A power equipment operation and maintenance monitoring method and system based on data analysis

Abstract

The application discloses a kind of power equipment operation and maintenance monitoring method and system based on data analysis, it is related to electric power data analysis technical field, by calculating the failure propagation state S of power equipment, to comprehensively understand the failure interaction and propagation trend between equipment. By the comprehensive analysis of the distance D between power equipment and the failure propagation state S, the propagation range R of failure is calculated, the range of equipment that may be affected by failure is determined, and further data support is provided for adjusting the operating state of power equipment. Finally, according to the analysis results of failure propagation state S and influence range R, the equipment state Z that needs to be adjusted is determined, and through the trigger mechanism of adaptive matching power supply scheduling strategy, the intelligentialization and accuracy of power equipment operation and maintenance management are significantly improved, which overcomes the limitations that the correlation between equipment and the propagation influence cannot be comprehensively considered in traditional methods, so as to better cope with the complex failure propagation problem of modern power grid.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power data analysis, in particular to a power equipment operation and maintenance monitoring method and system based on data analysis. BACKGROUND

[0002] With the rapid development of intelligent technology, data analysis has gradually become an indispensable part of the power industry. In the power system, the stability and operation efficiency of the equipment are directly related to the safety of social energy supply, and power equipment operation and maintenance monitoring is an important part of ensuring the stable operation of the system. This field covers a wide range of technologies, including monitoring, fault diagnosis, predictive maintenance and other aspects.

[0003] In this process, real-time data collection and analysis become the core means. Specifically, power equipment operation and maintenance monitoring involves a wide variety of equipment, including transformers, switchgear, cables and transmission lines in substations. These devices need to be monitored in real time for their health status during daily operation, especially in complex power networks, where the failure of each device can trigger a chain reaction and affect the stable operation of the entire power grid.

[0004] Existing power equipment monitoring methods focus more on real-time monitoring and local fault warning of single devices. Traditional monitoring systems often rely on simple sensor data collection and fixed threshold alarm mechanisms. While this approach can quickly capture anomalies in individual devices, it is difficult to analyze the interactions between different devices and the global effects of fault propagation. For example, when a transformer fails, the traditional method may only warn of the device's anomaly, ignoring whether the failure will cause load anomalies or systemic failures in other related devices. Moreover, existing methods often fail to fully consider temporal and spatial factors such as the time, location of device failure and changes in surrounding loads, which leads to a relative lag in fault prediction and risk assessment, making it impossible to take effective preventive measures before the failure occurs. Although some advanced algorithms have begun to attempt multi-device fault diagnosis, most systems still cannot achieve global temporal and spatial analysis, lacking the ability to predict fault propagation paths. SUMMARY

[0005] To overcome the deficiencies of the prior art, the present application provides a power equipment operation and maintenance monitoring method and system based on data analysis, which solves the problems mentioned in the background art.

[0006] To achieve the above purpose, the present application is implemented by the following technical scheme: a power equipment operation and maintenance monitoring method based on data analysis, comprising the following steps:

[0007] S1, collecting real-time running state data of the equipment through sensors and equipment monitoring systems, collecting space-time information of the equipment, and then preprocessing the real-time running state data and the space-time information to form a space-time feature vector Fnew;

[0008] S2, extracting features from the space-time feature vector Fnew to obtain a feature vector associated with the occurrence of a fault, and forming a fault prediction feature vector Ffail;

[0009] S3, based on the obtained space-time feature vector Fnew and fault prediction feature vector Ffail, and in combination with historical fault data and network connection relationships stored by the power equipment, establishing a propagation matrix M between the power equipment, and obtaining a fault propagation state S of the power equipment;

[0010] S4, based on the space-time information in the space-time feature vector Fnew, obtaining a distance D between the power equipment, and calculating a propagation range of the fault based on the obtained fault propagation state S of the power equipment, to obtain a fault propagation influence range R;

[0011] S5, based on the obtained fault propagation state S and fault propagation influence range R, analyzing to obtain a power equipment state Z that needs to be adjusted, and regulating a trigger mechanism of a power supply scheduling strategy that is adaptively matched to the power equipment state Z.

[0012] Preferably, S1 includes S11 and S12;

[0013] S11, collecting real-time running state data and space-time information of the equipment through sensors and monitoring systems of the equipment, the real-time running state data including load L, power P, temperature W and vibration V data of the power equipment, and the space-time information including position coordinates (x, y) of the power equipment;

[0014] S12, preprocessing the real-time running state data, the preprocessing including missing data filling and standardization processing, obtaining standard load CL, standard power CP, standard temperature CW and standard vibration CV after preprocessing, and integrating with the space-time information to obtain the space-time feature vector Fnew.

[0015] Preferably, S2 includes S21 and S22;

[0016] S21, extracting features from the space-time feature vector Fnew to obtain a feature vector associated with the occurrence of a fault, including a load and fault correlation coefficient RLF, a temperature and fault correlation coefficient RWF, a vibration and fault correlation coefficient RVF, and a power and fault correlation coefficient RPF;

[0017] S22, reorganizing the position coordinates (x, y) and the time stamp t in the space-time feature vector Fnew through the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF and the power-fault correlation coefficient RPF to obtain a fault prediction feature vector Ffail.

[0018] Preferably, the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF and the power-fault correlation coefficient RPF can understand the correlation degree between the standard load CL, the standard power CP, the standard temperature CW and the standard vibration CV and the fault mark F;

[0019] Wherein, the correlation degree is as follows:

[0020] When the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF and the power-fault correlation coefficient RPF = 1, it indicates a positive correlation, indicating that when the standard load CL, the standard power CP, the standard temperature CW and the standard vibration CV increase, the probability of failure also increases, and there is a strict linear relationship between the two;

[0021] When the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF and the power-fault correlation coefficient RPF = 0, it indicates that there is no linear relationship, indicating that when the standard load CL, the standard power CP, the standard temperature CW and the standard vibration CV change, the probability of failure will not change, and the changes of the two are not related;

[0022] When the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF and the power-fault correlation coefficient RPF = -1, it indicates a negative correlation, indicating that when the standard load CL, the standard power CP, the standard temperature CW and the standard vibration CV increase, the probability of failure decreases, and there is a strict negative linear relationship between the two.

[0023] Preferably, the load-fault correlation coefficient RLF is obtained by the following calculation formula:

[0024]

[0025] In the formula, CL(p) represents the standard load of the pth data point, F(p) represents the fault mark of the power equipment at the pth data point, μ(F) represents the mean value of the fault mark data, reflecting the average probability of failure in the sampling time period, μ(CL) represents the mean value of the standard load data, specifically indicating the average value of all standard loads in the standard load sequence, n represents the total number of data points, specifically indicating the number of samples participating in the calculation of the power equipment;

[0026] The temperature and fault correlation coefficient RWF is obtained by the following calculation formula:

[0027]

[0028] In the formula, CW(p) represents the standard temperature of the pth data point, μ(CW) represents the mean of the standard temperature data, and specifically represents the average of all standard loads in the standard temperature sequence.

[0029] The vibration and fault correlation coefficient RVF is obtained by the following calculation formula:

[0030]

[0031] In the formula, CV(p) represents the standard vibration of the pth data point, μ(CV) represents the mean of the standard vibration data, and specifically represents the average of all standard loads in the standard vibration sequence.

[0032] The power and fault correlation coefficient RPF is obtained by the following calculation formula:

[0033]

[0034] In the formula, CP(p) represents the standard power of the pth data point, μ(CP) represents the mean of the standard power data, and specifically represents the average of all standard loads in the standard power sequence.

[0035] Preferably, S3 includes S31 and S32.

[0036] S31, based on the obtained space-time feature vector Fnew, combines the historical fault data stored by the power equipment and the connection relationship between each power equipment;

[0037] The historical fault data includes fault occurrence time, type and influence range; the connection relationship includes power transmission connection between power equipment, physical connection between power equipment and data exchange connection between power equipment;

[0038] Based on the historical fault data, the connection relationship between the power equipment and the space-time feature vector Fnew of the power equipment, the influence of different power equipment on other power equipment when a fault occurs is analyzed, including that a power equipment fault causes power failure, thereby affecting the connected other power equipment; the influence obtained based on the analysis establishes a propagation matrix M, each row and each column in the propagation matrix M represents a power equipment, and the element m(i, j) in the propagation matrix M represents the influence degree of the power equipment i on the power equipment j.

[0039] Preferably, S32 analyzes the fault propagation state S of each power device based on the propagation matrix M and the fault prediction feature vector Ffail, wherein the fault propagation state S is used to reflect the case that the fault of each power device is not only determined by the fault probability of the power device itself, but also related to the fault state of the adjacent device of the power device and the propagation path between the power devices;

[0040] The fault propagation state S is obtained by the following calculation formula:

[0041]

[0042] In the formula, S(i, t) represents the fault propagation state of the power device i at time t, a(i) represents the weighted coefficient of the power device i, which specifically represents the fault sensitivity of the power device i, Ffail(i, t) represents the fault prediction feature vector of the power device i at time t, w represents the total number of power devices, β(i, j) represents the fault influence weight of the power device i on the power device j, m(i, j) represents the influence degree of the power device i on the power device j in the propagation matrix M, Ffail(j, t) represents the fault prediction feature vector of the power device j at time t, λ(i, j) represents the attenuation factor of the fault propagation, which specifically represents the rate of attenuation of the propagation effect with the space distance and the time elapse when the fault propagates from the power device i to the power device j, △t represents the fault propagation time difference, and exp represents the exponential attenuation function.

[0043] Preferably, S4 includes S41;

[0044] S41, based on the space-time information in the space-time feature vector Fnew, obtains the distance D between the power devices, and calculates the propagation range of the fault with the obtained fault propagation state S of the power device to obtain the fault propagation influence range R;

[0045] Wherein, the distance D is calculated and obtained through the position coordinates (x, y) in the space-time information of the space-time feature vector Fnew;

[0046] The fault propagation influence range R is obtained by the following calculation formula:

[0047]

[0048] In the formula, R(i) represents the fault propagation influence range of the power device i, D(i, j) represents the distance between the power device i and the power device j, Dmax represents the upper limit influence distance of the power device fault propagation, which is specifically used for normalizing the distance D(i, j) between the power device i and the power device j, for simulating the distance attenuation effect.

[0049] Preferably, S5 includes S51;

[0050] S51, analyzing according to the obtained fault propagation state S and the fault propagation influence range R, obtaining the power equipment state Z that needs to be adjusted, and regulating the trigger mechanism of the power supply scheduling strategy that is adaptively matched to the power equipment state Z;

[0051] The power equipment state Z is obtained by the following analysis method:

[0052]

[0053] In the formula, Z(i, t) represents the power equipment state of the power equipment i at time t, S(i, t) represents the fault propagation state of the power equipment i at time t, R(i, t) represents the fault propagation influence range of the power equipment i at time t, Sthe represents the preset fault propagation state trigger threshold, and Rthe represents the preset fault propagation influence range trigger threshold.

[0054] When the power equipment state Z(i, t) of the power equipment i at time t is 1, it indicates that the power equipment i needs to be adjusted, the power supply scheduling strategy matched to the power equipment i is triggered, and the related inspection and maintenance personnel are prompted that the power equipment i needs to be maintained, a maintenance task is generated and sent to the to-be-processed task list of the related inspection and maintenance personnel for processing.

[0055] When the power equipment state Z(i, t) of the power equipment i at time t is 0, it indicates that the power equipment i does not need to be adjusted.

[0056] The matched power supply scheduling strategy is used to detect the number of power equipment that needs to be adjusted, and when the total number of power equipment that needs to be adjusted reaches the preset distributed fault threshold, the fault equipment is prompted to be fault separated.

[0057] A power equipment operation and maintenance monitoring system based on data analysis includes a power equipment data acquisition module, a fault prediction correlation module, a power equipment fault propagation module, a propagation influence range module, and a power equipment operation and maintenance decision module.

[0058] The power equipment data acquisition module collects real-time running state data of the equipment through sensors and equipment monitoring systems, and collects space-time information of the equipment, and then pre-processes the real-time running state data and the space-time information to form a space-time feature vector Fnew.

[0059] The fault prediction correlation module extracts features from the space-time feature vector Fnew, obtains a feature vector associated with a fault occurrence, and forms a fault prediction feature vector Ffail.

[0060] The power equipment fault propagation module is based on the obtained space-time feature vector Fnew and the fault prediction feature vector Ffail, and combines the historical fault data and network connection relationship stored by the power equipment, to establish a propagation matrix M between the power equipment, and obtain a fault propagation state S of the power equipment;

[0061] The propagation influence range module obtains the distance D between the power equipment based on the space-time information in the space-time feature vector Fnew, and calculates the propagation range of the fault by the obtained fault propagation state S of the power equipment, to obtain a fault propagation influence range R;

[0062] The power equipment operation and maintenance decision module analyzes the obtained fault propagation state S and the fault propagation influence range R, obtains a power equipment state Z that needs to be adjusted, and controls the trigger mechanism of the power supply scheduling strategy that is adaptively matched to the power equipment state Z.

[0063] The application provides a power equipment operation and maintenance monitoring method and system based on data analysis, which has the following beneficial effects:

[0064] (1) The fault propagation state S of the power equipment is calculated, so that the fault interaction and propagation trend between the equipment are comprehensively understood. The distance D between the power equipment and the fault propagation state S are comprehensively analyzed, the propagation range R of the fault is calculated, the range of the equipment that may be affected by the fault is determined, and data support is further provided for adjusting the operation state of the power equipment. Finally, according to the analysis results of the fault propagation state S and the influence range R, the equipment state Z that needs to be adjusted is determined, and the trigger mechanism of the power supply scheduling strategy that is adaptively matched is controlled, which significantly improves the intelligence and accuracy of the power equipment operation and maintenance management, overcomes the limitation that the correlation and propagation influence between the equipment cannot be comprehensively considered in the traditional method, and better deals with the complex fault propagation problem of the modern power grid.

[0065] (2) By establishing the propagation matrix M, the influence degree between each power equipment is quantified, and it is further revealed how a fault of one equipment affects other power equipment through power transmission, physical connection or data exchange, etc. Each element m(i, j) in the propagation matrix M represents the influence of the power equipment i on the power equipment j, which helps to identify the potential fault chain. On this basis, by calculating the fault propagation state S, it is further revealed that the fault propagation of the power equipment is not only affected by the fault probability itself, but also affected by the correlation with the adjacent equipment and the propagation path. It can effectively prevent large-scale fault propagation, improve the emergency response capability of the power equipment operation, and especially in the early stage of the fault, the propagation range of the fault can be accurately predicted, and the stability of the power equipment operation and maintenance is improved.

[0066] (3) By combining the space-time feature vector Fnew of the power equipment and the fault propagation state S, as well as the distance D between the power equipment, the accurate calculation of the fault propagation influence range R is realized. Through the normalization processing of the distance between the equipment and the application of the exponential decay function, the spatial attenuation effect of the fault propagation can be effectively simulated, and the accurate definition of the fault propagation influence range is ensured. Subsequently, based on the fault propagation state S and the influence range R, the power equipment state Z that needs to be adjusted can be intelligently analyzed, and the corresponding power equipment scheduling strategy is triggered. This scheduling mechanism can curb the further spread of the fault by adjusting the equipment state in the early stage of fault propagation. BRIEF DESCRIPTION OF DRAWINGS

[0067] Figure 1 For the power equipment operation and maintenance monitoring method based on data analysis of the present application, a step schematic diagram is shown in the figure;

[0068] Figure 2 For the power equipment operation and maintenance monitoring system based on data analysis of the present application, a block diagram schematic diagram is shown in the figure;

[0069] Figure 3 For the correlation degree fluctuation schematic diagram; DETAILED DESCRIPTION

[0070] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0071] Embodiment 1

[0072] The present application provides a power equipment operation and maintenance monitoring method based on data analysis, please refer to Figure 1 , including the following steps:

[0073] S1, the real-time running state data of the equipment is collected through the sensor and the equipment monitoring system, and the space-time information of the equipment is collected, and then the real-time running state data and the space-time information are preprocessed to form a space-time feature vector Fnew;

[0074] S2, the space-time feature vector Fnew is subjected to feature extraction, the feature vector associated with the occurrence of the fault is obtained, and a fault prediction feature vector Ffail is formed;

[0075] S3, based on the obtained space-time feature vector Fnew and fault prediction feature vector Ffail, and combined with the historical fault data and network connection relationship stored by the power equipment, a propagation matrix M between the power equipment is established, and the fault propagation state S of the power equipment is obtained;

[0076] S4, based on the space-time information in the space-time feature vector Fnew, the distance D between the power equipment is obtained, and the propagation range of the fault is calculated based on the obtained fault propagation state S of the power equipment, and the influence range R of the fault propagation is obtained;

[0077] S5, according to the analysis of the obtained fault propagation state S and the fault propagation influence range R, the power equipment state Z that needs to be adjusted is obtained, and the trigger mechanism of the power supply scheduling strategy that is adaptively matched with the power equipment state Z is adjusted.

[0078] In this embodiment, by forming the fault prediction feature vector Ffail, the accuracy and sensitivity of fault prediction are improved. Then, based on the space-time feature vector Fnew and the fault prediction feature vector Ffail, the historical fault data and the network connection relationship of the power equipment are combined to construct the fault propagation matrix M, and the fault propagation state S of the power equipment is calculated, so that the fault interaction and propagation trend between the devices are comprehensively understood. Through the comprehensive analysis of the distance D between the power equipment and the fault propagation state S, the propagation range R of the fault is calculated, the range of the devices that may be affected by the fault is determined, and further data support is provided for adjusting the operation state of the power equipment. Finally, according to the analysis results of the fault propagation state S and the influence range R, the device state Z that needs to be adjusted is determined, and through the trigger mechanism of the power supply scheduling strategy that is adaptively matched, the intelligence and accuracy of the power equipment operation and maintenance management are significantly improved, overcoming the limitations of traditional methods that cannot comprehensively consider the correlation and propagation influence between devices, so as to better cope with the complex fault propagation problem of modern power grid.

[0079] Embodiment 2

[0080] This embodiment is an explanation and description in embodiment 1, please refer to Figure 1 and Figure 3 , specifically: S1 includes S11 and S12;

[0081] S11, through the sensors and monitoring systems of the devices, the real-time running state data and space-time information of the devices are collected in real time, the real-time running state data includes the load L, power P, temperature W and vibration V data of the power equipment, and the space-time information includes the position coordinates (x, y) of the power equipment;

[0082] S12, the real-time running state data is preprocessed, the preprocessing includes missing data filling and standardization processing, the standard load CL, standard power CP, standard temperature CW and standard vibration CV after preprocessing are obtained, and the space-time information is integrated to obtain the space-time feature vector Fnew.

[0083] S2 includes S21 and S22;

[0084] S21, feature extraction is performed on the space-time feature vector Fnew, a feature vector associated with the occurrence of the fault is obtained, including a load and fault correlation coefficient RLF, a temperature and fault correlation coefficient RWF, a vibration and fault correlation coefficient RVF, and a power and fault correlation coefficient RPF;

[0085] S22, the load and fault correlation coefficient RLF, the temperature and fault correlation coefficient RWF, the vibration and fault correlation coefficient RVF, and the power and fault correlation coefficient RPF are recombined with the position coordinates (x, y) and the time stamp t in the space-time feature vector Fnew, and a fault prediction feature vector Ffail is obtained.

[0086] The load and fault correlation coefficient RLF, the temperature and fault correlation coefficient RWF, the vibration and fault correlation coefficient RVF, and the power and fault correlation coefficient RPF can understand the correlation degree between the standard load CL, the standard power CP, the standard temperature CW, and the standard vibration CV and the fault mark F, as shown in Table 1;

[0087] Wherein, the correlation degree is as follows:

[0088] When the load and fault correlation coefficient RLF, the temperature and fault correlation coefficient RWF, the vibration and fault correlation coefficient RVF, and the power and fault correlation coefficient RPF are 1, it indicates a positive correlation, indicating that when the standard load CL, the standard power CP, the standard temperature CW, and the standard vibration CV increase, the probability of fault occurrence also increases, and there is a strict linear relationship between the two;

[0089] When the load and fault correlation coefficient RLF, the temperature and fault correlation coefficient RWF, the vibration and fault correlation coefficient RVF, and the power and fault correlation coefficient RPF are 0, it indicates that there is no linear relationship, indicating that when the standard load CL, the standard power CP, the standard temperature CW, and the standard vibration CV change, the probability of fault occurrence also does not change, and the changes of the two are not related;

[0090] When the load and fault correlation coefficient RLF, the temperature and fault correlation coefficient RWF, the vibration and fault correlation coefficient RVF, and the power and fault correlation coefficient RPF are -1, it indicates a negative correlation, indicating that when the standard load CL, the standard power CP, the standard temperature CW, and the standard vibration CV increase, the probability of fault occurrence decreases, and there is a strict negative linear relationship between the two;

[0091] Table 1:

[0092] .

[0093] The load and fault correlation coefficient RLF is obtained by the following calculation formula:

[0094]

[0095] In the formula, CL(p) represents the standard load of the pth data point, F(p) represents the failure flag of the power equipment at the pth data point, μ(F) represents the mean of the failure flag data, reflecting the average probability of failure occurring in the sampling time period, μ(CL) represents the mean of the standard load data, specifically the average of all standard loads in the standard load sequence, n represents the total number of data points, specifically the number of samples participating in the calculation of the power equipment;

[0096] The temperature and failure correlation coefficient RWF is obtained by the following calculation formula:

[0097]

[0098] In the formula, CW(p) represents the standard temperature of the pth data point, and μ(CW) represents the mean of the standard temperature data, specifically the average of all standard loads in the standard temperature sequence;

[0099] The vibration and failure correlation coefficient RVF is obtained by the following calculation formula:

[0100]

[0101] In the formula, CV(p) represents the standard vibration of the pth data point, and μ(CV) represents the mean of the standard vibration data, specifically the average of all standard loads in the standard vibration sequence;

[0102] The power and failure correlation coefficient RPF is obtained by the following calculation formula:

[0103]

[0104] In the formula, CP(p) represents the standard power of the pth data point, and μ(CP) represents the mean of the standard power data, specifically the average of all standard loads in the standard power sequence.

[0105] In this embodiment, by preprocessing real-time data and integrating spatio-temporal information, a spatio-temporal feature vector Fnew is formed to provide comprehensive basic data for subsequent fault prediction. In the feature extraction process, by calculating the load and fault correlation coefficient RLF, the temperature and fault correlation coefficient RWF, the vibration and fault correlation coefficient RVF, and the power and fault correlation coefficient RPF, the linear relationship between each operating state and fault occurrence can be quantified, and the fault occurrence probability can be determined by the fault marker F(p). This process can accurately assess the relevance of different operating state parameters and faults, help to early warn potential fault risks of equipment, and provide accurate basis for subsequent fault propagation prediction. Finally, combined with these correlation coefficients, the fault prediction feature vector Ffail will further promote the intelligent operation and maintenance management of power equipment, realize the accuracy and foresight of fault prediction, avoid the over-reliance on a single indicator and potential prediction blind spots in traditional operation and maintenance, and thus improve the fault prevention capability of power equipment.

[0106] Embodiment 3

[0107] This embodiment is an explanation and description in embodiment 2, please refer to Figure 1 , in particular: S3 includes S31 and S32;

[0108] S31, based on the obtained spatio-temporal feature vector Fnew, combined with the historical fault data stored by the power equipment and the connection relationship between each power equipment;

[0109] Among them, the historical fault data includes fault occurrence time, type and influence range; the connection relationship includes power transmission connection between power equipment, physical connection between power equipment and data exchange connection between power equipment;

[0110] Based on the historical fault data, the connection relationship between the power equipment and the spatio-temporal feature vector Fnew of the power equipment, the influence of different power equipment on other power equipment when a fault occurs is analyzed, including that when one power equipment fails, it causes power failure and further affects the connected other power equipment; the influence obtained based on the analysis establishes a propagation matrix M, each row and each column in the propagation matrix M represents a power equipment, and the element m(i, j) in the propagation matrix M represents the influence degree of the power equipment i on the power equipment j, wherein the propagation matrix M is mainly determined by analyzing the transmission path between the equipment and the mode of historical fault.

[0111] S32, based on the propagation matrix M and the fault prediction feature vector Ffail, the fault propagation state S of each power equipment is analyzed, wherein the fault propagation state S is used to reflect that the fault of each power equipment is not only determined by the fault probability of the power equipment itself, but also related to the fault state of the adjacent equipment of the power equipment and the propagation path between the power equipment;

[0112] The fault propagation state S is obtained by the following calculation formula:

[0113]

[0114] In the formula, S(i, t) represents the fault propagation state of the power equipment i at time t, a(i) represents the weighted coefficient of the power equipment i, which specifically represents the fault sensitivity of the power equipment i, and is usually set according to the importance, fault bearing capacity and the like of the equipment, Ffail(i, t) represents the fault prediction feature vector of the power equipment i at time t, w represents the total number of power equipment, β(i, j) represents the fault influence weight of the power equipment i on the power equipment j, m(i, j) represents the influence degree of the power equipment i on the power equipment j in the propagation matrix M, Ffail(j, t) represents the fault prediction feature vector of the power equipment j at time t, λ(i, j) represents the attenuation factor of the fault propagation, which specifically represents the rate of attenuation of the propagation effect with the space distance and the lapse of time when the fault propagates from the power equipment i to the power equipment j, △t represents the fault propagation time difference, and exp represents the exponential attenuation function.

[0115] In this embodiment, by comprehensively considering the space-time feature vector Fnew of the power equipment, the historical fault data and the connection relationship between the equipment, the fault propagation path and the influence degree between the power equipment can be accurately analyzed, so that more accurate fault propagation prediction can be realized. First, by establishing the propagation matrix M, the influence degree between each power equipment is quantified, and it is further revealed how a device failure affects other power equipment through power transmission, physical connection or data exchange and the like. Each element m(i, j) in the propagation matrix M represents the influence of the power equipment i on the power equipment j, which helps to identify the potential fault chain. On this basis, by calculating the fault propagation state S, it is further revealed that the fault propagation of the power equipment is not only affected by the fault probability itself, but also affected by the association with the adjacent equipment and the propagation path. It can effectively prevent large-scale fault propagation, improve the emergency response capability of the power equipment operation, and especially in the early stage of the fault, the scope of the fault can be accurately predicted, and the stability of the power equipment operation and maintenance can be improved.

[0116] Embodiment 4

[0117] This embodiment is an explanation and description in embodiment 3. Please refer to Figure 1 , in particular: S4 includes S41;

[0118] S41, based on the space-time information in the space-time feature vector Fnew, the distance D between the power equipment is obtained, and the propagation range of the fault is calculated with the obtained fault propagation state S of the power equipment, to obtain the fault propagation influence range R;

[0119] wherein the distance D is obtained by calculating the position coordinates (x, y) in the spatiotemporal information of the spatiotemporal feature vector Fnew;

[0120] The fault propagation influence range R is obtained by the following calculation formula:

[0121]

[0122] wherein R(i) represents the fault propagation influence range of the power equipment i, D(i, j) represents the distance between the power equipment i and the power equipment j, Dmax represents the upper limit of the influence distance of the power equipment fault propagation, and is specifically used for normalizing the distance D(i, j) between the power equipment i and the power equipment j, for simulating the distance attenuation effect, that is, the farther the distance between the power equipments, the smaller the influence of the fault propagation, and the rate of the influence reduction is calculated by an exponential attenuation function.

[0123] S5 comprises S51;

[0124] S51, according to the obtained fault propagation state S and the fault propagation influence range R, analyzes to obtain the power equipment state Z that needs to be adjusted, and controls the trigger mechanism of the power supply scheduling strategy that is adaptively matched to the power equipment state Z;

[0125] The power equipment state Z is obtained by the following analysis method:

[0126]

[0127] wherein Z(i, t) represents the power equipment state of the power equipment i at time t, S(i, t) represents the fault propagation state of the power equipment i at time t, R(i, t) represents the fault propagation influence range of the power equipment i at time t, Sthe represents a preset fault propagation state trigger threshold, Rthe represents a preset fault propagation influence range trigger threshold, and Hthe represents a preset power equipment health index threshold;

[0128] When the power equipment state Z(i, t) of the power equipment i at time t is 1, it indicates that the power equipment i needs to be adjusted, the matching power supply scheduling strategy of the power equipment i is triggered, and the related inspection and maintenance personnel are prompted that the power equipment i needs to be maintained, a maintenance task is generated and sent to the to-be-processed task list of the related inspection and maintenance personnel for processing;

[0129] When the power equipment state Z(i, t) of the power equipment i at time t is 0, it indicates that the power equipment i does not need to be adjusted;

[0130] The matching power supply scheduling strategy is used to detect the number of power equipment needing adjustment, and when the total number of power equipment needing adjustment reaches a preset distributed fault threshold, fault separation of the faulty equipment is prompted.

[0131] In this embodiment, the accurate calculation of the fault propagation influence range R is realized by combining the space-time feature vector Fnew of the power equipment and the fault propagation state S, and the distance D between the power equipment. By normalizing the distance between the equipment and applying an exponential decay function, the spatial decay effect of fault propagation can be effectively simulated, ensuring the accurate definition of the fault propagation influence range. Subsequently, based on the fault propagation state S and the influence range R, the power equipment state Z needing adjustment can be intelligently analyzed, and the corresponding power equipment scheduling strategy is triggered. This scheduling mechanism can curb the further spread of faults by adjusting the equipment state in the early stage of fault propagation. When the power equipment state Z is 1, timely adjustment instructions are issued, and maintenance tasks are automatically generated, improving the response speed and work efficiency of power equipment operation and maintenance. Through this method, not only the maintenance scheduling of power equipment can be optimized, but also the spread of faults can be effectively reduced and the overall reliability and recovery ability of the power system can be improved through accurate power equipment state monitoring at critical moments.

[0132] Embodiment 5

[0133] A power equipment operation and maintenance monitoring system based on data analysis, please refer to Figure 2 , specifically: including power equipment data acquisition module, fault prediction correlation module, power equipment fault propagation module, propagation influence range module and power equipment operation and maintenance decision module;

[0134] The power equipment data acquisition module collects real-time running state data of the equipment through sensors and equipment monitoring systems, and collects space-time information of the equipment, and then pre-processes the real-time running state data and the space-time information to form a space-time feature vector Fnew;

[0135] The fault prediction correlation module extracts features from the space-time feature vector Fnew to obtain feature vectors associated with fault occurrence, and forms a fault prediction feature vector Ffail;

[0136] The power equipment fault propagation module obtains the space-time feature vector Fnew and the fault prediction feature vector Ffail, and combines the historical fault data and the network connection relationship of the power equipment stored by the power equipment to establish a propagation matrix M between the power equipment, and obtains the fault propagation state S of the power equipment;

[0137] The propagation influence range module obtains the distance D between the power equipment based on the space-time information in the space-time feature vector Fnew, and calculates the propagation range of the fault together with the obtained fault propagation state S of the power equipment, to obtain the fault propagation influence range R;

[0138] The power equipment operation and maintenance decision module analyzes the obtained fault propagation state S and fault propagation influence range R, obtains the power equipment state Z that needs to be adjusted, and regulates the trigger mechanism of the power supply scheduling strategy that is adaptively matched with the power equipment state Z.

[0139] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and modifications can be made to these embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for monitoring power equipment operation and maintenance based on data analysis, characterized in that: The following steps are involved: S1. Collect the real-time operating status data of the equipment through sensors and equipment monitoring systems, and collect the spatiotemporal information of the equipment at the same time. Then, after preprocessing the real-time operating status data and spatiotemporal information, form the spatiotemporal feature vector Fnew; S1 includes S11 and S12; S11. Using the device's sensors and monitoring system, collect real-time operating status data and spatiotemporal information of the device. The real-time operating status data includes load L, power P, temperature W, and vibration V data of the power device. The spatiotemporal information includes the location coordinates (x, y) of the power device. S12. Preprocess the real-time operating status data, including missing data filling and standardization, to obtain the preprocessed standard load CL, standard power CP, standard temperature CW, and standard vibration CV, and integrate them with the spatiotemporal information to obtain the spatiotemporal feature vector Fnew; S2. Extract the spatiotemporal feature vector Fnew to obtain the feature vector associated with the fault occurrence and form the fault prediction feature vector Ffail; S2 includes S21 and S22; S21. Extract features from the spatiotemporal feature vector Fnew to obtain feature vectors associated with the occurrence of the fault, including the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF, and the power-fault correlation coefficient RPF. S22, obtain a fault prediction feature vector Ffail by recombining the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF, and the power-fault correlation coefficient RPF with the position coordinates (x, y) and the timestamp t in the spatiotemporal feature vector Fnew; S3. Based on the acquired spatiotemporal feature vector Fnew and the fault prediction feature vector Ffail, and in combination with the historical fault data stored in the power equipment and the network connection relationship, a propagation matrix M between the power equipment is established to obtain the fault propagation state S of the power equipment; S4. Based on the spatiotemporal information in the spatiotemporal feature vector Fnew, the distance D between the power devices is obtained, and the fault propagation range is calculated based on the obtained fault propagation state S of the power devices to obtain the fault propagation impact range R; S5. Analyze the acquired fault propagation state S and fault propagation impact range R to acquire the power equipment state Z that needs to be adjusted, and regulate the trigger mechanism of the power supply scheduling strategy to adaptively match the power equipment state Z.

2. A method for monitoring power equipment operation and maintenance based on data analysis according to claim 1, characterized in that: The correlation coefficients between load and fault RLF, temperature and fault RWF, vibration and fault RVF and power and fault RPF can be used to understand the correlation between standard load CL, standard power CP, standard temperature CW and standard vibration CV and fault mark F. The degree of correlation is as follows: When the load-fault correlation coefficient RLF, temperature-fault correlation coefficient RWF, vibration-fault correlation coefficient RVF, and power-fault correlation coefficient RPF = 1, it indicates a positive correlation, which means that when the standard load CL, standard power CP, standard temperature CW, and standard vibration CV increase, the probability of fault occurrence also increases, and the two have a strict linear relationship; When the load-fault correlation coefficient RLF, temperature-fault correlation coefficient RWF, vibration-fault correlation coefficient RVF, and power-fault correlation coefficient RPF = 0, it means there is no linear relationship, which means that when the standard load CL, standard power CP, standard temperature CW, and standard vibration CV change, the probability of fault occurrence will not change, and the changes of the two are unrelated; When the load-fault correlation coefficient RLF, the temperature-fault correlation coefficient RWF, the vibration-fault correlation coefficient RVF, and the power-fault correlation coefficient RPF = -1, it indicates a negative correlation, which means that when the standard load CL, standard power CP, standard temperature CW, and standard vibration CV increase, the probability of a fault occurring decreases, and the two have a strict negative linear relationship.

3. A method for monitoring power equipment operation and maintenance based on data analysis according to claim 2, characterized in that: The load-fault correlation coefficient RLF is obtained by the following calculation formula: Where CL(p) represents the standard load at the p-th data point, F(p) represents the fault mark of the power equipment at the p-th data point, μ(F) represents the mean of the fault mark data, which reflects the average probability of a fault occurring during the sampling period, μ(CL) represents the mean of the standard load data, specifically the average value of all standard loads in the standard load sequence, and n represents the total number of data points, specifically the number of samples of the power equipment involved in the calculation. The temperature-fault correlation coefficient RWF is obtained by the following calculation formula: Where CW(p) represents the standard temperature of the p-th data point, μ(CW) represents the mean of the standard temperature data, specifically the average value of all standard temperature data in the standard temperature sequence; The vibration and fault correlation coefficient RVF is obtained by the following calculation formula: Where CV(p) represents the standard vibration of the p-th data point, μ(CV) represents the mean of the standard vibration data, specifically the average value of all standard vibration data in the standard vibration sequence; The power-fault correlation coefficient RPF is obtained by the following calculation formula: Where CP(p) represents the standard power of the pth data point, and μ(CP) represents the mean of the standard power data, specifically the average value of all standard power data in the standard power sequence.

4. A method for monitoring power equipment operation and maintenance based on data analysis according to claim 3, characterized in that: S3 includes S31 and S32; S31, based on the acquired spatiotemporal feature vector Fnew, combined with the historical fault data stored in the power equipment and the connection relationship between each power equipment; Among them, historical fault data includes the time, type and impact range of the fault; connection relationships include power transmission connections between power equipment, physical connections between power equipment and data exchange connections between power equipment; Based on historical fault data, the connection relationship between power equipment and the spatiotemporal characteristic vector Fnew of power equipment, the impact of different power equipment on other power equipment when a fault occurs is analyzed, including the power outage caused by the failure of one power equipment, which in turn affects other connected power equipment; based on the impact obtained from the analysis, a propagation matrix M is established, where each row and each column of the propagation matrix M represents a power equipment, and the element m(i, j) in the propagation matrix M represents the degree of influence of power equipment i on power equipment j.

5. A method for monitoring power equipment operation and maintenance based on data analysis according to claim 4, characterized in that: S32. Analyze the fault propagation state S of each power device based on the propagation matrix M and the fault prediction eigenvector Ffail. The fault propagation state S reflects that the fault of each power device is not only determined by the fault probability of the power device itself, but also by the fault states of neighboring devices and the propagation paths between the power devices. The fault propagation state S is obtained by the following calculation formula: Where S(i, t) represents the fault propagation state of power device i at time t, α(i) represents the weighting coefficient of power device i, specifically the fault sensitivity of power device i, Ffail(i, t) represents the fault prediction feature vector of power device i at time t, w represents the total number of power devices, β(i, j) represents the fault impact weight of power device i on power device j, m(i, j) represents the degree of influence of power device i on power device j in the propagation matrix M, Ffail(j, t) represents the fault prediction feature vector of power device j at time t, λ(i, j) represents the attenuation factor of fault propagation, specifically the rate at which the propagation effect decays with spatial distance and time when the fault propagates from power device i to power device j, △t represents the fault propagation time difference, and exp represents the exponential decay function.

6. A method for monitoring power equipment operation and maintenance based on data analysis according to claim 5, characterized in that: S4 includes S41; S41. Based on the spatiotemporal information in the spatiotemporal feature vector Fnew, the distance D between the power devices is obtained, and the fault propagation range is calculated using the obtained fault propagation state S of the power devices to obtain the fault propagation impact range R. The distance D is obtained by calculating the position coordinates (x, y) in the spatiotemporal information of the spatiotemporal feature vector Fnew; The fault propagation impact range R is obtained using the following calculation formula: Where R(i) represents the fault propagation impact range of power equipment i, D(i, j) represents the distance between power equipment i and power equipment j, and Dmax represents the upper limit of the power equipment fault propagation impact distance, which is specifically used to normalize the distance D(i, j) between power equipment i and power equipment j. Used to simulate distance decay effects.

7. A method for monitoring power equipment operation and maintenance based on data analysis according to claim 6, characterized in that: S5 includes S51; S51. Analyze the acquired fault propagation state S and fault propagation impact range R to acquire the power equipment state Z that needs to be adjusted, and regulate the trigger mechanism of the power supply scheduling strategy to adaptively match the power equipment state Z; The power equipment status Z is obtained through the following analysis method: Where Z(i, t) represents the power device state of power device i at time t, S(i, t) represents the fault propagation state of power device i at time t, R(i, t) represents the fault propagation impact range of power device i at time t, Sthe represents the preset fault propagation state trigger threshold, and Rthe represents the preset fault propagation impact range trigger threshold; When the power equipment state Z(i, t) of power equipment i at time t is 1, it indicates that power equipment i needs to be adjusted, triggering the matching power supply scheduling strategy of power equipment i. At the same time, the relevant inspection and maintenance personnel are notified that power equipment i needs maintenance, and a maintenance task is generated and sent to the pending task list of the relevant inspection and maintenance personnel for processing; When the power device state Z(i, t) of the power device i at time t = 0, it means that the power device i does not need to be adjusted; The matching power supply scheduling strategy is used to detect the number of power equipment that needs to be adjusted. When the total number of power equipment that needs to be adjusted reaches a preset distributed fault threshold, a prompt is given to perform fault isolation on the faulty equipment.

8. A power equipment operation and maintenance monitoring system based on data analysis, applied to a power equipment operation and maintenance monitoring method based on data analysis according to any one of claims 1 to 7, characterized in that: It includes power equipment data acquisition module, fault prediction association module, power equipment fault propagation module, propagation impact range module and power equipment operation and maintenance decision module; The power equipment data acquisition module collects the real-time operating status data of the equipment through sensors and equipment monitoring systems, and also collects the spatiotemporal information of the equipment. After preprocessing the real-time operating status data and spatiotemporal information, it forms a spatiotemporal feature vector Fnew. The fault prediction association module extracts features from the spatiotemporal feature vector Fnew, obtains feature vectors associated with the occurrence of faults, and forms the fault prediction feature vector Ffail; The power equipment fault propagation module establishes the propagation matrix M between power equipment based on the acquired spatiotemporal feature vector Fnew and the fault prediction feature vector Ffail, combined with the historical fault data stored in the power equipment and the network connection relationship, and obtains the fault propagation status S of the power equipment; The propagation impact range module obtains the distance D between the power equipment based on the spatiotemporal information in the spatiotemporal feature vector Fnew, and calculates the fault propagation range with the acquired fault propagation state S of the power equipment to obtain the fault propagation impact range R; The power equipment operation and maintenance decision module analyzes the acquired fault propagation state S and fault propagation impact range R, obtains the power equipment state Z that needs to be adjusted, and regulates the trigger mechanism of the power supply scheduling strategy to adaptively match the power equipment state Z.

Images