Intelligent identification system and method for underwater equipment detection
By using intelligent identification systems and methods, and employing genetic algorithms and big data analysis, reliable collaborative target robots are selected, solving the problem of inaccurate positioning in underwater equipment detection and achieving rapid and accurate detection of faulty equipment.
Patent Information
- Application Number
- CN202310450209.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-04-25
- Publication Date
- 2026-04-17
AI Technical Summary
Existing underwater equipment detection and identification methods cannot effectively improve the accuracy of robots in locating faulty equipment, which may result in errors in the location of the faulty equipment and make it impossible to quickly reach the location of the faulty equipment.
By combining a search data acquisition module, a data management center, a collaborative target screening module, an equipment search management module, and an equipment detection and identification module, reliable collaborative target robots are selected using genetic algorithms and big data analysis. The positioning fault tolerance range is defined to ensure that the robot accurately reaches the location of the faulty equipment for detection.
This improves the accuracy of underwater robots in locating faulty underwater equipment, saves on positioning and detection costs, and ensures that the robot can quickly and accurately reach the faulty equipment for detection and identification.
Smart Images

Figure CN121878609A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of equipment positioning and detection technology, specifically to an intelligent identification system and method for underwater equipment detection. Background Technology
[0002] The detection, identification, and repair of faulty equipment is an indispensable part of the entire underwater system. Accurate and timely identification of the initiation and evolution of underwater structural cracks is of great significance to the safe operation of marine equipment. However, due to the harsh underwater working environment, high risk, low efficiency, and uncontrollable operation, underwater robots have gradually become an important tool for completing various underwater tasks. However, existing underwater equipment detection and identification methods still have some drawbacks: when underwater equipment malfunctions, underwater robots are needed to go to the malfunction site to detect and identify the faulty point to help repair the faulty equipment. Underwater, the underwater robot needs to search for and locate the faulty equipment to reach the destination. However, due to the robot's own positioning error and the influence of various underwater environmental factors, the location of the faulty equipment may be inaccurate. Existing technologies cannot effectively improve the accuracy of the robot in locating the faulty equipment so as to control the robot to reach the location of the faulty equipment as soon as possible and save detection and identification time.
[0003] Therefore, a smart identification system and method for underwater equipment detection is needed to solve the above problems. Summary of the Invention
[0004] The purpose of this invention is to provide an intelligent identification system and method for underwater equipment detection, so as to solve the problems mentioned in the background art.
[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent identification system for underwater equipment detection, the system comprising: a search data acquisition module, a data management center, a cooperative target screening module, an equipment search management module, and an equipment detection and identification module; The output of the search data acquisition module is connected to the input of the data management center. The output of the data management center is connected to the input of the collaborative target filtering module and the device search management module. The output of the collaborative target filtering module is connected to the input of the device search management module. The output of the device search management module is connected to the input of the device detection and identification module. The search data acquisition module collects data on the underwater robot's search and location of faulty underwater equipment, as well as historical search data, and transmits all collected data to the data management center. All collected data is stored and managed through the data management center. The cooperative target screening module filters out robots that will cooperate with the current underwater robot to search for faulty underwater equipment. The device search and management module controls the cooperative targets to conduct a cooperative search for faulty underwater devices. When the underwater robot searches for and reaches the location of the faulty underwater equipment, the device detection and identification module detects and identifies the faulty equipment.
[0006] Furthermore, the search data acquisition module includes a robot data acquisition unit and a predetermined trajectory acquisition unit; The output terminals of the robot data acquisition unit and the predetermined trajectory acquisition unit are connected to the input terminal of the data management center; The robot data acquisition unit is used to collect the number of underwater robots that are simultaneously searching for different faulty devices with the current underwater robot, the maximum search distance of the underwater robot, the number of times the corresponding underwater robot has previously searched for faulty underwater devices, and the number of times it has successfully searched for faulty underwater devices. The predetermined trajectory acquisition unit is used to acquire predetermined trajectory data of the current underwater robot when it initially locates the faulty device, and to acquire predetermined trajectory data of underwater robots that are simultaneously searching for different faulty devices.
[0007] Furthermore, the collaborative target screening module includes an initial positioning acquisition unit, a relative position analysis unit, and a robot screening unit; The input terminals of the initial positioning acquisition unit and the relative position analysis unit are connected to the output terminal of the data management center, the output terminal of the initial positioning acquisition unit is connected to the input terminal of the relative position analysis unit, and the output terminal of the relative position analysis unit is connected to the input terminal of the robot screening unit. The initial positioning acquisition unit is used to obtain the location information of the faulty equipment initially located by the underwater robot. The relative position analysis unit is used to analyze the straight-line distance between the underwater robot searching for different faulty devices and the location of the faulty device when it moves to the point where the distance to the predetermined trajectory of the current underwater robot when it initially locates the faulty device is the shortest. The straight-line distance is compared with the maximum search distance of the corresponding robot, and robots whose straight-line distance is less than or equal to the maximum search distance are selected. The robot screening unit is used to perform secondary screening of robots based on the shortest distance between the predetermined trajectory of the screened robot and the predetermined trajectory of the current robot, and the straight-line distance between the screened robot and the location of the faulty equipment when it moves to the shortest distance point, and transmits the screening results to the equipment search and management module.
[0008] Furthermore, the device search management module includes a detection data analysis unit, a collaborative target elimination unit, and a collaborative search management unit; The input end of the detection data analysis unit is connected to the output end of the robot screening unit and the data management center, the output end of the detection data analysis unit is connected to the input end of the collaborative target elimination unit, and the output end of the collaborative target elimination unit is connected to the input end of the collaborative search management unit. The detection data analysis unit is used to retrieve data on the number of times the robot selected in the secondary screening has previously searched for underwater faulty equipment and the number of times it has successfully searched for underwater faulty equipment, and to analyze the historical detection success rate of the robot selected in the secondary screening. The collaborative target elimination unit is used to set a success rate threshold, eliminate robots with a historical detection success rate lower than the threshold, and use the remaining robots as collaborative targets. The cooperative search management unit is used to locate the faulty equipment that the current underwater robot needs to search for when the cooperative target moves to the point where the distance to the predetermined trajectory when the current underwater robot initially locates the faulty equipment is the shortest. The unit then obtains the location information and transmits the location information to the equipment detection and identification module.
[0009] Furthermore, the device detection and identification module includes a positioning adjustment reminder unit and a fault detection and identification unit; The input terminal of the positioning adjustment reminder unit is connected to the output terminal of the collaborative search management unit, and the output terminal of the positioning adjustment reminder unit is connected to the input terminal of the fault detection and identification unit. The positioning adjustment reminder unit is used to analyze the location information of the faulty equipment searched by the cooperative target, divide the positioning fault tolerance range according to the location information, and determine whether the location of the faulty equipment initially located by the current underwater robot is within the positioning fault tolerance range: if it is, control the current underwater robot to continue moving towards the initially located faulty equipment location; if it is not, send an alarm signal to remind the user to search for the faulty equipment again and reposition the faulty equipment until the current underwater robot moves to the location of the faulty equipment. The fault detection and identification unit is used to detect and identify the fault in the equipment using a binocular camera after the underwater robot moves to the location of the faulty equipment, and transmit the detection data to the detection terminal.
[0010] A smart identification method for underwater equipment detection includes the following steps: S1: Collect data on the underwater robot's search and location of faulty underwater equipment, as well as historical search data; S2: Select robots that will cooperate with the current underwater robot to search for faulty underwater equipment, and control the cooperative target to cooperate in the search for faulty underwater equipment; S3: Based on the collaborative search results, divide the positioning fault tolerance range, determine whether the location of the faulty equipment initially located by the underwater robot is within the positioning fault tolerance range, and execute step S4; S4: If present, control the current underwater robot to continue moving towards the initially located faulty device; if not, prompt the user to re-search for the faulty device until the current underwater robot moves to the location of the faulty device. S5: When the underwater robot searches for and reaches the location of the faulty underwater equipment, it detects and identifies the faulty part of the equipment.
[0011] Furthermore, in step S1: the number of underwater robots simultaneously searching for different faulty devices with the current underwater robot is collected as m, and the maximum search distance set of the corresponding underwater robots is d = {d1, d2, ..., d...} i , ..., d m The system collects the number of times the corresponding underwater robot has previously searched for faulty underwater devices and the number of times the corresponding underwater robot has successfully searched for faulty underwater devices. It also collects the predetermined trajectory of the current underwater robot when it initially locates the faulty device and the predetermined trajectory of the underwater robot that is simultaneously searching for different faulty devices. Furthermore, in step S2: retrieve the predetermined trajectories of the current underwater robot and the underwater robots simultaneously searching for different faulty devices, and obtain the set of shortest distances between the predetermined trajectories of the underwater robots simultaneously searching for different faulty devices and the predetermined trajectory of the current underwater robot when it initially locates the faulty device, as D = {D1, D2, ..., D...} m The shortest distance between two trajectories is calculated using a genetic algorithm. The set of position coordinates of m underwater robots simultaneously searching for different faulty devices, moving along predetermined trajectories to the point where the distance to the predetermined trajectory when the current underwater robot initially locates the faulty device, is (X, Y) = {(X1, Y1), (X2, Y2), ..., (X...}. m Y m The underwater robot has initially located the faulty equipment at coordinates (x, y). According to formula H... i =[(X i -x) 2 +(Y i -y) 2 ] 1 / 2 Calculate the straight-line distance H from the initially located faulty device to the point where a randomly selected underwater robot moves to the position that minimizes the distance to its current predetermined trajectory. iThe set of straight-line distances from the position of each of the m underwater robots that moves to the position with the shortest distance from the current underwater robot's predetermined trajectory to the initially located faulty equipment is obtained as H = {H1, H2, ..., H...} i H m}, compare H i and d i If H i >d i This indicates that the straight-line distance exceeds the maximum search distance of the corresponding robot; if H i ≤d i This indicates that the straight-line distance does not exceed the maximum search distance of the corresponding robot, and the corresponding robot can find the faulty device at this location. Robots whose straight-line distance does not exceed the maximum search distance are selected. Since the underwater robot's own positioning may have some errors, in order to reduce the errors, when the underwater robot is searching for underwater faulty equipment, it is verified by the cooperation of other underwater robots to see if the underwater faulty equipment currently located by the underwater robot has shifted. There is no need to arrange another underwater robot to cooperate. Instead, the robot that needs to search for underwater faulty equipment at the same time as the current underwater robot is used to cooperate, which saves positioning and detection costs. The selected collaborative robot searches for the faulty device at the shortest distance to the current underwater robot's predetermined trajectory. Considering that different underwater robots have different maximum search distances, if the distance between the corresponding location and the faulty device exceeds the maximum search distance, it is determined that the corresponding robot may not be able to find the faulty device and therefore does not have collaborative capabilities. Based on the corresponding judgment conditions, robots with collaborative capabilities are initially selected. There are n robots whose straight-line distance does not exceed the maximum search distance. The set of shortest distances between the predetermined trajectories of the corresponding n robots and the predetermined trajectory of the current underwater robot when it initially locates the faulty device is V = {V1, V2, ..., V...}. n}, V⊂D, the set of straight-line distances from the position where the n robots move to the position with the shortest distance to the current underwater robot's predetermined trajectory to the initially located faulty equipment position is h={h1, h2, ..., h n}, h⊂H, according to formula P j =1 / [(V j / ∑ n j=1 V j )+(h j / ∑ n j=1 h j )] Calculate the reliability P of randomly selecting a robot as the cooperative target. j The set of reliability of n robots as collaborative targets is obtained as P = {P1, P2, ..., P...} j, ..., P n}, compare the reliability levels, and set the reliability threshold as (∑ n j=1 P j ) / n, and then a second screening is conducted to select robots with a reliability level higher than the threshold; After the initial screening is completed, in order to improve the accuracy of the location of the faulty equipment found by the selected collaborative targets, the robots are screened a second time. The closer the predetermined trajectories of the robots are and the closer the distance from the shortest distance of the current robot's predetermined trajectory to the faulty equipment, the higher the accuracy of the location of the faulty equipment found by the corresponding robot and the higher the reliability of using it as a collaborative target. Screening the robots a second time helps to improve the accuracy of verifying the location of the faulty equipment found by the current robot based on the collaborative target search data. The set of previous searches for faulty underwater equipment by the underwater robot, which was selected through secondary screening, is K = {K1, K2, ..., K}. f The set of previous successful searches for faulty underwater equipment is F = {F1, F2, ..., F}. f}, where f represents the number of robots selected in the second screening, according to the formula Q i =F i / K i Calculate the historical detection success rate Q of a randomly selected robot through secondary screening. i The set of historical detection success rates of the robots selected through secondary screening is Q = {Q1, Q2, ..., Q...} i Q f}, set the success rate threshold as (∑ f i=1 Q i ) / f, compare the success rate with the threshold, remove robots with historical detection success rates below the threshold, and use the remaining robots as cooperative targets. When the cooperative target moves to the point where the distance to the predetermined trajectory when the current underwater robot initially locates the faulty equipment is the shortest, the cooperative target is used to locate the faulty equipment that the current underwater robot needs to search for. The number of cooperative targets is greater than 1. In addition to considering the reliability of the candidate as a collaboration target in the current environment, the search and localization capabilities of the selected collaboration target also need to be evaluated. The stronger the search and localization capability, the more accurately the corresponding robot can locate the faulty device. The best basis for verifying its search and localization capability is the historical data of searching and detecting faulty devices. Through big data analysis, the success rate of the robot searching and detecting faulty devices is selected in the second screening, and the final collaboration target is selected. After three screenings, it is ensured that the collaboration target has the ability to search and detect the faulty device that the current robot needs to search for with a high success rate.
[0012] Furthermore, in steps S3-S4: The location information of the faulty equipment located by the collaborative target is obtained. Using the random incremental method, the smallest circle covering all the faulty equipment locations located by the collaborative target is obtained, with center (a, b) and radius r. The positioning fault tolerance range is divided as follows: the range of the circle centered at (a, b) with radius r. If [(ax)...] 2 +(by) 2 ] 1 / 2 If ≤r, determine that the initial location of the faulty equipment located by the underwater robot is within the positioning fault tolerance range, and control the underwater robot to continue moving towards the initially located faulty equipment location; if [(ax] 2 +(by) 2 ] 1 / 2 >r indicates that the location of the faulty device initially located by the underwater robot is not within the positioning error tolerance range, prompting the underwater robot to re-search for the faulty device until the underwater robot moves to the location of the faulty device; The stochastic incremental algorithm is an important algorithm in computational geometry that can be used to solve the minimum circle cover problem. After selecting the collaborative target, the robot uses the collaborative target to search for and locate the faulty device in a suitable location. Based on the obtained location information of the faulty device, the positioning fault tolerance range is divided. By analyzing whether the faulty device initially located by the robot is within the fault tolerance range, the accuracy of the initial positioning data is verified. This helps to promptly re-search for and locate the faulty device so that the robot can reach the faulty device as quickly and accurately as possible, and perform fault detection and identification for the faulty device.
[0013] Compared with the prior art, the beneficial effects achieved by the present invention are: This invention verifies whether the underwater faulty equipment located by the current underwater robot has shifted by cooperating with other underwater robots. There is no need to arrange other underwater robots to cooperate. Instead, it uses robots that need to search for underwater faulty equipment at the same time as the current underwater robot to cooperate, which saves positioning and detection costs. By analyzing faulty equipment search and detection data through big data analysis and filtering collaborative targets three times, the accuracy of verifying the location of faulty equipment currently searched by the robot based on the search data of collaborative targets is improved. After selecting the collaborative target, the robot uses the collaborative target to search for and locate the faulty device at a suitable location. Based on the obtained location information of the faulty device, the positioning error tolerance range is divided. By analyzing whether the faulty device initially located by the robot is within the error tolerance range, the accuracy of the initial positioning data is verified. This helps to promptly re-search for and locate the faulty device so that the robot can reach the faulty device as quickly and accurately as possible. This enables fault detection and identification of the faulty device and improves the accuracy of the underwater robot in locating underwater faulty devices. Attached Figure Description
[0014] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a structural diagram of an intelligent identification system for underwater equipment detection according to the present invention; Figure 2 This is a flowchart of an intelligent identification method for underwater equipment detection according to the present invention. Implementation
[0015] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.
[0016] The following is combined with Figures 1-2 The present invention will be further described with reference to specific embodiments.
[0017] Example 1: As Figure 1 As shown, this embodiment provides an intelligent identification system for underwater equipment detection. The system includes: a search data acquisition module, a data management center, a collaborative target screening module, an equipment search management module, and an equipment detection and identification module. The output of the search data acquisition module is connected to the input of the data management center. The output of the data management center is connected to the input of the collaborative target filtering module and the device search management module. The output of the collaborative target filtering module is connected to the input of the device search management module. The output of the device search management module is connected to the input of the device detection and identification module. The underwater robot collects data on its search and location of faulty underwater equipment, as well as historical search data, through the search data acquisition module, and transmits all collected data to the data management center. All collected data is stored and managed through the data management center; The collaborative target filtering module identifies robots that will collaborate with the current underwater robot to search for faulty underwater equipment. The equipment search and management module controls the collaborative search for faulty underwater equipment by controlling the collaborative targets. When the underwater robot searches for and reaches the location of the faulty underwater equipment, the equipment detection and identification module detects and identifies the faulty part of the equipment.
[0018] The search data acquisition module includes a robot data acquisition unit and a predetermined trajectory acquisition unit; The outputs of the robot data acquisition unit and the predetermined trajectory acquisition unit are connected to the input of the data management center. The robot data acquisition unit is used to collect data on the number of underwater robots that are simultaneously searching for different faulty devices with the current underwater robot, the maximum search distance of the underwater robot, the number of times the corresponding underwater robot has previously searched for faulty underwater devices, and the number of times it has successfully searched for faulty underwater devices. The predetermined trajectory acquisition unit is used to acquire predetermined trajectory data of the current underwater robot when it initially locates the faulty device, and to acquire predetermined trajectory data of underwater robots that are simultaneously searching for different faulty devices.
[0019] The collaborative target selection module includes an initial positioning acquisition unit, a relative position analysis unit, and a robot selection unit; The input ends of the initial positioning acquisition unit and the relative position analysis unit are connected to the output end of the data management center. The output end of the initial positioning acquisition unit is connected to the input end of the relative position analysis unit, and the output end of the relative position analysis unit is connected to the input end of the robot screening unit. The initial positioning acquisition unit is used to obtain the location information of the faulty equipment initially located by the underwater robot. The relative position analysis unit is used to analyze the straight-line distance between the underwater robot searching for different faulty devices and the location of the faulty device when it moves to the point where the distance to the predetermined trajectory of the current underwater robot when it initially locates the faulty device is the shortest. The straight-line distance is compared with the maximum search distance of the corresponding robot, and robots whose straight-line distance is less than or equal to the maximum search distance are selected. The robot screening unit is used to perform secondary screening of robots based on the shortest distance between the predetermined trajectory of the screened robot and the predetermined trajectory of the current robot, and the straight-line distance between the screened robot and the location of the faulty equipment when it moves to the shortest distance. The screening results are then transmitted to the equipment search and management module.
[0020] The device search management module includes a detection data analysis unit, a collaborative target elimination unit, and a collaborative search management unit; The input end of the detection data analysis unit is connected to the output end of the robot screening unit and the data management center; the output end of the detection data analysis unit is connected to the input end of the collaborative target elimination unit; and the output end of the collaborative target elimination unit is connected to the input end of the collaborative search management unit. The detection data analysis unit is used to retrieve data on the number of times the robot selected in the secondary screening has searched for underwater faulty equipment and the number of times it has successfully searched for underwater faulty equipment, and to analyze the historical detection success rate of the robot selected in the secondary screening. The collaborative target elimination unit is used to set a success rate threshold, eliminate robots with a historical detection success rate lower than the threshold, and use the remaining robots as collaborative targets. The collaborative search management unit is used to locate the faulty equipment that the current underwater robot needs to search for when the collaborative target moves to the point where the distance to the predetermined trajectory when the current underwater robot initially locates the faulty equipment is the shortest. The unit then obtains the location information and transmits the location information to the equipment detection and identification module.
[0021] The equipment detection and identification module includes a positioning adjustment reminder unit and a fault detection and identification unit; The input end of the positioning adjustment reminder unit is connected to the output end of the collaborative search management unit, and the output end of the positioning adjustment reminder unit is connected to the input end of the fault detection and identification unit. The positioning adjustment reminder unit is used to analyze the location information of the faulty equipment found by the collaborative target, divide the positioning fault tolerance range based on the location information, and determine whether the current underwater robot's initial positioning of the faulty equipment is within the positioning fault tolerance range: if it is, control the current underwater robot to continue moving towards the initially located faulty equipment location; if it is not, send an alarm signal to remind the user to search for the faulty equipment again and reposition the faulty equipment until the current underwater robot moves to the location of the faulty equipment. The fault detection and identification unit is used to detect and identify the fault in the equipment after the underwater robot moves to the location of the faulty equipment, and transmits the detection data to the detection terminal.
[0022] Example 2: Figure 2 As shown, this embodiment provides an intelligent identification method for underwater equipment detection, which is implemented based on the intelligent identification system in this embodiment, and specifically includes the following steps: S1: Collect data on underwater robots searching for and locating faulty underwater equipment, as well as historical search data. Collect m data on the number of underwater robots simultaneously searching for different faulty equipment, and the corresponding maximum search distance set for the underwater robots is d = {d1, d2, ..., d...} i , ..., d m The system collects the number of times the corresponding underwater robot has previously searched for faulty underwater devices and the number of times the corresponding underwater robot has successfully searched for faulty underwater devices. It also collects the predetermined trajectory of the current underwater robot when it initially locates the faulty device and the predetermined trajectory of the underwater robot that is simultaneously searching for different faulty devices. For example: if the number of underwater robots simultaneously searching for different faulty devices is m=8, the corresponding maximum search distance set of the underwater robots is d={d1, d2, d3, d4, d5, d6, d7, d8}={100, 120, 80, 110, 116, 118, 95, 106}, in meters; S2: Select robots that will collaborate with the current underwater robot to search for faulty underwater equipment. Retrieve the predetermined trajectories of the current underwater robot and the underwater robots simultaneously searching for different faulty equipment. Obtain the set of shortest distances between the predetermined trajectories of the underwater robots simultaneously searching for different faulty equipment and the predetermined trajectory of the current underwater robot when it initially locates the faulty equipment, which is D={D1, D2, D3, D4, D5, D6, D7, D8}={20, 10, 50, 60, 25, 18, 32, 30}. Use a genetic algorithm to calculate the shortest distance between the two trajectories. Obtain the set of position coordinates (X, Y)={(X1, Y1), (X2, Y2), ..., (X... m Y m The underwater robot has initially located the faulty equipment at coordinates (x, y). According to formula H... i =[(X i -x) 2 +(Y i -y) 2 ] 1 / 2 Calculate the straight-line distance H from the initially located faulty device to the point where a randomly selected underwater robot moves to the position that minimizes the distance to its current predetermined trajectory. i The set of straight-line distances from the position where each of the m underwater robots moves to the shortest distance from its current predetermined trajectory to the initially located faulty device is obtained as H = {H1, H2, H3, H4, H5, H6, H7, H8} = {85, 50, 100, 108, 110, 112, 101, 105}. Compare H... i and d i If H i >d i This indicates that the straight-line distance exceeds the maximum search distance of the corresponding robot; if H i ≤d iThis indicates that the straight-line distance does not exceed the maximum search distance of the corresponding robot, and the corresponding robot can find the faulty device at this location. The robots whose straight-line distance does not exceed the maximum search distance are selected as follows: robots with maximum search distances of d1, d2, d4, d5, d6, and d8 respectively. A total of n=6 robots are selected as having straight-line distances not exceeding the maximum search distance. The set of shortest distances between the predetermined trajectories of the corresponding n robots and the predetermined trajectory of the current underwater robot when initially locating the faulty device is V={V1, V2, V3, V4, V5, V6}={20, 10, 60, 25, 18, 30}, V⊂D. The set of straight-line distances from the position where the corresponding n robots move to the position with the shortest distance from the current underwater robot's predetermined trajectory to the initially located faulty device is h={h1, h2, h3, h4, h5, h6}={85, 50, 108, 110, 112, 105}, h⊂H. According to formula P... j =1 / [(V j / ∑ n j=1 V j )+(h j / ∑ n j=1 h j )] Calculate the reliability P of randomly selecting a robot as the cooperative target. j ≈3.7, resulting in a reliability set of n robots as collaborative targets, P={P1, P2, P3, P4, P5, P6}={3.7, 6.7, 1.8, 2.9, 4.9, 2.7}. Comparing the reliability levels, a reliability threshold is set as (∑ n j=1 P j ) / n≈3.6, and robots with a reliability higher than the threshold are selected through a second screening. The set of previous searches for faulty underwater equipment by the selected underwater robots is K={K1, K2, K3}={10, 8, 9}, and the set of previous successful searches for faulty underwater equipment is F={F1, F2, F3}={10, 7, 5}. According to the formula Q i =F i / K i Calculate the historical detection success rate Q of a randomly selected robot through secondary screening. i The historical detection success rate set of the robots selected after secondary screening is obtained as Q={Q1, Q2, Q3}={1, 0.88, 0.56}. The success rate threshold is set as (∑ f i=1 Q i) / f=0.8, compare the success rate with the threshold, remove robots with historical detection success rates below the threshold, and use the remaining robots as collaborative targets: the collaborative targets are the underwater robots corresponding to Q1 and Q2. When the collaborative target moves to the point where the distance to the predetermined trajectory of the current underwater robot when it initially locates the faulty device is the shortest, the collaborative target is used to locate the faulty device that the current underwater robot needs to search for. The number of collaborative targets is greater than 1. S3: Based on the collaborative search results, define the positioning fault tolerance range, obtain the location information of the faulty equipment located by the collaborative target, and use the random incremental method to obtain the smallest circle covering all the faulty equipment location points located by the collaborative target with center (a, b) and radius r. Define the positioning fault tolerance range as the range of the circle centered at (a, b) with radius r. Determine whether the faulty equipment location initially located by the underwater robot is within the positioning fault tolerance range. If [(ax) 2 +(by) 2 ] 1 / 2 If ≤r, it indicates that the initial location of the faulty equipment by the underwater robot is within the positioning tolerance range; if [(ax) 2 +(by) 2 ] 1 / 2 >r, if the location of the faulty device initially located by the underwater robot is not within the positioning fault tolerance range, proceed to step S4; S4: If present, control the current underwater robot to continue moving towards the initially located faulty device; if not, prompt the user to search for the faulty device again until the current underwater robot moves to the location of the faulty device.
[0023] S5: When the underwater robot searches for and reaches the location of the faulty underwater equipment, it uses the binocular camera installed on the underwater robot to detect and identify the faulty equipment and transmits the detection data to the detection terminal.
[0024] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.
Claims
1. An intelligent identification system for underwater equipment detection, characterized in that: The system includes: a search data acquisition module, a data management center, a collaborative target filtering module, a device search management module, and a device detection and identification module; The output of the search data acquisition module is connected to the input of the data management center. The output of the data management center is connected to the input of the collaborative target filtering module and the device search management module. The output of the collaborative target filtering module is connected to the input of the device search management module. The output of the device search management module is connected to the input of the device detection and identification module. The search data acquisition module collects data on the underwater robot's search and location of faulty underwater equipment, as well as historical search data, and transmits all collected data to the data management center. All collected data is stored and managed through the data management center. The cooperative target screening module filters out robots that will cooperate with the current underwater robot to search for faulty underwater equipment. The device search and management module controls the cooperative targets to conduct a cooperative search for faulty underwater devices. When the underwater robot searches for and reaches the location of the faulty underwater equipment, the device detection and identification module detects and identifies the faulty equipment.
2. The intelligent identification system for underwater equipment detection according to claim 1, characterized in that: The search data acquisition module includes a robot data acquisition unit and a predetermined trajectory acquisition unit; The output terminals of the robot data acquisition unit and the predetermined trajectory acquisition unit are connected to the input terminal of the data management center; The robot data acquisition unit is used to collect the number of underwater robots that are simultaneously searching for different faulty devices with the current underwater robot, the maximum search distance of the underwater robot, the number of times the corresponding underwater robot has previously searched for faulty underwater devices, and the number of times it has successfully searched for faulty underwater devices. The predetermined trajectory acquisition unit is used to acquire predetermined trajectory data of the current underwater robot when it initially locates the faulty device, and to acquire predetermined trajectory data of underwater robots that are simultaneously searching for different faulty devices.
3. The intelligent identification system for underwater equipment detection according to claim 1, characterized in that: The collaborative target screening module includes an initial positioning acquisition unit, a relative position analysis unit, and a robot screening unit; The input terminals of the initial positioning acquisition unit and the relative position analysis unit are connected to the output terminal of the data management center, the output terminal of the initial positioning acquisition unit is connected to the input terminal of the relative position analysis unit, and the output terminal of the relative position analysis unit is connected to the input terminal of the robot screening unit. The initial positioning acquisition unit is used to obtain the location information of the faulty equipment initially located by the underwater robot. The relative position analysis unit is used to analyze the straight-line distance between the underwater robot searching for different faulty devices and the location of the faulty device when it moves to the point where the distance to the predetermined trajectory of the current underwater robot when it initially locates the faulty device is the shortest. The straight-line distance is compared with the maximum search distance of the corresponding robot, and robots whose straight-line distance is less than or equal to the maximum search distance are selected. The robot screening unit is used to perform secondary screening of robots based on the shortest distance between the predetermined trajectory of the screened robot and the predetermined trajectory of the current robot, and the straight-line distance between the screened robot and the location of the faulty equipment when it moves to the shortest distance point, and transmits the screening results to the equipment search and management module.
4. The intelligent identification system for underwater equipment detection according to claim 3, characterized in that: The device search management module includes a detection data analysis unit, a collaborative target elimination unit, and a collaborative search management unit; The input end of the detection data analysis unit is connected to the output end of the robot screening unit and the data management center, the output end of the detection data analysis unit is connected to the input end of the collaborative target elimination unit, and the output end of the collaborative target elimination unit is connected to the input end of the collaborative search management unit. The detection data analysis unit is used to retrieve data on the number of times the robot selected in the secondary screening has previously searched for underwater faulty equipment and the number of times it has successfully searched for underwater faulty equipment, and to analyze the historical detection success rate of the robot selected in the secondary screening. The collaborative target elimination unit is used to set a success rate threshold, eliminate robots with a historical detection success rate lower than the threshold, and use the remaining robots as collaborative targets. The cooperative search management unit is used to locate the faulty equipment that the current underwater robot needs to search for when the cooperative target moves to the point where the distance to the predetermined trajectory when the current underwater robot initially locates the faulty equipment is the shortest. The unit then obtains the location information and transmits the location information to the equipment detection and identification module.
5. The intelligent identification system for underwater equipment detection according to claim 4, characterized in that: The equipment detection and identification module includes a positioning adjustment reminder unit and a fault detection and identification unit; The input terminal of the positioning adjustment reminder unit is connected to the output terminal of the collaborative search management unit, and the output terminal of the positioning adjustment reminder unit is connected to the input terminal of the fault detection and identification unit. The positioning adjustment reminder unit is used to analyze the location information of the faulty equipment searched by the cooperative target, divide the positioning fault tolerance range according to the location information, and determine whether the location of the faulty equipment initially located by the current underwater robot is within the positioning fault tolerance range: if it is, control the current underwater robot to continue moving towards the initially located faulty equipment location; if it is not, send an alarm signal to remind the user to search for the faulty equipment again and reposition the faulty equipment until the current underwater robot moves to the location of the faulty equipment. The fault detection and identification unit is used to detect and identify the fault in the equipment using a binocular camera after the underwater robot moves to the location of the faulty equipment, and transmit the detection data to the detection terminal.
6. An intelligent identification method for underwater equipment detection, characterized in that: Includes the following steps: S1: Collect data on the underwater robot's search and location of faulty underwater equipment, as well as historical search data; S2: Select robots that will cooperate with the current underwater robot to search for faulty underwater equipment, and control the cooperative target to cooperate in the search for faulty underwater equipment; S3: Based on the collaborative search results, divide the positioning fault tolerance range, determine whether the location of the faulty equipment initially located by the underwater robot is within the positioning fault tolerance range, and execute step S4; S4: If present, control the current underwater robot to continue moving towards the initially located faulty device; if not, prompt the user to re-search for the faulty device until the current underwater robot moves to the location of the faulty device. S5: When the underwater robot searches for and reaches the location of the faulty underwater equipment, it detects and identifies the faulty part of the equipment.
7. The intelligent identification method for underwater equipment detection according to claim 6, characterized in that: In step S1: the number of underwater robots searching for different fault devices simultaneously with the current underwater robot is m, the maximum search distance set of the corresponding underwater robot is d={d1, d2, …, d i , …, d m}, the number of times the corresponding underwater robot searches for underwater fault devices in the past and the number of times the corresponding underwater robot successfully searches for underwater fault devices in the past are collected, the trajectory predetermined by the current underwater robot when it preliminarily locates the fault device is collected, and the predetermined trajectory of the underwater robot searching for different fault devices simultaneously with the current underwater robot is collected; In step S2: retrieve the predetermined trajectories of the current underwater robot and the underwater robots simultaneously searching for different faulty devices. Obtain the set of shortest distances between the predetermined trajectories of the underwater robots simultaneously searching for different faulty devices and the predetermined trajectory of the current underwater robot when it initially locates the faulty device, as D = {D1, D2, ..., D...} m }, the set of position coordinates of m underwater robots simultaneously searching for different faulty devices, moving along a predetermined trajectory to the point where the distance to the predetermined trajectory of the current underwater robot when it initially locates the faulty device, is (X, Y) = {(X1, Y1), (X2, Y2), ..., (X... m Y m The underwater robot has initially located the faulty equipment at coordinates (x, y). According to formula H... i =[(X i -x) 2 +(Y i -y) 2 ] 1 / 2 Calculate the straight-line distance H from the initially located faulty device to the point where a randomly selected underwater robot moves to the position that minimizes the distance to its current predetermined trajectory. i The set of straight-line distances from the position of each of the m underwater robots that moves to the position with the shortest distance from the current underwater robot's predetermined trajectory to the initially located faulty equipment is obtained as H = {H1, H2, ..., H...} i H m }, compare H i and d i If H i >d i This indicates that the straight-line distance exceeds the maximum search distance of the corresponding robot; if H i ≤d i This indicates that the straight-line distance does not exceed the maximum search distance of the corresponding robot, thus filtering out robots whose straight-line distance does not exceed the maximum search distance.
8. The intelligent identification method for underwater equipment detection according to claim 7, characterized in that: There are n robots whose straight-line distance does not exceed the maximum search distance. The set of shortest distances between the predetermined trajectories of the corresponding n robots and the predetermined trajectory of the current underwater robot when it initially locates the faulty device is V = {V1, V2, ..., V...}. n }, V⊂D, the set of straight-line distances from the position where the n robots move to the position with the shortest distance to the current underwater robot's predetermined trajectory to the initially located faulty equipment position is h={h1, h2, ..., h n }, h⊂H, according to formula P j =1 / [(V j / ∑ n j=1 V j )+(h j / ∑ n j=1 h j )] Calculate the reliability P of randomly selecting a robot as the cooperative target. j The set of reliability of n robots as collaborative targets is obtained as P = {P1, P2, ..., P...} j , ..., P n }, compare the reliability levels, and set the reliability threshold as (∑ n j=1 P j ) / n, and then a second screening is performed to select robots with a reliability level higher than the threshold.
9. The intelligent identification method for underwater equipment detection according to claim 8, characterized in that: The set of previous searches for faulty underwater equipment by the underwater robot, which was selected through secondary screening, is K = {K1, K2, ..., K}. f The set of previous successful searches for faulty underwater equipment is F = {F1, F2, ..., F}. f }, where f represents the number of robots selected in the second screening, according to the formula Q i =F i / K i Calculate the historical detection success rate Q of a randomly selected robot through secondary screening. i The set of historical detection success rates of the robots selected through secondary screening is Q = {Q1, Q2, ..., Q...} i Q f }, set the success rate threshold as (∑ f i= 1Q i ) / f, compare the success rate with the threshold, remove robots with historical detection success rates below the threshold, and use the remaining robots as cooperative targets. When the cooperative target moves to the point where the distance to the predetermined trajectory when the current underwater robot initially locates the faulty equipment is the shortest, the cooperative target is used to locate the faulty equipment that the current underwater robot needs to search for.
10. The intelligent identification method for underwater equipment detection according to claim 7, characterized in that: In steps S3-S4: The location information of the faulty equipment located by the collaborative target is obtained. Using the random incremental method, the smallest circle covering all the faulty equipment locations located by the collaborative target is obtained, with center (a, b) and radius r. The positioning fault tolerance range is defined as the area centered at (a, b) and with radius r. If [(ax)...] 2 +(by) 2 ] 1 / 2 If ≤r, determine that the initial location of the faulty equipment located by the underwater robot is within the positioning fault tolerance range, and control the underwater robot to continue moving towards the initially located faulty equipment location; if [(ax] 2 +(by) 2 ] 1 / 2 >r indicates that the location of the faulty device initially located by the underwater robot is outside the positioning error tolerance range, prompting the user to re-search for the faulty device until the underwater robot moves to the location of the faulty device.