Power grid operation and maintenance management system and method based on intelligent fusion gateway

Abstract

The invention relates to a power grid operation and maintenance management system and method based on an intelligent fusion gateway. The method comprises the following steps: monitoring and collecting equipment operation state data in real time through an intelligent fusion gateway, including equipment current, equipment voltage and equipment temperature, and transmitting the data to a power grid operation and maintenance management server through the intelligent fusion gateway; and performing time sequence analysis on the operation state data of the equipment by using a data processing and analysis algorithm based on artificial intelligence and deep learning in the power grid operation and maintenance management server, and further performing correlation feature extraction and difference calculation based on heat effect-heat characterization, thereby detecting the working state of the power grid equipment. Therefore, whether the working state of the power grid equipment is abnormal or not can be judged based on depiction and comparative analysis of the thermal effect and the thermal representation of the power grid equipment, so that the fault of the power grid equipment can be timely and effectively detected and responded, and more intelligent power grid operation and maintenance management is realized.

Description

Technical Field

[0001] The present application relates to the technical field of power grid operation and maintenance management, and in particular, to a power grid operation and maintenance management system and method based on an intelligent fusion gateway. Background Art

[0002] As electricity demand continues to grow, the safe and stable operation of the power grid has become increasingly important. Traditional power grid operation and maintenance management methods mainly rely on manual inspections and regular maintenance, which has many problems such as slow response, untimely fault handling, and high maintenance costs. In addition, the limitations of manual inspections make it difficult to fully monitor the real-time status of equipment, resulting in potential faults not being discovered in time, thus affecting the reliability and safety of the power grid.

[0003] Therefore, an optimized power grid operation and maintenance management system is desired. Summary of the invention

[0004] This summary is provided to introduce concepts in a brief form that will be described in detail in the detailed description below. This summary is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0005] In a first aspect, the present application provides a power grid operation and maintenance management method based on an intelligent fusion gateway, the method comprising:

[0006] A time queue for collecting device operation status data through an intelligent fusion gateway, wherein the device operation status includes device current, device voltage and device temperature;

[0007] Transmitting the time queue of the equipment operation status data to the power grid operation and maintenance management server through the intelligent fusion gateway;

[0008] On the power grid operation and maintenance management server, time series encoding is performed on the time series of the equipment operation status data to obtain a time series of equipment current local time series implicit correlation feature vectors, a time series of equipment current local time series implicit correlation feature vectors, and a time series of equipment temperature local time series implicit correlation feature vectors;

[0009] Input the time queue of the local timing implicitly associated characteristic vector of the device current and the time queue of the local timing implicitly associated characteristic vector of the device current into the node characteristic timing propagation network based on the node energy decay mechanism respectively to obtain the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector;

[0010] Inputting the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector into a device thermal effect encoder to obtain a device thermal effect timing encoding vector;

[0011] Inputting the time queue of the local temporal implicit correlation feature vector of the device temperature into a feature aggregation network based on local significant gating of feature energy to obtain a temporal encoding vector of the thermal representation of the device temperature;

[0012] The positional difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector is calculated to obtain thermal effect-thermal characterization timing difference feature information, and whether there is an abnormality in the working state of the power grid device is determined based on the thermal effect-thermal characterization timing difference feature information.

[0013] Optionally, in the power grid operation and maintenance management server, the time queue of the equipment operation status data is time-series encoded to obtain a time queue of local time series implicitly associated feature vectors of equipment current, a time queue of local time series implicitly associated feature vectors of equipment current, and a time queue of local time series implicitly associated feature vectors of equipment temperature, including: in the power grid operation and maintenance management server, the time queue of the equipment operation status data is data preprocessed according to the parameter sample dimension to obtain a time queue of equipment current, a time queue of equipment voltage, and a time queue of equipment temperature; the time queue of the equipment current, the time queue of the equipment voltage, and the time queue of the equipment temperature are respectively input into a sequence encoder based on a 1D-CNN model to obtain a time queue of local time series implicitly associated feature vectors of the equipment current, a time queue of local time series implicitly associated feature vectors of the equipment current, and a time queue of local time series implicitly associated feature vectors of the equipment temperature.

[0014] Optionally, the time queue of the local timing implicitly associated feature vector of the device current and the time queue of the local timing implicitly associated feature vector of the device current are respectively input into the node feature time series propagation network based on the node energy decay mechanism to obtain the device current time series propagation aggregate representation vector and the device voltage time series propagation aggregate representation vector, including: based on the mean and standard deviation of each local timing implicitly associated feature vector of the device current in the time queue of the local timing implicitly associated feature vector of the device current, calculating the energy significant descriptor of each local timing implicitly associated feature vector of the device current to obtain a sequence of local timing energy significant descriptors of the device current; extracting the timestamps of each local timing implicitly associated feature vector of the device current in the time queue of the local timing implicitly associated feature vector of the device current to obtain a sequence of device current timestamps; using the local timing implicitly associated feature vector of the device current corresponding to the current time point in the time queue of the local timing implicitly associated feature vector of the device current as the current local timing implicitly associated feature vector of the device current and using the local timing implicitly associated feature vectors of the device current corresponding to other time points as the historical local timing implicitly associated feature vector of the device current. The method comprises the following steps: calculating the time series implicit association feature vector to obtain the time queue of the current device current local time series implicit association feature vector and the historical device current local time series implicit association feature vector; calculating the energy time decay factor of each historical device current local time series implicit association feature vector in the time queue of the historical device current local time series implicit association feature vector relative to the current device current local time series implicit association feature vector to obtain the sequence of device current local time series energy time decay factors; using the sequence of the device current local time series energy significant descriptors as positive adjustment factors and the sequence of the device current local time series energy time decay factors as negative adjustment factors, performing time series propagation aggregation on the time queue of the historical device current local time series implicit association feature vector to obtain the device current local time series historical node propagation aggregation representation feature vector; and calculating the position-weighted sum of the device current local time series historical node propagation aggregation representation feature vector and the current device current local time series implicit association feature vector based on the energy significant descriptors corresponding to the current device current local time series implicit association feature vector to obtain the device current time series propagation aggregation representation vector.

[0015] Optionally, based on the mean and standard deviation of each device current local time series implicitly associated feature vector in the time queue of the device current local time series implicitly associated feature vector, the energy significant descriptors of each device current local time series implicitly associated feature vector are calculated to obtain a sequence of device current local time series energy significant descriptors, including: calculating the mean and standard deviation of each device current local time series implicitly associated feature vector in the time queue of the device current local time series implicitly associated feature vector to obtain a sequence of device current local means and a sequence of device current local standard deviations; calculating the standard deviation of each device current local time series implicitly associated feature vector in the time queue of the device current local time series implicitly associated feature vector to obtain a sequence of device current local standard deviations; and adding each corresponding group in the time queue of the device current local time series implicitly associated feature vector and the sequence of the device current local mean. After the implicitly associated characteristic vector of the local timing of the device current and the local mean of the device current are differentiated by position, each position characteristic value in the sequence of the obtained differential characteristic vectors is modulated to the fourth power to obtain a sequence of the local timing modulation characteristic vectors of the device current; the expected value of each local timing modulation characteristic vector of the device current in the sequence of the local timing modulation characteristic vectors of the device current is calculated to obtain a sequence of the local timing positive expected factors of the device current; the fourth power modulation value of each local standard deviation of the device current in the sequence of the local standard deviation of the device current is calculated to obtain a sequence of the local timing inverse expected factors of the device current; each group of corresponding local timing positive expected factors of the device current and local timing inverse expected factors of the device current in the sequence of the local timing positive expected factors of the device current and the sequence of the local timing inverse expected factors of the device current are divided to obtain a sequence of the local timing energy significant descriptors of the device current.

[0016] Optionally, the energy time decay factors of each historical device current local time series implicitly associated characteristic vector in the time queue of the historical device current local time series implicitly associated characteristic vector are calculated relative to the current device current local time series implicitly associated characteristic vector to obtain a sequence of device current local time series energy time decay factors, including: respectively calculating the device current timestamp corresponding to the current device current local time series implicitly associated characteristic vector and the device current timestamp corresponding to each historical device current local time series implicitly associated characteristic vector, subtracting them from each other and rounding them down to obtain a sequence of time span values; calculating the squares of each time span value in the sequence of time span values, dividing the obtained sequence of span square modulation values ​​by the time attenuation inverse scaling parameter by position and multiplying them by the attenuation rate positive scaling parameter by position to obtain a sequence of time series span energy decay coefficients; using each time series span energy decay coefficient in the sequence of time series span energy decay coefficients as an exponential power, calculating a natural exponential function value with the natural constant e as the base to obtain a sequence of device current local time series energy time decay factors.

[0017] Optionally, using the sequence of the device current local timing energy significant descriptors as positive adjustment factors and the sequence of the device current local timing energy time decay factors as negative adjustment factors, the time queue of the historical device current local timing implicitly associated feature vectors is subjected to timing propagation aggregation to obtain the device current local timing history node propagation aggregation representation feature vector, including: calculating the positional division of the sequence of the device current local timing energy significant descriptors and the sequence of the device current local timing energy time decay factors, using the obtained device current local timing energy weight as a weighting coefficient, and calculating the positional weighted sum of the time queue of the historical device current local timing implicitly associated feature vectors to obtain the device current local timing history node propagation aggregation representation feature vector.

[0018] Optionally, the device current timing propagation aggregate representation vector and the device voltage timing propagation aggregate representation vector are input into a device thermal effect encoder to obtain a device thermal effect timing encoding vector, including: multiplying the device current timing propagation aggregate representation vector and the device voltage timing propagation aggregate representation vector by position points to obtain the device thermal effect timing encoding vector.

[0019] Optionally, the time queue of the local time series implicitly associated feature vectors of the device temperature is input into a feature aggregation network based on feature energy local significance gating to obtain a device temperature thermal representation time series encoding vector, including: based on the maximum value, minimum value, mean value and variance of each device temperature local time series implicitly associated feature vector in the time queue of the local time series implicitly associated feature vectors of the device temperature, determining the characteristic energy level coefficients of each device temperature local time series implicitly associated feature vector to obtain a sequence of device temperature local time series characteristic energy level coefficients; determining the scale of the local neighborhood of the local time series of the device temperature, and taking the scale of the local neighborhood of the local time series of the device temperature as The mean calculation range is to calculate the local neighborhood mean of each of the local timing characteristic energy level coefficients of the device temperature respectively to obtain a sequence of device temperature local timing characteristic energy level significance descriptors; the sequence of device temperature local timing characteristic energy level significance descriptors is input into a mask module based on a gating function to obtain a sequence of mask-gated probabilistic device temperature local timing characteristic energy level significance descriptors; the sequence of mask-gated probabilistic device temperature local timing characteristic energy level significance descriptors is used as a sequence of weights, and the position-weighted sum of the time queue of the device temperature local timing implicitly associated feature vector is calculated to obtain the temperature thermal characterization timing encoding vector.

[0020] Optionally, the positional difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector is calculated to obtain thermal effect-thermal characterization timing difference feature information, and whether the working state of the power grid equipment is abnormal is determined based on the thermal effect-thermal characterization timing difference feature information, including: calculating the positional difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector to obtain a thermal effect-thermal characterization timing difference representation vector as the thermal effect-thermal characterization timing difference feature information; inputting the thermal effect-thermal characterization timing difference representation vector into a classifier-based power grid equipment state detection module to obtain a detection result, and the detection result is used to indicate whether the working state of the power grid equipment is abnormal.

[0021] In a second aspect, the present application provides a power grid operation and maintenance management system based on an intelligent fusion gateway, the system comprising:

[0022] The device operation status data collection module is used to collect the time queue of the device operation status data through the intelligent fusion gateway, wherein the device operation status includes device current, device voltage and device temperature;

[0023] A data transmission module, used for transmitting the time queue of the equipment operation status data to the power grid operation and maintenance management server through the intelligent fusion gateway;

[0024] A timing encoding module is used to perform timing encoding on the time queue of the equipment operation status data in the power grid operation and maintenance management server to obtain a time queue of equipment current local timing implicit correlation feature vectors, a time queue of equipment current local timing implicit correlation feature vectors, and a time queue of equipment temperature local timing implicit correlation feature vectors;

[0025] A node characteristic timing propagation network module is used to input the time queue of the local timing implicitly associated characteristic vector of the device current and the time queue of the local timing implicitly associated characteristic vector of the device current into the node characteristic timing propagation network based on the node energy decay mechanism to obtain the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector;

[0026] A device thermal effect encoding module, used for inputting the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector into a device thermal effect encoder to obtain a device thermal effect timing encoding vector;

[0027] A feature aggregation network module is used to input the time queue of the local temporal implicit correlation feature vector of the device temperature into a feature aggregation network based on local significant gating of feature energy to obtain a temporal encoding vector of thermal representation of the device temperature;

[0028] The working state determination module of the power grid equipment is used to calculate the position difference between the equipment temperature thermal characterization timing coding vector and the equipment thermal effect timing coding vector to obtain thermal effect-thermal characterization timing difference feature information, and determine whether the working state of the power grid equipment is abnormal based on the thermal effect-thermal characterization timing difference feature information.

[0029] By adopting the above technical solution, the intelligent fusion gateway is used to monitor and collect the equipment operation status data in real time, including equipment current, equipment voltage and equipment temperature, and transmit these data to the power grid operation and maintenance management server through the intelligent fusion gateway, so as to use the data processing and analysis algorithm based on artificial intelligence and deep learning in the power grid operation and maintenance management server to perform time series analysis on the equipment operation status data, and further perform correlation feature extraction and difference calculation based on thermal effect-thermal characterization, so as to detect the working status of the power grid equipment. In this way, it is possible to judge whether there is an abnormality in the working status of the power grid equipment based on the characterization and comparative analysis of the thermal effect and thermal characterization of the power grid equipment, so as to detect and respond to power grid equipment failures in a timely and effective manner, and realize more intelligent power grid operation and maintenance management.

[0030] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale. In the drawings:

[0032] Figure 1 The present invention is a flowchart of a power grid operation and maintenance management method based on an intelligent fusion gateway according to an exemplary embodiment.

[0033] Figure 2 It is a block diagram of a power grid operation and maintenance management system based on an intelligent fusion gateway according to an exemplary embodiment.

[0034] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment.

[0035] Figure 4 It is an application scenario diagram of a power grid operation and maintenance management method based on an intelligent fusion gateway according to an exemplary embodiment. DETAILED DESCRIPTION

[0036] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments described herein. Instead, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0037] It should be understood that the various steps described in the method implementation of the present application can be performed in different orders and / or performed in parallel. In addition, the method implementation may include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0038] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0039] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0040] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0041] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0042] The specific implementation of the present application is described in detail below with reference to the accompanying drawings.

[0043] Figure 1 is a flow chart of a power grid operation and maintenance management method based on an intelligent fusion gateway according to an exemplary embodiment. Figure 1 As shown, the method includes:

[0044] Step S101, collecting a time queue of device operation status data through an intelligent fusion gateway, wherein the device operation status includes device current, device voltage and device temperature;

[0045] Step S102: transmitting the time queue of the equipment operation status data to the power grid operation and maintenance management server through the intelligent fusion gateway;

[0046] Step S103: On the power grid operation and maintenance management server, time series encoding is performed on the time series of the equipment operation status data to obtain a time series of equipment current local time series implicit correlation feature vectors, a time series of equipment current local time series implicit correlation feature vectors, and a time series of equipment temperature local time series implicit correlation feature vectors;

[0047] Step S104, respectively inputting the time queue of the local timing implicitly associated characteristic vector of the device current and the time queue of the local timing implicitly associated characteristic vector of the device current into the node characteristic timing propagation network based on the node energy decay mechanism to obtain the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector;

[0048] Step S105, inputting the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector into a device thermal effect encoder to obtain a device thermal effect timing encoding vector;

[0049] Step S106, inputting the time queue of the local time series implicitly associated feature vector of the device temperature into a feature aggregation network based on feature energy local significance gating to obtain a device temperature thermal representation time series encoding vector;

[0050] Step S107, calculate the position difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector to obtain thermal effect-thermal characterization timing difference feature information, and determine whether there is an abnormality in the working state of the power grid equipment based on the thermal effect-thermal characterization timing difference feature information.

[0051] As an important bridge connecting various sensors with cloud or local processing systems, the intelligent fusion gateway has efficient data collection and transmission capabilities, which can ensure the accuracy and real-time nature of the data. The intelligent fusion gateway can collect the operating data of the equipment (such as voltage, current, temperature, etc.) in real time, and send this data to the power grid operation and maintenance management server for processing through an efficient data transmission mechanism, so as to detect the working status of the power grid equipment in a timely and effective manner. In this way, it not only improves the efficiency of data collection on the operating status of the equipment, but also lays the foundation for subsequent data analysis and power grid equipment fault detection.

[0052] Based on this, in the technical solution of the present application, a power grid operation and maintenance management system based on an intelligent fusion gateway is proposed, which can monitor and collect equipment operation status data in real time through the intelligent fusion gateway, including equipment current, equipment voltage and equipment temperature, and transmit these data to the power grid operation and maintenance management server through the intelligent fusion gateway, so as to use the data processing and analysis algorithm based on artificial intelligence and deep learning in the power grid operation and maintenance management server to perform time series analysis on the equipment operation status data, and further perform correlation feature extraction and difference calculation based on thermal effect-thermal characterization, so as to detect the working status of the power grid equipment. In this way, it is possible to judge whether there is an abnormality in the working status of the power grid equipment based on the characterization and comparative analysis of the thermal effect and thermal characterization of the power grid equipment, so as to detect and respond to power grid equipment failures in a timely and effective manner, and realize more intelligent power grid operation and maintenance management.

[0053] Specifically, in the technical solution of the present application, first, a time queue of equipment operation status data is collected through an intelligent fusion gateway, wherein the equipment operation status includes equipment current, equipment voltage and equipment temperature, and the time queue of the equipment operation status data is transmitted to a power grid operation and maintenance management server through the intelligent fusion gateway.

[0054] In one embodiment of the present application, in the power grid operation and maintenance management server, the time queue of the equipment operation status data is time-series encoded to obtain a time queue of local time series implicitly associated feature vectors of equipment current, a time queue of local time series implicitly associated feature vectors of equipment current, and a time queue of local time series implicitly associated feature vectors of equipment temperature, including: in the power grid operation and maintenance management server, the time queue of the equipment operation status data is data preprocessed according to the parameter sample dimension to obtain a time queue of equipment current, a time queue of equipment voltage, and a time queue of equipment temperature; the time queue of the equipment current, the time queue of the equipment voltage, and the time queue of the equipment temperature are respectively input into a sequence encoder based on a 1D-CNN model to obtain a time queue of local time series implicitly associated feature vectors of the equipment current, a time queue of local time series implicitly associated feature vectors of the equipment current, and a time queue of local time series implicitly associated feature vectors of the equipment temperature.

[0055] In the power grid operation and maintenance management server, the time queue of the equipment operation status data is processed and analyzed to detect the working status of the power grid equipment. Specifically, first, the time queue of the equipment operation status data is preprocessed according to the parameter sample dimension to obtain the time queue of the equipment current, the time queue of the equipment voltage and the time queue of the equipment temperature. The preprocessing method can separate the equipment operation status data into different equipment operation status parameter (current, voltage, temperature) samples, and perform time sequence regularization on different equipment operation status parameter samples to obtain the time queue of the equipment current, the time queue of the equipment voltage and the time queue of the equipment temperature. In this way, the data structure of different types of equipment operation status can be made clearer, which is convenient for subsequent analysis and processing. Specifically, the time series of each state parameter can be processed independently, so as to more effectively extract features related to fault detection. For example, the change of current may directly reflect the change of load, while the change of temperature may be related to the heat dissipation condition of the equipment, avoiding the complexity of confusing different types of data.

[0056] Then, the time queue of the device current, the time queue of the device voltage, and the time queue of the device temperature are respectively input into a sequence encoder based on the 1D-CNN model for encoding, so as to respectively extract the local timing implicit correlation feature information of the device current, the device voltage, and the device temperature in the time dimension, thereby obtaining the time queue of the local timing implicit correlation feature vector of the device current, the time queue of the local timing implicit correlation feature vector of the device current, and the time queue of the local timing implicit correlation feature vector of the device temperature.

[0057] In one embodiment of the present application, the time queue of the local timing implicitly associated feature vector of the device current and the time queue of the local timing implicitly associated feature vector of the device current are respectively input into the node feature time series propagation network based on the node energy decay mechanism to obtain the device current time series propagation aggregate representation vector and the device voltage time series propagation aggregate representation vector, including: based on the mean and standard deviation of each device current local timing implicitly associated feature vector in the time queue of the local timing implicitly associated feature vector of the device current, the energy significant descriptor of each device current local timing implicitly associated feature vector is calculated to obtain a sequence of device current local timing implicitly associated feature vectors; the timestamps of each device current local timing implicitly associated feature vector in the time queue of the local timing implicitly associated feature vector of the device current are extracted to obtain a sequence of device current timestamps; the device current local timing implicitly associated feature vector corresponding to the current time point in the time queue of the local timing implicitly associated feature vector of the device current is used as the current device current local timing implicitly associated feature vector and the device current local timing implicitly associated feature vectors corresponding to other time points are used as the historical device current local timing implicitly associated feature vector. The method comprises the following steps: calculating the implicit correlation feature vector of the local time series of current to obtain the time queue of the implicit correlation feature vector of the local time series of current of the current device and the implicit correlation feature vector of the local time series of historical device current; calculating the energy time decay factor of each historical device current local time series implicit correlation feature vector in the time queue of the local time series of historical device current relative to the implicit correlation feature vector of the local time series of current device to obtain the sequence of the energy time decay factor of the local time series of device current; using the sequence of the energy significant descriptors of the local time series of device current as the positive adjustment factor and the sequence of the energy time decay factor of the local time series of device current as the negative adjustment factor, performing time propagation aggregation on the time queue of the local time series of historical device current implicit correlation feature vectors to obtain the device current local time series historical node propagation aggregation representation feature vector; and calculating the position-weighted sum of the device current local time series historical node propagation aggregation representation feature vector and the current device current local time series implicit correlation feature vector based on the energy significant descriptor corresponding to the local time series of current device current to obtain the device current time series propagation aggregation representation vector.

[0058] It should be understood that current and voltage are two key parameters that represent the operating status of power grid equipment. The local time series characteristics of the two in the time dimension have a correlation relationship based on the full time domain, that is, the local time series characteristics of current or voltage in the current local time period will affect the subsequent current and voltage detection and power grid equipment status analysis. Therefore, in order to better capture the time series characteristics of current and voltage data in the full time domain, the local time series characteristics of current and voltage in different time periods are respectively subjected to time domain aggregation analysis, so as to more accurately perform the subsequent power grid equipment detection task, in the technical solution of the present application, the time queue of the local time series implicitly associated feature vector of the device current and the time queue of the local time series implicitly associated feature vector of the device current are further input into the node feature time series propagation network based on the node energy decay mechanism to obtain the device current time series propagation aggregation representation vector and the device voltage time series propagation aggregation representation vector. The node feature time series propagation network based on the node energy decay mechanism can aggregate features through the significance and time series decay characteristics of the local time series feature energy of the device power parameter under the time node to generate a propagation aggregation representation vector. By inputting the local time series implicit feature vectors of the device current and voltage into the node feature time series propagation network based on the node energy decay mechanism, the system can independently learn and identify the importance of the local time series implicit features of each parameter at different time nodes, as well as the impact on the comprehensive representation of information during the information propagation aggregation process. In this way, the information transmission contribution can be adjusted for the time series decay characteristics of each power parameter, so as to better reflect the impact of historical data on the current state, thereby strengthening the features related to the current time point and ensuring that the local time series information of each parameter can be fully utilized, which helps to improve the robustness and accuracy of the model and provide a basis for subsequent power grid equipment working status detection.

[0059] In one embodiment of the present application, based on the mean and standard deviation of each device current local time series implicitly associated feature vector in the time queue of the device current local time series implicitly associated feature vector, the energy significant descriptors of the each device current local time series implicitly associated feature vector are calculated to obtain a sequence of device current local time series energy significant descriptors, including: calculating the mean and standard deviation of each device current local time series implicitly associated feature vector in the time queue of the device current local time series implicitly associated feature vector to obtain a sequence of device current local means and a sequence of device current local standard deviations; calculating the standard deviation of each device current local time series implicitly associated feature vector in the time queue of the device current local time series implicitly associated feature vector to obtain a sequence of device current local standard deviations; and combining each of the time queues of the device current local time series implicitly associated feature vector and the sequence of the device current local mean with the standard deviation of the local time series implicitly associated feature vector. After the corresponding device current local timing implicit correlation feature vectors and device current local mean values ​​are differentiated by position, each position feature value in the obtained sequence of differential feature vectors is modulated to the fourth power to obtain a sequence of device current local timing modulation feature vectors; the expected value of each device current local timing modulation feature vector in the sequence of device current local timing modulation feature vectors is calculated to obtain a sequence of device current local timing positive expected factors; the fourth power modulation value of each device current local standard deviation in the sequence of device current local standard deviations is calculated to obtain a sequence of device current local timing inverse expected factors; the device current local timing positive expected factors and device current local timing inverse expected factors corresponding to each group in the sequence of device current local timing positive expected factors and the sequence of device current local timing inverse expected factors are divided to obtain a sequence of device current local timing energy significant descriptors.

[0060] Furthermore, in one embodiment of the present application, the energy time decay factor of each historical device current local timing implicitly associated characteristic vector in the time queue of the historical device current local timing implicitly associated characteristic vector is calculated relative to the current device current local timing implicitly associated characteristic vector to obtain a sequence of device current local timing implicitly associated characteristic vectors, including: respectively calculating the device current timestamp corresponding to the current device current local timing implicitly associated characteristic vector and the device current timestamp corresponding to each historical device current local timing implicitly associated characteristic vector, subtracting them from each other and rounding them down to obtain a sequence of time span values; after calculating the square of each time span value in the sequence of time span values, dividing the obtained sequence of span square modulation values ​​by the time attenuation inverse scaling parameter by position and multiplying them by the attenuation rate positive scaling parameter by position to obtain a sequence of time span energy decay coefficients; using each time span energy decay coefficient in the sequence of time span energy decay coefficients as an exponential power, calculating a natural exponential function value with the natural constant e as the base to obtain a sequence of device current local timing energy time decay factors.

[0061] Furthermore, in one embodiment of the present application, the sequence of the device current local timing energy significant descriptors is used as a positive adjustment factor and the sequence of the device current local timing energy time decay factors is used as a negative adjustment factor, and the time queue of the historical device current local timing implicitly associated feature vectors is subjected to timing propagation aggregation to obtain the device current local timing history node propagation aggregation representation feature vector, including: calculating the positional division of the sequence of the device current local timing energy significant descriptors and the sequence of the device current local timing energy time decay factors, using the obtained device current local timing energy weight as a weighting coefficient, and calculating the positional weighted sum of the time queue of the historical device current local timing implicitly associated feature vectors to obtain the device current local timing history node propagation aggregation representation feature vector.

[0062] Specifically, the time queue of the implicitly associated characteristic vector of the local timing of the device current is input into the node characteristic timing propagation network based on the node energy decay mechanism for processing using the following node characteristic propagation formula to obtain the device current timing propagation aggregation representation vector;

[0063] Among them, the node feature propagation formula is:

[0064] X={x1,x2,…x k -1,x k}

[0065]

[0066]

[0067]

[0068]

[0069] Where X is the time queue of the implicit correlation feature vector of the local time series of the device current, x k-1 and x k are the (k-1)th and kth device current local time series implicit correlation feature vectors in the time queue of the device current local time series implicit correlation feature vectors, respectively, x i is the i-th device current local time series implicit correlation feature vector in the time queue of the device current local time series implicit correlation feature vector, is the jth position eigenvalue in the implicit correlation eigenvector of the local time series of the i-th device current, L is the length of the implicit correlation eigenvector of the local time series of the i-th device current, μ i is the mean of the implicit correlation eigenvector of the local time series of the current of the i-th device, σ i is the standard deviation of the implicit correlation eigenvector of the local time series of the i-th device current, E(·) represents the expected value of the calculation, is the energy significant descriptor of the implicit correlation eigenvector of the local time series of the i-th device current, exp(·) represents the exponential function value with the natural constant e as the base, γ is the positive scaling parameter controlling the decay rate, M is the inverse scaling parameter controlling the time decay period, t i and t k Represent the timestamps of the implicitly associated feature vectors of the local timing of the current of the i-th and k-th devices, Indicates a round-down operation. is the energy-significant descriptor of the implicit correlation feature vector of the local timing of the kth device current, α and β are trainable weight hyperparameters, and x k+1 A representation vector for the device current timing propagation aggregation.

[0070] Furthermore, considering that current and voltage are two key parameters that affect the thermal effect of the device, there are complex correlation patterns and timing dynamic characteristics between the two. Therefore, in order to comprehensively consider their common influence on the thermal effect of the device and capture more comprehensive device state feature representation information, in the technical solution of the present application, the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector are further input into the device thermal effect encoder to obtain the device thermal effect timing encoding vector. In particular, in a specific example of the present application, the corresponding elements of the two vectors can be effectively combined by the operation of position point multiplication to emphasize the correlation between them. This ensures that the relative importance of current and voltage is fully considered when generating the device thermal effect timing encoding vector. This method can strengthen those features that show significant thermal effects at a specific time point, while weakening irrelevant or redundant information. That is, by performing position point multiplication on their timing aggregation representation vectors, the relationship between the two can be dynamically modeled, reflecting their influence on the device thermal effect at different time points. In this way, subsequent analysis and prediction can be made more accurate, especially when dealing with complex power grid device states.

[0071] In one embodiment of the present application, the device current timing propagation aggregate representation vector and the device voltage timing propagation aggregate representation vector are input into a device thermal effect encoder to obtain a device thermal effect timing encoding vector, including: multiplying the device current timing propagation aggregate representation vector and the device voltage timing propagation aggregate representation vector by position point to obtain the device thermal effect timing encoding vector.

[0072] Next, considering that the change of device temperature is closely related to the operating state of the power grid equipment, it can reflect the change of thermal conditions of the power grid equipment. Moreover, each device temperature local time series implicit correlation feature vector in the time queue of the device temperature local time series implicit correlation feature vector respectively contains the local time series implicit correlation features related to the device temperature in each local time period. There is a hidden relationship of correlation between the temperature time series features in this local time series. In addition, different temperature local time series features have different importance and contribution to the subsequent device temperature comprehensive thermal characterization and power grid equipment working state detection tasks. Therefore, in the technical solution of the present application, the time queue of the device temperature local time series implicit correlation feature vector is further input into the feature aggregation network based on the feature energy local significance gating to obtain the device temperature thermal characterization time series encoding vector. Through the processing of the feature aggregation network based on the feature energy local significance gating, the significant and important parts of the local time series features of each device temperature can be effectively aggregated, and unimportant or redundant information can be filtered out. Specifically, the feature aggregation network based on local significant gating of feature energy can identify which local time series temperature changes have a greater impact on subsequent tasks by quantifying the local energy distribution, so as to focus more on these important features when performing comprehensive thermal characterization of device temperature. This quantization process helps to improve the sensitivity to key data. The feature aggregation method based on local significant gating of feature energy ensures that the generated time series encoding vector only contains feature information that has a practical impact on the characterization of the thermal effect of the device, thereby improving the model's ability to understand the thermal characterization time series of power grid equipment and its ability to judge the subsequent working status.

[0073] In one embodiment of the present application, the time queue of the local timing implicitly associated feature vectors of the device temperature is input into a feature aggregation network based on feature energy local significance gating to obtain a device temperature thermal representation time series encoding vector, including: based on the maximum value, minimum value, mean value and variance of each device temperature local timing implicitly associated feature vector in the time queue of the local timing implicitly associated feature vectors of the device temperature, determining the feature energy level coefficients of each device temperature local timing implicitly associated feature vector to obtain a sequence of device temperature local timing feature energy level coefficients; determining the scale of the local neighborhood of the local timing of the device temperature, with the local neighborhood of the local timing of the device temperature as the scale of the local neighborhood of the local timing of the device temperature. The scale is used as the mean calculation range, and the local neighborhood mean of each device temperature local timing feature energy level coefficient is calculated respectively to obtain a sequence of device temperature local timing feature energy level significance descriptors; the sequence of device temperature local timing feature energy level significance descriptors is input into a mask module based on a gating function to obtain a sequence of mask-gated probabilistic device temperature local timing feature energy level significance descriptors; the sequence of mask-gated probabilistic device temperature local timing feature energy level significance descriptors is used as a sequence of weights, and the position-weighted sum of the time queue of the device temperature local timing implicitly associated feature vector is calculated to obtain the temperature thermal characterization timing encoding vector.

[0074] Furthermore, in one embodiment of the present application, based on the maximum value, minimum value, mean value and variance of each device temperature local timing implicitly associated feature vector in the time queue of the device temperature local timing implicitly associated feature vector, the characteristic energy level coefficient of each device temperature local timing implicitly associated feature vector is determined to obtain a sequence of device temperature local timing characteristic energy level coefficients, including: calculating the maximum value, minimum value, mean value and variance of the device temperature local timing implicitly associated feature vector to obtain the device temperature local timing maximum value, the device temperature local timing minimum value, the device temperature local timing average value and the device temperature local timing variance; calculating the sum of the device temperature local timing variance and the hyperparameter to obtain the first device temperature local timing; local energy statistical factor of the local timing of the device temperature; calculating the difference between the maximum value of the local timing of the device temperature and the average value of the local timing of the device temperature to obtain the maximum deviation value of the local timing of the device temperature; calculating the difference between the minimum value of the local timing of the device temperature and the average value of the local timing of the device temperature to obtain the minimum deviation value of the local timing of the device temperature; calculating the sum of the squares of the maximum deviation value of the local timing of the device temperature and the minimum deviation value of the local timing of the device temperature and adding it to the hyperparameter to obtain the local energy statistical factor of the second local timing of the device temperature; calculating the division between the local energy statistical factor of the local timing of the first device temperature and the local energy statistical factor of the local timing of the second device temperature to obtain the local timing characteristic energy level coefficient of the device temperature.

[0075] Furthermore, in one embodiment of the present application, the sequence of the device temperature local timing feature energy level significance descriptors is input into a mask module based on a gating function to obtain a sequence of mask-gated probabilistic device temperature local timing feature energy level significance descriptors, including: using the negative number of each device temperature local timing feature energy level significance descriptor in the sequence of the device temperature local timing feature energy level significance descriptors as an exponential power, calculating an exponential function value with a natural constant e as the base to obtain a sequence of device temperature local timing feature energy level class support significance descriptors; calculating the positional sum between the sequence of device temperature local timing feature energy level class support significance descriptors and a constant 1 to obtain a sequence of linear modulation device temperature local timing feature energy level class support significance descriptors; calculating each linear modulation device temperature local timing feature energy level in the sequence of linear modulation device temperature local timing feature energy level class support significance descriptors. The class supports the inverse of the significance descriptor to obtain a sequence of device temperature local timing gated probabilistic feature energy level significance descriptors; each device temperature local timing gated probabilistic feature energy level significance descriptor in the sequence of device temperature local timing gated probabilistic feature energy level significance descriptors is masked to obtain a sequence of masked gated probabilistic device temperature local timing feature energy level significance descriptors; wherein, each device temperature local timing gated probabilistic feature energy level significance descriptor in the sequence of device temperature local timing gated probabilistic feature energy level significance descriptors is masked to obtain a sequence of masked gated probabilistic device temperature local timing feature energy level significance descriptors, including: in response to the device temperature local timing gated probabilistic feature energy level significance descriptor being greater than a predetermined threshold, taking the original value of the device temperature local timing gated probabilistic feature energy level significance descriptor, otherwise setting it to 0.

[0076] Specifically, the time queue of the local time series implicitly associated feature vector of the device temperature is input into the feature aggregation network based on the local significant gating of feature energy for processing with the following feature aggregation formula to obtain the device temperature thermal representation time series encoding vector;

[0077] Among them, the feature aggregation formula is:

[0078] X={x1,x2,…,x k , …, x n}

[0079]

[0080]

[0081]

[0082] w si=mask(w i )

[0083]

[0084] Y={y1,y2,…,y k , …, y n},y i =w si ·x i

[0085]

[0086] Where X is the time queue of the implicit correlation feature vector of the local time series of the device temperature, x i is the i-th device temperature local time series implicit correlation feature vector in the time queue of the device temperature local time series implicit correlation feature vector, x k and x n are the kth and nth device temperature local time series implicit correlation feature vectors in the time queue of the device temperature local time series implicit correlation feature vectors, μ i is the mean of the implicit correlation eigenvector of the local time series of the temperature of the i-th device, σ i 2 is the variance of the implicit correlation feature vector of the local time series of the temperature of the i-th device, ε is a hyperparameter, max(x i ) represents the maximum value of the local time series implicit correlation feature vector of the i-th device temperature, min(x i ) represents the minimum value of the local time series implicit correlation feature vector of the i-th device temperature, e i is the characteristic energy level coefficient of the implicit correlation characteristic vector of the local timing of the temperature of the i-th device, Num r Indicated by the characteristic energy level coefficient e i The number of characteristic energy coefficients in the local neighborhood centered at q is the characteristic energy level coefficient of the implicit correlation characteristic vector of the local timing of the qth device temperature, e ci is the characteristic energy level significance descriptor of the implicit correlation characteristic vector of the local timing of the temperature of the i-th device, w i is the gated probabilistic feature energy level significance descriptor of the implicit correlation feature vector of the local timing of the temperature of the i-th device, mask(·) is the masking operation, θ is the predetermined threshold, w si is the mask-gated probabilistic feature energy level significance descriptor of the implicit correlation feature vector of the local timing of the temperature of the i-th device, y iis the significant enhanced device temperature local timing implicit correlation feature vector corresponding to the i-th device temperature local timing implicit correlation feature vector, n is the number of feature vectors in the time queue of the significant enhanced device temperature local timing implicit correlation feature vector, and f is the temperature thermal representation timing encoding vector.

[0087] Furthermore, the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector reflect the device temperature thermal characterization timing characteristics and thermal effect timing characteristics respectively, and when the power grid equipment is working normally, there is an implicit correlation feature and interactive relationship between the thermal characterization characteristics and thermal effect characteristics of the equipment. When the power grid equipment is in an abnormal working state, this relationship will be destroyed. Therefore, in order to better detect the abnormal working state of the power grid equipment, in the technical solution of the present application, the position difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector is further calculated to obtain a thermal effect-thermal characterization timing difference representation vector. By calculating the position difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector, the significant differences and dynamic changes between the thermal effect and temperature characterization can be highlighted, helping to identify the deviation between the device thermal effect and temperature in the time domain, which helps to better understand the operating state of the equipment, thereby revealing potential anomalies or faults.

[0088] In one embodiment of the present application, the positional difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector is calculated to obtain thermal effect-thermal characterization timing difference feature information, and based on the thermal effect-thermal characterization timing difference feature information, it is determined whether the working state of the power grid equipment is abnormal, including: calculating the positional difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector to obtain a thermal effect-thermal characterization timing difference representation vector as the thermal effect-thermal characterization timing difference feature information; inputting the thermal effect-thermal characterization timing difference representation vector into a classifier-based power grid equipment state detection module to obtain a detection result, and the detection result is used to indicate whether the working state of the power grid equipment is abnormal.

[0089] Then, the thermal effect-thermal characterization time series difference representation vector is input into the classifier-based power grid equipment state detection module to obtain a detection result, which is used to indicate whether the working state of the power grid equipment is abnormal. In other words, the thermal effect and thermal characterization time series difference characteristics of the power grid equipment are classified and processed to determine whether the working state of the power grid equipment is abnormal, so as to detect and respond to power grid equipment failures in a timely and effective manner, and realize more intelligent power grid operation and maintenance management.

[0090] In a preferred example, when the device thermal effect timing coding vector expresses a position-based thermal effect coding feature based on the local timing node distribution energy timing propagation feature of the device current and the device voltage, and the device temperature thermal characterization timing coding vector expresses a local time domain energy significance aggregation feature based on the local timing correlation feature of the device temperature, the thermal effect-thermal characterization timing difference representation vector obtained by calculating the position-based difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector will also have a distribution regression pattern offset caused by the uneven difference in the timing distribution pattern of the positional features, that is, it will cause the thermal effect-thermal characterization timing difference representation vector to overflow the detection result obtained by inputting the classifier-based power grid equipment status detection module, affecting its accuracy.

[0091] Based on this, when the thermal effect-thermal characterization time series difference representation vector is input into a classifier-based power grid equipment state detection module to obtain a detection result, the present application optimizes the thermal effect-thermal characterization time series difference representation vector. Specifically, the optimization includes the steps of:

[0092] Determine the abnormal probability value corresponding to the abnormality of the working state of the power grid equipment obtained by inputting the thermal effect-thermal characterization time series difference representation vector into the power grid equipment state detection module based on the classifier, and pass the thermal effect-thermal characterization time series difference representation vector through a probabilistic activation function to obtain a probabilistic thermal effect-thermal characterization time series difference representation vector;

[0093] Subtract the probabilistic thermal effect-thermal characterization time-series difference representation vector from the unit feature vector, and use the feature vector resulting from the subtraction as a base to calculate a power function with the abnormal probability value as an exponent;

[0094] Performing a dot multiplication of the power function vector and the probabilistic thermal effect-thermal characterization temporal difference representation vector to obtain a thermal effect-thermal characterization temporal difference intermediate feature vector;

[0095] Taking the absolute value of each eigenvalue of the probabilistic thermal effect-thermal characterization time series difference representation vector as a base, calculating a power function with the inverse of the abnormal probability value as an exponent, and summing all eigenvalues ​​to obtain a thermal effect-thermal characterization time series difference bias eigenvalue; and

[0096] After the thermal effect-thermal characterization temporal difference bias eigenvalue is multiplied by a weight as a hyperparameter, the thermal effect-thermal characterization temporal difference intermediate eigenvector is interpolated to obtain an optimized thermal effect-thermal characterization temporal difference representation vector.

[0097] Wherein, let the probabilistic thermal effect-thermal characterization time series difference representation vector be denoted as V, then the optimized thermal effect-thermal characterization time series difference representation vector V′ is expressed as:

[0098]

[0099] Where I is the unit eigenvector and v i ∈V, is the eigenvalue of the probabilistic thermal effect-thermal representation time series difference representation vector V, V is the probabilistic thermal effect-thermal representation time series difference representation vector, V′ is the optimized thermal effect-thermal representation time series difference representation vector, α is the weight of the hyperparameter, p is the abnormal probability value, ⊙ is the position point multiplication, is positional subtraction, It is positional addition.

[0100] That is, for the thermal effect-thermal characterization time series difference representation vector, based on the convergence limit of the probability distribution of the Cauchy-Hadamard form power series, the feature set of the thermal effect-thermal characterization time series difference representation vector is represented by a power series based on the convergence probability, and a set convergence bounded bias based on each eigenvalue of the thermal effect-thermal characterization time series difference representation vector as a convergence radius representation is added, so as to avoid the invalid overflow of the classification result caused by the deviation of the distribution mode of the thermal effect-thermal characterization time series difference representation vector caused by the gradient propagation of the model parameters based on the convergence probability in the regression process of the power grid equipment state detection module based on the classifier under the unified probability convergence limit standard, thereby improving the accuracy of the detection result obtained by the power grid equipment state detection module based on the classifier. In this way, the working state of the power grid equipment can be detected more accurately, so that the power grid equipment failure can be responded to in time, and more intelligent power grid operation and maintenance management can be realized.

[0101] In summary, the above scheme is adopted to monitor and collect the equipment operation status data in real time through the intelligent fusion gateway, including equipment current, equipment voltage and equipment temperature, and transmit these data to the power grid operation and maintenance management server through the intelligent fusion gateway, so as to use the data processing and analysis algorithm based on artificial intelligence and deep learning in the power grid operation and maintenance management server to perform time series analysis on the equipment operation status data, and further perform correlation feature extraction and difference calculation based on thermal effect-thermal characterization, so as to detect the working status of the power grid equipment. In this way, it is possible to judge whether there is an abnormality in the working status of the power grid equipment based on the characterization and comparative analysis of the thermal effect and thermal characterization of the power grid equipment, so as to detect and respond to power grid equipment failures in a timely and effective manner, and realize more intelligent power grid operation and maintenance management.

[0102] Figure 2 FIG. 1 is a block diagram of a power grid operation and maintenance management system based on an intelligent converged gateway according to an exemplary embodiment. Figure 2 As shown, the system 200 includes:

[0103] The device operation status data collection module 201 is used to collect the time queue of the device operation status data through the intelligent fusion gateway, wherein the device operation status includes the device current, the device voltage and the device temperature;

[0104] The data transmission module 202 is used to transmit the time queue of the equipment operation status data to the power grid operation and maintenance management server through the intelligent fusion gateway;

[0105] The timing coding module 203 is used to perform timing coding on the time queue of the equipment operation status data in the power grid operation and maintenance management server to obtain a time queue of the equipment current local timing implicit correlation feature vector, a time queue of the equipment current local timing implicit correlation feature vector, and a time queue of the equipment temperature local timing implicit correlation feature vector;

[0106] The node characteristic timing propagation network module 204 is used to input the time queue of the local timing implicitly associated characteristic vector of the device current and the time queue of the local timing implicitly associated characteristic vector of the device current into the node characteristic timing propagation network based on the node energy decay mechanism to obtain the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector;

[0107] The device thermal effect encoding module 205 is used to input the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector into a device thermal effect encoder to obtain a device thermal effect timing encoding vector;

[0108] A feature aggregation network module 206 is used to input the time queue of the local temporal implicitly associated feature vector of the device temperature into a feature aggregation network based on feature energy local significance gating to obtain a device temperature thermal representation temporal encoding vector;

[0109] The working state determination module 207 of the power grid equipment is used to calculate the position difference between the equipment temperature thermal characterization timing coding vector and the equipment thermal effect timing coding vector to obtain thermal effect-thermal characterization timing difference feature information, and determine whether the working state of the power grid equipment is abnormal based on the thermal effect-thermal characterization timing difference feature information.

[0110] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 600 suitable for implementing the embodiment of the present application. The terminal device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0111] like Figure 3 As shown, the electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage device 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0112] Typically, the following devices may be connected to the I / O interface 605: an input device 606 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 607 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 608 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 609. The communication device 609 may allow the electronic device 600 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 600 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0113] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 609, or installed from the storage device 608, or installed from the ROM 602. When the computer program is executed by the processing device 601, the above-mentioned functions defined in the method of the embodiment of the present application are executed.

[0114] It should be noted that the computer-readable medium mentioned above in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0115] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0116] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0117] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0118] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0119] The modules involved in the embodiments described in this application can be implemented by software or hardware. The name of the module does not limit the module itself in some cases. For example, the test parameter acquisition module can also be described as a "module for acquiring device test parameters corresponding to the target device".

[0120] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0121] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0122] Figure 4 FIG. 1 is an application scenario diagram of a power grid operation and maintenance management method based on an intelligent converged gateway according to an exemplary embodiment. Figure 4 As shown, in this application scenario, first, the time queue of the device operation status data is collected through the intelligent fusion gateway, wherein the device operation status includes the device current (for example, Figure 4 C1 as shown in the figure), device voltage (e.g. Figure 4 C2) and device temperature (e.g. Figure 4 Then, the acquired device current, device voltage and device temperature are input to a server (for example, Figure 4 In S) shown in , the server is capable of processing the device current, the device voltage and the device temperature based on the power grid operation and maintenance management algorithm of the intelligent fusion gateway to determine whether there is any abnormality in the working state of the power grid equipment based on the thermal effect-thermal characterization timing differential feature information.

[0123] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

[0124] In addition, although each operation is described in a specific order, this should not be construed as requiring these operations to be performed in the specific order shown or to be performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the application. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0125] Although the subject matter has been described in language specific to structural features and / or method logic actions, it should be understood that the subject matter defined is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementation. With respect to the apparatus in the above-mentioned embodiments, the specific manner in which each module performs the operation has been described in detail in the embodiments related to the method, and will not be described in detail here.

Claims

1. A power grid operation and maintenance management method based on an intelligent fusion gateway, characterized in that: include: A time queue for collecting device operation status data through an intelligent fusion gateway, wherein the device operation status includes device current, device voltage and device temperature; Transmitting the time queue of the equipment operation status data to the power grid operation and maintenance management server through the intelligent fusion gateway; On the power grid operation and maintenance management server, time series encoding is performed on the time series of the equipment operation status data to obtain a time series of equipment current local time series implicit correlation feature vectors, a time series of equipment current local time series implicit correlation feature vectors, and a time series of equipment temperature local time series implicit correlation feature vectors; Input the time queue of the local timing implicitly associated characteristic vector of the device current and the time queue of the local timing implicitly associated characteristic vector of the device current into the node characteristic timing propagation network based on the node energy decay mechanism respectively to obtain the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector; Inputting the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector into a device thermal effect encoder to obtain a device thermal effect timing encoding vector; Inputting the time queue of the local temporal implicit correlation feature vector of the device temperature into a feature aggregation network based on local significant gating of feature energy to obtain a temporal encoding vector of the thermal representation of the device temperature; The positional difference between the device temperature thermal characterization timing coding vector and the device thermal effect timing coding vector is calculated to obtain thermal effect-thermal characterization timing difference feature information, and whether there is an abnormality in the working state of the power grid device is determined based on the thermal effect-thermal characterization timing difference feature information.

2. The power grid operation and maintenance management method based on the intelligent fusion gateway according to claim 1 is characterized in that: In the power grid operation and maintenance management server, the time queue of the equipment operation status data is time-series encoded to obtain a time queue of equipment current local time sequence implicit correlation feature vectors, a time queue of equipment current local time sequence implicit correlation feature vectors, and a time queue of equipment temperature local time sequence implicit correlation feature vectors, including: On the power grid operation and maintenance management server, preprocessing the time queue of the equipment operation status data according to the parameter sample dimension to obtain the time queue of the equipment current, the time queue of the equipment voltage and the time queue of the equipment temperature; The time queue of the device current, the time queue of the device voltage and the time queue of the device temperature are respectively input into the sequence encoder based on the 1D-CNN model to obtain the time queue of the local timing implicit correlation feature vector of the device current, the time queue of the local timing implicit correlation feature vector of the device current and the time queue of the local timing implicit correlation feature vector of the device temperature.

3. The power grid operation and maintenance management method based on the intelligent fusion gateway according to claim 2 is characterized in that: Inputting the time queue of the local timing implicitly associated characteristic vector of the device current and the time queue of the local timing implicitly associated characteristic vector of the device current into the node characteristic timing propagation network based on the node energy decay mechanism respectively to obtain the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector, including: Based on the mean and standard deviation of each device current local time series implicit correlation feature vector in the time queue of the device current local time series implicit correlation feature vector, calculate the energy significant descriptor of each device current local time series implicit correlation feature vector to obtain a sequence of device current local time series energy significant descriptors; Extracting the timestamps of the local time series implicitly associated characteristic vectors of the device current in the time queue of the local time series implicitly associated characteristic vectors of the device current to obtain a sequence of device current timestamps; Taking the device current local time sequence implicit association feature vector corresponding to the current time point in the time queue of the device current local time sequence implicit association feature vector as the current device current local time sequence implicit association feature vector and taking the device current local time sequence implicit association feature vector corresponding to other time points as the historical device current local time sequence implicit association feature vector to obtain the time queue of the current device current local time sequence implicit association feature vector and the historical device current local time sequence implicit association feature vector; Calculate the energy time decay factor of each historical device current local time series implicit correlation feature vector in the time queue of the historical device current local time series implicit correlation feature vector relative to the current device current local time series implicit correlation feature vector to obtain a sequence of device current local time series energy time decay factors; Using the sequence of the significant descriptors of the local time series energy of the device current as a positive adjustment factor and the sequence of the time decay factors of the local time series energy of the device current as a negative adjustment factor, the time queue of the implicitly associated feature vectors of the local time series of the historical device current is subjected to time series propagation aggregation to obtain a feature vector representing the historical node propagation aggregation of the local time series of the device current; Based on the energy significant descriptor corresponding to the implicit correlation feature vector of the current device current local timing, the position-weighted sum of the device current local timing history node propagation aggregation representation feature vector and the current device current local timing implicit correlation feature vector is calculated to obtain the device current timing propagation aggregation representation vector.

4. The power grid operation and maintenance management method based on the intelligent fusion gateway according to claim 3 is characterized in that: Based on the mean and standard deviation of each device current local time series implicit correlation feature vector in the time queue of the device current local time series implicit correlation feature vector, calculating the energy significant descriptor of each device current local time series implicit correlation feature vector to obtain a sequence of device current local time series energy significant descriptors, including: Calculating the mean and standard deviation of each device current local time series implicit correlation feature vector in the time queue of the device current local time series implicit correlation feature vector to obtain a sequence of device current local means and a sequence of device current local standard deviations; Calculating the standard deviation of each device current local time series implicit correlation feature vector in the time queue of the device current local time series implicit correlation feature vector to obtain a sequence of device current local standard deviations; After performing positional differentiation on each group of corresponding local time series implicitly associated characteristic vectors of the device current and the local mean value of the device current in the time queue of the local time series implicitly associated characteristic vectors of the device current and the sequence of the local mean value of the device current, each position characteristic value in the obtained sequence of differential characteristic vectors is modulated to the fourth power to obtain a sequence of local time series modulation characteristic vectors of the device current; Calculating the expected value of each device current local timing modulation characteristic vector in the sequence of device current local timing modulation characteristic vectors to obtain a sequence of device current local timing positive expected factors; Calculating the fourth power modulation value of each device current local standard deviation in the sequence of device current local standard deviations to obtain a sequence of device current local timing inverse expectation factors; Each group of corresponding device current local timing positive expected factors and device current local timing inverse expected factors in the sequence of device current local timing positive expected factors and the sequence of device current local timing inverse expected factors are divided to obtain the sequence of device current local timing energy significant descriptors.

5. The power grid operation and maintenance management method based on the intelligent fusion gateway according to claim 4 is characterized in that: Calculating the energy time decay factor of each historical device current local time series implicit correlation feature vector in the time queue of the historical device current local time series implicit correlation feature vector relative to the current device current local time series implicit correlation feature vector to obtain a sequence of device current local time series energy time decay factors, including: Respectively calculating the device current timestamp corresponding to the current device current local time series implicit correlation feature vector and the device current timestamp corresponding to each historical device current local time series implicit correlation feature vector, subtracting them from each other and rounding them down to obtain a sequence of time span values; After calculating the square of each time span value in the sequence of time span values, the obtained sequence of span square modulation values ​​is divided by the time decay inverse scaling parameter by position and multiplied by the decay rate positive scaling parameter by position to obtain a sequence of time series span energy decay coefficients; Taking each time-series span energy attenuation coefficient in the sequence of time-series span energy attenuation coefficients as an exponential power, a natural exponential function value with a natural constant e as a base is calculated to obtain a sequence of local time-series energy time attenuation factors of the device current.

6. The power grid operation and maintenance management method based on the intelligent fusion gateway according to claim 5 is characterized in that: Taking the sequence of the significant descriptors of the local timing series energy of the device current as the positive adjustment factor and the sequence of the time decay factors of the local timing series energy of the device current as the negative adjustment factor, the time queue of the historical device current local timing implicitly associated feature vectors is subjected to time propagation aggregation to obtain the device current local timing series historical node propagation aggregation representation feature vector, including: calculating the positional division of the sequence of the significant descriptors of the local timing series energy of the device current and the sequence of the time decay factors of the local timing series energy of the device current, using the obtained device current local timing series energy weight as the weighting coefficient, and calculating the positional weighted sum of the time queue of the historical device current local timing implicitly associated feature vectors to obtain the device current local timing series historical node propagation aggregation representation feature vector.

7. The power grid operation and maintenance management method based on the intelligent fusion gateway according to claim 6 is characterized in that: The device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector are input into the device thermal effect encoder to obtain the device thermal effect timing encoding vector, including: multiplying the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector by position point to obtain the device thermal effect timing encoding vector.

8. The power grid operation and maintenance management method based on intelligent fusion gateway according to claim 7 is characterized in that: Inputting the time queue of the local temporal implicit correlation feature vector of the device temperature into a feature aggregation network based on local significant gating of feature energy to obtain a temporal encoding vector of the thermal representation of the device temperature, including: Determine the characteristic energy level coefficients of the local timing implicitly associated characteristic vectors of the device temperature based on the maximum value, minimum value, mean value and variance of each local timing implicitly associated characteristic vector of the device temperature in the time queue of the local timing implicitly associated characteristic vector of the device temperature to obtain a sequence of the local timing implicitly associated characteristic energy level coefficients of the device temperature; Determine the scale of the local neighborhood of the local time series of the device temperature, use the scale of the local neighborhood of the local time series of the device temperature as the mean calculation range, and respectively calculate the local neighborhood mean of each of the local time series characteristic energy level coefficients of the device temperature to obtain a sequence of significant descriptors of the local time series characteristic energy level of the device temperature; Inputting the sequence of the device temperature local temporal feature energy level significance descriptors into a mask module based on a gating function to obtain a sequence of mask-gated probabilistic device temperature local temporal feature energy level significance descriptors; The sequence of the mask-gated probabilistic device temperature local temporal feature energy level significance descriptors is used as a sequence of weights, and the position-weighted sum of the time queue of the device temperature local temporal implicit association feature vector is calculated to obtain the temperature thermal characterization temporal encoding vector.

9. The power grid operation and maintenance management method based on intelligent fusion gateway according to claim 8 is characterized in that: Calculating the position difference between the device temperature thermal characterization time series coding vector and the device thermal effect time series coding vector to obtain thermal effect-thermal characterization time series difference feature information, and determining whether the working state of the power grid device is abnormal based on the thermal effect-thermal characterization time series difference feature information, including: Calculating the position difference between the device temperature thermal characterization time series encoding vector and the device thermal effect time series encoding vector to obtain a thermal effect-thermal characterization time series difference representation vector as the thermal effect-thermal characterization time series difference feature information; The thermal effect-thermal characterization time-series difference representation vector is input into a classifier-based power grid equipment state detection module to obtain a detection result, and the detection result is used to indicate whether there is an abnormality in the working state of the power grid equipment.

10. A power grid operation and maintenance management system based on an intelligent fusion gateway, characterized in that: include: The device operation status data collection module is used to collect the time queue of the device operation status data through the intelligent fusion gateway, wherein the device operation status includes device current, device voltage and device temperature; A data transmission module, used for transmitting the time queue of the equipment operation status data to the power grid operation and maintenance management server through the intelligent fusion gateway; A timing encoding module is used to perform timing encoding on the time queue of the equipment operation status data in the power grid operation and maintenance management server to obtain a time queue of equipment current local timing implicit correlation feature vectors, a time queue of equipment current local timing implicit correlation feature vectors, and a time queue of equipment temperature local timing implicit correlation feature vectors; A node characteristic timing propagation network module is used to input the time queue of the local timing implicitly associated characteristic vector of the device current and the time queue of the local timing implicitly associated characteristic vector of the device current into the node characteristic timing propagation network based on the node energy decay mechanism to obtain the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector; A device thermal effect encoding module, used for inputting the device current timing propagation aggregation representation vector and the device voltage timing propagation aggregation representation vector into a device thermal effect encoder to obtain a device thermal effect timing encoding vector; A feature aggregation network module is used to input the time queue of the local temporal implicit correlation feature vector of the device temperature into a feature aggregation network based on local significant gating of feature energy to obtain a temporal encoding vector of thermal representation of the device temperature; The working state determination module of the power grid equipment is used to calculate the position difference between the equipment temperature thermal characterization timing coding vector and the equipment thermal effect timing coding vector to obtain thermal effect-thermal characterization timing difference feature information, and determine whether the working state of the power grid equipment is abnormal based on the thermal effect-thermal characterization timing difference feature information.

Images