Power equipment data collection, analysis and testing platform based on multi-source fusion claims reporting

Abstract

The present invention belongs to the technical field of power equipment management, and specifically is a power equipment data collection, analysis and detection platform based on multi-source fusion claim declaration, including a server, a power equipment monitoring module, a data fusion module, a data in-depth analysis module and a claim declaration module; the present invention collects data of power equipment from multiple data sources through the power equipment monitoring module, and adopts a data fusion algorithm to fuse the multi-source data. The data in-depth analysis module adopts data mining and machine learning technology to conduct in-depth analysis on the fused power equipment operation status data set. The claim declaration module automatically determines whether to generate corresponding claim declaration information based on the in-depth analysis results, thereby realizing comprehensive and accurate monitoring of the operation status of the power equipment, improving the accuracy and efficiency of the claim declaration, and being able to formulate matching management plans for different power equipment and timely optimize and improve the platform, with a high degree of intelligence.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment management, and in particular to a power equipment data collection, analysis and detection platform based on multi-source fusion claims reporting. Background Art

[0002] Power equipment refers to the equipment that performs power transmission and distribution, voltage conversion, protection and control in the power system. It mainly includes two categories: power generation equipment and power supply equipment. With the continuous development of the power system, the safe and stable operation of power equipment is crucial to the stability of the power system. However, due to equipment aging, environmental factors, human errors and other reasons, power equipment failures occur from time to time;

[0003] Traditional power equipment monitoring and claims reporting methods usually rely on a single data source, which often cannot fully and accurately reflect the operating status of power equipment, resulting in adverse effects on the accuracy and efficiency of claims reporting. In addition, they cannot accurately feedback the historical claims status of each power equipment and reasonably plan subsequent equipment management plans, and cannot accurately evaluate the operating performance of the detection platform, resulting in a low degree of intelligence.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the invention

[0005] The purpose of the present invention is to provide an electric power equipment data collection, analysis and detection platform based on multi-source fusion claims reporting, which solves the problem that the existing technology is often unable to comprehensively and accurately reflect the operating status of the equipment, resulting in the accuracy and efficiency of claims reporting being adversely affected, and cannot accurately feedback the historical claims status of each electric power equipment and accurately evaluate the operating performance of the detection platform, and has a low level of intelligence.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] The power equipment data collection, analysis and detection platform based on multi-source fusion claims declaration includes a server, a power equipment monitoring module, a data fusion module, a data in-depth analysis module and a claims declaration module; the power equipment monitoring module collects power equipment data from multiple data sources through an API interface, data capture and sensor detection, and sends the collected multi-source data of the power equipment to the data fusion module via the server, wherein the data sources include the power equipment's own monitoring system, the external environment monitoring system and the manual operation recording system;

[0008] The data fusion module uses a data fusion algorithm to fuse the received multi-source data of the power equipment, eliminate redundancy and contradiction between the data, generate a comprehensive power equipment operation status data set, and send the generated power equipment operation status data set to the data in-depth analysis module via the server;

[0009] The data in-depth analysis module uses data mining and machine learning technology to conduct in-depth analysis on the integrated power equipment operating status data set, and sends the corresponding in-depth analysis results to the claim declaration module via the server; the claim declaration module automatically determines whether to generate corresponding claim declaration information based on the in-depth analysis results of the data in-depth analysis module, and sends the generated claim declaration information of the power equipment to the relevant departments for review and processing; among them, the relevant departments include the insurance company's claims department, the power equipment maintenance department and the technical department responsible for power equipment failure investigation.

[0010] Furthermore, the specific operation process of the data in-depth analysis module includes:

[0011] Preprocess the fused data set of power equipment operation status, including data cleaning, denoising and normalization operations; use data mining technology to conduct data mining, and capture the correlation between the power equipment operation status and the external environment and human operation factors through association rule mining. Use cluster analysis to classify equipment with similar operation characteristics, capture the commonalities and differences between power equipment, and classify the operation status of power equipment according to historical data through classification and prediction, and predict potential fault trends;

[0012] Based on data mining, machine learning technology is used to accurately analyze and predict the operating status of the equipment; when the data in-depth analysis module identifies the abnormal status of the power equipment or predicts a potential failure trend, a detailed report is generated, including the faulty equipment information, failure time, failure type and the inferred cause of the failure.

[0013] Furthermore, the specific operation process of the claims reporting module includes:

[0014] Obtain the in-depth analysis results of the data in-depth analysis module, generate corresponding claim declaration information according to the content of the report generated by the in-depth analysis module, and automatically select the corresponding claim terms and claims process. After the claim declaration information is generated, it will be sent to the relevant department for review and processing;

[0015] After the claim declaration information is sent, the processing process is tracked and monitored. If the relevant departments have questions about the claim declaration information or need further information, the claim declaration module will receive the corresponding feedback in a timely manner and work with the data in-depth analysis module to provide the required additional data or explanatory information.

[0016] Furthermore, the server is communicatively connected to the operation efficiency detection and evaluation module and the operation condition detection and evaluation module. The operation efficiency detection and evaluation module is used to detect and analyze the operation efficiency of the power equipment data acquisition and analysis detection platform, generate a normal operation efficiency detection signal or an abnormal operation efficiency detection signal through analysis, and send the normal operation efficiency detection signal or the abnormal operation efficiency detection signal to the server;

[0017] The server sends the normal operation efficiency detection signal to the operation condition detection and evaluation module. The operation condition detection and evaluation module is used to analyze the operation smoothness of the power equipment data acquisition, analysis and detection platform, generate a normal operation condition signal or an abnormal operation condition signal through analysis, and send the normal operation condition signal or the abnormal operation condition signal to the server; after generating the abnormal operation efficiency signal or the abnormal operation condition signal, the power equipment data acquisition, analysis and detection platform is optimized and improved.

[0018] Furthermore, the specific operation process of the operation efficiency detection and evaluation module includes:

[0019] The time when the power equipment monitoring module sends the multi-source data of the power equipment to the data fusion module via the server is collected and marked as the initial time of operation and measurement, and the time when the claim declaration module automatically determines whether to generate the corresponding claim declaration information is collected and marked as the end time of operation and measurement, and the time difference between the end time of operation and measurement and the initial time of operation and measurement is calculated to obtain the meter measurement time; the management cycle is set, all meter measurement times within the management cycle are collected, and all meter measurement times are established into a meter measurement time set;

[0020] The meter measurement condition analysis value is obtained by calculating the mean of the meter measurement time set, and the number of subsets in the meter measurement time set whose values ​​exceed the preset meter measurement time threshold is marked as meter measurement efficiency outliers; the operation efficiency evaluation value is obtained by numerically calculating the meter measurement condition analysis value and the meter measurement efficiency outlier, and the operation efficiency evaluation value is numerically compared with the preset operation efficiency evaluation threshold. If the operation efficiency evaluation value exceeds the preset operation efficiency evaluation threshold, an operation efficiency detection abnormal signal is generated; if the operation efficiency evaluation value does not exceed the preset operation efficiency evaluation threshold, a normal operation efficiency detection signal is generated.

[0021] Furthermore, the specific operation process of the transport condition detection and evaluation module includes:

[0022] The number of times the power equipment data collection, analysis and detection platform is attacked by the network during the management period is collected and marked as the platform attack value, and several detection time points are set during the management period, and the power equipment data collection, analysis and detection platform is scanned for vulnerabilities at the corresponding detection time points, and the ratio of the number of detection time points with vulnerabilities to the total number of detection time points is marked as the vulnerability analysis value, and the number of vulnerabilities at all detection time points is averaged to obtain the vulnerability status value;

[0023] The operation analysis value is obtained by numerically calculating the platform attack value, vulnerability analysis value and vulnerability condition value, and the operation analysis value is numerically compared with the preset operation analysis threshold. If the operation analysis value exceeds the preset operation analysis threshold, an operation abnormality signal is generated.

[0024] Furthermore, if the operation status table analysis value does not exceed the preset operation status table analysis threshold, the number of times the power equipment data acquisition, analysis and detection platform cannot operate normally within the management period is obtained and marked as the non-operation frequency analysis value, and the time difference between each time of non-operation and the time of normal operation recovery is calculated to obtain the non-operation time length, all non-operation time lengths are summed up to obtain the non-operation time analysis value, and the ratio of the number of non-operation time lengths exceeding the preset non-operation time length threshold to the non-operation frequency analysis value is marked as the non-operation excess analysis value;

[0025] The operation condition analysis value is obtained by numerically calculating the operation condition table analysis value, the non-operation frequency analysis value, the non-operation time analysis value and the non-operation excess analysis value, and the operation condition analysis value is numerically compared with the preset operation condition analysis threshold value. If the operation condition analysis value exceeds the preset operation condition analysis threshold value, an abnormal operation signal is generated; if the operation condition analysis value does not exceed the preset operation condition analysis threshold value, a normal operation signal is generated.

[0026] Furthermore, the server is connected to the power equipment management module for communication. The power equipment management module obtains the power equipment to be supervised, marks the corresponding power equipment as i, where i is a positive integer; collects the commissioning date of the power equipment i, marks the interval between the commissioning date and the current date as the commissioning stage, obtains all the claim declaration information generated by the power equipment i during the commissioning stage, collects the number of claims and the total amount of claims based on the claim declaration information, and calculates the time difference between the occurrence times of two adjacent groups of claim processes to obtain the claim interval value;

[0027] The average of all claim interval values ​​is calculated to obtain the claim interval value, the power equipment management score is obtained by numerically calculating the number of claims, the total claim amount and the claim interval value, and the power equipment management score is numerically compared with the preset power equipment management score threshold. If the power equipment management score exceeds the preset power equipment management score threshold, the corresponding power equipment i is marked as a high-claim management object; if the power equipment management score does not exceed the preset power equipment management score threshold, the corresponding power equipment i is marked as a low-claim management object, and the marking information of the power equipment i is sent to the server.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. In the present invention, the data of the power equipment is collected from multiple data sources through the power equipment monitoring module, the data fusion module uses the data fusion algorithm to fuse the multi-source data, the data in-depth analysis module uses data mining and machine learning technology to conduct in-depth analysis on the fused power equipment operation status data set, and the claim declaration module automatically determines whether to generate corresponding claim declaration information according to the in-depth analysis results, so as to realize comprehensive and accurate monitoring of the operation status of the power equipment, improve the accuracy and efficiency of the claim declaration, and reasonably analyze the claim status of the power equipment in the commissioning stage through the power equipment management module, so as to formulate matching management plans for different power equipment in the future, with a high degree of intelligence;

[0030] 2. In the present invention, the operation efficiency of the power equipment data acquisition, analysis and testing platform is detected and analyzed through the operation efficiency detection and evaluation module, and a normal operation efficiency detection signal or an abnormal operation efficiency detection signal is generated through analysis. When the normal operation efficiency detection signal is generated, the operation smoothness of the power equipment data acquisition, analysis and testing platform is analyzed through the operation condition detection and evaluation module, and a normal operation condition signal or an abnormal operation condition signal is generated through analysis. After the abnormal operation efficiency detection signal or the abnormal operation condition signal is generated, the power equipment data acquisition, analysis and testing platform is optimized and improved to ensure the subsequent performance of the power equipment data acquisition, analysis and testing platform and further improve its intelligence level. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0032] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0033] Figure 2 This is a system block diagram of Embodiment 2 and Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Embodiment 1: Figure 1As shown, the electric power equipment data collection, analysis and detection platform based on multi-source fusion claims declaration proposed in the present invention includes a server, an electric power equipment monitoring module, a data fusion module, a data in-depth analysis module and a claims declaration module; wherein the electric power equipment monitoring module collects data of the electric power equipment from multiple data sources through API interface, data capture and sensor detection, and sends the collected multi-source data of the electric power equipment to the data fusion module via the server, wherein the data source includes the monitoring system of the electric power equipment itself, the external environment monitoring system and the manual operation recording system, etc., and the collected data includes but is not limited to the operating parameters, environmental parameters and operation records of the electric power equipment, etc.;

[0036] The data fusion module uses data fusion algorithms to fuse the multi-source data of the received power equipment, such as weighted average method, Kalman filter method, neural network method, etc., to fuse the collected multi-source data, eliminate redundancy and contradiction between data, and generate a comprehensive power equipment operation status data set, and send the generated power equipment operation status data set to the data in-depth analysis module via the server;

[0037] The data in-depth analysis module uses data mining and machine learning technologies to conduct in-depth analysis on the integrated power equipment operation status data set, identify the abnormal status of the equipment, predict the failure trend of the equipment, and send the corresponding in-depth analysis results to the claim declaration module via the server; the specific operation process of the data in-depth analysis module is as follows:

[0038] The fused data set of power equipment operation status is preprocessed, including data cleaning, denoising and normalization, to improve the quality and availability of the data. The processed data will be used for subsequent mining and analysis; data mining techniques are used for data mining, such as association rule mining, cluster analysis, classification and prediction, to conduct in-depth analysis of the processed data; for example, association rule mining can be used to discover the relationship between the equipment operation status and external environment, human operation and other factors, and cluster analysis can be used to group equipment with similar operation characteristics into one category, thereby discovering the commonalities and differences between the equipment, and classification and prediction can be used to classify the equipment operation status based on historical data and predict possible future fault trends;

[0039] Based on data mining, machine learning technologies such as deep learning, support vector machines, and random forests are used to analyze and predict the operating status of the equipment more accurately. It should be noted that these machine learning algorithms can automatically learn the operating rules of the equipment and predict the future status of the equipment based on the learned rules. Through continuous learning and adjustment, the machine learning model can gradually improve the accuracy of the prediction.

[0040] When the data in-depth analysis module identifies the abnormal state of the power equipment or predicts a potential failure trend, it generates a detailed report, including the faulty equipment information, failure time, failure type and the inferred cause of the failure. This report is based on the in-depth analysis of multi-source data and is therefore highly accurate and reliable. It should be noted that the data in-depth analysis module will also establish a fault model based on the equipment's operating history data and fault data. The fault model can determine and reflect the equipment's fault distribution, fault frequency, fault severity and other information, thereby providing a strong basis for claims reporting. When the equipment fails, the claims reporting module can quickly determine the fault type, fault cause and other information based on the fault model, and generate corresponding claims reporting basis information.

[0041] The claim declaration module automatically determines whether to generate corresponding claim declaration information based on the in-depth analysis results of the data in-depth analysis module, and sends the generated claim declaration information of the power equipment to relevant departments for review and processing; the relevant departments include the insurance company's claims department, the power equipment maintenance department, and the technical department responsible for power equipment failure investigation, etc. Through the automated information sending mechanism, it can ensure that these departments receive the claim declaration information as soon as possible, so as to review and process it in time; the specific operation process of the claim declaration module is as follows:

[0042] Obtain the in-depth analysis results of the data in-depth analysis module. When the data in-depth analysis module identifies the abnormal state of the power equipment or predicts the potential failure trend and generates a detailed report, the claim declaration module generates corresponding claim declaration information according to the content of the generated report, including basic information of the equipment (such as equipment model, manufacturer, installation location, etc.), specific description of the failure, time of the failure, potential losses that may be caused by the failure, etc.; and can automatically select corresponding claim terms and claims procedures according to the type and cause of the power equipment failure;

[0043] After the claim declaration information is generated, it will be sent to the relevant departments for review and processing. After the claim declaration information is sent, the processing process will be tracked and monitored. If the relevant departments have questions about the claim declaration information or need further information, the claim declaration module will receive the corresponding feedback in a timely manner and work with the data in-depth analysis module to provide the required additional data or explanatory information. This real-time feedback mechanism helps to ensure the smooth progress of the claims process and further improve the accuracy and efficiency of claims declaration.

[0044] It should be noted that the claims reporting module plays a vital role in the power equipment data collection, analysis and detection platform based on multi-source fusion claims reporting. It automatically generates and sends claims reporting information based on the output results of the data in-depth analysis module, and tracks and monitors the entire claims process. This automated processing method not only improves the accuracy and efficiency of claims reporting, but also reduces the possibility of human errors, bringing significant improvements to the claims work of power equipment.

[0045] Further, the server is connected in communication with the power equipment management module, and the power equipment management module obtains the power equipment to be supervised, marks the corresponding power equipment as i, where i is a positive integer; collects the commissioning date of the power equipment i, marks the interval between the commissioning date and the current date as the commissioning stage, obtains all the claim declaration information generated by the power equipment i in the commissioning stage, collects the number of claims and the total amount of claims of the power equipment i based on the claim declaration information, calculates the time difference between the occurrence times of two adjacent groups of claim processes to obtain the claim interval value, and calculates the average of all claim interval values ​​to obtain the claim interval value;

[0046] By formula The number of claims GL i, the total amount of claims GKi and the claim interval value GF i are numerically calculated to obtain the power equipment management score GY i, where a1, a2 and a3 are preset proportional coefficients, and the values ​​of a1, a2 and a3 are all positive numbers; and the larger the value of the power equipment management score GYi, the worse the operating performance of the power equipment i;

[0047] The power equipment management score GYi is numerically compared with the preset power equipment management score threshold. If the power equipment management score GYi exceeds the preset power equipment management score threshold, it indicates that the operating performance of the power equipment i is poor and it is necessary to strengthen the key supervision of the power equipment i, then the corresponding power equipment i will be marked as a high-level claim management object; if the power equipment management score GYi does not exceed the preset power equipment management score threshold, it indicates that the operating performance of the power equipment i is good, then the corresponding power equipment i will be marked as a low-level claim management object, and the marking information of the power equipment i will be sent to the server, so that matching management plans can be formulated for different power equipment in the future, which is convenient for the subsequent management of the power equipment and has a high degree of intelligence.

[0048] Embodiment 2: Figure 2As shown, the difference between this embodiment and embodiment 1 is that the server is connected to the operation efficiency detection and evaluation module in communication, and the operation efficiency detection and evaluation module detects and analyzes the operation efficiency of the power equipment data acquisition, analysis and detection platform, generates a normal operation efficiency detection signal or an abnormal operation efficiency detection signal through analysis, and sends the normal operation efficiency detection signal or the abnormal operation efficiency detection signal to the server, and optimizes and improves the power equipment data acquisition, analysis and detection platform after generating the abnormal operation efficiency detection signal, so as to ensure the subsequent use performance of the power equipment data acquisition, analysis and detection platform; the specific operation process of the operation efficiency detection and evaluation module is as follows:

[0049] The time when the power equipment monitoring module sends the multi-source data of the power equipment to the data fusion module via the server is collected and marked as the initial time of operation and measurement, and the analysis end time when the claim declaration module automatically determines whether to generate the corresponding claim declaration information is collected and marked as the end time of operation and measurement, and the time difference between the end time of operation and measurement and the initial time of operation and measurement is calculated to obtain the meter measurement time, wherein the larger the value of the meter measurement time is, the lower the analysis efficiency of the corresponding analysis process is;

[0050] A management cycle is set, preferably, the management cycle is thirty-five days; all meter measurement times within the management cycle are collected, and a meter measurement time set is established for all meter measurement times; the meter measurement condition analysis value is obtained by calculating the mean of the meter measurement time set, and the number of subsets in the meter measurement time set whose values ​​exceed the preset meter measurement time threshold is marked as meter measurement efficiency anomaly values; it should be noted that the larger the values ​​of the meter measurement condition analysis value and the meter measurement efficiency anomaly value are, the lower the overall operating efficiency of the power equipment data collection, analysis and detection platform within the management cycle is;

[0051] The meter condition analysis value XS and the meter efficiency anomaly value XP are numerically calculated using the formula XK=fw1*XS+fw2*XP to obtain the operation efficiency evaluation value XK, wherein fw1 and fw2 are preset weight coefficients, fw2>fw1>0; and, the larger the numerical value of the operation efficiency evaluation value XK is, the worse the overall operation efficiency of the power equipment data collection, analysis and detection platform during the management period is; the operation efficiency evaluation value XK is numerically compared with the preset operation efficiency evaluation threshold value, if the operation efficiency evaluation value XK exceeds the preset operation efficiency evaluation threshold value, indicating that the overall operation efficiency of the power equipment data collection, analysis and detection platform during the management period is poor, then an operation efficiency detection abnormal signal is generated; if the operation efficiency evaluation value XK does not exceed the preset operation efficiency evaluation threshold value, indicating that the overall operation efficiency of the power equipment data collection, analysis and detection platform during the management period is good, then a normal operation efficiency detection signal is generated.

[0052] Embodiment 3: Figure 2As shown, the difference between this embodiment and embodiment 1 and embodiment 2 is that the server is connected to the operation detection and evaluation module in communication, and the server sends the normal operation detection signal to the operation detection and evaluation module. The operation detection and evaluation module analyzes the operation smoothness of the power equipment data acquisition, analysis and detection platform, generates a normal operation signal or an abnormal operation signal through analysis, and sends the normal operation signal or the abnormal operation signal to the server. After the abnormal operation signal is generated, the power equipment data acquisition, analysis and detection platform is optimized and improved to further ensure the subsequent use performance of the power equipment data acquisition, analysis and detection platform. The specific operation process of the operation detection and evaluation module is as follows:

[0053] The number of times the power equipment data collection, analysis and detection platform is attacked by the network during the management period is collected and marked as the platform attack value, and several detection time points are set during the management period, and the power equipment data collection, analysis and detection platform is scanned for vulnerabilities at the corresponding detection time points, and the ratio of the number of detection time points with vulnerabilities to the total number of detection time points is marked as the vulnerability analysis value, and the number of vulnerabilities scanned at the corresponding detection time point is marked as the vulnerability status table value, and the vulnerability status table values ​​(i.e., the number of vulnerabilities) of all detection time points in the management period are averaged to obtain the vulnerability status value;

[0054] By formula The platform attack value RF, vulnerability analysis value RK and vulnerability condition value RQ are numerically calculated to obtain the operation status analysis value RY, wherein kp1, kp2 and kp3 are preset proportional coefficients, kp2>kp3>kp1>0; and, the larger the value of the operation status analysis value RY is, the worse the overall operation performance of the power equipment data collection, analysis and detection platform during the management period is; the operation status analysis value RY is numerically compared with the preset operation status analysis threshold value, if the operation status analysis value RY exceeds the preset operation status analysis threshold value, indicating that the overall operation performance of the power equipment data collection, analysis and detection platform during the management period is poor, then an abnormal operation signal is generated.

[0055] Furthermore, if the operation table analysis value RY does not exceed the preset operation table analysis threshold, the number of times the power equipment data acquisition, analysis and detection platform cannot operate normally during the management period (that is, the power equipment data acquisition, analysis and detection platform cannot operate normally due to a crash or other conditions) is obtained and marked as a non-operation frequency analysis value, and the time difference between each time when the operation cannot be performed and the time when normal operation is restored is calculated to obtain the non-operation duration, all non-operation durations are summed up to obtain the non-operation duration analysis value, and the non-operation duration is numerically compared with the preset non-operation duration threshold, and the ratio of the number of non-operation durations exceeding the preset non-operation duration threshold to the non-operation frequency analysis value is marked as a non-operation excess analysis value;

[0056] The operation status analysis value WX is obtained by numerically calculating the operation status table analysis value RY, the non-operation frequency analysis value WK, the non-operation time analysis value WF and the non-operation excess analysis value WS through the formula WX=ty1*RY+ty2*WK+ty3*WF / (ty2+ty4)+ty4*WS, wherein ty1, ty2, ty3, ty4 are preset proportional coefficients, and the values ​​of ty1, ty2, ty3, ty4 are all greater than zero; and the larger the value of the operation status analysis value WX is, the worse the operation status of the power equipment data acquisition, analysis and detection platform is in general within the management period;

[0057] The operation condition analysis value WX is numerically compared with the preset operation condition analysis threshold. If the operation condition analysis value WX exceeds the preset operation condition analysis threshold, it indicates that the operation condition of the power equipment data collection, analysis and detection platform within the management period is poor on the whole, and an abnormal operation signal is generated; if the operation condition analysis value WX does not exceed the preset operation condition analysis threshold, it indicates that the operation condition of the power equipment data collection, analysis and detection platform within the management period is good on the whole, and a normal operation signal is generated.

[0058] The working principle of the present invention is as follows: when in use, the data of the power equipment is collected from multiple data sources through the power equipment monitoring module, the data fusion module adopts the data fusion algorithm to fuse the multi-source data of the received power equipment to generate a comprehensive power equipment operation status data set, the data in-depth analysis module adopts data mining and machine learning technology to perform in-depth analysis on the fused power equipment operation status data set, the claim declaration module automatically determines whether to generate corresponding claim declaration information according to the in-depth analysis result of the data in-depth analysis module, and sends the generated claim declaration information of the power equipment to the relevant department for review and processing, by fusing multiple data sources, the comprehensive and accurate monitoring of the operation status of the power equipment is realized, the accuracy and efficiency of the claim declaration are improved, the possibility of human error is reduced, and significant improvements are brought to the claim work of the power equipment, and the power equipment management module reasonably analyzes the claim status of all power equipment that needs to be supervised in the commissioning stage, and accordingly marks the corresponding power equipment as a claim senior management object or a claim low management object, so that the matching management plan can be formulated for different power equipment in the future, which is convenient for the subsequent management of the power equipment, and has a high degree of intelligence.

[0059] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The preferred embodiments of the present invention disclosed above are only used to help explain the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only specific implementation methods. Obviously, many modifications and changes can be made according to the contents of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present invention, so that technicians in the relevant technical field can understand and use the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. The power equipment data collection, analysis and detection platform based on multi-source fusion claims reporting is characterized by: It includes a server, a power equipment monitoring module, a data fusion module, a data in-depth analysis module and a claim declaration module; the power equipment monitoring module collects power equipment data from multiple data sources through API interface, data capture and sensor detection, and sends the collected multi-source data of the power equipment to the data fusion module via the server, wherein the data sources include the power equipment's own monitoring system, external environment monitoring system and manual operation recording system; The data fusion module uses a data fusion algorithm to fuse the received multi-source data of the power equipment to generate a comprehensive power equipment operation status data set, and sends the generated power equipment operation status data set to the data in-depth analysis module via the server; The data in-depth analysis module uses data mining and machine learning technology to conduct in-depth analysis on the integrated power equipment operation status data set, and sends the corresponding in-depth analysis results to the claim declaration module through the server; the claim declaration module automatically determines whether to generate corresponding claim declaration information based on the in-depth analysis results of the data in-depth analysis module, and sends the generated power equipment claim declaration information to the relevant departments for review and processing; The server is connected to the operation efficiency detection and evaluation module and the operation condition detection and evaluation module in communication. The operation efficiency detection and evaluation module is used to detect and analyze the operation efficiency of the power equipment data acquisition and analysis detection platform, generate a normal operation efficiency detection signal or an abnormal operation efficiency detection signal through analysis, and send the normal operation efficiency detection signal or the abnormal operation efficiency detection signal to the server; The server sends the normal operation efficiency detection signal to the operation condition detection and evaluation module, which is used to analyze the operation smoothness of the power equipment data acquisition, analysis and detection platform, generate a normal operation condition signal or an abnormal operation condition signal through analysis, and send the normal operation condition signal or the abnormal operation condition signal to the server; after generating the abnormal operation efficiency signal or the abnormal operation condition signal, optimize and improve the power equipment data acquisition, analysis and detection platform; The specific operation process of the operation efficiency detection and evaluation module includes: The time when the power equipment monitoring module sends the multi-source data of the power equipment to the data fusion module via the server is collected and marked as the initial time of operation and measurement, and the time when the claim declaration module automatically determines whether to generate the corresponding claim declaration information is collected and marked as the end time of operation and measurement, and the time difference between the end time of operation and measurement and the initial time of operation and measurement is calculated to obtain the meter measurement time; the management cycle is set, all meter measurement times within the management cycle are collected, and all meter measurement times are established into a meter measurement time set; The meter condition analysis value is obtained by calculating the mean of the meter measurement time set, and the number of subsets in the meter measurement time set whose values ​​exceed the preset meter measurement time threshold is marked as meter measurement efficiency outliers; the meter condition analysis value XS and the meter measurement efficiency outlier XP are numerically calculated by the formula XK=fw1*XS+fw2*XP to obtain the operation efficiency evaluation value XK, wherein fw1 and fw2 are preset weight coefficients, and fw2>fw1>0; the operation efficiency evaluation value is numerically compared with the preset operation efficiency evaluation threshold, and if the operation efficiency evaluation value exceeds the preset operation efficiency evaluation threshold, an abnormal operation efficiency detection signal is generated; if the operation efficiency evaluation value does not exceed the preset operation efficiency evaluation threshold, a normal operation efficiency detection signal is generated; The specific operation process of the transportation detection and evaluation module includes: The number of times the power equipment data collection, analysis and detection platform is attacked by the network during the management period is collected and marked as the platform attack value, and several detection time points are set during the management period, and the power equipment data collection, analysis and detection platform is scanned for vulnerabilities at the corresponding detection time points, and the ratio of the number of detection time points with vulnerabilities to the total number of detection time points is marked as the vulnerability analysis value, and the number of vulnerabilities at all detection time points is averaged to obtain the vulnerability status value; By formula The platform hit value RF, the vulnerability analysis value RK and the vulnerability condition value RQ are numerically calculated to obtain the operation status analysis value RY, wherein kp1, kp2 and kp3 are preset proportional coefficients, kp2>kp3>kp1>0; the operation status analysis value is numerically compared with the preset operation status analysis threshold value, and if the operation status analysis value exceeds the preset operation status analysis threshold value, an abnormal operation signal is generated; If the operation status table analysis value does not exceed the preset operation status table analysis threshold, the number of times the power equipment data acquisition, analysis and detection platform cannot operate normally within the management period is obtained and marked as the non-operation frequency analysis value, and the time difference between each time of non-operation and the time of normal operation recovery is calculated to obtain the non-operation time length, and all non-operation time lengths are summed up to obtain the non-operation time analysis value, and the ratio of the number of non-operation time lengths exceeding the preset non-operation time length threshold to the non-operation frequency analysis value is marked as the non-operation excess analysis value; The operation condition analysis value WX is obtained by numerically calculating the operation condition table analysis value RY, the non-operation frequency analysis value WK, the non-operation time analysis value WF and the non-operation super analysis value WS through the formula WX=ty1*RY+ty2*WK+ty3*WF / (ty2+ty4)+ty4*WS, wherein ty1, ty2, ty3, ty4 are preset proportional coefficients, and the values ​​of ty1, ty2, ty3, ty4 are all greater than zero; the operation condition analysis value is numerically compared with the preset operation condition analysis threshold value, if the operation condition analysis value exceeds the preset operation condition analysis threshold value, an abnormal operation condition signal is generated; if the operation condition analysis value does not exceed the preset operation condition analysis threshold value, a normal operation condition signal is generated; The server is connected to the power equipment management module for communication. The power equipment management module obtains the power equipment to be supervised, marks the corresponding power equipment as i, and i is a positive integer; collects the commissioning date of the power equipment i, marks the interval between the commissioning date and the current date as the commissioning stage, obtains all the claim declaration information generated by the power equipment i in the commissioning stage, collects the number of claims and the total amount of claims based on the claim declaration information, and calculates the time difference between the occurrence times of two adjacent groups of claim processes to obtain the claim interval value; calculates the average of all claim interval values ​​to obtain the claim interval value; By formula The number of claims GLi, the total amount of claims GKi and the claim interval value GFi are numerically calculated to obtain the power equipment management score GYi, where a1, a2, and a3 are preset proportional coefficients, and the values ​​of a1, a2, and a3 are all positive numbers; the power equipment management score is numerically compared with the preset power equipment management score threshold. If the power equipment management score exceeds the preset power equipment management score threshold, the corresponding power equipment i is marked as a high-claim management object; if the power equipment management score does not exceed the preset power equipment management score threshold, the corresponding power equipment i is marked as a low-claim management object, and the marking information of the power equipment i is sent to the server.

2. The power equipment data collection, analysis and detection platform based on multi-source fusion claims reporting according to claim 1 is characterized in that: The specific operation process of the data in-depth analysis module includes: The fused data set of power equipment operation status is preprocessed and data mining is performed using data mining technology. Based on data mining, machine learning technology is used to accurately analyze and predict the operation status of the equipment. When the data in-depth analysis module identifies the abnormal state of the power equipment or predicts a potential failure trend, a detailed report is generated.

3. The power equipment data collection, analysis and detection platform based on multi-source fusion claims reporting according to claim 1 is characterized in that: The specific operation process of the claims reporting module includes: Obtain the in-depth analysis results of the data in-depth analysis module, generate corresponding claim declaration information according to the content of the report generated by the in-depth analysis module, and automatically select the corresponding claim terms and claims process. After the claim declaration information is generated, it will be sent to the relevant department for review and processing; After the claim declaration information is sent, the processing process is tracked and monitored. If the relevant departments have questions about the claim declaration information or need further information, the claim declaration module will receive the corresponding feedback in a timely manner and work with the data in-depth analysis module to provide the required additional data or explanatory information.

Images