Power equipment alarm method and device

Abstract

The invention provides a power equipment alarm method and device, and the method comprises the steps: obtaining a real-time measurement value of a monitoring index according to the set monitoring index; calculating a state estimation value of the monitoring index according to the real-time measurement value and an optimal memory matrix which is dynamically updated based on a historical measurement value of the monitoring index, and generating a state estimation matrix; and generating a power equipment alarm result according to the state estimation matrix and a fault alarm threshold trust domain matrix which is dynamically updated based on the historical measurement value of the monitoring index. According to the method and the device, the accuracy of the monitoring index state estimation value calculated based on the optimal memory matrix is effectively ensured, and the accuracy of the power equipment alarm result is determined according to the state estimation value; and the efficiency of calculating the state estimation value and the electric power alarm result is greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of power equipment monitoring, and more specifically, to a power equipment alarm method and device. Background Art

[0002] The digital remote meter for substation is an intelligent monitoring instrument with the functions of local monitoring of the status of the primary equipment in the substation and remote data upload. It mainly covers six types of meters: SF6 digital density meter, arrester digital leakage current meter, transformer digital oil temperature meter, transformer digital oil level meter, transformer digital gas relay, transformer digital oil pressure gauge. These meters use digital and communication technology to monitor various non-electrical parameters (such as gas density, gas pressure, oil temperature, oil level, gas volume, number of actions, etc.) and electrical parameters (such as leakage current) in real time. Through the digital data upload function, the monitoring data can be transmitted to the cloud platform or other management systems to realize remote monitoring and management of substation equipment. The alarm function of power equipment can be realized through data processing and analysis.

[0003] These digital remote meters are widely used in key equipment in substations, such as transformers, GIS (gas insulated switchgear), lightning arresters, mutual inductors, etc., and can detect equipment status in real time and upload data. With these data, operation and maintenance personnel can monitor the operating status of the equipment at any time, detect faults and abnormalities in a timely manner, and take measures to improve the stability and safety of the equipment. However, the current fault and abnormality alarms of power equipment usually rely on simple threshold alarms, change rate alarms and other methods. These methods are difficult to accurately and efficiently extract effective information from monitoring data, resulting in poor accuracy and efficiency of alarms. Summary of the invention

[0004] In order to solve the technical problem in the prior art that substation power equipment failure and abnormality alarms can only simply rely on threshold alarms and change rate alarms, resulting in poor alarm accuracy and efficiency, the present invention provides a power equipment alarm method and device.

[0005] According to one aspect of the present invention, the present invention provides an electric power equipment alarm method, the method comprising:

[0006] According to the set monitoring indicators, real-time measurement values ​​of the monitoring indicators are obtained, wherein the monitoring indicators include operating indicators of digital meters of substations and environmental parameters of substations;

[0007] Calculate the state estimation value of the monitoring indicator according to the real-time measurement value and the optimal memory matrix dynamically updated based on the historical measurement value of the monitoring indicator to generate a state estimation matrix;

[0008] An electric power equipment alarm result is generated according to the state estimation matrix and a fault alarm threshold trust domain matrix that is dynamically updated based on historical measurement values ​​of the monitoring indicators.

[0009] According to another aspect of the present invention, the present invention provides an electric power equipment alarm device, the device comprising:

[0010] A data acquisition module, used to obtain real-time measurement values ​​of monitoring indicators according to set monitoring indicators, wherein the monitoring indicators include operating indicators of substation digital meters and substation environmental parameters;

[0011] A data calculation module, used to calculate the state estimation value of the monitoring indicator according to the real-time measurement value and the optimal memory matrix dynamically updated based on the historical measurement value of the monitoring indicator, and generate a state estimation matrix;

[0012] The result output module is used to generate an electric power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators.

[0013] According to another aspect of the present invention, the present invention provides a computer-readable storage medium, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0014] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0015] The electric power equipment alarm method and device of the present invention, wherein the method comprises: obtaining the real-time measurement value of the monitoring indicator according to the set monitoring indicator; calculating the state estimation value of the monitoring indicator according to the real-time measurement value and the optimal memory matrix dynamically updated based on the historical measurement value of the monitoring indicator, and generating the state estimation matrix; generating the electric power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement value of the monitoring indicator. The method and device dynamically update the optimal memory matrix of the monitoring indicator measurement value based on the historical data of the monitoring indicator of the electric power equipment alarm, and dynamically update the alarm threshold trust domain based on the historical data of the monitoring indicator, thereby effectively ensuring the accuracy of the monitoring indicator state estimation value calculated based on the optimal memory matrix, and the accuracy of the electric power equipment alarm result determined according to the state estimation value, and by establishing a matrix for multiple monitoring indicators for calculation, the efficiency of calculating the state estimation value and the electric power alarm result is also greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0017] Figure 1 A flowchart of a power equipment alarm method according to a preferred embodiment of the present invention;

[0018] Figure 2 A flowchart of a power equipment alarm method according to a preferred embodiment of the present invention;

[0019] Figure 3 Schematic diagram of the structure of an electronic device according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0020] Now, exemplary embodiments of the present invention are described with reference to the accompanying drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. These embodiments are provided to disclose the present invention in detail and completely and to fully convey the scope of the present invention to those skilled in the art. The terms used in the exemplary embodiments shown in the accompanying drawings are not intended to limit the present invention. In the accompanying drawings, the same units / elements are marked with the same reference numerals.

[0021] Unless otherwise specified, the terms (including technical terms) used herein have the commonly understood meanings to those skilled in the art. In addition, it is understood that the terms defined in commonly used dictionaries should be understood to have the same meanings as those in the context of the relevant fields, and should not be understood as idealized or overly formal meanings.

[0022] Exemplary Methods

[0023] Figure 1 FIG. 1 is a flow chart of a power equipment alarm method according to a preferred embodiment of the present invention. Figure 1 As shown, the electric power equipment alarm method described in this preferred embodiment starts from step 101.

[0024] In step 101, according to the set monitoring indicators, real-time measurement values ​​of the monitoring indicators are obtained, wherein the monitoring indicators include operation indicators of substation digital meters and substation environmental parameters.

[0025] In this preferred embodiment, the digital meters in the substation are used to collect the operating data and environmental parameters of the meters in real time, and various non-electrical parameters (such as gas density, gas pressure, oil temperature, oil level, gas volume, number of operations, etc.) and electrical parameters (such as leakage current) are transmitted to the substation monitoring host (or monitoring data collection and aggregation system such as auxiliary control host). The monitored power equipment includes: GIS, transformers, lightning arresters, mutual inductors, etc.

[0026] Preferably, the state estimation value of the monitoring indicator is calculated based on the optimal memory matrix dynamically updated according to the value of the intended evaluation indicator and the historical measurement value of the monitoring indicator, and before generating the state estimation matrix, the method further includes:

[0027] When there are n monitoring indicators, the historical measurement values ​​of the n monitoring indicators at the sampling time are recorded as the observation vector X = [x1, x2, ..., x n ] T ;

[0028] For multiple sensors that collect measurement values ​​of n monitoring indicators, select n sensors with high trust scores to obtain historical measurement values ​​of the n monitoring indicators at m historical sampling moments, generate m observation vectors, and generate an initial memory matrix D(T) based on the m observation vectors, wherein the trust score is determined by the score in the score table preset according to expert experience, and T is a sampling period consisting of m sampling moments;

[0029] The initial memory matrix D(T) is calculated by using a sliding window update method, an exponentially weighted moving average method, a Kalman filter method and an incremental learning method to generate a corresponding optimized memory matrix, wherein a sliding window is used to limit the time range of historical measurement values, an exponentially weighted moving average method is used to smooth the influence of historical measurement values ​​at different sampling moments, a Kalman filter is used to predict and correct historical measurement values ​​of monitoring indicators, and the initial memory matrix is ​​adjusted in real time by incremental learning;

[0030] An optimal memory matrix is ​​generated according to the initial memory matrix and the optimized memory matrix.

[0031] In this preferred embodiment, since there may be multiple sensors collecting data for one monitoring indicator in the substation, in order to improve the accuracy of data collection, the trust level of the accuracy of the collected data is scored according to the characteristics of different sensors, and sensors with high trust scores are preferentially selected for data collection. At the same time, considering the changes in operating conditions, the impact of the time of data collection on data accuracy, etc., in order to ensure the accuracy of the power equipment state estimation value calculated based on the real-time collected data, the collected historical data is continuously and dynamically updated. This preferred embodiment adopts a sliding window update method, an exponentially weighted moving average method, a Kalman filter, and an incremental learning method to construct an optimal memory matrix for historical data. Specifically, a sliding window is used to limit the time range of the data, and the exponentially weighted moving average method is used to smooth the impact of historical data (the exponentially weighted moving average method inputs a memory matrix generated based on high-trust historical data, and then assigns a weight value to several historical memory matrices before the memory matrix and the memory matrix to obtain a new memory matrix. This method emphasizes the importance of the current sample and gradually downplays the importance of historical samples. The closer the data is to the current one, the greater the weight, and vice versa. The weight is approximately smaller and can be set based on experience). The Kalman filter performs dynamic prediction and correction of the measurement value, and the model is adjusted in real time through incremental learning.

[0032] Preferably, the optimal memory matrix is ​​generated according to the initial memory matrix and the optimized memory matrix, wherein the calculation formula of the optimal memory matrix is:

[0033] D H (T+1)=γ1(T+1)*D w (T+1)+γ2(T+1)*D e (T+1)

[0034] +γ3(T+1)*D k (T+1)+γ4(T+1)*D l (T+1)

[0035]

[0036] Where D H (T+1) is the optimal memory matrix of sampling period T+1, D w (T+1), D e (T+1), D k (T+1) and D l(T+1) is the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method, γ1(T+1), γ2(T+1), γ3(T+1) and γ4(T+1) are the weight coefficients of the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method in calculating the optimal memory matrix, D j (T) represents the value of the jth column of the initial memory matrix D(T) in the sampling period T. The values ​​of i represent the sliding window update method, exponentially weighted moving average method, Kalman filter method and incremental learning method, respectively. It represents the value of the jth column in the sampling period T+1 when the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method are used respectively.

[0037] According to the calculation formula of the weight coefficients above, the weight values ​​are dynamically adjusted according to the errors of the memory matrices obtained by the four methods. The memory matrix obtained by the method with the smaller error will get a larger weight. By dynamically adjusting the weight coefficients above, the optimal memory matrix can adapt to the update requirements of the state estimation value.

[0038] In step 102, the state estimation value of the monitoring indicator is calculated according to the real-time measurement value and the optimal memory matrix dynamically updated based on the historical measurement value of the monitoring indicator to generate a state estimation matrix.

[0039] In step 103, an electric power equipment alarm result is generated according to the state estimation matrix and a fault alarm threshold trust domain matrix dynamically updated based on historical measurement values ​​of the monitoring indicators.

[0040] Preferably, before generating the power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators, the method further includes:

[0041] Let X be the observation vector composed of n monitoring indicators, the objective function f(X) be the fault alarm threshold distribution function of X, and the Gaussian process model g(X) be used to approximate the objective function. The posterior distribution of the Gaussian process model g(X) is:

[0042] g(X)~Ν(μ(X),σ 2 (X)

[0043] Where μ(X) is the mean function, σ 2 (X) is the covariance function, which represents the predicted value and uncertainty of the objective function f(X) respectively. The calculation formula is:

[0044] μ(X)=k(X,I)K -1 Y

[0045] σ 2 (X) = k(X,X)-k(X,I)K -1 k(I,X)

[0046] Where k(X,I), k(X,X) and k(X,I) are kernel functions, K is the covariance matrix, I is the input matrix of the measured values ​​of the observation vector X, and Y is the observation value matrix of the objective function f(X) obtained based on the input matrix I;

[0047] The measured values ​​of the observation vector X obtained in the historical time period T and the corresponding observed values ​​of the objective function f(X) are used as training data to determine the expression of the Gaussian process model g(X);

[0048] Set the initial trust domain T1 of the fault alarm threshold trust domain matrix of the historical time period T, and its expression is:

[0049]

[0050] Where n is the dimension of the monitoring indicator, f(X0) is the initial search point of the objective function f(X), and Δ1 is the initial radius of the fault alarm threshold trust threshold;

[0051] Based on the expressions of the objective function f(X) and the Gaussian process model g(X), the observation vector X at the sampling time t+(k+1)Δ is calculated. t The objective function observation value and the Gaussian process model predicted value Among them, sampling time t is the last sampling time of the historical time period T, Δ t is the sampling time interval, k is a natural number, and its initial value is 1;

[0052] According to the objective function observation and Gaussian process model prediction value and Calculate the ratio of the actual improvement of the observation vector to the predicted improvement ρ t , and its calculation formula is:

[0053]

[0054] According to the ratio The initial trust domain T1 of the fault alarm threshold combination matrix is ​​used to dynamically update the fault alarm threshold combination matrix, where:

[0055] when When the trust domain is expanded, Δ k+1 =γ e Δ k ;

[0056] when When keeping the trust region unchanged, Δ k+1 =Δ k ;

[0057] when When , the trust region is contracted, Δ k+1 =γ s Δ k ;

[0058] Where μ1 and μ2 are the thresholds for determining trust region updates, γ e is the expansion coefficient, γ e >1,γ s is the shrinkage coefficient, 0<γ s <1.

[0059] In this preferred implementation, by dynamically updating the trust domain of the alarm threshold based on historical data, it is possible to better adapt to the actual equipment operation situation, improve the accuracy of fault identification and reduce false alarms.

[0060] Preferably, the generating of the power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators includes:

[0061] When the state estimation value of the monitoring indicator in the state estimation matrix is ​​located in the corresponding fault alarm threshold trust domain matrix, determining that the alarm result of the monitoring indicator is in an alarm state, otherwise it is in a non-alarm state;

[0062] Output the power equipment alarm results based on the alarm results of n monitoring indicators.

[0063] The power equipment alarm method described in this preferred embodiment continuously updates the optimal memory matrix of the monitoring indicators and the state estimation values ​​corresponding to the monitoring indicators based on the historical measurement values ​​of the monitoring indicators set for the power equipment, thereby ensuring the mean regression and dynamic adjustment of the state estimation values ​​and the alarm threshold trust domain obtained based on the real-time measurement values ​​of the monitoring indicators acquired in real time, thereby greatly improving the accuracy and efficiency of the power equipment alarm.

[0064] Exemplary Devices

[0065] Figure 2 FIG. 1 is a schematic diagram of the structure of the power equipment alarm device according to a preferred embodiment of the present invention. Figure 2 As shown, the electric power equipment alarm device 200 described in this preferred embodiment includes:

[0066] The data acquisition module 201 is used to obtain the real-time measurement value of the monitoring index according to the set monitoring index, wherein the monitoring index includes the operation index of the substation digital meter and the substation environmental parameters;

[0067] A data calculation module 202, configured to calculate a state estimation value of the monitoring indicator according to the real-time measurement value and an optimal memory matrix dynamically updated based on the historical measurement value of the monitoring indicator, and generate a state estimation matrix;

[0068] The result output module 203 is used to generate an electric power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators.

[0069] Preferably, the device further comprises a first updating module, configured to:

[0070] When there are n monitoring indicators, the historical measurement values ​​of the n monitoring indicators at the sampling time are recorded as the observation vector X = [x1, x2, ..., x n ] T ;

[0071] For multiple sensors that collect measurement values ​​of n monitoring indicators, select n sensors with high trust scores to obtain historical measurement values ​​of the n monitoring indicators at m historical sampling moments, generate m observation vectors, and generate an initial memory matrix D(T) based on the m observation vectors, wherein the trust score is determined by the score in the score table preset according to expert experience, and T is a sampling period consisting of m sampling moments;

[0072] The initial memory matrix D(T) is calculated by using a sliding window update method, an exponentially weighted moving average method, a Kalman filter method and an incremental learning method to generate a corresponding optimized memory matrix, wherein a sliding window is used to limit the time range of historical measurement values, an exponentially weighted moving average method is used to smooth the influence of historical measurement values ​​at different sampling moments, a Kalman filter is used to predict and correct historical measurement values ​​of monitoring indicators, and the initial memory matrix is ​​adjusted in real time by incremental learning;

[0073] An optimal memory matrix is ​​generated according to the initial memory matrix and the optimized memory matrix.

[0074] Preferably, the first updating module generates an optimal memory matrix according to the initial memory matrix and the optimized memory matrix, wherein the calculation formula of the optimal memory matrix is:

[0075] D H (T+1)=γ1(T+1)*D w (T+1)+γ2(T+1)*D e(T+1)

[0076] +γ3(T+1)*D k (T+1)+γ4(T+1)*D l (T+1)

[0077]

[0078] Where D H (T+1) is the optimal memory matrix of sampling period T+1, D w (T+1), D e (T+1), D k (T+1) and D l (T+1) is the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method, γ1(T+1), γ2(T+1), γ3(T+1) and γ4(T+1) are the weight coefficients of the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method in calculating the optimal memory matrix, D j (T) represents the value of the jth column of the initial memory matrix D(T) in the sampling period T. The values ​​of i represent the sliding window update method, exponentially weighted moving average method, Kalman filter method and incremental learning method, respectively. It represents the value of the jth column in the sampling period T+1 when the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method are used respectively.

[0079] Preferably, the device further comprises a second updating module, configured to:

[0080] Let X be the observation vector composed of n monitoring indicators, the objective function f(X) be the fault alarm threshold distribution function of X, and the Gaussian process model g(X) be used to approximate the objective function. The posterior distribution of the Gaussian process model g(X) is:

[0081] g(X)~Ν(μ(X),σ 2 (X)

[0082] Where μ(X) is the mean function, σ 2 (X) is the covariance function, which represents the predicted value and uncertainty of the objective function f(X) respectively. The calculation formula is:

[0083] μ(X)=k(X,I)K -1 Y

[0084] σ 2 (X) = k(X,X)-k(X,I)K -1 k(I,X)

[0085] Where k(X,I), k(X,X) and k(X,I) are kernel functions, K is the covariance matrix, I is the input matrix of the measured values ​​of the observation vector X, and Y is the observation value matrix of the objective function f(X) obtained based on the input matrix I;

[0086] The measured values ​​of the observation vector X obtained in the historical time period T and the corresponding observed values ​​of the objective function f(X) are used as training data to determine the expression of the Gaussian process model g(X);

[0087] Set the initial trust domain T1 of the fault alarm threshold trust domain matrix of the historical time period T, and its expression is:

[0088]

[0089] Where n is the dimension of the monitoring indicator, f(X0) is the initial search point of the objective function f(X), and Δ1 is the initial radius of the fault alarm threshold trust threshold;

[0090] Based on the expressions of the objective function f(X) and the Gaussian process model g(X), the observation vector X at the sampling time t+(k+1)Δ is calculated. t The objective function observation value and the Gaussian process model predicted value Among them, sampling time t is the last sampling time of the historical time period T, Δ t is the sampling time interval, k is a natural number, and its initial value is 1;

[0091] According to the objective function observation and Gaussian process model prediction value and Calculate the ratio of the actual improvement of the observation vector to the predicted improvement ρ t , and its calculation formula is:

[0092]

[0093] According to the ratio The initial trust domain T1 of the fault alarm threshold combination matrix is ​​used to dynamically update the fault alarm threshold combination matrix, where:

[0094] when When the trust domain is expanded, Δ k+1 =γ e Δ k ;

[0095] when When keeping the trust region unchanged, Δ k+1 =Δ k ;

[0096] when When , the trust region is contracted, Δ k+1 =γ s Δ k ;

[0097] Where u1 and μ2 are the thresholds for determining trust region updates, γ e is the expansion coefficient, γ e >1,γ s is the shrinkage coefficient, 0<γ s <1.

[0098] Preferably, the result output module 203 generates a power equipment alarm result according to the state estimation matrix and a fault alarm threshold trust domain matrix dynamically updated based on historical measurement values ​​of the monitoring indicators, including:

[0099] When the state estimation value of the monitoring indicator in the state estimation matrix is ​​located in the corresponding fault alarm threshold trust domain matrix, determining that the alarm result of the monitoring indicator is in an alarm state, otherwise it is in a non-alarm state;

[0100] Output the power equipment alarm results based on the alarm results of n monitoring indicators.

[0101] The electric power equipment alarm device described in this preferred embodiment collects real-time measurement values ​​of monitoring indicators, and the steps of performing electric power equipment alarm based on the continuously updated optimal memory matrix and alarm threshold trust domain matrix are the same as the steps of the electric power equipment alarm method described in the present invention, and the technical effects achieved are also the same, which will not be repeated here.

[0102] Exemplary Electronic Devices

[0103] Figure 3 The electronic device according to the preferred embodiment of the present invention is a schematic diagram of the structure of the electronic device. The electronic device can be any one or both of the first device and the second device, or a stand-alone device independent of them, and the stand-alone device can communicate with the first device and the second device to receive the collected input signal from them. Figure 3 FIG. 1 is a block diagram of an electronic device according to an embodiment of the present disclosure. Figure 3 As shown, the electronic device includes one or more processors 301 and a memory 302 .

[0104] The processor 301 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0105] The memory 302 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 301 may run the program instructions to implement the energy consumption anomaly diagnosis method based on the enterprise energy consumption space of each disclosed embodiment described above and / or other desired functions. In one example, the electronic device may also include: an input device 303 and an output device 304, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0106] In addition, the input device 303 may also include, for example, a keyboard, a mouse, and the like.

[0107] The output device 304 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0108] Of course, to simplify, Figure 3 Only some of the components related to the present disclosure in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device may further include any other appropriate components.

[0109] Exemplary computer program products and computer-readable storage media

[0110] In addition to the above-mentioned methods and devices, an embodiment of the present disclosure may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the power equipment alarm method according to various embodiments of the present disclosure described in the above-mentioned "Exemplary Method" section of this specification.

[0111] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the disclosed embodiments, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0112] In addition, an embodiment of the present disclosure may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of the power equipment alarm method according to various embodiments of the present disclosure described in the above "Exemplary Method" section of this specification.

[0113] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable 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.

[0114] The basic principles of the present disclosure are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present disclosure. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, and are not limitations. The above details do not limit the present disclosure to the necessity of adopting the above specific details to be implemented.

[0115] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0116] The block diagrams of the devices, apparatuses, equipment, and systems involved in this disclosure are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including," "comprising," "having," and the like are open words, referring to "including but not limited to," and can be used interchangeably therewith. The words "or" and "and" used herein refer to the words "and / or," and can be used interchangeably therewith, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to," and can be used interchangeably therewith.

[0117] The method and apparatus of the present disclosure may be implemented in many ways. For example, the method and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present disclosure. Therefore, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

[0118] It should also be noted that in the apparatus, equipment and method of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present disclosure. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present disclosure. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown here, but to the widest scope consistent with the principles and novel features disclosed herein.

[0119] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for warning electric power equipment, characterized in that: The method comprises: According to the set monitoring indicators, real-time measurement values ​​of the monitoring indicators are obtained, wherein the monitoring indicators include operating indicators of digital meters of substations and environmental parameters of substations; Calculate the state estimation value of the monitoring indicator according to the real-time measurement value and the optimal memory matrix dynamically updated based on the historical measurement value of the monitoring indicator to generate a state estimation matrix; An electric power equipment alarm result is generated according to the state estimation matrix and a fault alarm threshold trust domain matrix that is dynamically updated based on historical measurement values ​​of the monitoring indicators.

2. The method according to claim 1, characterized in that The optimal memory matrix dynamically updated based on the proposed evaluation index value and the historical measurement value of the monitoring index is used to calculate the state estimation value of the monitoring index, and before generating the state estimation matrix, it also includes: When there are n monitoring indicators, the historical measurement values ​​of the n monitoring indicators at the sampling time are recorded as the observation vector X = [x1, x2, ..., x n ] T ; For multiple sensors that collect measurement values ​​of n monitoring indicators, select n sensors with high trust scores to obtain historical measurement values ​​of the n monitoring indicators at m historical sampling moments, generate m observation vectors, and generate an initial memory matrix D(T) based on the m observation vectors, wherein the trust score is determined by the score in the score table preset according to expert experience, and T is a sampling period consisting of m sampling moments; The initial memory matrix D(T) is calculated by using a sliding window update method, an exponentially weighted moving average method, a Kalman filter method and an incremental learning method to generate a corresponding optimized memory matrix, wherein a sliding window is used to limit the time range of historical measurement values, an exponentially weighted moving average method is used to smooth the influence of historical measurement values ​​at different sampling moments, a Kalman filter is used to predict and correct historical measurement values ​​of monitoring indicators, and the initial memory matrix is ​​adjusted in real time by incremental learning; An optimal memory matrix is ​​generated according to the initial memory matrix and the optimized memory matrix.

3. The method according to claim 2, characterized in that The optimal memory matrix is ​​generated according to the initial memory matrix and the optimized memory matrix, wherein the calculation formula of the optimal memory matrix is: D H (T+1)=γ1(T+1)*D w (T+1)+γ2(T+1)*D e (T+1) +γ3(T+1)*D k (T+1)+γ4(T+1)*D l (T+1) Where D H (T+1) is the optimal memory matrix of sampling period T+1, D w (T+1), D e (T+1), D k (T+1) and D l (T+1) is the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method, γ1(T+1), γ2(T+1), γ3(T+1) and γ4(T+1) are the weight coefficients of the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method in calculating the optimal memory matrix, D j (T) represents the value of the jth column of the initial memory matrix D(T) in the sampling period T. The values ​​of i represent the sliding window update method, exponentially weighted moving average method, Kalman filter method and incremental learning method, respectively. It represents the value of the jth column in the sampling period T+1 when the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method are used respectively.

4. The method according to claim 1, characterized in that: Before generating the power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators, the method further includes: Let X be the observation vector composed of n monitoring indicators, the objective function f(X) be the fault alarm threshold distribution function of X, and the Gaussian process model g(X) be used to approximate the objective function. The posterior distribution of the Gaussian process model g(X) is: g(X)~Ν(μ(X),σ 2 (X)) Where μ(X) is the mean function, σ 2 (X) is the covariance function, which represents the predicted value and uncertainty of the objective function f(X) respectively. The calculation formula is: μ(X)=k(X,I)K -1 Y σ 2 (X)=k(X,X)-k(X,I)K -1 k(I,X) Where k(X,I), k(X,X) and k(X,I) are kernel functions, K is the covariance matrix, I is the input matrix of the measured values ​​of the observation vector X, and Y is the observation value matrix of the objective function f(X) obtained based on the input matrix I; The measured values ​​of the observation vector X obtained in the historical time period T and the corresponding observed values ​​of the objective function f(X) are used as training data to determine the expression of the Gaussian process model g(X); Set the initial trust domain T1 of the fault alarm threshold trust domain matrix of the historical time period T, and its expression is: Where n is the dimension of the monitoring indicator, f(X0) is the initial search point of the objective function f(X), and Δ1 is the initial radius of the fault alarm threshold trust threshold; Based on the expressions of the objective function f(X) and the Gaussian process model g(X), the observation vector X at the sampling time t+(k+1)Δ is calculated. t The objective function observation value f(X t+(k+1)Δt ) and the Gaussian process model prediction value Among them, sampling time t is the last sampling time of the historical time period T, Δ t is the sampling time interval, k is a natural number, and its initial value is 1; According to the objective function observation and Gaussian process model prediction value and Calculate the ratio of the actual improvement of the observation vector to the predicted improvement ρ t , and its calculation formula is: According to the ratio The initial trust domain T1 of the fault alarm threshold combination matrix is ​​used to dynamically update the fault alarm threshold combination matrix, where: when When the trust domain is expanded, Δ k+1 =γ e Δ k ; when When keeping the trust region unchanged, Δ k+1 =Δ k ; when When Δk is shrunk, the trust region is +1 =γ s Δ k ; Where μ1 and μ2 are the thresholds for determining trust region updates, γ e is the expansion coefficient, γ e >1,γ s is the shrinkage coefficient, 0<γ s <1.

5. The method according to claim 1, characterized in that The generating of the power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators includes: When the state estimation value of the monitoring indicator in the state estimation matrix is ​​located in the corresponding fault alarm threshold trust domain matrix, determining that the alarm result of the monitoring indicator is in an alarm state, otherwise it is in a non-alarm state; Output the power equipment alarm results based on the alarm results of n monitoring indicators.

6. An electric power equipment alarm device, characterized in that: The device comprises: A data acquisition module, used to obtain real-time measurement values ​​of monitoring indicators according to set monitoring indicators, wherein the monitoring indicators include operating indicators of substation digital meters and substation environmental parameters; A data calculation module, used to calculate the state estimation value of the monitoring indicator according to the real-time measurement value and the optimal memory matrix dynamically updated based on the historical measurement value of the monitoring indicator, and generate a state estimation matrix; The result output module is used to generate an electric power equipment alarm result according to the state estimation matrix and the fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators.

7. The device according to claim 6, characterized in that The device also includes a first updating module, configured to: When there are n monitoring indicators, the historical measurement values ​​of the n monitoring indicators at the sampling time are recorded as the observation vector X = [x1, x2, ..., x n ] T ; For multiple sensors that collect measurement values ​​of n monitoring indicators, select n sensors with high trust scores to obtain historical measurement values ​​of the n monitoring indicators at m historical sampling moments, generate m observation vectors, and generate an initial memory matrix D(T) based on the m observation vectors, wherein the trust score is determined by the score in the score table preset according to expert experience, and T is a sampling period consisting of m sampling moments; The initial memory matrix D(T) is calculated by using a sliding window update method, an exponentially weighted moving average method, a Kalman filter method and an incremental learning method to generate a corresponding optimized memory matrix, wherein a sliding window is used to limit the time range of historical measurement values, an exponentially weighted moving average method is used to smooth the influence of historical measurement values ​​at different sampling moments, a Kalman filter is used to predict and correct historical measurement values ​​of monitoring indicators, and the initial memory matrix is ​​adjusted in real time by incremental learning; An optimal memory matrix is ​​generated according to the initial memory matrix and the optimized memory matrix.

8. The device according to claim 7, characterized in that The first updating module generates an optimal memory matrix according to the initial memory matrix and the optimized memory matrix, wherein the calculation formula of the optimal memory matrix is: D H (T+1)=γ1(T+1)*D w (T+1)+γ2(T+1)*D e (T+1) +γ3(T+1)*D k (T+1)+γ4(T+1)*D l (T+1) Where D H (T+1) is the optimal memory matrix of sampling period T+1, D w (T+1), D e (T+1), D k (T+1) and D l (T+1) is the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method, γ1(T+1), γ2(T+1), γ3(T+1) and γ4(T+1) are the weight coefficients of the optimized memory matrix generated by the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method in calculating the optimal memory matrix, D j (T) represents the value of the jth column of the initial memory matrix D(T) in the sampling period T. The values ​​of i represent the sliding window update method, exponentially weighted moving average method, Kalman filter method and incremental learning method, respectively. It represents the value of the jth column in the sampling period T+1 when the sliding window update method, exponential weighted moving average method, Kalman filter method and incremental learning method are used respectively.

9. The device according to claim 6, characterized in that The device also includes a second updating module, configured to: Let X be the observation vector composed of n monitoring indicators, the objective function f(X) be the fault alarm threshold distribution function of X, and the Gaussian process model g(X) be used to approximate the objective function. The posterior distribution of the Gaussian process model g(X) is: g(X)~Ν(μ(X),σ 2 (X)) Where μ(X) is the mean function, σ 2 (X) is the covariance function, which represents the predicted value and uncertainty of the objective function f(X) respectively. The calculation formula is: μ(X)=k(X,I)K -1 Y σ 2 (X)=k(X,X)-k(X,I)K -1 k(I,X) Where k(X,I), k(X,X) and k(X,I) are kernel functions, K is the covariance matrix, I is the input matrix of the measured values ​​of the observation vector X, and Y is the observation value matrix of the objective function f(X) obtained based on the input matrix I; The measured values ​​of the observation vector X obtained in the historical time period T and the corresponding observed values ​​of the objective function f(X) are used as training data to determine the expression of the Gaussian process model g(X); Set the initial trust domain T1 of the fault alarm threshold trust domain matrix of the historical time period T, and its expression is: Where n is the dimension of the monitoring indicator, f(X0) is the initial search point of the objective function f(X), and Δ1 is the initial radius of the fault alarm threshold trust threshold; Based on the expressions of the objective function f(X) and the Gaussian process model g(X), the observation vector X at the sampling time t+(k+1)Δ is calculated. t The objective function observation value and the Gaussian process model predicted value Among them, sampling time t is the last sampling time of the historical time period T, Δ t is the sampling time interval, k is a natural number, and its initial value is 1; According to the objective function observation and Gaussian process model prediction value and Calculate the ratio of the actual improvement of the observation vector to the predicted improvement ρ t , and its calculation formula is: According to the ratio The initial trust domain T1 of the fault alarm threshold combination matrix is ​​used to dynamically update the fault alarm threshold combination matrix, where: when When the trust domain is expanded, Δ k+1 =γ e Δ k ; when When keeping the trust region unchanged, Δ k+1 =Δ k ; when When , the trust region is contracted, Δ k+1 =γ s Δ k ; Where μ1 and μ2 are the thresholds for determining trust region updates, γ e is the expansion coefficient, γ e >1,γ s is the shrinkage coefficient, 0<γ s <1.

10. The device according to claim 6, characterized in that The result output module generates a power equipment alarm result according to the state estimation matrix and a fault alarm threshold trust domain matrix dynamically updated based on the historical measurement values ​​of the monitoring indicators, including: When the state estimation value of the monitoring indicator in the state estimation matrix is ​​located in the corresponding fault alarm threshold trust domain matrix, determining that the alarm result of the monitoring indicator is in an alarm state, otherwise it is in a non-alarm state; Output the power equipment alarm results based on the alarm results of n monitoring indicators.

11. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 5.

12. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 5.

Images