A device defect detection system based on visual robot

By building a device defect and robot status assessment model, the equipment defect level and status assessment are realized, and the problem of improper matching of equipment defect detection and repair in the existing technology is solved, the repair efficiency and resource utilization are improved, and the system stability and reliability are improved. .

CN118278653BActive Publication Date: 2024-11-12YIWEISI INTELLIGENT AUTOMATION EQUIP WUXI CO LTD
View PDF 12 Cites 0 Cited by

Patent Information

Application Number
CN202410265675.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-03-08
Publication Date
2024-11-12
Estimated Expiration
2044-03-08

AI Technical Summary

Technical Problem

The existing equipment defect detection system cannot match the corresponding robot repair operations according to the equipment defect level, resulting in an increase in repair time or wasted resources, and it is unable to effectively adapt to changes in equipment defects and robot status.

Method used

A equipment defect detection system based on visual robots was designed, including data acquisition module, defect level assessment module, robot status assessment module and intelligent matching module. By constructing defect level and status assessment models, an evaluation index is generated, and a rating is performed. The intelligent matching module determines the best robot for repair work.

Benefits of technology

Optimize resource allocation, improve repair efficiency and quality, realize automated allocation, improve system stability and reliability, and adapt to various equipment defects and changes in robot status.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118278653B_ABST
    Figure CN118278653B_ABST
Patent Text Reader

Abstract

The present invention discloses an equipment defect detection system based on a visual robot, which specifically relates to the technical field of equipment defect detection, and includes a data acquisition module, a defect grade assessment module, a robot state assessment module, an intelligent matching module, and an early warning module. The system grades the detected equipment defects, constructs a robot state assessment model according to the acquired robot state data, generates a robot state assessment index, compares the robot state assessment index with a preset robot state assessment index stage threshold, grades the existing robot operation state, and matches the best robot for repair work for equipment defects of different levels through the intelligent matching module, so as to avoid the situation that the equipment defect degree is high but the robot equipment state is poor, which is helpful to optimize resource allocation, can better adapt to various equipment defects and changes in robot state, and improve the stability and reliability of the system.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of equipment defect detection, and more specifically, to an equipment defect detection system based on a visual robot. Background Art

[0002] With the rapid development of industrial manufacturing, the requirements for equipment quality are getting higher and higher, and defect detection has become an important link in the production process. The equipment defect detection system based on visual robots refers to the use of computer vision technology to detect defects, errors or anomalies on equipment or products, and control the robot to repair the equipment defects based on the detected defect information.

[0003] In the current equipment defect detection, there is a lack of assessment of the equipment defect level, which makes it impossible to match the corresponding robot according to the equipment defect level to perform repair operations on it. When the equipment defect level is high but the robot's equipment condition is poor, the robot may malfunction frequently when repairing the equipment defect, increasing the repair time and making it impossible to repair it in one go. When the equipment defect level is low but the robot's equipment condition is high, it may lead to excessive waste of resources.

[0004] In order to solve the above defects, a technical solution is now provided. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an equipment defect detection system based on a visual robot to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] An equipment defect detection system based on a visual robot includes a data acquisition module, a defect level assessment module, a robot state assessment module, an intelligent matching module, and an early warning module, wherein each module is connected through a signal;

[0008] The data acquisition module is used to collect equipment defect data and robot status data. After the data are collected, the equipment defect data and the robot status data are transmitted to the defect level assessment module and the robot status assessment module respectively.

[0009] The defect grade assessment module is used to construct a defect grade assessment model based on equipment defect data, generate an equipment defect grade assessment index, and grade equipment defects based on the equipment defect grade assessment coefficient;

[0010] The robot state assessment module is used to construct a robot state assessment model based on the robot state data, generate a robot state assessment index, and assess the existing robot state level based on the robot state assessment index;

[0011] An intelligent matching module is used to customize matching rules according to the equipment defect level and robot status level, and determine the robot used to repair the equipment defect based on the matching results;

[0012] The early warning module is used to send out early warning signals to remind staff to perform manual matching.

[0013] In a preferred embodiment, the equipment defect data includes corrosion coverage data and crack depth data;

[0014] The corrosion coverage data include the corrosion area fluctuation rate, and the crack depth data include the crack depth change rate;

[0015] The corrosion area fluctuation rate and crack depth change rate are marked as AF and KO, respectively.

[0016] In a preferred embodiment, the calculation expression of the corrosion area fluctuation rate is as follows: Where [t x ,t y ] indicates the time period when the corrosion area on the equipment surface changes. represents the rate of change of corrosion area with time, T(t) represents the ambient temperature at time t, and H(t) represents the ambient humidity at time t;

[0017] The calculation expression of crack depth change rate is as follows: Where ΔD represents the change in crack depth, and Δt represents the change in the time it takes for the crack to change.

[0018] In a preferred embodiment, the equipment defect grade assessment index is calculated by a formula according to the corrosion area fluctuation rate and the crack depth change rate;

[0019] Compare the equipment defect grade assessment index with the preset equipment defect grade assessment index stage threshold to grade the existing equipment defects;

[0020] The stage threshold of the equipment defect level assessment index includes a first threshold of the equipment defect level assessment index and a second threshold of the equipment defect level assessment index, and the second threshold of the equipment defect level assessment index is greater than the first threshold of the equipment defect level assessment index;

[0021] If the equipment defect level assessment index is greater than or equal to the second threshold value of the equipment defect level assessment index, a first-level defect level is generated;

[0022] If the equipment defect level assessment index is less than the second threshold value of the equipment defect level assessment index, and the equipment defect level assessment index is greater than or equal to the first threshold value of the equipment defect level assessment index, a secondary defect level is generated;

[0023] If the equipment defect level assessment index is less than or equal to the first threshold value of the equipment defect level assessment index, a third level defect level is generated.

[0024] In a preferred embodiment, the robot status data includes sensitivity data, response data, and power data;

[0025] The sensitivity data includes the torque application abnormality coefficient, the response data includes the abnormal response duration coefficient, and the power data includes the current remaining power;

[0026] The torque application abnormality coefficient, abnormal response time coefficient, and current remaining power are marked as QE, FA, and FI, respectively.

[0027] In a preferred embodiment, the logic for obtaining the torque application abnormality coefficient is as follows:

[0028] During the time period when the robot is performing repair work, multiple equidistant monitoring points are set up, and the actual torque of multiple monitoring points is obtained in real time through the torque sensor, which is marked as NJ. i , i={1,2,...,k}, k is a positive integer, i represents the order number of different monitoring points;

[0029] The actual torque obtained is compared with the preset applied torque. When the actual torque is not equal to the preset applied torque, it is marked as abnormal torque, that is, j={1,2,...,m}, m is a positive integer, j represents the order number of abnormal torque; the torque application abnormal coefficient is calculated according to the abnormal torque, and the expression is as follows

[0030] The logic for obtaining the abnormal response time coefficient is as follows:

[0031] Record the time when the command is sent: record the timestamp when the controller sends the command, and mark it as the time when the command is sent;

[0032] Record the command execution time: When the robot receives the command and executes the task, the timestamp at this time is recorded and marked as the command execution time;

[0033] Calculate the response time: The response time is equal to the instruction execution time minus the instruction sending time;

[0034] Set the critical threshold of response time and mark it as LJ;

[0035] The abnormal response time coefficient is calculated based on the response time and the critical response time threshold. The expression is as follows Wherein XY represents the response time, v={1,2,...,n}, n is a positive integer, and v represents the sequence number whose response time is greater than or equal to the critical threshold of the response time.

[0036] In a preferred embodiment, the robot state assessment index is calculated by a formula according to the torque application abnormality coefficient, the abnormal response time coefficient, and the current remaining power;

[0037] Compare the robot state assessment index with the preset robot state assessment index stage threshold, and grade the existing robot operation state;

[0038] The robot state assessment index threshold includes a robot state assessment index first threshold and a robot state assessment index second threshold, and the robot state assessment index second threshold is greater than the robot state assessment index first threshold;

[0039] If the robot state assessment index is greater than or equal to the second threshold value of the robot state assessment index, a first-level state level is generated;

[0040] If the robot state assessment index is less than the second threshold value of the robot state assessment index, and the robot state assessment index is greater than or equal to the first threshold value of the robot state assessment index, a secondary state level is generated;

[0041] If the robot state assessment index is less than or equal to the first threshold value of the robot state assessment index, a three-level state grade is generated.

[0042] In a preferred embodiment, defect level intervals are divided according to the equipment defect level, and the equipment defects in each level interval are sorted from large to small according to the equipment defect level assessment index, and an equipment defect ranking table for each level interval is generated;

[0043] Start matching from the first device defect in the device defect sorting table;

[0044] Set the matching range and calculate the matching range based on the location of the equipment defect;

[0045] Prioritize robots of corresponding levels within the matching range;

[0046] When there are multiple robots of corresponding levels within the matching range, they are sorted from large to small according to the robot status assessment index, and a robot ranking table is generated. The first robot is used to repair the current equipment defect;

[0047] When no robot of the corresponding level is found within the matching range, the upward compatibility strategy is enabled;

[0048] Check whether there are existing equipment defects in the equipment defect sorting table of the previous level interval. If there are no equipment defects, select the last robot in the robot sorting table of the previous level to repair the current equipment defects. If there are equipment defects, the early warning module will issue an early warning signal to remind the staff to perform manual matching.

[0049] Technical effects and advantages of the present invention:

[0050] 1. The present invention rates the detected equipment defects, builds a robot state assessment model according to the acquired robot state data, generates a robot state assessment index, compares the robot state assessment index with a preset robot state assessment index stage threshold, rates the existing robot operation state, and matches the best robot for repair work for equipment defects of different levels through an intelligent matching module, thereby avoiding the situation where the equipment defect degree is high but the robot equipment state is poor, helping to optimize resource allocation, so that robots in good state are more used to deal with serious equipment defects, improving the efficiency and quality of repair work, realizing automatic allocation of robot repair tasks, being able to better adapt to various equipment defects and changes in robot states, and improving the stability and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0052] Figure 1 This is a schematic diagram of the structure of Example 1 of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Example 1

[0055] The present invention provides Figure 1 The device defect detection system based on a visual robot shown in the figure includes a data acquisition module, a defect level assessment module, a robot state assessment module, an intelligent matching module, and an early warning module, and each module is connected by a signal;

[0056] The data acquisition module is used to collect equipment defect data and robot status data. After the data are collected, the equipment defect data and the robot status data are transmitted to the defect level assessment module and the robot status assessment module respectively.

[0057] A data acquisition module, including a sensor unit, a data preprocessing unit, and a feature extraction unit;

[0058] A sensor unit, including a plurality of sensors and a camera device for acquiring device surface images and additional geometric information as well as operation status data of the robot;

[0059] The data preprocessing unit is used to preprocess the acquired relevant data, including the following steps:

[0060] Sensor data: including missing value processing, outlier processing, data cleaning, and data standardization;

[0061] Missing value processing: Detect and process missing values ​​in the data. Missing values ​​may affect the accuracy of the analysis, so appropriate methods are usually required to fill or delete missing values.

[0062] Outlier processing: Detect and process outliers, which may be caused by sensor failure, measurement error, or other reasons. Usually, operations such as deleting or replacing outliers are adopted.

[0063] Data cleaning: Clean the data to ensure its consistency and accuracy, which may include removing duplicates, resolving data format issues, etc.

[0064] Data normalization: Normalize the data to the same scale to eliminate unit differences or value range differences between different sensors. This can be achieved through Mini-Max normalization or Z-score normalization.

[0065] Image data: including noise removal, image quality enhancement, and image clarity;

[0066] Noise removal: Use image processing techniques, such as median filtering and Gaussian blur, to remove noise from images. These methods can smooth images, reduce unnecessary pixel jitter or interference, and improve image quality. If there is a specific type of noise in the image, appropriate noise reduction algorithms or filters can be used to eliminate or reduce this noise;

[0067] Image quality enhancement: adjust the contrast, brightness and color balance of the image to enhance the visual effect of the image, which can be achieved through histogram equalization, grayscale stretching, color correction and other methods;

[0068] Image sharpening: Applying sharpening techniques to an image to improve its clarity and detail. This can be achieved by enhancing edges, applying sharpening algorithms, or applying specific image enhancement filters.

[0069] A feature extraction unit extracts data related to equipment defects and data related to the robot's operating status from sensor data and image data;

[0070] The equipment defect data and the robot status data are transmitted to the defect level assessment module and the robot status assessment module respectively;

[0071] The defect grade assessment module is used to construct a defect grade assessment model based on equipment defect data, generate an equipment defect grade assessment index, and grade equipment defects based on the equipment defect grade assessment coefficient;

[0072] Equipment defect data includes corrosion coverage data and crack depth data;

[0073] The corrosion coverage data include the corrosion area fluctuation rate, and the crack depth data include the crack depth change rate;

[0074] The corrosion area fluctuation rate and crack depth change rate are marked as AF and KO, respectively;

[0075] The corrosion coverage data include the corrosion area fluctuation rate, and the crack depth data include the crack depth change rate;

[0076] The corrosion area fluctuation rate is a parameter used to measure the abnormal fluctuation of the corrosion degree of the equipment surface with the change of ambient temperature and humidity. It can be used to quantitatively describe the trend of the corrosion change of the equipment under different environmental conditions. The higher the corrosion area fluctuation rate, the higher the degree of defects on the equipment surface. The greater the fluctuation of the corrosion area, the more difficult it is for the robot to repair it, and thus the higher the defect level of the equipment surface is assessed.

[0077] The calculation expression of the corrosion area fluctuation rate is as follows Where [t x ,t y ] indicates the time period when the corrosion area on the equipment surface changes. represents the rate of change of corrosion area with time, T(t) represents the ambient temperature at time t, and H(t) represents the ambient humidity at time t;

[0078] The corrosion area of ​​the device surface can be obtained by calculating the number of pixels on the device surface where corrosion occurs in the device surface image, and recording the time period when the corrosion changes occur to obtain [t x ,t y ], the ambient temperature and humidity can be obtained in real time through the temperature sensor and humidity sensor;

[0079] The crack depth change rate is used to measure the rate at which cracks on the equipment surface change over time. The higher the crack depth change rate, the more serious the deterioration trend of the cracks on the equipment surface, the more difficult it is for the robot to repair, and the higher the defect level of the equipment surface, that is, the higher the requirements for the robot that needs to perform the repair work;

[0080] The calculation expression of crack depth change rate is as follows: Where ΔD represents the change in crack depth, and Δt represents the change in the time at which the crack changes.

[0081] The crack depth can be monitored in real time by ultrasonic sensors, and the time when the crack depth changes can be recorded;

[0082] According to the corrosion area fluctuation rate and crack depth change rate, a defect grade assessment model is constructed to generate the equipment defect grade assessment index. The formula is as follows: Where TH is the equipment defect rating index, a 1 、a 2 are the proportional coefficients of the corrosion area fluctuation rate and crack depth change rate, respectively, where a 1 >a 2 >0;

[0083] Compare the equipment defect grade assessment index with the preset equipment defect grade assessment index stage threshold to grade the existing equipment defects;

[0084] The stage threshold of the equipment defect level assessment index includes a first threshold of the equipment defect level assessment index and a second threshold of the equipment defect level assessment index, and the second threshold of the equipment defect level assessment index is greater than the first threshold of the equipment defect level assessment index;

[0085] If the equipment defect level assessment index is greater than or equal to the second threshold of the equipment defect level assessment index, it indicates that the degree of damage to the equipment surface is very serious, and a first-level defect level is generated. The robot that needs to be repaired must maintain a higher performance operating state;

[0086] If the equipment defect level assessment index is less than the second threshold value of the equipment defect level assessment index, and the equipment defect level assessment index is greater than or equal to the first threshold value of the equipment defect level assessment index, it indicates that the degree of damage of the defects on the current equipment surface is average and there may be a trend of deterioration, and a secondary defect level is generated. For the robot performing the repair work, its operating performance does not need to be optimal;

[0087] If the equipment defect level assessment index is less than or equal to the first threshold of the equipment defect level assessment index, it indicates that the degree of damage on the surface of the equipment is relatively light, and a third-level defect level is generated. For the repair robot, it is only required to be able to perform simple repair work.

[0088] Transmit the equipment defect information after grade assessment to the intelligent matching module;

[0089] The robot state assessment module is used to construct a robot state assessment model based on the robot state data, generate a robot state assessment index, and assess the existing robot state level based on the robot state assessment index;

[0090] The robot status data includes sensitivity data, response data, and power data;

[0091] The sensitivity data includes the torque application abnormality coefficient, the response data includes the abnormal response duration coefficient, and the power data includes the current remaining power;

[0092] The torque application abnormality coefficient, abnormal response time coefficient, and current remaining power are marked as QE, FA, and FI respectively;

[0093] The torque application abnormality coefficient is used to measure the degree of abnormality of the force applied by the robot's mechanical arm to the surface of the equipment when the robot is performing repair work. The higher the torque application abnormality coefficient, the worse the robot's operating state is, and the greater the probability that the torque (torque) applied to the surface of the equipment will be abnormal, which may cause the defects on the surface of the equipment to further deteriorate. The higher the torque application abnormality coefficient, the worse the stability of the robot's operating state is, and the lower its assessment level is.

[0094] The logic for obtaining the torque application abnormality coefficient is as follows:

[0095] During the time period when the robot is performing repair work, multiple equidistant monitoring points are set up, and the actual torque of multiple monitoring points is obtained in real time through the torque sensor, which is marked as NJ. i , i={1,2,...,k}, k is a positive integer, i represents the order number of different monitoring points;

[0096] The actual torque obtained is compared with the preset applied torque. When the actual torque is not equal to the preset applied torque, it means that the robot has poor sensitivity and its applied torque deviates, which is marked as abnormal torque. j={1,2,...,m}, m is a positive integer, j represents the order number of abnormal torque, when the actual torque is equal to the preset applied torque, it indicates that the sensitivity of the robot is within the normal range; the torque application abnormality coefficient is calculated according to the abnormal torque, and the expression is as follows

[0097] The abnormal response time coefficient is used to measure the degree of abnormality in the time required for the controller to issue a command and the robot to execute the command when the robot is performing repair work. The longer the abnormal response time, the worse the robot's operating status and the lower its assessment level;

[0098] The logic for obtaining the abnormal response time coefficient is as follows:

[0099] Record the time when the command is sent: record the timestamp when the controller sends the command, and mark it as the time when the command is sent;

[0100] Record the command execution time: When the robot receives the command and executes the task, the timestamp at this time is recorded and marked as the command execution time;

[0101] Calculate the response time: The response time is equal to the instruction execution time minus the instruction sending time;

[0102] Set the critical threshold of response time and mark it as LJ;

[0103] The abnormal response time coefficient is calculated based on the response time and the critical response time threshold. The expression is as follows Where XY represents the response time, v = {1, 2, ..., n}, n is a positive integer, and v represents the order number of the response time greater than or equal to the critical threshold of the response time;

[0104] The current remaining power is used to measure the power reserve of the robot's battery or energy system, and is used to evaluate the sustainable working time of the robot in the process of performing tasks. The lower the current remaining power, the lower the robot may not be able to cope with higher-level equipment defects in the subsequent equipment defect repair, and the lower its assessment level;

[0105] The robot status assessment model is constructed based on the torque application abnormality coefficient, abnormal response time coefficient, and current remaining power to generate the robot status assessment index. The formula is as follows: Where JQ is the robot status assessment index, b 1 , b 2 , b 3 are the torque application abnormality coefficient, abnormal response time coefficient, and current remaining power proportional coefficient, respectively, where b 1 >b 2 >b 3 >0;

[0106] Compare the robot state assessment index with the preset robot state assessment index stage threshold, and grade the existing robot operation state;

[0107] The robot state assessment index threshold includes a robot state assessment index first threshold and a robot state assessment index second threshold, and the robot state assessment index second threshold is greater than the robot state assessment index first threshold;

[0108] If the robot status assessment index is greater than or equal to the second threshold value of the robot status assessment index, the robot is in excellent operating condition and can handle the repair work of higher-level equipment defects, generating a first-level status level;

[0109] If the robot status assessment index is less than the second threshold value of the robot status assessment index, and the robot status assessment index is greater than or equal to the first threshold value of the robot status assessment index, it indicates that the robot is in a general operating state and can handle the repair work of general equipment defects, generating a secondary state level;

[0110] If the robot status assessment index is less than or equal to the first threshold of the robot status assessment index, it indicates that the robot is in a poor operating state and can only handle simple repair work, generating a third-level status level;

[0111] The robots that have been graded are transferred to the intelligent matching module;

[0112] An intelligent matching module is used to customize matching rules according to the equipment defect level and robot status level, and determine the robot used to repair the equipment defect based on the matching results;

[0113] Defect level intervals are divided according to the equipment defect level, and the equipment defects in each level interval are sorted from large to small according to the equipment defect level assessment index, and a ranking table of equipment defects in each level interval is generated;

[0114] Start matching from the first device defect in the device defect sorting table;

[0115] It should be noted that the equipment defects in each level range start to be matched at the same time;

[0116] Set the matching range, that is, preset a range radius and calculate the matching range based on the location of the equipment defect;

[0117] Prioritize robots of corresponding levels within the matching range;

[0118] When there are multiple robots of corresponding levels within the matching range, they are sorted from large to small according to the robot status assessment index, and a robot ranking table is generated. The first robot is used to repair the current equipment defect;

[0119] When no robot of the corresponding level is found within the matching range, the upward compatibility strategy is enabled;

[0120] Check whether there are any equipment defects in the equipment defect ranking table of the previous level interval. If there are no equipment defects, select the last robot in the robot ranking table of the previous level to repair the current equipment defects. If there are equipment defects, send out an early warning signal through the early warning module to remind the staff to perform manual matching;

[0121] The present invention rates the detected equipment defects, constructs a robot state assessment model according to the acquired robot state data, generates a robot state assessment index, compares the robot state assessment index with a preset robot state assessment index stage threshold, rates the existing robot operating state, and matches the best robot for repair work for equipment defects of different levels through an intelligent matching module, thereby avoiding the situation where the equipment defect degree is high but the robot equipment state is poor, helping to optimize resource allocation, so that robots in good state are more used to deal with serious equipment defects, improving the efficiency and quality of repair work, realizing automatic allocation of robot repair tasks, being able to better adapt to various equipment defects and changes in robot states, and improving the stability and reliability of the system.

[0122] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0123] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0124] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0125] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0126] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0127] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A device defect detection system based on visual robots, Features: It includes data acquisition module, defect level assessment module, robot status assessment module, intelligent matching module and early warning module, and each module is connected through signals; The data acquisition module is used to collect equipment defect data and robot status data. After the data are collected, the equipment defect data and the robot status data are transmitted to the defect level assessment module and the robot status assessment module respectively. The defect grade assessment module is used to construct a defect grade assessment model based on equipment defect data, generate an equipment defect grade assessment index, and grade equipment defects based on the equipment defect grade assessment coefficient; The robot state assessment module is used to construct a robot state assessment model based on the robot state data, generate a robot state assessment index, and assess the existing robot state level based on the robot state assessment index; An intelligent matching module is used to customize matching rules according to the equipment defect level and robot status level, and determine the robot used to repair the equipment defect based on the matching results; The early warning module is used to send out early warning signals to remind the staff to perform manual matching; Equipment defect data includes corrosion coverage data and crack depth data; The corrosion coverage data include the corrosion area fluctuation rate, and the crack depth data include the crack depth change rate; The corrosion area fluctuation rate and crack depth change rate are marked as AF and KO, respectively; The calculation expression of the corrosion area fluctuation rate is as follows Where [t x ,t y ] indicates the time period when the corrosion area on the equipment surface changes. represents the rate of change of corrosion area with time, T(t) represents the ambient temperature at time t, and H(t) represents the ambient humidity at time t; The calculation expression of crack depth change rate is as follows: Where ΔD represents the change in crack depth, and Δt represents the change in the time at which the crack changes. According to the corrosion area fluctuation rate and crack depth change rate, a defect grade assessment model is constructed to generate the equipment defect grade assessment index. The formula is as follows: Where TH is the equipment defect rating index, a 1 、a 2 are the proportional coefficients of the corrosion area fluctuation rate and crack depth change rate, respectively, where a 1 >a 2 >0; The robot status data includes sensitivity data, response data, and power data; The sensitivity data includes the torque application abnormality coefficient, the response data includes the abnormal response duration coefficient, and the power data includes the current remaining power; The torque application abnormality coefficient, abnormal response time coefficient, and current remaining power are marked as QE, FA, and FI respectively; The logic for obtaining the torque application abnormality coefficient is as follows: During the time period when the robot is performing repair work, multiple equidistant monitoring points are set up, and the actual torque of multiple monitoring points is obtained in real time through the torque sensor, which is marked as NJ. i , i={1,2,...,k}, k is a positive integer, i represents the order number of different monitoring points; The actual torque obtained is compared with the preset applied torque. When the actual torque is not equal to the preset applied torque, it is marked as abnormal torque, that is, m is a positive integer, j represents the order number of the abnormal torque; the torque application abnormal coefficient is calculated according to the abnormal torque, and the expression is as follows The logic for obtaining the abnormal response time coefficient is as follows: Record the time when the command is sent: record the timestamp when the controller sends the command, and mark it as the time when the command is sent; Record the command execution time: When the robot receives the command and executes the task, the timestamp at this time is recorded and marked as the command execution time; Calculate the response time: The response time is equal to the instruction execution time minus the instruction sending time; Set the critical threshold of response time and mark it as LJ; The abnormal response time coefficient is calculated based on the response time and the critical response time threshold. The expression is as follows Where XY represents the response time, v = {1, 2, ..., n}, n is a positive integer, and v represents the order number of the response time greater than or equal to the critical threshold of the response time; The robot status assessment model is constructed based on the torque application abnormality coefficient, abnormal response time coefficient, and current remaining power to generate the robot status assessment index. The formula is as follows: Where JQ is the robot status assessment index, b 1 , b 2 , b 3 are the torque application abnormality coefficient, abnormal response time coefficient, and current remaining power proportional coefficient, respectively, where b 1 >b 2 >b 3 >0.

2. According to claim 1, a device defect detection system based on a visual robot, Features: The equipment defect grade assessment index is calculated by formula based on the corrosion area fluctuation rate and crack depth change rate; Compare the equipment defect grade assessment index with the preset equipment defect grade assessment index stage threshold to grade the existing equipment defects; The stage threshold of the equipment defect level assessment index includes a first threshold of the equipment defect level assessment index and a second threshold of the equipment defect level assessment index, and the second threshold of the equipment defect level assessment index is greater than the first threshold of the equipment defect level assessment index; If the equipment defect level assessment index is greater than or equal to the second threshold value of the equipment defect level assessment index, a first-level defect level is generated; If the equipment defect level assessment index is less than the second threshold value of the equipment defect level assessment index, and the equipment defect level assessment index is greater than or equal to the first threshold value of the equipment defect level assessment index, a secondary defect level is generated; If the equipment defect level assessment index is less than or equal to the first threshold value of the equipment defect level assessment index, a third level defect level is generated.

3. According to claim 1, a device defect detection system based on a visual robot, Features: The robot status assessment index is calculated by formula according to the torque application abnormality coefficient, abnormal response time coefficient, and current remaining power; Compare the robot state assessment index with the preset robot state assessment index stage threshold, and grade the existing robot operation state; The robot state assessment index threshold includes a robot state assessment index first threshold and a robot state assessment index second threshold, and the robot state assessment index second threshold is greater than the robot state assessment index first threshold; If the robot state assessment index is greater than or equal to the second threshold value of the robot state assessment index, a first-level state level is generated; If the robot state assessment index is less than the second threshold value of the robot state assessment index, and the robot state assessment index is greater than or equal to the first threshold value of the robot state assessment index, a secondary state level is generated; If the robot state assessment index is less than or equal to the first threshold value of the robot state assessment index, a three-level state grade is generated.

4. According to claim 1, a device defect detection system based on a visual robot, Features: Defect level intervals are divided according to the equipment defect level, and the equipment defects in each level interval are sorted from large to small according to the equipment defect level assessment index, and a ranking table of equipment defects in each level interval is generated; Start matching from the first device defect in the device defect sorting table; Set the matching range and calculate the matching range based on the location of the equipment defect; Prioritize robots of corresponding levels within the matching range; When there are multiple robots of corresponding levels within the matching range, they are sorted from large to small according to the robot status assessment index, and a robot ranking table is generated. The first robot is used to repair the current equipment defect; When no robot of the corresponding level is found within the matching range, the upward compatibility strategy is enabled; Check whether there are existing equipment defects in the equipment defect sorting table of the previous level interval. If there are no equipment defects, select the last robot in the robot sorting table of the previous level to repair the current equipment defects. If there are equipment defects, the early warning module will issue an early warning signal to remind the staff to perform manual matching.

Citation Information

Patent Citations

  • Task allocation algorithm based on individual capacity in heterogeneous multi-robot system

    CN102831318A

  • Scheduling method and device for service robot

    CN107291078A

  • Power distribution network distribution scheduling duty task automatic division method and system, and computer equipment

    CN111311129A

  • Pipeline defect classification and grading method and system based on image recognition

    CN112669269A

  • Pipeline defect detection method, system and equipment and computer readable storage medium

    CN114140625A