Intelligent operation and maintenance method and system for extrusion processing workshop based on digital twinning

Abstract

The invention relates to the technical field of intelligent manufacturing, in particular to an extrusion processing workshop intelligent operation and maintenance method and system based on digital twinning, and the method comprises the following steps: importing a production plan through a digital twinning system, generating a processing task list, and synchronizing a virtual model; the specification of the billet is obtained by using RFID, and a tracking code is generated and a task is bound. And matching process parameters, regulating and controlling the temperature of the heating machine, collecting temperature data and generating a compensation instruction. Based on the compensation instruction, planning a manipulator path, monitoring a pose correction deviation, and feeding the billet into an extruder; calling a pressure curve, collecting a pressure value, and generating an adjusting instruction by combining material simulation to realize constant strain rate extrusion; according to the pressure feedback, the wire collecting tension is adjusted, the wire diameter fluctuation is monitored, and a speed compensation instruction is generated; generating a wire unloading path according to the specification of the wire coil, and controlling the robot to place the wire coil and update a task state; according to the invention, efficient, accurate and intelligent extrusion processing operation and maintenance are realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent manufacturing technology, and in particular to an intelligent operation and maintenance method and system for an extrusion processing workshop based on digital twins. Background Art

[0002] In modern manufacturing, extrusion processing technology is widely used in the field of metal material forming, especially in industries such as aerospace, automobile manufacturing and precision industry. The accuracy, stability and degree of automation of the extrusion forming process directly affect product quality and production efficiency. In recent years, with the development of intelligent manufacturing technology, digital twins, as a new technology that integrates the physical world and the virtual simulation world, provide new solutions for the intelligent operation and maintenance of the manufacturing process.

[0003] However, the existing extrusion processing operation and maintenance system still faces multiple technical bottlenecks. On the one hand, data isolation and the lack of real-time synchronization mechanism make it impossible to efficiently integrate production plans, equipment status, sensor data, etc., affecting the overall production coordination. On the other hand, there is insufficient linkage between processes such as heating, extrusion, wire collection, and wire unloading. In the actual production process, problems such as extrusion pressure fluctuations, wire diameter changes, and robot motion deviations cannot be adjusted in real time, resulting in poor product consistency. Existing intelligent operation and maintenance methods still rely on fixed empirical parameters for precise control and dynamic optimization, and are difficult to adapt to complex processing conditions. Summary of the invention

[0004] The present invention provides an intelligent operation and maintenance method and system for an extrusion processing workshop based on digital twin.

[0005] An intelligent operation and maintenance method for an extrusion processing workshop based on digital twins includes the following steps: S1, production plan analysis: import the production plan through the digital twin system to generate a processing task list including billet specifications and process parameters. The digital twin system includes a virtual model and sensor network synchronized with the physical production line; S2, material tracking: obtaining the specification and quantity information of the brazing billet through RFID scanning, uploading it to the digital twin system to generate a billet tracking code, and binding the billet tracking code to the task item in the processing task list; S3, dynamic preheating: matching preset process parameters according to the billet tracking code, adjusting the temperature and time of the heating machine, collecting billet surface temperature distribution data in real time and generating temperature compensation instructions, wherein the temperature compensation instructions are used to correct the heating parameters to achieve uniform heating of the billet; S4, collaborative transmission: based on the correction result of the temperature compensation instruction, planning the movement path of the manipulator, monitoring the manipulator posture data in real time and comparing it with the preset path in the virtual model, generating a path deviation correction instruction, and controlling the manipulator to feed the billet into the extruder die barrel; S5, Closed-loop extrusion: Call the corresponding pressure parameter curve according to the billet tracking code, collect the pressure value in the die barrel of the extruder in real time, generate a dynamic pressure adjustment instruction by combining the material flow simulation data in the virtual model, and control the extruder to achieve constant strain rate extrusion; S6, Adaptive wire winding: Generate a wire winding tension adjustment instruction according to the extrusion pressure feedback data, synchronously adjust the tension parameter of the wire winder, and collect the wire diameter fluctuation information through a laser rangefinder to generate an extrusion speed compensation instruction and feedback it to the extruder; S7, Intelligent wire unloading: Generate a wire unloading robot grasping path instruction based on the wire coil specification data corresponding to the billet tracking code, control the robot to place the wire coil on the transporter, and update the completion status in the processing task list.

[0006] Optionally, the S1 includes: S11, Production plan parsing: Convert the externally input production plan file into a structured data format, extract the billet material code, target size, and process number fields therein, and generate an original production plan data set; S12, Data validity verification: Perform rule verification on the original production plan data set. The rule verification includes: Verify whether the billet material code exists in the preset material library; Verify whether the target size meets the specification constraints of the extruder die barrel; Verify whether the temperature-pressure parameters corresponding to the process number are complete; If the verification fails, generate an exception identifier and trigger a manual review process. If the verification passes, output the verified production plan data; S13, Virtual model synchronization: According to the billet material code in the verified production plan data, call the thermal expansion coefficient and thermal conductivity parameters in the material library, update the physical properties of the billet entity in the virtual model of the digital twin system, and generate the synchronized virtual model parameters; S14, Sensor network configuration: Based on the process number in the verified production plan data, load the corresponding sensor acquisition strategy, generate sensor configuration parameters and send them to the physical production line. The sensor acquisition strategy includes: Set the sampling frequency (≥10Hz) and temperature range for the infrared thermal imager; Set the threshold alarm range for the pressure sensor; Configure the encoding rule associated with the billet specification for the RFID scanner; S15. Task list generation: Correlate and bind the verified production plan data, synchronized virtual model parameters, and sensor configuration parameters, and generate a processing task list arranged in the production order. Each task item in the processing task list contains fields: blank ingot tracking code (reserved), material code, target size, process parameters, virtual model version number, and sensor configuration ID.

[0007] Optionally, S2 includes: S21. RFID tag parsing: Perform RFID scanning on the filler metal blank ingots, extract the blank ingot specification information, batch number, and storage time in the RFID tag, and generate an original blank ingot data set.

[0008] S22. Blank ingot specification matching: Match the original blank ingot data set with the processing task list to confirm the correspondence between the blank ingot specification and the process parameters; If the match is successful, output the matched blank ingot task data. If the match fails, generate an exception identifier and trigger the exception handling mechanism.

[0009] S23. Blank ingot tracking code generation: Generate a blank ingot tracking code based on the matched blank ingot task data, and establish a tracking index, and output the blank ingot tracking data with the tracking code. S24. Tracking data upload: Upload the blank ingot tracking data to the digital twin system and establish a real-time data mapping relationship.

[0010] S25. Processing task binding: Update the processing task list based on the blank ingot tracking data, and bind the blank ingot tracking code to the task item.

[0011] S26. Task execution status initialization: Generate initial status information for the blank ingots with the tasks bound.

[0012] Optionally, S3 includes: S31. Process parameter matching: Retrieve the corresponding process parameters in the processing task list according to the blank ingot tracking code, and extract the target heating temperature, preheating time, and temperature uniformity requirements; Combine the current status of the equipment to correct the target temperature setting value to ensure that the temperature setting conforms to the current working conditions, and output the matched heating parameter data. S32. Heating equipment setting: Based on the heating parameter data, send a heating temperature setting instruction to the heating machine and initialize the temperature control mode.

[0013] S33. Temperature data acquisition: During the heating process, collect the surface temperature distribution data of the blank ingot in real time and establish a temperature history curve.

[0014] S34, Temperature uniformity analysis: Based on the temperature history curve, calculate the temperature uniformity index of the billet and detect whether it meets the set threshold; If the temperature uniformity index is lower than the set threshold, it is determined that the billet is unevenly heated, and a temperature anomaly identifier is generated.

[0015] S35, Temperature compensation instruction generation: If the temperature anomaly identifier is triggered, calculate the heating parameter correction value and generate a temperature compensation instruction.

[0016] S36, Closed-loop heating control: Based on the temperature compensation instruction, dynamically adjust the operating parameters of the heating machine and continuously monitor the heating effect.

[0017] Optionally, the S4 includes: S41, Manipulator path planning: Based on the adjustment result of the temperature compensation instruction, plan the manipulator movement path in the digital twin system and generate path planning data.

[0018] S42, Path execution instruction generation: Based on the path planning data, send an execution instruction to the manipulator control system and initialize the motion control mode.

[0019] S43, Real-time pose monitoring: During the manipulator's path execution, collect the manipulator pose data in real time and synchronize it with the digital twin system.

[0020] S44, Path deviation calculation: Based on the real-time pose data, compare it with the path planning data, calculate the path deviation, and generate deviation data.

[0021] S45, Path deviation correction: Based on the path deviation data, generate a path deviation correction instruction and dynamically adjust the manipulator movement.

[0022] S46, Target position verification: When the manipulator approaches the extrusion die barrel, detect the target position accuracy and perform the final position correction.

[0023] Optionally, the S5 includes: S51, Pressure parameter curve call: According to the billet tracking code, retrieve the corresponding pressure parameter curve in the processing task list and load it into the extrusion machine control system.

[0024] S52, Pressure data acquisition: During the extrusion process, collect the pressure value inside the extrusion die barrel in real time and establish a pressure monitoring data stream.

[0025] S53, Material flow simulation calculation: Based on the pressure monitoring data stream, perform a material flow simulation in the digital twin system, predict the billet deformation state, and generate material flow simulation data.

[0026] Optionally, S5 further includes: S54, dynamic pressure regulation instruction generation: Calculate the extrusion machine pressure adjustment amount based on the material flow simulation data, and generate a dynamic pressure regulation instruction.

[0027] S55, closed-loop pressure control: Based on the dynamic pressure regulation instruction, adjust the extrusion machine pressure in real time and monitor the adjustment effect.

[0028] S56, extrusion process status update: After extrusion is completed, record the final extrusion status and update the processing task list.

[0029] Optionally, S6 includes: S61, extrusion pressure feedback data acquisition: During the extrusion process, real-time collect the extrusion machine pressure feedback data and upload it to the digital twin system.

[0030] S62, wire take-up tension calculation: Based on the pressure feedback data, calculate the wire take-up tension requirement value and generate an initial wire take-up tension setting value.

[0031] S63, tension regulation instruction generation: Based on the wire take-up tension setting value, generate a wire take-up machine tension regulation instruction and send it to the wire take-up control system.

[0032] S64, wire diameter fluctuation monitoring: During the wire take-up process, use a laser rangefinder to collect wire diameter data and generate diameter fluctuation information.

[0033] S65, extrusion speed compensation instruction generation: Based on the diameter fluctuation information, calculate the extrusion speed adjustment amount and generate an extrusion speed compensation instruction.

[0034] S66, closed-loop tension control: Based on the tension regulation instruction and the extrusion speed compensation instruction, dynamically adjust the operating parameters of the wire take-up machine and the extrusion machine.

[0035] Optionally, S7 includes: S71, wire coil specification data parsing: Based on the billet tracking code, retrieve the corresponding wire coil specification data in the processing task list, parse the wire unloading parameters, and output the parsed wire coil specification data.

[0036] S72, wire unloading robot path planning: Based on the wire coil specification data, plan the grasping path of the wire unloading robot in the digital twin system and generate path planning data.

[0037] S73, grasping path execution instruction generation: Based on the path planning data, send a path execution instruction to the wire unloading robot control system and initialize the grasping control mode.

[0038] S74, Real-time Pose Monitoring: During the path execution of the wire unloading robot, real-time robot pose data is collected to generate a real-time pose data stream.

[0039] S75, Path Deviation Correction: Based on the real-time pose data, compare it with the path planning data, calculate the path deviation, and generate a deviation correction instruction.

[0040] S76, Target Position Verification and Coil Placement: When the wire unloading robot approaches the transfer machine, detect the final placement position of the coil and perform final position correction.

[0041] S77, Update of Processing Task Completion Status: After the wire unloading of the coil is completed, update the completion status in the processing task list and store it in the digital twin system.

[0042] An intelligent operation and maintenance system for an extrusion processing workshop based on digital twin, used to implement the above-mentioned intelligent operation and maintenance method for an extrusion processing workshop based on digital twin, includes the following modules: Digital Twin Module: Used to construct a virtual model synchronized with the physical production line, load blank specifications, process parameters, equipment status, and sensor data to achieve virtual-real synchronization and data fusion; Production Plan Management Module: Used to parse the production plan file, verify the blank specifications and process parameters, generate a processing task list, and synchronize it with the virtual model; Loading Tracking Module: Used to obtain blank specification information through RFID scanning, generate a blank tracking code, and establish a tracking index to associate the processing task with the blank data; Dynamic Preheating Control Module: Used to match preset process parameters according to the blank tracking code, regulate the temperature of the heating machine, collect temperature data in real time, and generate a temperature compensation instruction to ensure uniform heating of the blank; Collaborative Transfer Module: Used to plan the motion path of the manipulator based on the correction result of the temperature compensation instruction, monitor the pose of the manipulator in real time, and generate a path deviation correction instruction to control the manipulator to accurately feed into the extrusion machine die barrel; Closed-loop Extrusion Control Module: Used to call the pressure parameter curve, collect the pressure value in the extrusion machine die barrel in real time, combine with the material flow simulation data, generate a dynamic pressure adjustment instruction to achieve constant strain rate extrusion; Adaptive Wire Winding Module: Used to generate a wire winding tension adjustment instruction based on the extrusion pressure feedback data, adjust the tension parameter of the wire winding machine, and collect the wire diameter fluctuation information to generate an extrusion speed compensation instruction and feedback it to the extrusion machine; Intelligent Wire Unloading Module: Based on the coil specification data corresponding to the blank tracking code, generate a wire unloading robot grasping path instruction, control the robot to place the coil on the transfer machine, and update the completion status in the processing task list.

[0043] Advantages of the present invention: In the present invention, a virtual model synchronized with the physical production line is constructed through a digital twin module, and through the intelligent analysis of the production plan management module, the integration of billet specifications, process parameters, equipment status, and sensor data is achieved. Relying on the dynamic preheating control module and the closed-loop extrusion control module, temperature, pressure, and flow characteristic data are collected in real time during the heating and extrusion stages, and compensation instructions are dynamically generated based on material flow simulation calculations, enabling the temperature field and stress field to be evenly matched to achieve constant strain rate extrusion. At the same time, the adaptive wire winding module automatically adjusts the wire winding tension according to the wire diameter fluctuation information, ensuring the full-process closed-loop optimization of the extrusion-wire winding-unloading process, and improving the processing consistency and product quality.

[0044] In the present invention, through the feeding tracking module, the automatic tracking of the billet from warehousing to extrusion is realized and bound to the processing task list to ensure accurate feeding. The collaborative transfer module uses temperature compensation instructions for robotic arm path planning, and combines real-time pose monitoring and path deviation correction to ensure that the robotic arm accurately docks with the extrusion machine die barrel, reducing manual intervention. The intelligent wire unloading module plans the path of the wire unloading robot based on the wire coil specification data, and uses grasping force feedback control and laser ranging correction to ensure the safe handling of the wire coil and automatically place it on the transfer machine. The unmanned operation of the whole process reduces the human error in the production process and improves the operation efficiency of the workshop. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only those of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0046] Figure 1 is a schematic flow chart of the method according to the embodiment of the present invention; Figure 2 is a schematic flow chart of the system according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The present invention will be described in detail below in conjunction with the drawings and specific embodiments. At the same time, it should be noted here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments. For some well-known technologies, those skilled in the art can also adopt other alternative methods for implementation; and the drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0048] It should be noted that in the specification, the mention of "an embodiment", "embodiments", "exemplary embodiments", "some embodiments", etc. indicates that the described embodiments may include specific features, structures or characteristics, but not necessarily every embodiment includes such specific features, structures or characteristics. Additionally, when combining embodiments to describe specific features, structures or characteristics, implementing such features, structures or characteristics in combination with other embodiments (whether explicitly described or not) should be within the knowledge scope of those skilled in the relevant art.

[0049] Generally, terms can be understood at least in part from their use in context. For example, at least in part depending on the context, the term "one or more" used herein can be used to describe any feature, structure or characteristic in a singular sense, or can be used to describe a combination of features, structures or characteristics in a plural sense. Additionally, the term "based on" can be understood as not necessarily aiming to convey a set of exclusive factors, but rather, at least in part depending on the context, allowing for the existence of other factors that may not be explicitly described.

[0050] As Figure 1 shown, an intelligent operation and maintenance method for an extrusion processing workshop based on digital twin includes the following steps: S1. Production plan parsing: Import the production plan through the digital twin system to generate a processing task list containing billet specifications and process parameters. The digital twin system includes a virtual model synchronized with the physical production line and a sensor network; S2. Loading tracking: Obtain the specifications and quantity information of the solder billets through RFID scanning, upload them to the digital twin system to generate billet tracking codes, and bind the billet tracking codes to the task items in the processing task list; S3. Dynamic preheating: Match the preset process parameters according to the billet tracking code, regulate the temperature and time of the heating machine, and collect the surface temperature distribution data of the billet in real time to generate a temperature compensation instruction, which is used to correct the heating parameters to achieve uniform heating of the billet; S4. Cooperative transfer: Based on the correction result of the temperature compensation instruction, plan the motion path of the manipulator, monitor the pose data of the manipulator in real time and compare it with the preset path in the virtual model to generate a path deviation correction instruction, and control the manipulator to send the billet into the extrusion machine die barrel; S5. Closed-loop extrusion: Call the corresponding pressure parameter curve according to the billet tracking code, collect the pressure value in the extrusion machine die barrel in real time, and generate a dynamic pressure adjustment instruction in combination with the material flow simulation data in the virtual model to control the extrusion machine to achieve constant strain rate extrusion; S6. Adaptive wire winding: Generate a wire winding tension adjustment instruction according to the extrusion pressure feedback data, synchronously adjust the tension parameters of the wire winding machine, and collect the wire diameter fluctuation information through a laser rangefinder to generate an extrusion speed compensation instruction and feedback it to the extrusion machine; S7, Intelligent wire unloading: Based on the wire coil specification data corresponding to the billet tracking code, generate the grasping path instruction for the wire unloading robot, control the robot to place the wire coil on the transfer machine, and update the completion status in the processing task list.

[0051] S1 includes: S11, Production plan parsing: Convert the externally input production plan file into a structured data format, extract the billet material code, target size, and process number fields therein, and generate the original production plan data set; S12, Data validity verification: Perform rule verification on the original production plan data set. The rule verification includes: Verify whether the billet material code exists in the preset material library; Verify whether the target size conforms to the specification constraints of the extrusion machine die barrel; Verify whether the temperature-pressure parameters corresponding to the process number are complete; If the verification fails, generate an exception identifier and trigger the manual review process. If the verification passes, output the verified production plan data; S13, Virtual model synchronization: According to the billet material code in the verified production plan data, call the thermal expansion coefficient and thermal conductivity parameters in the material library, update the physical properties of the billet entity in the virtual model of the digital twin system, and generate the synchronized virtual model parameters; S14, Sensor network configuration: Based on the process number in the verified production plan data, load the corresponding sensor acquisition strategy, generate the sensor configuration parameters and send them to the physical production line. The sensor acquisition strategy includes: Set the sampling frequency (≥10Hz) and temperature range for the infrared thermal imager; Set the threshold alarm range for the pressure sensor; Configure the encoding rule associated with the billet specification for the RFID scanner; S15, Task list generation: Associate and bind the verified production plan data, the synchronized virtual model parameters, and the sensor configuration parameters, and generate the processing task list in the production order. Each task item in the processing task list contains the fields: billet tracking code (reserved), material code, target size, process parameters, virtual model version number, and sensor configuration ID.

[0052] S2 includes: S21, RFID tag parsing: Perform RFID scanning on the solder billet, extract the billet specification information, batch number, and storage time in the RFID tag, and generate the original billet data set, including: Parse the encoding format in the RFID tag and extract the fields matching the production task; Detect the validity of the RFID tag. If the tag information is missing or damaged, trigger the manual verification process; The parsed original ingot dataset contains the following fields: ingot number, material code, target size, batch number, and storage time.

[0053] S22, Ingot specification matching: Match the original ingot dataset with the processing task list to confirm the correspondence between the ingot specifications and process parameters, including: Perform index matching based on the ingot number and the task number in the processing task list to find the target task item; Verify whether the material code of the ingot is consistent with the target material in the processing task list; Verify whether the target size of the ingot is within the dimensional tolerance range in the processing task list; If the matching is successful, output the ingot task data after matching. If the matching fails, generate an exception identifier and trigger the exception handling mechanism.

[0054] S23, Ingot tracking code generation: Based on the matched ingot task data, generate the ingot tracking code, establish a tracking index, and output the ingot tracking data with the tracking code, including: Generate a unique ingot tracking code based on the ingot number, batch number, and processing task number; Create an ingot tracking index in the digital twin system to ensure that the corresponding ingot data can be called through the tracking code in subsequent steps; S24, Tracking data upload: Upload the ingot tracking data to the digital twin system and establish a real-time data mapping relationship, including: Create a corresponding virtual ingot object in the digital twin system based on the ingot tracking code and load the matched specification information; Bind the virtual ingot object to the task item in the processing task list to ensure that the ingot tracking data can be correctly called during task scheduling; Synchronize the ingot tracking data to the physical production line to ensure that the equipment can access the ingot information in real time.

[0055] S25, Processing task binding: Based on the ingot tracking data, update the processing task list, bind the ingot tracking code to the task item, including: Search for the task item to be executed in the processing task list according to the task number; Write the corresponding ingot tracking code in the task item to ensure that the ingot data can be correctly retrieved during task execution; Generate a task binding record as the input for subsequent task execution steps.

[0056] S26, Task Execution Status Initialization: Generate initial status information for the billets bound to the task to ensure that subsequent steps can accurately track their processing status, including: Set the initial process status, including heating status = not heated, extrusion status = not processed, wire winding status = not wound; Record the current timestamp as the reference time for subsequent status changes; Store the initial status data in the digital twin system and associate it with the billet tracking code for subsequent steps to call.

[0057] S3 includes: S31, Process Parameter Matching: According to the billet tracking code, retrieve the corresponding process parameters in the processing task list and extract the target heating temperature, preheating time, and temperature uniformity requirements, including: Based on the billet tracking code, match the target process number in the processing task list; According to the target process number, read the standard heating temperature, heating time, and temperature distribution uniformity threshold from the process database; Combine the current status of the equipment to correct the target temperature setting value to ensure that the temperature setting conforms to the current working conditions, and output the matched heating parameter data; S32, Heating Equipment Setting: Based on the heating parameter data, send a heating temperature setting instruction to the heating machine and initialize the temperature control mode, including: Analyze the target heating temperature and preheating time in the heating parameter data to generate a temperature control setting instruction; According to the equipment type, select the applicable temperature control mode, including PID closed-loop control mode or adaptive heating mode; Send the temperature control setting instruction to the heating machine control system and enter the heating state to ensure that the equipment executes according to the matched heating parameters.

[0058] S33, Temperature Data Acquisition: During the heating process, real-time collect the billet surface temperature distribution data and establish a temperature history curve, including: Collect the billet surface temperature data through an infrared thermal imager and thermocouple sensors and upload it to the digital twin system; Align the temperature data in time sequence according to the collected timestamp to ensure data synchronization; Generate a temperature history curve, including real-time temperature change trend, maximum temperature, minimum temperature, and temperature gradient information, and store it in the temperature monitoring database.

[0059] S34, Temperature Uniformity Analysis: Based on the temperature history curve, calculate the billet temperature uniformity index and detect whether it meets the set threshold, including: Calculate the maximum deviation value of the billet surface temperature, defined as: , where and are the current highest temperature and lowest temperature respectively; Calculate the temperature uniformity index, which is defined as: , where is the target heating temperature after matching; If the temperature uniformity index is lower than the set threshold, it is determined that the ingot heating is uneven, and a temperature anomaly identifier is generated.

[0060] S35, Temperature compensation instruction generation: If the temperature anomaly identifier is triggered, calculate the heating parameter correction value and generate a temperature compensation instruction, including: Calculate the temperature compensation amount to ensure that the temperature uniformity after heating meets the set standard; Select an applicable compensation strategy based on the current temperature gradient, including extending the heating time, adjusting the heating machine power, or dynamically adjusting the ingot position; Generate a temperature compensation instruction and store it in the digital twin system to ensure that the compensation instruction is available for the heating machine to execute.

[0061] S36, Closed-loop heating control: Based on the temperature compensation instruction, dynamically adjust the operating parameters of the heating machine and continuously monitor the heating effect, including: Send the temperature compensation instruction to the heating machine control system to dynamically adjust the temperature set value or heating time; Re-collect the temperature data and calculate the temperature uniformity index to ensure that the temperature deviation after compensation meets the process requirements; If the temperature uniformity index reaches the set standard, end the heating process and update the heating completion status in the processing task list.

[0062] S4 includes: S41, Manipulator path planning: Based on the adjustment result of the temperature compensation instruction, plan the manipulator movement path in the digital twin system and generate path planning data, including: Analyze the temperature compensation instruction to determine the current heating state and position coordinates of the ingot; Call the manipulator movement parameters in the virtual model to generate the optimal trajectory of the manipulator from the current grasping position to the extrusion machine die barrel; Calculate the manipulator joint angle sequence and movement time parameters to ensure that the path conforms to the equipment movement constraints; Output the path planning data, including the path coordinate sequence, joint angle sequence, and execution schedule.

[0063] S42, Path execution instruction generation: Based on the path planning data, send an execution instruction to the manipulator control system and initialize the motion control mode, including: Generate motion control instructions based on path planning data, including the starting point, target point, and acceleration / deceleration parameters; Set the path tracking mode to ensure that the manipulator executes according to the planned path, including position closed-loop control or velocity feedforward control; Send the path execution instruction to the manipulator control system and enter the motion execution state.

[0064] S43, Real-time pose monitoring: During the manipulator's path execution, collect the manipulator's pose data in real time and synchronize it with the digital twin system, including: Obtain the real-time position, angle, and velocity data of the manipulator through the inertial measurement unit and the optical positioning system; Analyze the pose data and align the path planning data based on the timestamp to ensure data consistency; Upload the real-time pose data of the manipulator to the digital twin system and update the state of the manipulator in the virtual model.

[0065] S44, Path deviation calculation: Based on the real-time pose data, compare it with the path planning data, calculate the path deviation, and generate deviation data, including: Calculate the offset between the actual path and the planned path , defined as: , where is the current pose of the manipulator, is the target pose of the manipulator in the path planning data; Calculate the manipulator's attitude error, including the rotation angle deviation and joint angle deviation; Generate path deviation data, including information such as position error, attitude error, and velocity deviation.

[0066] S45, Path deviation correction: Based on the path deviation data, generate path deviation correction instructions and dynamically adjust the manipulator's motion, including: Calculate the correction vector based on the path deviation data to ensure that the manipulator's motion trajectory returns to the planned path; Set the correction strategy, including online adjustment of path points or adjustment of joint control modes; Generate path deviation correction instructions and send them to the manipulator control system to correct the motion trajectory in real time.

[0067] S46, Target position verification: When the manipulator approaches the extrusion machine die barrel, detect the target position accuracy and perform the final position correction, including: Detect the final position of the billet relative to the die barrel through a laser range finder or a vision recognition system; Calculate the final position error and perform end correction to align the billet with the center of the extrusion machine die barrel; After confirming that the position error is within the allowable range, send the final placement instruction to complete the billet transfer.

[0068] S5 includes: S51, pressure parameter curve call: According to the billet tracking code, retrieve the corresponding pressure parameter curve in the processing task list and load it into the extruder control system, including: Based on the billet tracking code, match the target process number in the processing task list; Call the standard pressure parameter curve in the process database to obtain the corresponding extrusion force-time relationship data; According to the current equipment status, adjust the initial pressure setting value to ensure compliance with the target process requirements; Output the loaded pressure parameter curve as the control benchmark for the extrusion process.

[0069] S52, pressure data acquisition: During the extrusion process, real-time collect the pressure value in the die barrel of the extruder and establish a pressure monitoring data stream, including: Obtain the extrusion force data through the internal pressure sensor of the die barrel and upload it to the digital twin system; Align the pressure data in time sequence according to the acquisition timestamp to ensure data integrity; Generate a pressure monitoring data stream, including real-time pressure change trend, maximum pressure, minimum pressure, and pressure fluctuation range, and store it in the pressure monitoring database.

[0070] S53, material flow simulation calculation: Based on the pressure monitoring data stream, perform material flow simulation in the digital twin system to predict the billet deformation state and generate material flow simulation data, including: Based on the loaded pressure parameter curve, simulate the flow behavior of the billet material in the virtual model; Calculate the flow velocity field, stress distribution, and temperature change of the material under different extrusion forces; Combine the real-time pressure data to dynamically correct the simulation calculation to ensure the prediction accuracy; Generate material flow simulation data, including parameters such as strain distribution, flow velocity, and temperature gradient.

[0071] S5 also includes: S54, dynamic pressure adjustment instruction generation: Based on the material flow simulation data, calculate the pressure adjustment amount of the extruder and generate a dynamic pressure adjustment instruction, including: Calculate the deviation between the current extrusion speed and the target constant strain rate , expressed as: , where is the current extrusion speed, is the target speed corresponding to the constant strain rate; Adjust the pressure setpoint of the extruder according to the pressure feedback value to ensure that the flow rate meets the process requirements; Generate a dynamic pressure adjustment instruction and store it in the digital twin system for the extruder to execute.

[0072] S55, Closed-loop pressure control: Based on the dynamic pressure adjustment instruction, adjust the extruder pressure in real time and monitor the adjustment effect, including: Send a pressure adjustment instruction to the extruder control system to dynamically adjust the pressure set value; Re-collect pressure data and calculate the current pressure change trend to ensure that the adjusted pressure curve meets the set target; If the pressure fluctuation exceeds the allowable range, trigger secondary adjustment, optimize the pressure adjustment parameters, and ensure the stability of the extrusion process.

[0073] S56, Extrusion process status update: After extrusion is completed, record the final extrusion status and update the processing task list, including: Record data such as the final pressure distribution, material flow rate, and extrusion forming time; Analyze the equipment operation status based on the data change trend during the extrusion process to determine whether there are any abnormalities; Update the extrusion completion status of the billet in the processing task list and generate a quality assessment report; Store the extrusion process data in the digital twin system for subsequent process optimization analysis.

[0074] S6 includes: S61, Extrusion pressure feedback data acquisition: During the extrusion process, real-time collect the extrusion machine pressure feedback data and upload it to the digital twin system, including: Obtain the real-time extrusion pressure value through the internal pressure sensor of the die barrel and analyze the pressure change curve; Align the pressure data in time series according to the acquisition timestamp to ensure data synchronization; Generate a pressure feedback data stream, including the current pressure value, pressure fluctuation range, and stress change trend, and store it in the pressure monitoring database.

[0075] S62, Wire take-up tension calculation: Based on the pressure feedback data, calculate the required value of the wire take-up tension and generate an initial wire take-up tension set value, including: Calculate the current suitable wire take-up tension according to the mathematical model of the extrusion pressure and the wire diameter change, and the calculation is: , where, is the target wire take-up tension, is the tension coefficient, is the current extrusion pressure; Combine the current operating status of the wire take-up machine to correct the target wire take-up tension to ensure that the tension is within the allowable range of the equipment; Generate the setting value of the wire take-up tension and store it in the wire take-up control system.

[0076] S63, Tension adjustment instruction generation: Based on the setting value of the wire take-up tension, generate the tension adjustment instruction for the wire take-up machine and send it to the wire take-up control system, including: Generate the control parameters for controlling the motor torque and speed according to the setting value of the wire take-up tension; Set the closed-loop control mode of the wire take-up machine tension to ensure that the tension is adjustable in real time; Generate the tension adjustment instruction and send it to the execution unit of the wire take-up machine to adjust the tension according to the setting value.

[0077] S64, Wire diameter fluctuation monitoring: During the wire take-up process, use a laser rangefinder to collect the wire diameter data and generate the diameter fluctuation information, including: Real-time detect the wire diameter through the laser ranging sensor and upload it to the digital twin system; Calculate the average value and standard deviation of the current wire diameter and form a diameter fluctuation curve; Generate the diameter fluctuation information and store it in the wire take-up monitoring database.

[0078] S65, Extrusion speed compensation instruction generation: Based on the diameter fluctuation information, calculate the extrusion speed adjustment amount and generate the extrusion speed compensation instruction, including: Calculate the relationship between the current wire diameter deviation and the target diameter to determine the speed adjustment range; Generate the extrusion speed compensation instruction according to the diameter change trend to maintain the target diameter; Store it in the digital twin system and send it to the extrusion machine control system to adjust the extrusion machine speed.

[0079] S66, Closed-loop tension control: Based on the tension adjustment instruction and the extrusion speed compensation instruction, dynamically adjust the operating parameters of the wire take-up machine and the extrusion machine, including: Adjust the motor torque of the wire take-up machine according to the real-time wire take-up tension data to ensure the stability of the tension; Dynamically adjust the extrusion machine speed according to the extrusion speed compensation instruction to ensure the stability of the wire diameter; Monitor the adjusted wire take-up tension and extrusion speed. If they still exceed the allowable range, trigger secondary adjustment to optimize the control parameters and ensure the stable operation of the system.

[0080] S7 includes: S71, Wire coil specification data parsing: Based on the billet tracking code, retrieve the corresponding wire coil specification data in the processing task list and parse the wire unloading parameters, and output the parsed wire coil specification data, including: Find the corresponding wire coil specification information in the processing task list according to the billet tracking code; Extract key parameters such as the diameter, length, weight, and material of the wire coil to ensure that the wire unloading strategy adapts to the target specifications; Analyze the load capacity of the transfer machine in the target storage area to ensure that the wire unloading robot's grasping meets the requirements of the transfer machine's load-bearing; Output the parsed wire coil specification data as the input for the wire unloading path planning.

[0081] S72, Wire Unloading Robot Path Planning: Based on the wire coil specification data, plan the grasping path of the wire unloading robot in the digital twin system and generate path planning data, including: Calculate the optimal path of the wire unloading robot from the current wire coil storage area to the transfer machine according to the final placement position of the wire coil; Analyze the kinematic constraints of the wire unloading robot to ensure that the path planning conforms to the motion capabilities of the robotic arm; Calculate the clamping pose of the wire unloading robot to determine the optimal grasping point and avoid the offset of the wire coil's center of gravity; Generate path planning data, including motion trajectory points, clamping postures, and execution schedules.

[0082] S73, Generation of Grasping Path Execution Instructions: Based on the path planning data, send path execution instructions to the control system of the wire unloading robot and initialize the grasping control mode, including: Generate motion control instructions for the wire unloading robot to grasp, transport, and place according to the path planning data; Set the grasping force feedback control mode to ensure that the wire coil does not slip or get damaged during transportation; Send the path execution instructions to the control system of the wire unloading robot and enter the grasping execution state.

[0083] S74, Real-time Pose Monitoring: During the execution of the path by the wire unloading robot, collect the robot's pose data in real time to generate a real-time pose data stream, including: Obtain the real-time position, pose, and clamping force data of the wire unloading robot through an inertial measurement unit and an optical sensor; Align the pose data in time series according to the acquisition timestamp to ensure data consistency; Generate a real-time pose data stream and upload it to the digital twin system to update the robot state in the virtual model.

[0084] S75, Path Deviation Correction: Based on the real-time pose data, compare it with the path planning data, calculate the path deviation, and generate deviation correction instructions, including: Calculate the offset between the actual motion path and the planned path , which is calculated as: , where is the current pose of the wire unloading robot, It is the target pose of the wire unloading robot in the path planning data; Calculate the clamping force error to ensure that the grasping force is within the safe range and avoid damage to the wire coil; Generate a path deviation correction instruction and send it to the control system of the wire unloading robot to adjust the robot's motion trajectory.

[0085] S76, Target position verification and wire coil placement: When the wire unloading robot approaches the transfer machine, detect the final placement position of the wire coil and perform final position correction, including: Detect the actual position of the transfer machine and the wire coil docking point through a laser range finder sensor and a visual recognition system; Calculate the wire coil offset, adjust the pose of the wire unloading robot to ensure that the wire coil is accurately placed in the target area; After confirming that the position error is within the allowable range, send a placement instruction to complete the wire coil unloading.

[0086] S77, Update of the processing task completion status: After the wire coil unloading is completed, update the completion status in the processing task list and store it in the digital twin system, including: Record information such as the wire unloading timestamp, placement position, and wire coil status to ensure data traceability; Analyze the robot's motion execution based on the deviation data during the wire unloading process to determine whether the wire unloading strategy needs to be adjusted; Update the processing completion status of the billet in the processing task list and generate a quality assessment report; Store the wire unloading process data in the digital twin system for subsequent process optimization analysis.

[0087] As Figure 2 shown, an intelligent operation and maintenance system for an extrusion processing workshop based on digital twins, which is used to implement the above-mentioned intelligent operation and maintenance method for an extrusion processing workshop based on digital twins, includes the following modules: Digital twin module: Used to build a virtual model synchronized with the physical production line, load billet specifications, process parameters, equipment status, and sensor data to achieve virtual-real synchronization and data fusion; Production plan management module: Used to parse the production plan file, verify the billet specifications and process parameters, generate a processing task list, and synchronize it with the virtual model; Loading tracking module: Used to obtain billet specification information through RFID scanning, generate a billet tracking code, and establish a tracking index to associate the processing task with the billet data; Dynamic preheating control module: Used to match preset process parameters according to the billet tracking code, control the temperature of the heating machine, collect temperature data in real time, and generate a temperature compensation instruction to ensure uniform heating of the billet; Collaborative transfer module: It is used to plan the movement path of the manipulator based on the correction result of the temperature compensation instruction, monitor the pose of the manipulator in real time, generate a path deviation correction instruction, and control the manipulator to accurately feed it into the extrusion barrel of the extruder; Closed-loop extrusion control module: It is used to call the pressure parameter curve, collect the pressure value in the extrusion barrel of the extruder in real time, combine with the material flow simulation data, generate a dynamic pressure adjustment instruction, and achieve constant strain rate extrusion; Adaptive wire take-up module: It is used to generate a wire take-up tension adjustment instruction based on the extrusion pressure feedback data, adjust the tension parameter of the wire take-up machine, collect the wire diameter fluctuation information, and generate an extrusion speed compensation instruction to feedback to the extruder; Intelligent wire unloading module: Based on the wire coil specification data corresponding to the billet tracking code, generate a wire unloading robot grasping path instruction, control the robot to place the wire coil on the transfer machine, and update the completion status in the processing task list.

[0088] The present invention covers any alternatives, modifications, equivalent methods and solutions made within the spirit and scope of the present invention. In order to enable the public to have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, and those skilled in the art can fully understand the present invention without the description of these details. In addition, well-known methods, processes, flows, components and circuits, etc. are not described in detail to avoid unnecessary confusion to the essence of the present invention.

[0089] The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. An intelligent operation and maintenance method for an extrusion processing workshop based on digital twins, characterized in that: The following steps are involved: S1, production plan analysis: import the production plan through the digital twin system to generate a processing task list including billet specifications and process parameters. The digital twin system includes a virtual model and sensor network synchronized with the physical production line; S2, material tracking: obtaining the specification and quantity information of the brazing billet through RFID scanning, uploading it to the digital twin system to generate a billet tracking code, and binding the billet tracking code to the task item in the processing task list; S3, dynamic preheating: matching preset process parameters according to the billet tracking code, adjusting the temperature and time of the heating machine, collecting billet surface temperature distribution data in real time and generating temperature compensation instructions, wherein the temperature compensation instructions are used to correct the heating parameters to achieve uniform heating of the billet; S4, collaborative transmission: based on the correction result of the temperature compensation instruction, planning the movement path of the manipulator, monitoring the manipulator posture data in real time and comparing it with the preset path in the virtual model, generating a path deviation correction instruction, and controlling the manipulator to feed the billet into the extruder die barrel; S5, closed-loop extrusion: calling the corresponding pressure parameter curve according to the billet tracking code, collecting the pressure value in the die barrel of the extruder in real time, generating dynamic pressure adjustment instructions in combination with the material flow simulation data in the virtual model, and controlling the extruder to achieve constant strain rate extrusion; S6, adaptive wire collection: Generate wire collection tension adjustment instructions based on extrusion pressure feedback data, synchronously adjust the wire collection machine tension parameters, collect wire diameter fluctuation information through a laser rangefinder, generate extrusion speed compensation instructions and feed them back to the extruder; S7, intelligent wire unloading: based on the wire coil specification data corresponding to the billet tracking code, generate the wire unloading robot grasping path instruction, control the robot to place the wire coil on the transfer machine, and update the completion status in the processing task list.

2. According to claim 1, the intelligent operation and maintenance method of an extrusion processing workshop based on digital twin is characterized in that: The S1 includes: S11, production plan analysis: converting the external input production plan file into a structured data format, extracting the billet material code, target size, and process number fields therein, and generating an original production plan data set; S12, data validity check: performing rule check on the original production plan data set, the rule check includes: Verify whether the billet material code exists in the preset material library; Verify that the target size meets the specification constraints of the extruder die barrel; Verify whether the temperature-pressure parameters corresponding to the process number are complete; If the verification fails, an exception identifier is generated and the manual review process is triggered. If the verification passes, the verified production plan data is output; S13, virtual model synchronization: according to the billet material code in the verified production plan data, the thermal expansion coefficient and thermal conductivity parameters in the material library are called, the physical properties of the billet entity in the virtual model of the digital twin system are updated, and the synchronized virtual model parameters are generated; S14, sensor network configuration: based on the process number in the verified production plan data, load the corresponding sensor acquisition strategy, generate sensor configuration parameters and send them to the physical production line; S15, task list generation: the verified production plan data, synchronized virtual model parameters, and sensor configuration parameters are associated and bound, and arranged in production order to generate a processing task list.

3. According to claim 2, the intelligent operation and maintenance method of an extrusion processing workshop based on digital twin is characterized in that: The S2 includes: S21, RFID tag analysis: perform RFID scanning on the brazing billet, extract the billet specification information, batch number, and storage time in the RFID tag, and generate an original billet data set; S22, billet specification matching: matching the original billet data set with the processing task list to confirm the corresponding relationship between the billet specifications and the process parameters; If the match is successful, the matched billet task data is output; if the match fails, an exception identifier is generated and the exception handling mechanism is triggered; S23, billet tracking code generation: based on the matched billet task data, a billet tracking code is generated, a tracking index is established, and billet tracking data with the tracking code is output; S24, tracking data upload: uploading the billet tracking data to the digital twin system and establishing a real-time data mapping relationship; S25, processing task binding: based on the billet tracking data, updating the processing task list, and binding the billet tracking code with the task item; S26, task execution status initialization: generating initial status information for the billet bound to the completed task.

4. According to claim 3, the intelligent operation and maintenance method of an extrusion processing workshop based on digital twin is characterized in that: The S3 includes: S31, process parameter matching: according to the billet tracking code, the corresponding process parameters are retrieved in the processing task list, and the target heating temperature, preheating time, and temperature uniformity requirements are extracted; Combined with the current state of the equipment, the target temperature setting value is corrected and the matching heating parameter data is output; S32, heating equipment setting: based on the heating parameter data, a heating temperature setting instruction is sent to the heating machine, and a temperature control mode is initialized; S33, temperature data collection: during the heating process, real-time collection of billet surface temperature distribution data and establishment of a temperature history curve; S34, temperature uniformity analysis: based on the temperature history curve, calculating the billet temperature uniformity index, and detecting whether it meets the set threshold; If the temperature uniformity index is lower than the set threshold, the billet is judged to be heated unevenly and a temperature anomaly identifier is generated; S35, temperature compensation instruction generation: if the temperature abnormality identifier is triggered, the heating parameter correction value is calculated and a temperature compensation instruction is generated; S36, closed-loop heating control: based on the temperature compensation instruction, dynamically adjust the operating parameters of the heating machine and continuously monitor the heating effect.

5. According to claim 4, the intelligent operation and maintenance method of an extrusion processing workshop based on digital twin is characterized in that: The S4 includes: S41, manipulator path planning: based on the adjustment result of the temperature compensation instruction, planning the manipulator movement path in the digital twin system and generating path planning data; S42, path execution instruction generation: based on the path planning data, sending an execution instruction to the manipulator control system and initializing the motion control mode; S43, real-time posture monitoring: during the robot’s path execution, the robot’s posture data is collected in real time and synchronized with the digital twin system; S44, path deviation calculation: based on the real-time posture data, compare with the path planning data, calculate the path deviation, and generate deviation data; S45, path deviation correction: based on the path deviation data, generating a path deviation correction instruction, and dynamically adjusting the movement of the manipulator; S46, target position verification: When the robot approaches the extruder die barrel, the target position accuracy is detected and the final position correction is performed.

6. According to claim 5, the intelligent operation and maintenance method of an extrusion processing workshop based on digital twin is characterized in that: The S5 includes: S51, calling the pressure parameter curve: according to the billet tracking code, searching the corresponding pressure parameter curve in the processing task list, and loading it into the extruder control system; S52, pressure data collection: during the extrusion process, the pressure value in the die barrel of the extruder is collected in real time, and a pressure monitoring data stream is established; S53, material flow simulation calculation: based on the pressure monitoring data stream, perform material flow simulation in the digital twin system, predict the deformation state of the billet, and generate material flow simulation data.

7. The intelligent operation and maintenance method of an extrusion processing workshop based on digital twin according to claim 6 is characterized in that: The S5 further includes: S54, generating a dynamic pressure adjustment instruction: calculating the extruder pressure adjustment amount based on the material flow simulation data, and generating a dynamic pressure adjustment instruction; S55, closed-loop pressure control: based on the dynamic pressure adjustment instruction, adjusting the extruder pressure in real time and monitoring the adjustment effect; S56, extrusion process status update: after the extrusion is completed, the final extrusion status is recorded and the processing task list is updated.

8. The intelligent operation and maintenance method of an extrusion processing workshop based on digital twin according to claim 7 is characterized in that: The S6 includes: S61, extrusion pressure feedback data collection: during the extrusion process, the extruder pressure feedback data is collected in real time and uploaded to the digital twin system; S62, calculating the wire collection tension: calculating the wire collection tension requirement value based on the pressure feedback data, and generating an initial wire collection tension setting value; S63, generating a tension adjustment instruction: generating a wire receiving machine tension adjustment instruction based on the wire receiving tension setting value, and sending the instruction to the wire receiving control system; S64, wire diameter fluctuation monitoring: During the wire collection process, a laser rangefinder is used to collect wire diameter data and generate diameter fluctuation information; S65, generating an extrusion speed compensation instruction: calculating an extrusion speed adjustment amount based on the diameter fluctuation information, and generating an extrusion speed compensation instruction; S66, closed-loop tension control: dynamically adjusting the operating parameters of the wire collecting machine and the extruder based on the tension adjustment instruction and the extrusion speed compensation instruction.

9. The intelligent operation and maintenance method of an extrusion processing workshop based on digital twin according to claim 8 is characterized in that: The S7 includes: S71, wire coil specification data analysis: based on the billet tracking code, the corresponding wire coil specification data is retrieved in the processing task list, and the wire unloading parameters are analyzed, and the analyzed wire coil specification data is output; S72, wire unloading robot path planning: based on the wire coil specification data, planning the grasping path of the wire unloading robot in the digital twin system, and generating path planning data; S73, generating a grasping path execution instruction: based on the path planning data, sending a path execution instruction to the wire unloading robot control system, and initializing a grasping control mode; S74, real-time posture monitoring: during the execution of the path by the wire unloading robot, the robot posture data is collected in real time to generate a real-time posture data stream; S75, path deviation correction: based on the real-time posture data, compare with the path planning data, calculate the path deviation, and generate a deviation correction instruction; S76, target position verification and wire roll placement: when the wire unloading robot approaches the transfer machine, the final placement position of the wire roll is detected and the final position correction is performed; S77, update of processing task completion status: after the wire coil is unloaded, the completion status in the processing task list is updated and stored in the digital twin system.

10. An intelligent operation and maintenance system for an extrusion processing workshop based on digital twin, used to implement an intelligent operation and maintenance method for an extrusion processing workshop based on digital twin as described in any one of claims 1 to 9, characterized in that: Includes the following modules: Digital twin module: used to build a virtual model synchronized with the physical production line, load billet specifications, process parameters, equipment status and sensor data, and achieve virtual-real synchronization and data fusion; Production plan management module: used to parse production plan files, verify billet specifications and process parameters, generate processing task lists, and synchronize with virtual models; Feeding tracking module: used to obtain billet specification information through RFID scanning, generate billet tracking code, and establish tracking index to associate processing tasks with billet data; Dynamic preheating control module: used to match preset process parameters according to the billet tracking code, adjust the temperature of the heating machine, collect temperature data in real time, and generate temperature compensation instructions to ensure uniform heating of the billet; Collaborative transmission module: used to plan the robot's motion path based on the correction results of the temperature compensation instruction, monitor the robot's posture in real time, and generate path deviation correction instructions to control the robot to accurately feed into the extruder die barrel; Closed-loop extrusion control module: used to call the pressure parameter curve, collect the pressure value in the die barrel of the extruder in real time, combine the material flow simulation data, generate dynamic pressure adjustment instructions, and realize constant strain rate extrusion; Adaptive wire collection module: used to generate wire collection tension adjustment instructions based on extrusion pressure feedback data, adjust the tension parameters of the wire collection machine, collect wire diameter fluctuation information, generate extrusion speed compensation instructions and feedback to the extruder; Intelligent wire unloading module: Based on the wire coil specification data corresponding to the billet tracking code, it generates the wire unloading robot grabbing path instructions, controls the robot to place the wire coil on the transfer machine, and updates the completion status in the processing task list.

Images