Electric power pipe gallery operation and maintenance method and device, computer equipment and storage medium

Abstract

The invention relates to an electric power pipe gallery operation and maintenance method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring sensor data under multiple dimensions collected for electric power pipe gallery equipment; determining at least one target dimension from the plurality of dimensions based on a matching result between the sensor data under each dimension and corresponding preset data; based on the respective sensor data under each target dimension, determining the fault occurrence probability of the electric power pipe gallery equipment under each target dimension; based on each fault occurrence probability, predicting a target fault type of the electric power pipe gallery equipment; and outputting an operation and maintenance strategy which is matched with the target fault type and aims at the electric power pipe gallery equipment. By adopting the method, the operation and maintenance efficiency and the operation and maintenance accuracy can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of power grids, and in particular, to a power pipe gallery operation and maintenance method, device, computer device, computer-readable storage medium, and computer program product. Background Art

[0002] The power pipe gallery is an important part of the modern urban power infrastructure. It is mainly an underground tunnel or passage for centralized laying of power cables, aiming to improve power transmission efficiency, ensure power supply safety, and reduce ground space occupation.

[0003] Currently, the operation and maintenance of the power pipe gallery mainly involve regularly arranging personnel to enter the pipe gallery to inspect the equipment. However, manual operation and maintenance are time-consuming and laborious, and the operation and maintenance scope is limited, making it difficult to comprehensively monitor the state of the pipe gallery, resulting in low operation and maintenance efficiency. Summary of the Invention

[0004] Based on this, it is necessary to provide a power pipe gallery operation and maintenance method, device, computer device, computer-readable storage medium, and computer program product that can improve the operation and maintenance efficiency and accuracy for the above technical problems.

[0005] In a first aspect, the present application provides a power pipe gallery operation and maintenance method, including: obtaining sensor data in multiple dimensions collected for power pipe gallery equipment; determining at least one target dimension from multiple dimensions based on the matching results between the sensor data in each dimension and corresponding preset data; determining the probability of a fault occurring in the power pipe gallery equipment in each target dimension based on the sensor data in each target dimension; predicting the target fault type of the power pipe gallery equipment based on the probabilities of the faults; and outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0006] In one embodiment, the determining the probability of a fault occurring in the power pipe gallery equipment in each target dimension based on the sensor data in each target dimension includes: obtaining a knowledge graph, where the knowledge graph includes candidate fault types, at least one candidate dimension corresponding to each candidate fault type, and historical sensor data corresponding to each candidate dimension; determining the candidate dimensions in the knowledge graph that respectively match each target dimension; and for each target dimension, determining the probability of a fault occurring in the power pipe gallery equipment in the target dimension based on the data similarity between the sensor data in the target dimension and the historical sensor data corresponding to the matching candidate dimension.

[0007] In one embodiment, predicting the target fault type of the power pipe gallery equipment based on each of the fault occurrence probabilities includes: for each of the fault occurrence probabilities, determining a corresponding candidate fault type from the knowledge graph; and determining the intersection of multiple candidate fault types as the target fault type of the power pipe gallery equipment.

[0008] In one embodiment, outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type includes: when the target fault type represents equipment failure or equipment downtime, determining multiple fault influencing factors that match the target fault type; determining the fault influence probabilities of at least two fault influencing factors for the target fault type; and outputting an operation and maintenance strategy for the power pipe gallery equipment based on the multiple fault influence probabilities.

[0009] In one embodiment, outputting an operation and maintenance strategy for the power pipe gallery equipment based on the multiple fault influence probabilities includes: determining the maximum probability among the multiple fault influence probabilities; and determining the operation and maintenance strategy that matches the fault influencing factor corresponding to the maximum probability as the operation and maintenance strategy for the power pipe gallery equipment.

[0010] In one embodiment, the sensor data includes image data; the method further includes: analyzing the image data to determine the defect type of the power pipe gallery equipment; and when the defect type is crack, corrosion, or equipment damage, adjusting and outputting an adjusted operation and maintenance strategy based on the defect type.

[0011] In a second aspect, the present application also provides a power pipe gallery operation and maintenance device, including: an acquisition module, configured to acquire sensor data in multiple dimensions collected for power pipe gallery equipment; a determination module, configured to determine at least one target dimension from multiple dimensions based on the matching result between the sensor data in each dimension and the corresponding preset data; a processing module, configured to determine the fault occurrence probability of the power pipe gallery equipment in each target dimension based on the sensor data in each target dimension; an analysis module, configured to predict the target fault type of the power pipe gallery equipment based on each of the fault occurrence probabilities; and an operation and maintenance module, configured to output an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0012] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the following steps are implemented: obtaining sensor data under multiple dimensions collected for power pipe gallery equipment; determining at least one target dimension from multiple dimensions based on the matching results between the sensor data under each dimension and the corresponding preset data; determining the probability of a fault occurring in the power pipe gallery equipment under each target dimension based on the sensor data under each target dimension; predicting the target fault type of the power pipe gallery equipment based on the probabilities of the faults occurring; and outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0013] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: obtaining sensor data under multiple dimensions collected for power pipe gallery equipment; determining at least one target dimension from multiple dimensions based on the matching results between the sensor data under each dimension and the corresponding preset data; determining the probability of a fault occurring in the power pipe gallery equipment under each target dimension based on the sensor data under each target dimension; predicting the target fault type of the power pipe gallery equipment based on the probabilities of the faults occurring; and outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0014] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the following steps are implemented: obtaining sensor data under multiple dimensions collected for power pipe gallery equipment; determining at least one target dimension from multiple dimensions based on the matching results between the sensor data under each dimension and the corresponding preset data; determining the probability of a fault occurring in the power pipe gallery equipment under each target dimension based on the sensor data under each target dimension; predicting the target fault type of the power pipe gallery equipment based on the probabilities of the faults occurring; and outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0015] The above power pipe gallery operation and maintenance method, device, computer equipment, computer-readable storage medium and computer program product obtain sensor data in multiple dimensions collected for power pipe gallery equipment, determine at least one target dimension from multiple dimensions based on the matching results between the sensor data in each dimension and the corresponding reference data, and determine the probability of a fault occurring in the power pipe gallery equipment in each target dimension based on the respective sensor data in each target dimension. Based on the respective fault occurrence probabilities, the target fault type of the power pipe gallery equipment is predicted, and then an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type is output. Thus, by collecting sensor data of the power pipe gallery equipment in multiple dimensions, intelligent operation and maintenance of the power pipe gallery equipment can be achieved. Compared with the manual operation and maintenance method, the operation and maintenance time can be saved, the operation and maintenance scope can be expanded, comprehensive monitoring of the power pipe gallery can be realized, and the operation and maintenance efficiency can be improved. Moreover, based on the probability of a fault occurring in each target dimension of the power pipe gallery equipment, the fault type of the power pipe gallery equipment can be predicted, and an operation and maintenance strategy that matches the target fault type of the power pipe gallery equipment can be output, which can improve the operation and maintenance efficiency and the operation and maintenance accuracy rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a schematic flow chart of the power pipe gallery operation and maintenance method in one embodiment;

[0018] Figure 2 It is a schematic flow chart of determining the probability of a fault occurring in the power pipe gallery equipment in each target dimension based on the respective sensor data in each target dimension in one embodiment;

[0019] Figure 3 It is a schematic flow chart of predicting the target fault type of the power pipe gallery equipment based on the respective fault occurrence probabilities in one embodiment;

[0020] Figure 4 It is a schematic flow chart of outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type in one embodiment;

[0021] Figure 5 It is a schematic flow chart of the power pipe gallery operation and maintenance method in another embodiment;

[0022] Figure 6 It is a schematic flow chart of the power pipe gallery operation and maintenance method in another embodiment;

[0023] Figure 7 is a structural block diagram of an operation and maintenance device for a power cable tunnel in an embodiment;

[0024] Figure 8 is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0025] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0026] Different from the way of manually inspecting the power cable tunnel, currently, an intelligent operation and maintenance platform for the power cable tunnel can be designed to achieve intelligent operation and maintenance of the power cable tunnel.

[0027] For example, an intelligent operation and maintenance platform of "intelligent line + robot" is applied to the utility tunnel in a certain place to realize data docking between the "robot" and the "intelligent line", based on general-purpose equipment, and solve the positioning and data transmission requirements necessary for the robot to run in the tunnel. As the core of the entire utility tunnel, the intelligent operation and maintenance platform plays a leading role in the entire operation process, and various functions and services are triggered and mobilized by the platform. Sub-systems such as the robot system, the tunnel environment monitoring system, the fan monitoring system, the water pump monitoring system, and the lighting monitoring system are connected to the intelligent operation and maintenance platform through an industrial ring network to realize instruction issuance and status upload. Specifically, the intelligent operation and maintenance platform mainly includes 6 layers, specifically the infrastructure layer, the interface control layer, the data center layer, the service support layer, the application layer and the interaction layer. The infrastructure layer includes sub-systems such as environment monitoring, ventilation and drainage, fire protection, pipeline monitoring, lighting, video, and robots, which are both data collectors and task executors. The intelligent operation and maintenance platform docks with the robot system and various professional weak current sub-systems downward at the interface control layer, collects various data and conducts remote control. Horizontally, it can dock with the smart city system, the monitoring system of the pipeline units entering the tunnel, etc. At the same time, the interface control layer monitors the interface quality and can give an alarm in time when abnormal phenomena are found. The intelligent operation and maintenance platform stores various operation data in domains, performs post-data processing and big data analysis at the data center layer. The intelligent operation and maintenance platform sets 6 major sub-systems at the application layer, including operation monitoring, emergency command and dispatch, operation and maintenance management, service management, organization management, and business analysis. At the same time, the intelligent operation and maintenance platform supports interaction with the interface.

[0028] For another example, a company has studied an intelligent operation and maintenance for a power engineering based on multiple wireless communication technologies, as well as an on-line monitoring system for the unit. The system includes three parts. One is the on-site monitoring terminal, the second is the wireless communication unit, and the third is the remote monitoring and control center. In this system, the on-site monitoring device is a Charge-Coupled Device (CCD) industrial high-definition camera, which can conduct real-time video monitoring on the operation dynamics of on-site power equipment, and transmit the monitoring video and its data to the local server, or transmit it to the remote monitoring and control center through a wireless communication network.

[0029] For another example, a company has designed a new operation status diagnosis system for the cable lines in the power cable compartment of an integrated pipe gallery based on mobile sensing. It uses wavelet decomposition to compress the sensed data, and designs algorithms according to the data characteristics of the front and back ends and the application scenarios, forming a set of cable line state analysis and prediction based on short-term front-end data and multi-dimensional fusion analysis and decision-making system for the big data background, comprehensively realizing the seamless connection of equipment identification, status perception, data interaction and intelligent diagnosis and the multi-level cable operation reliability evaluation.

[0030] As can be seen from the above, to improve the operation and maintenance efficiency, an intelligent operation and maintenance platform for the power pipe gallery can be designed. In this application, a power pipe gallery operation and maintenance method based on the digital twin platform can be designed to achieve the intelligent operation and maintenance of the power pipe gallery. The digital twin platform is an intelligent operation and maintenance system integrating data collection, analysis, simulation, and management, which can fuse and process the collected data such as sound, temperature, humidity, pressure, vibration, gas concentration, and images, and display different types of data through multiple visualization tools. For example, physical quantities such as temperature data, humidity data, and pressure data can be visualized in the form of color gradients, dynamic isosurfaces, heat maps, etc.; vibration data can be visualized in the form of dynamic arrows or fluctuating animations superimposed on the 3D models of equipment or pipelines; gas concentration can be visualized in the form of dynamic flowing particles; image data (such as video monitoring, infrared thermal imaging) can be visualized in two forms: texture mapping and embedded windows.

[0031] Specifically, the digital twin platform includes a server, which is used to obtain sensor data in multiple dimensions collected for the power pipe gallery equipment, determine at least one target dimension from multiple dimensions based on the matching results between the sensor data in each dimension and the corresponding preset data, and determine the probability of a fault occurring in the power pipe gallery equipment in the target dimension based on the sensor data in each target dimension. Based on the probabilities of each fault occurring, determine the target fault type of the power pipe gallery equipment, and then output an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0032] Among them, the server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0033] In one embodiment, as Figure 1 shown, a method for operation and maintenance of a power pipe gallery is provided. Taking the method applied to a server in a digital twin platform as an example, the method includes the following steps:

[0034] S102, Obtain sensor data in multiple dimensions collected for power pipe gallery equipment.

[0035] Among them, power pipe gallery equipment refers to various equipment and facilities used in the power pipe gallery to ensure power transmission, monitoring, maintenance, and management. The power pipe gallery equipment determines the core operation and safety guarantee of the power pipe gallery and is easily affected by environmental factors and equipment status. Therefore, it is necessary to perform operation and maintenance on the power pipe gallery equipment.

[0036] In some cases, power pipe gallery equipment can be determined based on the equipment distribution and equipment importance in the power pipe gallery. In other cases, power pipe gallery equipment can also be determined based on the operation and maintenance regulations of the power company. In other cases, power pipe gallery equipment can also be determined based on power industry-related standards such as GB 50174 and IEC 61850, or other methods can be used to determine power pipe gallery equipment. For example, power pipe gallery equipment can include power equipment, equipment rooms, cables, ventilators, drainage systems, and pipelines, etc.

[0037] In one of the embodiments, different types of sensors can be deployed at different target positions of the power pipe gallery equipment to collect sensors corresponding to the corresponding dimensions. For example, taking the power pipe gallery equipment as a cable, by deploying temperature sensors, humidity sensors, pressure sensors, etc. at different target positions of the cable, sensor data in multiple dimensions such as sound, temperature, humidity, pressure, vibration, gas concentration, and image can be collected.

[0038] In some cases, different types of sensors can send the collected sensors to the server through Internet of Things technology.

[0039] S104, Based on the matching results between the sensor data in each dimension and the corresponding preset data, determine at least one target dimension from multiple dimensions.

[0040] The preset data corresponding to each dimension refers to the data when the power pipe gallery equipment operates normally in this dimension.

[0041] In one embodiment, for the sensor data in each dimension, when the data change trend between the sensor data and the corresponding preset data matches, the dimension corresponding to the sensor data is determined as the target dimension.

[0042] In one embodiment, the sensor detection value represents the sensor data, and the preset detection value represents the preset data. When the sensor detection value does not exceed the preset detection value, the dimension corresponding to the sensor data is determined as the target dimension. For example, when the current temperature detected by the temperature sensor does not exceed the preset temperature, the temperature dimension corresponding to the current temperature is determined as the target dimension. Further, the probability of a fault occurring in the power pipe gallery equipment in the temperature dimension can be determined based on the current temperature.

[0043] It should be understood that when the sensor data does not match the corresponding preset data, it indicates that the sensor data may be abnormal data. Therefore, by analyzing the sensor data, the probability of the impact of the possible faults of the power pipe gallery equipment under this abnormal data can be determined.

[0044] S106. Based on the sensor data in each target dimension, determine the probability of a fault occurring in the power pipe gallery equipment in each target dimension.

[0045] Among them, the probability of a fault occurring refers to the probability of a fault occurring in the power pipe gallery equipment. The implementation method of determining the probability of a fault occurring in the power pipe gallery equipment in each target dimension based on the sensor data in each target dimension is not limited. The following examples are given in combination with possible implementation methods.

[0046] In one embodiment, obtain the historical sensor data of the power pipe gallery equipment in each dimension and the corresponding historical probability of a fault occurring; for each dimension, based on the corresponding historical sensor data and historical probability of a fault occurring, train a convolutional neural network to obtain a fault detection model matching each dimension; for each target dimension, based on the fault detection model corresponding to the target dimension, analyze the sensor data of the target dimension, and the probability of a fault occurring in the power pipe gallery equipment in the target dimension can be obtained.

[0047] S108. Based on the probabilities of a fault occurring, predict the target fault type of the power pipe gallery equipment.

[0048] Among them, the implementation method of predicting the target fault type of the power pipe gallery equipment based on the probabilities of a fault occurring is not limited. The following examples are given in combination with possible implementation methods.

[0049] In one embodiment, the maximum failure occurrence probability among the failure occurrence probabilities is determined; based on the mapping relationship between the dimension and the failure type, the failure type corresponding to the target dimension that matches the maximum failure occurrence probability is determined as the target failure type of the predicted power pipe gallery equipment.

[0050] For example, if the target dimension represents temperature, the target failure type may include line failure; if the target dimension represents vibration, the target failure type may include bearing failure or component looseness; if the target dimension represents humidity, the target failure type may include line short circuit.

[0051] S110. Output an operation and maintenance strategy for the power pipe gallery equipment that matches the target failure type.

[0052] The operation and maintenance strategy refers to the strategy for solving the target failure type of the power pipe gallery equipment. The operation and maintenance strategy may include operation and maintenance suggestions and the operation and maintenance time matching the power pipe gallery equipment. For example, the operation and maintenance suggestions may include: detecting the heat dissipation system and bearing wear condition, increasing moisture removal measures, checking for possible gas leakage points, strengthening the ventilation system, checking for hidden dangers of line aging and short circuit, or that the equipment may have early failures, that the equipment may have loose parts or mechanical failures and requires shutdown for maintenance, etc.

[0053] In one embodiment, based on the mapping relationship between the failure type and the operation and maintenance strategy, the operation and maintenance strategy that matches the target failure type can be determined as the operation and maintenance strategy for the power pipe gallery equipment. Among them, in the mapping relationship between the failure type and the operation and maintenance strategy, the failure type may include insulation layer aging, rupture, cable joint overheating, cable support looseness, ventilation fan failure shutdown, and drainage system blockage, etc. The specific content of the mapping content can be set based on the actual situation.

[0054] In some embodiments, if the digital twin platform includes a display interface, the operation and maintenance strategy for the power pipe gallery equipment can be output on the display interface. Thus, the operation and inspection personnel can perform operation and maintenance on the power pipe gallery equipment based on the output operation and maintenance strategy.

[0055] In some embodiments, if the digital twin platform is communicatively connected to the operation and maintenance terminal, the operation and maintenance strategy for the power pipe gallery equipment can be output to the operation and maintenance terminal. Thus, the operation and inspection personnel can immediately perform operation and maintenance on the power pipe gallery equipment on site, which can improve the operation and maintenance efficiency.

[0056] Based on Figure 1As shown in the figure, by obtaining sensor data under multiple dimensions collected for power pipe gallery equipment, based on the matching results between the sensor data under each dimension and the corresponding reference data, at least one target dimension is determined from multiple dimensions, and based on the sensor data under each target dimension, the probability of a fault occurring for the power pipe gallery equipment under each target dimension is determined. Based on the respective probabilities of a fault occurring, the target fault type of the power pipe gallery equipment is predicted, and then an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type is output. Thus, by collecting sensor data of the power pipe gallery equipment under multiple dimensions, intelligent operation and maintenance of the power pipe gallery equipment can be realized. Compared with the manual operation and maintenance method, it can save operation and maintenance time, expand the operation and maintenance scope, achieve comprehensive monitoring of the power pipe gallery, and improve operation and maintenance efficiency. Moreover, through the probability of a fault occurring for the power pipe gallery equipment under each target dimension, the fault type of the power pipe gallery equipment can be predicted, and an operation and maintenance strategy that matches the target fault type of the power pipe gallery equipment can be output, which can improve operation and maintenance efficiency and operation and maintenance accuracy.

[0057] Combined with Figure 1 As can be seen from the content shown, in one of the embodiments, the sensor data under each dimension may include sensor data at multiple acquisition times. When it is determined based on the sensor data at multiple acquisition times that there is an abnormal change in the data, the emergency response mechanism is immediately activated. Thus, for sudden faults or emergencies, by activating the emergency response mechanism, rapid decision-making and immediate disposal can be carried out to avoid the expansion of the accident and reduce the accident risk.

[0058] For example, when the device temperature at multiple acquisition times rises sharply, there may be a risk of overheating damage, and then the emergency response mechanism of load reduction or power-off is immediately activated. When the device pressure at multiple acquisition times rises sharply, there may be a risk of explosion, and then the emergency response mechanism for starting the pressure relief device to work is immediately activated.

[0059] Combined with Figure 1 As can be seen from the content shown, the fault type of the power pipe gallery equipment can be predicted based on the probability of a fault occurring for the power pipe gallery equipment under each target dimension. In other embodiments, the future operating state of the power pipe gallery can also be predicted based on a deep learning model, and then the corresponding operation and maintenance strategy is output.

[0060] Specifically, obtain the historical sensor data of the power pipe gallery equipment in multiple dimensions; preprocess the historical sensor data in multiple dimensions; based on the processed historical sensor data in multiple dimensions, train a Long Short-Term Memory (LSTM) deep learning model to obtain a target model; input the sensor data of the power pipe gallery equipment in multiple dimensions into the target model, and the future operating state of the predicted power pipe gallery can be obtained. Through the analysis results of the future operating state, corresponding operation and maintenance strategies can be output.

[0061] Among them, the preprocessing can include outlier removal processing, missing value filling processing, and time alignment processing. In some cases, the linear interpolation method can be used to implement the missing value filling processing. In some cases, since the data collected by different sensors are separate time lines, through time alignment processing, the historical sensor data in all dimensions can be aligned to the same starting time.

[0062] For example, if it is predicted that the future cable temperature exceeds the normal range and there is a risk of causing a line fault, corresponding operation and maintenance strategies matching the line fault can be output. If it is predicted that the future fan vibration exceeds the normal range and there is a risk of bearing failure and component loosening, operation and maintenance strategies matching the bearing failure and component loosening can be output. If it is predicted that the environmental humidity exceeds the normal range, it may indicate that the equipment surrounding environment is humid, there is a risk of causing equipment corrosion or insulation performance degradation, and further may lead to short circuits or other electrical faults, then corresponding operation and maintenance strategies can be output.

[0063] For example, Table 1 provides an example of an analysis result and corresponding operation and maintenance strategies, where:

[0064] Table 1

[0065]

[0066] In one embodiment, based on the sensor data in each target dimension, the implementation method of determining the fault occurrence probability of the power pipe gallery equipment in each target dimension (i.e., S106) can be as Figure 2 shown, including the following steps:

[0067] S202, obtain a knowledge graph, which includes candidate fault types, at least one candidate dimension corresponding to each candidate fault type, and historical sensor data corresponding to each candidate dimension.

[0068] Among them, the knowledge graphs corresponding to different power pipe gallery devices are different, that is, there is a corresponding relationship between the knowledge graph and the power pipe gallery device. The candidate dimension refers to the dimension that causes the failure corresponding to the candidate failure type. For example, if the candidate failure type is a line failure, the corresponding candidate dimensions may include temperature, pressure, vibration, etc., that is, temperature data, pressure data, vibration data, etc. may cause a line failure of the power pipe gallery device; if the candidate failure type is a short circuit, the corresponding candidate dimensions may include humidity, gas concentration, etc.

[0069] Among them, the historical sensor data corresponding to the candidate dimension may refer to the fitting data of all historical sensor data corresponding to the candidate dimension, or may refer to a single historical sensor data, which is not limited in this application.

[0070] S204. Determine the candidate dimensions respectively matched with each target dimension in the knowledge graph.

[0071] S206. For each target dimension, based on the data similarity between the sensor data under the target dimension and the historical sensor data corresponding to the matched candidate dimension, determine the probability of failure occurrence of the power pipe gallery device under the target dimension.

[0072] In one embodiment, when the number of matched candidate dimensions is one, the data similarity between the sensor data under the target dimension and the historical sensor data corresponding to the matched candidate dimension is determined as the probability of failure occurrence of the power pipe gallery device under the target dimension.

[0073] In one embodiment, when the number of matched candidate dimensions is multiple, determine the data similarity between the sensor data under the target dimension and the historical sensor data corresponding to each candidate dimension; determine the maximum data similarity among the data similarities as the probability of failure occurrence of the power pipe gallery device under the target dimension.

[0074] Alternatively, determine the target similarities exceeding the similarity threshold from the data similarities; when the number of target similarities is one, determine the target similarity as the probability of failure occurrence of the power pipe gallery device under the target dimension; when the number of target similarities is multiple, determine the average value of the multiple target similarities as the probability of failure occurrence of the power pipe gallery device under the target dimension.

[0075] Based on Figure 2 The method shown can determine the probability of failure occurrence of the power pipe gallery device under the target dimension by combining historical sensor data, thereby improving the prediction accuracy of fault diagnosis.

[0076] In one embodiment, based on each probability of failure occurrence, the implementation manner of predicting the target failure type (i.e., S108) of the power pipe gallery device can be as Figure 3 shown, including the following steps:

[0077] S302. For each failure occurrence probability, determine the corresponding candidate failure types from the knowledge graph.

[0078] Wherein, the failure occurrence probability is determined based on the historical sensor data corresponding to the candidate dimensions in the knowledge graph. Then, based on the failure occurrence probability, the corresponding candidate failure types in the knowledge graph can be inferred reversely.

[0079] For example, if the failure occurrence probability under the first target dimension is determined based on the historical sensor data corresponding to the first candidate dimension A in the knowledge graph, then the first candidate failure type corresponding to the first candidate dimension A in the knowledge graph is the candidate failure type corresponding to the failure occurrence probability.

[0080] For example, if the failure occurrence probability under the second target dimension is determined based on the historical sensor data corresponding to the second candidate dimension B and the historical sensor data corresponding to the third candidate dimension C in the knowledge graph, then the candidate failure types corresponding to the failure occurrence probability include: the first candidate failure type corresponding to the second candidate dimension B in the knowledge graph and the second candidate failure type corresponding to the third candidate dimension C.

[0081] S304. Determine the intersection of multiple candidate failure types as the target failure type of the power pipe gallery equipment.

[0082] For example, in combination with S302, if multiple candidate failure types include the first candidate failure type corresponding to the first candidate dimension A, the first candidate failure type corresponding to the second candidate dimension B, and the second candidate failure type corresponding to the third candidate dimension C, then the first candidate failure type is the target failure type of the power pipe gallery equipment.

[0083] Based on Figure 3 the content shown above, by determining the target failure type of the power pipe gallery equipment based on the knowledge graph, the processing efficiency can be improved.

[0084] In one embodiment, the implementation manner of outputting the operation and maintenance strategy (i.e., S110) for the power pipe gallery equipment that matches the target failure type can be as Figure 4 shown, including the following steps:

[0085] S402. When the target failure type represents equipment failure or equipment shutdown, determine multiple failure influencing factors that match the target failure type.

[0086] Among them, the fault influence factors refer to the factors that affect the occurrence of the faults corresponding to the target fault type. For example, the target event can be set as equipment failure or equipment shutdown. The primary causes that lead to the target event refer to the main factors directly causing the target event, such as too high temperature, abnormal vibration, etc.; the secondary causes that lead to the target event refer to the potential factors causing the primary causes, such as cooling system failure, motor abnormality, etc.; the tertiary causes that lead to the target event refer to the potential factors causing the secondary causes, such as cable aging, load overload, etc. Then, when the target fault type represents equipment failure or equipment shutdown, the multiple fault influence factors matching the target fault type include the factors corresponding to the causes at different levels, such as too high temperature, abnormal vibration, cooling system failure, motor abnormality, cable aging, load overload, etc.

[0087] S404. Determine the fault influence probabilities of at least two fault influence factors for the target fault type.

[0088] In one embodiment, the fault influence probability is the product of the fault occurrence probabilities of each fault influence factor for the target fault type. For example, P(equipment failure) = P(too high temperature) * P(abnormal vibration), where P(equipment failure) represents the fault influence probability, P(too high temperature) represents the fault occurrence probability corresponding to the fault influence factor of too high temperature, that is, the probability of the fault corresponding to the target fault type caused by the fault influence factor of too high temperature, and P(abnormal vibration) represents the fault occurrence probability corresponding to the fault influence factor of abnormal vibration.

[0089] Among them, the fault occurrence probability of the fault influence factor for the target fault type can be determined based on the knowledge graph. Specifically, among the sensor data in multiple dimensions, the sensor data matching the dimension corresponding to the fault influence factor is determined as the first data; for the candidate fault types matching the target fault type in the knowledge graph, the historical sensor data corresponding to the candidate dimension matching the dimension corresponding to the fault influence factor among the matching candidate fault types is determined as the second data; based on the data similarity between the first data and the second data, the fault occurrence probability of the fault influence factor for the target fault type is obtained.

[0090] For example, if the fault influence factor is too high temperature and the dimension corresponding to the fault influence factor is the temperature dimension, then among the sensor data in multiple dimensions, the current temperature data collected by the temperature sensor is determined; and the historical temperature data corresponding to the candidate fault types of equipment failure or equipment shutdown is determined from the knowledge graph; by calculating the data similarity between the current temperature data and the historical temperature data, the fault occurrence probability corresponding to the fault influence factor of too high temperature can be obtained.

[0091] In some cases, for the factor representing the fault type among the fault influencing factors, sensor data of the device corresponding to the fault type can be obtained in multiple dimensions, and based on the sensor data in multiple dimensions, the fault occurrence probability of the device corresponding to the fault type can be determined. For example, if the fault influencing factor is a cooling system fault, the fault occurrence probability of the cooling system can be determined based on the sensor data of the cooling system in multiple dimensions, where the specific implementation method can refer to Figure 1 the content shown.

[0092] S406, based on multiple fault influence probabilities, output an operation and maintenance strategy for the power pipe gallery equipment.

[0093] Among them, the greater the fault influence probability, the greater the probability that the fault influencing factor corresponding to the fault influence probability causes the occurrence of the fault corresponding to the target fault type. There is no limit to the method of outputting an operation and maintenance strategy for the power pipe gallery equipment based on multiple fault influence probabilities. The following will give examples in combination with possible implementation methods.

[0094] In one embodiment, determine the maximum probability among multiple fault influence probabilities; determine the operation and maintenance strategy matching the fault influencing factor corresponding to the maximum probability as the operation and maintenance strategy for the power pipe gallery equipment.

[0095] In one embodiment, multiple fault influence probabilities can be sorted in descending order, and the top M probabilities can be obtained; determine the operation and maintenance strategies respectively matching the fault influencing factors corresponding to the M probabilities as the operation and maintenance strategy for the power pipe gallery equipment. That is, for each fault influencing factor among the fault influencing factors corresponding to the M probabilities, combine the operation and maintenance strategies corresponding to each fault influencing factor to obtain the operation and maintenance strategy for the power pipe gallery equipment.

[0096] Based on Figure 4 the content shown, by determining the factors directly affecting the occurrence of the fault corresponding to the target fault type from multiple fault influencing factors, thus, when outputting an operation and maintenance strategy for the power pipe gallery equipment, the operation and maintenance accuracy for the power pipe gallery equipment can be improved.

[0097] Combined with the above content, it should be understood that the target fault type of the power pipe gallery equipment can be determined based on the abnormal data in the sensor data in multiple dimensions, that is, the sensor data in the target dimension; and when the target fault type is equipment shutdown or equipment failure, based on the fault influence probabilities of at least two fault influencing factors for the target fault type, determine the direct factors directly affecting the occurrence of the fault corresponding to the target fault type from multiple fault influencing factors affecting the target fault type, and then output the corresponding operation and maintenance strategy, which can effectively solve the fault and improve the operation and maintenance accuracy.

[0098] In one embodiment, the sensor data includes image data. Specifically, as Figure 5 shown, a method for operation and maintenance of a power pipe gallery is provided, including the following steps:

[0099] S502, analyze the image data to determine the defect type of the power pipe gallery equipment.

[0100] Among them, there is no limit to the way of analyzing the image data to determine the defect type of the power pipe gallery equipment. For example, the image data can be analyzed through a convolutional neural network to identify the defect type of the power pipe gallery equipment.

[0101] S504, in the case where the defect type is crack, corrosion or equipment damage, adjust and output the adjusted operation and maintenance strategy based on the defect type.

[0102] Among them, there is no limit to the way of adjusting and outputting the adjusted operation and maintenance strategy based on the defect type. The following will give examples in combination with possible implementation methods.

[0103] In one embodiment, when a preset operation and maintenance suggestion for the defect type is added to the operation and maintenance strategy, the adjusted operation and maintenance strategy can be obtained.

[0104] In one embodiment, historical operation and maintenance suggestions matching the defect type can be obtained. The historical operation and maintenance suggestions refer to the strategy after the operation and maintenance experts adjust the preset operation and maintenance strategy based on operation and maintenance experience; when the historical operation and maintenance suggestions are added to the operation and maintenance strategy, the adjusted operation and maintenance strategy can be obtained.

[0105] Based on Figure 5 the method shown, by combining the defect type of the power pipe gallery equipment to adjust the operation and maintenance strategy, thus, when performing operation and maintenance on the power pipe gallery equipment based on the adjusted operation and maintenance strategy, the operation and maintenance accuracy can be improved.

[0106] Combining the above content, in one embodiment, as Figure 6 shown, a method for operation and maintenance of a power pipe gallery is provided. Taking the example that the method is applied to the server of the digital twin platform, it includes the following steps:

[0107] S602, obtain sensor data in multiple dimensions collected for the power pipe gallery equipment.

[0108] Among them, the sensor data in multiple dimensions may include data such as sound, temperature, humidity, pressure, vibration, gas concentration, and image.

[0109] S604, based on the matching result between the sensor data in each dimension and the corresponding preset data, determine at least one target dimension from multiple dimensions.

[0110] S606. Obtain a knowledge graph, which includes candidate fault types, at least one candidate dimension corresponding to each candidate fault type, and historical sensor data corresponding to each candidate dimension.

[0111] S608. Determine the candidate dimensions in the knowledge graph that respectively match each target dimension.

[0112] S610. For each target dimension, based on the data similarity between the sensor data under the target dimension and the historical sensor data corresponding to the matched candidate dimension, determine the probability of a fault occurring in the power pipe gallery equipment under the target dimension.

[0113] S612. For each probability of a fault occurring, determine the corresponding candidate fault type from the knowledge graph.

[0114] S614. Determine the intersection of multiple candidate fault types as the target fault type of the power pipe gallery equipment.

[0115] S616. Output the operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0116] Among them, the specific content of S602 - S616 can refer to the foregoing content for adaptation description and will not be elaborated here.

[0117] Combined with the above content, it can be seen that the power pipe gallery operation and maintenance method provided by this application can collect sensor data such as sound, temperature, humidity, pressure, vibration, gas concentration, and image in real time by deploying different types of sensors on the power pipe gallery equipment, and can upload the sensor data to the digital twin platform through the Internet of Things technology. Thus, the server in the digital twin platform can use big data analysis methods and machine learning algorithms to process the data, and further realize fault diagnosis and early warning.

[0118] The digital twin platform is an intelligent system integrating data collection, analysis, simulation, and management, which can fuse and process the collected data such as sound, temperature, humidity, pressure, vibration, gas concentration, and image, and can display the processing results through a variety of visualization tools.

[0119] In some cases, a time series data analysis model and a convolutional neural network can be used to perform correlation analysis on sensor data such as temperature, humidity, pressure, and vibration, identify long-term change trends, and predict the operating status and possible faults of the power pipe gallery equipment. In terms of predictive maintenance, the time series model LSTM is used to analyze the historical trends and future changes of key parameters to provide real-time assessment and fault prediction of the equipment health status.

[0120] In some cases, efficient and accurate risk detection and prediction can be achieved through the synergy of machine learning models and expert systems. For example, the digital twin platform can use the isolation forest algorithm and support vector machine to identify abnormal events from sensor data, and combine the Bayesian network to analyze the correlation between sensors to infer the probability of potential failures. For image data, convolutional neural networks can further detect equipment defects in the pipe gallery, such as cracks, corrosion, or component damage, and fuse this information with other sensor data. When an abnormality or potential risk is detected, the digital twin platform can trigger a multi-level early warning mechanism and send different types of alarm information according to the severity of the risk: SMS, application notification, email. In addition, the rule engine of the digital twin platform is based on fault tree analysis, combining sensor data and expert knowledge, which can trace and diagnose chain failures and help operation and inspection personnel quickly locate problems.

[0121] In some cases, the knowledge graph can be constructed through the semantic association between power corridor equipment and fault types, current sensor data, and historical sensor data to achieve more accurate operation and maintenance decisions. For example, the knowledge graph can associate different types of power corridor equipment, sensor data of power corridor equipment in multiple dimensions, and historical sensor data with fault types, and continuously enrich and optimize the knowledge base through machine learning models. When new sensor data is uploaded to the digital twin platform, the system will automatically call the knowledge graph for matching analysis, determine whether the current operating status is consistent with the historical fault mode, and predict possible faults.

[0122] It should be understood that associating different types of power corridor equipment, sensor data of power corridor equipment in multiple dimensions, and historical sensor data and fault types can dynamically capture the complex relationships and potential risks of equipment operation. Through this semantic association, not only can the anomalies of a single device be identified, but also the linkage effects between devices can be analyzed. For example, when a sensor detects a temperature anomaly, it can be combined with the detected sensor data, environmental data, and the operating status of other associated devices to infer whether there are problems such as local overload, equipment aging, or environmental temperature and humidity imbalance, and predict the fault chain that these factors may cause.

[0123] Moreover, the knowledge base is continuously enriched and optimized through machine learning models, enabling the platform to self-learn and improve during actual operation and maintenance. As data continues to accumulate, machine learning models can discover new failure modes and operating rules, and add these new knowledge to the knowledge graph, thereby improving the platform's predictive capabilities and decision-making accuracy. For example, when certain sensor data exhibits previously unseen abnormal patterns, the system can use unsupervised learning algorithms to identify potential risks, and through an expert feedback mechanism, mark new failure modes into the database to enhance the system's adaptability.

[0124] In some cases, the digital twin platform can also build a three-dimensional dynamic model based on sensor data in multiple dimensions. The three-dimensional dynamic model can also be updated in real time through the latest monitoring data uploaded by Internet of Things technology, so that the model is highly consistent with the actual pipe gallery environment. Whenever the sensor collects change data such as temperature, humidity, vibration or gas concentration, this information will be immediately transmitted to the digital twin platform and reflected synchronously in the model. Thus, whether it is a slight fluctuation of environmental parameters or a significant change in equipment status, by presenting it in real time in the model, it can ensure that the operation and maintenance personnel grasp the latest situation.

[0125] In some cases, through the digital twin platform, operation and maintenance personnel can remotely view the operation status of the power pipe gallery in real time at any time and place. This platform not only integrates all sensor data, but also provides a dynamic visualization interface, enabling operation and maintenance personnel to intuitively monitor various indicators such as temperature, humidity, pressure, vibration and gas concentration. The multi-dimensional data display ability of the platform enables operation and maintenance personnel to quickly identify potential risk factors and changes in equipment status, so as to take corresponding measures for management and maintenance in a timely manner.

[0126] Moreover, the predictive maintenance based on the knowledge graph enables the platform to also have an intelligent decision support function. Thus, the platform analyzes historical sensor data and real-time sensor information to assist operation and maintenance personnel in formulating targeted operation and maintenance plans. The platform supports the formulation and adjustment of operation and maintenance strategies, and can intelligently recommend the best maintenance timing and methods according to the data of the equipment in multiple dimensions. Further, the digital twin platform can quickly generate an emergency response plan to help operation and maintenance personnel make decisions quickly. The platform integrates rich fault handling knowledge and historical emergency cases, and operation and maintenance personnel can quickly evaluate the on-site situation and take necessary measures according to the combined operation and maintenance strategies output.

[0127] Based on the above content, it can be seen that the power pipe gallery operation and maintenance method provided in this application based on the digital twin platform can monitor the operation status of the power pipe gallery in real time, discover and solve problems in a timely manner, and can also use Internet of Things technology to achieve real-time upload of monitoring data and synchronous update of the model. It can also perform remote operation and maintenance management through the digital twin platform to improve operation and maintenance efficiency, that is, it combines multiple functions such as real-time monitoring, accurate fault diagnosis, intelligent decision support, dynamic model update and emergency response, fully meeting the operation and maintenance needs of the power pipe gallery. Therefore, the implementation of this method will provide an efficient and intelligent management solution for the power pipe gallery, and can improve the safety, reliability and economy of the power system.

[0128] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless specifically stated herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0129] Based on the same inventive concept, an embodiment of the present application further provides a power pipe gallery operation and maintenance device for implementing the power pipe gallery operation and maintenance method involved above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the power pipe gallery operation and maintenance device provided below can refer to the limitations on the power pipe gallery operation and maintenance method in the above text, and will not be repeated here.

[0130] In an exemplary embodiment, as Figure 7 shown, a power pipe gallery operation and maintenance device is provided, including: an acquisition module 702, a determination module 704, a processing module 706, an analysis module 708, and an operation and maintenance module 710, where:

[0131] The acquisition module 702 is used to acquire sensor data in multiple dimensions collected for power pipe gallery equipment; the determination module 704 is used to determine at least one target dimension from multiple dimensions based on the matching results between the sensor data in each dimension and the corresponding preset data; the processing module 706 is used to determine the probability of a fault occurring in the power pipe gallery equipment in each target dimension based on the sensor data in each target dimension; the analysis module 708 is used to predict the target fault type of the power pipe gallery equipment based on the probabilities of various faults occurring; the operation and maintenance module 710 is used to output an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

[0132] In one of the embodiments, the processing module is further used to: acquire a knowledge graph, where the knowledge graph includes candidate fault types, at least one candidate dimension corresponding to each candidate fault type, and historical sensor data corresponding to each candidate dimension; determine the candidate dimensions in the knowledge graph that respectively match each target dimension; for each target dimension, determine the probability of a fault occurring in the power pipe gallery equipment in the target dimension based on the data similarity between the sensor data in the target dimension and the historical sensor data corresponding to the matching candidate dimension.

[0133] In one embodiment, the analysis module is further configured to: for each failure occurrence probability, determine the corresponding candidate failure types from the knowledge graph; and determine the intersection of the multiple candidate failure types as the target failure type of the power pipe gallery equipment.

[0134] In one embodiment, the operation and maintenance module is further configured to: when the target failure type indicates equipment failure or equipment downtime, determine multiple failure influencing factors that match the target failure type; determine the failure influence probabilities of at least two failure influencing factors for the target failure type; and output an operation and maintenance strategy for the power pipe gallery equipment based on the multiple failure influence probabilities.

[0135] In one embodiment, the operation and maintenance module is further configured to: determine the maximum probability among the multiple failure influence probabilities; and determine the operation and maintenance strategy that matches the failure influencing factor corresponding to the maximum probability as the operation and maintenance strategy for the power pipe gallery equipment.

[0136] In one embodiment, the sensor data includes image data; the operation and maintenance module is further configured to: analyze the image data to determine the defect type of the power pipe gallery equipment; and in the case where the defect type is crack, corrosion, or equipment damage, adjust and output an adjusted operation and maintenance strategy based on the defect type.

[0137] Each module in the above power pipe gallery operation and maintenance device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0138] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 8As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as sensor data in multiple dimensions collected for power pipe gallery equipment. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a power pipe gallery operation and maintenance method.

[0139] Those skilled in the art can understand that Figure 8 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0140] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0141] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0142] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0143] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0144] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0145] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in this application.

[0146] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for operation and maintenance of a power pipe gallery, characterized in that, The method includes: Obtaining sensor data in multiple dimensions collected for power pipe gallery equipment; Determining at least one target dimension from multiple dimensions based on the matching results between the sensor data in each dimension and the corresponding preset data; Determining the probability of a fault occurring in the power pipe gallery equipment in each of the target dimensions based on the sensor data in each of the target dimensions; Predicting the target fault type of the power pipe gallery equipment based on the probabilities of the faults occurring; Outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

2. The method according to claim 1, characterized in that The determining the probability of a fault occurring in the power pipe gallery equipment in each of the target dimensions based on the sensor data in each of the target dimensions includes: Obtaining a knowledge graph, where the knowledge graph includes candidate fault types, at least one candidate dimension corresponding to each candidate fault type, and historical sensor data corresponding to each candidate dimension; Determining the candidate dimensions in the knowledge graph that respectively match each of the target dimensions; For each of the target dimensions, determining the probability of a fault occurring in the power pipe gallery equipment in the target dimension based on the data similarity between the sensor data in the target dimension and the historical sensor data corresponding to the matching candidate dimension.

3. The method according to claim 2, wherein The predicting the target fault type of the power pipe gallery equipment based on the probabilities of the faults occurring includes: For each of the probabilities of the faults occurring, determining the corresponding candidate fault type from the knowledge graph; Determining the intersection of multiple candidate fault types as the target fault type of the power pipe gallery equipment.

4. The method according to claim 1, wherein The outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type includes: When the target fault type represents equipment failure or equipment shutdown, determining multiple fault influencing factors that match the target fault type; Determining the fault influencing probabilities of at least two fault influencing factors for the target fault type; Outputting an operation and maintenance strategy for the power pipe gallery equipment based on multiple fault influencing probabilities.

5. The method according to claim 4, characterized in that The outputting an operation and maintenance strategy for the power pipe gallery equipment based on multiple fault influencing probabilities includes: Determining the maximum probability among multiple fault influencing probabilities; Determining the operation and maintenance strategy that matches the fault influencing factor corresponding to the maximum probability as the operation and maintenance strategy for the power pipe gallery equipment.

6. The method according to any one of claims 1 to 5, characterized in that, The sensor data includes image data; the method further includes: Analyzing the image data to determine the defect type of the power pipe gallery equipment; When the defect type is crack, corrosion, or equipment damage, adjusting and outputting an adjusted operation and maintenance strategy based on the defect type.

7. An operation and maintenance device for a power pipe gallery, characterized in that, The device includes: An obtaining module for obtaining sensor data in multiple dimensions collected for power pipe gallery equipment; A determining module for determining at least one target dimension from multiple dimensions based on the matching results between the sensor data in each dimension and the corresponding preset data; A processing module for determining the probability of a fault occurring in the power pipe gallery equipment in each of the target dimensions based on the sensor data in each of the target dimensions; An analysis module for predicting a target fault type of the power pipe gallery equipment based on each of the fault occurrence probabilities; An operation and maintenance module for outputting an operation and maintenance strategy for the power pipe gallery equipment that matches the target fault type.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images