Part defective rate detection robot, control system and method
By designing an automated control system for part defect rate detection robot and machine learning algorithms, the problem of inefficiency of traditional parts quality control methods is solved, efficient and accurate part detection is achieved, and production efficiency and product quality control are improved.
Patent Information
- Application Number
- CN202411296540.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-18
- Publication Date
- 2024-11-22
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional parts quality control methods are inefficient, subjective, and susceptible to human factors, resulting in unstable testing results. It is necessary to develop an efficient, accurate and automated part defect rate detection system.
A part defect rate detection robot including outriggers, telescopic legs, detection table, laser rangefinder, stress tester and camera was designed. The control system of machine learning algorithms is combined to realize automated detection and data analysis, and through visual inspection. , size detection and function detection, identify defective products and generate inspection reports.
It realizes continuous and efficient automation of part inspection, reduces production line downtime, quickly identify and process defective products, improves inspection accuracy and consistency, enhances product quality control, and reduces rework and waste.
Smart Images

Figure CN118988779A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of parts detection, and in particular to a parts defective rate detection robot, control system and method. Background Art
[0002] In modern manufacturing, parts quality control is a key link to ensure product performance and reliability. With the development of industrial automation and intelligent manufacturing technology, higher requirements are placed on the detection of defective parts in the production process.
[0003] However, traditional quality control methods rely on experienced quality inspectors to identify defective products through visual inspection and manual measurement. This method is inefficient, highly subjective, and easily affected by human factors, resulting in unstable detection results. Therefore, it is particularly important to develop an efficient, accurate, and automated part defect rate detection system. Summary of the Invention
[0004] In view of the shortcomings of the existing technology, the present invention provides a parts defect rate detection robot, control system and method, which solves the problem of low efficiency of traditional parts quality control methods.
[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a parts defective rate detection robot, comprising a support leg, a telescopic leg, and a base, the upper outer wall of the support leg is provided with a conveyor belt, the left outer wall of the support leg is provided with a finished product frame, the rear outer wall of the support leg is fixedly connected with an adjustment frame, the upper outer wall of the adjustment frame is slidably connected with a clamping mechanical arm, the lower outer wall of the adjustment frame is provided with a scrap frame, the upper surface of the telescopic leg is fixedly connected with a detection platform, the upper surface of the detection platform is fixedly connected with a laser rangefinder, the lower surface of the detection platform is fixedly connected with a pressure tester, the upper surface of the base is fixedly connected with a detection mechanical arm, the outer wall of the detection mechanical arm is fixedly connected with a camera, and the upper surface of the detection mechanical arm is fixedly connected with a light source.
[0006] Preferably, a robot control system for detecting defective parts rate includes a system control module, a data processing module, and a user interface module. The system control module is the core of the entire detection system and is responsible for coordinating the work of the robot and each detection module. The data processing module is responsible for collecting, analyzing and storing detection data, identifying defective products through machine learning algorithms, calculating the defective rate, and generating detection reports. The user interface module provides an operation interface, through which users can view the detection results in real time, control the system operation, query historical data, and generate reports.
[0007] Preferably, the system control module includes a robot control unit, a detection control unit, a data processing unit, and a user interface management unit. The robot control unit uses CAD drawings and production line layouts to plan the motion trajectory of the robotic arm so that the trajectory avoids obstacles and optimizes the path to reduce picking and handling time, and controls the servo motor of the robotic arm through PLC to enable it to have precise positioning and smooth movement, monitors the speed and acceleration of the robotic arm in real time, and manages the end effector's grasping of parts, adjusting angles, and precise placement operations. It adjusts the grasping force and grasping method according to the shape and material of the parts to avoid damage to the parts. The detection control unit generates a detection task queue based on the production plan and detection requirements, and reasonably schedules the detection tasks. The task scheduling system monitors the status of each detection module in real time, dynamically adjusts task allocation, and manages the workflow of visual inspection, dimensional inspection, and functional inspection to ensure that each detection module runs efficiently in sequence, sets detection priority, gives priority to key parts, and monitors various parameters in the detection process in real time. The various parameters include detection time and detection accuracy. The detection strategy is dynamically adjusted according to the detection results and parameter changes. The detection strategy includes adjusting the brightness of the light source and recalibrating the measuring equipment.
[0008] Preferably, the data processing unit collects data generated by the visual inspection system, size inspection system and function inspection system in real time through sensors and interface modules, and preprocesses the data. The preprocessing includes noise filtering, data standardization, and using machine learning algorithms to analyze the data, train models to identify defective and qualified products, analyze inspection data, generate statistical reports and trend analysis, provide insights into production quality, and finally store the inspection results in a database. The database sets a backup mechanism to back up data regularly to prevent data loss. The user interface management unit provides an operation interface, and users can quickly understand the system status and inspection results, and display the inspection results, defective rate statistics and system status in real time, and provide a variety of data visualization methods. The visualization methods include charts and graphics, providing system configuration, fault diagnosis and maintenance functions, and users can adjust inspection parameters and calibrate equipment through the interface.
[0009] Preferably, the data processing module includes a data acquisition unit, a data analysis unit, and a report generation unit. The data acquisition unit collects data from the laser rangefinder, the pressure tester, and the camera in real time, including image data, dimension data, and functional test data, and preprocesses the data. The preprocessing includes noise filtering and data standardization. Visual inspection data: Get images from the camera and transfer them to the computer through the image acquisition card. Dimension detection data: Get dimension data from laser rangefinder or coordinate measuring machine and transmit it to computer via wired or wireless mode. Functional test data: Get test data from the pressure tester or electrical performance tester and transmit it to the computer via wired or wireless means.
[0010] Preferably, the data analysis unit uses a machine learning algorithm to analyze the data and train a model to identify defective and qualified products. The algorithm includes a decision tree, a support vector machine, and a neural network. The best algorithm is selected according to the specific application. Data analysis process: Data preprocessing: preprocessing the collected data, including data cleaning and normalization; Feature extraction: Extract key features from preprocessed data, including dimensional deviations and surface defects; Model training: Use the extracted features to train the machine learning model and build a defective product identification model; Model validation: Use the validation set to validate the model, adjust model parameters, and improve recognition accuracy; Data analysis: Use trained models to analyze new data, identify defective and qualified products, and generate statistical reports and trend analysis.
[0011] Preferably, the report generating unit generates a detailed test report based on the test data, including defect rate statistics and defect analysis information, and provides a report export function, supporting PDF and Excel formats for easy sharing and archiving; Report generation process: Data aggregation: aggregate the data of each detection module to generate comprehensive detection data; Report writing: Write detailed test reports based on test data, including defect rate statistics, defect analysis, and test trends; Report export: Provides report export function in multiple formats. Users can export reports in PDF and Excel formats according to their needs; Report archiving: The generated test reports are archived, and users can query historical reports through the interface.
[0012] Preferably, the user interface module includes a test result display unit, a system control unit, and a data query unit. The test result display unit is used to display the results of the parts currently tested in real time, distinguish between defective and qualified products, and provide a statistical chart of the defective rate to intuitively display the production quality situation; Test result display process: Data acquisition: obtaining real-time detection result data from the data processing unit; Data display: Display the test result data on the user interface in the form of charts and text; Data update: The displayed data is updated in real time so that users can see the latest test results.
[0013] Preferably, the system control unit is used to provide a switching function between manual and automatic operation modes, adjust the system working mode as needed, and provide system start, stop and reset buttons to control the system operation status, and provide an emergency stop function to deal with emergencies; System control flow: Mode switching: select manual or automatic operation mode through the interface; System operation: Control the start, stop and reset operations of the system through the interface; Emergency stop: Provide an emergency stop button to immediately stop the system in an emergency; The data query unit provides historical inspection data query function, provides the function of retrieving data by time, batch, and part number conditions, and supports the generation and export of inspection reports to facilitate quality management and production improvement. Finally, it provides data visualization function and generates various statistical charts to help users analyze production quality trends; Data query process: Query condition input: The user enters the query conditions on the interface, which include time range, batch number, and part number; Data retrieval: The system retrieves relevant test data from the database based on the query conditions entered by the user; Data display: Display the retrieved data on the user interface in the form of charts and text; Report generation: Choose whether to generate and export the test report, and support report export in multiple formats.
[0014] Preferably, a detection method for a parts defective rate detection robot control system includes the following specific steps: S1: Initialization. After the system starts, it automatically performs self-tests, including checks on the robotic arm, end effector, and sensors. The user enters and adjusts parameters for part specifications, test standards, and test sequence through the interface. After the self-test and parameter settings are completed, the system enters standby mode and is ready to begin testing. S2: Part identification and positioning: The robotic arm picks up the part from the production line or silo according to the set path. The end effector performs preliminary positioning on the part to confirm that it is in the correct position. The part enters the visual inspection area, and the camera captures the part image. Based on the image processing results, the position and angle of the part are adjusted. S3: Inspection process: The camera captures the image of the part, the image processing algorithm analyzes the image, identifies surface defects, and transmits the inspection results to the control system, which records the inspection data. The laser rangefinder or three-dimensional coordinate measuring machine measures the key dimensions of the part to ensure that they are within the tolerance range. The measurement data is transmitted to the control system, which records the inspection data. The pressure tester performs a withstand voltage test on the part. The electrical performance tester is selected to test the electrical parameters. The functional simulator is selected to simulate the working environment for functional testing. The test data is transmitted to the control system, which records the inspection data. S4: Data collection and analysis: The robot transmits the collected data to the control system, which stores the detection data in the database. The data processing unit uses machine learning algorithms to analyze the data, identify defective and qualified products, calculate the defective rate based on the analysis results, and store the results in the database. S5: Result output: The user interface displays the results of the currently tested parts in real time, including the classification of defective and qualified parts. The test results and defective rate calculation results are stored in the database. The system generates a detailed test report based on the test data, and the user can view and export the report through the interface. S6: Processing of defective products. The system automatically classifies defective products and qualified products based on the test results, marks the defective products as defective, and guides them to the designated location for further processing. According to corporate standards, defective products may be retested, returned for repair, or directly scrapped. After the processing is completed, the processing results and process of the defective products are recorded in the database.
[0015] The present invention provides a robot, control system, and method for detecting defective parts. It has the following beneficial effects: 1. The present invention can continuously and efficiently perform parts inspection through the robot body, reducing the downtime of the production line. The automated system quickly identifies and processes defective products, preventing them from flowing into the next production link, thereby reducing rework and waste and achieving the effect of improving the production efficiency of parts.
[0016] 2. The present invention can collect and analyze test data in real time through the data processing unit, provide instant defective rate statistics and quality analysis reports, and the user interface provides powerful data query and traceability functions. Users can easily query historical test data and generate reports to help with quality traceability and improvement, thereby achieving the effect of improving data management and analysis capabilities.
[0017] 3. The present invention integrates multiple detection technologies, including visual inspection, dimensional inspection and functional inspection, through the system to ensure comprehensive quality control of parts. The system can detect part defects in the early stages of production, correct and handle them in a timely manner, reduce the production of defective products, and thus achieve the effect of enhancing product quality control.
[0018] 4. The present invention can eliminate subjective errors in manual inspection through the visual inspection system, size inspection system and function inspection system. The control system and data processing unit can calibrate the inspection equipment in real time to ensure the accuracy of the inspection results, thereby achieving the effect of improving the inspection accuracy and consistency of parts. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] Figure 1 A three-dimensional diagram of a parts defective rate detection robot according to the present invention; Figure 2 Schematic diagram of the detection platform of the present invention; Figure 3 Schematic diagram of the detection robot arm of the present invention; Figure 4 This is a schematic diagram of the control system architecture of a parts defective rate detection robot of the present invention; Figure 5 This is a schematic diagram of the system control module architecture of the present invention; Figure 6 This is a schematic diagram of the data processing module architecture of the present invention; Figure 7 Schematic diagram of the user interface module architecture of the present invention.
[0020] Among them, 1. Support legs; 2. Conveyor belt; 3. Finished product frame; 4. Adjustment frame; 5. Clamping robot arm; 6. Scrap frame; 7. Telescopic legs; 8. Testing table; 9. Laser rangefinder; 10. Pressure tester; 11. Base; 12. Testing robot arm; 13. Camera; 14. Light source. DETAILED DESCRIPTION
[0021] The following will clearly and completely describe the technical solution of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.
[0022] Please see the attached Figure 1 - Attachment Figure 7An embodiment of the present invention provides a robot for inspecting defective parts rate, comprising a support leg 1, a telescopic leg 7, and a base 11. A conveyor belt 2 is provided on the upper outer wall of the support leg 1, a finished product frame 3 is provided on the left outer wall of the support leg 1, an adjustment frame 4 is fixedly connected to the rear outer wall of the support leg 1, a clamping mechanical arm 5 is slidably connected to the upper outer wall of the adjustment frame 4, a scrap frame 6 is provided on the lower outer wall of the adjustment frame 4, an inspection platform 8 is fixedly connected to the upper surface of the telescopic leg 7, a laser rangefinder 9 is fixedly connected to the upper surface of the inspection platform 8, a pressure tester 10 is fixedly connected to the lower surface of the inspection platform 8, an inspection mechanical arm 12 is fixedly connected to the upper surface of the base 11, a camera 13 is fixedly connected to the outer wall of the inspection mechanical arm 12, and a light source 14 is fixedly connected to the upper surface of the inspection mechanical arm 12; Specifically, the support leg 1 is used to support the conveyor belt 2, the conveyor belt 2 is used to transport the finished product frame 3 and cooperate with other production steps, the finished product frame 3 is used to hold parts that have passed the inspection, the adjustment frame 4 is used to support the clamping robot arm 5 for sliding adjustment, the clamping robot arm 5 is used to grab the parts to be inspected and distinguish the parts that have completed the inspection, the scrap frame 6 is used to hold parts that have failed the inspection, the telescopic leg 7 is used to adjust the height of the inspection table 8, the parts to be inspected grabbed by the clamping robot arm 5 are placed on the upper surface of the inspection table 8, the laser rangefinder 9, the pressure tester 10, the inspection robot arm 12, and the camera 13 are used to detect the parts to be inspected on the upper surface of the inspection table 8, and the light source 14 is used to provide sufficient light for part inspection.
[0023] A robot control system for detecting defective parts rate includes a system control module, a data processing module, and a user interface module. The system control module is the core of the entire detection system and is responsible for coordinating the work of the robot and each detection module. The data processing module is responsible for collecting, analyzing and storing detection data, identifying defective parts through machine learning algorithms, calculating the defective rate, and generating detection reports. The user interface module provides an operation interface through which users can view detection results in real time, control system operation, query historical data, and generate reports.
[0024] The system control module includes a robot control unit, a detection control unit, a data processing unit, and a user interface management unit. The robot control unit uses CAD drawings and production line layouts to plan the motion trajectory of the robotic arm, so that the trajectory avoids obstacles and optimizes the path to reduce picking and handling time. It controls the servo motor of the robotic arm through PLC to enable precise positioning and smooth movement, monitors the speed and acceleration of the robotic arm in real time, and manages the end effector's grasping of parts, adjusting angles, and precise placement operations. It adjusts the grasping force and grasping method according to the shape and material of the parts to avoid damage to the parts. The detection control unit generates a detection task queue based on the production plan and detection requirements, and schedules detection tasks reasonably. The task scheduling system monitors the status of each detection module in real time, dynamically adjusts task allocation, and manages the workflow of visual inspection, dimensional inspection, and functional inspection to ensure that each detection module runs efficiently in sequence, sets detection priorities, gives priority to key parts, and monitors various parameters in the detection process in real time. The parameters include detection time and detection accuracy. The detection strategy is dynamically adjusted according to the detection results and parameter changes. The detection strategy includes adjusting the brightness of the light source and recalibrating the measuring equipment.
[0025] The data processing unit uses sensors and interface modules to collect data generated by the visual inspection system, dimensional inspection system and functional inspection system in real time, and preprocesses the data. The preprocessing includes noise filtering, data standardization, and the use of machine learning algorithms to analyze the data, train models to identify defective and qualified products, analyze inspection data, generate statistical reports and trend analysis, provide insights into production quality, and finally store the inspection results in the database. The database sets a backup mechanism to back up data regularly to prevent data loss. The user interface management unit provides an operation interface, so that users can quickly understand the system status and inspection results, and display the inspection results, defective rate statistics and system status in real time. It provides a variety of data visualization methods, including charts and graphics, and provides system configuration, fault diagnosis and maintenance functions. Users can adjust inspection parameters and calibrate equipment through the interface.
[0026] The data processing module includes a data acquisition unit, a data analysis unit, and a report generation unit. The data acquisition unit collects data from the laser rangefinder 9, the pressure tester 10, and the camera 13 in real time, including image data, dimension data, and functional test data, and preprocesses the data. The preprocessing includes noise filtering and data standardization. Visual inspection data: Get images from the camera and transfer them to the computer through the image acquisition card. Dimension detection data: Get dimension data from laser rangefinder or coordinate measuring machine and transmit it to computer via wired or wireless mode. Functional test data: Get test data from the pressure tester or electrical performance tester and transmit it to the computer via wired or wireless means.
[0027] The data analysis unit uses machine learning algorithms to analyze data and train models to identify defective and qualified products. Algorithms include decision trees, support vector machines, and neural networks. The best algorithm is selected based on the specific application. Data analysis process: Data preprocessing: preprocess the collected data, including data cleaning and normalization; Feature extraction: Extract key features from preprocessed data, including dimensional deviations and surface defects; Model training: Use the extracted features to train the machine learning model and build a defective product identification model; Model validation: Use the validation set to validate the model, adjust model parameters, and improve recognition accuracy; Data analysis: Use trained models to analyze new data, identify defective and qualified products, and generate statistical reports and trend analysis.
[0028] The report generation unit generates detailed test reports based on the test data, including defect rate statistics and defect analysis information, and provides report export function in PDF and Excel formats for easy sharing and archiving; Report generation process: Data aggregation: aggregate the data of each detection module to generate comprehensive detection data; Report writing: Write detailed test reports based on test data, including defect rate statistics, defect analysis, and test trends; Report export: Provides report export function in multiple formats. Users can export reports in PDF and Excel formats according to their needs; Report archiving: The generated test reports are archived, and users can query historical reports through the interface.
[0029] The user interface module includes a test result display unit, a system control unit, and a data query unit. The test result display unit is used to display the results of the currently tested parts in real time, distinguish between defective and qualified products, and provide a statistical chart of the defective rate to intuitively display the production quality situation; Test result display process: Data acquisition: obtaining real-time detection result data from the data processing unit; Data display: Display the test result data on the user interface in the form of charts and text; Data update: The displayed data is updated in real time so that users can see the latest test results.
[0030] The system control unit is used to provide the switching function between manual and automatic operation modes, adjust the system working mode as needed, and provide system start, stop and reset buttons to control the system operation status, and provide an emergency stop function to deal with emergencies; System control flow: Mode switching: select manual or automatic operation mode through the interface; System operation: Control the start, stop and reset operations of the system through the interface; Emergency stop: Provide an emergency stop button to immediately stop the system in an emergency; The data query unit provides historical inspection data query function, provides the function of retrieving data by time, batch, and part number conditions, and supports the generation and export of inspection reports to facilitate quality management and production improvement. Finally, it provides data visualization function and generates various statistical charts to help users analyze production quality trends; Data query process: Query condition input: The user enters the query conditions on the interface, including time range, batch number, and part number; Data retrieval: The system retrieves relevant test data from the database based on the query conditions entered by the user; Data display: Display the retrieved data on the user interface in the form of charts and text; Report generation: Choose whether to generate and export the test report, and support report export in multiple formats.
[0031] A detection method for a parts defect rate detection robot control system includes the following specific steps: S1: Initialization: After the system is started, the robot and detection module will perform self-inspection to ensure that all components are operating normally. Users set inspection parameters, part specifications, inspection standards, etc. through the interface.
[0032] After the system is started, it automatically performs self-tests, including checks on the robotic arm, end effector, and sensors. The user enters and adjusts parameters for part specifications, test standards, and test sequence through the interface. After the self-test and parameter settings are completed, the system enters standby mode and is ready to begin testing. S2: Parts identification and positioning: The robot arm picks up the parts from the production line or silo and uses the end effector to perform preliminary positioning. The part enters the recognition area of the visual inspection system, the camera captures the part image, and makes positioning adjustments.
[0033] The robotic arm picks up parts from the production line or silo according to the set path. The end effector performs preliminary positioning on the part to confirm that the part is in the correct position. The part enters the visual inspection area, and the camera captures the part image. Based on the image processing results, the position and angle of the part are adjusted. S3: Detection process: Visual inspection: High-definition cameras scan the surface of parts, image processing algorithms identify surface defects, and the results are transmitted to the control system. Dimension detection: Laser rangefinder and three-coordinate measuring machine measure the size of parts, and transmit the data to the control system. Functional testing: Pressure testers, electrical performance testers and functional simulators are used to perform functional testing, and the results are transmitted to the control system.
[0034] The camera captures the image of the part, the image processing algorithm analyzes the image, identifies surface defects, and transmits the test results to the control system, which records the test data. A laser rangefinder or a three-dimensional coordinate measuring machine measures the key dimensions of the part to ensure that they are within the tolerance range. The measurement data is transmitted to the control system, which records the test data. The pressure tester performs a withstand voltage test on the part. An electrical performance tester is selected to test electrical parameters. A functional simulator is selected to simulate the working environment for functional testing. The test data is transmitted to the control system, which records the test data. S4: Data collection and analysis: The detection data is transmitted to the data processing unit through the control system for real-time analysis. The data processing unit uses machine learning algorithms to analyze data, calculate the defective rate and identify defective products.
[0035] The robot transmits the collected data to the control system, which stores the detection data in the database. The data processing unit uses machine learning algorithms to analyze the data, identify defective and qualified products, calculate the defective rate based on the analysis results, and store the results in the database. S5: Result output: The user interface displays the test results in real time, and the defective rate calculation results are stored in the database. The system generates a detailed test report, which users can view and export through the interface.
[0036] The user interface displays the results of the currently tested parts in real time, including the classification of defective and qualified parts. The test results and defective rate calculation results are stored in the database. The system generates a detailed test report based on the test data, and the user can view and export the report through the interface. S6: Handling of defective products: The system automatically classifies defective products and qualified products according to the test results and guides the defective products to the designated location. The defective product handling process includes re-inspection, repair or scrapping, and the specific handling method is carried out according to corporate standards.
[0037] The system automatically classifies defective and qualified products based on the test results, marks the defective products as defective, and guides them to a designated location for further processing. According to corporate standards, defective products may be retested, returned for repair, or directly scrapped. After processing is completed, the results and process of the defective product processing are recorded in the database.
[0038] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.
Claims
1. A robot for detecting defective parts, comprising a support leg (1), a telescopic leg (7), and a base (11). It is characterized in that The upper outer wall of the support leg (1) is provided with a conveyor belt (2), the left outer wall of the support leg (1) is provided with a finished product frame (3), the rear outer wall of the support leg (1) is fixedly connected to an adjustment frame (4), the upper outer wall of the adjustment frame (4) is slidably connected to a clamping mechanical arm (5), the lower outer wall of the adjustment frame (4) is provided with a waste frame (6), the upper surface of the telescopic leg (7) is fixedly connected to a detection platform (8), the upper surface of the detection platform (8) is fixedly connected to a laser rangefinder (9), the lower surface of the detection platform (8) is fixedly connected to a pressure tester (10), the upper surface of the base (11) is fixedly connected to a detection mechanical arm (12), the outer wall of the detection mechanical arm (12) is fixedly connected to a camera (13), and the upper surface of the detection mechanical arm (12) is fixedly connected to a light source (14).
2. A parts defective rate detection robot control system, according to the parts defective rate detection robot of claim 1, It is characterized in that It includes a system control module, a data processing module, and a user interface module. The system control module is the core of the entire detection system and is responsible for coordinating the work of the robot and each detection module. The data processing module is responsible for collecting, analyzing and storing detection data, identifying defective products through machine learning algorithms, calculating the defective rate, and generating detection reports. The user interface module provides an operation interface through which users can view detection results in real time, control system operation, query historical data, and generate reports.
3. A robot control system for detecting defective parts according to claim 2, It is characterized in that The system control module includes a robot control unit, a detection control unit, a data processing unit, and a user interface management unit. The robot control unit uses CAD drawings and production line layouts to plan the motion trajectory of the robot arm so that the trajectory avoids obstacles and optimizes the path to reduce the picking and handling time, and controls the servo motor of the robot arm through PLC to enable it to have precise positioning and smooth movement, monitors the speed and acceleration of the robot arm in real time, and manages the end effector's grasping of parts, adjusting angles, and precise placement operations. According to the shape and material of the parts, the grasping force and grasping method are adjusted to avoid damage to the parts. The detection control unit generates a detection task queue according to the production plan and detection requirements, and reasonably schedules the detection tasks. The task scheduling system monitors the status of each detection module in real time, dynamically adjusts task allocation, and manages the workflow of visual detection, size detection, and functional detection to ensure that each detection module runs efficiently in sequence, sets detection priorities, and gives priority to the detection of key parts, and monitors various parameters in the detection process in real time. The various parameters include detection time and detection accuracy. According to the detection results and parameter changes, the detection strategy is dynamically adjusted. The detection strategy includes adjusting the brightness of the light source and recalibrating the measuring equipment.
4. A robot control system for detecting defective parts according to claim 3, It is characterized in that The data processing unit collects data generated by the visual inspection system, size inspection system and function inspection system in real time through sensors and interface modules, and pre-processes the data. The pre-processing includes noise filtering, data standardization, and using machine learning algorithms to analyze the data, train models to identify defective and qualified products, analyze inspection data, generate statistical reports and trend analysis, provide insights into production quality, and finally store the inspection results in a database. The database sets a backup mechanism to back up data regularly to prevent data loss. The user interface management unit provides an operation interface, and the user can quickly understand the system status and inspection results, and display the inspection results, defective rate statistics and system status in real time, and provide a variety of data visualization methods. The visualization methods include charts and graphics, provide system configuration, fault diagnosis and maintenance functions, and the user can adjust the inspection parameters and calibrate the equipment through the interface.
5. A robot control system for detecting defective parts according to claim 2, It is characterized in that The data processing module comprises a data acquisition unit, a data analysis unit and a report generation unit. The data acquisition unit acquires data from a laser rangefinder (9), a pressure tester (10) and a camera (13) in real time, including image data, dimension data and functional test data, and performs preprocessing on the data. The preprocessing includes noise filtering and data standardization. Visual inspection data: Get images from the camera and transfer them to the computer through the image acquisition card. Dimension detection data: Get dimension data from laser rangefinder or coordinate measuring machine and transmit it to computer via wired or wireless method. Functional test data: Get test data from pressure tester or electrical performance tester and transmit it to computer via wired or wireless means.
6. A robot control system for detecting defective parts according to claim 5, It is characterized in that The data analysis unit uses a machine learning algorithm to analyze the data and train a model to identify defective and qualified products. The algorithm includes a decision tree, a support vector machine, and a neural network. The best algorithm is selected according to the specific application. Data analysis process: Data preprocessing: preprocessing the collected data, including data cleaning and normalization; Feature extraction: extract key features from preprocessed data, including dimensional deviation and surface defects; Model training: Use the extracted features to train the machine learning model and build a defective product identification model; Model verification: Use the verification set to verify the model, adjust the model parameters, and improve the recognition accuracy; Data analysis: Use trained models to analyze new data, identify defective and qualified products, and generate statistical reports and trend analysis.
7. A robot control system for detecting defective parts according to claim 5, It is characterized in that The report generation unit generates a detailed test report based on the test data, including defect rate statistics and defect analysis information, and provides a report export function, supporting PDF and Excel formats for easy sharing and archiving; Report generation process: Data aggregation: Aggregate the data of each detection module to generate comprehensive detection data; Report writing: Write detailed test reports based on test data, including defect rate statistics, defect analysis, and test trends; Report export: Provides report export functions in multiple formats. Users can export reports in PDF and Excel formats as required; Report archiving: The generated test reports are archived, and users can query historical reports through the interface.
8. A robot control system for detecting defective parts according to claim 2, It is characterized in that The user interface module includes a test result display unit, a system control unit, and a data query unit. The test result display unit is used to display the results of the parts currently tested in real time, distinguish between defective and qualified products, and provide a statistical chart of the defective rate to intuitively display the production quality situation; Test result display process: Data acquisition: obtaining real-time detection result data from the data processing unit; Data display: Display the test result data on the user interface in the form of charts and texts; Data update: The displayed data is updated in real time so that users can see the latest test results.
9. A robot control system for detecting defective parts according to claim 8, It is characterized in that The system control unit is used to provide a switching function between manual and automatic operation modes, adjust the system working mode as needed, and provide system start, stop and reset buttons to control the system operating status, and provide an emergency stop function to deal with emergencies; System control flow: Mode switching: select manual or automatic operation mode through the interface; System operation: Control the start, stop and reset operations of the system through the interface; Emergency stop: Provide an emergency stop button to immediately stop the system in an emergency; The data query unit provides historical inspection data query function, provides data retrieval function by time, batch, part number condition, and supports the generation and export of inspection reports to facilitate quality management and production improvement, and finally provides data visualization function to generate various statistical charts to help users analyze production quality trends; Data query process: Query condition input: The user enters the query condition on the interface, and the query condition includes time range, batch number, and part number; Data retrieval: The system retrieves relevant test data from the database based on the query conditions entered by the user; Data display: Display the retrieved data on the user interface in the form of charts and texts; Report generation: Choose whether to generate and export the test report. Report export in multiple formats is supported.
10. A detection method for a parts defective rate detection robot control system, applied to a parts defective rate detection robot control system as claimed in any one of claims 2 to 9, It is characterized in that The specific steps include: S1: Initialization. After the system is started, it automatically performs self-tests, including the inspection of the robot arm, end effector, and sensor. The user inputs and adjusts the parameters of part specifications, inspection standards, and inspection sequence through the interface. After the self-test and parameter setting are completed, the system enters the standby state and is ready to start the inspection; S2: Parts identification and positioning: The robot arm picks up parts from the production line or silo according to the set path. The end effector performs preliminary positioning of the parts to confirm that the parts are in the correct position. The parts enter the visual inspection area, and the camera captures the part image. Based on the image processing results, the position and angle of the parts are adjusted. S3: Inspection process, the camera captures the image of the part, the image processing algorithm analyzes the image, identifies surface defects, and transmits the inspection results to the control system, which records the inspection data. The laser rangefinder or the three-dimensional coordinate measuring machine measures the key dimensions of the part to ensure that it is within the tolerance range. The measurement data is transmitted to the control system, which records the inspection data. The pressure tester performs a withstand voltage test on the part, the electrical performance tester is selected to test the electrical parameters, and the functional simulator is selected to simulate the working environment for functional testing. The test data is transmitted to the control system, and the control system records the inspection data; S4: Data collection and analysis. The robot transmits the collected data to the control system. The control system stores the detection data in the database. The data processing unit uses machine learning algorithms to analyze the data, identify defective and qualified products, calculate the defective rate based on the analysis results, and store the results in the database. S5: Result output: the user interface displays the results of the parts currently being tested in real time, including the classification of defective and qualified products. The test results and defective rate calculation results are stored in the database. The system generates a detailed test report based on the test data, and the user can view and export the report through the interface. S6: Processing of defective products. The system automatically classifies defective products and qualified products according to the test results, marks the defective products as defective products, and guides them to the designated location to wait for further processing. According to corporate standards, defective products may be re-tested, returned for repair, or directly scrapped. After the processing is completed, the processing results and process of the defective products are recorded in the database.
Citation Information
Patent Citations
Product detection method based on machine vision
CN105817430A
Automobile part precise dimension detection tooling
CN108775866A
Flexible detection and analysis system for casting key surfaces and internal defects
CN109772724A
Lightning protection insulator performance detection device and method
CN115877148A
Multi-machine joint detection system and method for extracted motor stator slot wedge
CN117782196A
