Plastic metal processing system based on multi-dimensional perception and intelligent regulation and control
Through the accurate recognition of workpieces with multi-dimensional perception and deep learning, the machining accuracy regulation of adaptive control and tool wear monitoring of multi-modal data fusion, the problem of low recognition accuracy, difficulty in ensuring accuracy and difficult tool wear monitoring in plastic metal processing is solved, and an efficient and stable machining process is achieved.
Patent Information
- Application Number
- CN202510374838.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-27
- Publication Date
- 2025-07-11
AI Technical Summary
In the plastic metal processing, existing industrial robots have problems such as low workpiece identification and positioning accuracy, difficult machining accuracy and difficult tool wear monitoring, which affects processing quality and efficiency.
The workpiece precision identification and positioning algorithm is adopted for multi-dimensional perception and deep learning, combined with the machining accuracy intelligent regulation algorithm with adaptive control and real-time monitoring, and the tool wear monitoring system for multimodal data fusion and machine learning, so as to achieve accurate identification, real-time monitoring and parameter adjustment of workpieces by integrating multiple sensors and intelligent algorithms.
Improve the accuracy of workpiece identification and positioning, ensure processing accuracy and quality, monitor tool wear in real time, and improve production efficiency and management convenience.
Smart Images
Figure CN120287113A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of information technology, and particularly relates to a plastic-metal processing system based on multi-dimensional perception and intelligent regulation. Background Art
[0002] Plastic-metal processing is an important basic link in the manufacturing industry and is widely used in multiple fields such as automobiles, aerospace, and machinery manufacturing. With the continuous development of the manufacturing industry and the progress of technology, higher requirements are put forward for the precision, efficiency, and quality of plastic-metal processing. Industrial robots, with their high degree of automation, high operating precision, and high working efficiency, have been widely used in the process of plastic-metal processing, such as metal cutting, welding, grinding, drilling, etc. However, there are still many problems in the application of current industrial robots in the field of plastic-metal processing, which restricts the further development of the plastic-metal processing industry.
[0003] Low workpiece recognition and positioning accuracy: During the plastic-metal processing process, the shapes, sizes, and materials of workpieces are different, and the placement positions before processing have a certain degree of randomness. Traditional industrial robot workpiece recognition and positioning systems mainly rely on simple visual recognition technology, which is easily affected by factors such as lighting conditions, workpiece surface roughness, and stains, resulting in low recognition and positioning accuracy. During the actual processing process, the situation of excessive deviation of the robot processing position often occurs, which not only affects the processing accuracy but also may lead to workpiece scrapping and increase production costs.
[0004] Difficult to guarantee processing accuracy: Plastic-metal processing has extremely high requirements for accuracy. Different processing processes and workpiece materials require different processing parameters, such as cutting speed, feed rate, cutting depth, etc. Most of the existing industrial robot plastic-metal processing systems adopt preset fixed processing parameters and cannot be adjusted in real time according to the actual situation of the workpiece and the changes during the processing process. Moreover, due to factors such as vibration and thermal deformation during the processing process, the processing accuracy will be further affected, resulting in unstable processing quality.
[0005] Difficult to monitor tool wear: Tools are key consumables in the plastic-metal processing process, and the wear degree of tools directly affects the processing quality and production efficiency. At present, the monitoring of tool wear in industrial robot plastic-metal processing systems mainly relies on manual regular inspections or simple time counting methods, which cannot accurately grasp the tool wear situation in real time. When the tool wears excessively and cannot be replaced in time, it will lead to a decline in processing quality, a reduction in processing efficiency, and even damage to workpieces and equipment. Summary of the Invention
[0006] The present invention provides an industrial robot plastic-metal processing system based on multi-dimensional perception and intelligent regulation, including:
[0007] Precision Identification and Location Algorithm Module for Workpieces Based on Multi-Dimensional Sensing and Deep Learning: By integrating various types of sensors such as high-resolution vision sensors, laser ranging sensors, and tactile sensors on industrial robots, multi-dimensional information of workpieces including images, dimensions, shapes, positions, surface roughness, etc. is obtained in real time. Let the image information collected by the vision sensor be I, the dimension information obtained by the laser ranging sensor be D, and the information such as surface roughness sensed by the tactile sensor be T
[0008] ; Using the multi-dimensional sensing method, through the formula M = f(I, D, T), where f is a multi-dimensional data fusion function based on the attention mechanism, the data of different sensors are fused to construct the comprehensive information model M of the workpiece. Combining with the deep learning algorithm, the convolutional neural network (CNN), let its model output be O = CNN(M), and a mapping relationship model between the workpiece features and the identification and location results is established through the analysis of the output O to achieve the precision identification and location of the workpiece;
[0009] Intelligent Regulation Algorithm Module for Machining Precision Based on Adaptive Control and Real-Time Monitoring: Install various sensors such as force sensors, displacement sensors, and temperature sensors on the machining tools and workpieces of industrial robots to monitor the machining process parameters such as cutting force F, machining displacement S, and machining temperature Tp in real time. Combine with the on-line detection technology to obtain the machining precision information of the dimensional deviation ΔL and shape deviation ΔSh of the workpiece after machining. Using the adaptive control algorithm, through the formula
[0010] ΔP = g(F, S, Tp, ΔL, ΔSh), where g is an adaptive control function, and the adjustment amount ΔP of the machining parameters of the industrial robot is automatically calculated according to the real-time monitoring data to achieve the intelligent regulation of the machining precision;
[0011] Tool Wear Monitoring System Module Based on Multi-Modal Data Fusion and Machine Learning: Install various sensors such as vibration sensors, current sensors, and acoustic emission sensors on the tools of industrial robots to collect multi-modal data such as vibration signals V, current changes Ic, and acoustic emission signals A during the machining process of the tools. Using the multi-modal data fusion technology, through the formula W = h(V, Ic, A), where h is a multi-modal data fusion function based on the attention mechanism to construct the comprehensive data model W of tool wear. Combining with the support vector machine machine learning algorithm, let the tool wear degree be Wd, through the model Wd = SVM(W)
[0012] Establish an association model between the tool wear characteristics and the wear degree to achieve the real-time monitoring of the tool wear degree;
[0013] Efficient production system module for plastic and metal processing based on multi-robot collaboration and task optimization allocation: It can reasonably decompose and allocate tasks according to the plastic and metal processing technological process and production tasks, and assign them to multiple industrial robots to complete collaboratively. It establishes a communication and collaboration mechanism among multiple robots to achieve information sharing and collaborative operation, and has an intelligent task optimization allocation function that can adjust the task allocation scheme in real time according to changes in production tasks and the working status of robots.
[0014] Intelligent monitoring and management platform module for plastic and metal processing process: By interacting with the plastic and metal processing system of industrial robots, it can collect and store data in real time during the plastic and metal processing process, such as workpiece information, processing parameters, processing accuracy, tool wear conditions, and robot operating status. Using big data analysis and visualization technologies, it realizes intelligent monitoring and management of the plastic and metal processing process, and has intelligent early warning and fault diagnosis functions.
[0015] Furthermore, in the workpiece precise recognition and positioning algorithm module based on multi-dimensional perception and deep learning, multi-dimensional data fusion adopts a fusion network based on the attention mechanism, and the deep learning algorithm uses a convolutional neural network (CNN) or a recurrent neural network (RNN) to learn and train a large amount of workpiece data to establish a workpiece recognition and positioning model.
[0016] Furthermore, in the intelligent processing accuracy regulation algorithm module based on adaptive control and real-time monitoring, sensors installed on the processing tools and workpieces collect data in real time at a set frequency and transmit it to the adaptive control parameter adjustment module. The adaptive control algorithm calculates the adjustment amount of industrial robot processing parameters in real time according to the collected data.
[0017] Furthermore, in the tool wear monitoring system module based on multi-modal data fusion and machine learning, multi-modal data fusion adopts a fusion network based on the attention mechanism, and uses machine learning algorithms such as principal component analysis (PCA) to analyze and process the fused data to extract tool wear characteristics.
[0018] Furthermore, in the efficient production system module for plastic and metal processing based on multi-robot collaboration and task optimization allocation, factors such as the working ability, working range, and current status of the robots are considered during task allocation. During the collaboration process, the robots can adjust the collaboration strategy according to the real-time task situation and production progress.
[0019] Furthermore, in the intelligent monitoring and management platform module for plastic and metal processing process, big data analysis technology is used to analyze and mine the collected data to extract valuable information such as production efficiency analysis, processing quality problem prediction, and equipment failure early warning, and the analysis results are displayed in the form of charts and reports through visualization technology.
[0020] Furthermore, for the workpiece precise recognition and positioning algorithm module based on multi-dimensional perception and deep learning, when deploying sensors, according to the actual requirements of plastic and metal processing, it ensures comprehensive and accurate acquisition of multi-dimensional information of the workpiece, and the collected data is transmitted to the multi-dimensional data fusion module through the network.
[0021] Furthermore, for the machining accuracy intelligent regulation algorithm module based on adaptive control and real-time monitoring, the on-line detection device is installed at the outlet of the processing equipment, and it can detect the size and shape of the workpiece after processing in real time and transmit the machining accuracy information to the adaptive control parameter adjustment module.
[0022] Furthermore, for the tool wear monitoring system module based on multi-modal data fusion and machine learning, the sensor collects multi-modal data of the tool in real time according to the set frequency and transmits it to the multi-modal data fusion module through the network.
[0023] Furthermore, for the high-efficiency production system module of plastic and metal processing based on multi-robot cooperation and task optimization allocation, the multi-robot cooperation control module has the function of intelligent task optimization allocation, and it can automatically re-allocate tasks when a robot fails or the task volume changes.
[0024] Beneficial effects:
[0025] Improve the accuracy of workpiece recognition and positioning: The workpiece precise recognition and positioning algorithm based on multi-dimensional perception and deep learning can comprehensively utilize the information of multiple sensors to achieve precise recognition and positioning of the workpiece, improve the accuracy and stability of recognition and positioning, reduce the machining position deviation, and improve the machining accuracy and the qualified rate of workpieces.
[0026] Ensure machining accuracy: The machining accuracy intelligent regulation algorithm based on adaptive control and real-time monitoring can automatically adjust the machining actions and parameters of the industrial robot according to the machining parameters and workpiece machining accuracy information monitored in real time, realize the intelligent regulation of machining accuracy, ensure the stability and consistency of machining quality, and improve product quality.
[0027] Real-time monitor tool wear: The tool wear monitoring system based on multi-modal data fusion and machine learning can quickly and accurately monitor the wear degree of the tool, timely remind the operator to replace the tool, ensure machining quality and production efficiency, and reduce production costs.
[0028] Improve production efficiency: The high-efficiency production system of plastic and metal processing based on multi-robot cooperation and task optimization allocation can reasonably allocate tasks to multiple robots to complete collaboratively, realize information sharing and collaborative operation among robots, improve production efficiency, shorten the production cycle, and meet the needs of large-scale plastic and metal processing.
[0029] Convenient production management: The intelligent monitoring and management platform for the plastic and metal processing process provides real-time production process monitoring and decision-making support for managers. It has intelligent early warning and fault diagnosis functions, and can timely detect and solve problems in the production process. Description of the Drawings
[0030] Figure 1 Schematic diagram of the module flow. Detailed Implementation Manner
[0031] Example 1:
[0032] An industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation, including:
[0033] Workpiece precise recognition and positioning algorithm module based on multi-dimensional perception and deep learning: By integrating various types of sensors such as high-resolution vision sensors, laser range sensors, and tactile sensors on the industrial robot, multi-dimensional information of the workpiece including images, dimensions, shapes, positions, surface roughness, etc. is obtained in real time. Let the image information collected by the vision sensor be I, the dimension information obtained by the laser range sensor be D, and the information such as surface roughness sensed by the tactile sensor be T
[0034] ; Using the multi-dimensional perception method, through the formula M = f(I, D, T), where f is a multi-dimensional data fusion function based on the attention mechanism, the data of different sensors are fused to construct a comprehensive information model M of the workpiece. Combining with the deep learning algorithm, the convolutional neural network (CNN), let its model output be O = CNN(M), and a mapping relationship model between workpiece features and recognition and positioning results is established by analyzing the output O to achieve precise recognition and positioning of the workpiece;
[0035] Processing accuracy intelligent regulation algorithm module based on adaptive control and real-time monitoring: Install various sensors such as force sensors, displacement sensors, and temperature sensors on the processing tools and workpieces of the industrial robot to real-time monitor processing process parameters such as cutting force F, processing displacement S, and processing temperature Tp. Combining with on-line detection technology to obtain processing accuracy information such as workpiece size deviation ΔL and shape deviation ΔSh after processing. Using the adaptive control algorithm, through the formula
[0036] ΔP = g(F, S, Tp, ΔL, ΔSh), where g is an adaptive control function, and the adjustment amount ΔP of the industrial robot processing parameters is automatically calculated according to the real-time monitoring data to achieve intelligent regulation of the processing accuracy;
[0037] Tool wear monitoring system module based on multimodal data fusion and machine learning: Install various sensors such as vibration sensors, current sensors, and acoustic emission sensors on the tool of the industrial robot to collect real-time multimodal data of vibration signal V, current change Ic, and acoustic emission signal A during the machining process. Using multimodal data fusion technology, through the formula W = h(V, Ic, A), where h is a multimodal data fusion function based on the attention mechanism, construct a comprehensive tool wear data model W. Combine with the support vector machine machine learning algorithm. Let the tool wear degree be Wd, and through the model Wd = SVM(W)
[0038] Establish an association model between tool wear characteristics and wear degree to realize real-time monitoring of tool wear degree;
[0039] Efficient production system module for plastic-metal processing based on multi-robot cooperation and task optimization allocation: It can reasonably decompose and allocate tasks to multiple industrial robots according to the plastic-metal processing process flow and production tasks, establish a communication and cooperation mechanism between multiple robots to achieve information sharing and collaborative operation, and have an intelligent task optimization allocation function that can adjust the task allocation scheme in real time according to production task changes and robot working conditions;
[0040] Intelligent monitoring and management platform module for plastic-metal processing process: Through data interaction with the industrial robot plastic-metal processing system, collect and store data in real time during the plastic-metal processing process, such as workpiece information, processing parameters, processing accuracy, tool wear conditions, and robot operating status. Use big data analysis and visualization technology to realize intelligent monitoring and management of the plastic-metal processing process, and have intelligent early warning and fault diagnosis functions.
[0041] Perception layer: Install various types of sensors such as high-resolution vision sensors, laser range sensors, tactile sensors, force sensors, displacement sensors, temperature sensors, vibration sensors, current sensors, and acoustic emission sensors on the industrial robot to obtain information about workpieces, machining processes, and tools in real time. At the same time, install various environmental monitoring devices such as temperature and humidity sensors and noise sensors in the machining equipment and working environment to monitor the status of the machining environment. These sensors collect data in real time and transmit the data to the data processing layer.
[0042] Data processing layer: It includes a multi-dimensional data fusion module, a deep learning model training module, an adaptive control parameter adjustment module, a multi-modal data fusion module, and a machine learning model training module. The multi-dimensional data fusion module performs fusion processing on the data collected by multi-dimensional sensors to construct a comprehensive information model of the workpiece; the deep learning model training module uses deep learning algorithms to learn and train a large amount of workpiece data to establish a workpiece recognition and positioning model; the adaptive control parameter adjustment module adjusts the processing parameters of the industrial robot according to the data collected by the sensors using adaptive control algorithms; the multi-modal data fusion module performs fusion processing on the data collected by multi-modal sensors to construct a comprehensive data model of tool wear; the machine learning model training module uses machine learning algorithms to learn and train a large amount of tool wear data to establish a tool wear monitoring model.
[0043] Decision-making layer: It includes a workpiece precise recognition and positioning module, a processing precision intelligent regulation module, a tool wear monitoring module, a multi-robot cooperation control module, and an intelligent monitoring and management module. The workpiece precise recognition and positioning module realizes the precise recognition and positioning of the workpiece according to the results of the multi-dimensional data fusion module and the deep learning model training module using workpiece precise recognition and positioning algorithms; the processing precision intelligent regulation module realizes the intelligent regulation of the processing precision according to the results of the adaptive control parameter adjustment module combined with on-line detection data; the tool wear monitoring module realizes the real-time monitoring of the tool wear degree according to the results of the multi-modal data fusion module and the machine learning model training module using a tool wear monitoring system; the multi-robot cooperation control module reasonably distributes tasks to multiple robots according to the technological process and production tasks of plastic-metal processing and realizes the cooperation control between robots; the intelligent monitoring and management module is responsible for collecting, storing, analyzing, and displaying the data in the plastic-metal processing process to realize the intelligent monitoring and management of the plastic-metal processing process.
[0044] Execution layer: The industrial robot executes workpiece recognition, positioning, processing operations, tool wear monitoring, and cooperation tasks, etc. according to the control instructions generated by the decision-making layer. At the same time, it transmits the feedback information in the execution process back to the data processing layer and the decision-making layer for system adjustment and optimization.
[0045] Application layer: It is mainly an intelligent monitoring and management platform for the plastic-metal processing process, providing a friendly interaction interface for managers to realize functions such as real-time monitoring, data analysis, decision support, and intelligent warning of the plastic-metal processing process.
[0046] Implementation of the workpiece precise recognition and positioning algorithm based on multi-dimensional perception and deep learning
[0047]
[0048] Sensor Deployment and Data Acquisition: According to the actual requirements of plastic-metal processing, multi-dimensional sensors such as high-resolution vision sensors, laser range sensors, and tactile sensors are reasonably deployed to ensure comprehensive and accurate acquisition of multi-dimensional information of workpieces. The sensors collect data in real time according to the set frequency and transmit it to the multi-dimensional data fusion module in the data processing layer through the network.
[0049] Multi-dimensional Data Fusion and Feature Extraction: The multi-dimensional data fusion module uses a multi-dimensional data fusion algorithm based on deep learning, such as a fusion network based on the attention mechanism, to fuse different types of sensor data. Deep learning algorithms, such as convolutional neural networks (CNNs), are used to analyze and process the fused data to extract detailed features such as the type, shape, size, position, and surface roughness of the workpiece.
[0050] Deep Learning Model Training and Application: A large number of workpiece data of different types are collected to construct a training dataset. Deep learning algorithms, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs), are used to learn and train the training dataset to establish a workpiece recognition and positioning model. During the actual processing, the workpiece precise recognition and positioning module inputs the extracted features into the trained model to achieve precise recognition and positioning of the workpiece.
[0051] Implementation of Intelligent Regulation Algorithm for Machining Accuracy Based on Adaptive Control and Real-time Monitoring
[0052] Sensor Installation and Data Acquisition: A variety of high-precision sensors such as force sensors, displacement sensors, and temperature sensors are installed on the machining tools and workpieces of industrial robots to monitor various parameters during the machining process in real time, such as cutting force, machining displacement, and machining temperature. At the same time, on-line inspection equipment such as coordinate measuring machines and profilers is installed at the outlet of the machining equipment to detect the size and shape of the machined workpiece in real time and obtain the machining accuracy information of the workpiece. The sensors and on-line inspection equipment collect data in real time according to the set frequency and transmit it to the adaptive control parameter adjustment module in the data processing layer through the network.
[0053] Adaptive Control Algorithm Implementation: The adaptive control parameter adjustment module uses an adaptive control algorithm to calculate the adjustment amount of the machining parameters of the industrial robot in real time according to the machining parameters collected by the sensors and the workpiece machining accuracy information obtained by the on-line inspection equipment. The machining accuracy intelligent regulation module automatically adjusts the machining actions and parameters of the industrial robot according to the adjustment amount to achieve intelligent regulation of the machining accuracy.
[0054] Intelligent control and execution of processing accuracy: During the plastic and metal processing, the industrial robot adjusts the processing actions and parameters in real time according to the control instructions generated by the intelligent control module of processing accuracy to ensure the stability and consistency of processing quality. At the same time, according to the feedback information during the processing, the parameters of the adaptive control algorithm are continuously optimized to improve the control effect of processing accuracy.
[0055] Implementation of tool wear monitoring system based on multimodal data fusion and machine learning
[0056] Sensor installation and data collection: Various types of sensors such as vibration sensors, current sensors, and acoustic emission sensors are installed on the tools of industrial robots to collect multimodal data of the tools during processing in real time, including vibration signals, current changes, acoustic emission signals, etc. The sensors collect data in real time at the set frequency and transmit it to the multimodal data fusion module of the data processing layer through the network.
[0057] Multimodal data fusion and feature extraction: The multimodal data fusion module uses a multimodal data fusion algorithm based on deep learning, such as a fusion network based on an attention mechanism, to fuse different types of sensor data. Machine learning algorithms, such as principal component analysis (PCA), are used to analyze and process the fused data to extract key information that can reflect the characteristics of tool wear.
[0058] Machine learning model training and application: Collect a large amount of different types of tool wear data and build a training data set.
[0059] Machine learning algorithms, such as support vector machines (SVM) and neural networks, are used to learn and train the training data set to establish a correlation model between tool wear characteristics and wear degree. In the actual processing process, the tool wear monitoring module inputs the extracted features into the trained model to achieve real-time monitoring of tool wear degree.
[0060] Implementation of an efficient production system for plastic and metal processing based on multi-robot collaboration and optimal task allocation
[0061] Task analysis and allocation: The multi-robot collaborative control module analyzes the tasks in detail according to the process flow and production tasks of plastic and metal processing, decomposes the tasks into multiple subtasks, and reasonably allocates them to multiple industrial robots according to the characteristics and requirements of each subtask. When allocating tasks, the robot's working ability, working range, current status and other factors are considered to ensure the rationality and efficiency of task allocation.
[0062] Establishment of communication and collaboration mechanism: Establish a communication network among multiple robots to achieve real-time information interaction between robots. Through the collaborative control algorithm, coordinate the movement and operation of multiple robots to ensure that they can cooperate with each other and complete different processing procedures simultaneously, improving production efficiency. During the collaboration process, robots can adjust the collaboration strategy in a timely manner according to the real-time task situation and production progress to ensure the efficient and stable operation of the production process.
[0063] Implementation of intelligent task optimization and allocation: The multi-robot collaborative control module has the function of intelligent task optimization and allocation, and can adjust the task allocation scheme in real time according to the changes in production tasks and the working status of robots. For example, when a certain robot fails or the task volume suddenly increases, the intelligent task optimization and allocation function can automatically re-allocate the task to other robots to ensure the smooth completion of production tasks.
[0064] Implementation of the intelligent monitoring and management platform for the plastic-metal processing process
[0065] Data collection and transmission: The intelligent monitoring and management module collects various data in the plastic-metal processing process in real time through the data interface with the plastic-metal processing system of industrial robots, such as workpiece information, processing parameters, processing accuracy, tool wear condition, robot operation status, etc. After formatting the collected data, it is transmitted to the intelligent monitoring and management platform through the network.
[0066] Data analysis and visualization: Use big data analysis technology to analyze and mine the data transmitted to the platform, extract valuable information, such as production efficiency analysis, prediction of processing quality problems, equipment failure warning, etc. Through visualization technology, display the analysis results in the form of charts, reports, etc. on the interface of the intelligent monitoring and management platform to provide intuitive and clear production process monitoring and decision-making support for managers.
[0067] Implementation of intelligent warning and fault diagnosis functions: In the intelligent monitoring and management platform, establish an intelligent warning and fault diagnosis model. By setting thresholds and analysis models, monitor the data in the plastic-metal processing process in real time. When the data exceeds the set threshold or abnormal conditions occur, the platform automatically issues a warning signal and conducts fault diagnosis to prompt managers to take corresponding measures to ensure the smooth progress of the production process.
Claims
1. A plastic metal processing system based on multi-dimensional perception and intelligent regulation, characterized in that Including: Precise identification and positioning algorithm module of workpieces based on multi-dimensional perception and deep learning: By integrating high-resolution vision sensors, laser ranging sensors, and tactile sensors on industrial robots, multi-dimensional information of workpieces including images, dimensions, shapes, positions, and surface roughness is obtained in real time. Let the image information collected by the vision sensor be I, the dimension information obtained by the laser ranging sensor be D, and the information such as surface roughness sensed by the tactile sensor be T. Using the multi-dimensional perception method, through the formula M = f(I, D, T), where f is a multi-dimensional data fusion function based on the attention mechanism, the data of different sensors are fused to construct a comprehensive information model M of the workpiece. Combining with the deep learning algorithm, the convolutional neural network (CNN), let its model output be O = CNN(M). By analyzing the output O, a mapping relationship model between workpiece features and recognition and positioning results is established to achieve precise identification and positioning of workpieces; Intelligent regulation algorithm module of machining accuracy based on adaptive control and real-time monitoring: Force sensors, displacement sensors, and temperature sensors are installed on the machining tools and workpieces of industrial robots to monitor the machining process parameters of cutting force F, machining displacement S, and machining temperature Tp in real time. Combining with on-line detection technology, the machining accuracy information of the dimensional deviation ΔL and shape deviation ΔSh of the workpiece after machining is obtained. Using the adaptive control algorithm, through the formula ΔP = g(F, S, Tp, ΔL, ΔSh), where g is an adaptive control function, the adjustment amount ΔP of the machining parameters of the industrial robot is automatically calculated according to the real-time monitoring data to achieve intelligent regulation of machining accuracy; Tool wear monitoring system module based on multi-modal data fusion and machine learning: Vibration sensors, current sensors, and acoustic emission sensors are installed on the tools of industrial robots to collect multi-modal data of vibration signals V, current changes Ic, and acoustic emission signals A during the machining process of the tools. Using multi-modal data fusion, through the formula W = h(V, Ic, A), where h is a multi-modal data fusion function based on the attention mechanism, a comprehensive data model W of tool wear is constructed. Combining with the support vector machine machine learning algorithm, let the tool wear degree be Wd. By establishing a correlation model between tool wear characteristics and wear degree through the model Wd = SVM(W), real-time monitoring of tool wear degree is achieved; Efficient production system module of plastic-metal processing based on multi-robot cooperation and task optimization allocation: According to the plastic-metal processing process flow and production tasks, the tasks are reasonably decomposed and allocated to multiple industrial robots to complete collaboratively. A communication and cooperation mechanism between multiple robots is established to achieve information sharing and collaborative operation, and it has an intelligent task optimization allocation function to adjust the task allocation scheme in real time according to changes in production tasks and the working status of robots; Intelligent Monitoring and Management Platform Module for Plastic Metal Processing: By interacting with the plastic metal processing system of industrial robots, it can collect and store data in real time during the plastic metal processing, such as workpiece information, processing parameters, processing accuracy, tool wear conditions, and robot operating status. Using big data analysis and visualization technologies, it realizes intelligent monitoring and management of the plastic metal processing process, and has functions of intelligent early warning and fault diagnosis.
2. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, wherein In the workpiece precise recognition and positioning algorithm module based on multi-dimensional perception and deep learning, the multi-dimensional data fusion adopts a fusion network based on the attention mechanism, and the deep learning algorithm uses a convolutional neural network (CNN) or a recurrent neural network (RNN) to learn and train a large amount of workpiece data to establish a workpiece recognition and positioning model.
3. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, characterized in that, In the intelligent control algorithm module for processing accuracy based on adaptive control and real-time monitoring, sensors installed on the processing tools and workpieces collect data in real time at a set frequency and transmit it to the adaptive control parameter adjustment module. The adaptive control algorithm calculates the adjustment amount of industrial robot processing parameters in real time according to the collected data.
4. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, wherein In the tool wear monitoring system module based on multi-modal data fusion and machine learning, the multi-modal data fusion adopts a fusion network based on the attention mechanism, and uses the principal component analysis (PCA) machine learning algorithm to analyze and process the fused data to extract tool wear characteristics.
5. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, characterized in that, In the high-efficiency production system module for plastic metal processing based on multi-robot cooperation and task optimization allocation, when allocating tasks, factors such as the working ability, working range, and current status of the robots are considered. During the cooperation process, the robots can adjust the cooperation strategy according to the real-time task situation and production progress.
6. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, wherein In the intelligent monitoring and management platform module for the plastic metal processing process, big data analysis is used to analyze and mine the collected data to extract valuable information such as production efficiency analysis, prediction of processing quality problems, and equipment failure early warning, and the analysis results are displayed in the form of charts and reports through visualization technologies.
7. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, characterized in that, In the workpiece precise recognition and positioning algorithm module based on multi-dimensional perception and deep learning, when deploying sensors, according to the actual needs of plastic metal processing, it is ensured to comprehensively and accurately obtain multi-dimensional information of the workpiece, and the collected data is transmitted to the multi-dimensional data fusion module through the network.
8. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, characterized in that, In the intelligent control algorithm module for processing accuracy based on adaptive control and real-time monitoring, the on-line detection device is installed at the outlet of the processing equipment, and it can detect the size and shape of the processed workpiece in real time and transmit the processing accuracy information to the adaptive control parameter adjustment module.
9. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, wherein, In the tool wear monitoring system module based on multi-modal data fusion and machine learning, the sensors collect multi-modal data of the tool in real time at a set frequency and transmit it to the multi-modal data fusion module through the network.
10. The industrial robot plastic and metal processing system based on multi-dimensional perception and intelligent regulation according to claim 1, wherein In the high-efficiency production system module for plastic metal processing based on multi-robot cooperation and task optimization allocation, the multi-robot cooperation control module has the function of intelligent task optimization allocation, and can automatically re-allocate tasks when a robot fails or the task volume changes.