Creep forming flexible intelligent manufacturing system control method and device based on OOPN

Abstract

The invention relates to the technical field of flexible intelligent manufacturing, and provides an OOPN-based creep forming flexible intelligent manufacturing system control method and device, and the method comprises the steps: constructing an OOPN model of a creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and an OOPN technology; collecting production state data in the operation process of the creep forming flexible intelligent manufacturing system; importing the production state data into the OOPN model to obtain a current control scheme, and updating the creep forming process decision and the OOPN model according to the current control scheme by applying the trained process decision model; and the updated OOPN model is applied to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme. And accurate shape manufacturing of the large thin-wall part can be completed, and the situation that in the manufacturing process, due to unforeseen circumstances, a system is deadlocked or runs disorderly is effectively prevented.

Description

Technical Field

[0001] The present application belongs to the field of flexible intelligent manufacturing technology, and in particular, relates to a creep forming flexible intelligent manufacturing system control method and device based on OOPN. Background Art

[0002] As complex thin-walled components are the key load-bearing structures of aerospace transportation equipment, their manufacturing level determines the transportation efficiency and reliability of the equipment.

[0003] Creep aging technology has effectively solved the problems of the existing thin-walled component manufacturing technology, such as the separation of energy field in time and space during the forming process, low manufacturing efficiency, asynchronous and mutually constrained forming process, and difficulty in meeting the requirements of high-performance and precise manufacturing of aerospace equipment structures. However, at present, the creep forming technology of large thin-walled parts mainly uses autoclaves to complete the forming process, which requires high temperature and high pressure processing conditions and a closed processing environment. Therefore, the traditional creep aging forming process has the problems of difficult online monitoring, low visualization, and difficult dynamic adjustment. The creep forming flexible intelligent manufacturing system is a composite energy field-controlled creep aging integrated manufacturing system with time and space integration of form evolution. The intelligent comprehensive management and control system manually / automatically forms production decisions according to the process requirements of the workpiece, production resource constraints and other conditions. At the same time, through the perception, analysis and feedback of the form evolution information of the forming manufacturing process, the intelligent flexible clamping system, the automated three-dimensional optical measurement system, the intelligent dynamic three-dimensional wide-range measurement system, the laser heating system, and the electric pulse auxiliary system are reasonably dispatched and controlled to effectively link the subsystems, improve the system manufacturing efficiency and product quality, and realize the intelligent management and control of the creep aging forming precision manufacturing process of thin-walled parts. Summary of the invention

[0004] The main purpose of the embodiments of the present invention is to provide a creep forming flexible intelligent manufacturing system control method and device based on OOPN, which can complete the precise manufacturing of large thin-walled parts and effectively prevent the system from deadlocking or operating disorders due to unexpected situations such as possible equipment failures, parameter deviations in the actual process, and unqualified thin-walled parts forming quality in the manufacturing process in the prior art.

[0005] In a first aspect, a control method for a creep forming flexible intelligent manufacturing system based on OOPN is provided, the method comprising: constructing an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; collecting production status data during the operation of the creep forming flexible intelligent manufacturing system, the production status data including equipment status data of each production equipment and deformation evolution information data of processed thin-walled parts; importing the production status data into the OOPN model to obtain the current control scheme, and applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; applying the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

[0006] In another possible implementation, the creep forming flexible intelligent manufacturing system includes: an intelligent flexible clamping system, an integrated management and control system, and an automated three-dimensional optical measurement system, an intelligent dynamic three-dimensional wide-range measurement system, a laser heating system, and an electric pulse auxiliary system connected to the integrated management and control system; the thin-walled parts to be processed are placed on the intelligent flexible clamping system, the automated three-dimensional optical measurement system and the laser heating system are installed on the corresponding robot, the intelligent dynamic three-dimensional wide-range measurement system is placed above the thin-walled parts, and the electric pulse auxiliary system is placed on one side of the intelligent flexible clamping system; the intelligent flexible clamping system holds, adsorbs and moves the thin-walled parts to a preset position according to the process requirements and forming goals, the electric pulse auxiliary system provides the thin-walled parts with the temperature required by the process, the intelligent dynamic three-dimensional wide-range measurement system monitors the temperature, stress and strain of the thin-walled parts in real time, and the laser heating system is used to perform temperature compensation operations on temperature-uneven areas. After each process step is completed, the automated three-dimensional optical measurement system scans the surface contour of the thin-walled parts and obtains the forming results, and feeds the forming results back to the integrated management and control system, and adjusts the next process parameters through the integrated management and control system.

[0007] In a possible implementation, an OOPN model of a creep forming flexible intelligent manufacturing system is constructed according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology, including: constructing an OPN model with production equipment as the object according to the operation behavior logic of any production equipment in the creep forming flexible intelligent manufacturing system combined with the OOPN technology, and The production equipment corresponds to The OPN model is expressed as ,in, is the set of all places in the object, is the set of all transitions in the object, The input library of the object is a collection, The output library of the object is collected. is the input mapping function from places to transitions, is the output mapping function from transition to place; according to the OPN model of each production equipment in the creep forming flexible intelligent manufacturing system and the logical relationship between the operation behaviors of each production equipment, the OOPN model of the creep forming flexible intelligent manufacturing system is constructed. The OOPN model of the creep forming flexible intelligent manufacturing system is expressed as , , , ,in, For the The output library in the OPN model With Input locations in the OPN model The door changes between.

[0008] In another possible implementation, the production status data is imported into the OOPN model to obtain the current control scheme, including: analyzing the equipment status data of each production equipment and the shape evolution information data of the processed thin-walled parts, and obtaining the parameter data of each OPN model corresponding to each production equipment in the OOPN model; obtaining the control data of each OPN model based on the parameter data, and combining them to obtain the current control scheme.

[0009] In another possible implementation, before applying the trained process decision model to update the creep forming process decision and OOPN model according to the current control scheme, it includes: obtaining historical data of the creep forming flexible intelligent manufacturing system for thin-walled parts processing and preparation, the historical data including historical process parameter data in the thin-walled parts processing and preparation process and historical forming effect data of the thin-walled parts, the historical process parameter data including production status data; inputting the historical process parameter data into the process decision model based on deep reinforcement learning, and outputting predicted forming effect data after being processed by the process decision model; calculating the error between the predicted forming effect data and the historical forming effect data, and adjusting the process decision model according to the error until the error meets the requirements, thereby obtaining the trained process decision model.

[0010] In another possible implementation, the trained process decision model is used to update the creep forming process decision and the OOPN model according to the current control scheme, including: determining the current process parameter data according to the current control scheme, applying the trained process decision model to process the current process parameter data and outputting an updated creep forming process decision; and feeding back the updated creep forming process decision to the OOPN model to obtain an updated OOPN model.

[0011] In another possible implementation, the production status data includes, but is not limited to: thin-walled part position, stress, strain, temperature, and suction cup pressure.

[0012] In the second aspect, a control device for a creep forming flexible intelligent manufacturing system based on OOPN is provided, and the device includes: a model construction module, which is used to construct an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; a data acquisition module, which is used to collect production status data during the operation of the creep forming flexible intelligent manufacturing system, and the production status data includes equipment status data of each production equipment and shape evolution information data of processed thin-walled parts; a decision adjustment module, which is used to import the production status data into the OOPN model to obtain the current control scheme, and apply the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; a feedback control module, which is used to apply the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

[0013] According to a third aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a creep forming flexible intelligent manufacturing system control method based on OOPN is implemented as provided in the first aspect.

[0014] In a fourth aspect, a non-transitory computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a creep forming flexible intelligent manufacturing system control method based on OOPN is implemented as provided in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in describing the embodiments of the present application are briefly introduced below.

[0016] Figure 1 A flowchart of a creep forming flexible intelligent manufacturing system control method based on OOPN is provided for one embodiment of the present invention; Figure 2 A schematic diagram of the structure of a creep forming flexible intelligent manufacturing system provided by an embodiment of the present invention; Figure 3 A schematic diagram of an OPN model of a comprehensive management and control system in a creep forming flexible intelligent manufacturing system provided in an embodiment of the present invention; Figure 4 A schematic diagram of an OPN model of an intelligent flexible clamping system in a creep forming flexible intelligent manufacturing system provided in an embodiment of the present invention; Figure 5 A schematic diagram of gate transition of an OPN model of an integrated management and control system provided in an embodiment of the present invention; Figure 6 A schematic diagram of the gate transition of the OPN model of the intelligent flexible clamping system provided by an embodiment of the present invention; Figure 7 A schematic diagram of a control method for a creep forming flexible intelligent manufacturing system based on OOPN is provided as an embodiment of the present invention; Figure 8 A structural diagram of a creep forming flexible intelligent manufacturing system control device based on OOPN provided by one embodiment of the present invention; Fig. 9 A schematic diagram of the physical structure of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0017] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar modules or modules with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present invention.

[0018] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, modules and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, modules, components and / or groups thereof. It should be understood that when we refer to a module as being "connected" or "coupled" to another module, it may be directly connected or coupled to the other modules, or there may be intermediate modules. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any modules and all combinations of one or more associated listed items.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the implementation method of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0020] The technical solution of the present application and how to solve the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0021] In the field of control theory and control engineering, Object Oriented Petri Nets (OOPN) represents a technology that combines object-oriented and Petri net modeling. This term is often mentioned in the field of complex system modeling. OOPN maps the target system into objects that collaborate with each other, and uses Petri nets to describe the behavior of each object and the communication relationship between objects. It uses the information hiding mechanism to make the internal implementation details of each object (i.e., Petri subnet) unknown to the outside world, and only provides its calling interface to the outside world. The core goal of this application is to solve the defects and limitations of the current technology. By introducing a creep forming intelligent manufacturing system control method for large thin-walled parts forming equipment based on OOPN (object-oriented Petri nets), it aims to reduce the impact of human intervention on the production process and significantly improve the level of intelligent manufacturing.

[0022] like Figure 1 FIG. 1 is a flow chart of a creep forming flexible intelligent manufacturing system control method based on OOPN provided by an embodiment of the present invention, the method comprising: Step S11, constructing an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology.

[0023] Step S12, collecting production status data during the operation of the creep forming flexible intelligent manufacturing system, the production status data including equipment status data of each production equipment and shape evolution information data of the processed thin-walled parts.

[0024] Step S13, importing the production status data into the OOPN model to obtain the current control scheme, and applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme.

[0025] Step S14, applying the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

[0026] According to the process requirements of the formed thin-walled parts, the embodiment of the present invention collects real-time status data from the creep forming flexible intelligent manufacturing system of large thin-walled parts based on sensors and measurement systems, transmits the data to the constructed OOPN model, obtains the current control scheme of the creep forming flexible intelligent manufacturing system of large thin-walled parts, and converts the current control scheme into relevant control instructions and sends them to each subsystem, so that each subsystem works according to the control instructions, can complete the precise manufacturing of large thin-walled parts, and effectively prevents the occurrence of system deadlock or operation disorder due to unexpected situations in the manufacturing project.

[0027] In the embodiments of the present invention, see Figure 2The creep forming flexible intelligent manufacturing system includes: an intelligent flexible clamping system 1, an integrated control system 6, and an automated three-dimensional optical measurement system 2, an intelligent dynamic three-dimensional wide-area measurement system 3, a laser heating system 4, and an electric pulse auxiliary system 5 connected to the integrated control system 6. The thin-walled workpiece to be processed is placed on the intelligent flexible clamping system 1, the automated three-dimensional optical measurement system 2 and the laser heating system 4 are installed on the corresponding robot, the intelligent dynamic three-dimensional wide-area measurement system 3 is placed above the thin-walled workpiece, and the electric pulse auxiliary system 5 is placed on one side of the intelligent flexible clamping system 1. The automated three-dimensional optical measurement system 2 and the laser heating system 4 are installed on different multifunctional 6-axis robots, and the intelligent dynamic three-dimensional wide-area measurement system 3 is installed at a high place directly above the thin-walled workpiece.

[0028] The intelligent flexible clamping system 1 supports, adsorbs and moves the thin-walled parts to the preset position according to the process requirements and forming targets. The electric pulse auxiliary system 5 provides the temperature required by the process for the thin-walled parts. If a fault alarm signal appears in the system, each subsystem will stop working immediately until the alarm signal is lifted. The intelligent dynamic three-dimensional wide-area measurement system 3 monitors the temperature, stress and strain of thin-walled parts in real time. The laser heating system 4 is used to perform temperature compensation operations on areas with uneven temperature. After each process step is completed, the automated three-dimensional optical measurement system 2 scans the surface contour of the thin-walled part and obtains the forming results, and feeds the forming results back to the integrated control system 6, and adjusts the next process parameters through the integrated control system 6. The integrated control system 6 controls the work of the automated three-dimensional optical measurement system 2, the intelligent dynamic three-dimensional wide-area measurement system 3, the laser heating system 4 and the electric pulse auxiliary system 5 according to the adjusted process parameters to complete the processing and preparation of thin-walled parts.

[0029] In step S11, optionally, firstly, an OPN model with production equipment as the object is constructed according to the operation behavior logic of any production equipment in the creep forming flexible intelligent manufacturing system combined with the OOPN technology, and then the OPN model is constructed according to the operation behavior logic of any production equipment in the creep forming flexible intelligent manufacturing system combined with the OOPN technology. The production equipment corresponds to The OPN model is expressed as ,in, is the set of all places in the object, is the set of all transitions in the object, The input library of the object is a collection, The output library of the object is collected. is the input mapping function from places to transitions, is the output mapping function from transition to place. This application obtains the OPN models corresponding to the integrated control system, intelligent flexible clamping system, automated three-dimensional optical measurement system, laser heating system, electric pulse auxiliary system and intelligent dynamic three-dimensional wide-range measurement system in the creep forming flexible intelligent manufacturing system. The OPN model of the integrated control system and the OPN model of the intelligent flexible clamping system are explained below.

[0030] The OPN model of the integrated management and control system 6 is as follows Figure 3 As shown in Table 1, the meaning of each symbol in the OPN model is shown in Table 1, and the description of the four conditions in the figure is shown in Table 2. P Indicates the library, P The black dot in the figure represents a token. T Indicates change, black T For instantaneous change, hollow T Delay / random transition, that is, to reach the hollow T After the trigger state, it needs to wait for a certain time before it can be triggered or the trigger time is unknown. M It is an input place or an output place, that is, there is an arrow pointing to T of M is the input place, otherwise it is the output place.

[0031] Table 1 Meaning of symbols in the OPN model of the integrated management and control system

[0032] Table 2 Description of conditions in the OPN model of the integrated management and control system

[0033] in ∑T is the cumulative processing time, T task Estimated processing time for this task, T pm Time for next preventive maintenance; i is the processing step number, I Set the total number of processes for this task; m k For the library P k The number of tokens in the .

[0034] The OPN model of the intelligent flexible clamping system 1 is as follows Figure 4 As shown in the figure, the meaning of each symbol in the OPN model is shown in Table 3, and the description of the three conditions in the figure is shown in Table 4.

[0035] Table 3 Meaning of symbols in the OPN model of intelligent flexible clamping system

[0036] Table 4 Description of conditions in the OPN model of the intelligent flexible clamping system

[0037] The OPN models of the automated 3D optical measurement system, laser heating system, electric pulse assisted system, and intelligent dynamic 3D wide-area measurement system are similar and will not be elaborated here.

[0038] After obtaining the OPN model corresponding to each production equipment, the OOPN model of the creep forming flexible intelligent manufacturing system is constructed according to the OPN model of each production equipment in the creep forming flexible intelligent manufacturing system and the logical relationship between the operation behaviors of each production equipment. The OOPN model of the creep forming flexible intelligent manufacturing system is expressed as , , , ,in, For the The output library in the OPN model With Input locations in the OPN model The door changes between.

[0039] Object-oriented Petri nets divide the control system into several modules and encapsulate their internal operating mechanisms. The information transmission between objects is controlled by gate transitions. Messages are sent out through gate transitions and information is received from the entrance to achieve communication connections between different manufacturing units. The system coordinates the activities and sequences of different objects by controlling the activation of gate transitions to solve problems such as conflicts and deadlocks in the system. In the embodiment of the present invention, the gate transitions of the OPN model of the integrated control system 6 are as follows: Figure 5 As shown, the gate transition of the OPN model of the intelligent flexible clamping system 1 Figure 6 As shown, the meanings of the symbols in the figure are shown in Table 5 below.

[0040] Table 5 Meaning of gate transition symbols of OPN model

[0041] Figure 5 and Figure 6 The same G in the two means that they are connected, for example, Figure 5 Output location in Transition through the door to Figure 5 Input place in and input place , and the others are similar and will not be repeated here. Through gate transition, the OPN models of each production equipment are assembled to obtain the OOPN model of the creep forming flexible intelligent manufacturing system. In this way, the OOPN model of the creep forming flexible intelligent manufacturing system is constructed according to the actual behavior logic of the creep forming flexible intelligent manufacturing system. P , T , M , and the connection relationship of gate transitions are represented, and the operation behavior logic of the creep forming flexible intelligent manufacturing system is reflected during the operation of the OOPN model.

[0042] In the embodiment of the present invention, the control process of the creep forming flexible intelligent manufacturing system is shown in FIG. Figure 7 The process decision model is trained according to the historical data of the creep forming flexible intelligent manufacturing system, and the trained process decision model is obtained. The OOPN model of the creep forming flexible intelligent manufacturing system is constructed according to the operation behavior logic of the creep forming flexible intelligent manufacturing system. During the forming and preparation process of large thin-walled parts, the production status data of the creep forming flexible intelligent manufacturing system is collected in real time. The OOPN model obtains the current control scheme based on the real-time collected production status data. The process decision model obtains the updated creep forming process decision according to the current control scheme and feedback updates the OOPN model. The updated OOPN model performs feedback control on the actual large thin-walled creep forming flexible intelligent manufacturing system according to the current control scheme.

[0043] In the embodiment of the present invention, the production status data includes, but is not limited to: thin-walled part position, stress, strain, temperature, and suction cup pressure. P , T , M The data is obtained through analysis of production status data, and a small amount of P The state or the signal that triggers T can be directly determined based on the production state data. The state of part P or the signal that triggers T is obtained by analyzing multiple production equipment state data and thin-walled part shape evolution information data.

[0044] In an embodiment of the present invention, before applying the trained process decision model to update the creep forming process decision and OOPN model according to the current control scheme, the process decision model needs to be trained. Optionally, historical data of the creep forming flexible intelligent manufacturing system for thin-walled parts processing and preparation is obtained, the historical data includes historical process parameter data during the thin-walled parts processing and preparation process and historical forming effect data of the thin-walled parts, and the historical process parameter data includes production status data; the historical process parameter data is input into the process decision model based on deep reinforcement learning, and the predicted forming effect data is output after being processed by the process decision model; the error between the predicted forming effect data and the historical forming effect data is calculated, and the process decision model is adjusted according to the error until the error meets the requirements, and the trained process decision model is obtained.

[0045] It should be noted that the historical data includes the number of work steps and the time, temperature, stress, strain, positive pulse frequency, pulse duty cycle, pulse current, etc. of each work step. The process decision model is composed of a deep reinforcement learning model. The training of the deep reinforcement learning model is the parameters mentioned above, and the output is the forming amount. It can be understood that the input of the training is the process and the output is the forming effect. According to the characteristics of deep reinforcement learning, the trained model will select the process parameters required for each work step in order to obtain the forming amount. In this way, the trained model can select the various parameters mentioned above for the set target forming amount, thereby realizing the process decision model; the process decision model is composed of a deep reinforcement learning model based on the proximal policy optimization (PPO) algorithm. The policy optimization method selects the policy gradient method, and the reward value of each work step is 0.

[0046] In step S13, optionally, the equipment status data of each production equipment and the shape evolution information data of the processed thin-walled parts are first analyzed to obtain the parameter data of each OPN model corresponding to each production equipment in the OOPN model; then the control data of each OPN model is obtained according to the parameter data, and the current control scheme is obtained by combining. Taking the current control scheme of the fault data collected by the intelligent flexible clamping system 1 as an example: the current token is in the library P 16 , that is, the intelligent flexible clamping system 1 is in the i At this time, the creep forming flexible intelligent manufacturing system collects displacement data of a flexible component in the intelligent flexible clamping system 1 and there is a large deviation from the set data, so a fault occurs. T 21 , the intelligent flexible clamping system 1 enters a fault state P 21 At this time, due to P 21 and P16 Both have tokens, so trigger T 22 Start maintenance, enter P 22 Intelligent flexible clamping system maintenance status, at this time P 16 There is no token, so the intelligent flexible clamping system 1 is not in the first i The processing status of the work step can be understood as when the intelligent flexible clamping system 1 fails, the intelligent flexible clamping system 1 is controlled according to the OPN model to immediately stop processing and start repairing the equipment to ensure the safety of on-site personnel and equipment. Triggered after the maintenance is completed T 23 Maintenance completed, token re-entered P 16 , indicating that the intelligent flexible clamping system 1 is restarted and in the i Processing status of the work step.

[0047] It should be noted that the types of historical data used to train the process decision model in the embodiment of the present invention are more than the real-time collected data. For example, historical data includes strain and temperature, but the real-time collected data may have both strain and temperature or may only have temperature data. That is, when training the process decision model, no matter what the real-time collected data is, training can be performed. In this way, this issue has been considered when establishing the process decision model, so that when the process decision model is applied to the real-time collected data in the future, only part of the data can be used.

[0048] In step S13, optionally, current process parameter data is determined according to the current control scheme, the trained process decision model is applied to process the current process parameter data and an updated creep forming process decision is output; the updated creep forming process decision is fed back to the OOPN model to obtain an updated OOPN model.

[0049] It should be noted that feeding back the updated creep forming process decision to the OOPN model actually updates the values ​​of certain parameters in the OOPN, such as the waiting time of the delay transition and the number of process steps. I For example, in the OPN model diagram of the intelligent flexible clamping system, the original creep forming process plan is divided into 2 steps, each step is 5 hours, but according to the updated creep forming process decision, it is 3 steps, each step is 4 hours, then Figure 4 In the OPN model of the intelligent flexible clamping system, [condition 6] I should change from 2 to 3, and T 17 The trigger delay is set from 5h to 4h. Therefore, the OOPN model is feedback controlled according to the control decision.

[0050] After the OOPN model is updated, the updated OOPN model is applied to feedback control the creep forming flexible intelligent manufacturing system according to the current control scheme. In the specific creep forming flexible intelligent manufacturing system, each production equipment adjusts the action and process parameters according to the current control scheme, and issues instructions through the communication protocol to enable each subsystem to cooperate with each other to perform related actions and jointly complete the task of precise manufacturing of large thin-walled parts. This can effectively prevent the system from deadlocking or operating disorder due to unexpected situations in the manufacturing process.

[0051] The embodiment of the present invention uses an intelligent integrated management and control system to automatically form a process recipe based on the shape evolution information of the manufacturing process components obtained through online measurement during the actual operation of the creep forming flexible intelligent manufacturing system for large thin-walled parts, dynamically adjust the actions and process parameters of each subsystem, and issue instructions through a communication protocol to enable each subsystem to cooperate with each other to perform related actions, and jointly complete the task of precise shape manufacturing of large thin-walled parts. An OOPN model that reflects the actual behavior logic of the creep forming flexible intelligent manufacturing system for large thin-walled parts is constructed, combining deep reinforcement learning with OOPN system modeling technology, and innovatively integrating and applying it to the flexible intelligent manufacturing system for thin-walled parts, truly realizing the intelligent control of equipment behavior and process decision-making, and can effectively prevent the system from deadlocking or operating disorder due to unexpected situations in the manufacturing project.

[0052] In summary, the embodiment of the present invention constructs an OOPN model of a creep forming flexible intelligent manufacturing system according to the operating behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; collects production status data during the operation of the creep forming flexible intelligent manufacturing system, including equipment status data of each production equipment and shape evolution information data of processed thin-walled parts; imports the production status data into the OOPN model to obtain the current control scheme, and uses the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; uses the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme, which can complete the shape-precision manufacturing of large thin-walled parts and effectively prevent the occurrence of system deadlock or operation disorder due to unexpected situations in the manufacturing project.

[0053] like Figure 8 The figure shows a structural diagram of a creep forming flexible intelligent manufacturing system control device based on OOPN provided by an embodiment of the present invention, the device comprising: A model building module 801 is used to build an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; The data acquisition module 802 is used to collect the production status data during the operation of the creep forming flexible intelligent manufacturing system, and the production status data includes the equipment status data of each production equipment and the shape evolution information data of the processed thin-walled parts; The decision adjustment module 803 is used to import the production status data into the OOPN model to obtain the current control scheme, and apply the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; The feedback control module 804 is used to apply the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

[0054] The device of the above embodiment is applied to the corresponding method in the above embodiment, and has the beneficial effects of the corresponding method embodiment, which will not be described in detail here.

[0055] Fig. 9 An example of a physical structure diagram of an electronic device is shown in FIG. Fig. 9 As shown, the electronic device may include: a processor (processor) 901, a communication interface (Communications Interface) 902, a memory (memory) 903 and a communication bus 904, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The processor may call the logic instructions in the memory to execute a creep forming flexible intelligent manufacturing system control method based on OOPN, the method comprising: constructing an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; collecting production status data during the operation of the creep forming flexible intelligent manufacturing system, the production status data including the equipment status data of each production equipment and the shape evolution information data of the processed thin-walled parts; importing the production status data into the OOPN model to obtain the current control scheme, and applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; applying the updated OOPN model to feedback control the creep forming flexible intelligent manufacturing system according to the current control scheme.

[0056] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0057] On the other hand, an embodiment of the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by the computer, the computer can execute a creep forming flexible intelligent manufacturing system control method based on OOPN provided by the above-mentioned method embodiments, and the method includes: constructing an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and OOPN technology; collecting production status data during the operation of the creep forming flexible intelligent manufacturing system, the production status data including equipment status data of each production equipment and deformation evolution information data of the processed thin-walled parts; importing the production status data into the OOPN model to obtain the current control scheme, and applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; applying the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

[0058] On the other hand, an embodiment of the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute a creep forming flexible intelligent manufacturing system control method based on OOPN provided in the above-mentioned embodiments, the method comprising: constructing an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; collecting production status data during the operation of the creep forming flexible intelligent manufacturing system, the production status data including equipment status data of each production equipment and deformation evolution information data of the processed thin-walled parts; importing the production status data into the OOPN model to obtain the current control scheme, and applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; applying the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

[0059] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0060] The above is only a partial implementation of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A creep forming flexible intelligent manufacturing system control method based on OOPN, characterized in that: The method comprises: Constructing an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; Collecting production status data during the operation of the creep forming flexible intelligent manufacturing system, wherein the production status data includes equipment status data of each production equipment and shape evolution information data of the processed thin-walled parts; Importing the production status data into the OOPN model to obtain a current control scheme, and applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; The updated OOPN model is applied to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

2. The method according to claim 1, characterized in that The creep forming flexible intelligent manufacturing system includes: an intelligent flexible clamping system, an integrated control system, and an automated three-dimensional optical measurement system, an intelligent dynamic three-dimensional wide-area measurement system, a laser heating system, and an electric pulse auxiliary system connected to the integrated control system; the thin-walled workpiece to be processed is placed on the intelligent flexible clamping system, the automated three-dimensional optical measurement system and the laser heating system are installed on the corresponding robot, the intelligent dynamic three-dimensional wide-area measurement system is placed above the thin-walled workpiece, and the electric pulse auxiliary system is placed on one side of the intelligent flexible clamping system; The intelligent flexible clamping system holds, adsorbs and moves the thin-walled part to a preset position according to the process requirements and molding goals. The electric pulse auxiliary system provides the thin-walled part with the temperature required by the process. The intelligent dynamic three-dimensional wide-range measurement system monitors the temperature, stress and strain of the thin-walled part in real time. The laser heating system is used to perform temperature compensation on areas with uneven temperature. After each step of the process is completed, the automated three-dimensional optical measurement system scans the surface contour of the thin-walled part and obtains the molding results, and feeds back the molding results to the comprehensive management and control system, and adjusts the next process parameters through the comprehensive management and control system.

3. The method according to claim 1, characterized in that The OOPN model of the creep forming flexible intelligent manufacturing system is constructed according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology, including: According to the operation behavior logic of any production equipment in the creep forming flexible intelligent manufacturing system, combined with the OOPN technology, an OPN model with the production equipment as the object is constructed. The production equipment corresponds to The OPN model is expressed as ,in, is the set of all places in the object, is the set of all transitions in the object, The input library of the object is a collection, The output library of the object is collected. is the input mapping function from places to transitions, is the output mapping function from transition to place; According to the OPN model of each production equipment in the creep forming flexible intelligent manufacturing system and the logical relationship between the operation behaviors of each production equipment, the OOPN model of the creep forming flexible intelligent manufacturing system is constructed. The OOPN model of the creep forming flexible intelligent manufacturing system is expressed as: , , , ,in, For the The output library in the OPN model is With The input library in the OPN model The door changes between.

4. The method according to claim 1, characterized in that The step of importing the production status data into the OOPN model to obtain a current control scheme includes: Analyze the equipment status data of each production equipment and the shape evolution information data of the processed thin-walled parts to obtain the parameter data of each OPN model corresponding to each production equipment in the OOPN model; The control data of each OPN model is acquired according to the parameter data, and the current control scheme is obtained by combining them.

5. The method according to claim 1, characterized in that Before applying the trained process decision model according to the current control scheme to update the creep forming process decision and the OOPN model, the method includes: Acquire historical data of thin-walled parts processing and preparation by the creep forming flexible intelligent manufacturing system, wherein the historical data includes historical process parameter data during the thin-walled parts processing and preparation process and historical forming effect data of the thin-walled parts, wherein the historical process parameter data includes production status data; Inputting the historical process parameter data into a process decision model based on deep reinforcement learning, and outputting predicted molding effect data after being processed by the process decision model; The error between the predicted molding effect data and the historical molding effect data is calculated, and the process decision model is adjusted according to the error until the error meets the requirement, thereby obtaining a trained process decision model.

6. The method according to claim 1, characterized in that The applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme includes: Determining current process parameter data according to the current control scheme, applying the trained process decision model to process the current process parameter data and outputting an updated creep forming process decision; The updated creep forming process decision is fed back to the OOPN model to obtain an updated OOPN model.

7. The method according to claim 1, characterized in that The production status data include: thin-walled part position, stress, strain, temperature, and suction cup pressure.

8. A creep forming flexible intelligent manufacturing system control device based on OOPN, characterized in that: The device comprises: A model building module, used to build an OOPN model of the creep forming flexible intelligent manufacturing system according to the operation behavior logic of the creep forming flexible intelligent manufacturing system and the OOPN technology; A data acquisition module is used to collect production status data during the operation of the creep forming flexible intelligent manufacturing system, wherein the production status data includes equipment status data of each production equipment and shape evolution information data of the processed thin-walled parts; A decision adjustment module, used for importing the production status data into the OOPN model to obtain a current control scheme, and applying the trained process decision model to update the creep forming process decision and the OOPN model according to the current control scheme; A feedback control module is used to apply the updated OOPN model to perform feedback control on the creep forming flexible intelligent manufacturing system according to the current control scheme.

9. An electronic 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 program, an OOPN-based creep forming flexible intelligent manufacturing system control method is implemented as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, an OOPN-based creep forming flexible intelligent manufacturing system control method is implemented as described in any one of claims 1 to 7.

Images