input vector, each state contains 5 main variables: forging temperature (for example: 850℃), current heating time (for example: 60 seconds), heating furnace status (idle, working), forging press status (idle, working), and the number of queued workpieces (for example: 2 pieces). The input layer has 5 neurons to process this data.

[0107] The first hidden layer is a fully connected layer with 64 neurons. The first hidden layer is responsible for extracting the features of the input vector and generating a high-dimensional feature vector for analysis in subsequent layers.

[0108] The second hidden layer is a fully connected layer with 32 neurons, which further compresses the high-dimensional feature vector and provides information for decision output.

[0109] Output layer: Action space: The DDQN outputs a Q-value for each possible action. In the landing gear forging process, the action space is defined as follows: Adjust the heating time (decrease by 5 seconds, maintain the current time, increase by 5 seconds), a total of 3 actions; Select forging equipment (select forging press 1, select forging press 2), a total of 2 actions; Whether to trigger the heating furnace to reheat (yes, no), a total of 2 actions. The DDQN output layer has 7 neurons, corresponding to these 7 possible actions.

[0110] The optimal scheduling strategy can be represented in the action space as the optional operation A of the processing equipment t , such as whether to return to the heating furnace, continue processing or stop:

[0111] A t={heat,forge,cool,stop}

[0112] Among them, heat means heating, forge means forging, cool means cooling, and stop means stopping processing.

[0113] On this basis, the DDQN algorithm's online training and real-time feedback mechanism enables timely adjustments to scheduling plans during the production process based on collected real-time data (such as equipment operating status and forging temperature). Based on the actual temperature changes of the forging, it can determine whether reheating is necessary or whether it can proceed directly to the next forging step, thus avoiding quality issues caused by overheating or insufficient temperature. This dynamic scheduling makes the entire production process more intelligent and efficient.

[0114] In some embodiments, the overall energy consumption model is constructed based on the forging temperature change model, and the overall energy consumption model includes a heating energy consumption sub-model in the heating stage, a forging energy consumption sub-model in the forging stage, and a heat dissipation sub-model in the heat dissipation stage.

[0115] The overall energy consumption model provides a basis for energy consumption optimization. The heating energy consumption sub-model in the thermal stage, the forging energy consumption sub-model in the forging stage, and the heat dissipation sub-model in the heat dissipation stage are used to describe the energy consumption change process of forgings from the heating furnace to the forging press.

[0116] Based on the forging temperature change model, the overall energy consumption model of forging in each stage is constructed. The model is divided into three main parts:

[0117] 1) During the heating phase, the energy consumed by the heating furnace to heat the forging is calculated, which is mainly related to the heating time, heating furnace power, specific heat capacity of the forging and target temperature.

[0118] The forging is heated by an external heat source to reach the appropriate processing temperature. The heating energy consumption sub-model can be expressed as:

[0119]

[0120] Where m is the mass of the forging, c is the specific heat capacity of the material, and T target Indicates the target temperature, T inital represents the initial temperature, η furnace Indicates the efficiency of the heating furnace, P standby Indicates the power of the device when it is in standby mode during the heating process, t standby Indicates the duration of the device standby during the heating process.

[0121] To ensure that the forging reaches the target temperature, the heating time t heat as follows:

[0122]

[0123] Among them, P furnace Indicates the heating power of the heating furnace.

[0124] 2) During the forging stage, estimate the heat loss of the forging due to die heat exchange during the forging process. This part of the energy consumption is mainly determined by the forging die temperature and contact time.

[0125] The forging is plastically deformed by applying force through the forming equipment. The energy consumption of the forging process depends on the working power, working time and applied force of the forging press. The forging energy consumption sub-model is expressed as follows:

[0126]

[0127] Among them, P press is the working efficiency of the forging press, t forge Is the duration of forging, is the kinetic energy generated by the deformation of the forging, m is the mass of the forging, and v is the deformation velocity.

[0128] Forging time t forge It is related to the applied force and the deformation resistance of the material and can be estimated by the empirical formula:

[0129]

[0130] Among them, F required The force required to achieve the target deformation, F press is the force applied by the forging press.

[0131] 3) During the heat dissipation phase, the heat exchange between the forging and the surrounding environment is considered during transportation from the heating furnace to the forging press and during return to the heating furnace after forging. The model calculates the heat loss at each stage and combines it with the heating and forging energy consumption to obtain the total energy consumption for the entire production process.

[0132] The heat dissipation of forgings is mainly divided into three parts: the heat exchange between the forging and the environment during the process of forging from the heating furnace to the forging press, the heat dissipation caused by the contact between the forging and the forging hammer or forging die during the forging process, and the heat exchange between the forging and the environment during the process of returning from the forging press to the heating furnace. The heat dissipation sub-model of forgings is expressed as follows:

[0133]

[0134] Among them, Q 环境 is the heat exchange between the forging and the environment, h is the air convection heat transfer coefficient on the forging surface, A is the surface area of ​​the forging, T 锻件 is the temperature of the forging, T 环境 is the ambient temperature, t 转移 It is the time from the heating furnace to the forging press, Q模具 is the heat dissipation between the forging and the die or hammer, k 接触 is the contact thermal conductivity between the forging and the forging die, A 接触 is the contact area between the forging and the forging die, T 模具 is the temperature of the forging die, t 锻压 is the time the forging is pressed on the forging press, Q 环境返回 is the heat exchange amount between the forging and the environment during the process of returning from the forging press to the heating furnace, t 返回 is the time it takes for forgings to return from the forging press to the heating furnace, Q 总 It's Q 环境 , Q 模具 and Q 环境返回 The sum of .

[0135] For example, in the heating stage, assume that the landing gear blank is heated from ambient temperature (25°C) to 1200°C. According to the law of conservation of energy, the energy required is:

[0136] Q 加热 =m×c×(T 目标 -T 环境 )=800×500×(1200-25)=472,000,000J

[0137] Since 1 kWh is equal to 3600 kJ, the energy consumption is:

[0138] E 加热 =Q 加热 / (3600×1000)=131.1kWh

[0139] Considering the power of the heating furnace is 500kW, the heating time is:

[0140] t 加热 =E 加热 / P 加热炉 =131.1 / 500=0.2622 hours≈15.7 minutes

[0141] During the forging stage, the contact between the die and the forging causes heat to be lost from the forging. The heat loss can be calculated using Fourier's law:

[0142] Q 锻造 =k×A 锻模 ×(T 锻件 -T 锻模 )×t 锻造 =100×2×(1200-300)×60=10,800,000J

[0143] Converted to energy consumption:

[0144] E 锻造 =Q 锻造 / (3600×1000)=3.0kWh

[0145] In the heat dissipation stage, when the forging is exposed to the air, it exchanges heat with the environment through heat convection. According to Newton's law of cooling, the heat dissipation can be calculated as:

[0146] Q 耗散 =h×A 空气 ×(T 锻件 -T 环境 )×t 暴露 =10×3×(1200-25)×90=318,750J

[0147] Converted to energy consumption:

[0148] E 耗散 =Q 耗散 / (3600×1000)=0.0885kWh

[0149] The total energy consumption of forgings during the heating, forging and heat dissipation stages is:

[0150] E 总 =E 加热 +E 锻造 +E 耗散 =131.1+3.0+0.0885=134.19kWh

[0151] In this embodiment, the energy consumption changes of forgings during the processing are analyzed through the heating energy consumption sub-model in the heating stage, the forging energy consumption sub-model in the forging stage, and the heat dissipation sub-model in the heat dissipation stage. This can accurately describe the processing process at the energy consumption level, providing a basis for reducing the production energy consumption of forgings.

[0152] In addition, it can also collect and analyze actual production data in real time and dynamically adjust scheduling plans to reduce overall energy consumption, improve production efficiency and ensure product quality.

[0153] In some embodiments, the reward function R total The overall energy consumption model is constructed based on the temperature time-varying constraint and is used to describe the energy consumption of the forging during the processing, and is expressed as:

[0154] R total =R heat +R temp-error +R forge-temp +R forge-heat-loss +R exposure

[0155] R heat =-α·(c p ·m·(T 目标 -T 初始)+ΔE 炉 )

[0156] R temp-error =-β·|T 目标 -T 初始 |

[0157]

[0158] R forge-heat-loss =-δ·Q 模具

[0159] R exposure =-λ·Q 环境

[0160] Among them, R heat is the reward function for the heating process, R temp-error is the furnace temperature fluctuation reward function, R forge-temp is the reward function of the forging process, R forge-heat-loss is the heat loss reward function of the forging process, R exposure is the heat exchange reward function of the forging exposed to air, c p is the specific heat capacity of the forging material, m is the mass of the forging, T 目标 is the target temperature after forging heating, T 初始 is the initial temperature of the forging, ΔE 炉 is the fixed energy consumption of the heating furnace, which is proportional to the heating time, T min Is the lowest temperature for forging, T max Is the highest temperature of forging, T 锻件 is the temperature of the forging, Q 模具 is the heat dissipation between the forging and the die or hammer, Q 环境 is the heat exchange between the forging and the environment, α, β, γ, δ, and λ are the penalty coefficients of the reward function considering the energy consumption at each stage, T min and T max A time-varying constraint for defining the temperature of the forging.

[0161] like Figure 4 As shown, at the forging temperature T 锻件 In T min If the temperature is between 100°C and room temperature, the forging needs to be reheated in the heating furnace. 锻件 In T max In the above cases, the forging needs to be cooled.

[0162] In this embodiment, the total reward function R totalIt is directly related to energy consumption models such as heating, forging, and heat dissipation. By optimizing processing efficiency and energy consumption, designing reward functions, and minimizing energy consumption in each link through intelligent scheduling, overall energy efficiency optimization can be achieved.

[0163] Calculate the current state S through the value function t and action A t The value Q(S t ,A t ):

[0164]

[0165] Where γ is the discount factor, S t+1 and A t+1 are the state and action at the next moment, R t is the reward value of the action at the current moment.

[0166] In some embodiments, after inputting the input vector into the scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model, the method further includes:

[0167] Calculating a reward value for the optimal scheduling strategy through a reward function;

[0168] Parameters of the scheduling optimization model are optimized using the reward value.

[0169] During DDQN learning and iteration, the loss function is defined as the error between the current estimated network output and the target network output. The mean squared error (MSE) is used as the loss function for parameter optimization. The learning rate is set to 0.001, which means that the step size of each update is small to ensure stable convergence. The discount factor γ is set to 0.99, indicating that the model prioritizes the long-term benefits of future rewards. An exploration and exploitation strategy (ε-greedy strategy) is used: The initial exploration rate ε is set to 0.9 and gradually decreases as training progresses, reaching a minimum of 0.05. This means that actions with higher Q values ​​are prioritized in most situations.

[0170] During the iteration process, DDQN continuously learns based on feedback from actual data and optimizes the scheduling plan for producing forgings by production equipment in the workshop.

[0171] Through the online training and real-time feedback mechanism of the DDQN algorithm, this application can adjust the scheduling plan in a timely manner during the production process based on the real-time collected production data (such as the operating status of the equipment, the temperature of the forgings, etc.). Based on the actual temperature changes of the forgings, it can be judged whether it needs to be heated again or whether it can directly enter the next forging process, thereby avoiding quality problems caused by overheating or insufficient temperature. This dynamic scheduling makes the entire production process more intelligent and efficient.

[0172] During the heating process, the initial temperature is set at 1200°C. By real-time monitoring of the temperature change of the forging from inside the furnace to outside the furnace (assuming a temperature drop rate of 50°C per minute), when the forging temperature drops to 1000°C, the DDQN algorithm is triggered to determine whether the forging needs to be returned to the heating furnace.

[0173] During the forging process, as the forging moves from the heating furnace to the forging press, the ambient heat exchange causes the temperature to drop. Assuming the required forging temperature range is 950°C to 1050°C, when the forging temperature approaches the critical temperature (for example, 980°C), DDQN determines whether to proceed with forging immediately or, based on the queue status of the forging press, temporarily place the forging until the equipment is free.

[0174] During the forging and heating cycle, if the temperature of the forging drops to an unacceptable range (such as below 900°C) after forging, the DDQN algorithm will decide to return the forging to the heating furnace based on a comprehensive assessment of energy efficiency and quality, and determine the heating time based on the heat loss rate to ensure minimum energy consumption and restore the temperature to the required for forging range.

[0175] During the heating phase, DDQN compared the effects of different heating times (such as 60 seconds, 65 seconds, and 70 seconds) and found that 60 seconds was enough to make the forging reach the appropriate temperature (for example, 950°C). Therefore, after multiple iterations, the system gradually chose to heat for 60 seconds instead of the original 90 seconds. Considering that forgings usually need to be returned to the furnace three times during the forging process, the total heating time is reduced by 90 seconds. Through the scheduling of forging presses, DDQN found that selecting forging press 1 usually reduces waiting time, so when forging press 1 is idle, the system gives priority to this equipment. The following is the energy saving effect calculation for a single heating of 60 seconds:

[0176] Q 耗散，优化 =10×3×(1200-25)×60=212500J

[0177]

[0178] E 总，优化 =131.1+3.0+0.059=134.159kWh

[0179] The above results show that the application of this method reduces heating time and total energy consumption. The total heating time is reduced from 270 seconds in the traditional process to 120 seconds, which reduces furnace energy consumption, reduces the frequency of workpiece heating cycles, and shortens the process cycle. While maintaining the forming temperature, temperature feedback and dynamic adjustment ensure that the forging quality is not affected.

[0180] In this embodiment, efficient scheduling optimization under the temperature time-varying constraint in the forming and manufacturing of large aerospace components can be achieved, which effectively improves production efficiency, reduces energy consumption, and improves the component forming quality. After heating, the forging process is quickly entered to avoid the heated forgings cooling too much in the environment and then being reheated. By reducing the exposure time of the forgings from the heating furnace to the forging press and after forging, the heat exchange with the environment is reduced, the heat loss is reduced, and the forgings are ensured to be forged within an appropriate temperature range to avoid quality problems caused by too low temperature or energy waste caused by too high temperature. Through intelligent scheduling, the connection between each process is optimized, the heat dissipation between the forgings and the forging dies, and between the forgings and the environment is reduced, and the forging temperature is maintained to the maximum extent. It is suitable for large aerospace components, effectively improves production efficiency, reduces energy consumption, and improves the component forming quality.

[0181] The scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large-scale aerospace components provided in the embodiment of the present application can be executed by an efficient scheduling optimization device under the time-varying temperature constraint of the forming and manufacturing of large-scale aerospace components. In the embodiment of the present application, the efficient scheduling optimization device under the time-varying temperature constraint of the forming and manufacturing of large-scale aerospace components is used as an example to illustrate the efficient scheduling optimization device under the time-varying temperature constraint of the forming and manufacturing of large-scale aerospace components provided in the embodiment of the present application.

[0182] The embodiment of the present application also provides an efficient scheduling optimization device for forming and manufacturing large aerospace components under the time-varying temperature constraints.

[0183] like Figure 5 As shown, the efficient scheduling optimization device under the time-varying temperature constraint of the aerospace large-scale component forming and manufacturing includes:

[0184] An acquisition module 510 is used to acquire production data of forgings, where the production equipment of the forgings includes a heating furnace and a forging press;

[0185] A first processing module 520 is configured to determine, based on the production data, an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace state of the heating furnace, a forging press state of the forging press, and a number of queued workpieces;

[0186] The second processing module 530 inputs the input vector into the scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model for scheduling the production equipment and deciding the subsequent processing steps of the forgings. The scheduling optimization model is constructed based on a neural network model.

[0187] According to the efficient scheduling optimization device under the time-varying temperature constraints of the forming and manufacturing of large aerospace components provided in the embodiment of the present application, the optimal scheduling strategy is predicted for the input vector consisting of the forging temperature, heating time, heating furnace status, forging press status and number of queued workpieces, and an intelligent decision is made whether to perform heating, forging or transfer processes. It can effectively cope with complex production processes in which the temperature changes dynamically with time, reduce unnecessary heating times and heating time, reduce the energy consumption of the heating furnace, improve production efficiency, ensure the quality of forging forming, solve the problems of excessive energy consumption and low production efficiency caused by temperature changes in the forging forming process, and achieve energy efficiency optimization in the forging forming process.

[0188] The efficient scheduling optimization device for forming and manufacturing large-scale aerospace components under time-varying temperature constraints in the embodiments of the present application can be an electronic device or a component of an electronic device, such as an integrated circuit or chip. The electronic device can be a terminal or other device other than a terminal. For example, the electronic device can be a tablet computer, a laptop computer, a PDA, an ultra-mobile personal computer (UMPC), a netbook, or a personal digital assistant (PDA), etc., and the embodiments of the present application do not specifically limit this.

[0189] The efficient scheduling optimization device for forming and manufacturing large-scale aerospace components under time-varying temperature constraints in the embodiments of the present application can be a device having an operating system. The operating system can be a Linux operating system, a Windows operating system, or other possible operating systems, which are not specifically limited in the embodiments of the present application.

[0190] The efficient scheduling optimization device under the time-varying temperature constraints of the forming and manufacturing of large aerospace components provided in the embodiment of the present application can realize the various processes implemented in the scheduling optimization method embodiment under the time-varying temperature constraints of the forming and manufacturing of large aerospace components in the above-mentioned embodiment. To avoid repetition, they will not be repeated here.

[0191] In some embodiments, as Figure 6 As shown, an embodiment of the present application also provides an electronic device 600, including a processor 601, a memory 602, and a computer program stored in the memory 602 and executable on the processor 601. When the program is executed by the processor 601, each process of the above-mentioned scheduling optimization method embodiment under the time-varying temperature constraint of the forming and manufacturing of large aerospace components is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0192] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0193] An embodiment of the present application also provides a non-transitory computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the various processes of the above-mentioned scheduling optimization method embodiment under the time-varying temperature constraint of the forming and manufacturing of large aerospace components, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0194] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0195] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components.

[0196] The processor is the processor in the electronic device in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory ROM, a random access memory RAM, a magnetic disk or an optical disk.

[0197] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, which are coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above-mentioned scheduling optimization method embodiment under the time-varying temperature constraints of the forming and manufacturing of large aerospace components, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0198] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0199] It should be noted that, in this article, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, it should be noted that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in the opposite order according to the functions involved. For example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0200] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, or network equipment, etc.) to execute the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components in each embodiment of the present application.

[0201] In the description of this application, "first feature" and "second feature" may include one or more such features.

[0202] In the description of this application, “plurality” means two or more.

[0203] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of this application, ordinary technicians in this field can also make many forms without departing from the purpose of this application and the scope of protection of the claims, all of which are within the protection of this application.

[0204] Throughout this specification, reference to terms such as "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0205] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.

Claims

1. A scheduling optimization method for forming and manufacturing large-scale aerospace components under time-varying temperature constraints, characterized by: include: Acquiring production data of forgings, wherein the production equipment of the forgings includes a heating furnace and a forging press; determining, based on the production data, an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace state of the heating furnace, a forging press state of the forging press, and a number of queued workpieces; Inputting the input vector into a scheduling optimization model to obtain an optimal scheduling strategy output by the scheduling optimization model for scheduling the production equipment and determining the subsequent processing steps of the forgings, wherein the scheduling optimization model is constructed based on a neural network model; After inputting the input vector into the scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model, the method further includes: Calculating a reward value for the optimal scheduling strategy through a reward function; Optimizing parameters of the scheduling optimization model using the reward value; The reward function The overall energy consumption model is constructed based on the temperature time-varying constraint and is used to describe the energy consumption of the forging during the processing, and is expressed as: ； in, is the heating process reward function, is the furnace temperature fluctuation reward function, is the forging process reward function, is the heat loss reward function of the forging process, is the heat exchange reward function of the forging exposed to air, is the specific heat capacity of the forging material, is the quality of the forging, is the target temperature after the forging is heated, is the initial temperature of the forging, is the fixed energy consumption of the heating furnace, which is proportional to the heating time. It is the lowest temperature for forging. It is the highest temperature for forging. is the temperature of the forging, is the heat dissipation between the forging and the die or hammer, is the heat exchange between the forging and the environment, α, β, γ, δ, and λ are the penalty coefficients of the reward function considering the energy consumption at each stage, and A time-varying constraint for defining the temperature of the forging.

2. The scheduling optimization method for forming and manufacturing large-scale aerospace components under time-varying temperature constraints according to claim 1 is characterized in that: The neural network model includes an estimation network and a target network. The estimation network is used to output the optimal scheduling strategy according to the input vector, and the target network is used to train the estimation network.

3. The scheduling optimization method for forming and manufacturing large-scale aerospace components under time-varying temperature constraints according to claim 2 is characterized in that: The estimation network includes an input layer, a first hidden layer, a second hidden layer, and an output layer connected in sequence; inputting the input vector into the scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model includes: receiving the input vector through the input layer and passing it to the first hidden layer; Performing feature extraction on the input vector through the first hidden layer to obtain a high-dimensional feature vector; compressing the high-dimensional feature vector through the second hidden layer to obtain a compressed feature vector; A plurality of feasible actions corresponding to the compressed feature vector are determined through the output layer, and an action combination with the highest Q value among the plurality of feasible actions is determined as the optimal scheduling strategy.

4. The scheduling optimization method for forming and manufacturing large-scale aerospace components under time-varying temperature constraints according to claim 1 is characterized in that: The step of determining, based on the production data, an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace state of the heating furnace, a forging press state, and a number of queued workpieces, comprises: constructing a forging temperature variation model of the forging based on the temperature data, and obtaining the forging temperature corresponding to the forging temperature variation model; Inputting the temperature data into a forging temperature variation model of the forging to obtain the forging temperature output by the forging temperature variation model; The forging temperature, the heating time, the heating furnace state, the forging press state and the number of queued workpieces output by the forging temperature change model are represented by vectors to obtain the input vector.

5. The scheduling optimization method for forming and manufacturing large-scale aerospace components under time-varying temperature constraints according to claim 1 is characterized in that: The overall energy consumption model is constructed based on the forging temperature change model, and includes a heating energy consumption sub-model in the heating stage, a forging energy consumption sub-model in the forging stage, and a heat dissipation sub-model in the heat dissipation stage.

6. An efficient scheduling optimization device for forming and manufacturing large-scale aerospace components under time-varying temperature constraints, characterized by: include: An acquisition module, configured to acquire production data of forgings, wherein the production equipment of the forgings includes a heating furnace and a forging press; a first processing module for determining, based on the production data, an input vector consisting of a forging temperature of the forging, a heating time, a heating furnace state of the heating furnace, a forging press state of the forging press, and a number of queued workpieces; a second processing module, inputting the input vector into a scheduling optimization model to obtain an optimal scheduling strategy output by the scheduling optimization model for scheduling the production equipment and determining the subsequent processing steps of the forgings, wherein the scheduling optimization model is constructed based on a neural network model; After inputting the input vector into the scheduling optimization model to obtain the optimal scheduling strategy output by the scheduling optimization model, the method further includes: Calculating a reward value for the optimal scheduling strategy through a reward function; Optimizing parameters of the scheduling optimization model using the reward value; The reward function The overall energy consumption model is constructed based on the temperature time-varying constraint and is used to describe the energy consumption of the forging during the processing, and is expressed as: ； in, is the heating process reward function, is the furnace temperature fluctuation reward function, is the forging process reward function, is the heat loss reward function of the forging process, is the heat exchange reward function of the forging exposed to air, is the specific heat capacity of the forging material, is the quality of the forging, is the target temperature after the forging is heated, is the initial temperature of the forging, is the fixed energy consumption of the heating furnace, which is proportional to the heating time. It is the lowest temperature for forging. It is the highest temperature for forging. is the temperature of the forging, is the heat dissipation between the forging and the die or hammer, is the heat exchange between the forging and the environment, α, β, γ, δ, and λ are the penalty coefficients of the reward function considering the energy consumption at each stage, and A time-varying constraint for defining the temperature of the forging.

7. 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, it implements the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components as described in any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the scheduling optimization method under the time-varying temperature constraint of the forming and manufacturing of large aerospace components as described in any one of claims 1 to 5 is implemented.

Images