Intelligent power plant joint inspection system and method based on intelligent robot

Abstract

The application discloses a smart power plant combined inspection system and method based on intelligent robots, relates to the technical field of circuit inspection, and collects path information in the smart power plant area in real time, constructs an inspection network based on the collected path information, sets a coordinate system and a reference point based on the constructed inspection network, and carries out accurate positioning on the intelligent robot in the operation process in real time based on the set coordinate system and reference point; after positioning is completed, a real-time prediction digital twin model is established through a data simulation algorithm process based on the accurate positioning of the intelligent robot, the set coordinate system and the reference point, path planning is carried out on the constructed inspection network through a path planning algorithm, and the path planning result is input into the real-time prediction digital twin model; finally, the intelligent robot is controlled based on the established real-time prediction digital twin model, the path planning result and the current accurate positioning of the intelligent robot, and the efficiency of power plant inspection is improved.

Description

Technical Field

[0001] This invention relates to the field of circuit inspection technology, and more specifically to a smart power plant joint inspection system and method based on intelligent robots. Background Technology

[0002] Traditional inspection methods are usually manual, which requires inspectors to have high professional skills to deal with various situations. However, traditional inspection methods are inefficient and inaccurate because they are done manually.

[0003] Existing technology, such as the invention patent application with publication number CN116455083A, discloses an inspection and control system for smart grids. Its method includes: a sequential online management mechanism that generates inspection plans, receives inspection plans from inspection experts, conducts on-site inspections, and uploads inspection results. This mechanism enables control over the inspection process and improves the smooth progress of safety inspections. By setting up offline inspection shields as a medium for receiving inspection plans and storing and uploading inspection results, it prevents unauthorized external personnel from receiving or altering inspection plans and data. Furthermore, inspection experts must carry the inspection shields for on-site inspections and sequentially upload inspection locations and results. Uploading to the next inspection location is impossible without recording inspection results, thus improving the quality of power grid inspections.

[0004] As can be seen from the above solutions, the current inspection method still relies on traditional manual inspection, which is inefficient, lacks real-time performance and accuracy, and has certain limitations. Summary of the Invention

[0005] The purpose of this invention is to provide a smart power plant joint inspection system and method based on intelligent robots, which solves the problems existing in the background technology.

[0006] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a joint inspection method for smart power plants based on intelligent robots, specifically including the following steps:

[0007] S1. Collect path information within the smart power plant area in real time and build an inspection network based on the collected path information;

[0008] S2. Based on the construction of the inspection network, a coordinate system and reference points are set, and the intelligent robot in operation is accurately positioned in real time based on the set coordinate system and reference points.

[0009] S21. Based on the construction of the inspection network, set the coordinate system and reference points;

[0010] S22. Based on the constructed inspection network, establish a motion model and a reference model for the intelligent robot;

[0011] S23. Based on the established intelligent robot motion model and intelligent robot reference model, the intelligent robot is accurately positioned during operation through iterative positioning calculation.

[0012] S3. Based on the precise positioning of the intelligent robot, the setting of the coordinate system and reference points, a real-time predictive digital twin model is established through a data simulation algorithm process;

[0013] S4. Perform path planning on the constructed inspection network using a path planning algorithm, and input the path planning results into the real-time prediction digital twin model;

[0014] S5. Control the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot.

[0015] Preferably, the real-time collection of path information within the smart power plant area and the construction of an inspection network based on the collected path information includes the following steps:

[0016] Define the smart power plant area and collect path information within the smart power plant area in real time;

[0017] Set path information A triple composition, This indicates the starting point of the path information. This indicates the end point of the path information. Indicates the distance of the path;

[0018] The collected path information is used to build an inspection network.

[0019] Preferably, the process of setting the coordinate system and reference points based on the constructed inspection network includes the following steps:

[0020] The origin of the coordinate system is set at the center of the smart power plant area. The horizontal direction of the smart power plant area is the X-axis of the three-dimensional coordinate system, the vertical direction is the Y-axis of the three-dimensional coordinate system, and the vertical direction is the Z-axis of the three-dimensional coordinate system. At the same time, based on the constructed three-dimensional coordinate system, m, n, and b reference points are evenly set at unit distances in the three axes respectively.

[0021] Preferably, the process of establishing the intelligent robot motion model and intelligent robot reference model based on the constructed inspection network includes the following steps:

[0022] The motion model of the intelligent robot is shown below:

[0023] ;

[0024] in, This represents the position of the intelligent robot in the set coordinate system at time t. This represents the position of the intelligent robot in the set coordinate system at time t-1. This indicates that the intelligent robot monitoring equipment at time t-1 is... Position relative to reference point Measurement data, Indicates about location and measurement data The equation of motion for intelligent robots The motion error of the intelligent robot at time t is the error distance between the set position and the actual position.

[0025] The intelligent robot reference model is shown below:

[0026] ;

[0027] in, This indicates that at time t, the intelligent robot monitoring equipment is at... Position relative to reference point Measurement data, This represents the i-th reference point in the defined coordinate system. Indicates about location and reference point The reference equation for intelligent robots Represents time t with respect to the reference point The measured error data.

[0028] Preferably, the precise localization of the intelligent robot during operation, based on the established intelligent robot motion model and intelligent robot reference model, through iterative localization calculation, includes the following steps:

[0029] S231. Summarize the intelligent robot motion model and intelligent robot reference model, and perform noise reduction through multi-frame averaging noise reduction.

[0030] Let U be the number of frames for multi-frame average noise reduction. The multi-frame average noise reduction formula is as follows:

[0031] ;

[0032] ;

[0033] in, This represents the motion model of the intelligent robot after multi-frame average noise reduction. This represents the reference model of the intelligent robot after multi-frame average noise reduction. This represents the motion equations after multi-frame average noise reduction. This represents the reference equation after multi-frame average noise reduction;

[0034] S232. After noise reduction is completed, the precise positioning of the intelligent robot during operation is determined by positioning correction.

[0035] The distance from the intelligent robot to each reference point is calculated based on the measurement data of the reference points using the intelligent robot reference model;

[0036] The position of the intelligent robot is corrected using an averaging algorithm based on the distance between the intelligent robot and each reference point;

[0037] ;

[0038] in, This indicates the corrected location of the intelligent robot. This represents the correction amount for the i-th reference point. This represents the change in distance between the intelligent robot and the reference point. Indicates the number of reference points;

[0039] The corrected position of the intelligent robot is set as the precise location of the intelligent robot.

[0040] Preferably, the process of establishing a real-time predictive digital twin model based on the precise positioning of the intelligent robot, setting a coordinate system and reference points, and using data simulation algorithms includes the following steps:

[0041] Let the motion model of the intelligent robot be represented by a probability function. The reference model for the intelligent robot is represented by a probability function. ;

[0042] Calculate the probability model of a single step movement of an intelligent robot using digital twins;

[0043] ;

[0044] Calculate the probability of multi-step motion based on a one-step motion probability model;

[0045] A real-time predictive digital twin model is established based on the multi-step motion probability and the precise positioning of current intelligent robots.

[0046] Preferably, the step of performing path planning on the constructed inspection network using a path planning algorithm and inputting the path planning results into the real-time prediction digital twin model includes the following steps:

[0047] S41. Initialize the population of all paths in the constructed inspection network;

[0048] Define the initial population as the solution space; define each intelligent robot as a "whale"; define the inspection target as "prey";

[0049] Let the position of each whale in the solution space be: ;

[0050] Each whale is set to randomly choose to surround its prey or use a bubble net to drive it away, with each whale having an equal probability of choosing either behavior.

[0051] S42. After the population initialization is completed, the prey is tracked based on the search algorithm;

[0052] S43. Use bubble nets to drive away prey during tracking;

[0053] When whales use bubble nets to drive away prey, they also constantly update their position.

[0054] When using a bubble net, the formula for updating the whale's position is as follows:

[0055] ;

[0056] in, The default value for a constant is 1. Let e ​​be a random number uniformly distributed in the range [-1, 1], and let e represent the natural constant.

[0057] S44. Iterate using the whale optimization algorithm until each inspection target is completed, and output the inspection target corresponding to each intelligent robot.

[0058] The output of each intelligent robot's patrol target is set as the path planning result.

[0059] Preferably, after the population initialization is completed, tracking prey based on the search algorithm includes the following steps:

[0060] When whales surround their prey, they will either swim toward the whale in the best position or toward a random whale.

[0061] As the whale swims towards its optimal position, the whale's position is updated using the following formula:

[0062] ;

[0063] in, Let A represent the optimal whale position at time t, where A is a uniformly distributed area in (- ). , Random numbers within ) The initial value is 2 and decreases linearly with the number of iterations, and B is a random number uniformly distributed in (0,2); This represents the position of the k-th whale at time t+1. This represents the position of the k-th whale at time t. This represents the roulette wheel selection function. Represents a random angle between 0 and 360 degrees;

[0064] When swimming towards the random location of the whale, the whale's position is updated using the following formula:

[0065] ;

[0066] in, This represents the random position of the whale at time t. This represents the position of the h-th whale at time t+1. This represents the position of the h-th whale at time t;

[0067] When set At that time, the whale chooses to swim towards the optimal position. At that time, the whale chooses to swim towards the location of a random whale.

[0068] Preferably, the control of the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot includes the following steps:

[0069] Real-time collection of the current precise location and energy data of the intelligent robot;

[0070] By using the controlled variable method, the energy consumption of the intelligent robot within a unit distance is recorded. The energy data of the intelligent robot, the energy consumption of the intelligent robot within a unit distance, the current precise positioning of the intelligent robot, and the path planning results of the corresponding intelligent robot are input into the real-time predictive digital twin model. The probability of the intelligent robot completing the inspection is calculated based on the real-time predictive digital twin model.

[0071] When it is detected that an intelligent robot cannot complete the inspection, the route is replanned using a path planning algorithm, and the intelligent robot is controlled based on the replanning result.

[0072] When the intelligent robot detects a fault during the inspection process, it will immediately report it and arrange for professional personnel to handle it.

[0073] This invention also discloses a smart power plant joint inspection system based on intelligent robots, which is used to realize a smart power plant joint inspection method based on intelligent robots. The system includes: a data acquisition module, an inspection network construction module, a precise positioning module, a digital twin prediction module, and a real-time control module.

[0074] The data acquisition module is used to collect path information within the smart power plant area in real time;

[0075] The inspection network construction module is used to construct an inspection network based on the real-time collected path information, and to set the inspection route and reference points;

[0076] The precise positioning module is used to precisely locate the intelligent robot based on the constructed inspection network and the set reference points.

[0077] The digital twin prediction module is used to construct a digital twin prediction model based on the precise positioning of the intelligent robot, and to predict the movement of the intelligent robot based on the constructed digital twin prediction.

[0078] The real-time control module is used to control the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot.

[0079] The beneficial effects of this invention are as follows:

[0080] (1) This invention collects path information in the area of ​​a smart power plant in real time and builds an inspection network based on the collected path information. At the same time, it sets a coordinate system and reference points based on the constructed inspection network and performs real-time precise positioning of the intelligent robot in operation based on the set coordinate system and reference points. After positioning is completed, a real-time predictive digital twin model is established through a data simulation algorithm based on the precise positioning of the intelligent robot, the set coordinate system and reference points. At the same time, a path planning algorithm is used to plan the path of the constructed inspection network and input the path planning results into the real-time predictive digital twin model. Finally, the intelligent robot is controlled based on the established real-time predictive digital twin model, the path planning results and the current precise positioning of the intelligent robot, thereby improving the efficiency of power plant inspection.

[0081] (2) This invention improves the accuracy of intelligent robot inspection by constructing an inspection network and setting a coordinate system and reference points, and by establishing an intelligent robot motion model and an intelligent robot reference model based on the constructed inspection network, and by accurately positioning the intelligent robot based on the established model.

[0082] (3) This invention establishes a real-time predictive digital twin model based on the precise positioning of the intelligent robot, setting of coordinate system and reference point, and calculates the motion probability of the intelligent robot by establishing the real-time predictive digital twin model, thereby improving the rationality of intelligent robot inspection.

[0083] (4) The present invention performs path planning on the constructed inspection network through path planning algorithm, and inputs the path planning results into the real-time prediction digital twin model. At the same time, the intelligent robot is controlled based on the digital twin model, which improves the reliability of intelligent robot inspection. Attached Figure Description

[0084] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0085] Figure 1 This is a schematic diagram of the intelligent robot's joint inspection method for smart power plants according to the present invention. Detailed Implementation

[0086] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0087] In a specific embodiment of the present invention,

[0088] Reference Figure 1 As shown, this invention provides a joint inspection method for smart power plants based on intelligent robots, including the following steps:

[0089] S1. Collect path information within the smart power plant area in real time and build an inspection network based on the collected path information;

[0090] S2. Based on the construction of the inspection network, a coordinate system and reference points are set, and the intelligent robot in operation is accurately positioned in real time based on the set coordinate system and reference points.

[0091] S21. Based on the construction of the inspection network, set the coordinate system and reference points;

[0092] S22. Based on the constructed inspection network, establish a motion model and a reference model for the intelligent robot;

[0093] S23. Based on the established intelligent robot motion model and intelligent robot reference model, the intelligent robot is accurately positioned during operation through iterative positioning calculation.

[0094] S3. Based on the precise positioning of the intelligent robot, the setting of the coordinate system and reference points, a real-time predictive digital twin model is established through a data simulation algorithm process;

[0095] S4. Perform path planning on the constructed inspection network using a path planning algorithm, and input the path planning results into the real-time prediction digital twin model;

[0096] S5. Control the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot;

[0097] Furthermore, referring to Figure 1 As shown, the real-time collection of path information within the smart power plant area and the construction of an inspection network based on the collected path information include the following steps:

[0098] Define the smart power plant area and collect path information within the smart power plant area in real time;

[0099] Set path information A triple composition, This indicates the starting point of the path information. This indicates the end point of the path information. Indicates the distance of the path;

[0100] The collected path information is used to construct an inspection network;

[0101] Furthermore, referring to Figure 1 As shown, setting the coordinate system and reference points based on the constructed ground inspection network includes the following steps:

[0102] The origin of the coordinate system is set at the center of the smart power plant area. The horizontal direction of the smart power plant area is the X-axis of the three-dimensional coordinate system, the vertical direction is the Y-axis of the three-dimensional coordinate system, and the vertical direction is the Z-axis of the three-dimensional coordinate system. Based on the constructed three-dimensional coordinate system, m, n, and b reference points are evenly set at unit distances along the three axes respectively.

[0103] Furthermore, referring to Figure 1 As shown, establishing the intelligent robot motion model and intelligent robot reference model based on the constructed inspection network includes the following steps:

[0104] The motion model of the intelligent robot is shown below:

[0105] ;

[0106] in, This represents the position of the intelligent robot in the set coordinate system at time t. This represents the position of the intelligent robot in the set coordinate system at time t-1. This indicates that the intelligent robot monitoring equipment at time t-1 is... Position relative to reference point Measurement data, Indicates about location and measurement data The equation of motion for intelligent robots The motion error of the intelligent robot at time t is the error distance between the set position and the actual position.

[0107] The intelligent robot reference model is shown below:

[0108] ;

[0109] in, This indicates that at time t, the intelligent robot monitoring equipment is at... Position relative to reference point Measurement data, This represents the i-th reference point in the defined coordinate system. Indicates about location and reference point The reference equation for intelligent robots Represents time t with respect to the reference point The measured error data;

[0110] Furthermore, referring to Figure 1 As shown, based on the established intelligent robot motion model and intelligent robot reference model, the precise localization of the intelligent robot during operation is achieved through iterative localization calculation, including the following steps:

[0111] S231. Summarize the intelligent robot motion model and intelligent robot reference model, and perform noise reduction through multi-frame averaging noise reduction.

[0112] Let U be the number of frames for multi-frame average noise reduction. The multi-frame average noise reduction formula is as follows:

[0113] ;

[0114] ;

[0115] in, This represents the motion model of the intelligent robot after multi-frame average noise reduction. This represents the reference model of the intelligent robot after multi-frame average noise reduction. This represents the motion equations after multi-frame average noise reduction. This represents the reference equation after multi-frame average noise reduction;

[0116] S232. After noise reduction is completed, the precise positioning of the intelligent robot during operation is determined by positioning correction.

[0117] The distance from the intelligent robot to each reference point is calculated based on the measurement data of the reference points using the intelligent robot reference model;

[0118] Furthermore, the position of the intelligent robot is corrected using an averaging algorithm based on the distance between the intelligent robot and each reference point;

[0119] ;

[0120] in, This indicates the corrected location of the intelligent robot. This represents the correction amount for the i-th reference point. This represents the change in distance between the intelligent robot and the reference point. Indicates the number of reference points;

[0121] The corrected position of the intelligent robot is set as the precise location of the intelligent robot;

[0122] Furthermore, referring to Figure 1 As shown, a real-time predictive digital twin model is established through a data simulation algorithm process based on the precise positioning of the intelligent robot, the setting of the coordinate system and reference points;

[0123] Let the motion model of the intelligent robot be represented by a probability function. The reference model for the intelligent robot is represented by a probability function. ;

[0124] Calculate the probability model of a single step movement of an intelligent robot using digital twins;

[0125] ;

[0126] Furthermore, the probability of multi-step motion is calculated based on the calculated one-step motion probability model;

[0127] Furthermore, a real-time predictive digital twin model is established based on the multi-step motion probability and the current precise positioning of intelligent robots;

[0128] Furthermore, referring to Figure 1 As shown, the process of planning paths for the constructed inspection network using a path planning algorithm and inputting the path planning results into a real-time prediction digital twin model includes the following steps:

[0129] S41. Initialize the population of all paths in the constructed inspection network;

[0130] Define the initial population as the solution space; define each intelligent robot as a "whale"; define the inspection target as "prey";

[0131] Let the position of each whale in the solution space be: ;

[0132] Each whale is set to randomly choose to surround its prey or use a bubble net to drive it away, with each whale having an equal probability of choosing either behavior.

[0133] S42. After the population initialization is completed, the prey is tracked based on the search algorithm;

[0134] When whales surround their prey, they will either swim toward the whale in the best position or toward a random whale.

[0135] As the whale swims towards its optimal position, the whale's position is updated using the following formula:

[0136] ;

[0137] in, Let A represent the optimal whale position at time t, where A is a uniformly distributed area in (- ). , Random numbers within ) The initial value is 2 and decreases linearly with the number of iterations, and B is a random number uniformly distributed in (0,2); This represents the position of the k-th whale at time t+1. This represents the position of the k-th whale at time t. This represents the roulette wheel selection function. Represents a random angle between 0 and 360 degrees;

[0138] When swimming towards the random location of the whale, the whale's position is updated using the following formula:

[0139] ;

[0140] in, This represents the random position of the whale at time t. This represents the position of the h-th whale at time t+1. This represents the position of the h-th whale at time t;

[0141] When set At that time, the whale chooses to swim towards the optimal position. At that time, the whale chooses to swim towards the location of a random whale;

[0142] S43. Use bubble nets to drive away prey during tracking;

[0143] When whales use bubble nets to drive away prey, they also constantly update their position.

[0144] When using a bubble net, the formula for updating the whale's position is as follows:

[0145] ;

[0146] in, The default value for a constant is 1. Let e ​​be a random number uniformly distributed in the range [-1, 1], and let e represent the natural constant.

[0147] S44. Iterate using the whale optimization algorithm until each inspection target is completed, and output the inspection target corresponding to each intelligent robot.

[0148] The output of each intelligent robot's patrol target is defined as the path planning result.

[0149] Furthermore, referring to Figure 1 As shown, controlling the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot includes the following steps:

[0150] Real-time collection of the current precise location and energy data of the intelligent robot;

[0151] By using the controlled variable method, the energy consumption of the intelligent robot within a unit distance is recorded. The energy data of the intelligent robot, the energy consumption of the intelligent robot within a unit distance, the current precise positioning of the intelligent robot, and the path planning results of the corresponding intelligent robot are input into the real-time predictive digital twin model. The probability of the intelligent robot completing the inspection is calculated based on the real-time predictive digital twin model.

[0152] When it is detected that an intelligent robot cannot complete the inspection, the route is replanned using a path planning algorithm, and the intelligent robot is controlled based on the replanning result.

[0153] Furthermore, when the intelligent robot detects a fault during the inspection process, it will immediately report it and arrange for professional personnel to handle it.

[0154] In one specific embodiment, the smart power plant joint inspection system based on intelligent robots is used to implement a smart power plant joint inspection method based on intelligent robots. The system includes: a data acquisition module, an inspection network construction module, a precise positioning module, a digital twin prediction module, and a real-time control module.

[0155] The data acquisition module is used to collect path information within the smart power plant area in real time;

[0156] The inspection network construction module is used to construct an inspection network based on the real-time collected path information, and to set the inspection route and reference points;

[0157] The precise positioning module is used to precisely locate the intelligent robot based on the constructed inspection network and the set reference points.

[0158] The digital twin prediction module is used to construct a digital twin prediction model based on the precise positioning of the intelligent robot, and to predict the movement of the intelligent robot based on the constructed digital twin prediction.

[0159] The real-time control module is used to control the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot.

[0160] It should be noted that,

[0161] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications or additions should fall within the protection scope of the present invention.

Claims

1. A joint inspection method for smart power plants based on intelligent robots, characterized in that, Includes the following steps: S1. Collect path information within the smart power plant area in real time and build an inspection network based on the collected path information; S2. Based on the construction of the inspection network, a coordinate system and reference points are set, and the intelligent robot in operation is accurately positioned in real time based on the set coordinate system and reference points. S21. Based on the construction of the inspection network, set the coordinate system and reference points; S22. Based on the constructed inspection network, establish a motion model and a reference model for the intelligent robot; S23. Based on the established intelligent robot motion model and intelligent robot reference model, the intelligent robot is accurately positioned during operation through iterative positioning calculation. S3. Based on the precise positioning of the intelligent robot, the setting of the coordinate system and reference points, a real-time predictive digital twin model is established through a data simulation algorithm process; S4. Perform path planning on the constructed inspection network using a path planning algorithm, and input the path planning results into the real-time prediction digital twin model; S5. Control the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot.

2. The joint inspection method for smart power plants based on intelligent robots according to claim 1, characterized in that, The real-time collection of path information within the smart power plant area and the construction of an inspection network based on the collected path information include the following steps: Define the smart power plant area and collect path information within the smart power plant area in real time; Set path information A triple composition, This indicates the starting point of the path information. This indicates the end point of the path information. Indicates the distance of the path; The collected path information is used to build an inspection network.

3. The joint inspection method for smart power plants based on intelligent robots according to claim 1, characterized in that, The process of setting the coordinate system and reference points based on the constructed ground inspection network includes the following steps: The origin of the coordinate system is set at the center of the smart power plant area. The horizontal direction of the smart power plant area is the X-axis of the three-dimensional coordinate system, the vertical direction is the Y-axis of the three-dimensional coordinate system, and the vertical direction is the Z-axis of the three-dimensional coordinate system. At the same time, based on the constructed three-dimensional coordinate system, m, n, and b reference points are evenly set at unit distances in the three axes respectively.

4. The joint inspection method for smart power plants based on intelligent robots according to claim 1, characterized in that, The constructed inspection network establishes a motion model and a reference model for the intelligent robot. Includes the following steps: The motion model of the intelligent robot is shown below: ； in, This represents the position of the intelligent robot in the set coordinate system at time t. This represents the position of the intelligent robot in the set coordinate system at time t-1. This indicates that the intelligent robot monitoring equipment at time t-1 is... Position relative to reference point Measurement data, Indicates about location and measurement data The equation of motion for intelligent robots The motion error of the intelligent robot at time t is the error distance between the set position and the actual position. The intelligent robot reference model is shown below: ； in, This indicates that at time t, the intelligent robot monitoring equipment is at... Position relative to reference point Measurement data, This represents the i-th reference point in the defined coordinate system. Indicates about location and reference point The reference equation for intelligent robots Represents time t with respect to the reference point The measured error data.

5. The joint inspection method for smart power plants based on intelligent robots according to claim 4, characterized in that, The precise localization of the intelligent robot during operation, based on the established intelligent robot motion model and intelligent robot reference model, through iterative localization calculation, includes the following steps: S231. Summarize the intelligent robot motion model and intelligent robot reference model, and perform noise reduction through multi-frame averaging noise reduction. Let U be the number of frames for multi-frame average noise reduction. The multi-frame average noise reduction formula is as follows: ； ； in, This represents the motion model of the intelligent robot after multi-frame average noise reduction. This represents the reference model of the intelligent robot after multi-frame average noise reduction. This represents the motion equations after multi-frame average noise reduction. This represents the reference equation after multi-frame average noise reduction; S232. After noise reduction is completed, the precise positioning of the intelligent robot during operation is determined by positioning correction. The distance from the intelligent robot to each reference point is calculated based on the measurement data of the reference points using the intelligent robot reference model; The position of the intelligent robot is corrected using an averaging algorithm based on the distance between the intelligent robot and each reference point; ； in, This indicates the corrected location of the intelligent robot. This represents the correction amount for the i-th reference point. This represents the change in distance between the intelligent robot and the reference point. Indicates the number of reference points; The corrected position of the intelligent robot is set as the precise location of the intelligent robot.

6. The joint inspection method for smart power plants based on intelligent robots according to claim 5, characterized in that, The process of establishing a real-time predictive digital twin model based on precise positioning of the intelligent robot, setting of coordinate system and reference points, and data simulation algorithm includes the following steps: Let the motion model of the intelligent robot be represented by a probability function. The reference model for the intelligent robot is represented by a probability function. ; Calculate the probability model of a single step movement of an intelligent robot using digital twins; ； Calculate the probability of multi-step motion based on a one-step motion probability model; A real-time predictive digital twin model is established based on the multi-step motion probability and the precise positioning of current intelligent robots.

7. The joint inspection method for smart power plants based on intelligent robots according to claim 1, characterized in that, The process of performing path planning on the constructed inspection network using a path planning algorithm and inputting the path planning results into a real-time prediction digital twin model includes the following steps: S41. Initialize the population of all paths in the constructed inspection network; Define the initial population as the solution space; define each intelligent robot as a "whale"; define the inspection target as "prey"; Let the position of each whale in the solution space be: ; Each whale is set to randomly choose to surround its prey or use a bubble net to drive it away, with each whale having an equal probability of choosing either behavior. S42. After the population initialization is completed, the prey is tracked based on the search algorithm; S43. Use bubble nets to drive away prey during tracking; When whales use bubble nets to drive away prey, they also constantly update their position. When using a bubble net, the formula for updating the whale's position is as follows: ； in, The default value for a constant is 1. Let e ​​be a random number uniformly distributed in the range [-1, 1], and let e represent the natural constant. S44. Iterate using the whale optimization algorithm until each inspection target is completed, and output the inspection target corresponding to each intelligent robot. The output of each intelligent robot's patrol target is set as the path planning result.

8. The joint inspection method for smart power plants based on intelligent robots according to claim 7, characterized in that, After the population initialization is completed, the prey tracking based on the search algorithm includes the following steps: When whales surround their prey, they will either swim toward the whale in the best position or toward a random whale. As the whale swims towards its optimal position, the whale's position is updated using the following formula: ； in, Let A represent the optimal whale position at time t, where A is a uniformly distributed area in (- ). , Random numbers within ) The initial value is 2 and decreases linearly with the number of iterations, and B is a random number uniformly distributed in (0,2); This represents the position of the k-th whale at time t+1. This represents the position of the k-th whale at time t. This represents the roulette wheel selection function. Represents a random angle between 0 and 360 degrees; When swimming towards the random location of the whale, the whale's position is updated using the following formula: ； in, This represents the random position of the whale at time t. This represents the position of the h-th whale at time t+1. This represents the position of the h-th whale at time t; When set At that time, the whale chooses to swim towards the optimal position. At that time, the whale chooses to swim towards the location of a random whale.

9. The joint inspection method for smart power plants based on intelligent robots according to claim 1, characterized in that, The control of the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot includes the following steps: Real-time collection of the current precise location and energy data of the intelligent robot; By using the controlled variable method, the energy consumption of the intelligent robot within a unit distance is recorded. The energy data of the intelligent robot, the energy consumption of the intelligent robot within a unit distance, the current precise positioning of the intelligent robot, and the path planning results of the corresponding intelligent robot are input into the real-time predictive digital twin model. The probability of the intelligent robot completing the inspection is calculated based on the real-time predictive digital twin model. When it is detected that an intelligent robot cannot complete the inspection, the route is replanned using a path planning algorithm, and the intelligent robot is controlled based on the replanning result. When the intelligent robot detects a fault during the inspection process, it will immediately report it and arrange for professional personnel to handle it.

10. A system for implementing the intelligent robot-based joint inspection method for smart power plants according to any one of claims 1-9, characterized in that, include: The system includes a data acquisition module, an inspection network construction module, a precise positioning module, a digital twin prediction module, and a real-time control module. The data acquisition module is used to collect path information within the smart power plant area in real time; The inspection network construction module is used to construct an inspection network based on the real-time collected path information, and to set the inspection route and reference points; The precise positioning module is used to precisely locate the intelligent robot based on the constructed inspection network and the set reference points. The digital twin prediction module is used to construct a digital twin prediction model based on the precise positioning of the intelligent robot, and to predict the movement of the intelligent robot based on the constructed digital twin prediction. The real-time control module is used to control the intelligent robot based on the established real-time predictive digital twin model, path planning results, and the current precise positioning of the intelligent robot.

Images