A patrol system configuration method based on standard point library

Abstract

The present invention discloses a patrol system configuration method based on a standard point library, relates to the technical field of drone patrol, and is used to solve the problem of inflexible drone patrol requirements; the present invention establishes an intelligent standard point library and automated point management, and can flexibly generate and dynamically adjust equipment point configurations according to different equipment types, functional requirements and spatial distributions, thereby achieving more accurate and efficient equipment patrol, and introduces intelligent perception and multi-modal joint patrol technology, which improves the accuracy of fault detection through sensor data fusion and intelligent analysis, and optimizes patrol paths and task scheduling to ensure that high-risk equipment is patrolled first and maintained in a timely manner. In addition, the point optimization and dynamic adjustment mechanism can adjust the patrol path and task priority in real time according to the equipment health status, environmental changes and fault warning information, thereby improving the timeliness of patrols and the accuracy of equipment maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle inspection, and more specifically, to a method for configuring an inspection system based on a standard point library. Background Art

[0002] Drone power inspection technology utilizes the high maneuverability and flexibility of drones. By carrying a variety of sensors such as high-definition cameras, infrared thermal imagers, and lidars, it can achieve efficient inspections of transmission lines, poles, insulators, and other power equipment in substations. Drone inspections can cover areas that are difficult to reach with traditional manual inspections, and can significantly improve inspection efficiency and reduce inspection costs through automated path planning and intelligent task allocation.

[0003] Deficiencies in existing technologies: In traditional substation equipment inspection management, equipment inspection efficiency is generally low. Traditional inspection methods usually rely on manual inspections or simple periodic inspections, and cannot obtain the operating status and health data of the equipment in real time, resulting in a time-consuming and labor-intensive inspection process, and it is difficult to ensure comprehensive coverage. Secondly, task priorities are not adjusted in a timely manner, and inspection plans are usually pre-made, failing to respond to changes in equipment health status or emergency fault warnings in a timely manner. The inspection frequency and inspection focus of the equipment cannot be flexibly adjusted according to real-time data and actual risks, thereby affecting the early detection and timely handling of equipment failures. There are blind spots in equipment health monitoring. Traditional monitoring methods mostly rely on single sensor data and lack accurate assessment of the comprehensive health status of the equipment, resulting in insufficient monitoring of potential faults, and even the inability to predict equipment risks, resulting in power loss. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, there is a solution as follows to solve the problem of inflexible requirements for drone patrols in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A patrol system configuration method based on a standard point library comprises the following steps:

[0007] Based on the equipment type, functional requirements and spatial distribution, an extended equipment point model is constructed, and a corresponding point model is generated for each type of equipment;

[0008] Automatically generate point configuration based on the equipment list and standard point library, dynamically adjust patrol points, and optimize task priority based on equipment operating status and health index;

[0009] Collect and integrate different types of data, detect equipment failures through intelligent analysis, formulate multi-modal inspection tasks and optimize routes;

[0010] Monitor equipment health status and patrol demand changes in real time to adjust patrol routes, dynamically update point configurations and task priorities, and prioritize detection and processing of high-risk equipment.

[0011] In a preferred embodiment, based on the equipment type, functional requirements and spatial distribution, an extended equipment point model is constructed, and a corresponding point model is generated for each type of equipment. The specific steps are as follows:

[0012] Classify equipment types according to their physical properties, functional categories, and working requirements, and set different equipment point models for each type of equipment;

[0013] Describe the space and function, determine the space coordinates according to the equipment location, and assign different task requirements according to the equipment function. The equipment function includes the monitoring indicators and patrol frequency of the equipment. The monitoring indicators include temperature, vibration, and humidity.

[0014] A standard point model corresponding to each type of equipment is constructed based on the classification information of the equipment category. The standard point model includes spatial coordinates, equipment functions, patrol requirements, and state-dependent factors.

[0015] In a preferred embodiment, the point configuration is automatically generated according to the equipment list and the standard point library, and the patrol points are dynamically adjusted. The specific steps include:

[0016] For each device in the substation, the type identification of the device is matched with the point template in the standard point library. The equipment list includes the device ID, type, and location. The corresponding standard point model is searched and referenced through the device type information;

[0017] Through mapping relationships, combined with the model and location parameters of the equipment, patrol points are automatically generated, and point configurations are automatically assigned to each device according to the spatial location of the equipment and task requirements;

[0018] Associate the standard point library with the equipment operating status, and dynamically adjust the point priority and patrol task allocation based on the equipment health and operating status.

[0019] In a preferred implementation, the task priority is optimized in combination with the equipment operation status and health index, and the specific steps are as follows:

[0020] Use the equipment's operating data, including temperature, pressure, and current, to calculate the equipment health index, and adjust the priority of the equipment points according to the equipment health index. i The calculation expression of HI i =α·T i +β·V i +γ·P i , where Ti is the temperature of device i, V i is the vibration state of device i, P i is the pressure or load of equipment i, α, β, γ are weight coefficients;

[0021] When the equipment status changes, adjust the patrol points according to the current load changes of the equipment;

[0022] Dynamically adjust the point inspection frequency f according to the equipment health index i , update point configuration: f i (t) = f i0 ·(1+λ·HI i (t)), where f i0 is the default patrol frequency, λ is the dynamic adjustment factor, which controls the growth ratio of the patrol frequency; HI i (t) is the device health index of device i at time t;

[0023] Dynamically optimize equipment inspection points, predict areas where equipment failures occur based on historical data and real-time monitoring data, and adjust inspection tasks at equipment points based on the prediction results.

[0024] In a preferred embodiment, different types of data are collected and integrated, and equipment failures are detected through intelligent analysis, multi-modal inspection tasks are formulated, and paths are optimized, including the following steps:

[0025] Collect data from multiple sensors to collect real-time operating data of substation equipment. Sensors include temperature sensors, humidity sensors, vibration sensors, current sensors, drone-mounted high-definition cameras, and infrared thermal imagers.

[0026] Fuse data from different sensors as device status information;

[0027] Combine the sensor data, equipment location and equipment health status in the equipment status information to formulate multimodal inspection tasks. Based on the priority of multimodal inspection tasks, equipment health status and sensor working status, use scheduling algorithms to perform task scheduling and path optimization.

[0028] When the equipment health index exceeds the preset threshold, an alarm is automatically issued and inspection equipment is dispatched for inspection on a priority basis.

[0029] In a preferred embodiment, the patrol path is adjusted by real-time monitoring of the health status of the equipment and the changes in patrol requirements, and the point configuration and task priority are dynamically updated to perform priority detection and processing of high-risk equipment, including the following steps:

[0030] Changes in equipment health index and patrol demand trigger point adjustments. The formula is: Among them, Tri i is the trigger condition for adjusting the position of device i, I(·) is the indicator function, which returns 1 when the device status meets the fault or abnormal condition, otherwise it returns 0, D ik is the state change value of the kth monitoring point of device i, T k is the environmental or operating condition of the monitoring point k, HI i is the device health index of device i, Thr i is the device health index threshold of device i, K is the total number of monitoring points of device i, Thres k is the threshold of the kth monitoring point;

[0031] Re-optimize intelligent paths and re-plan points. Based on dynamically changing point requirements and adjusted points, the patrol path will be re-planned.

[0032] The path optimization goal is to minimize the total patrol time T total , Among them, D i is the patrol distance of device i, task time (i) is the patrol time of device i, Priority i is the task priority of device i, which is determined by the device health index and fault warning conditions;

[0033] During each inspection, sensor data, camera images, and the real-time status of patrol equipment are continuously collected and updated. When new data feedback indicates that the equipment status has changed or a new problem has occurred, the point configuration is automatically updated and the inspection task is rescheduled.

[0034] When a fault warning is triggered, the patrol task is automatically adjusted according to the abnormality type;

[0035] When the point configuration is dynamically adjusted, the patrol path is replanned, the patrol order is adjusted according to the new points and equipment priorities, and the patrol tasks are reallocated to drones and ground robot equipment according to the current task load;

[0036] According to the load capacity, health status and task priority of the equipment, the task redistribution and path adjustment formula is: Among them, P is the path set, P i is a path in the path set, D i is the patrol distance of device i, task time (i) is the patrol time of device i, Priority i is the task priority of device i.

[0037] Technical effects and advantages of a patrol system configuration method based on a standard point library of the present invention:

[0038] The present invention establishes an intelligent standard point library and automated point management, which can flexibly generate and dynamically adjust equipment point configurations according to different equipment types, functional requirements and spatial distributions, thereby achieving more accurate and efficient equipment inspections. It introduces intelligent perception and multimodal joint inspection technology, and improves the accuracy of fault detection through sensor data fusion and intelligent analysis, and optimizes inspection paths and task scheduling to ensure that high-risk equipment receives priority inspections and timely maintenance. In addition, the point optimization and dynamic adjustment mechanism can adjust the inspection path and task priority in real time according to the equipment health status, environmental changes and fault warning information, thereby improving the timeliness of inspections and the accuracy of equipment maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The present invention is a flowchart of a patrol system configuration method based on a standard point library. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] In order to achieve the above objectives, Figure 1 A structural schematic diagram of a patrol system configuration method based on a standard point library of the present invention is given, which specifically includes the following steps:

[0042] Based on the equipment type, functional requirements and spatial distribution, an extended equipment point model is constructed, and a corresponding point model is generated for each type of equipment;

[0043] Automatically generate point configuration based on the equipment list and standard point library, dynamically adjust patrol points, and optimize task priority based on equipment operating status and health index;

[0044] Collect and integrate different types of data, detect equipment failures through intelligent analysis, formulate multi-modal inspection tasks and optimize routes;

[0045] Monitor equipment health status and patrol demand changes in real time to adjust patrol routes, dynamically update point configurations and task priorities, and prioritize detection and processing of high-risk equipment.

[0046] Step 1: Establish an intelligent standard point library to adapt to various types and layouts of substation equipment. Each point of each equipment needs to be modeled according to its spatial distribution, functional requirements and patrol task characteristics to form a point model with high flexibility and scalability. The specific steps are as follows:

[0047] Classify equipment types according to their physical properties, functional categories, and working requirements. Each type of equipment (such as transformers, circuit breakers, current transformers, etc.) will have different equipment point models.

[0048] Conduct spatial and functional descriptions, i.e. each equipment point contains spatial coordinates (such as GPS position or relative position), and assigns different task requirements according to equipment functions. Specific functional requirements may involve equipment monitoring indicators (such as temperature, vibration, humidity, etc.) and patrol frequency;

[0049] Model construction: When designing the standard point library, use the classification information of equipment categories to build a standard point model corresponding to each type of equipment. The model not only contains static spatial information (such as coordinates), but also the state-dependent factors of the equipment (such as load, voltage, etc.);

[0050] Each equipment point model can be expressed in the following form: i =(X i , Y i , Z i , f i , M i , Θ i ), where X i , Y i , Z i are the spatial coordinates of device i (which can be global positioning system (GPS) coordinates or relative coordinates), f i is the functional requirement of equipment i, such as monitoring target (temperature, pressure, etc.); M i is the state dependency factor of device i, reflecting its working state or health condition; Θ i It is the inspection demand of the equipment, such as inspection frequency and monitoring indicators. After the equipment point model is established, all equipment points can be automatically generated according to the equipment type.

[0051] Construct the mapping relationship between the equipment point model and the equipment type, that is, determine the mapping relationship between the equipment type and the standard point model, and automatically configure the equipment point according to the specific equipment list. The specific processing steps are as follows:

[0052] In terms of equipment list and point mapping, for each device in the substation, the type identification of the device is matched with the point template in the standard point library. The equipment list consists of information such as device ID, type, and location. The corresponding standard point model is found and referenced through the device type information;

[0053] Point generation and configuration, that is, automatically generating specific inspection points through mapping relationships and combining specific parameters of the equipment (such as model, location, etc.). In this process, point configuration is automatically assigned to each device based on the spatial location of the device and task requirements;

[0054] Assume that the device type is T and the point model is M(T), then the mapping relationship between the device type and the point model is: i =M(T i ), here, P i is the point configuration of the i-th device, T i is the type of device i, M(T i ) is the standard point model corresponding to this type of equipment.

[0055] Associate the point database with the equipment operating status, and dynamically adjust the point priority and patrol task allocation based on the health status and operating status of the equipment;

[0056] The equipment health index is calculated using the equipment's operating data (such as temperature, pressure, current and other parameters) to indicate the equipment's health status. This index can be used as a reference for equipment inspection priority. According to the equipment's health index, the priority of the equipment points is adjusted. Equipment with poor health status requires more inspection attention, so the inspection frequency of its points is increased. i improve;

[0057] When the equipment status changes, the patrol points are adjusted according to the current working status of the equipment (such as load changes). Specifically, when the equipment is running under high load or abnormal conditions, the system will increase the patrol frequency of the corresponding points and dynamically adjust the monitoring requirements of the points according to real-time data. The equipment health index HI i The calculation of HI can be performed by the following weighted formula: i =α·T i +β·V i +γ·P i , where T i is the temperature of device i, V i is the vibration state of device i, P i is the pressure or load of equipment i, α, β, and γ are the corresponding weight coefficients, reflecting the impact of different parameters on the health of the equipment;

[0058] According to the equipment health index, the point inspection frequency f can be dynamically adjusted i , update the point configuration model: fi (t) = f i0 ·(1+λ·HI i (t)), where f i0 is the default patrol frequency, λ is the dynamic adjustment factor, which controls the growth rate of patrol frequency, HI i (t) is the device health index of device i at time t;

[0059] At the same time, the equipment inspection points are dynamically optimized to ensure priority inspections of key areas. That is, historical data and real-time monitoring data are combined with machine learning models (such as random forests, support vector machines, etc.) to predict areas where equipment failures may occur. According to the prediction results, the inspection tasks of the corresponding points are adjusted to give more attention to areas with higher failure risks. The spatial coordinates of the equipment points are combined with real-time obstacle information, and path planning algorithms (such as A* or Di jkstra algorithms) are used to optimize the inspection path, reduce inspection time and distance, and ensure that key equipment areas are not missed.

[0060] Step 2: Based on the established intelligent standard point library and the equipment list, automatically generate point configuration. The specific steps are as follows:

[0061] Input the equipment list. Based on the actual equipment list of the substation, the system will automatically obtain the information of all the equipment to be inspected, including equipment ID, type, location, model, etc. The equipment list may be provided in the form of a database table or other electronic form;

[0062] According to the equipment type (such as transformer, circuit breaker, current transformer, etc.), the corresponding point template is retrieved from the standard point library. Each equipment has a corresponding standard point model, which contains all the necessary patrol points and monitoring requirements of the equipment. i To find the matching standard point model M(T i ), thereby generating specific point configuration for each device;

[0063] Automatically generate point configurations based on specific equipment parameters (such as location, equipment status, patrol requirements, etc.). Each point configuration includes spatial location, patrol requirements, monitoring indicators, etc. After the equipment list and the point library are matched, the system will fill in the specific parameters of each equipment point through an automated algorithm, such as patrol frequency, sensor type, etc. Once the equipment point configuration is generated, the system will store these configurations in the point management database and associate them with the equipment list to establish a two-way binding relationship between the equipment and the point. The initialization process of the point configuration can be expressed as: i =f(E i ,M(T i )), where C i is the final point configuration of device i, Ei is the specific parameters of device i (such as location, type, etc.), M(T i ) is the standard point model;

[0064] Based on the equipment list and standard point library, all equipment can be processed in batches, and the corresponding point configuration can be automatically generated for each equipment. After the point configuration is generated, the system will automatically verify whether each point meets the actual needs and standard requirements of the equipment. If a point configuration that does not meet the requirements is found, the system will automatically feedback and provide optimization suggestions or adjustment operations;

[0065] Once the point configuration is generated, the patrol system will automatically store all point information into the point database and keep it synchronized with the equipment information. The patrol system supports the addition, deletion and modification of point information. If some equipment is replaced or relocated, users can dynamically update the points through the system. After the point configuration is generated, the system will compare and accept the points according to the preset standards and actual patrol requirements. Through point comparison, it ensures that all equipment points meet the actual patrol requirements. During the comparison process, if any non-compliant points are found, the patrol system will mark them and propose optimization plans.

[0066] Step 3: Conduct intelligent perception and multi-modal joint inspection. Through intelligent perception technology (such as sensor fusion, visual recognition, etc.) and multi-modal joint inspection (such as the coordinated work of drones, cameras, sensors and other equipment), the comprehensiveness and accuracy of inspections are improved. Through the joint processing and intelligent analysis of multiple sensor information, the health status and potential faults of substation equipment can be more efficiently monitored and warned. The specific steps are as follows:

[0067] Carry out data collection from multiple sensors, and collect the operation data of substation equipment in real time by deploying different types of sensors (such as temperature sensors, humidity sensors, vibration sensors, current sensors, etc.). In addition, use drones equipped with high-definition cameras, infrared thermal imagers and other equipment to collect images and videos, and further obtain the appearance and temperature distribution information of the equipment;

[0068] Collect data for fusion, that is, fuse the data from different sensors to obtain more accurate equipment status information. The fusion of multimodal sensor data can be achieved through deep learning or traditional data fusion algorithms (such as Kalman filtering, Bayesian inference, etc.), thereby making up for the limitations of a single sensor and improving the reliability and accuracy of the data;

[0069] Based on the fused sensor data, machine learning models (such as neural networks, support vector machines, decision trees, etc.) are used for intelligent analysis and fault diagnosis. By training the model, abnormal conditions and potential faults of the equipment can be identified. For example, by analyzing the changing trends of parameters such as temperature, humidity, and vibration, it is possible to identify whether there are signs of equipment overload or impending failure. The health status of the equipment is evaluated by combining the historical data and real-time monitoring data of the equipment. The equipment health index plays an important role in this process. The model quantitatively scores the health status of the equipment based on its health index.

[0070] Combining multiple sensor data, equipment locations and equipment health status in the equipment status information, a multimodal inspection task is formulated. Different types of sensors (such as drones, ground robots, handheld terminals, etc.) can work together to perform multimodal joint inspections at different equipment operating states and locations. For example, when a drone detects an abnormality on the surface of a device, a ground robot can be immediately dispatched to conduct a more detailed inspection. Based on the priority of the multimodal inspection task, the equipment health status and the working status of the sensor, a scheduling algorithm (such as genetic algorithm, A* path planning, particle swarm optimization, etc.) is used for task scheduling and path optimization. The goal is to ensure that key equipment is inspected first by minimizing the inspection time and maximizing the inspection efficiency. For example, the goal of task scheduling is to minimize the total inspection time T total : Among them, D ij is the path length between device i and device j, task time (i, j) is the time required for the task to go from device i to device j;

[0071] During the inspection process, the system monitors the working status of each sensor and inspection equipment in real time, and synchronizes with the cloud platform through data streams to ensure real-time data updates. Users can view the real-time status of the equipment and the progress of the inspection through a visual interface;

[0072] Based on intelligent analysis and fault diagnosis results, it can provide real-time fault warnings. When the equipment health index HI or monitoring indicators exceed the preset threshold, the system will automatically issue an alarm and prioritize the dispatch of inspection equipment for inspection. It will automatically make decisions and respond based on the type of fault. For example, when a device overheats, the system can automatically dispatch the air conditioning system to cool it down, or notify the inspection personnel to go to the site for processing.

[0073] Through intelligent perception and multi-modal joint inspection, combined with data fusion, intelligent analysis and fault diagnosis algorithms of multiple sensors, the system can monitor the health status of substation equipment in real time and provide accurate fault warnings. On this basis, the system automatically schedules inspection tasks and optimizes inspection paths, while ensuring the efficiency and real-time nature of the inspection process through data synchronization and real-time monitoring.

[0074] Step 4: Dynamically optimize and adjust the patrol points according to the equipment's operating status, patrol requirements, environmental changes, and fault warning information. Automatically adjust the patrol path and points when equipment abnormalities, faults occur, or the environment changes to ensure that patrol efficiency and equipment health are monitored and managed in real time. The specific steps are as follows:

[0075] Detect patrol demand changes. Based on the health status of the equipment, environmental monitoring data, and external interference (such as weather changes, power grid fluctuations, etc.), the patrol system will evaluate the patrol demand of the equipment. For example, when the health index of a certain equipment is lower than the set threshold, the patrol system will automatically adjust the patrol frequency or path of the equipment to give priority to the inspection;

[0076] The point dynamic adjustment trigger is when the device status changes or there is an emergency (such as device failure, temperature abnormality, etc.). The system will trigger the point adjustment according to the new monitoring data. For example, when the device temperature exceeds the preset threshold, the system will adjust the patrol path and give priority to patrolling the monitoring points of the device.

[0077] Equipment health index and patrol demand change trigger point adjustment formula: Among them, Tri i is the trigger condition for adjusting the position of device i, I(·) is the indicator function, which returns 1 when the device status meets the fault or abnormal condition, otherwise it returns 0, D ik is the state change value of the kth monitoring point of device i, T k is the environment or operating conditions (such as temperature, humidity, etc.) of the monitoring point k, HI i is the device health index of device i, Thr i is the device health index threshold of device i, K is the total number of monitoring points of device i, Thres k is the threshold of the kth monitoring point;

[0078] Re-perform intelligent path optimization and point re-planning. Based on the dynamically changing point requirements and the adjusted points, the system will re-plan the patrol path. Using the path optimization algorithm, while ensuring the shortest time or minimum energy consumption, ensure the patrol coverage of key points of the equipment. When optimizing the path, it is necessary to consider factors such as the health status of the equipment, the priority of the patrol task, and the avoidance of obstacles. The system adjusts the patrol priority of each point according to the health status of the equipment (such as the equipment health index) and the urgency of the task. For example, when the health index of a certain device is low, the system will automatically increase the patrol frequency and priority of the device to detect potential faults in a timely manner. The path optimization goal is to minimize the total patrol time T total , which takes into account the equipment health status and point priority, Among them, Di is the patrol distance of device i, task time (i) is the patrol time of device i, Priority i is the task priority of device i, which is determined by the device health index and fault warning conditions;

[0079] The priority of the equipment task is determined by the equipment's health index and fault warning conditions. The priority is determined by comprehensively considering the health index (reflecting the health status of the equipment) and the severity of the fault warning (reflecting the risk of the equipment failing). The expression is as follows: Among them, HI i is the device health index of device i. The lower the device health index value, the worse the device status is, which means that the device needs a higher priority for inspection or maintenance. max is the maximum value of the device health index (usually 1, indicating that the device is in the best health state), which is used to standardize the device health index so that it is always between 0 and 1; w1 is the weight coefficient of the health index, which is used to adjust the impact of the health index on the priority, and is usually set to a value between 0 and 1, reflecting the importance of the health status to the task priority; Alert i Alert is the fault warning status of device i (generating a warning value 0 or 1), which is a binary indicator variable. i =1, otherwise Alert i =0, if the equipment fault warning occurs, it means that the equipment may fail soon and operation and maintenance measures need to be taken immediately; w2 is the weight coefficient of the fault warning, which is used to adjust the impact of the fault warning on the task priority; it is usually set to a value between 0 and 1, reflecting the impact of the fault warning on the task priority;

[0080] During each inspection, the system continuously collects and updates sensor data, camera images, and the real-time status of patrol equipment. When new data feedback indicates that the equipment status has changed or a new problem has occurred, the system automatically updates the point configuration and reschedules the inspection task. Based on the feedback of real-time data, the system will make real-time adjustments to the points. For example, when it is detected that the temperature of the equipment is gradually rising, the system will automatically adjust the patrol path, add the point of the equipment to the current patrol path in advance, or increase the number of patrols.

[0081] When a fault warning is triggered (such as the equipment health index exceeds the threshold, or the sensor data is abnormal), the system will automatically adjust the patrol task according to the abnormal type. For example, if a device fault warning is triggered, the system will immediately adjust the patrol task, set the point of the device as an emergency task, adjust the patrol priority and shorten the patrol cycle. The system will dynamically update the point configuration according to the warning information to ensure that the patrol of abnormal equipment can be carried out as soon as possible to reduce the probability of failure: Alert i =Thre i -HI i , NewPriority i =Priority i ·I (Alert i >0), where Alert i is the warning value of device i, I (Alert i >0) is an indicator function, which means that when the health index of the device exceeds the threshold, it returns 1. i is the new task priority of device i, which increases the patrol priority of the device in the early warning response. i is the device health index threshold of device i.

[0082] When the point configuration is dynamically adjusted, the patrol path is replanned and the patrol order is adjusted according to the new points and equipment priorities to ensure that the equipment can detect and handle abnormalities as soon as possible. If a device fails or the patrol task changes, the patrol task is reallocated to drones, ground robots and other equipment according to the current task load. When the task is redistributed, the load capacity, health status and priority of the equipment are taken into consideration. The formula for task redistribution and path adjustment is: Among them, P is the set of possible paths, P i is a path in the path set, D i is the patrol distance of device i, task time (i) is the patrol time of device i, Priority i is the task priority of device i;

[0083] Through point optimization and dynamic adjustment, the system can automatically adjust patrol tasks when equipment status changes, the environment changes, or fault warnings occur. The combination of dynamic point adjustment, path optimization, and task redistribution can effectively improve patrol efficiency and give priority to detection and processing when equipment failures or abnormalities occur. It utilizes equipment health status, environmental monitoring data, and real-time feedback to ensure continuous health monitoring and intelligent maintenance of substation equipment.

[0084] It should be noted that the threshold information in this embodiment is pre-set by professionals and will not be explained in detail here. Some parameter English letters in the embodiments have the same situation, but different meanings are explained when used, which will not be explained one by one here.

[0085] The present invention establishes an intelligent standard point library and automated point management, which can flexibly generate and dynamically adjust equipment point configurations according to different equipment types, functional requirements and spatial distributions, thereby achieving more accurate and efficient equipment inspections. It introduces intelligent perception and multimodal joint inspection technology, and improves the accuracy of fault detection through sensor data fusion and intelligent analysis, and optimizes inspection paths and task scheduling to ensure that high-risk equipment receives priority inspections and timely maintenance. In addition, the point optimization and dynamic adjustment mechanism can adjust the inspection path and task priority in real time according to the equipment health status, environmental changes and fault warning information, thereby improving the timeliness of inspections and the accuracy of equipment maintenance.

[0086] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0087] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0088] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0089] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0090] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0091] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A patrol system configuration method based on a standard point library, characterized in that: The steps include: Based on the equipment type, functional requirements and spatial distribution, an extended equipment point model is constructed, and a corresponding point model is generated for each type of equipment; Automatically generate point configuration based on the equipment list and standard point library, dynamically adjust patrol points, and optimize task priority based on equipment operating status and health index; Collect and integrate different types of data, detect equipment failures through intelligent analysis, formulate multi-modal inspection tasks and optimize routes; Monitor equipment health status and patrol demand changes in real time to adjust patrol routes, dynamically update point configurations and task priorities, and prioritize detection and processing of high-risk equipment.

2. According to claim 1, a patrol system configuration method based on a standard point library is characterized in that: Based on the equipment type, functional requirements and spatial distribution, an extended equipment point model is constructed, and a corresponding point model is generated for each type of equipment. The specific steps are as follows: Classify equipment types according to their physical properties, functional categories, and working requirements, and set different equipment point models for each type of equipment; Describe the space and function, determine the space coordinates according to the equipment location, and assign different task requirements according to the equipment function. The equipment function includes the monitoring indicators and patrol frequency of the equipment. The monitoring indicators include temperature, vibration, and humidity. A standard point model corresponding to each type of equipment is constructed based on the classification information of the equipment category. The standard point model includes spatial coordinates, equipment functions, patrol requirements, and state-dependent factors.

3. According to claim 2, a patrol system configuration method based on a standard point library is characterized in that: According to the equipment list and standard point library, point configuration is automatically generated and patrol points are dynamically adjusted. The specific steps include: For each device in the substation, the type identification of the device is matched with the point template in the standard point library. The equipment list includes the device ID, type, and location. The corresponding standard point model is searched and referenced through the device type information; Through mapping relationships, combined with the model and location parameters of the equipment, patrol points are automatically generated, and point configurations are automatically assigned to each device according to the spatial location of the equipment and task requirements; Associate the standard point library with the equipment operating status, and dynamically adjust the point priority and patrol task allocation based on the equipment health and operating status.

4. The patrol system configuration method based on the standard point library according to claim 3 is characterized in that: Combine the equipment operation status and health index to optimize the task priority. The specific steps are as follows: Use the equipment's operating data, including temperature, pressure, and current, to calculate the equipment health index, and adjust the priority of the equipment points according to the equipment health index. i The calculation expression of HI i =α·T i +β·V i +γ·P i , where T i is the temperature of device i, V i is the vibration state of device i, P i is the pressure or load of equipment i, α, β, γ are weight coefficients; When the equipment status changes, adjust the patrol points according to the current load changes of the equipment; Dynamically adjust the point inspection frequency f according to the equipment health index i , update point configuration: f i (t) = f i0 ·(1+λ·HI i (t)), where f i0 is the default patrol frequency, λ is the dynamic adjustment factor, which controls the growth ratio of the patrol frequency; HI i (t) is the device health index of device i at time t; Dynamically optimize equipment inspection points, predict areas where equipment failures occur based on historical data and real-time monitoring data, and adjust inspection tasks at equipment points based on the prediction results.

5. According to claim 4, a patrol system configuration method based on a standard point library is characterized in that: Collect and fuse different types of data, detect equipment failures through intelligent analysis, formulate multimodal inspection tasks and optimize paths, including the following steps: Collect data from multiple sensors to collect real-time operating data of substation equipment. Sensors include temperature sensors, humidity sensors, vibration sensors, current sensors, drone-mounted high-definition cameras, and infrared thermal imagers. Fuse data from different sensors as device status information; Combine the sensor data, equipment location and equipment health status in the equipment status information to formulate multimodal inspection tasks. Based on the priority of the multimodal inspection tasks, equipment health status and sensor working status, use the scheduling algorithm to perform task scheduling and path optimization. When the equipment health index exceeds the preset threshold, an alarm is automatically issued and inspection equipment is dispatched for inspection on a priority basis.

6. The patrol system configuration method based on the standard point library according to claim 5 is characterized in that: Real-time monitoring of equipment health status and patrol demand changes to adjust patrol routes, dynamically update point configurations and task priorities, and prioritize detection and processing of high-risk equipment, including the following steps: Changes in equipment health index and patrol demand trigger point adjustments. The formula is: Among them, Tri i is the trigger condition for adjusting the position of device i, I(·) is the indicator function, which returns 1 when the device status meets the fault or abnormal condition, otherwise it returns 0, D ik is the state change value of the kth monitoring point of device i, T k is the environmental or operating condition of the monitoring point k, HI i is the device health index of device i, Thr i is the device health index threshold of device i, K is the total number of monitoring points of device i, shres k is the threshold of the kth monitoring point; Re-optimize intelligent paths and re-plan points. Based on dynamically changing point requirements and adjusted points, the patrol path will be re-planned. The path optimization goal is to minimize the total patrol time T total , Among them, D i is the patrol distance of device i, task time (i) is the patrol time of device i, Priority i is the task priority of device i, which is determined by the device health index and fault warning conditions; During each inspection, sensor data, camera images, and the real-time status of patrol equipment are continuously collected and updated. When new data feedback indicates that the equipment status has changed or a new problem has occurred, the point configuration is automatically updated and the inspection task is rescheduled. When a fault warning is triggered, the patrol task is automatically adjusted according to the abnormality type; When the point configuration is dynamically adjusted, the patrol path is replanned, the patrol order is adjusted according to the new points and equipment priorities, and the patrol tasks are reallocated to drones and ground robot equipment according to the current task load; According to the load capacity, health status and task priority of the equipment, the task redistribution and path adjustment formula is: Among them, P is the path set, P i is a path in the path set, D i is the patrol distance of device i, taak time (i) is the patrol time of device i, Priority i is the task priority of device i.

Images