Monitoring method, device and equipment of power transformation equipment and storage medium

Abstract

The invention relates to the technical field of power transformation equipment, and discloses a power transformation equipment monitoring method and device, equipment and a storage medium, and the method comprises the steps: obtaining the real-time multivariate time sequence data of the power transformation equipment; preprocessing the real-time multivariate time sequence data to obtain processed data; performing exception analysis on the processed data to obtain an exception analysis result; and performing abnormity early warning according to an abnormity analysis result. According to the embodiment of the invention, by collecting and processing the multivariate time sequence data of the power transformation equipment in real time, comprehensive and real-time monitoring of the power transformation equipment is realized, and the monitoring efficiency is remarkably improved. In addition, the abnormal condition of the power transformation equipment can be accurately identified, the risk of false alarm and missing alarm is reduced, and the monitoring accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of substation equipment, and in particular to a monitoring method, device, equipment and storage medium for substation equipment. Background Art

[0002] With the complexity and intelligence of power systems, the stable operation of substation equipment has become particularly important. Substation equipment is a key component of the power system, responsible for voltage conversion, current distribution and protection. In modern power systems, failures in substation equipment will not only cause local power outages, but may also trigger chain reactions and affect the stability of the entire power grid. In related technologies, when monitoring substation equipment, it often relies on the experience of operation and maintenance personnel, which has the problems of low monitoring efficiency and low accuracy. Summary of the invention

[0003] Based on this, it is necessary to propose a monitoring method, device, equipment and storage medium for substation equipment in order to address the problems of low monitoring efficiency and low accuracy in related technologies when monitoring substation equipment.

[0004] In a first aspect, an embodiment of the present application provides a method for monitoring a substation, the method comprising:

[0005] Acquire real-time multivariate time series data of substation equipment, where the real-time multivariate time series data includes one or more of electrical parameters, equipment operation data, operation data, and equipment environment data;

[0006] Preprocess the real-time multivariate time series data to obtain processed data;

[0007] Perform abnormal analysis on the processed data to obtain abnormal analysis results;

[0008] Issue abnormal warnings based on abnormal analysis results.

[0009] In a second aspect, an embodiment of the present application provides a monitoring device for a substation, the device comprising:

[0010] An acquisition module is used to acquire real-time multivariate time series data of the substation equipment, where the real-time multivariate time series data includes one or more of electrical parameters, equipment operation data, operation data, and equipment environment data;

[0011] A preprocessing module is used to preprocess the real-time multivariate time series data to obtain processed data;

[0012] An analysis module is used to perform an abnormal analysis on the processed data and obtain an abnormal analysis result;

[0013] The early warning module is used to issue an abnormal early warning according to the abnormal analysis results. The acquisition module is used to acquire the real-time multivariate time series data of the substation equipment. The real-time multivariate time series data includes: one or more of electrical parameters, equipment operation data, operation data, and equipment environment data;

[0014] A preprocessing module is used to preprocess the real-time multivariate time series data to obtain processed data;

[0015] An analysis module is used to perform an abnormal analysis on the processed data and obtain an abnormal analysis result;

[0016] The early warning module is used to issue abnormal early warnings based on abnormal analysis results.

[0017] In a third aspect, an embodiment of the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0018] Acquire real-time multivariate time series data of substation equipment, where the real-time multivariate time series data includes one or more of electrical parameters, equipment operation data, operation data, and equipment environment data;

[0019] Preprocess the real-time multivariate time series data to obtain processed data;

[0020] Perform abnormal analysis on the processed data to obtain abnormal analysis results;

[0021] Issue abnormal warnings based on abnormal analysis results.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor performs the following steps:

[0023] Acquire real-time multivariate time series data of substation equipment, where the real-time multivariate time series data includes one or more of electrical parameters, equipment operation data, operation data, and equipment environment data;

[0024] Preprocess the real-time multivariate time series data to obtain processed data;

[0025] Perform abnormal analysis on the processed data to obtain abnormal analysis results;

[0026] Issue abnormal warnings based on abnormal analysis results.

[0027] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: the embodiments of the present application obtain real-time multivariate time series data of the substation equipment, pre-process the real-time multivariate time series data to obtain processed data, perform abnormal analysis on the processed data to obtain abnormal analysis results, and issue abnormal warnings based on the abnormal analysis results. The embodiments of the present application achieve comprehensive and real-time monitoring of the substation equipment by real-time acquisition and processing of multivariate time series data of the substation equipment, significantly improving the monitoring efficiency. In addition, the abnormal conditions of the substation equipment can be accurately identified, reducing the risk of false alarms and missed alarms, and improving the monitoring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0029] in:

[0030] Figure 1 is a flow chart of a method for monitoring a power substation in one embodiment;

[0031] Figure 2 is a structural block diagram of a monitoring device for a power transformation device in one embodiment;

[0032] Figure 3 FIG. 4 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work are protected by the present application.

[0034] It should be noted that the terms "include", "comprises" and "have" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, terminal, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices. In the claims, specification and drawings of the present application, relational terms such as "first" and "second" are merely used to distinguish one entity / operation / object from another entity / operation / object, and do not necessarily require or imply any such real-time relationship or order between these entities / operations / objects.

[0035] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0036] With the complexity and intelligence of power systems, the stable operation of substation equipment has become particularly important. Substation equipment is a key component of the power system, responsible for voltage conversion, current distribution and protection. In modern power systems, failures in substation equipment will not only cause local power outages, but may also trigger chain reactions and affect the stability of the entire power grid. In related technologies, when monitoring substation equipment, it often relies on the experience of operation and maintenance personnel, which has the problems of low monitoring efficiency and low accuracy.

[0037] In view of this, the embodiment of the present application realizes comprehensive and real-time monitoring of substation equipment by real-time collection and processing of multivariate time series data of substation equipment, significantly improving monitoring efficiency. In addition, it can also accurately identify abnormal conditions of substation equipment, reduce the risk of false alarms and missed alarms, and improve monitoring accuracy.

[0038] In order to illustrate the technical solution of the present application, a specific embodiment is provided below for illustration.

[0039] Figure 1 A schematic diagram of the implementation process of a monitoring method for substation equipment provided in an embodiment of the present application is shown. The method can be applied to computer equipment, specifically smart phones, tablet computers, laptops, ultra-mobile personal computers (UMPCs), netbooks, etc.

[0040] Specifically, the above-mentioned monitoring method for substation equipment may include the following steps S101 to S104.

[0041] Step S101, obtaining real-time multivariate time series data of a substation.

[0042] Among them, real-time multivariate time series data refers to various types of data with time series characteristics generated by substation equipment during operation, which may include one or more of electrical parameters, equipment operation data, operation data, and equipment environment data. Substation equipment is equipment used in power systems to transform voltage, distribute electrical energy, and control electrical energy, such as transformers, circuit breakers, and disconnectors.

[0043] In an embodiment of the present application, a computer device may establish an electrical connection with a substation or a sensor on the substation to obtain real-time multivariate time series data of the substation. Various sensors and monitoring devices, such as current transformers, voltage transformers, temperature sensors, vibration sensors, cameras, etc., may be installed on the substation to collect electrical parameters, equipment operation data, operation data, equipment environment data, etc. in real time. A data acquisition system may be established to transmit the data collected by the sensors and monitoring devices to a data center or cloud platform by wire or wireless means. In the data center or cloud platform, the data from different sensors and monitoring devices are integrated to form a real-time multivariate time series data set and sent to the computer device.

[0044] Step S102, preprocessing the real-time multivariate time series data to obtain processed data.

[0045] In an embodiment of the present application, a computer device may pre-process the original real-time multivariate time series data, which may include data cleaning, data organization, data conversion, data dimensionality reduction, etc., to improve data quality, reduce noise interference, and provide more accurate data input for subsequent abnormality analysis.

[0046] Specifically, computer equipment can use data cleaning tools or algorithms to remove invalid data (such as missing values, outliers), duplicate data, etc. to ensure the accuracy and completeness of the data. Data can also be sorted by time series to ensure the time sequence of the data. Data can also be standardized, normalized, discretized, and other transformations according to analysis requirements to improve analysis efficiency and accuracy. Data can also be reduced in dimension using methods such as principal component analysis (PCA) and linear discriminant analysis (LDA) to reduce data redundancy and computational complexity.

[0047] Step S103, performing an abnormality analysis on the processed data to obtain an abnormality analysis result.

[0048] The abnormality analysis result is a conclusion or result on whether there is an abnormality in the substation equipment, which can be an abnormality score, abnormality label or other forms of output.

[0049] In an embodiment of the present application, the computer device can use statistical methods (such as mean, variance analysis), machine learning algorithms (such as clustering, classification, regression, etc.), etc. to conduct in-depth analysis of the preprocessed data, identify abnormal patterns or behaviors, and thus obtain abnormal analysis results.

[0050] Step S104: issue an abnormal warning based on the abnormal analysis result.

[0051] In an implementation manner of the present application, when the abnormal analysis result reaches a preset threshold or meets specific conditions, the computer device can trigger an early warning mechanism and send a warning signal to the operation and maintenance personnel, so as to promptly remind the operation and maintenance personnel to pay attention to the abnormal situation of the substation equipment and take corresponding measures to deal with it, so as to prevent the fault from expanding or triggering a chain reaction.

[0052] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: the embodiments of the present application obtain real-time multivariate time series data of the substation equipment, pre-process the real-time multivariate time series data to obtain processed data, perform abnormal analysis on the processed data to obtain abnormal analysis results, and issue abnormal warnings based on the abnormal analysis results. The embodiments of the present application achieve comprehensive and real-time monitoring of the substation equipment by real-time acquisition and processing of multivariate time series data of the substation equipment, significantly improving the monitoring efficiency. In addition, the abnormal conditions of the substation equipment can be accurately identified, reducing the risk of false alarms and missed alarms, and improving the monitoring accuracy.

[0053] In some implementations of the present application, an abnormality analysis is performed on the processed data to obtain an abnormality analysis result, which may specifically include steps S401 to S404.

[0054] Step S401, performing data distribution analysis on real-time multivariate time series data to obtain a first abnormality analysis result.

[0055] Among them, data distribution analysis refers to the analysis of the distribution characteristics of data to identify abnormal values, abnormal patterns or abnormal changes in data distribution.

[0056] In an embodiment of the present application, a computer device may perform data distribution analysis on real-time multivariate time series data to obtain a first abnormality analysis result.

[0057] In some specific implementations of the present application, data distribution analysis is performed on real-time multivariate time series data to obtain a first abnormality analysis result, which may specifically include steps S501 to S503.

[0058] Step S501, using the LSTM network to perform contextual anomaly analysis on real-time multivariate time series data to obtain contextual anomaly analysis results.

[0059] Among them, the Long Short-Term Memory (LSTM) network is a special recurrent neural network (RNN) that can learn long-term dependencies. The LSTM network solves the gradient vanishing or gradient exploding problems that are prone to occur in traditional RNNs when processing long sequence data by introducing mechanisms such as input gates, forget gates, and output gates. Contextual anomalies refer to the situation in which a data point in time series data may appear normal alone, but appears abnormal when considering its context (i.e., previous and subsequent data points).

[0060] In the implementation of the present application, the computer device can input new real-time multivariate time series data into the trained LSTM model, and the LSTM model outputs the data points that appear normal individually but abnormal in the entire sequence, which are predicted based on the context information. These abnormal data points are then scored in combination with the context anomaly scoring formula to obtain the context anomaly analysis results.

[0061] Specifically, the context anomaly scoring formula can be:

[0062]

[0063] Among them, score(x) 1 is the context anomaly score, and its superscript is 1, indicating that it corresponds to the first scoring formula in the implementation of the present application. x represents an actual data point or data vector. Represents LSTM network prediction data. μ train Represents the standard deviation of the training set data used by the LSTM network.

[0064] Step S502: performing point anomaly analysis on the real-time multivariate time series data based on a point anomaly scoring algorithm to obtain a point anomaly analysis result.

[0065] Among them, point anomaly refers to a single data point in time series data that deviates significantly from the normal range.

[0066] In an embodiment of the present application, the computer device can calculate the anomaly score of each data point using the point anomaly score formula based on the standard deviation and mean of the data set, directly evaluate the degree of anomaly of each data point, and thus obtain a point anomaly analysis result.

[0067] Specifically, the context anomaly scoring formula can be:

[0068]

[0069] Among them, score(x) 2 is the point anomaly score, and its superscript is 2, indicating that it corresponds to the second scoring formula in the implementation of this application. x represents the actual data point or data vector. μ is the mean vector. Σ -1 is the inverse matrix of the covariance matrix, and χ is the set threshold.

[0070] Step S503: combining the point anomaly analysis result and the context anomaly analysis result to obtain a first anomaly analysis result.

[0071] In an implementation manner of the present application, a computer device may fuse the context anomaly analysis results and the point anomaly analysis results, and specifically may adopt methods such as weighted averaging and voting mechanisms, so as to determine whether the data is abnormal based on the fused results.

[0072] The implementation method of the present application comprehensively utilizes context information and the degree of abnormality of a single data point to improve the accuracy and robustness of anomaly detection, and is suitable for complex and changeable real-time multivariate time series data anomaly detection scenarios.

[0073] Step S402, performing sequence mining analysis on the real-time multivariate time series data to obtain a second anomaly analysis result.

[0074] Among them, sequence mining analysis is used to discover patterns, trends and cyclical changes in time series data.

[0075] In an embodiment of the present application, a computer device may perform sequence mining analysis on real-time multivariate time series data to obtain a second anomaly analysis result to discover time patterns, trends, and periodic changes in the data to obtain a second anomaly analysis result.

[0076] In some specific implementations of the present application, sequence mining analysis is performed on real-time multivariate time series data to obtain a second abnormality analysis result, which may specifically include steps S601 to S603.

[0077] Step S601, obtaining multiple groups of historical multivariate time series data.

[0078] Among them, historical multivariate time series data refers to the stored multidimensional time series data generated by substation equipment during its past operation.

[0079] In the implementation of the present application, the computer device can extract the operation data of the substation equipment in the past period of time from the database or storage system. These data may include parameter values ​​such as current, voltage, temperature, etc. at multiple time points, thereby providing benchmark data for subsequent comparison and analysis.

[0080] Step S602, assembling multiple groups of historical multivariate time series data into a data set.

[0081] In the implementation of the present application, the computer device can sort and organize the multiple sets of historical data obtained to form a set of data containing multiple time periods. This can be achieved through data preprocessing and cleaning steps to ensure the accuracy and consistency of the data and facilitate subsequent comparison and analysis. The data set can be compared with the real-time data as a whole, making it easier to identify abnormal changes in the device.

[0082] Step S603, comparing the real-time multivariate time series data with the data set to obtain a second abnormality analysis result.

[0083] In an embodiment of the present application, a computer device may use an appropriate algorithm or model (such as a machine learning model, a time series analysis algorithm, etc.) to compare real-time data with a data set. Specifically, it may include calculating similarity, distance, or other metrics to evaluate the difference between real-time data and historical data. To identify abnormal behavior in real-time data. The computer device may output a conclusion or result about whether the device is abnormal based on the comparison results. This result may be a simple abnormal label (such as "normal", "abnormal"), an abnormal score (a numerical value indicating the degree of abnormality), or other forms of output.

[0084] Specifically, the sequence mining scoring formula can be:

[0085]

[0086] Among them, score(x) 3 is the sequence mining score, and its superscript is 3, indicating that it corresponds to the third scoring formula in the implementation of this application. i Represents the i-th data in the data set. ω i represents the abnormal index of the data. τ represents the coverage boundary of the data. d(x,Λ i ) represents the collected data x and the data Λ in the decision set i The Mahalanobis distance.

[0087] Specifically, the calculation method of the abnormal index is as follows:

[0088]

[0089] in, Indicates the abnormality degree of decision data i.

[0090] By comparing real-time data and historical data, the implementation methods of the present application can more accurately identify abnormal behavior of a device and reduce false positives and false negatives.

[0091] Step S403, performing relationship mining analysis on the real-time multivariate time series data to obtain a third abnormality analysis result.

[0092] Among them, relation mining analysis is used to discover the relationship between variables in the data set, including correlation, causal relationship and association rules. In substation equipment monitoring, relation mining analysis can help identify the mutual influence between different equipment or different parameters, and provide clues for anomaly detection and fault diagnosis.

[0093] In the implementation manner of the present application, the computer equipment can perform relationship mining and analysis on real-time multivariate time series data, analyze the complex relationship between variables by mining the relationship between substation equipment, and identify abnormal relationship patterns, thereby improving the effect of multi-dimensional time series anomaly detection.

[0094] In some specific implementations of the present application, relationship mining analysis is performed on real-time multivariate time series data to obtain a third abnormal analysis result, which may specifically include steps S701 to S705.

[0095] Step S701, obtaining the connection relationship between the substation equipment.

[0096] Among them, the connection relationship refers to the mutual relationship between substation equipment due to electrical connection or functional relationship.

[0097] In the implementation manner of the present application, the computer device can determine the electrical connection or functional dependency between the various substation devices by consulting database records or real-time monitoring data, and provide basic information for constructing a relationship skeleton diagram.

[0098] Step S702: construct a relationship skeleton diagram between substation equipment according to the connection relationship.

[0099] Among them, the relational skeleton diagram is a graphical representation method used to show the connection relationship between substation equipment.

[0100] In an implementation manner of the present application, a computer device may use nodes and edges in graph theory to represent substation equipment and the connection relationships between them. Specifically, a relationship skeleton diagram may be constructed using graphical tools or programming methods to intuitively display the relationship between substation equipment to facilitate subsequent analysis.

[0101] Step S703, obtaining the collected data of the neighbor nodes in the relationship skeleton graph.

[0102] Among them, neighbor nodes are other nodes directly connected to the current node in the graph structure.

[0103] In an embodiment of the present application, a computer device may collect data of neighboring nodes of each node in a relationship skeleton graph in real time or periodically through a data acquisition system to provide data support for calculating a predicted value of a current node.

[0104] Step S704, calculating the predicted value of the current node in the relationship skeleton graph according to the collected data of the neighboring nodes in the relationship skeleton graph.

[0105] The predicted value is a prediction of the future state or current state of the current node based on historical data or data of neighbor nodes in the relationship skeleton graph.

[0106] In an embodiment of the present application, a computer device may utilize a machine learning algorithm (such as time series prediction, regression analysis, etc.) to predict the state of a current node based on data from neighboring nodes, thereby providing a basis for subsequent anomaly detection.

[0107] Step S705: Compare the predicted value with the collected data to obtain a third abnormality analysis result.

[0108] In the implementation of the present application, the computer device can calculate the difference between the predicted value and the actual collected data, set a threshold to determine whether there is an abnormality. By comparing the predicted value with the actual value, potential abnormalities or faults can be discovered, thereby improving the accuracy of the monitoring system.

[0109] The implementation method of the present application uses relationship mining analysis to consider not only the data of a single substation device, but also its relationship with other devices, so as to more accurately identify anomalies.

[0110] Specifically, the relationship mining scoring formula can be:

[0111]

[0112] Wherein, N is the number of substation equipment in the relational skeleton diagram. is the predicted value. i To collect data.

[0113] Specifically, the calculation method of the predicted value is:

[0114]

[0115] Where K is the number of attention heads in the attention network and σ is the attention coefficient. is the node feature.

[0116] Specifically, the calculation method of the attention coefficient is:

[0117]

[0118] Where i represents a substation. j represents another substation. W is a learnable weight matrix. T is a learnable attention parameter vector. i and h jIndicates the data collected by each node. ∥ indicates the splicing operation. N i are all the devices associated with substation i. exp represents the exponential function. tan represents the tangent function.

[0119] Step S404: combining the first abnormality analysis result, the second abnormality analysis result and the third abnormality analysis result to obtain an abnormality analysis result.

[0120] In an implementation manner of the present application, after obtaining the first abnormality analysis result, the second abnormality analysis result and the third abnormality analysis result, the computer device can integrate the three to obtain a total abnormality analysis result to accurately reflect the abnormal situation of the substation equipment.

[0121] In some specific implementations of the present application, relationship mining analysis is performed on real-time multivariate time series data to obtain a third abnormal analysis result, which may specifically include step S801 and step S802.

[0122] Step S801, assigning weights to the first abnormality analysis result, the second abnormality analysis result, and the third abnormality analysis result.

[0123] In the implementation of the present application, the computer device can assign different weight values ​​to the first, second, and third abnormal analysis results according to factors such as the accuracy, stability, and importance of each monitoring means. For example, if the temperature anomaly has the greatest impact on the operation of the substation equipment, a higher weight can be assigned to the first abnormal analysis result to ensure that the importance of the abnormal conditions revealed by each monitoring means can be more accurately reflected in the comprehensive judgment, thereby improving the accuracy of the final abnormal analysis result.

[0124] Step S802, calculating an abnormality analysis result according to the first abnormality analysis result, the second abnormality analysis result, the third abnormality analysis result and the corresponding weights.

[0125] In an embodiment of the present application, the computer device may multiply each abnormal analysis result by its corresponding weight, and then add the products to obtain the final abnormal analysis result. The formula may be expressed as: abnormal analysis result = first abnormal analysis result × first weight + second abnormal analysis result × second weight + third abnormal analysis result × third weight. By taking a weighted average approach, the results of multiple monitoring methods are comprehensively considered to obtain a comprehensive abnormal judgment, thereby improving the reliability and accuracy of the judgment.

[0126] In some implementations of the present application, an abnormality warning is performed based on the abnormality analysis result, which may specifically include steps S901 to S903.

[0127] Step S901, determining the warning level corresponding to the abnormal analysis result.

[0128] In the implementation of the present application, the computer device can compare the value or classification of the abnormal analysis result with the preset warning level standard to determine the warning level corresponding to the abnormality. For example, if the abnormal analysis result exceeds the normal range by 5%, it may be determined as a slight warning; if it exceeds 20%, it is determined as a moderate warning; if it exceeds 50% or more, it is determined as a severe warning. The implementation of the present application converts the abstract abnormal analysis results into specific warning levels, which is easy to understand and deal with.

[0129] Step S902: Generate a corresponding warning strategy according to the warning level.

[0130] In the implementation mode of the present application, the computer device can select the corresponding strategy from the preset warning strategy library according to the warning level. These strategies may include sending text messages, emails or APP push messages to operation and maintenance personnel, instructing them to conduct on-site inspections, shutdowns for maintenance or emergency treatment. The implementation mode of the present application can provide targeted response measures for abnormalities of different levels to ensure that abnormalities can be handled in a timely and effective manner to prevent the situation from escalating.

[0131] Step S903: Perform abnormal warning according to the warning strategy.

[0132] In the implementation mode of the present application, the computer device can send warning information to relevant personnel through appropriate communication channels according to the warning strategy, reminding them to pay attention to abnormal situations and take corresponding actions according to the warning strategy.

[0133] Figure 2 The schematic diagram of the structure of a monitoring device for a substation device provided in an embodiment of the present application is shown. The monitoring device 2 for a substation device can be configured on a computer device. Specifically, the monitoring device 2 for a substation device can include:

[0134] An acquisition module 201 is used to acquire real-time multivariate time series data of a substation device, where the real-time multivariate time series data includes one or more of electrical parameters, device operation data, operation data, and device environment data;

[0135] A preprocessing module 202 is used to preprocess the real-time multivariate time series data to obtain processed data;

[0136] The analysis module 203 is used to perform an abnormality analysis on the processed data to obtain an abnormality analysis result;

[0137] The warning module 204 is used to issue an abnormality warning according to the abnormality analysis result.

[0138] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: the embodiments of the present application obtain real-time multivariate time series data of the substation equipment, pre-process the real-time multivariate time series data to obtain processed data, perform abnormal analysis on the processed data to obtain abnormal analysis results, and issue abnormal warnings based on the abnormal analysis results. The embodiments of the present application achieve comprehensive and real-time monitoring of the substation equipment by real-time acquisition and processing of multivariate time series data of the substation equipment, significantly improving the monitoring efficiency. In addition, the abnormal conditions of the substation equipment can be accurately identified, reducing the risk of false alarms and missed alarms, and improving the monitoring accuracy.

[0139] In some implementations of the present application, the above analysis module 203 may also be used to:

[0140] Perform data distribution analysis on the real-time multivariate time series data to obtain a first abnormal analysis result;

[0141] Perform sequence mining analysis on real-time multivariate time series data to obtain the second anomaly analysis result;

[0142] Perform relationship mining analysis on real-time multivariate time series data to obtain the third anomaly analysis result;

[0143] The first abnormality analysis result, the second abnormality analysis result and the third abnormality analysis result are combined to obtain an abnormality analysis result.

[0144] In some implementations of the present application, the above analysis module 203 may also be used to:

[0145] Use LSTM network to perform contextual anomaly analysis on real-time multivariate time series data to obtain contextual anomaly analysis results;

[0146] Based on the point anomaly scoring algorithm, point anomaly analysis is performed on real-time multivariate time series data to obtain point anomaly analysis results;

[0147] The point anomaly analysis result and the context anomaly analysis result are combined to obtain a first anomaly analysis result.

[0148] In some implementations of the present application, the above analysis module 203 may also be used to:

[0149] Obtain multiple sets of historical multivariate time series data;

[0150] Combine multiple groups of historical multivariate time series data into a data set;

[0151] Compare the real-time multivariate time series data with the data set to obtain the second anomaly analysis result

[0152] In some implementations of the present application, the above analysis module 203 may also be used to:

[0153] Obtain the connection relationship between substation equipment;

[0154] Construct the relationship skeleton diagram between substation equipment according to the connection relationship;

[0155] Get the collected data of neighbor nodes in the relationship skeleton graph;

[0156] Calculate the predicted value of the current node in the relational skeleton graph based on the collected data of the neighboring nodes in the relational skeleton graph;

[0157] The predicted value is compared with the collected data to obtain the third abnormality analysis result.

[0158] In some implementations of the present application, the above analysis module 203 may also be used to:

[0159] assigning weights to the first abnormal analysis result, the second abnormal analysis result, and the third abnormal analysis result;

[0160] The abnormality analysis result is calculated according to the first abnormality analysis result, the second abnormality analysis result, the third abnormality analysis result and the corresponding weights.

[0161] In some implementations of the present application, the warning module 204 is further used to:

[0162] Determine the warning level corresponding to the abnormal analysis results;

[0163] Generate corresponding warning strategies according to the warning level;

[0164] Issue abnormal warnings based on warning strategies.

[0165] Figure 3 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 3 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor may implement the monitoring method for the substation. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor may implement the monitoring method for the substation. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0166] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps:

[0167] Acquire real-time multivariate time series data of substation equipment, where the real-time multivariate time series data includes one or more of electrical parameters, equipment operation data, operation data, and equipment environment data;

[0168] Preprocess the real-time multivariate time series data to obtain processed data;

[0169] Perform abnormal analysis on the processed data to obtain abnormal analysis results;

[0170] Issue abnormal warnings based on abnormal analysis results.

[0171] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: the embodiments of the present application obtain real-time multivariate time series data of the substation equipment, pre-process the real-time multivariate time series data to obtain processed data, perform abnormal analysis on the processed data to obtain abnormal analysis results, and issue abnormal warnings based on the abnormal analysis results. The embodiments of the present application achieve comprehensive and real-time monitoring of the substation equipment by real-time acquisition and processing of multivariate time series data of the substation equipment, significantly improving the monitoring efficiency. In addition, the abnormal conditions of the substation equipment can be accurately identified, reducing the risk of false alarms and missed alarms, and improving the monitoring accuracy.

[0172] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor performs the following steps:

[0173] Acquire real-time multivariate time series data of substation equipment, where the real-time multivariate time series data includes one or more of electrical parameters, equipment operation data, operation data, and equipment environment data;

[0174] Preprocess the real-time multivariate time series data to obtain processed data;

[0175] Perform abnormal analysis on the processed data to obtain abnormal analysis results;

[0176] Issue abnormal warnings based on abnormal analysis results.

[0177] The beneficial effects of the embodiments of the present application compared with the prior art are as follows: the embodiments of the present application obtain real-time multivariate time series data of the substation equipment, pre-process the real-time multivariate time series data to obtain processed data, perform abnormal analysis on the processed data to obtain abnormal analysis results, and issue abnormal warnings based on the abnormal analysis results. The embodiments of the present application achieve comprehensive and real-time monitoring of the substation equipment by real-time acquisition and processing of multivariate time series data of the substation equipment, significantly improving the monitoring efficiency. In addition, the abnormal conditions of the substation equipment can be accurately identified, reducing the risk of false alarms and missed alarms, and improving the monitoring accuracy.

[0178] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0179] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0180] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0181] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0182] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0183] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0184] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A monitoring method for substation equipment, characterized in that: The method comprises: Acquire real-time multivariate time series data of the substation equipment, wherein the real-time multivariate time series data includes one or more of electrical parameters, equipment operation data, operation data, and equipment environment data; Preprocessing the real-time multivariate time series data to obtain processed data; Performing an abnormality analysis on the processed data to obtain an abnormality analysis result; An abnormality warning is issued according to the abnormality analysis result.

2. The monitoring method for substation equipment according to claim 1, characterized in that: The performing abnormality analysis on the processed data to obtain abnormality analysis results includes: Performing data distribution analysis on the real-time multivariate time series data to obtain a first abnormality analysis result; Performing sequence mining analysis on the real-time multivariate time series data to obtain a second abnormal analysis result; Performing relationship mining analysis on the real-time multivariate time series data to obtain a third abnormal analysis result; The abnormality analysis result is obtained by combining the first abnormality analysis result, the second abnormality analysis result and the third abnormality analysis result.

3. The monitoring method for substation equipment according to claim 2, characterized in that: The performing data distribution analysis on the real-time multivariate time series data to obtain a first abnormality analysis result includes: Using an LSTM network to perform context anomaly analysis on the real-time multivariate time series data to obtain a context anomaly analysis result; Performing point anomaly analysis on the real-time multivariate time series data based on a point anomaly scoring algorithm to obtain a point anomaly analysis result; The point anomaly analysis result and the context anomaly analysis result are combined to obtain a first anomaly analysis result.

4. The monitoring method for substation equipment according to claim 2, characterized in that: The performing sequence mining analysis on the real-time multivariate time series data to obtain a second abnormal analysis result includes: Obtain multiple sets of historical multivariate time series data; Combining the multiple groups of historical multivariate time series data into a data set; The real-time multivariate time series data is compared with the data set to obtain the second anomaly analysis result.

5. The monitoring method for substation equipment according to claim 2, characterized in that: The performing relationship mining analysis on the real-time multivariate time series data to obtain a third abnormal analysis result includes: Obtain the connection relationship between substation equipment; Constructing a relationship skeleton diagram between the power transformation equipment according to the connection relationship; Obtaining collected data of neighbor nodes in the relationship skeleton graph; Calculating a predicted value of a current node in the relationship skeleton graph based on the collected data of neighboring nodes in the relationship skeleton graph; The predicted value is compared with the collected data to obtain the third abnormality analysis result.

6. The monitoring method for substation equipment according to claim 2, characterized in that: The combining the first abnormality analysis result, the second abnormality analysis result and the third abnormality analysis result to obtain the abnormality analysis result includes: assigning weights to the first abnormality analysis result, the second abnormality analysis result, and the third abnormality analysis result; The abnormality analysis result is calculated according to the first abnormality analysis result, the second abnormality analysis result, the third abnormality analysis result and corresponding weights.

7. The monitoring method for substation equipment according to claim 1, characterized in that: The abnormality warning according to the abnormality analysis result includes: Determine the warning level corresponding to the abnormal analysis result; Generate a corresponding warning strategy according to the warning level; An abnormal warning is performed according to the warning strategy.

8. A monitoring device for a power substation, characterized in that: The device comprises: An acquisition module, used to acquire real-time multivariate time series data of a substation device, wherein the real-time multivariate time series data includes one or more of electrical parameters, device operation data, operation data, and device environment data; A preprocessing module, used for preprocessing the real-time multivariate time series data to obtain processed data; An analysis module, used for performing an abnormality analysis on the processed data to obtain an abnormality analysis result; The early warning module is used to issue an abnormality early warning according to the abnormality analysis result.

9. A computer-readable storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a processor, the processor executes the steps of the monitoring method for substation equipment according to any one of claims 1 to 7.

10. A computer device, characterized in that: The device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the monitoring method for substation equipment according to any one of claims 1 to 7.

Images