Control method and device based on intelligent agent, equipment and medium

Abstract

The invention relates to the technical field of intelligent manufacturing and the technical field of automatic control, and discloses a control method, device and equipment based on an intelligent agent and a medium, and the method comprises the steps: obtaining first collection data of an automobile part die-casting production line and a root cause analysis result of the automobile part die-casting production line; inputting the first acquisition data of the automobile part die-casting production line and the root cause analysis result of the automobile part die-casting production line into the cloud model; generating an initial control strategy of the automobile part die-casting production line and simulation deduction data of the automobile part die-casting production line through the cloud model; receiving actual execution data of the automobile part die-casting production line returned by the reflection agent according to the initial control strategy; and generating a target control strategy of the automobile part die-casting production line based on the deviation model, the simulation deduction data, the actual execution data and the cloud model. The target control strategy obtaining efficiency of the automobile part die-casting production line can be improved.

Description

Technical Field

[0001] This application relates to the fields of intelligent manufacturing technology and automatic control technology, and in particular to a control method, device, equipment and medium based on intelligent agents. Background Technology

[0002] The automotive parts die-casting production line is a comprehensive production system meticulously constructed around the core process of automotive parts die-casting in the field of intelligent manufacturing. The production line is based on highly automated and intelligent die-casting equipment. This equipment can precisely control key parameters such as injection speed, pressure, and temperature, ensuring that the molten alloy rapidly fills the mold cavity under high pressure and high speed, forming automotive parts that meet design requirements.

[0003] However, the process of acquiring target control strategies for existing automotive parts die-casting production lines is cumbersome, which hinders the improvement of acquisition efficiency. This is because current technologies primarily employ manual acquisition methods to obtain target control strategies for automotive parts die-casting production lines. Manual acquisition consumes significant human and time resources, increasing the acquisition time and making it susceptible to human intervention. Therefore, it is detrimental to improving the efficiency of target control strategy acquisition. Summary of the Invention

[0004] This application provides a control method, device, equipment, and medium based on intelligent agents to solve the technical problem that the acquisition process of the target control strategy in the existing automotive parts die-casting production line is cumbersome and not conducive to improving the efficiency of target control strategy acquisition.

[0005] In a first aspect, embodiments of this application provide a control method based on an intelligent agent, applied to a cloud device, the control method comprising: Acquire the initial data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line; The first data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line are input into the cloud model; The initial control strategy and simulation data of the automotive parts die-casting production line are generated through cloud-based models. Receive actual execution data of the automotive parts die-casting production line returned by the reflective agent based on the initial control strategy; Based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, a target control strategy for the automotive parts die-casting production line is generated.

[0006] In one possible implementation of the first aspect, acquiring the first collected data and the root cause analysis results of the automotive parts die-casting production line includes: The system acquires images of automotive parts, identifies these images, and when a defect is found in an automotive part, it acquires the first acquisition command from the automotive parts die-casting production line. The first acquisition command and analysis command are then sent to the reflective agent within the edge device, which is deployed next to the control equipment of the automotive parts die-casting production line. Receive the first collection data of the automotive parts die-casting production line uploaded by the reflective agent according to the first collection instruction, and receive the root cause analysis results of the automotive parts die-casting production line uploaded by the reflective agent according to the analysis instruction.

[0007] In one possible implementation of the first aspect, the receiving of actual execution data of the automotive parts die-casting production line returned by the reflective agent according to the initial control strategy includes: The initial control strategy is sent to the reflective agent; Receive the actual execution data of the automotive parts die-casting production line returned by the reflective agent based on the initial control strategy.

[0008] In one possible implementation of the first aspect, the generation of the target control strategy for the automotive parts die-casting production line based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods includes: Based on the deviation model, simulation data of the automotive parts die-casting production line, and actual execution data of the automotive parts die-casting production line, the deviation coefficient of the cloud model is generated. The model parameters of the cloud model are adjusted by reducing the deviation coefficient until the deviation coefficient is less than the preset value. Then the adjustment of the model parameters of the cloud model is stopped, and the adjusted cloud model is generated. The system obtains the second acquisition instruction from the automotive parts die-casting production line, sends the second acquisition instruction to the reflective agent, receives the second acquisition data of the automotive parts die-casting production line uploaded by the reflective agent according to the second acquisition instruction, inputs the second acquisition data into the adjusted cloud model, and generates the target control strategy for the automotive parts die-casting production line through the adjusted cloud model.

[0009] In one possible implementation of the first aspect, the deviation model is defined as follows: ; The deviation coefficient of the cloud model represents the performance of the cloud model. The larger the deviation coefficient, the worse the cloud model's ability to extrapolate the die casting process and porosity. The smaller the deviation coefficient, the stronger the cloud model's ability to extrapolate the die casting process and porosity. A continuous curve representing the changes in the die-casting process in the actual execution data; A continuous curve representing the changes in the die-casting process in the simulation data; This indicates the porosity of automotive parts in the actual execution data; This represents the porosity of automotive parts in the simulation data.

[0010] In one possible implementation of the first aspect, the first data collected by the automotive parts die-casting production line includes the process parameters, operating parameters, and finished product quality inspection data of the automotive parts die-casting production line at the first moment. The second data collection for the automotive parts die-casting production line includes the process parameters, operating parameters, and finished product quality inspection data of the automotive parts die-casting production line at the second moment. The root cause analysis results of the automotive parts die-casting production line are the analysis results of the causes of quality defects that occur in the production process of the automotive parts die-casting production line.

[0011] In one possible implementation of the first aspect, the automotive parts die-casting production line includes a die-casting production line for automotive engine blocks and a die-casting production line for transmission housings.

[0012] Secondly, embodiments of this application provide a control device based on an intelligent agent, applied to a cloud device, comprising: The acquisition module is used to acquire the first data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line. The input module is used to input the first collected data and the root cause analysis results of the automotive parts die-casting production line into the cloud model; The generation module is used to generate the initial control strategy and simulation data of the automotive parts die-casting production line through cloud models. The receiving module is used to receive the actual execution data of the automotive parts die-casting production line returned by the reflective agent according to the initial control strategy; The generation module is used to generate target control strategies for automotive parts die-casting production lines based on deviation models, simulation data, actual execution data, cloud models, and predefined generation methods.

[0013] Thirdly, embodiments of this application provide a cloud device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the control method described in the first aspect above.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the control method described in the first aspect.

[0015] Fifthly, embodiments of this application provide a computer program product that, when run on a cloud device, causes the cloud device to execute the control method described in the first aspect.

[0016] The beneficial effects of the embodiments of this application are as follows: Firstly, based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, the target control strategy for the automotive parts die-casting production line is generated. Since no manual acquisition is required, the acquisition time of the target control strategy for the automotive parts die-casting production line is reduced, which is conducive to improving the acquisition efficiency of the target control strategy for the automotive parts die-casting production line. Secondly, since the adjusted cloud model is not affected by human intervention, it helps to improve the reliability of the target control strategy for automotive parts die-casting production lines. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a diagram illustrating an application scenario of the control method provided in the embodiments of this application. Figure 2 This is a flowchart illustrating the control method provided in an embodiment of this application; Figure 3 A flowchart illustrating the implementation of S205 provided in this application embodiment; Figure 4 A schematic block diagram of a control device provided in an embodiment of this application; Figure 5 A schematic diagram of the structure of the cloud device provided in the embodiments of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0020] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0021] It should be understood that in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0022] Furthermore, the technical solutions of the various embodiments can be combined with each other, but only if they are based on the ability of those skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0023] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0024] The control method provided in this application can be applied to cloud devices, including but not limited to cloud servers. The application does not impose any restrictions on the specific type of cloud device.

[0025] Please see Figure 1 , Figure 1 The application scenario diagram of the control method provided in the embodiments of this application is described in detail below: The cloud device connects to the edge device. The cloud device acquires images of automotive parts and identifies the images of automotive parts. When there is a defect in the automotive parts, it acquires the first acquisition command of the automotive parts die-casting production line and sends the first acquisition command and analysis command to the reflective agent in the edge device. The edge device is deployed next to the control equipment of the automotive parts die-casting production line. The cloud device receives the first collection data of the automotive parts die-casting production line uploaded by the reflective agent according to the first collection instruction, and receives the root cause analysis results of the automotive parts die-casting production line uploaded by the reflective agent according to the analysis instruction.

[0026] Among them, the reflective agent is an intelligent unit deployed on edge devices, possessing the ability to execute tasks and autonomously reflect and optimize. The reflective agent compares the actual production results with the preset quality and process targets, analyzes the root causes of defects, and obtains root cause analysis results.

[0027] While cloud devices possess powerful computing and storage capabilities, data transmission to and from the cloud incurs latency. Edge devices, located closer to the data source, allow reflective agents to quickly perform preliminary data processing and analysis locally, uploading only critical information to the cloud. This reduces unnecessary data transmission, significantly improving overall data processing speed and meeting the demands of scenarios with high real-time requirements.

[0028] In this embodiment, the cloud device connects to the edge device, and with the help of the reflective agent within the edge device, it can obtain the first collection data and the root cause analysis results of the automotive parts die-casting production line.

[0029] Retrieve the original list components of the Enterprise Resource Planning (ERP) system from different files.

[0030] Please see Figure 2 , Figure 2 This is a flowchart illustrating the control method provided in an embodiment of this application, which can be applied to cloud devices.

[0031] like Figure 2 As shown, the control method provided in this application includes the following steps, which are detailed below: S201, Obtain the first data collection and root cause analysis results of the automotive parts die-casting production line; The first data collected from the automotive parts die-casting production line includes the process parameters, operating parameters, and finished product quality inspection data of the automotive parts die-casting production line at the first moment. Among them, the root cause analysis results of the automotive parts die-casting production line are the analysis results of the causes of quality defects that occur in the production process of the automotive parts die-casting production line.

[0032] Among them, process parameters directly reflect the execution of the core processes in the die-casting process and are key to ensuring the quality of castings.

[0033] Process parameters include injection stage parameters, temperature parameters, and time parameters.

[0034] Injection stage parameters: injection speed, injection specific pressure, and pressurization trigger timing at each stage; Temperature parameters: real-time temperature of mold cavity, pouring temperature of molten alloy, and inlet and outlet temperatures of cooling water. Time-related parameters: pressure holding time, mold opening and closing time, and time for spraying release agent.

[0035] Operating parameters reflect the operating status of die-casting equipment and production line auxiliary systems, and are used to determine whether the die-casting equipment is in a stable operating range.

[0036] Operating parameters include equipment operating parameters, auxiliary system parameters, and environmental parameters.

[0037] Equipment operating parameters: die-casting machine clamping force, hydraulic system oil pressure, motor operating power; Auxiliary system parameters: release agent spraying pressure, material cylinder liquid level height, robot part picking positioning accuracy; Environmental parameters: real-time temperature, humidity, and compressed air pressure in the workshop.

[0038] Finished product quality inspection data is rapid inspection data completed immediately after the automotive parts are removed, used to determine whether the part is qualified.

[0039] Finished product quality inspection data includes: Visual inspection data: The results of determining whether there are defects such as pores, cold shuts, cracks, and burrs on the surface of automotive parts; Rapid dimensional inspection data: measured values ​​of key dimensions such as flatness of critical mounting surfaces of automotive parts and diameter of bearing holes; Basic performance related data: Real-time temperature of automotive parts after demolding.

[0040] S202, input the first collected data and the root cause analysis results of the automotive parts die-casting production line into the cloud model; Among them, the cloud model is a large language model that runs on cloud devices.

[0041] S203 generates the initial control strategy and simulation data of the automotive parts die-casting production line through cloud model; Among them, the simulation data of the automotive parts die-casting production line is a structured dataset output after virtual simulation calculation of the entire automotive parts die-casting process. It is used to predict process defects, optimize parameter combinations, verify production line cycle time, and support solution iteration and risk avoidance before actual production.

[0042] S204, Receive the actual execution data of the automotive parts die-casting production line returned by the reflective agent according to the initial control strategy; The actual execution data of the automotive parts die-casting production line returned by the receiving reflective agent according to the initial control strategy includes: The initial control strategy is sent to the reflective agent; Receive the actual execution data of the automotive parts die-casting production line returned by the reflective agent based on the initial control strategy.

[0043] S205 generates target control strategies for automotive parts die-casting production lines based on deviation models, simulation data, actual execution data, cloud models, and predefined generation methods.

[0044] The target control strategy for the automotive parts die-casting production line, based on deviation models, simulation data, actual execution data, cloud models, and predefined generation methods, includes: Based on the deviation model, simulation data of the automotive parts die-casting production line, and actual execution data of the automotive parts die-casting production line, the deviation coefficient of the cloud model is generated. The model parameters of the cloud model are adjusted by reducing the deviation coefficient until the deviation coefficient is less than the preset value. Then the adjustment of the model parameters of the cloud model is stopped, and the adjusted cloud model is generated. The system obtains the second acquisition instruction from the automotive parts die-casting production line, sends the second acquisition instruction to the reflective agent, receives the second acquisition data of the automotive parts die-casting production line uploaded by the reflective agent according to the second acquisition instruction, inputs the second acquisition data into the adjusted cloud model, and generates the target control strategy for the automotive parts die-casting production line through the adjusted cloud model.

[0045] Adjust the model parameters of the cloud model by reducing the deviation coefficient until the deviation coefficient is less than the preset value, then stop adjusting the model parameters of the cloud model and generate the adjusted cloud model, including: The mechanism knowledge and time-series operation data of die casting production are collected. An initial causal relationship framework is built through the mechanism knowledge. The time-series operation data is input into the initial causal relationship framework. Through verification and completion processing, a causal graph is obtained. The deviation coefficient, the current parameters of the cloud model, and the causal graph are input into the causal inference model to obtain the causal link. The deviation coefficient is reduced through the causal link, and the model parameters of the cloud model are adjusted until the deviation coefficient is less than the preset value. The adjustment of the model parameters of the cloud model is stopped, and the adjusted cloud model is generated.

[0046] The second data collection for the automotive parts die-casting production line includes process parameters, operating condition parameters, and finished product quality inspection data at a second specific time point. The first and second time points are different times.

[0047] The deviation model is defined as follows: ; The deviation coefficient of the cloud model represents the performance of the cloud model. The larger the deviation coefficient, the worse the cloud model's ability to extrapolate the die casting process and porosity. The smaller the deviation coefficient, the stronger the cloud model's ability to extrapolate the die casting process and porosity. A continuous curve representing the changes in the die-casting process in the actual execution data; A continuous curve representing the changes in the die-casting process in the simulation data; This indicates the porosity of automotive parts in the actual execution data; This represents the porosity of automotive parts in the simulation data.

[0048] Among them, the automotive parts die casting production line includes the die casting production line for automotive engine cylinder blocks and the die casting production line for transmission housings.

[0049] For ease of explanation, let's take a die-casting production line for an automobile engine block as an example, as follows: As a core component of the engine, the engine block requires extremely high dimensional accuracy and quality stability. Traditional production relies on manual experience to adjust parameters, resulting in significant fluctuations in wall thickness and bore diameter accuracy between different batches. This not only increases the assembly difficulty for OEMs but also raises rework rates and costs in the quality inspection process. After the adjusted cloud-based model generates a target control strategy for the die-casting production line of automotive engine blocks, standardized process parameter control ranges and deviation correction rules can be established. This eliminates the randomness introduced by manual operation and ensures that the dimensional accuracy and mechanical properties of each batch of engine blocks remain stable.

[0050] For ease of explanation, let's take the die-casting production line for gearbox housings as an example, as follows: The coaxiality of bearing bores and the flatness of mounting surfaces in the gearbox housing directly affect gear meshing accuracy and transmission efficiency. Traditional production relies on manual experience to adjust mold clamping force and release agent dosage, resulting in significant dimensional fluctuations between different batches. This not only increases the rework rate at the OEM assembly plant but can also lead to problems such as abnormal gearbox noise and shortened lifespan. After the adjusted cloud-based model generates a target control strategy for the gearbox housing die-casting production line, standardized process parameter control ranges and deviation correction rules can be established. This allows for precise control of key factors such as mold temperature, clamping force, and cooling time, eliminating the randomness of manual operation. After implementation, the dimensions and positional accuracy of housings across batches remain highly consistent, significantly improving assembly compatibility with gears, bearings, and other components, and reducing OEM assembly costs and after-sales failure rates.

[0051] The beneficial effects of the embodiments of this application are as follows: Firstly, based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, the target control strategy for the automotive parts die-casting production line is generated. Since no manual acquisition is required, the acquisition time of the target control strategy for the automotive parts die-casting production line is reduced, which is conducive to improving the acquisition efficiency of the target control strategy for the automotive parts die-casting production line. Secondly, since the adjusted cloud model is not affected by human intervention, it helps to improve the reliability of the target control strategy for automotive parts die-casting production lines.

[0052] Please see Figure 3 , Figure 3 The implementation flowchart of S205 provided in the embodiments of this application is described in detail below: S301 generates the deviation coefficient of the cloud model based on the deviation model, simulation data of the automotive parts die-casting production line, and actual execution data of the automotive parts die-casting production line. S302, adjust the model parameters of the cloud model by reducing the deviation coefficient until the deviation coefficient is less than the preset value, stop adjusting the model parameters of the cloud model, and generate the adjusted cloud model; S303: Obtain the second acquisition instruction of the automotive parts die-casting production line, send the second acquisition instruction to the reflective agent, receive the second acquisition data of the automotive parts die-casting production line uploaded by the reflective agent according to the second acquisition instruction, input the second acquisition data into the adjusted cloud model, and generate the target control strategy of the automotive parts die-casting production line through the adjusted cloud model.

[0053] In this embodiment of the application, the target control strategy for the automotive parts die-casting production line is generated by the adjusted cloud model, which helps to improve the stability of the target control strategy for the automotive parts die-casting production line.

[0054] For the control method described in the above embodiments, please refer to [link / reference]. Figure 4 , Figure 4 This is a schematic block diagram of the control device provided in the embodiments of this application. Figure 4 The control device 400 shown can be applied to, for example Figure 1 The application scenario diagram shows cloud devices. The following section uses cloud devices as an example to illustrate this. Figure 4 The control device 400 shown will be described in detail. The control device 400 may include an acquisition module 401, an input module 402, a generation module 403, a receiving module 404, and a generation module 405.

[0055] The acquisition module 401 is used to acquire the first collected data and the root cause analysis results of the automotive parts die-casting production line. Input module 402 is used to input the first collected data and the root cause analysis results of the automotive parts die casting production line into the cloud model; The generation module 403 is used to generate the initial control strategy and simulation data of the automotive parts die-casting production line through the cloud model. Receiver module 404 is used to receive the actual execution data of the automotive parts die-casting production line returned by the reflective agent according to the initial control strategy; The generation module 405 is used to generate target control strategies for automotive parts die-casting production lines based on deviation models, simulation data, actual execution data, cloud models, and predefined generation methods.

[0056] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0057] The beneficial effects of the embodiments of this application are as follows: Firstly, based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, the target control strategy for the automotive parts die-casting production line is generated. Since no manual acquisition is required, the acquisition time of the target control strategy for the automotive parts die-casting production line is reduced, which is conducive to improving the acquisition efficiency of the target control strategy for the automotive parts die-casting production line. Secondly, since the adjusted cloud model is not affected by human intervention, it helps to improve the reliability of the target control strategy for automotive parts die-casting production lines.

[0058] Please see Figure 5 , Figure 5 A schematic diagram of the structure of the cloud device provided in the embodiments of this application.

[0059] like Figure 5 As shown, Figure 5 The cloud device 2 includes: at least one processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the at least one processor 20, wherein the processor 20 executes the computer program 22 to implement the steps in any of the above method embodiments.

[0060] The cloud device 2 may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will understand that... Figure 5 This is merely an example of cloud device 2 and does not constitute a limitation on cloud device 2. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0061] The processor 20 is used to run a computer program 22 stored in the memory 21, and performs the following steps when executing the computer program 22: Acquire the initial data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line; The first data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line are input into the cloud model; The initial control strategy and simulation data of the automotive parts die-casting production line are generated through cloud-based models. Receive actual execution data of the automotive parts die-casting production line returned by the reflective agent based on the initial control strategy; Based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, a target control strategy for the automotive parts die-casting production line is generated.

[0062] The processor 20 may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors, field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0063] In some embodiments, the memory 21 may be an internal storage unit of the cloud device 2, such as a hard drive or memory of the cloud device 2. In other embodiments, the memory 21 may also be an external storage device of the cloud device 2, such as a plug-in hard drive, SmartMediaCard (SMC), SecureDigital (SD) card, or FlashCard equipped on the cloud device 2.

[0064] Furthermore, the memory 21 may include both internal storage units of the cloud device 2 and external storage devices. The memory 21 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 21 can also be used to temporarily store data that has been output or will be output.

[0065] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0066] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0067] The computer-readable storage medium may also be an external storage device of the control device or cloud device, such as a plug-in hard drive, smart media card (SMC), secure digital (SD) card, flash card, or non-transitory computer-readable storage medium equipped on the control device or cloud device.

[0068] Since the computer program stored in the computer-readable storage medium can execute any of the agent-based control methods provided in the embodiments of this application, the computer-readable storage medium can achieve the beneficial effects that any of the agent-based control methods provided in the embodiments of this application can achieve, as detailed in the preceding embodiments, and will not be repeated here.

[0069] This application provides a computer program product that, when run on a cloud device, causes the cloud device to execute the aforementioned control method.

[0070] Once a computer program product is loaded onto a cloud device, the following steps can be performed: Acquire the initial data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line; The first data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line are input into the cloud model; The initial control strategy and simulation data of the automotive parts die-casting production line are generated through cloud-based models. Receive actual execution data of the automotive parts die-casting production line returned by the reflective agent based on the initial control strategy; Based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, a target control strategy for the automotive parts die-casting production line is generated.

[0071] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0072] Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium includes: an entity or device for carrying computer program code to a cloud device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium.

[0073] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0074] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A control method based on an intelligent agent, characterized in that, The control method, applied to cloud devices, includes: Acquire the initial data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line; The first data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line are input into the cloud model; The initial control strategy and simulation data of the automotive parts die-casting production line are generated through cloud-based models. Receive actual execution data of the automotive parts die-casting production line returned by the reflective agent based on the initial control strategy; Based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, a target control strategy for the automotive parts die-casting production line is generated.

2. The control method according to claim 1, characterized in that, The acquisition of the first data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line include: The system acquires images of automotive parts, identifies these images, and when a defect is found in an automotive part, it acquires the first acquisition command from the automotive parts die-casting production line. The first acquisition command and analysis command are then sent to the reflective agent within the edge device, which is deployed next to the control equipment of the automotive parts die-casting production line. Receive the first collection data of the automotive parts die-casting production line uploaded by the reflective agent according to the first collection instruction, and receive the root cause analysis results of the automotive parts die-casting production line uploaded by the reflective agent according to the analysis instruction.

3. The control method according to claim 1, characterized in that, The receiving reflective agent returns the actual execution data of the automotive parts die-casting production line according to the initial control strategy, including: The initial control strategy is sent to the reflective agent; Receive the actual execution data of the automotive parts die-casting production line returned by the reflective agent based on the initial control strategy.

4. The control method according to claim 1, characterized in that, The target control strategy for the automotive parts die-casting production line is generated based on the deviation model, simulation data, actual execution data, cloud model, and predefined generation methods, including: Based on the deviation model, simulation data of the automotive parts die-casting production line, and actual execution data of the automotive parts die-casting production line, the deviation coefficient of the cloud model is generated. The model parameters of the cloud model are adjusted by reducing the deviation coefficient until the deviation coefficient is less than the preset value. Then the adjustment of the model parameters of the cloud model is stopped, and the adjusted cloud model is generated. The system obtains the second acquisition instruction from the automotive parts die-casting production line, sends the second acquisition instruction to the reflective agent, receives the second acquisition data of the automotive parts die-casting production line uploaded by the reflective agent according to the second acquisition instruction, inputs the second acquisition data into the adjusted cloud model, and generates the target control strategy for the automotive parts die-casting production line through the adjusted cloud model.

5. The control method according to claim 1, characterized in that, The deviation model is defined as follows: ； The deviation coefficient of the cloud model represents the performance of the cloud model. The larger the deviation coefficient, the worse the cloud model's ability to extrapolate the die casting process and porosity. The smaller the deviation coefficient, the stronger the cloud model's ability to extrapolate the die casting process and porosity. A continuous curve representing the changes in the die-casting process in the actual execution data; A continuous curve representing the changes in the die-casting process in the simulation data; This indicates the porosity of automotive parts in the actual execution data; This represents the porosity of automotive parts in the simulation data.

6. The control method according to claim 1, characterized in that, The first data collected from the automotive parts die-casting production line includes the process parameters, operating parameters, and finished product quality inspection data of the automotive parts die-casting production line at the first moment. The second data collection for the automotive parts die-casting production line includes the process parameters, operating parameters, and finished product quality inspection data of the automotive parts die-casting production line at the second moment. The root cause analysis results of the automotive parts die-casting production line are the analysis results of the causes of quality defects that occur in the production process of the automotive parts die-casting production line.

7. The control method according to claim 1, characterized in that, Automotive parts die casting production lines include die casting production lines for automotive engine blocks and die casting production lines for transmission housings.

8. A control device based on an intelligent agent, characterized in that, Applied to cloud devices, including: The acquisition module is used to acquire the first data collected from the automotive parts die-casting production line and the root cause analysis results of the automotive parts die-casting production line. The input module is used to input the first collected data and the root cause analysis results of the automotive parts die-casting production line into the cloud model; The generation module is used to generate the initial control strategy and simulation data of the automotive parts die-casting production line through cloud models. The receiving module is used to receive the actual execution data of the automotive parts die-casting production line returned by the reflective agent according to the initial control strategy; The generation module is used to generate target control strategies for automotive parts die-casting production lines based on deviation models, simulation data, actual execution data, cloud models, and predefined generation methods.

9. A cloud device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the control method as described in any one of claims 1 to 7.

Images