Industrial robot electronic manufacturing system based on intelligent cooperation

Abstract

The invention belongs to the technical field of information, and particularly relates to an industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent cooperation. Traditional electronic manufacturing has frequent problems in the aspects of component identification and assembly, welding process, quality detection, production cooperation and management and the like, and is low in efficiency and quality. According to the invention, through technologies of multi-dimensional sensing fusion, adaptive control, multi-modal data fusion and the like, in actual production scenes of manufacturing of smart phone mainboards, computer hard disk circuit boards, smart watches, tablet personal computers, electronic components and the like, the identification accuracy, the assembly precision, the welding quality, the qualified rate, the detection efficiency and the accuracy are greatly improved; the production efficiency is improved, the period is shortened, the failure rate is reduced, and the electronic manufacturing process is comprehensively optimized.

Description

Technical Field

[0001] The present invention belongs to the field of information technology, and in particular relates to an industrial robot electronic manufacturing system based on intelligent collaboration. Background Art

[0002] As a core component of the modern technology industry, the electronics manufacturing industry faces increasingly stringent requirements for precision, efficiency, and quality as electronic products continue to evolve and market competition intensifies. Industrial robots, with their high precision, speed, and reliability, are increasingly being used in electronics manufacturing, including surface mount technology (SMT), chip packaging, and circuit board assembly. However, the current application of industrial robots in electronics manufacturing still faces numerous challenges, hindering the industry's further development.

[0003] Low electronic component recognition and assembly accuracy: Electronic components are numerous, small, and complex in shape, and some have obscure surface features. Traditional industrial robotic electronic component recognition and assembly systems rely primarily on simple visual recognition and mechanical positioning. This approach is susceptible to factors such as surface reflections, dust, and static electricity, resulting in low recognition accuracy and poor assembly precision. In actual production, robots often misidentify components or exhibit significant deviations from assembly positions, impacting product quality while increasing production costs and cycle times.

[0004] Unstable welding process control: Welding is a critical process in electronics manufacturing, and welding quality directly impacts the performance and reliability of electronic products. Existing industrial robotic welding systems mostly use fixed welding parameters and operating procedures, which are unable to adjust and optimize in real time based on changes in electronic component material, shape, size, and welding environment. Furthermore, factors such as thermal deformation and arc fluctuations during the welding process further impact the stability and consistency of welding quality, resulting in low product qualification rates.

[0005] Inefficient product quality inspection: Quality inspection of electronic manufacturing products is crucial for ensuring product quality and market competitiveness. Currently, industrial robot product quality inspection systems rely primarily on manual spot checks and simple automated testing equipment. This approach suffers from low efficiency and poor accuracy, failing to meet the demands of large-scale production. Furthermore, manual inspections are susceptible to subjective factors, leading to biased results and making it difficult to identify and resolve product quality issues in a timely manner. Summary of the Invention

[0006] The present invention provides an industrial robot electronic manufacturing system based on intelligent collaboration, comprising:

[0007] The electronic component precise identification and high-precision assembly algorithm module based on multi-dimensional perception fusion and deep learning integrates multiple types of sensors on industrial robots to obtain multi-dimensional information of electronic components in real time. It uses multi-dimensional perception fusion technology and deep learning algorithms to achieve precise identification and high-precision assembly of electronic components. Suppose the electronic component information vector obtained by the multi-dimensional sensor is X = [x1, x2, …, xn], the feature vector after multi-dimensional data fusion is F(X), the electronic component recognition model established by the deep learning algorithm is M(F(X)), and the final recognition result is R = M(F(X)).

[0008] The intelligent control algorithm module for welding processes based on adaptive control and real-time monitoring uses a variety of sensors installed on the welding tools and electronic components of the industrial robot to monitor the parameters of the welding process in real time. Combined with online detection technology, it uses an adaptive control algorithm to achieve intelligent control of the welding process. Assuming the parameter vector of the welding process is P = [p1, p2, …, pm], and the weld quality parameter vector is Q = [q1, q2, …, qk], the adaptive control algorithm calculates the welding parameter adjustment ΔP based on P and Q, satisfying ΔP = f(P, Q), where f is the adaptive control function.

[0009] The product quality rapid detection system module based on multimodal data fusion and artificial intelligence installs various types of detection equipment on the electronic manufacturing production line to collect multimodal data of products in real time. It uses multimodal data fusion technology and artificial intelligence algorithms to achieve rapid detection of product quality and defect classification.

[0010] The electronic manufacturing efficient production system module based on multi-robot collaboration and dynamic task allocation can reasonably allocate tasks to multiple industrial robots for collaborative completion according to the electronic manufacturing process and production tasks. By establishing a communication and collaboration mechanism between multiple robots, information sharing and collaborative operations between robots are achieved, and it has the function of dynamic task allocation;

[0011] The intelligent monitoring and management platform module of the electronic manufacturing process interacts with the industrial robot electronic manufacturing system to collect and store various data in the electronic manufacturing process in real time. It uses big data analysis and visualization technology to provide managers with real-time production process monitoring and decision support, and has intelligent scheduling and fault diagnosis functions.

[0012] Furthermore, in the electronic component precise identification and high-precision assembly algorithm module of multi-dimensional perception fusion and deep learning, the multi-dimensional sensors include high-resolution visual sensors, laser displacement sensors, capacitive sensors, inductive sensors, etc., and the sensors are reasonably deployed according to the actual needs of electronic manufacturing.

[0013] Furthermore, in the intelligent control algorithm module of the welding process based on adaptive control and real-time monitoring, the sensors installed on the welding tools and electronic components include temperature sensors, current sensors, voltage sensors, force sensors, etc., and the online detection equipment performs real-time detection of the quality of the welds after welding.

[0014] Furthermore, in the product quality rapid detection system module based on multimodal data fusion and artificial intelligence, the multimodal detection equipment includes X-ray detection equipment, ultrasonic detection equipment, optical detection equipment, electrical performance detection equipment, etc., and the detection equipment is reasonably deployed according to the production line layout.

[0015] Furthermore, in the electronic manufacturing efficient production system module based on multi-robot collaboration and dynamic task allocation, real-time information exchange is achieved between multiple robots by establishing a communication network, and the dynamic task allocation function adjusts the task allocation plan in real time according to changes in production tasks and the working status of the robots.

[0016] Furthermore, in the intelligent monitoring and management platform module of the electronic manufacturing process, the collected data is analyzed and mined through big data analysis technology to extract valuable information such as production efficiency analysis, product quality problem prediction, and equipment failure warning.

[0017] Furthermore, the system also includes a perception layer, which is composed of various types of sensors installed on industrial robots and various detection equipment on the electronic manufacturing production line, and is used to obtain information on electronic components, welding processes and product quality in real time, and transmit the data to the data processing layer.

[0018] Furthermore, the data processing layer includes a multi-dimensional data fusion module, a deep learning model training module, an adaptive control parameter adjustment module, a multimodal data fusion module, and an artificial intelligence model training module to process the data transmitted by the perception layer and perform model training.

[0019] Furthermore, the decision-making layer includes an electronic component accurate identification and high-precision assembly module, a welding process intelligent control module, a product quality rapid detection module, a multi-robot collaborative control module, and an intelligent monitoring and management module, which generates control instructions based on the results of the data processing layer.

[0020] Furthermore, the execution layer includes industrial robots, which perform electronic component identification, assembly, welding operations, quality inspection, and collaborative tasks according to the control instructions generated by the decision layer, and transmit feedback information during the execution process back to the data processing layer and the decision layer.

[0021] Beneficial effects:

[0022] Improve the accuracy of electronic component recognition and assembly: The electronic component precise recognition and high-precision assembly algorithm based on multi-dimensional perception fusion and deep learning can comprehensively utilize information from multiple sensors to achieve precise recognition and high-precision assembly of electronic components, improve recognition accuracy and assembly accuracy, reduce product defective rate, and improve product quality.

[0023] Stable welding process control: The intelligent welding process control algorithm based on adaptive control and real-time monitoring can automatically adjust the welding movements and parameters of the industrial robot according to the real-time monitored welding parameters and weld quality information, realize intelligent control of the welding process, ensure the stability and consistency of welding quality, and improve product qualification rate.

[0024] Improve product quality inspection efficiency: The product quality rapid inspection system based on multimodal data fusion and artificial intelligence can quickly and accurately detect product quality, realize rapid inspection and defect classification of product quality, improve inspection efficiency and accuracy, and promptly discover and solve product quality problems.

[0025] Improve electronic manufacturing production efficiency: The electronic manufacturing efficient production system based on multi-robot collaboration and dynamic task allocation can reasonably allocate tasks to multiple robots for collaborative completion, realize information sharing and collaborative operation between robots, improve production efficiency, shorten production cycle, and meet the modern electronic manufacturing industry's demand for efficient production.

[0026] Convenient electronic manufacturing management: The intelligent monitoring and management platform of the electronic manufacturing process provides managers with real-time production process monitoring and decision support. It has intelligent scheduling and fault diagnosis functions, can reasonably schedule the robot's work tasks, promptly discover and solve the robot's fault problems, and improve the level of production management. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Module flow diagram. DETAILED DESCRIPTION

[0028] Example 1:

[0029] System architecture implementation

[0030] Perception layer: Industrial robots are equipped with various sensors, including high-resolution visual sensors, laser displacement sensors, capacitive sensors, inductive sensors, temperature sensors, current sensors, voltage sensors, and force sensors. Electronics manufacturing production lines are equipped with testing equipment, including X-ray, ultrasonic, optical, and electrical performance testing equipment, to obtain real-time information on electronic components, welding processes, and product quality. These sensors and testing equipment collect data in real time and transmit it to the data processing layer.

[0031] The electronic component precise identification and high-precision assembly algorithm module based on multi-dimensional perception fusion and deep learning integrates multiple types of sensors on industrial robots to obtain multi-dimensional information of electronic components in real time. It uses multi-dimensional perception fusion technology and deep learning algorithms to achieve precise identification and high-precision assembly of electronic components. Suppose the electronic component information vector obtained by the multi-dimensional sensor is X = [x1, x2, …, xn], the feature vector after multi-dimensional data fusion is F(X), the electronic component recognition model established by the deep learning algorithm is M(F(X)), and the final recognition result is R = M(F(X)).

[0032] The intelligent control algorithm module for welding processes based on adaptive control and real-time monitoring uses a variety of sensors installed on the welding tools and electronic components of the industrial robot to monitor the parameters of the welding process in real time. Combined with online detection technology, it uses an adaptive control algorithm to achieve intelligent control of the welding process. Assuming the parameter vector of the welding process is P = [p1, p2, …, pm], and the weld quality parameter vector is Q = [q1, q2, …, qk], the adaptive control algorithm calculates the welding parameter adjustment ΔP based on P and Q, satisfying ΔP = f(P, Q), where f is the adaptive control function.

[0033] Data processing layer: This includes a multi-dimensional data fusion module, a deep learning model training module, an adaptive control parameter adjustment module, a multimodal data fusion module, and an artificial intelligence model training module. The multi-dimensional data fusion module fuses and processes data collected by multi-dimensional sensors to construct a comprehensive information model for electronic components. The deep learning model training module uses deep learning algorithms to learn and train large amounts of electronic component data to establish a precise electronic component identification model. The adaptive control parameter adjustment module uses adaptive control algorithms to adjust the welding parameters of industrial robots based on data collected by sensors. The multimodal data fusion module fuses and processes data collected by multimodal detection equipment to construct a comprehensive information model for product quality. The artificial intelligence model training module uses artificial intelligence algorithms to learn and train large amounts of product quality data to establish a product quality detection model.

[0034] The decision-making layer includes the electronic component precision identification and high-precision assembly module, the welding process intelligent control module, the product quality rapid detection module, the multi-robot collaborative control module, and the intelligent monitoring and management module. The electronic component precision identification and high-precision assembly module uses the electronic component precision identification and high-precision assembly algorithm based on the results of the multi-dimensional data fusion module and the deep learning model training module to achieve precise identification and high-precision assembly of electronic components. The welding process intelligent control module uses the results of the adaptive control parameter adjustment module and real-time monitoring data to achieve intelligent control of the welding process. The product quality rapid detection module uses the product quality rapid detection system based on the results of the multimodal data fusion module and the artificial intelligence model training module to achieve rapid detection of product quality and defect classification. The multi-robot collaborative control module rationally allocates tasks to multiple robots based on the electronic manufacturing process and production tasks, and realizes collaborative control between robots. The intelligent monitoring and management module is responsible for collecting, storing, analyzing, and displaying data from the electronic manufacturing process, realizing intelligent monitoring and management of the electronic manufacturing process.

[0035] Execution layer: Industrial robots perform electronic component identification, assembly, welding, quality inspection, and collaborative tasks according to control instructions generated by the decision layer. At the same time, feedback from the execution process is transmitted back to the data processing layer and the decision layer to adjust and optimize the system.

[0036] Application layer: It is mainly an intelligent monitoring and management platform for the electronic manufacturing process, providing managers with a friendly interactive interface to realize real-time monitoring, data analysis, decision support, intelligent scheduling and fault diagnosis of the electronic manufacturing process.

[0037] Implementation of accurate identification and high-precision assembly algorithms for electronic components based on multi-dimensional perception fusion and deep learning

[0038] Sensor Deployment and Data Collection: Based on the actual needs of electronics manufacturing, multi-dimensional sensors such as high-resolution visual sensors, laser displacement sensors, capacitive sensors, and inductive sensors are deployed to ensure comprehensive and accurate acquisition of multi-dimensional information about electronic components. The sensors collect data in real time at a set frequency and transmit it over the network to the multi-dimensional data fusion module in the data processing layer.

[0039] Multi-dimensional Data Fusion and Feature Extraction: The multi-dimensional data fusion module uses deep learning-based multi-dimensional data fusion algorithms, such as attention-based fusion networks, to fuse data from different sensor types. Deep learning algorithms, such as convolutional neural networks (CNNs), are used to analyze and process the fused data, extracting detailed features such as the type, shape, size, location, and electrical characteristics of electronic components.

[0040] Deep learning model training and application: A large amount of data on various electronic components is 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 and establish a precise electronic component recognition model. In actual production, the electronic component precision recognition and high-precision assembly module inputs the extracted features into the trained model to achieve precise identification of electronic components. High-precision positioning algorithms, combined with assembly process requirements, are used to plan the optimal assembly path and motion for the robot.

[0041] Implementation of intelligent control algorithm for welding process based on adaptive control and real-time monitoring

[0042] Sensor Installation and Data Collection: A variety of high-precision sensors, including temperature sensors, current sensors, voltage sensors, and force sensors, are installed on the industrial robot's welding tools and electronic components to monitor various parameters during the welding process, such as welding temperature, current, voltage, and welding force, in real time. Furthermore, online testing equipment, such as microscopes and tensile testing machines, is installed at the welding equipment's exit to perform real-time inspections of the solder joints, capturing information such as their size, shape, and strength. The sensors and online testing equipment collect data in real time at a set frequency and transmit it via the network to the adaptive control parameter adjustment module in the data processing layer.

[0043] Adaptive Control Algorithm Implementation: The adaptive control parameter adjustment module uses an adaptive control algorithm to calculate the adjustment amount for the industrial robot's welding parameters in real time based on welding parameters collected by sensors and weld quality information obtained by online inspection equipment. The intelligent welding process control module automatically adjusts the industrial robot's welding movements and parameters based on the adjustment amount, achieving intelligent control of the welding process.

[0044] Intelligent welding process control and execution: During the electronics manufacturing process, industrial robots adjust welding movements and parameters in real time based on control instructions generated by the intelligent welding process control module, ensuring stable and consistent welding quality. Furthermore, based on feedback from the welding process, the parameters of the adaptive control algorithm are continuously optimized to improve the control effect of the welding process.

[0045] Implementation of a rapid product quality detection system based on multimodal data fusion and artificial intelligence

[0046] Testing Equipment Deployment and Data Collection: Multimodal testing equipment, including X-ray, ultrasonic, optical, and electrical performance testing equipment, is deployed strategically throughout the electronics manufacturing production line to ensure comprehensive and accurate multimodal data collection. The testing equipment collects data in real time at a set frequency and transmits it over the network to the multimodal data fusion module in the data processing layer.

[0047] Multimodal Data Fusion and Feature Extraction: The multimodal data fusion module uses deep learning-based multimodal data fusion algorithms, such as attention-based fusion networks, to fuse data from different types of testing equipment. Artificial intelligence algorithms, such as principal component analysis (PCA), are used to analyze and process the fused data, extracting key information that reflects product quality characteristics.

[0048] AI model training and application: Collect a large amount of diverse product quality data to construct a training dataset. Leveraging AI algorithms, such as deep learning and machine learning, this dataset is trained and analyzed to establish a product quality inspection model. During actual production, the rapid product quality inspection module inputs the extracted features into the trained model, enabling rapid product quality inspection and defect classification.

[0049] Implementation of an efficient production system for electronic manufacturing based on multi-robot collaboration and dynamic task allocation

[0050] Task Analysis and Allocation: The multi-robot collaborative control module analyzes tasks in detail based on the electronics manufacturing process and production tasks, breaking them down into multiple subtasks and assigning them to multiple industrial robots based on the characteristics and requirements of each subtask. Task allocation considers factors such as the robots' capabilities, work range, and current status to ensure rational and efficient task allocation.

[0051] Establishing a communication and collaboration mechanism: A multi-robot communication network is established to enable real-time information exchange between robots. Collaborative control algorithms coordinate the movements and operations of multiple robots, ensuring they can collaborate and simultaneously complete different production processes, improving production efficiency. During the collaborative process, robots can adjust their collaboration strategies based on real-time task status and production progress, ensuring efficient and stable production.

[0052] Dynamic Task Allocation: The multi-robot collaborative control module features dynamic task allocation, which adjusts the task allocation plan in real time based on changes in production tasks and the robots' working status. For example, if a robot malfunctions or the production workload suddenly increases, the dynamic task allocation function can automatically reallocate tasks to other robots to ensure smooth completion of production tasks.

[0053] Implementation of intelligent monitoring and management platform for electronic manufacturing process

[0054] Data Collection and Transmission: The intelligent monitoring and management module uses a data interface with the industrial robot electronics manufacturing system to collect various data from the electronics manufacturing process in real time, such as electronic component information, welding parameters, product quality information, and robot operating status. The collected data is formatted and transmitted via the network to the intelligent monitoring and management platform.

[0055] Data Analysis and Visualization: Utilizing big data analytics technology, data transmitted to the platform is analyzed and mined to extract valuable information, such as production efficiency analysis, product quality problem prediction, and equipment failure warnings. Through visualization technology, analysis results are displayed in the form of charts and reports on the intelligent monitoring and management platform interface, providing managers with intuitive and clear production process monitoring and decision-making support.

[0056] Intelligent Scheduling and Fault Diagnosis: Within the intelligent monitoring and management platform, an intelligent scheduling and fault diagnosis model is established. By setting rules and analyzing models, data from the electronics manufacturing process is monitored in real time. Based on production progress and the robot's operating status, the intelligent scheduling model can rationally schedule robot tasks. When a robot malfunctions, the fault diagnosis model promptly identifies and diagnoses the cause, prompting management to take appropriate measures and improving production management.

[0057] Example 2

[0058] Implementation of an algorithm for accurate identification and high-precision assembly of electronic components based on multi-dimensional perception fusion and deep learning

[0059] An electronics manufacturer traditionally uses simple visual recognition and mechanical positioning to produce smartphone motherboards. Workers manually identify electronic components under a microscope, working an eight-hour day and only managing to identify and assemble 50 motherboards. Due to the tiny size of the components and reflective surfaces, the recognition accuracy rate is only 70%, and assembly position deviations often exceed 0.2mm, resulting in a defective rate of 15%.

[0060] After introducing the algorithm presented in this paper, an industrial robot was integrated with high-resolution vision, laser displacement, capacitance, and inductance sensors. Multi-dimensional perception fusion technology was used to integrate multi-dimensional component information and identify components using a deep learning model. The robot can identify and assemble 20 motherboard components per hour, with recognition accuracy reaching 98%. Assembly position deviation was controlled within 0.05mm, and the defective rate was reduced to 3%. This significantly increased production efficiency and improved product quality.

[0061] Implementation of intelligent control algorithm for welding process based on adaptive control and real-time monitoring

[0062] Traditional welding systems utilize fixed parameters during the production of computer hard drive circuit boards. Due to the diverse material and size of components, thermal deformation and arc fluctuations during welding severely impact welding quality, leading to frequent problems such as cold solder joints and short circuits, resulting in a product pass rate of only 80%. Frequent manual intervention and parameter adjustments are required during the welding process, requiring five machine stops for every 100 circuit boards welded, severely impacting production schedules.

[0063] Using this algorithm, temperature, current, voltage, and force sensors are installed on welding tools and components, along with online solder joint quality monitoring equipment. This adaptive control algorithm automatically adjusts welding motion and parameters based on real-time parameters and solder joint quality. This has boosted product qualification rates to over 95%, requiring only one machine stop for adjustment per 100 circuit boards. This significantly improves welding quality consistency and production efficiency.

[0064] Implementation of a rapid product quality detection system based on multimodal data fusion and artificial intelligence

[0065] A company producing smartwatches previously relied on manual spot checks and simple automated testing equipment. Manual spot checks, at a rate of 10 products per hour, were subject to significant subjective influence, resulting in a 10% missed detection rate. The simple automated equipment could only detect single cosmetic defects and was unable to effectively detect internal structural or electrical performance issues.

[0066] Implementing the inspection system of this invention deploys X-ray, ultrasonic, optical, and electrical performance testing equipment on the production line. Multimodal data fusion and artificial intelligence algorithms rapidly analyze product multimodal data. This system can inspect 100 products per hour with 99% accuracy, accurately detecting all types of defects. This significantly improves inspection efficiency and accuracy, allowing for timely identification of product quality issues and reducing the risk of defective products entering the market.

[0067] Implementation of an efficient electronic manufacturing production system based on multi-robot collaboration and dynamic task allocation

[0068] At a tablet computer manufacturer, the traditional production model involved each process being independently completed by a single robot or human operator. This resulted in poor information flow between processes and long production cycles. Producing 1,000 tablet computers took five days, and equipment utilization was only 50%.

[0069] With this system, multiple robots collaborate to complete production tasks. Tasks are rationally allocated based on process flow and tasks, and a communication and collaboration mechanism is established. This allows the production of 1,000 tablet computers in just three days, increasing equipment utilization to 80%. This significantly improves production efficiency, effectively shortens production cycles, and reduces production costs.

[0070] Implementation of an intelligent monitoring and management platform for electronic manufacturing processes

[0071] A certain electronic component manufacturing company used to rely on manual records and experience-based judgments for production management. Production data could not be collected and analyzed in real time, production progress could not be controlled in a timely manner, and equipment failures often led to long production stoppages.

[0072] The introduction of an intelligent monitoring and management platform enables real-time collection of production process data, and big data analysis displays information such as production progress, product quality, and equipment status. Based on these analysis results, managers can adjust production plans in real time, predict equipment failures, and implement maintenance measures in advance. This has resulted in a 30% increase in production efficiency and a 40% reduction in equipment failure rates, significantly improving production management and ensuring efficient and stable production operations.

Claims

1. An industrial robot electronic manufacturing system based on intelligent collaboration, characterized in that: include: The electronic component precise identification and high-precision assembly algorithm module based on multi-dimensional perception fusion and deep learning integrates multiple types of sensors on industrial robots to obtain multi-dimensional information of electronic components in real time. It uses multi-dimensional perception fusion technology and deep learning algorithms to achieve precise identification and high-precision assembly of electronic components. Suppose the electronic component information vector obtained by the multi-dimensional sensor is X = [x1, x2, …, xn], the feature vector after multi-dimensional data fusion is F(X), the electronic component recognition model established by the deep learning algorithm is M(F(X)), and the final recognition result is R = M(F(X)). The intelligent control algorithm module for welding processes based on adaptive control and real-time monitoring uses a variety of sensors installed on the welding tools and electronic components of the industrial robot to monitor the parameters of the welding process in real time. Combined with online detection technology, it uses an adaptive control algorithm to achieve intelligent control of the welding process. Assuming the parameter vector of the welding process is P = [p1, p2, …, pm], and the weld quality parameter vector is Q = [q1, q2, …, qk], the adaptive control algorithm calculates the welding parameter adjustment ΔP based on P and Q, satisfying ΔP = f(P, Q), where f is the adaptive control function. The product quality rapid detection system module based on multimodal data fusion and artificial intelligence installs various types of detection equipment on the electronic manufacturing production line to collect multimodal data of products in real time. It uses multimodal data fusion technology and artificial intelligence algorithms to achieve rapid detection of product quality and defect classification. The electronic manufacturing efficient production system module based on multi-robot collaboration and dynamic task allocation can reasonably allocate tasks to multiple industrial robots for collaborative completion according to the electronic manufacturing process and production tasks. By establishing a communication and collaboration mechanism between multiple robots, information sharing and collaborative operations between robots are achieved, and it has the function of dynamic task allocation; The intelligent monitoring and management platform module of the electronic manufacturing process interacts with the industrial robot electronic manufacturing system to collect and store various data in the electronic manufacturing process in real time. It uses big data analysis and visualization technology to provide managers with real-time production process monitoring and decision support, and has intelligent scheduling and fault diagnosis functions.

2. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 1 is characterized in that: In the electronic component precise identification and high-precision assembly algorithm module of multi-dimensional perception fusion and deep learning, the multi-dimensional sensors include high-resolution visual sensors, laser displacement sensors, capacitive sensors, inductive sensors, etc., and the sensors are reasonably deployed according to the actual needs of electronic manufacturing.

3. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 1 is characterized in that: In the welding process intelligent control algorithm module based on adaptive control and real-time monitoring, the sensors installed on the welding tools and electronic components include temperature sensors, current sensors, voltage sensors, force sensors, etc., and the online detection equipment performs real-time detection of the quality of the welds after welding.

4. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 1 is characterized in that: In the product quality rapid detection system module based on multimodal data fusion and artificial intelligence, the multimodal detection equipment includes X-ray detection equipment, ultrasonic detection equipment, optical detection equipment, electrical performance detection equipment, etc., and the detection equipment is reasonably deployed according to the production line layout.

5. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 1 is characterized in that: In the electronic manufacturing efficient production system module based on multi-robot collaboration and dynamic task allocation, multiple robots achieve real-time information exchange by establishing a communication network, and the dynamic task allocation function adjusts the task allocation plan in real time according to changes in production tasks and the working status of the robots.

6. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 1 is characterized in that: In the intelligent monitoring and management platform module of the electronic manufacturing process, the collected data is analyzed and mined through big data analysis technology to extract valuable information such as production efficiency analysis, product quality problem prediction, and equipment failure warning.

7. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 1 is characterized in that: The system also includes a perception layer, which is composed of various types of sensors installed on industrial robots and various detection equipment on the electronic manufacturing production line. It is used to obtain information about electronic components, welding processes and product quality in real time, and transmit the data to the data processing layer.

8. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 7 is characterized in that: The data processing layer includes a multi-dimensional data fusion module, a deep learning model training module, an adaptive control parameter adjustment module, a multimodal data fusion module, and an artificial intelligence model training module to process the data transmitted by the perception layer and perform model training.

9. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 8, characterized in that: The decision-making layer includes an electronic component accurate identification and high-precision assembly module, a welding process intelligent control module, a product quality rapid detection module, a multi-robot collaborative control module, and an intelligent monitoring and management module, which generates control instructions based on the results of the data processing layer.

10. The industrial robot electronic manufacturing system based on multi-dimensional perception and intelligent collaboration according to claim 9, characterized in that: The execution layer includes industrial robots, which perform electronic component identification, assembly, welding operations, quality inspection, and collaborative tasks according to the control instructions generated by the decision layer, and transmit feedback information during the execution process back to the data processing layer and the decision layer.

Images