Intelligent power operation and maintenance management method and system for work order closed loop processing

Abstract

The application relates to the technical field of operation and maintenance management, and specifically discloses an intelligent power operation and maintenance management method and system for work order closed-loop processing, which comprises the following steps: remotely acquiring subject data of a power subject, identifying the subject data, and determining the operation correlation degree of the power subject; acquiring the motion trajectory of a worker, and determining the spatial correlation degree of the power subject; clustering the power subject according to the operation correlation degree and the spatial correlation degree; when the subject data of any power subject reaches a preset operation and maintenance condition, generating a direct operation and maintenance work order pointing to the power subject and an indirect operation and maintenance work order pointing to other power subjects of the same type; the application acquires the correlation between different power subjects in data and the correlation in space, and when a certain power subject needs operation and maintenance, the related power subjects are simultaneously subjected to operation and maintenance, so that one operation and maintenance is converted into multiple operation and maintenance of different subjects, and the utilization rate of operation and maintenance resources is greatly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of operation and maintenance, in particular to an intelligent power operation and maintenance management method and system for work order closed-loop processing. BACKGROUND

[0002] Traditional power operation and maintenance management involves a large amount of manual intervention, and has problems such as complex work order flow process, difficult to track execution progress, and low closed-loop efficiency. Especially under the background of increasingly complex power systems, a large number of equipment types, and a large amount of operation and maintenance tasks, efficiency is very important. An inefficient work order management architecture cannot fully utilize existing operation and maintenance resources. Therefore, how to improve the utilization rate of operation and maintenance resources is a technical problem that the present application intends to solve. SUMMARY

[0003] The present application aims to provide an intelligent power operation and maintenance management method and system for work order closed-loop processing to solve the problems raised in the background.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical solutions:

[0005] An intelligent power operation and maintenance management method for work order closed-loop processing, the method comprising:

[0006] remotely acquiring subject data of a power subject, identifying the subject data, and determining the operation relevance of the power subject;

[0007] acquiring the movement trajectory of a worker according to a monitoring system, and determining the spatial relevance of the power subject according to the movement trajectory;

[0008] clustering the power subject according to the operation relevance and the spatial relevance; wherein the clustering condition of the clustering process is determined by the resource amount of the operation and maintenance resource;

[0009] when the subject data of any power subject reaches a preset operation and maintenance condition, generating a direct operation and maintenance work order pointing to the power subject and an indirect operation and maintenance work order pointing to other power subjects of the same type; wherein the task amount of the indirect operation and maintenance work order is less than that of the direct operation and maintenance work order.

[0010] As a further solution of the present application, the step of remotely acquiring subject data of a power subject, identifying the subject data, and determining the operation relevance of the power subject comprises:

[0011] establishing a connection channel with the power subject, and remotely acquiring subject data of the power subject; the subject data is an array with a time label, and each element in the array corresponds to a data type;

[0012] The main body data is identified, the data of each element at different time is fitted as a curve, the element sequence number is reserved, and a curve sequence is obtained;

[0013] The curve sequences of any two power subjects are compared, and the curve correlation degree of the curve corresponding to each element sequence number is calculated;

[0014] The weight of the element corresponding to different curves is queried, and the running correlation degree is accumulated according to the weight;

[0015] The calculation process of the curve correlation degree comprises: calculating the DTW distance of the two curves participating in the calculation, and determining the curve correlation degree according to the inverse ratio of the DTW distance.

[0016] As a further scheme of the application: the step of acquiring the motion trajectory of the worker according to the monitoring system and determining the spatial correlation degree of the power subject comprises:

[0017] A connection channel with the monitoring system is established to acquire the scene video of the power scene;

[0018] The target recognition is performed on the scene video, the target is located, and the target feature is extracted;

[0019] All positions of the same target feature within a preset time period are acquired, all positions are fitted, and the motion trajectory of the target is obtained;

[0020] For any two power subjects, the distance between them and each motion trajectory is queried, and the spatial correlation degree of the power subject is determined according to the queried distance;

[0021] The calculation process of the spatial correlation degree is: when the distance between the two power subjects and a certain motion trajectory is less than a preset distance threshold, the motion trajectory is marked, the number of marked motion trajectories is recorded, and the spatial correlation degree is determined according to the direct ratio of the number.

[0022] As a further scheme of the application: the step of clustering the power subjects according to the running correlation degree and the spatial correlation degree comprises:

[0023] The resource amount of the operation and maintenance resource is queried, and the class number of clustering is determined according to the resource amount;

[0024] The class number is taken as the K value, and the power subjects are K-means clustered based on the running correlation degree and the spatial correlation degree;

[0025] The operation and maintenance work order being executed is queried in real time, and the resource amount of the operation and maintenance resource and the power subjects participating in clustering are updated according to the operation and maintenance work order.

[0026] As a further scheme of the present application: the step of generating the direct operation and maintenance work order for the power subject and the indirect operation and maintenance work order for other power subjects of the same type when the subject data of any power subject reaches the preset operation and maintenance condition comprises:

[0027] determining a first time range based on the current time and a preset first time span;

[0028] acquiring the subject data of each power subject within the first time range to construct an instantaneous data matrix;

[0029] inputting the instantaneous data matrix into the trained determination model to output a determination state; the determination state comprises reaching and not reaching, and is used to represent whether the subject data of the power subject reaches the preset operation and maintenance condition;

[0030] when the determination state is reaching, generating the direct operation and maintenance work order for the power subject and the indirect operation and maintenance work order for other power subjects of the same type;

[0031] wherein the task amount of the indirect operation and maintenance work order is less than the task amount of the direct operation and maintenance work order.

[0032] As a further scheme of the present application: the method further comprises:

[0033] recording the operation and maintenance process based on the memory installed on the power subject;

[0034] inputting the operation and maintenance process into a preset quantification model to obtain an operation and maintenance amount;

[0035] statistically acquiring the operation and maintenance amounts of the same power subject at different times, and adjusting the uploading frequency of the subject data according to the operation and maintenance amounts at different times;

[0036] fitting the operation and maintenance amounts at different times to obtain an operation and maintenance amount change function;

[0037] determining a second time range based on the current time and a preset second time span, calculating the integral of the operation and maintenance amount change function within the second time range, and adjusting the uploading frequency of the subject data according to the integral;

[0038] wherein the uploading frequency is inversely proportional to the integral.

[0039] The technical scheme of the present application also provides an intelligent power operation and maintenance management system for work order closed-loop processing, which comprises:

[0040] a subject data identification module, which is used to remotely acquire the subject data of the power subject, identify the subject data, and determine the operation correlation degree of the power subject;

[0041] a motion trajectory analysis module, which is used to acquire the motion trajectory of the worker according to the monitoring system, and determine the spatial correlation degree of the power subject according to the motion trajectory.

[0042] a power subject clustering module, configured to cluster the power subjects according to the operation correlation degree and the space correlation degree, wherein a clustering condition of the clustering process is determined by the resource quantity of the operation and maintenance resource;

[0043] an operation and maintenance work order generation module, configured to generate a direct operation and maintenance work order for any power subject and an indirect operation and maintenance work order for other power subjects of the same type when the subject data of the power subject reaches a preset operation and maintenance condition, wherein the task quantity of the indirect operation and maintenance work order is less than that of the direct operation and maintenance work order.

[0044] As a further scheme of the present application, the subject data identification module comprises:

[0045] a subject data acquisition unit, configured to establish a connection channel with the power subject and remotely acquire the subject data of the power subject, wherein the subject data is an array with a time label, and each element in the array corresponds to a data type;

[0046] a curve sequence acquisition unit, configured to identify the subject data, fit the data of each element at different time points into a curve, retain the element serial number, and obtain a curve sequence;

[0047] a correlation degree calculation unit, configured to compare the curve sequences of any two power subjects and calculate the curve correlation degree of the curve corresponding to each element serial number;

[0048] a correlation degree accumulation unit, configured to query the weight of the element corresponding to different curves, accumulate the curve correlation degrees according to the weight, and obtain the operation correlation degree;

[0049] wherein the calculation process of the curve correlation degree comprises: calculating the DTW distance of the two curves participating in the calculation, and determining the curve correlation degree according to the inverse ratio of the DTW distance.

[0050] As a further scheme of the present application, the motion trajectory analysis module comprises:

[0051] a scene video acquisition unit, configured to establish a connection channel with a monitoring system and acquire a scene video of a power scene;

[0052] a target identification unit, configured to identify a target in the scene video, locate the target, and extract a target feature;

[0053] a position fitting unit, configured to acquire all positions of the same target feature within a preset time period, fit all positions, and obtain a motion trajectory of the target;

[0054] a distance application unit, configured to query the distance between any two power subjects and each motion trajectory according to the distance, and determine the space correlation degree of the power subjects according to the queried distance;

[0055] The calculation process of the spatial correlation degree is as follows: when the distances between two power subjects and a motion track are both less than a preset distance threshold, the motion track is marked, the number of the marked motion tracks is recorded, and the spatial correlation degree is determined according to the proportionality of the number.

[0056] As a further scheme of the present application, the power subject clustering module comprises:

[0057] Inquiring the resource quantity of the operation and maintenance resource, and determining the class number of the clustering according to the resource quantity;

[0058] Taking the class number as the K value, performing K-means clustering on the power subjects based on the operation correlation degree and the spatial correlation degree;

[0059] Inquiring the operation and maintenance work order being executed in real time, and updating the resource quantity of the operation and maintenance resource and the power subjects participating in the clustering according to the operation and maintenance work order.

[0060] Compared with the prior art, the present application has the beneficial effects that: the present application obtains the correlation between different power subjects in data and the correlation in space, and when a certain power subject needs operation and maintenance, the related power subjects are simultaneously operated and maintained, so that one operation and maintenance is converted into multiple opportunistic operation and maintenance on different subjects, greatly improving the utilization rate of operation and maintenance resources. BRIEF DESCRIPTION OF DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only some embodiments of the present application.

[0062] Figure 1 The flow chart of the intelligent power operation and maintenance management method for work order closed loop processing.

[0063] Figure 2 The composition structure diagram of the intelligent power operation and maintenance management system for work order closed loop processing. DETAILED DESCRIPTION

[0064] In order to make the technical problems to be solved by the present application, technical solutions and beneficial effects more clearly, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application.

[0065] Figure 1 The flow chart of the intelligent power operation and maintenance management method for work order closed loop processing, in the embodiment of the present application, an intelligent power operation and maintenance management method for work order closed loop processing, the method comprises:

[0066] Step S100: remotely acquiring subject data of the power subject, identifying the subject data, and determining the operation correlation degree of the power subject;

[0067] The power subject is a power device applied in a power scene, and the power device is provided with a sensor and a data transmission module.

[0068] In step S100, the subject data of the power subject is remotely acquired, the subject data is identified, and the operation correlation degree of the power subject is determined.

[0069] A connection channel with the power subject is established, and the subject data of the power subject is remotely acquired.

[0070] The subject data is identified, the data of each element at different time points is fitted into a curve, the element serial number is reserved, and a curve sequence is obtained.

[0071] The curve sequences of any two power subjects are compared, and the curve correlation degree of the curve corresponding to each element serial number is calculated.

[0072] The weight of the element corresponding to different curves is queried, the curve correlation degrees are accumulated according to the weight, and the operation correlation degree is obtained.

[0073] A connection channel with the power subject is established, and the subject data of the power subject is remotely acquired.

[0074] The subject data is identified, the data of each element at different time points is fitted into a curve, the element serial number is reserved, and a curve sequence is obtained.

[0075] The comparison process and the curve correlation calculation process in the above content include: calculating the DTW distance of two curves participating in the calculation, and determining the curve correlation according to the inverse ratio of the DTW distance; the DTW distance is the distance obtained by applying the DTW (time warping algorithm).

[0076] Step S200: obtaining the motion trajectory of the staff according to the monitoring system, and determining the spatial correlation of the power body according to the motion trajectory;

[0077] The monitoring system is a camera cluster installed in the power scene, which is used for real-time monitoring of the power scene. It is the infrastructure of the power scene and is used for managing staff. In the technical solution of the present application, the staff is given monitoring permission by default. In fact, the manager will explicitly tell the staff where the camera is and that their work will be monitored. This monitoring is essentially the monitoring of public areas. The staff is given permission by default, but the video obtained cannot be randomly transmitted, and the management party is also explicitly aware. For the technical solution of the present application, the execution end is also the management party, that is, the party obtaining the monitoring video. The video is applied again, which also needs to be informed to the staff. Since this process does not involve privacy, the staff generally grants permission, so the technical solution of the present application defaults the staff to give monitoring permission and data application permission.

[0078] According to the motion trajectory of the staff obtained by the monitoring system, it can be determined that the staff often moves between which power bodies. If the power bodies often appear on the same motion trajectory, it can be considered that their work is closely related, and the correlation is higher, which is represented by the spatial correlation parameter.

[0079] It should be noted that spatial correlation is only a weak correlation. There may be a spatial correlation between two devices, such as needing to pass through another device to reach a certain device. This is also considered a correlation. Two devices with high spatial correlation actually indicate that there is a certain relationship in space, and it does not mean that the two devices are closely related.

[0080] Regarding step S200, the step of obtaining the motion trajectory of the staff according to the monitoring system and determining the spatial correlation of the power body according to the motion trajectory includes:

[0081] Establish a connection channel with the monitoring system to obtain the scene video of the power scene;

[0082] Perform target recognition on the scene video, locate the target, and extract the target feature;

[0083] Obtain all positions of the same target feature within a preset time period, fit all positions, and obtain the motion trajectory of the target.

[0084] querying distances of any two power subjects to each motion trajectory, and determining the spatial correlation of the power subjects according to the queried distances;

[0085] The calculation process of the spatial correlation is as follows: when the distances of the two power subjects to a motion trajectory are both less than a preset distance threshold, the motion trajectory is marked, the number of the marked motion trajectories is recorded, and the spatial correlation is determined according to the direct proportion of the number.

[0086] In the above content, the extraction process of the motion trajectory is not complex, and the existing video recognition process can completely achieve it. The way of converting the spatial correlation is as follows: for any two power subjects, the distances of the two power subjects to each motion trajectory are queried, when the distances are small enough, it is determined that the two power subjects appear on the same motion trajectory, then the number of the motion trajectories on which the two power subjects appear is counted, and the spatial correlation is determined according to the direct proportion of the number, that is, the more the two power subjects appear on the same motion trajectory, the greater the spatial correlation of the two power subjects.

[0087] Step S300: clustering the power subjects according to the operation correlation and the spatial correlation;

[0088] The operation correlation and the spatial correlation are used to represent the difference of the power subjects, and the difference has another meaning of distance. By means of the distance and the application of the clustering algorithm, the power subjects can be clustered. The clustering condition of the clustering process is determined by the resource amount of the operation and maintenance resource. The meaning of this process is that in the clustering result, how close the power subjects in each class are related to the clustering process. The more the resource amount of the operation and maintenance resource input into the clustering process, the closer the power subjects in the same class are. Therefore, the clustering condition is determined by the resource amount of the operation and maintenance resource. How to determine it is not limited in the technical solution of the present application, only that they are related is limited, and the specific degree of correlation is not restricted.

[0089] Regarding step S300, the step of clustering the power subjects according to the operation correlation and the spatial correlation comprises:

[0090] querying the resource amount of the operation and maintenance resource, and determining the class number of the clustering according to the resource amount;

[0091] taking the class number as the K value, and performing K-means clustering on the power subjects based on the operation correlation and the spatial correlation;

[0092] querying the operation and maintenance work order being executed in real time, and updating the resource amount of the operation and maintenance resource and the power subjects participating in the clustering according to the operation and maintenance work order.

[0093] The above defines the clustering scheme as a K-means clustering scheme, and defines the relationship between the resource quantity and the clustering condition as a relationship between the resource quantity and the number of categories, that is, the more the resource quantity, the more the number of categories, and the more accurate the classification.

[0094] In addition, the real-time query is performed on the operation and maintenance order being executed, the execution process consumes operation and maintenance resources, and therefore, the resource quantity needs to be updated, the execution process affects a batch of power subjects, in other words, a batch of power subjects will be maintained, and then it no longer participates in the remaining clustering links.

[0095] Step S400: when the subject data of any power subject reaches the preset operation and maintenance condition, a direct operation and maintenance order pointing to the power subject and an indirect operation and maintenance order pointing to other power subjects of the same category are generated; wherein the task quantity of the indirect operation and maintenance order is less than the task quantity of the direct operation and maintenance order;

[0096] The subject data of the power subject is identified, whether operation and maintenance is needed is determined, when the subject data of any power subject reaches the preset operation and maintenance condition, it is indicated that operation and maintenance is needed, a direct operation and maintenance order pointing to the power subject is generated, and at the same time, the application also generates an indirect operation and maintenance order pointing to other power subjects of the same category, the task quantity of the indirect operation and maintenance order is less than the task quantity of the direct operation and maintenance order, for example, the direct operation and maintenance order is a repair task, and the indirect operation and maintenance order is an inspection task.

[0097] The advantage of this process is that the technical scheme of the application does not generate a single order alone, but generates an order pointing to a batch of related power subjects when a problem occurs in a certain power subject, and the actual physical meaning is that when a problem occurs in a certain power subject, the related power subjects are also likely to have problems, and when performing operation and maintenance, the related power subjects are also subjected to simplified operation and maintenance, which makes most of the power subjects can be subjected to multiple advance incidental operation and maintenance, so that the problem does not occur after the operation and maintenance, which is a kind of precautionary architecture.

[0098] Regarding step S400, the step of generating a direct operation and maintenance order pointing to the power subject and an indirect operation and maintenance order pointing to other power subjects of the same category when the subject data of any power subject reaches the preset operation and maintenance condition comprises:

[0099] Determine a first time range based on the current time and a preset first time span;

[0100] Obtain the subject data of each power subject in the first time range, and construct an instantaneous data matrix;

[0101] Input the instantaneous data matrix into the trained determination model, and output a determination state; the determination state includes reaching and not reaching, and is used to represent whether the subject data of the power subject reaches the preset operation and maintenance condition;

[0102] When the determination state is reached, a direct operation and maintenance work order pointing to the power subject and an indirect operation and maintenance work order pointing to other power subjects of the same kind are generated;

[0103] The task amount of the indirect operation and maintenance work order is less than that of the direct operation and maintenance work order.

[0104] The above describes the application stage, and a first time range is determined based on a current time and a preset first time span, for example, data within one minute is obtained with the current time as the tail time, and a data matrix is constructed, because it is data within one minute, it is equivalent to instantaneous data relative to a long-time work flow, and is referred to as an instantaneous data matrix; the instantaneous data matrix is input into a trained determination model, and a determination state is output; the determination state includes reached and not reached, and is used to represent whether the subject data of the power subject reaches a preset operation and maintenance condition; the determination model belongs to a conventional classification model, and the technical solution of the present application will not be described in detail.

[0105] When the determination state is reached, a direct operation and maintenance work order pointing to the power subject and an indirect operation and maintenance work order pointing to other power subjects of the same kind are generated; the task amount of the indirect operation and maintenance work order is less than that of the direct operation and maintenance work order.

[0106] As a preferred embodiment of the technical solution of the present application, the method further comprises:

[0107] Recording the operation and maintenance process based on a memory installed on the power subject;

[0108] Inputting the operation and maintenance process into a preset quantification model to obtain an operation and maintenance amount;

[0109] Statistically obtaining operation and maintenance amounts of the same power subject at different times, and adjusting the subject data uploading frequency according to the operation and maintenance amounts at different times;

[0110] Fitting the operation and maintenance amounts at different times to obtain an operation and maintenance amount change function;

[0111] Determining a second time range based on a current time and a preset second time span, calculating an integral of the operation and maintenance amount change function within the second time range, and adjusting the subject data uploading frequency according to the integral;

[0112] The uploading frequency is inversely proportional to the integral.

[0113] In an example of the technical scheme of the present application, a self-adjusting scheme applied to a power subject is provided, a storage record operation and maintenance process is installed on the power subject, the operation and maintenance process is input into a preset quantitative model, an operation and maintenance amount is obtained, which indicates when and to what extent the power subject is operated and maintained, since the staff uploads the work type of their own work when operating and maintaining, the operation and maintenance amount corresponding to the work type can be directly inquired in a preset table (the operation and maintenance amount of each operation and maintenance work is determined by the management personnel in advance); the operation and maintenance amounts of the same power subject at different time points are counted, and the operation and maintenance amounts at different time points are fitted according to the operation and maintenance amounts at different time points, to obtain an operation and maintenance amount change function.

[0114] Finally, a second time range is determined based on the current time point and a preset second time span, such as 24 hours backward from the current time point as the second time range; the integral of the operation and maintenance amount change function in the second time range is calculated, the integral of the operation and maintenance amount itself does not have actual significance, since the operation and maintenance work is performed at irregular times, that is, there are multiple time points with operation and maintenance amounts on the time axis, and for the time points without operation and maintenance behavior, the operation and maintenance amount is actually zero, but after fitting into a function, these positions are not zero, at this time, the operation and maintenance amount in a period of time seems to have a certain significance, which can be used to represent the validity degree of the operation and maintenance behavior, the greater the operation and maintenance amount, the greater the integral, and the better the validity degree; it should be noted that this relationship is not necessarily certain, it is only a trend, it is a high probability event, for example, replacing accessories has a larger operation and maintenance amount than repairing accessories, and the validity time should be longer in theory, but considering the reality, it is entirely possible that a special case occurs, so that the validity time is shorter, this special case is not considered in the technical scheme of the present application, and the present application only considers the relevant relationship under normal conditions.

[0115] Figure 2 The composition structure block diagram of the intelligent power operation and maintenance management system for work order closed loop processing is shown in FIG. 1, as a preferred embodiment of the technical scheme of the present application, the present application further provides an intelligent power operation and maintenance management system for work order closed loop processing, the system 10 comprises:

[0116] a subject data identification module 11, which is used for remotely acquiring subject data of a power subject, identifying the subject data, and determining the operation correlation degree of the power subject;

[0117] a motion trajectory analysis module 12, which is used for acquiring the motion trajectory of the staff according to a monitoring system, and determining the spatial correlation degree of the power subject according to the motion trajectory;

[0118] a power subject clustering module 13, which is used for clustering the power subject according to the operation correlation degree and the spatial correlation degree; wherein the clustering condition of the clustering process is determined by the resource amount of the operation and maintenance resource;

[0119] The operation and maintenance order generation module 14 is configured to generate a direct operation and maintenance order for any power subject and an indirect operation and maintenance order for other power subjects of the same type when the subject data of the power subject reaches a preset operation and maintenance condition, and the task amount of the indirect operation and maintenance order is less than that of the direct operation and maintenance order.

[0120] Further, the subject data identification module 11 comprises:

[0121] The subject data acquisition unit is configured to establish a connection channel with the power subject and remotely acquire the subject data of the power subject, and the subject data is an array with a time label, and each element in the array corresponds to a data type.

[0122] The curve sequence acquisition unit is configured to identify the subject data, fit the data of each element at different time points into a curve, retain the element sequence number, and obtain a curve sequence.

[0123] The correlation calculation unit is configured to compare the curve sequences of any two power subjects, and calculate the curve correlation of the curve corresponding to each element sequence number.

[0124] The correlation accumulation unit is configured to query the weight of the element corresponding to different curves, accumulate the curve correlation according to the weight, and obtain the operation correlation.

[0125] The calculation process of the curve correlation comprises: calculating the DTW distance of the two curves participating in the calculation, and determining the curve correlation according to the inverse ratio of the DTW distance.

[0126] Specifically, the motion trajectory analysis module 12 comprises:

[0127] The scene video acquisition unit is configured to establish a connection channel with the monitoring system and acquire the scene video of the power scene.

[0128] The target identification unit is configured to perform target identification on the scene video, locate the target, and extract the target feature.

[0129] The position fitting unit is configured to acquire all positions of the same target feature within a preset time period, fit all positions, and obtain the motion trajectory of the target.

[0130] The distance application unit is configured to query the distance between any two power subjects and each motion trajectory according to the distance, and determine the spatial correlation of the power subjects according to the queried distance.

[0131] The calculation process of the spatial correlation comprises: when the distances between two power subjects and a motion trajectory are both less than a preset distance threshold, marking the motion trajectory, recording the number of marked motion trajectories, and determining the spatial correlation according to the direct ratio of the number.

[0132] Further, the power subject clustering module 13 comprises:

[0133] Inquiring a resource amount of the operation and maintenance resource, and determining a class number of the clustering according to the resource amount;

[0134] Taking the class number as a K value, and performing K-means clustering on the power subject based on the operation correlation degree and the space correlation degree;

[0135] Inquiring a running operation and maintenance order in real time, and updating the resource amount of the operation and maintenance resource and the power subject participating in the clustering according to the operation and maintenance order.

[0136] The above merely describes the preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement and improvement within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A smart power operation and maintenance management method with closed-loop processing of work orders, characterized in that, The method includes: Remotely acquire the main data of the power entity, identify the main data, and determine the operational relevance of the power entity; Based on the movement trajectory of the staff obtained from the monitoring system, the spatial correlation of the power entity is determined based on the movement trajectory. The power system is clustered based on the operational relevance and spatial relevance; wherein the clustering conditions are determined by the amount of operation and maintenance resources. When the main data of any power entity reaches the preset operation and maintenance conditions, a direct operation and maintenance work order is generated for that power entity and an indirect operation and maintenance work order is generated for other power entities of the same type; among them, the workload of the indirect operation and maintenance work order is less than that of the direct operation and maintenance work order. The steps of remotely acquiring the main data of the power entity, identifying the main data, and determining the operational relevance of the power entity include: Establish a connection channel with the power entity to remotely acquire the power entity's main data; the main data is an array containing time tags, and each element in the array corresponds to a data type; The main data is identified, and the data of each element at different times is fitted into a curve, retaining the element index to obtain a curve sequence; Compare the curve sequences of any two power entities and calculate the curve correlation of the curve corresponding to each element number. Query the weights of the elements corresponding to different curves, and sum the curve relevance based on the weights to obtain the running relevance; The process of calculating curve correlation includes: calculating the DTW distance between the two curves involved in the calculation, and determining the curve correlation based on the inverse ratio of the DTW distance; The step of obtaining the movement trajectory of the staff from the monitoring system and determining the spatial correlation of the power entity based on the movement trajectory includes: Establish a connection channel with the monitoring system to acquire scene videos of the power scenario; The scene video is subjected to target recognition, target location, and target feature extraction; Obtain all positions of the same target feature within a preset time period, fit all positions, and obtain the target's motion trajectory; For any two power entities, query their distances to each motion trajectory, and determine the spatial correlation of the power entities based on the queried distances; The spatial correlation calculation process is as follows: when the distance between two power entities and a certain motion trajectory is less than a preset distance threshold, the motion trajectory is marked, the number of marked motion trajectories is recorded, and the spatial correlation is determined according to the direct proportion of the number.

2. The intelligent power operation and maintenance management method for closed-loop processing of work orders according to claim 1, characterized in that, The step of clustering the power entities based on the operational relevance and spatial relevance includes: Query the resource quantity of operation and maintenance resources, and determine the number of clusters based on the resource quantity; Using the number of clusters as the K value, K-means clustering is performed on the power system based on operational relevance and spatial relevance; Real-time query of ongoing maintenance work orders, and update the resource quantity of maintenance resources and the power entities participating in clustering based on the maintenance work orders.

3. The intelligent power operation and maintenance management method for closed-loop processing of work orders according to claim 2, characterized in that, The step of generating a direct maintenance work order for that power entity and an indirect maintenance work order for other power entities of the same type when the entity's main data reaches the preset maintenance conditions includes: The first time range is determined based on the current moment and the preset first time span; Acquire the main data of each power entity within the first time range and construct an instantaneous data matrix; The instantaneous data matrix is ​​input into the trained judgment model, and the judgment status is output; the judgment status includes reached and not reached, which is used to characterize whether the main data of the power entity has reached the preset operation and maintenance conditions. When the status is determined to be reached, a direct maintenance work order is generated for the power entity and an indirect maintenance work order is generated for other power entities of the same type. Among them, the workload of indirect maintenance work orders is less than that of direct maintenance work orders.

4. The intelligent power operation and maintenance management method for closed-loop processing of work orders according to claim 1, characterized in that, The method further includes: The operation and maintenance process is recorded using a memory device installed on the main power unit. Input the operation and maintenance process into a preset quantitative model to obtain the operation and maintenance quantity; Statistics on the maintenance volume of the same power entity at different times, and based on the maintenance volume at different times; The operation and maintenance volume at different times is fitted to obtain the operation and maintenance volume change function; A second time range is determined based on the current moment and a preset second time span. The integral of the operation and maintenance quantity change function is calculated within the second time range, and the upload frequency of the main data is adjusted according to the integral. The upload frequency is inversely proportional to the integral.

5. An intelligent power operation and maintenance management system for closed-loop processing of work orders, characterized in that, The system includes: The main data identification module is used to remotely acquire the main data of the power entity, identify the main data, and determine the operational relevance of the power entity. The motion trajectory analysis module is used to obtain the motion trajectory of the staff from the monitoring system and determine the spatial correlation of the power entity based on the motion trajectory. The power entity clustering module is used to cluster power entities based on the operational relevance and spatial relevance; wherein, the clustering conditions of the clustering process are determined by the resource quantity of operation and maintenance resources; The maintenance work order generation module is used to generate direct maintenance work orders for any power entity and indirect maintenance work orders for other power entities of the same type when the main data of any power entity reaches the preset maintenance conditions; wherein, the workload of indirect maintenance work orders is less than that of direct maintenance work orders. The main data identification module includes: The main data acquisition unit is used to establish a connection channel with the power entity and remotely acquire the main data of the power entity; the main data is an array containing time tags, and each element in the array corresponds to a data type; The curve sequence acquisition unit is used to identify the main data, fit the data of each element at different times into a curve, retain the element index, and obtain the curve sequence. The correlation calculation unit is used to compare the curve sequences of any two power entities and calculate the curve correlation of the curve corresponding to each element number. The relevance accumulation unit is used to query the weights of elements corresponding to different curves, and accumulate the curve relevances based on the weights to obtain the running relevance. The process of calculating curve correlation includes: calculating the DTW distance between the two curves involved in the calculation, and determining the curve correlation based on the inverse ratio of the DTW distance; The motion trajectory analysis module includes: The scene video acquisition unit is used to establish a connection channel with the monitoring system and acquire scene videos of the power scene. The target recognition unit is used to perform target recognition on the scene video, locate the target, and extract target features; The position fitting unit is used to obtain all positions of the same target feature within a preset time period, fit all positions, and obtain the motion trajectory of the target. The distance application unit is used to query the distance between any two power entities and each movement trajectory, and determine the spatial correlation of the power entities based on the queried distances; The spatial correlation calculation process is as follows: when the distance between two power entities and a certain motion trajectory is less than a preset distance threshold, the motion trajectory is marked, the number of marked motion trajectories is recorded, and the spatial correlation is determined according to the direct proportion of the number.

6. The intelligent power operation and maintenance management system for closed-loop processing of work orders according to claim 5, characterized in that, The power entity clustering module includes: Query the resource quantity of operation and maintenance resources, and determine the number of clusters based on the resource quantity; Using the number of clusters as the K value, K-means clustering is performed on the power system based on operational relevance and spatial relevance; Real-time query of ongoing maintenance work orders, and update the resource quantity of maintenance resources and the power entities participating in clustering based on the maintenance work orders.

Images