Electric power inspection scheduling method and system based on artificial intelligence

Abstract

The invention provides an electric power inspection scheduling method and system based on artificial intelligence, relates to the technical field of resource scheduling, solves the problem of data islands, realizes information interconnection and intercommunication between different devices and systems, and ensures effective integration and analysis of device operation states, environment monitoring and historical fault data. The intelligent analysis capability is improved by combining machine learning and deep learning technologies, equipment fault risk assessment and task priority calculation are modeled by adopting a neural network algorithm, and the fault early warning accuracy and the intelligent level of task scheduling are improved; meanwhile, aiming at the problem of insufficient scheduling optimization of a traditional system, optimal resource configuration and efficient task execution are ensured by monitoring the state of routing inspection resources in real time, performing dynamic adjustment, optimizing resource configuration and routing inspection paths, calculating a comprehensive scheduling adaptability evaluation value Ae and optimizing a scheduling scheme according to an evaluation result; and the execution efficiency and the scheduling capability of the inspection task are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of resource scheduling, and particularly to an artificial intelligence-based power inspection scheduling method and system. Background Art

[0002] The power inspection scheduling system originated from the traditional manual inspection mode. In the early stage, it relied on manual regular inspection of transmission lines and substation equipment, which had problems such as high labor costs, low efficiency, and high safety risks. With the expansion of the power system scale and the development of information technology, inspection means based on communication technology and automation equipment have been gradually introduced, such as drone inspection, online monitoring systems, and intelligent sensors. The development of these technologies has significantly improved the timeliness and accuracy of power equipment fault detection, but there are still deficiencies in data integration, real-time scheduling, and intelligent analysis. In recent years, with the rapid development of Internet of Things (IoT), big data, and artificial intelligence (AI) technologies, the power inspection scheduling system has been continuously evolving towards intelligence, automation, and informatization, achieving efficient scheduling of inspection tasks and precise monitoring of equipment status.

[0003] However, in practical applications, the existing power inspection scheduling systems often have the following technical drawbacks:

[0004] 1. Data island problem: There is a lack of effective data interconnection and interoperability between different devices and systems, resulting in isolated information and affecting comprehensive analysis and decision-making;

[0005] 2. Limited intelligent analysis ability: The existing systems have insufficient intelligence in big data processing and fault prediction, and it is difficult to achieve precise early warning;

[0006] 3. Insufficient scheduling optimization: The scheduling method of inspection tasks is relatively single, and the optimal allocation of resources and task priorities are not fully considered. Summary of the Invention

[0007] The purpose of the present invention is to provide an artificial intelligence-based power inspection scheduling method to solve the problems raised in the above background art.

[0008] The present invention is achieved through the following technical solutions:

[0009] On the one hand, the present invention provides an artificial intelligence-based power inspection scheduling method, including the following steps:

[0010] S1. Obtain the power equipment distribution map, and label the serial numbers for various power equipment, inspection personnel, and inspection tasks; collect the operation status data, environmental monitoring data, and historical fault data of power equipment in real time, and then integrate them using a multi-source data interface to obtain a global device status data set, and construct a power equipment global data fusion platform;

[0011] S2. Based on the global device status data set, calculate the fault risk assessment value Fr and the device importance weight coefficient Wz of each power device respectively, generate the device inspection priority coefficient Px, sort all power devices according to the device inspection priority coefficient Px, select the devices to be inspected, and locate the devices to be inspected in the power device distribution map;

[0012] S3. Based on the devices to be inspected, real-time monitor the data related to the inspection resource status, construct a resource status data set, calculate and fit the inspection resource availability index Ry and the task urgency coefficient Tj, obtain the resource scheduling adaptability Pd and evaluate it, dynamically adjust the inspection resources and generate a preliminary inspection scheduling plan;

[0013] S4. Conduct real-time simulation calculation on the path of the inspection task, generate and evaluate the comprehensive scheduling adaptability evaluation value Ae, and judge whether the preliminary scheduling plan meets the inspection requirements according to the evaluation content of the comprehensive scheduling adaptability evaluation value Ae; if the inspection requirements are not met, readjust the scheduling priority and generate a secondary inspection scheduling plan;

[0014] S5. Real-time monitor the relevant dynamic data during the execution of the inspection task, including device operation status data, inspection progress data and environmental change data; evaluate by calculating the inspection task execution deviation value Ex, start the adaptive scheduling optimization mechanism, and adjust the inspection path and resource allocation strategy until the inspection task is completed.

[0015] Specifically, the step S1 specifically includes:

[0016] S101. Obtain the geographical location information and type information of power devices through the power device distribution information collection module, generate a power device distribution map, and respectively mark unique serial numbers for all power devices, inspection personnel and inspection tasks;

[0017] S102. By deploying various sensors and intelligent terminals on power devices, real-time collect power device operation status data, environmental monitoring data and historical fault data, and perform standardized preprocessing;

[0018] S103. Adopt a data fusion algorithm to integrate power device operation status data, environmental monitoring data and historical fault data from different sources, and finally construct a global device status data set.

[0019] Specifically, the step S2 specifically includes:

[0020] Extract the device operation status data and historical fault data from the global device status data set, use the neural network machine learning algorithm to model and analyze the device operation status, obtain the real-time operation parameter volatility Pr, device operation duration Tm, vibration abnormality degree Vd, device category weight Cl, device geographical location sensitivity Gr, and task association degree coefficient Rt, and perform dimensionless processing; calculate the fault risk assessment value Fr and importance weight coefficient Wz of each power device, and the specific calculation formulas are as follows:

[0021]

[0022] Specifically, the step S2 further includes:

[0023] Based on the fault risk assessment value Fr and the device importance weight coefficient Wz, generate the device inspection priority coefficient Px through the priority calculation model, and the specific calculation formula is as follows:

[0024] Px = α·Fr + β·Wz

[0025] In the formula, α is the weight coefficient of the fault risk assessment value Fr, β is the weight coefficient of the device importance weight coefficient Wz, and α + β = 1, 0 < α < 1, 0 < β < 1.

[0026] Specifically, the step S3 includes:

[0027] Integrate the inspection resource status-related data from different sources using the multi-source data interface, construct a resource status data set, and calculate the inspection resource availability index Ry and task urgency coefficient Tj, and the specific calculation formulas are as follows:

[0028]

[0029] Tj = ln(1 + Tfx×Tyc×Tqz)

[0030] In the formula, Rzy represents the current load rate of the resources in the resource status data set, Rkx represents the idle duration of the resources in the resource status data set, Rdl represents the geographical location offset of the resources in the resource status data set, Tfx represents the device fault risk assessment value in the resource status data set, Tyc represents the duration of continuous device operation abnormality in the resource status data set, Tqz represents the device importance weight coefficient in the resource status data set, ln is the natural logarithm, representing the logarithmic function with the mathematical constant e as the base.

[0031] Specifically, the step S3 further includes:

[0032] Use the following formula to fit the inspection resource availability index Ry and the task urgency coefficient Tj to obtain the resource scheduling adaptability Pd:

[0033]

[0034] Compare and evaluate according to the preset resource scheduling adaptation threshold Q and the resource scheduling adaptation degree Pd. The specific evaluation content is as follows:

[0035] If the resource scheduling adaptation degree Pd ≥ the resource scheduling adaptation threshold Q: It is determined that the current inspection resources match the task, and a preliminary inspection scheduling plan is generated, including starting the inspection resource scheduling, allocating resources to the corresponding tasks, and entering the task execution stage;

[0036] If the resource scheduling adaptation degree Pd < the resource scheduling adaptation threshold Q: It is determined that the matching degree between the inspection resources and the task does not meet the requirements, and the inspection resources are adjusted. The specific adjustment content is as follows:

[0037] Adjust the inspection resource configuration: Re-evaluate the allocation of inspection personnel and equipment, and give priority to calling idle or efficient resources;

[0038] Optimize the inspection path: Recalculate the optimal path to shorten the inspection response time;

[0039] Delay or merge low-priority tasks: Release resources to meet the requirements of high-priority tasks;

[0040] After the inspection resources are adjusted, recalculate the resource scheduling adaptation degree Pd and compare it with the resource scheduling adaptation threshold Q again until the resource scheduling adaptation degree Pd exceeds or reaches the resource scheduling adaptation threshold Q.

[0041] Specifically, step S4 specifically includes:

[0042] Based on the preliminarily generated inspection scheduling plan, construct an inspection task path simulation model, simulate the execution effects of inspection resources under different paths in real time and conduct comprehensive analysis, obtain the task completion timeliness Asx, resource load balance Afz, and inspection path accessibility Alj, and after dimensionless processing, calculate and obtain the comprehensive scheduling adaptability evaluation value Ae through the following formula:

[0043]

[0044] Compare and evaluate according to the preset scheduling adaptability threshold Qe and the comprehensive scheduling adaptability evaluation value Ae. The specific evaluation content is as follows:

[0045] If the comprehensive scheduling adaptability evaluation value Ae ≥ the scheduling adaptability threshold Qe: Judge that the preliminary scheduling plan meets the inspection requirements, and directly issue an execution instruction to start the inspection task;

[0046] If the comprehensive dispatching adaptability evaluation value Ae < the dispatching adaptability threshold Qe: It is determined that the preliminary dispatching plan does not meet the inspection requirements, then the dispatching priority is dynamically adjusted and a secondary inspection dispatching plan is generated.

[0047] Specifically, step S5 specifically includes:

[0048] By comprehensively analyzing relevant dynamic data during the execution of the monitoring and inspection tasks, the planned inspection resource utilization rate Zy and the actual resource utilization rate Zs in the equipment operation status data, the expected inspection progress Xy and the actual inspection progress Xs in the inspection progress data, and the expected environmental impact coefficient Hy and the actual environmental impact coefficient Hs in the environmental change data are obtained; and the inspection task execution deviation value Ex is calculated through the following formula:

[0049]

[0050] According to the comparison and evaluation between the preset inspection task execution deviation threshold Fx and the inspection task execution deviation value Ex, the following specific evaluation contents are obtained:

[0051] If the inspection task execution deviation value Ex ≤ the inspection task execution deviation threshold Fx: Keep the current dispatching strategy and continue the task execution;

[0052] If the inspection task execution deviation value Ex > the inspection task execution deviation threshold Fx: Automatically trigger the adaptive dispatching optimization mechanism, including:

[0053] Path optimization: Re-plan the inspection path to avoid risk areas and congested sections;

[0054] Resource reallocation: Dynamically adjust inspection personnel or inspection equipment, and call backup resources to supplement the current task;

[0055] Task reorganization: Merge, split or postpone some inspection tasks to adjust the overall task execution efficiency.

[0056] On the other hand, the present invention also provides an artificial intelligence-based power inspection dispatching system, which is applied to the method as described above. The system includes an equipment data fusion module, an equipment failure evaluation module, an inspection resource monitoring module, a dispatching path simulation module, and a task execution optimization module;

[0057] The equipment data fusion module is used to obtain the power equipment distribution map and number various power equipment, inspection personnel, and inspection tasks; collect the power equipment operation status data, environmental monitoring data, and historical failure data in real time, and then use the multi-source data interface for integration to construct a global equipment status data set;

[0058] The device failure assessment module is used to calculate the failure risk assessment value Fr and the device importance weight coefficient Wz of each power device respectively according to the global device status data set, generate the device inspection priority coefficient Px, sort all power devices according to the device inspection priority coefficient Px, select the devices to be inspected, and locate the devices to be inspected in the power device distribution map;

[0059] The inspection resource monitoring module is used to, based on the devices to be inspected, monitor the data related to the inspection resource status in real time, construct a resource status data set, calculate and fit the inspection resource availability index Ry and the task urgency coefficient Tj, obtain the resource scheduling adaptability Pd and evaluate it, dynamically adjust the inspection resources and generate a preliminary inspection scheduling plan;

[0060] The scheduling path simulation module is used to perform real-time simulation calculation on the path of the inspection task, generate and evaluate the comprehensive scheduling adaptability evaluation value Ae, judge whether the preliminary scheduling plan meets the inspection requirements according to the evaluation content of the comprehensive scheduling adaptability evaluation value Ae, and if it does not meet the inspection requirements, readjust the scheduling priority and generate a secondary inspection scheduling plan;

[0061] The task execution optimization module is used to monitor the relevant dynamic data during the execution of the inspection task in real time, including device operation status data, inspection progress data and environmental change data; by calculating and evaluating the inspection task execution deviation value Ex, start the adaptive scheduling optimization mechanism, and adjust the inspection path and resource allocation strategy until the inspection task is completed.

[0062] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0063] (1) By constructing a power device global data fusion platform, the problem of data islands existing in the existing system is effectively solved; the operation status data, environmental monitoring data, historical failure data, etc. of power devices are integrated through multi-source data interfaces, and the data from different sources are uniformly processed by using data fusion algorithms, so as to construct a global device status data set; by pre-labeling devices, inspection personnel and task serial numbers and integrating various types of data, data intercommunication between different systems is ensured, and global monitoring and precise management of power devices are realized.

[0064] (2) By using machine learning algorithms such as neural networks to model and analyze the device operation status data and historical failure data, calculate the device failure risk assessment value Fr and the device importance weight coefficient Wz, and generate the device inspection priority coefficient Px through the priority calculation model; using a deep learning model to analyze the dynamic data during the execution of the inspection task, so as to be able to accurately predict the failure risk and achieve precise early warning, improve the intelligent analysis ability of the system, and ensure the timeliness and effectiveness of the inspection task.

[0065] (3) By real - time monitoring the status data of inspection resources, dynamically adjust the inspection resources and generate a scheduling plan. During the execution of the inspection task, simulate the path and calculate the comprehensive scheduling adaptability evaluation value Ae to determine whether the inspection requirements are met. If the scheduling plan does not meet the requirements, the system makes dynamic adjustments by optimizing the inspection path, adjusting resource allocation, and delaying or merging low - priority tasks, ensuring the optimal allocation of resources and the efficient execution of inspection tasks, and further improving the system's scheduling ability and resource utilization efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings described below are only the preferred embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0067] Figure 1 It is a schematic diagram of the step - by - step process of a power inspection scheduling method based on artificial intelligence of the present invention;

[0068] Figure 2 It is a schematic diagram of the framework structure of a power inspection scheduling system based on artificial intelligence of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] In order to make the objectives, technical solutions and advantages of the present invention more obvious, the following will describe in detail the exemplary embodiments according to the present invention with reference to the drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein. Based on the embodiments of the present invention described herein, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0070] In the following description, a large number of specific details are given to provide a more thorough understanding of the present invention. However, it is obvious to those of ordinary skill in the art that the present invention can be implemented without one or more of these details. In other examples, some well - known technical features are not described to avoid confusion with the present invention.

[0071] It should be understood that the present invention can be implemented in different forms and should not be construed as limited to the embodiments presented herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and will fully convey the scope of the present invention to those skilled in the art.

[0072] The purpose of the terms used herein is only to describe specific embodiments and is not a limitation of the present invention. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms unless the context clearly dictates otherwise. It should also be understood that the terms "comprising" and / or "including", when used in this specification, identify the presence of the stated features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups. As used herein, the term "and / or" includes any and all combinations of the related listed items.

[0073] To thoroughly understand the present invention, detailed structures will be presented in the following description to illustrate the technical solutions proposed by the present invention. The alternative embodiments of the present invention are described in detail below. However, in addition to these detailed descriptions, the present invention may also have other embodiments.

[0074] See Figure 1 , on the one hand, the present invention provides an artificial intelligence-based power inspection scheduling method, including the following steps:

[0075] S1. Obtain the power equipment distribution map, and label the serial numbers for various power equipment, inspection personnel and inspection tasks; collect the power equipment operation status data, environmental monitoring data and historical fault data in real time, and then integrate them using a multi-source data interface to obtain a global device status data set, and build a power equipment global data fusion platform;

[0076] S2. Based on the global device status data set, calculate the fault risk assessment value Fr and the device importance weight coefficient Wz of each power equipment respectively, generate the device inspection priority coefficient Px, and sort all power equipment according to the device inspection priority coefficient Px, select the equipment to be inspected, and locate the equipment to be inspected in the power equipment distribution map;

[0077] S3. Based on the equipment to be inspected, monitor the data related to the inspection resource status in real time, build a resource status data set, calculate the inspection resource availability index Ry and the task urgency coefficient Tj and fit them, obtain the resource scheduling adaptability Pd and evaluate it, dynamically adjust the inspection resources and generate a preliminary inspection scheduling plan;

[0078] S4. Perform real-time simulation calculation on the path of the inspection task, generate a comprehensive scheduling adaptability evaluation value Ae and evaluate it, and judge whether the preliminary scheduling plan meets the inspection requirements according to the evaluation content of the comprehensive scheduling adaptability evaluation value Ae; if the inspection requirements are not met, readjust the scheduling priority and generate a secondary inspection scheduling plan;

[0079] S5. Monitor relevant dynamic data during the execution of the patrol inspection task in real time, including equipment operation status data, patrol inspection progress data, and environmental change data; calculate the execution deviation value Ex of the patrol inspection task and evaluate it, start the adaptive scheduling optimization mechanism, and adjust the patrol inspection path and resource allocation strategy until the patrol inspection task is completed.

[0080] In this embodiment, by constructing a global data fusion platform for power equipment, the problems of annotation and data integration of power equipment, patrol inspection personnel, and tasks are solved, the effective integration of equipment operation status data, environmental monitoring data, and historical fault data is realized, and comprehensive basic data is provided for subsequent decision-making; by combining machine learning algorithms, the fault risk assessment value Fr of power equipment and the equipment importance weight coefficient Wz can be accurately calculated, and the equipment patrol inspection priority coefficient Px is generated, thereby optimizing the sorting and priority of equipment patrol inspection to ensure that high-risk equipment is patrolled in a timely manner; based on real-time monitoring of patrol inspection resource status data and combining the resource availability index Ry and the task urgency coefficient Tj, the patrol inspection resources are dynamically adjusted, the optimal allocation of resources and the balance of task urgency are realized, and the adaptability Pd of the patrol inspection scheduling plan is effectively improved; by calculating the patrol inspection task path through real-time simulation, the comprehensive scheduling adaptability evaluation value Ae is generated, and it is judged whether the scheduling plan meets the patrol inspection requirements through evaluation, and the patrol inspection path and priority are adjusted in a timely manner to optimize the task execution efficiency; through the deep learning model, the dynamic data during the execution of the patrol inspection task is analyzed, the execution deviation value Ex of the patrol inspection task is calculated and evaluated, and the adaptive scheduling optimization mechanism is started, finally ensuring the smooth completion of the patrol inspection task.

[0081] Specifically, the step S1 specifically includes:

[0082] S101. Obtain the geographical location information and type information of power equipment through the power equipment distribution information collection module, generate a power equipment distribution map, and perform unique serial number annotation on all power equipment, patrol inspection personnel, and patrol inspection tasks respectively;

[0083] S102. Deploy various sensors and intelligent terminals on power equipment to collect power equipment operation status data, environmental monitoring data, and historical fault data in real time, and perform standardized preprocessing;

[0084] S103. Use a data fusion algorithm to integrate power equipment operation status data, environmental monitoring data, and historical fault data from different sources, and finally construct a global equipment status data set.

[0085] Specifically, the step S2 specifically includes:

[0086] Extract the device operation status data and historical fault data from the global device status data set, use the neural network machine learning algorithm to model and analyze the device operation status, obtain the real-time operation parameter volatility Pr, device operation duration Tm, vibration abnormality degree Vd, device category weight Cl, device geographical location sensitivity Gr, and task correlation coefficient Rt, and perform dimensionless processing; calculate the fault risk assessment value Fr and importance weight coefficient Wz of each power device. The specific calculation formulas are as follows:

[0087]

[0088] Specifically, the step S2 further specifically includes:

[0089] Based on the fault risk assessment value Fr and the device importance weight coefficient Wz, generate the device inspection priority coefficient Px through the priority calculation model. The specific calculation formula is as follows:

[0090] Px = α·Fr + β·Wz

[0091] In the formula, α is the weight coefficient of the fault risk assessment value Fr, β is the weight coefficient of the device importance weight coefficient Wz, and α + β = 1, 0 < α < 1, 0 < β < 1.

[0092] Exemplarily, sort all power devices according to the inspection priority coefficient Px. By arranging the inspection priority coefficients Px of all devices in descending order of numerical value, form a priority list, and mark the top 50% of the power devices as "devices to be inspected" according to the priority list; secondly, call the device space coordinate data in the power device distribution map to obtain the location information of the devices to be inspected; finally, mark the devices to be inspected in the distribution map.

[0093] Specifically, the step S3 specifically includes:

[0094] Integrate the inspection resource status-related data from different sources using the multi-source data interface, construct a resource status data set, and calculate and obtain the inspection resource availability index Ry and the task urgency coefficient Tj. The specific calculation formulas are as follows:

[0095]

[0096] Tj = ln(1 + Tfx×Tyc×Tqz)

[0097] Wherein, Rzy represents the current load rate of resources in the resource status data set, Rkx represents the idle duration of resources in the resource status data set, Rdl represents the geographical location offset of resources in the resource status data set, Tfx represents the device failure risk assessment value in the resource status data set, Tyc represents the duration of abnormal device operation in the resource status data set, Tqz represents the device importance weight coefficient in the resource status data set, and ln is the natural logarithm, representing the logarithmic function with the mathematical constant e as the base.

[0098] Specifically, step S3 further includes:

[0099] Using the following formula, fit the inspection resource availability index Ry and the task urgency coefficient Tj to obtain the resource scheduling adaptation degree Pd:

[0100]

[0101] Compare and evaluate according to the preset resource scheduling adaptation threshold Q and the resource scheduling adaptation degree Pd. The specific evaluation content is as follows:

[0102] If the resource scheduling adaptation degree Pd ≥ the resource scheduling adaptation threshold Q: It is determined that the current inspection resources match the task, and a preliminary inspection scheduling plan is generated, including starting the inspection resource scheduling, allocating resources to the corresponding tasks, and entering the task execution stage;

[0103] If the resource scheduling adaptation degree Pd < the resource scheduling adaptation threshold Q: It is determined that the matching degree of the inspection resources and the task does not meet the requirements, and the inspection resources are adjusted. The specific adjustment content is as follows:

[0104] Adjust the inspection resource configuration: Re-evaluate the allocation of inspection personnel and equipment, and preferentially call idle or efficient resources;

[0105] Optimize the inspection path: Recalculate the optimal path to shorten the inspection response time;

[0106] Delay or merge low-priority tasks: Release resources to meet the requirements of high-priority tasks;

[0107] After the inspection resources are adjusted, recalculate the resource scheduling adaptation degree Pd and compare it with the resource scheduling adaptation threshold Q again until the resource scheduling adaptation degree Pd exceeds or reaches the resource scheduling adaptation threshold Q.

[0108] Specifically, step S4 includes:

[0109] Based on the preliminary generated inspection and scheduling plan, construct an inspection task path simulation model, simulate the execution effects of inspection resources under different paths in real time and conduct comprehensive analysis. After obtaining the task completion timeliness Asx, resource load balance Afz, and inspection path accessibility Alj and performing dimensionless processing, calculate and obtain the comprehensive scheduling adaptability evaluation value Ae through the following formula:

[0110]

[0111] Compare and evaluate according to the preset scheduling adaptability threshold Qe and the comprehensive scheduling adaptability evaluation value Ae. The specific evaluation content is as follows:

[0112] If the comprehensive scheduling adaptability evaluation value Ae ≥ scheduling adaptability threshold Qe: Judge that the preliminary scheduling plan meets the inspection requirements, and directly issue an execution instruction to start the inspection task;

[0113] If the comprehensive scheduling adaptability evaluation value Ae < scheduling adaptability threshold Qe: Judge that the preliminary scheduling plan does not meet the inspection requirements, and dynamically adjust the scheduling priority and generate a secondary inspection scheduling plan.

[0114] Exemplarily, the geographical location information and type information of power equipment are obtained through the power equipment distribution information collection module. Combining the unique serial number markings of power equipment, inspection personnel, and inspection tasks, accurate equipment distribution and task management are realized; by deploying sensors and intelligent terminals to collect power equipment operation status data, environmental monitoring data, and historical fault data in real time, through standardized preprocessing and data fusion algorithm integration, the comprehensiveness and accuracy of the data are ensured, providing a reliable basis for subsequent decision-making; the neural network machine learning algorithm is used to model and analyze the equipment operation status. By calculating the real-time operation parameter volatility Pr, equipment operation duration Tm, vibration abnormality Vd, equipment category weight Cl, equipment geographical location sensitivity Gr, and task correlation coefficient Rt, the fault risk Fr and importance weight coefficient Wz of the equipment can be accurately evaluated, optimizing the priority ranking of inspection equipment; by combining the inspection resource availability index Ry and the task urgency coefficient Tj to evaluate the resource scheduling adaptability Pd, the efficient matching of inspection resources and tasks is realized, ensuring the reasonable allocation of resources and the timely execution of tasks; based on the simulation model of the inspection task path and the calculation of the comprehensive scheduling adaptability evaluation value Ae, the adaptability of the preliminary scheduling plan can be judged in real time. If it does not meet the inspection requirements, adjust the resource configuration, optimize the path planning, and adjust the task priority in a timely manner to improve the inspection efficiency and task completion quality.

[0115] Specifically, step S5 specifically includes:

[0116] By using a deep learning network model to comprehensively analyze relevant dynamic data during the execution of monitoring inspection tasks, the planned inspection resource utilization rate Zy and the actual resource utilization rate Zs in the equipment operation status data, the expected inspection progress Xy and the actual inspection progress Xs in the inspection progress data, and the expected environmental impact coefficient Hy and the actual environmental impact coefficient Hs in the environmental change data are obtained; and the inspection task execution deviation value Ex is calculated through the following formula:

[0117]

[0118] By comparing and evaluating the preset inspection task execution deviation threshold Fx with the inspection task execution deviation value Ex, the following specific evaluation contents are obtained:

[0119] If the inspection task execution deviation value Ex ≤ the inspection task execution deviation threshold Fx: maintain the current scheduling strategy and continue task execution;

[0120] If the inspection task execution deviation value Ex> the inspection task execution deviation threshold Fx: the adaptive scheduling optimization mechanism is automatically triggered, including:

[0121] Route optimization: replan inspection routes to avoid risky areas and congested sections;

[0122] Resource reallocation: dynamically adjust inspection personnel or inspection equipment, and call on spare resources to supplement current tasks;

[0123] Task reorganization: merge, split or postpone some inspection tasks to adjust the overall task execution efficiency.

[0124] For example, by conducting a comprehensive analysis of relevant dynamic data, the planned inspection resource utilization rate Zy and the actual resource utilization rate Zs in the equipment operation status data, the expected inspection progress Xy and the actual inspection progress Xs in the inspection progress data, and the expected environmental impact coefficient Hy and the actual environmental impact coefficient Hs in the environmental change data are obtained in real time, providing comprehensive data support for the execution effect of the inspection task; by calculating the inspection task execution deviation value Ex, the degree of deviation in task execution can be quantified, thereby providing a basis for scheduling optimization; when the inspection task execution deviation value Ex exceeds the preset inspection task execution deviation threshold Fx, the system will automatically trigger the adaptive scheduling optimization mechanism, perform path optimization, resource reallocation and task reorganization in real time, and maximize the inspection efficiency and task execution effect by replanning the inspection path, adjusting resource allocation and adjusting task sequence, ensuring that the inspection task is successfully completed according to the predetermined goals; the entire system can flexibly respond to various changes in the inspection process, optimize resource allocation and task scheduling, thereby improving the reliability, timeliness and flexibility of the inspection work.

[0125] On the other hand, seeFigure 2 , the present invention also provides an artificial intelligence-based power inspection and scheduling system, which is applied to the method described above. The system includes an equipment data fusion module, an equipment fault assessment module, an inspection resource monitoring module, a scheduling path simulation module, and a task execution optimization module;

[0126] The equipment data fusion module is used to obtain the power equipment distribution map and label the serial numbers of various power equipment, inspection personnel, and inspection tasks; collect the operation status data, environmental monitoring data, and historical fault data of power equipment in real time, and then integrate them using a multi-source data interface to construct a global equipment status data set;

[0127] The equipment fault assessment module is used to calculate the fault risk assessment value Fr and the equipment importance weight coefficient Wz of each power equipment respectively according to the global equipment status data set, generate the equipment inspection priority coefficient Px, and sort all power equipment according to the equipment inspection priority coefficient Px to select the equipment to be inspected, and locate the equipment to be inspected in the power equipment distribution map;

[0128] The inspection resource monitoring module is used to monitor the relevant data of the inspection resource status in real time based on the equipment to be inspected, construct a resource status data set, calculate and fit the inspection resource availability index Ry and the task urgency coefficient Tj, obtain the resource scheduling adaptability Pd and evaluate it, dynamically adjust the inspection resources and generate a preliminary inspection scheduling plan;

[0129] The scheduling path simulation module is used to perform real-time simulation calculation on the path of the inspection task, generate and evaluate the comprehensive scheduling adaptability evaluation value Ae, and judge whether the preliminary scheduling plan meets the inspection requirements according to the evaluation content of the comprehensive scheduling adaptability evaluation value Ae. If the inspection requirements are not met, readjust the scheduling priority and generate a secondary inspection scheduling plan;

[0130] The task execution optimization module is used to monitor the relevant dynamic data during the execution of the inspection task in real time, including the equipment operation status data, inspection progress data, and environmental change data; evaluate by calculating the inspection task execution deviation value Ex, start the adaptive scheduling optimization mechanism, and adjust the inspection path and resource allocation strategy until the inspection task is completed.

[0131] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An artificial intelligence-based power inspection and scheduling method, characterized in that, It includes the following steps: S1. Obtain the power equipment distribution map, and label each type of power equipment, inspection personnel, and inspection tasks with serial numbers; collect the power equipment operation status data, environmental monitoring data, and historical fault data in real time, and then integrate them using a multi-source data interface to obtain a global equipment status data set, and build a power equipment global data fusion platform; S2. Based on the global equipment status data set, calculate the fault risk assessment value Fr and the equipment importance weight coefficient Wz of each power equipment respectively, generate the equipment inspection priority coefficient Px, and sort all power equipment according to the equipment inspection priority coefficient Px, select the equipment to be inspected, and locate the equipment to be inspected in the power equipment distribution map; S3. Based on the equipment to be inspected, monitor the data related to the inspection resource status in real time, build a resource status data set, calculate and fit the inspection resource availability index Ry and the task urgency coefficient Tj, obtain the resource scheduling adaptability Pd and evaluate it, dynamically adjust the inspection resources and generate a preliminary inspection scheduling plan; S4. Conduct real-time simulation calculation on the path of the inspection task, generate and evaluate the comprehensive scheduling adaptability evaluation value Ae, and judge whether the preliminary scheduling plan meets the inspection requirements according to the evaluation content of the comprehensive scheduling adaptability evaluation value Ae; If the inspection requirements are not met, readjust the scheduling priority and generate a secondary inspection scheduling plan; S5. Monitor the relevant dynamic data during the execution of the inspection task in real time, including the equipment operation status data, inspection progress data, and environmental change data; evaluate by calculating the inspection task execution deviation value Ex, start the adaptive scheduling optimization mechanism, and adjust the inspection path and resource allocation strategy until the inspection task is completed.

2. The power inspection and scheduling method based on artificial intelligence according to claim 1, wherein The specific steps of S1 include: S101. Obtain the geographical location information and type information of power equipment through the power equipment distribution information collection module, generate a power equipment distribution map, and label each power equipment, inspection personnel, and inspection task with a unique serial number; S102. Deploy various sensors and intelligent terminals on power equipment to collect the power equipment operation status data, environmental monitoring data, and historical fault data in real time, and perform standardized preprocessing; S103. Use a data fusion algorithm to integrate the power equipment operation status data, environmental monitoring data, and historical fault data from different sources, and finally build a global equipment status data set.

3. The power inspection and scheduling method based on artificial intelligence according to claim 2, wherein The specific steps of S2 include: Extract the equipment operation status data and historical fault data from the global equipment status data set, use the neural network machine learning algorithm to model and analyze the equipment operation status, obtain the real-time operation parameter volatility Pr, equipment operation duration Tm, vibration abnormality Vd, equipment category weight Cl, equipment geographical location sensitivity Gr, and task correlation coefficient Rt, and perform dimensionless processing; calculate the fault risk assessment value Fr and the importance weight coefficient Wz of each power equipment, and the specific calculation formulas are as follows:

4. The power inspection and scheduling method based on artificial intelligence according to claim 3, characterized in that, The specific steps of S2 also include: Based on the fault risk assessment value Fr and the equipment importance weight coefficient Wz, the equipment inspection priority coefficient Px is generated through the priority calculation model. The specific calculation formula is as follows: Px = α·Fr + β·Wz In the formula, α is the weight coefficient of the fault risk assessment value Fr, β is the weight coefficient of the equipment importance weight coefficient Wz, and α + β = 1, 0 < α < 1, 0 < β < 1.

5. The power inspection and scheduling method based on artificial intelligence according to claim 4, characterized in that, The specific steps of step S3 include: After integrating the inspection resource status-related data from different sources using the multi-source data interface, a resource status data set is constructed, and the inspection resource availability index Ry and the task urgency coefficient Tj are calculated. The specific calculation formulas are as follows: Tj = ln(1 + Tfx×Tyc×Tqz) In the formula, Rzy represents the current load rate of the resource in the resource status data set, Rkx represents the idle duration of the resource in the resource status data set, Rdl represents the geographical location offset of the resource in the resource status data set, Tfx represents the equipment fault risk assessment value in the resource status data set, Tyc represents the duration of abnormal equipment operation in the resource status data set, Tqz represents the equipment importance weight coefficient in the resource status data set, and ln is the natural logarithm, representing the logarithmic function with the mathematical constant e as the base.

6. The power inspection and scheduling method based on artificial intelligence according to claim 5, characterized in that The specific steps of step S3 also include: Using the following formula, the inspection resource availability index Ry and the task urgency coefficient Tj are fitted to obtain the resource scheduling adaptability Pd: According to the comparison and evaluation between the preset resource scheduling adaptability threshold Q and the resource scheduling adaptability Pd, the specific evaluation content is as follows: If the resource scheduling adaptability Pd ≥ the resource scheduling adaptability threshold Q: It is determined that the current inspection resources match the task, and a preliminary inspection scheduling plan is generated, including starting the inspection resource scheduling, allocating resources to the corresponding tasks, and entering the task execution stage; If the resource scheduling adaptability Pd < the resource scheduling adaptability threshold Q: It is determined that the matching degree between the inspection resources and the task does not meet the requirements, and the inspection resources are adjusted. The specific adjustment content is as follows: Adjust the inspection resource configuration: Re-evaluate the allocation of inspection personnel and equipment, and preferentially call idle or efficient resources; Optimize the inspection path: Recalculate the optimal path to shorten the inspection response time; Delay or merge low-priority tasks: Release resources to meet the requirements of high-priority tasks; After the inspection resources are adjusted, recalculate the resource scheduling adaptability Pd and compare it with the resource scheduling adaptability threshold Q again until the resource scheduling adaptability Pd exceeds or reaches the resource scheduling adaptability threshold Q.

7. An artificial intelligence-based power inspection and scheduling method according to claim 6, characterized in that, The specific steps of step S4 include: Based on the preliminarily generated inspection scheduling plan, an inspection task path simulation model is constructed to real-time simulate the execution effects of inspection resources under different paths and comprehensively analyze them. After obtaining the task completion timeliness Asx, resource load balance Afz, and inspection path accessibility Alj and performing dimensionless processing, the comprehensive scheduling adaptability evaluation value Ae is calculated through the following formula: According to the comparison and evaluation between the preset scheduling adaptability threshold Qe and the comprehensive scheduling adaptability evaluation value Ae, the specific evaluation content is as follows: If the comprehensive scheduling adaptability evaluation value Ae ≥ the scheduling adaptability threshold Qe: It is judged that the preliminary scheduling plan meets the inspection requirements, and then the execution instruction is directly issued to start the inspection task; If the comprehensive scheduling adaptability evaluation value Ae < the scheduling adaptability threshold Qe: It is judged that the preliminary scheduling plan does not meet the inspection requirements, and then the scheduling priority is dynamically adjusted and a secondary inspection scheduling plan is generated.

8. An artificial intelligence-based power inspection scheduling method according to claim 7, characterized in that, The specific steps of step S5 include: By comprehensively analyzing relevant dynamic data during the execution of the monitoring inspection task, obtain the planned inspection resource utilization rate Zy and the actual resource utilization rate Zs in the equipment operation status data, the expected inspection progress Xy and the actual inspection progress Xs in the inspection progress data, and the expected environmental impact coefficient Hy and the actual environmental impact coefficient Hs in the environmental change data; and calculate and obtain the inspection task execution deviation value Ex through the following formula: According to the comparison and evaluation between the preset inspection task execution deviation threshold Fx and the inspection task execution deviation value Ex, obtain the following specific evaluation contents: If the inspection task execution deviation value Ex ≤ the inspection task execution deviation threshold Fx: Keep the current scheduling strategy and continue the task execution; If the inspection task execution deviation value Ex > the inspection task execution deviation threshold Fx: Automatically trigger the adaptive scheduling optimization mechanism, including: Path optimization: Re-plan the inspection path to avoid risk areas and congested sections; Resource reallocation: Dynamically adjust inspection personnel or inspection equipment, and call backup resources to supplement the current task; Task reorganization: Merge, split or postpone some inspection tasks to adjust the overall task execution efficiency.

9. An artificial intelligence-based power inspection and scheduling system, which is applied to the method according to any one of claims 1 to 8, characterized in that, The system includes an equipment data fusion module, an equipment fault evaluation module, an inspection resource monitoring module, a scheduling path simulation module, and a task execution optimization module; The equipment data fusion module is used to obtain the power equipment distribution map, and number all kinds of power equipment, inspection personnel and inspection tasks; collect the power equipment operation status data, environmental monitoring data and historical fault data in real time, and then use the multi-source data interface for integration to construct a global equipment status data set; The equipment fault evaluation module is used to calculate the fault risk evaluation value Fr and the equipment importance weight coefficient Wz of each power equipment respectively according to the global equipment status data set, generate the equipment inspection priority coefficient Px, and sort all power equipment according to the equipment inspection priority coefficient Px to select the equipment to be inspected, and locate the equipment to be inspected in the power equipment distribution map; The inspection resource monitoring module is used to monitor the relevant data of the inspection resource status in real time based on the equipment to be inspected, construct a resource status data set, calculate and fit the inspection resource availability index Ry and the task urgency coefficient Tj, obtain the resource scheduling adaptability Pd and evaluate it, dynamically adjust the inspection resources and generate a preliminary inspection scheduling plan; The described scheduling path simulation module is used to perform real-time simulation calculations on the path of the inspection task, generate a comprehensive scheduling adaptability evaluation value Ae and conduct an evaluation, and judge whether the preliminary scheduling plan meets the inspection requirements according to the evaluation content of the comprehensive scheduling adaptability evaluation value Ae. If the inspection requirements are not met, the scheduling priority is readjusted and a secondary inspection scheduling plan is generated; The described task execution optimization module is used to monitor relevant dynamic data during the execution of the inspection task in real time, including equipment operation status data, inspection progress data, and environmental change data; by calculating and evaluating the inspection task execution deviation value Ex, an adaptive scheduling optimization mechanism is started to adjust the inspection path and resource allocation strategy until the inspection task is completed.

Images