Substation equipment control method

Abstract

The invention discloses a substation equipment control method. The method comprises the following steps: acquiring operation data of substation equipment in real time by using a plurality of sensors; performing data fusion analysis on the operation data by adopting an ensemble Kalman filtering algorithm to obtain target state information; performing feature anomaly detection on the target state information and the operation data by using an anomaly data set detection algorithm to obtain an anomaly detection result; based on the operation data, the target state information and the anomaly detection result, evaluating the substation equipment to obtain a safety evaluation index vector; and according to the safety evaluation index vector, performing operation strategy checking and adjustment on the substation equipment to obtain a target operation strategy. The technical problems of poor accuracy, safety and real-time performance of a substation control scheme caused by one-sided data acquisition and low manual analysis and processing efficiency in related technologies are solved.

Description

Technical Field

[0001] The present application relates to the field of power system monitoring and control, and in particular, to a substation equipment control method. Background Art

[0002] With the development of modern power systems, the scale and complexity of power grids have increased. As a key node in the power grid, environmental perception and monitoring of substations have become particularly important. On the one hand, the traditional substation environmental monitoring and operation verification system relies on a single sensor device to collect environmental data and equipment operating status inside and outside the substation. The data collection is relatively one-sided, which will result in poor data accuracy and low reliability, resulting in low adaptability, low stability and poor security of the substation control solution. On the other hand, the substation environmental monitoring and operation verification system analyzes the environmental data and equipment operating status collected by the sensor equipment through manual calculation. The data processing efficiency is low and it is easily affected by human factors, resulting in poor real-time performance and poor security of the substation control solution.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiment of the present application provides a substation equipment control method to at least solve the technical problems in the related technology that data collection is relatively one-sided and manual analysis and processing efficiency is low, resulting in poor accuracy, security and real-time performance of the substation control solution.

[0005] According to one aspect of an embodiment of the present application, a substation equipment control method is provided, including: using multiple sensors to collect operating data of the substation equipment in real time; using a collective Kalman filter algorithm to perform data fusion analysis on the operating data to obtain target state information; using an abnormal data set detection algorithm to perform feature anomaly detection on the target state information and operating data to obtain anomaly detection results, wherein the anomaly detection results are used to identify defective states and / or abnormal states of the substation equipment; based on the operating data, the target state information and the anomaly detection results, the substation equipment is evaluated to obtain a safety assessment index vector; according to the safety assessment index vector, the operating strategy of the substation equipment is checked and adjusted to obtain a target operating strategy, wherein the target operating strategy is used to control the substation equipment to operate according to target safety conditions.

[0006] Optionally, a collective Kalman filter algorithm is used to perform data fusion analysis on the operating data to obtain target state information, including: denoising the operating data to obtain initial state information, wherein the initial state information includes: an initial state estimate and an initial error covariance matrix; using a state transition model, predicting the initial state information to obtain a prediction result, wherein the prediction result includes a predicted state and a prediction error covariance matrix; calculating a Kalman gain based on the measurement information and the prediction result, wherein the measurement information includes: measurement values ​​corresponding to the operating data, a measurement matrix and a measurement error covariance matrix, and the measurement matrix and the measurement error covariance matrix are determined by performance parameters of multiple sensors and characteristic parameters of the power system of the substation; using the Kalman gain to recursively update the prediction results to obtain target state information, wherein the target state information includes: a target state estimate and a target error covariance matrix.

[0007] Optionally, an abnormal data set detection algorithm is used to perform feature anomaly detection on the target state information and operating data to obtain an abnormality detection result, including: extracting features from the target state information and operating data to obtain feature values; and performing data detection on the target state information and operating data using the abnormal data detection algorithm and the feature values ​​to obtain an abnormality detection result.

[0008] Optionally, the characteristic values ​​include: temperature change rate, humidity change rate, vibration spectrum, infrared image characteristics, electrical parameter change rate and gas concentration change rate.

[0009] Optionally, the anomaly detection result includes a first anomaly data set, which is used to characterize accidental anomalies corresponding to substation equipment; using an abnormal data detection algorithm and eigenvalues ​​to perform data detection on target state information and operating data, and obtaining the anomaly detection result includes: using a target filter and eigenvalues ​​to select the first anomaly data set from the target state information and operating data, wherein the target filter is used to determine whether the target data point belongs to the first anomaly data set through the absolute deviation of the eigenvalue between the target data point and the median of the adjacent data points.

[0010] Optionally, the anomaly detection result includes a second anomaly data set, which is used to characterize the continuity anomaly corresponding to the substation equipment; using the abnormal data detection algorithm and the characteristic value to perform data detection on the target state information and the operation data, and obtaining the anomaly detection result includes: using the target clustering algorithm and the characteristic value to select the second anomaly data set from the target state information and the operation data, wherein the target clustering algorithm is used to determine whether multiple data points belong to the second anomaly data set through the overall similarity of multiple data points in the target time window and the data density index corresponding to the target time window.

[0011] Optionally, based on the operating data, target state information and abnormality detection results, the substation equipment is evaluated to obtain a safety assessment index vector, including: based on the operating data and the abnormality detection results, a timing state variable vector corresponding to the substation equipment is established; using the target state information, the timing state variable vector and the dynamic simulation model, the predicted state information of the substation equipment under multiple operating strategies is calculated, wherein the dynamic simulation model is used to characterize the timing relationship between the timing state variable vector and each operating strategy; based on the safety assessment model, multiple operating strategies and predicted state information, the safety assessment index vector corresponding to the substation equipment is determined.

[0012] Optionally, based on the operating data and the abnormality detection results, establishing the timing state variable vector corresponding to the substation equipment includes: obtaining the timing operation record of the substation equipment corresponding to the operating data; using the operating data to determine the timing environment parameters corresponding to the substation equipment; using the abnormality detection results to determine the timing equipment state corresponding to the substation equipment; creating the timing state variable vector based on the timing operation record, timing environment parameters and timing equipment state.

[0013] Optionally, using target state information, time series state variable vectors and dynamic simulation models, calculating predicted state information of substation equipment under multiple operation strategies includes: using target state information to determine initial conditions and initial parameters of the dynamic simulation model; inputting initial conditions, initial parameters, multiple operation strategies and time series state variable vectors into the dynamic simulation model to obtain predicted state information.

[0014] Optionally, the operation strategy of the substation equipment is calibrated and adjusted according to the safety assessment index vector to obtain the target operation strategy, including: determining the target safety condition according to the safety boundary thresholds corresponding to multiple operation strategies; using the safety assessment index vector and the target safety condition to calibrate the operation strategy of the substation equipment to obtain the calibration result; and dynamically adjusting the multiple operation strategies according to the calibration result to obtain the target operation strategy.

[0015] Optionally, the safety assessment index vector includes: a reliability component, a failure rate component and an operating cost component; the safety boundary threshold includes: a reliability threshold, a failure rate threshold and an operating cost threshold; the safety assessment index vector and the target safety condition are used to calibrate the operation strategy of the substation equipment, and the calibration result includes: in response to the reliability component being greater than or equal to the reliability threshold, the failure rate component being less than or equal to the failure rate threshold and the operating cost component being less than or equal to the operating cost threshold, determining that the calibration result is that the safety assessment index vector satisfies the target safety condition.

[0016] Optionally, the target operation strategy includes at least one second operation strategy; the multiple operation strategies are dynamically adjusted according to the verification results to obtain the target operation strategy including: in response to the safety assessment index vector corresponding to at least one first operation strategy among the multiple operation strategies failing to meet the target safety condition, determining the feedback control gain matrix corresponding to the first operation strategy; superimposing the feedback control gain matrix with the first operation strategy to obtain the second operation strategy.

[0017] According to another aspect of an embodiment of the present application, a computer-readable storage medium is also provided, including a computer-readable storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any one of the above-mentioned substation equipment control methods.

[0018] According to another aspect of an embodiment of the present application, a substation equipment control system is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute any one of the above-mentioned substation equipment control methods.

[0019] According to another aspect of an embodiment of the present application, a computer program product is also provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned substation equipment control methods is implemented.

[0020] In the embodiment of the present application, multiple sensors are used to collect the operation data of the substation equipment in real time; the ensemble Kalman filter algorithm is used to perform data fusion analysis on the operation data to obtain the target state information; the abnormal data set detection algorithm is used to perform feature abnormality detection on the target state information and the operation data to obtain the abnormality detection result, wherein the abnormality detection result is used to identify the defect state and / or abnormal state of the substation equipment; based on the operation data, the target state information and the abnormality detection result, the substation equipment is evaluated to obtain the safety assessment index vector; the operation strategy of the substation equipment is checked and adjusted according to the safety assessment index vector to obtain the target operation strategy, wherein the target operation strategy is used to control the substation equipment to operate according to the target safety conditions. Thus, the present application achieves the purpose of using multiple sensors to collect the operation data of the substation equipment in real time, analyzing the data through data fusion technology, ensuring the accuracy, reliability and efficiency of data processing, thereby achieving the technical effect of comprehensive and real-time detection of the substation environment and equipment status, improving the accuracy, safety and real-time performance of the substation control scheme, and thus solving the technical problems of poor accuracy, safety and real-time performance of the substation control scheme caused by one-sided data collection and low efficiency of manual analysis and processing in the related technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 It is a hardware structure block diagram of an optional terminal device for a substation equipment control method according to an embodiment of the present application;

[0023] Figure 2 is a flow chart of a substation equipment control method according to an embodiment of the present application;

[0024] Figure 3 It is a schematic diagram of an optional method for controlling substation equipment in an abnormal operating state according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0027] According to an embodiment of the present application, an embodiment of a substation equipment control method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0028] Figure 1 is a hardware structure block diagram of a terminal device for a substation equipment control method according to an optional embodiment of the present application, such as Figure 1 As shown, the terminal device may include one or more processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor (Microcontroller Unit, referred to as MCU) or a programmable logic device (Field Programmable Gate Array, referred to as FPGA)), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display device 110, an input / output device 108 (i.e., an I / O device), a Universal Serial Bus (USB) port (which may be included as one of the ports of a computer bus, not shown in the figure), a network interface (not shown in the figure), a power supply (not shown in the figure) and / or a camera (not shown in the figure). It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0029] It should be noted that the one or more processors 102 and / or other data processing circuits may be embodied in whole or in part as software, hardware, firmware or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be fully or partially integrated into any of the other components in the terminal device (or mobile device).

[0030] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the substation equipment control method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned substation equipment control method is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0031] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal device. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0032] Under the above operating environment, the embodiment of the present application provides the following Figure 2 The substation equipment control method shown, Figure 2 is a flow chart of a substation equipment control method according to an embodiment of the present application, such as Figure 2 As shown, the method includes the following steps S201 to S205.

[0033] Step S201: using multiple sensors to collect operation data of substation equipment in real time.

[0034] The above-mentioned multiple sensors may include but are not limited to: temperature sensor, humidity sensor, vibration sensor, voltage sensor, current sensor, power sensor, frequency sensor, gas concentration sensor, infrared imager, sound sensor, image sensor, wind speed sensor, wind direction sensor, rainfall sensor, oil pressure sensor.

[0035] The above-mentioned operation data may include environmental data and equipment status data.

[0036] The above-mentioned environmental data may include environmental data inside the substation and environmental data outside the substation.

[0037] The above-mentioned environmental data inside the substation can be used to monitor the internal environmental status of the substation, for example, the temperature of the internal environment of the substation, the air humidity of the internal environment of the substation, the sulfur hexafluoride gas concentration, and the images and videos of the internal monitoring of the substation.

[0038] The above-mentioned environmental data outside the substation can be used to monitor the external environmental status of the substation, for example, the temperature of the external environment of the substation, the air humidity of the external environment of the substation, images and videos of external monitoring of the substation, the wind speed of the external environment of the substation, the wind direction of the external environment of the substation, the rainfall of the external environment of the substation, and the geographical location information of the substation.

[0039] The above-mentioned equipment status data can be used to monitor the operating status of the substation, for example, the vibration of the substation equipment, the voltage of the substation equipment, the current of the substation equipment, the power factor of the substation equipment, the frequency of the substation equipment, the transformer oil temperature, the transformer oil pressure, the dissolved gas analysis (Dissolved Gas Analysis, DGA for short) data of the oil-immersed transformer, the infrared thermal imaging image of the substation equipment, the partial discharge signal of the substation equipment, the operating noise of the substation equipment, the switch status of the substation equipment, and the load condition of the substation equipment.

[0040] The specific implementation method of using multiple sensors to collect the operation data of substation equipment in real time can be: using multiple sensors installed inside and outside the substation to collect the internal and external environmental data and equipment operation status data of the substation in real time.

[0041] It is easy to understand that in the embodiments of the present application, multiple sensors installed inside and outside the substation are used to collect various operating data inside and outside the substation in real time, which can comprehensively and in real time monitor the environment inside and outside the substation and the operating status of the equipment, increase the data dimension, and improve the accuracy and reliability of the data. Compared with the solution that relies only on a single sensor device, the above-mentioned solution provided in the embodiments of the present application has more comprehensive data collection, and the collected data has higher accuracy and reliability.

[0042] Step S202: Use the ensemble Kalman filter algorithm to perform data fusion analysis on the operating data to obtain target state information.

[0043] The above-mentioned target state information may be an optimal state estimation of the substation equipment, and the target state information may be used to estimate the state of the substation equipment according to the operation data of the substation equipment.

[0044] The specific implementation method of using the ensemble Kalman filter algorithm to perform data fusion analysis on the operation data to obtain the target state information can be: using the ensemble Kalman filter algorithm to fuse the various operation data collected inside and outside the substation to obtain fused data, analyzing the fused data to obtain the target state information.

[0045] It is easy to understand that in the embodiment of the present application, a collective Kalman filter algorithm is used to perform data fusion analysis on the collected multiple operating data to obtain target state information, which can fuse data from different sources, improve the accuracy and reliability of the target state information, can process data in parallel, improve the efficiency of data processing, obtain target state information at a fast speed, and can update the target state information in real time, thereby ensuring the real-time nature of the target state information. Compared with the method of manual calculation and analysis, the target state information obtained by the above-mentioned scheme provided in the embodiment of the present application is more accurate, more reliable, and more real-time.

[0046] Step S203, using an abnormal data set detection algorithm, performs feature anomaly detection on the target state information and the operating data to obtain an anomaly detection result, wherein the anomaly detection result is used to identify defective states and / or abnormal states of substation equipment.

[0047] The above abnormal data set detection algorithm can be used to identify abnormal values ​​or outliers in a data set. The abnormal data set detection algorithm may include but is not limited to: an abnormal data set detection algorithm based on statistical methods (such as Hampel filter), an abnormal data set detection algorithm based on clustering, an abnormal data set detection algorithm based on time series (such as long short-term memory network, autoregressive integrated moving average model, etc.), and an abnormal data set detection algorithm based on distance (such as k-nearest neighbor algorithm). The above defect state can be used to indicate whether there is a potential fault or operating defect in the substation equipment. The above abnormal state can be used to indicate whether the substation equipment is in an abnormal operating state.

[0048] The specific implementation method of using the abnormal data set detection algorithm to perform feature anomaly detection on the target state information and operation data to obtain the abnormal detection result can be: using the abnormal data set detection algorithm to detect the abnormal data set, and obtaining the abnormal detection result based on the abnormal data set.

[0049] It is easy to understand that in the embodiments of the present application, the abnormal data set detection algorithm is used to perform feature abnormality detection on the target state information and operation data to obtain abnormal detection results, which can identify and process abnormal data in the data set, improve data quality, and timely discover potential problems of the substation, thereby increasing the speed of identifying defective states and / or abnormal states of substation equipment. Compared with manual processing, the abnormal detection results obtained by the above scheme provided in the embodiments of the present application are more real-time.

[0050] Step S204: Based on the operation data, target state information and abnormality detection results, the substation equipment is evaluated to obtain a safety evaluation index vector.

[0051] The safety evaluation index vector can be used to predict the future state of the substation equipment under different operation strategies. The safety evaluation index vector can also be used to evaluate the failure probability of the substation equipment under different operation strategies.

[0052] Based on the operation data, target state information and anomaly detection results, the substation equipment is evaluated to obtain the specific implementation method of the safety assessment index vector: using the collected operation data of the substation equipment to conduct a preliminary analysis of the substation equipment, and obtain the data used to predict the future state of the substation equipment under different operation strategies; based on the target state information and anomaly detection results, the data used to evaluate the failure probability of the substation equipment under different operation strategies are obtained.

[0053] It is easy to understand that in the embodiments of the present application, the substation equipment is evaluated based on the operating data, target state information and abnormal detection results to obtain a safety assessment index vector, which can predict the future state of the substation equipment under different strategies and simulate the failure probability of the substation equipment under different strategies. Compared with manual processing, the above scheme provided in the embodiments of the present application more accurately predicts the safety status of the substation equipment.

[0054] Step S205 , checking and adjusting the operation strategy of the substation equipment according to the safety assessment index vector to obtain a target operation strategy, wherein the target operation strategy is used to control the substation equipment to operate according to the target safety conditions.

[0055] The above target safety conditions can be set according to the actual situation of the substation equipment, and the target safety conditions can be used to ensure the safety of the target operation strategy.

[0056] The operation strategy of the substation equipment is checked and adjusted according to the safety assessment index vector. The specific implementation method of obtaining the target operation strategy can be: according to the safety assessment index vector corresponding to the target safety condition and the operation strategy, the operation strategy is checked; if the safety assessment index vector meets the target safety condition, the operation strategy is set as the target operation strategy; if the safety assessment index vector does not meet the target safety condition, the operation strategy is adjusted according to the safety assessment index vector.

[0057] It should be noted that if the safety assessment index vector corresponding to the adjusted operation strategy still does not meet the target safety condition, the operation strategy is further checked and adjusted until the safety assessment index vector corresponding to the adjusted operation strategy meets the target safety condition.

[0058] It is easy to understand that in the embodiment of the present application, the operation strategy of the substation equipment is checked and adjusted according to the safety assessment index vector to obtain the target operation strategy that meets the target safety conditions, which can optimize the operation strategy and reduce maintenance costs. In addition, in the embodiment of the present application, by setting the target safety conditions, the reliability of the target operation strategy can be improved to ensure the safety of equipment and personnel.

[0059] Through the above steps S201 to S205, multiple sensors are used to collect the operation data of the substation equipment in real time; the ensemble Kalman filter algorithm is used to perform data fusion analysis on the operation data to obtain the target state information; the abnormal data set detection algorithm is used to perform feature abnormality detection on the target state information and the operation data to obtain the abnormality detection result, wherein the abnormality detection result is used to identify the defect state and / or abnormal state of the substation equipment; based on the operation data, the target state information and the abnormality detection result, the substation equipment is evaluated to obtain the safety evaluation index vector; the operation strategy of the substation equipment is checked and adjusted according to the safety evaluation index vector to obtain the target operation strategy, wherein the target operation strategy is used to control the substation equipment to operate according to the target safety conditions. It can be understood that the scheme provided in the embodiment of the present application collects various operation data of the substation equipment based on multiple sensor devices, and processes various operation data by using the ensemble Kalman filter algorithm, the abnormal data set detection algorithm, and the target safety conditions to obtain the target operation strategy, comprehensively collects the operation data of the substation equipment, improves the data processing efficiency, and improves the accuracy, safety, and real-time performance of the substation control scheme.

[0060] Therefore, the embodiment of the present application achieves the purpose of using multiple sensors to collect the operating data of substation equipment in real time, analyzing the data through data fusion technology, and ensuring data accuracy, reliability and data processing efficiency, thereby achieving comprehensive and real-time detection of the substation environment and equipment status, and improving the accuracy, safety and real-time performance of the substation control solution. The technical effect further solves the technical problems in related technologies such as one-sided data collection and low efficiency of manual analysis and processing, resulting in poor accuracy, safety and real-time performance of the substation control solution.

[0061] The above method of the embodiment of the present application is further introduced below.

[0062] Optionally, in the above step S202, using the ensemble Kalman filter algorithm to perform data fusion analysis on the operation data to obtain the target state information may also include the following execution steps:

[0063] Step S221, performing denoising processing on the operating data to obtain initial state information, wherein the initial state information includes: initial state estimation and initial error covariance matrix;

[0064] Step S222, using the state transition model to predict the initial state information to obtain a prediction result, wherein the prediction result includes a predicted state and a prediction error covariance matrix;

[0065] Step S223, calculating the Kalman gain according to the measurement information and the prediction result, wherein the measurement information includes: a measurement value corresponding to the operation data, a measurement matrix and a measurement error covariance matrix, and the measurement matrix and the measurement error covariance matrix are determined by performance parameters of multiple sensors and characteristic parameters of the power system of the substation;

[0066] Step S224, recursively update the prediction result using the Kalman gain to obtain target state information, wherein the target state information includes: target state estimation and target error covariance matrix.

[0067] The above initial state estimation can be used to represent the preliminary estimation of the state of the substation equipment. The above initial error covariance matrix can be used to represent the uncertainty of the preliminary estimation of the state of the substation equipment.

[0068] The state transition model can be a mathematical model of the change of the state of the substation equipment over time, and the state transition model can be used to predict the dynamic behavior of the state of the substation equipment. The predicted state can be obtained by predicting the future state of the substation equipment based on the initial state information, and the predicted state can be used to represent the possible state of the substation equipment in the future. The prediction error covariance matrix can be used to represent the uncertainty of the predicted state of the substation equipment.

[0069] The above measurement error covariance matrix can be used to represent the statistical characteristics of the errors between the measurement values ​​of the substation equipment.

[0070] The above target state estimation can be used to represent the optimal state estimation of the substation equipment.

[0071] In order to more accurately predict the future state of substation equipment under the influence of various factors and predict the possibility of different state transitions of substation equipment, the state transition model is used to predict the initial state information and obtain the prediction results.

[0072] In order to accurately estimate the target state, the Kalman gain is calculated based on the measurement information and the prediction results, and the prediction results are recursively updated using the Kalman gain to obtain the target state information.

[0073] In an exemplary application scenario, the collected operation data is denoised to obtain an initial state estimate (denoted as ) and the initial error covariance matrix (denoted as P 0 ), further, the state transition model is used to predict the initial state information and obtain the predicted state (denoted as ) and the prediction error covariance matrix (denoted as P k|k-1 ), according to the measurement values, measurement matrix, measurement error covariance matrix, and predicted state corresponding to the running data and the prediction error covariance matrix (denoted as P k|k-1 ) to calculate the Kalman gain (denoted as K k ), using the Kalman gain K k The prediction results are recursively updated to obtain the target state estimate (denoted as ) and the target error covariance matrix (denoted as P k|k ).

[0074] The above prediction status It can be calculated by the following formula (1).

[0075]

[0076] In the above formula (1), A represents the state transfer matrix, B represents the control matrix, and u k Represents the control vector

[0077] The state transfer matrix can be used to represent the law of environmental data changing over time, and the state transfer matrix can be fitted by historical environmental data. The control matrix can be used to represent the degree of influence of the change of the control vector on the predicted state.

[0078] The above prediction error covariance matrix P k|k-1 It can be calculated by the following formula (2).

[0079] P k|k-1 =AP k-1|k-1 A T +Q Formula (2)

[0080] In the above formula (2), Q represents the process noise covariance matrix.

[0081] The above process noise covariance matrix can be used to represent quantitative data corresponding to environmental noise interference.

[0082] The above Kalman gain K k It can be calculated by the following formula (3).

[0083] K k =P k|k-1 H T (HP k|k-1 H T +R) -1 Formula (3)

[0084] In the above formula (3), R represents the measurement noise covariance matrix.

[0085] The above target state estimation It can be calculated by the following formula (4).

[0086]

[0087] In the above formula (4), z k Indicates the measured value corresponding to the running data.

[0088] The above target error covariance matrix P k|k It can be calculated by the following formula (5).

[0089] P k|k =(IK k H)P k|k -1 Formula (5)

[0090] Through the technical solution provided by the above steps S221 to S224, the embodiment of the present application performs denoising on the operating data to obtain initial state information, and uses the state transition model to predict the initial state information to obtain a prediction result, which can simulate various situations of the future state of the substation equipment, and the obtained prediction result is more accurate. Further, the Kalman gain is calculated based on the measurement information and the prediction result, and the prediction result is recursively updated using the Kalman gain to obtain the target state information. The prediction result can be dynamically adjusted according to the measurement information at the current moment and the prediction result at the current moment, and the state estimation is continuously optimized, so that the obtained target state information can maintain a high accuracy. Therefore, the embodiment of the present application can obtain more accurate target state information.

[0091] Optionally, in the above step S203, using an abnormal data set detection algorithm to perform feature anomaly detection on the target state information and the operation data, and obtaining anomaly detection results may also include the following execution steps:

[0092] Step S231, extracting features from target state information and operation data to obtain feature values;

[0093] Step S232, using an abnormal data detection algorithm and feature values ​​to perform data detection on the target state information and operating data to obtain an abnormal detection result.

[0094] Since the original target state information and original operation data may contain a large amount of redundant information, feature extraction is performed on the target state information and operation data to obtain the most representative and discriminative feature values, reduce data dimensions, reduce the complexity and computational cost of subsequent processing, and improve detection efficiency.

[0095] In order to identify the abnormal operating status of substation equipment more timely and improve the safety and stability of substation equipment operation, the abnormal data detection algorithm and eigenvalues ​​are used to perform data detection on the target state information and operation data to obtain the abnormal detection results.

[0096] In an exemplary application scenario, the target state estimation (denoted as ) and the measured value corresponding to the running data (denoted as z k ) to extract features and obtain feature values, which are used as inputs of abnormal data detection algorithms to perform data detection and detect defects and / or abnormal conditions of substation equipment in real time.

[0097] Through the technical solutions provided by the above steps S231 to S232, the embodiment of the present application extracts features from the target state information and operation data, takes into account the impact of a large amount of redundant information on subsequent processing, improves the efficiency of subsequent processing, and can obtain abnormal detection results more quickly. Furthermore, by using abnormal data detection algorithms and feature values ​​to perform data detection on the target state information and operation data, the abnormal operating state of the substation equipment can be identified more quickly. Therefore, the embodiment of the present application can obtain abnormal detection results more timely.

[0098] Optionally, in the above-mentioned substation equipment control method, the characteristic values ​​include: temperature change rate, humidity change rate, vibration spectrum, infrared image characteristics, electrical parameter change rate and gas concentration change rate.

[0099] The temperature change rate may include the temperature change rate of the substation internal environment and the temperature change rate of the substation external environment. The humidity change rate may include the humidity change rate of the substation internal environment and the humidity change rate of the substation external environment. The electrical parameter change rate may include the voltage change rate of the substation equipment, the current change rate of the substation equipment, the power factor change rate of the substation equipment, and the frequency change rate of the substation equipment.

[0100] In an exemplary application scenario, the target state is estimated The measured value z corresponding to the running data k Perform feature extraction to obtain the temperature change rate ΔT k , Humidity change rate ΔH k , vibration spectrum F k 、Infrared image features I k , electrical parameter change rate ΔE k and the gas concentration change rate ΔG k .

[0101] Through the technical solution provided above, in the embodiment of the present application, it is considered to input a variety of data collected by multiple sensor devices into the abnormal data detection algorithm to obtain abnormal detection results, increase the data dimension, and obtain abnormal detection results more accurately. In addition, in the case of a single sensor device failure, a highly reliable abnormal detection result can still be obtained, and the reliability of the abnormal detection solution is high. Therefore, the embodiment of the present application can avoid the problem of poor data accuracy and low reliability caused by relying only on a single sensor device to collect data in the related art, and can obtain abnormal detection results with better accuracy and higher reliability.

[0102] Optionally, the anomaly detection result includes a first anomaly data set, and the first anomaly data set is used to characterize the accidental anomaly corresponding to the substation equipment; in the above step S232, the target state information and operation data are subjected to data detection using an abnormal data detection algorithm and eigenvalues, and obtaining the anomaly detection result may also include: using a target filter and eigenvalues ​​to select a first anomaly data set from the target state information and operation data, wherein the target filter is used to determine whether the target data point belongs to the first anomaly data set by the absolute deviation of the eigenvalue between the target data point and the median of the adjacent data points.

[0103] The above-mentioned accidental anomaly may be an abnormal display of the substation equipment caused by at least one of the following conditions: sensor error, environmental noise interference. The above-mentioned eigenvalue absolute deviation may be used to represent the difference between the target data point and the adjacent data points.

[0104] Since in real life, when using sensors to collect data, it is difficult to avoid being affected by sensor errors and environmental noise interference. Therefore, in an embodiment of the present application, a target filter and eigenvalue are used to filter out a first abnormal data set corresponding to accidental abnormalities of substation equipment from the target state information and operation data. This can reduce the noise in the data, make the data more accurately reflect the actual situation of the substation equipment, improve the stability and accuracy of data detection, and thus improve the accuracy of the abnormality detection results.

[0105] In an exemplary application scenario, the Hampel filter is selected as the abnormal data detection algorithm, and a time window is defined. The time window can be used to represent the time range of multiple data points to be detected. The Hampel filter is used to detect the target data point (denoted as r i ) is used for detection, and the median of the target data point and the adjacent data points (denoted as M i ) between the absolute deviation of the eigenvalues ​​(denoted as S wi ) determines whether the target data point belongs to the first anomaly data set.

[0106] The above target data point r i The median value M of the adjacent data points iIt can be calculated by the following formula (6).

[0107] M i =median(R i ) Formula (6)

[0108] In the above formula (6), R i = {r i-g ,…,r i+g} represents a data sequence centered on the i-th data point with a time window size of 2g+1.

[0109] The absolute deviation S of the above eigenvalues wi It can be used to measure the discreteness of the data sequence. The absolute deviation of the eigenvalue can be calculated by the following formula (7).

[0110] S wi =1.4826×median(|R i -M i |) Formula (7)

[0111] The target data point r is determined by the following formula (8): i Whether it belongs to the first abnormal data set. If formula (8) holds, then the target data point r i Belongs to the first abnormal data set.

[0112] |r i -M i |≥k×S wi Formula (8)

[0113] In the above formula (8), k represents an adjustable parameter.

[0114] In addition, the above abnormal data detection algorithm can also be used to process the first abnormal data set. i belongs to the first abnormal data set, then the target data point r i Replaced with the median value M of the target data point and the adjacent data points i .

[0115] Through the technical solution provided above, in the embodiment of the present application, it is considered to screen the accidental abnormal data in the target state information and the operation data through the target filter, so as to avoid the problem of low data detection accuracy caused by the influence of sensor error and environmental noise interference during the data detection process as much as possible. Therefore, the embodiment of the present application can detect data more accurately, and the obtained abnormal detection result is more accurate.

[0116] Optionally, the anomaly detection result includes a second anomaly data set, which is used to characterize the continuity anomaly corresponding to the substation equipment; in the above step S232, the target state information and operation data are subjected to data detection using an abnormal data detection algorithm and a characteristic value, and obtaining the anomaly detection result may also include: using a target clustering algorithm and a characteristic value to select a second anomaly data set from the target state information and operation data, wherein the target clustering algorithm is used to determine whether multiple data points belong to the second anomaly data set through the overall similarity of multiple data points within a target time window and a data density index corresponding to the target time window.

[0117] The above-mentioned continuity anomaly may be caused by the abnormal display of substation equipment when at least one of the following conditions exists: substation equipment failure, substation environment change. The above-mentioned overall similarity can be used to represent the data correlation of multiple data points within the target time window. The overall similarity can be obtained by the following method: obtaining the overall similarity based on distance measurement (such as Euclidean distance, Manhattan distance, dynamic time warping, etc.), and obtaining the overall similarity based on correlation coefficient (such as Pearson correlation coefficient). The above-mentioned data density index can be used to represent the data distribution density of multiple data points within the target time window.

[0118] When substation equipment fails and / or the substation environment changes, the substation equipment is in a continuous abnormal state. In order to more accurately and quickly screen out the continuous abnormal data in the target state information and operation data, the target clustering algorithm and eigenvalue are used to select the second abnormal data set from the target state information and operation data.

[0119] In an exemplary application scenario, an improved density-based spatial data clustering algorithm (Density-Based Spatial Clustering of Applications with Noise, referred to as DBSCAN) is selected as an abnormal data detection algorithm, and a target time window with a time window width of n is defined. The target time window contains multiple data points within a period of time, and the multiple data points in the time window are regarded as the overall data. When the number of data points in the target time window reaches n, the DBSCAN algorithm is used to detect the overall data. Based on the overall similarity of the overall data (denoted as D n×n ), determine the initial minPts value, and calculate the data density index (denoted as Den) corresponding to the target time window according to the initial value of minPts and the candidate value of Eps. Thus, the data density index Den is used to determine whether multiple data points belong to the second abnormal data set.

[0120] The above target time window width may be an adjustable parameter.

[0121] The above overall similarity Dn×n It can be used to quantify the similarity between multiple data points in the target time window. The overall similarity can be obtained by calculating the distance between each pair of data points in the target time window. The overall similarity can be calculated by the following formula (9).

[0122] D n×n ={Dist(i,j)|1≤i,j≤n} Formula (9)

[0123] In the above formula (9), Dist(i,j) represents the distance between the i-th data point and the j-th data point.

[0124] The candidate values ​​of the above-mentioned Eps can be calculated by the following formula (10).

[0125]

[0126] In the above formula (10), NN k Represents the kth nearest neighbor data point among multiple nearest neighbor data points of the i-th data point.

[0127] The data density index Den corresponding to the above target time window can be calculated by the following formula (11).

[0128]

[0129] The following three conditions are used to determine whether multiple data points in the target time window belong to the second abnormal data set:

[0130] Condition 1: Den(2)>k×Den(3);

[0131] Condition 2: k>10;

[0132] Condition 3: ΔDen(i) decreases continuously and approaches 0.

[0133] If the above three conditions are all met, it is determined that the multiple data points belong to the second abnormal data set.

[0134] In addition, the third standard deviation principle (ie, 3σ principle) can be used to verify the second abnormal data set.

[0135] Specifically, the standard deviation (denoted as σ) corresponding to the second abnormal data set is calculated, and the distribution of data points in the second abnormal data set is detected based on the standard deviation σ and the mean of the normal distribution (denoted as μ). If the second abnormal data set to be selected meets the three times standard deviation principle, it passes the verification.

[0136] The above triple standard deviation principle is shown in the following formula (12).

[0137] |ρ-μ|≤3σ Formula (12)

[0138] In the above formula (12), ρ represents the covariance coefficient, and the covariance coefficient can be calculated by the following formula (13).

[0139]

[0140] In the above formula (12), x and y represent a pair of data points in the target time window.

[0141] Through the technical solution provided above, in the embodiment of the present application, the target clustering algorithm is considered to be used to screen the continuous abnormal data in the target state information and operation data, so that the data of the substation equipment in normal operation can be stably clustered, and the continuous abnormal data can be more accurately identified. In addition, the target clustering algorithm can quickly process high-dimensional data sets and can identify continuous abnormal data more timely. Therefore, the embodiment of the present application can screen the second abnormal data set more accurately and timely, and the obtained abnormal detection results are more accurate and timely.

[0142] Optionally, in the above step S204, based on the operation data, the target state information and the abnormality detection result, evaluating the substation equipment to obtain the safety assessment index vector may also include the following execution steps:

[0143] Step S241, establishing a time series state variable vector corresponding to the substation equipment based on the operation data and the abnormality detection result;

[0144] Step S242, using the target state information, the time series state variable vector and the dynamic simulation model, calculating the predicted state information of the substation equipment under multiple operation strategies, wherein the dynamic simulation model is used to characterize the time series relationship between the time series state variable vector and each operation strategy;

[0145] Step S243, determining the safety assessment index vector corresponding to the substation equipment based on the safety assessment model, multiple operation strategies and predicted state information.

[0146] The above-mentioned time series state variable vector can be used to represent the state of the substation equipment changing over time, and the time series state variable vector can include the state information of the substation equipment at different time points. The above-mentioned dynamic simulation model can be used to predict the operating state of the substation equipment. The above-mentioned multiple operation strategies can be effective operation strategies summarized based on historical experience, and the multiple operation strategies can be obtained by manual formulation or based on deep learning models. The above-mentioned safety assessment model can be used to evaluate the operating state, failure risk and safety performance of the substation equipment, and the safety assessment model can be constructed by using a time series analysis algorithm and a classification algorithm.

[0147] When there is a risk of failure in substation equipment, a variety of operating strategies can usually be adopted to control the substation equipment. In order to evaluate the impact of different operating strategies on the safe operation of substation equipment, in an embodiment of the present application, the target state information, the time series state variable vector and the dynamic simulation model are used to calculate the predicted state information of the substation equipment under a variety of operating strategies. Furthermore, based on the safety assessment model, the multiple operating strategies and the predicted state information, the safety assessment index vector corresponding to the substation equipment is determined.

[0148] Exemplarily, the above safety assessment index vector J(t) can be calculated by the following formula (14).

[0149] J(t)=M(x(t),u(t)) Formula (14)

[0150] In the above formula (14), M represents the safety assessment model, x(t) represents the time series device state variable vector corresponding to the substation equipment, and u(t) represents multiple operation strategies.

[0151] Through the technical solutions provided by the above steps S241 to S243, the embodiment of the present application can simulate the state of substation equipment under various operation strategies by using target state information, time series state variable vectors and dynamic simulation models, and can compare and analyze the safety assessment index vectors corresponding to the substation equipment under different operation strategies, thereby analyzing the impact of different operation strategies on the safe operation of substation equipment, and can predict the potential failures or abnormalities of substation equipment when different operation strategies are adopted, and optimize the operation strategy. Therefore, the operation strategy obtained by the embodiment of the present application is more secure.

[0152] Optionally, in the above step S241, establishing the time series state variable vector corresponding to the substation equipment based on the operation data and the abnormality detection result may also include the following execution steps:

[0153] Step S2411, obtaining the time sequence operation record of the substation equipment corresponding to the operation data;

[0154] Step S2412, using the operation data to determine the timing environment parameters corresponding to the substation equipment;

[0155] Step S2413, using the abnormality detection result to determine the timing device state corresponding to the substation equipment;

[0156] Step S2414, creating a timing state variable vector based on the timing operation record, the timing environment parameters and the timing device state.

[0157] The above-mentioned sequential operation record may be a record log of the operation on the substation equipment, and the sequential operation record may be used to track the specific operation behavior and operation time of the operation on the substation equipment.

[0158] In an exemplary application scenario, the timing operation record (denoted as U(t)) of the substation equipment corresponding to the operating data is obtained, the timing environment parameters (denoted as E(t)) corresponding to the substation equipment are determined using the operating data, and the timing device state (denoted as S(t)) corresponding to the substation equipment is determined using the abnormality detection result. Based on the timing operation record, the timing environment parameters and the timing device state, a timing state variable vector (denoted as x(t)) is created.

[0159] The above-mentioned time series state variable vector x(t) can be calculated by the following formula (15).

[0160] x(t)=[E(t),S(t),U(t)] Formula (15)

[0161] Through the technical solutions provided by the above steps S2411 to S2414, the embodiment of the present application creates a timing state variable vector through timing operation records, timing environment parameters and timing device status, which can make full use of multi-dimensional data and obtain the timing state variable vector in a more comprehensive, in-depth and accurate manner.

[0162] Optionally, in the above step S242, using the target state information, the time series state variable vector and the dynamic simulation model to calculate the predicted state information of the substation equipment under multiple operation strategies may also include the following execution steps:

[0163] Step S2421, using the target state information, determining the initial conditions and initial parameters of the dynamic simulation model;

[0164] Step S2422, inputting initial conditions, initial parameters, multiple operation strategies and time-series state variable vectors into the dynamic simulation model to obtain predicted state information.

[0165] Since the target state information contains the expected operation of the system, using the target state information to determine the initial conditions and initial parameters of the dynamic simulation model can make the dynamic simulation model more accurately reflect the dynamic characteristics of the actual system.

[0166] In an exemplary application scenario, the target state information is used to determine the initial conditions (denoted as x(0)) and initial parameters (denoted as θ) of the dynamic simulation model. The initial conditions x(0), initial parameters θ, multiple operation strategies and time series state variable vectors are input into the dynamic simulation model to simulate the substation equipment using each of the multiple operation strategies (denoted as u i (t)), the corresponding substation equipment is predicted to obtain the predicted status information of the substation equipment.

[0167] The above initial conditions can be the state variable vector of the substation equipment at time t=0, and the initial conditions can be used to reflect the current overall operation state of the substation. The above initial parameters can be the dynamic simulation model parameter vector used to describe the change of the substation equipment state over time, and the initial parameters can be used to represent the environmental changes and equipment operation states that affect the substation equipment state.

[0168] The above dynamic simulation model can be expressed by the following equation (16).

[0169]

[0170] According to the above formula (16), corresponding to each operation strategy u i (t), and the following formula (17) is obtained.

[0171]

[0172] In the above formula (16), x i (t) represents the operation strategy u i (t) corresponds to the state variable vector at time.

[0173] Through the technical solutions provided by the above steps S2421 to S2422, the embodiment of the present application utilizes the target state information to determine the initial conditions and initial parameters of the dynamic simulation model, which can improve the accuracy of the simulation process of the dynamic simulation model and improve the accuracy of the predicted state information.

[0174] Optionally, in the above step S205, checking and adjusting the operation strategy of the substation equipment according to the safety assessment index vector to obtain the target operation strategy may also include the following execution steps:

[0175] Step S251, determining a target safety condition according to safety boundary thresholds corresponding to a plurality of operation strategies;

[0176] Step S252, using the safety assessment index vector and the target safety condition, verifying the operation strategy of the substation equipment to obtain a verification result;

[0177] Step S253, dynamically adjust the multiple operation strategies according to the verification results to obtain the target operation strategy.

[0178] The above safety boundary threshold can be set to different values ​​according to different operation strategies. The above verification result can be used to indicate whether the safety assessment index vector meets the safety boundary threshold.

[0179] Since different operating strategies may have different safety boundary thresholds, and accordingly, different operating strategies correspond to different target safety conditions, therefore, determining the target safety conditions according to the safety boundary thresholds corresponding to a variety of operating strategies can more specifically set different safety boundary thresholds for different operating strategies, obtain different target safety conditions, and improve the accuracy and safety of the control scheme of the substation equipment.

[0180] In order to ensure the safety of the control scheme of substation equipment, the operation strategy of substation equipment is verified by using the safety assessment index vector and target safety condition corresponding to the operation strategy. Furthermore, multiple operation strategies are dynamically adjusted according to the verification results to obtain the target operation strategy.

[0181] In an exemplary application scenario, the embodiment of the present application sets safety boundary thresholds corresponding to multiple operating strategies, determines the target safety conditions, uses the safety assessment index vector and the target safety conditions to verify the operating strategies of the substation equipment, and dynamically adjusts the multiple operating strategies according to the verification results to obtain the target operating strategy. It takes into account the determination of different target safety conditions when different operating strategies are adopted, and the control scheme of the substation equipment obtained is more accurate and safer. It also takes into account the use of safety assessment index vectors and the target safety conditions to verify the operating strategies of the substation equipment, and dynamically adjusts the multiple operating strategies according to the verification results to obtain the target operating strategy, thereby ensuring the safety of the control scheme of the substation equipment.

[0182] Optionally, the safety assessment index vector includes: a reliability component, a failure rate component and an operating cost component; the safety boundary threshold includes: a reliability threshold, a failure rate threshold and an operating cost threshold; in the above step S252, the operation strategy of the substation equipment is verified using the safety assessment index vector and the target safety condition, and the verification result may also include: in response to the reliability component being greater than or equal to the reliability threshold, the failure rate component being less than or equal to the failure rate threshold and the operating cost component being less than or equal to the operating cost threshold, determining that the verification result is that the safety assessment index vector satisfies the target safety condition.

[0183] In an exemplary application scenario, the safety evaluation index vector corresponding to the operation strategy includes: reliability component R(t), failure rate component F(t) and operation cost component C(t). The reliability threshold corresponding to the operation strategy is set to T R , set the failure rate threshold corresponding to the operation strategy to T F , set the operating cost threshold corresponding to the operation strategy to T C The following conditions are used to determine whether the security assessment index vector corresponding to the operation strategy meets the target security conditions: R(t)≥T R ,F(t)≤TF ,C(t)≤T C If the above three conditions are met, the verification result is determined to be a safety assessment index vector that meets the target safety condition.

[0184] Through the technical solution provided above, in the embodiment of the present application, a variety of safety assessment indicators are taken into consideration. During the verification process, the reliability, failure rate and operating cost of the operation strategy are comprehensively considered, and the verification results can be obtained more accurately and specifically, thereby obtaining a more accurate and targeted target operation strategy.

[0185] Optionally, the target operation strategy includes at least one second operation strategy; in the above step S253, dynamically adjusting the multiple operation strategies according to the verification result to obtain the target operation strategy also includes the following execution steps:

[0186] Step S2531, in response to a safety assessment index vector corresponding to at least one first operation strategy among the multiple operation strategies not satisfying a target safety condition, determining a feedback control gain matrix corresponding to the first operation strategy;

[0187] Step S2532: superimpose the feedback control gain matrix and the first operation strategy to obtain a second operation strategy.

[0188] Since the feedback control gain matrix can be used to accurately adjust the operating strategy, thereby timely determining the second operating strategy, the embodiment of the present application superimposes the feedback control gain matrix with the first operating strategy to obtain the second operating strategy, thereby improving the accuracy of the second operating strategy and the efficiency of the process of determining the second operating strategy.

[0189] In an exemplary application scenario, if the first operation strategy (denoted as u old (t)) does not meet the target safety condition, the feedback control gain matrix (denoted as K) corresponding to the first operation strategy is obtained. Further, based on the feedback control gain matrix K and the first operation strategy u old (t), and obtain the second operation strategy (denoted as u new (t)).

[0190] The above second operation strategy can be calculated by the following formula (18).

[0191] u new (t) = u old (t)+K(x obs (t)-x sim (t)) Formula (18)

[0192] In the above formula (18), x obs (t) represents the actual monitoring state, xsim (t) represents the simulation result status.

[0193] Through the technical solution provided by the above steps S2531 to S2532, the embodiment of the present application obtains the second operation strategy by superimposing the feedback control gain matrix and the first operation strategy, and can accurately adjust the operation strategy dynamically to improve the efficiency of obtaining the target operation strategy. Therefore, the second operation strategy obtained by the embodiment of the present application is more accurate and timely.

[0194] The above-mentioned substation equipment control method can be applied to the scene where the substation equipment needs to be controlled. Taking the scene where the substation equipment is in an abnormal state as an example, a method is provided as follows: Figure 3 The schematic diagram shown in FIG. 1 is used to control substation equipment in abnormal operating conditions. Figure 3 As shown, multiple operating data of substation equipment are collected in real time, and a plurality of operating data are fused and analyzed by using a collective Kalman filter to obtain target state information, and feature value extraction is performed on the target state information and operating data, and anomaly detection is performed by using a Hampel filter and an improved DBSCAN algorithm, and the operating state of substation equipment in an abnormal operating state under each of a plurality of operating strategies is predicted, and a corresponding safety assessment index vector is obtained, and a safety check is performed according to the safety assessment index vector corresponding to the operating strategy, and the operating strategy is optimized. Therefore, on the one hand, the embodiment of the present application performs a fusion analysis of a plurality of operating data by using a collective Kalman filter, increases the data dimension, and improves the accuracy and reliability of the data; on the other hand, the embodiment of the present application performs anomaly detection by using a Hampel filter and an improved DBSCAN algorithm, predicts the operating state of substation equipment under a plurality of operating strategies, and performs a safety check according to the safety assessment index vector corresponding to the operating strategy, optimizes the operating strategy, improves the efficiency and accuracy of the anomaly detection process, and improves the real-time and safety of the substation control scheme.

[0195] According to another aspect of the embodiment of the present application, a computer-readable storage medium is also provided, the storage medium including a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute any of the aforementioned substation equipment control methods.

[0196] Optionally, in this embodiment, the above-mentioned storage medium can be configured to store a computer program for executing the following steps: using multiple sensors to collect operating data of substation equipment in real time; using a collective Kalman filter algorithm to perform data fusion analysis on the operating data to obtain target state information; using an abnormal data set detection algorithm to perform feature anomaly detection on the target state information and operating data to obtain anomaly detection results, wherein the anomaly detection results are used to identify defective states and / or abnormal states of substation equipment; based on the operating data, target state information and anomaly detection results, the substation equipment is evaluated to obtain a safety assessment index vector; according to the safety assessment index vector, the operating strategy of the substation equipment is calibrated and adjusted to obtain a target operating strategy, wherein the target operating strategy is used to control the substation equipment to operate according to target safety conditions.

[0197] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0198] According to another aspect of an embodiment of the present application, a substation equipment control system is also provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute any one of the aforementioned substation equipment control methods.

[0199] Optionally, in this embodiment, the above-mentioned processor can be configured to perform the following steps through a computer program: using multiple sensors to collect operating data of substation equipment in real time; using a collective Kalman filter algorithm to perform data fusion analysis on the operating data to obtain target state information; using an abnormal data set detection algorithm to perform feature anomaly detection on the target state information and operating data to obtain anomaly detection results, wherein the anomaly detection results are used to identify defective states and / or abnormal states of substation equipment; based on the operating data, target state information and anomaly detection results, the substation equipment is evaluated to obtain a safety assessment index vector; according to the safety assessment index vector, the operating strategy of the substation equipment is calibrated and adjusted to obtain a target operating strategy, wherein the target operating strategy is used to control the substation equipment to operate according to target safety conditions.

[0200] According to another aspect of the embodiments of the present invention, a computer program product is further provided. Optionally, the computer program product can provide a substation equipment control service based on the substation equipment control method.

[0201] Optionally, in this embodiment, the computer program product may be a set of instructions and codes pre-written according to the substation equipment control method. The computer program product may run on various computer platforms, including personal computers, servers, mobile devices, etc.

[0202] Optionally, in this embodiment, the instructions and codes corresponding to the computer program product are used to implement the following method steps: using multiple sensors to collect operating data of substation equipment in real time; using a collective Kalman filter algorithm to perform data fusion analysis on the operating data to obtain target state information; using an abnormal data set detection algorithm to perform feature anomaly detection on the target state information and operating data to obtain anomaly detection results, wherein the anomaly detection results are used to identify defective states and / or abnormal states of substation equipment; based on the operating data, target state information and anomaly detection results, the substation equipment is evaluated to obtain a safety assessment index vector; according to the safety assessment index vector, the operating strategy of the substation equipment is calibrated and adjusted to obtain a target operating strategy, wherein the target operating strategy is used to control the substation equipment to operate according to target safety conditions.

[0203] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiment and its optional implementation manners, which will not be described in detail here.

[0204] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0205] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0206] Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the whole or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, ROM, RAM, mobile hard disks, magnetic disks or optical disks.

[0207] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A substation equipment control method, characterized in that: include: Use multiple sensors to collect operating data of substation equipment in real time; Using an ensemble Kalman filter algorithm to perform data fusion analysis on the operating data to obtain target state information; Using an abnormal data set detection algorithm, feature anomaly detection is performed on the target state information and the operation data to obtain an anomaly detection result, wherein the anomaly detection result is used to identify a defect state and / or an abnormal state of the substation equipment; Based on the operation data, the target state information and the abnormality detection result, the substation equipment is evaluated to obtain a safety evaluation index vector; The operation strategy of the substation equipment is checked and adjusted according to the safety assessment index vector to obtain a target operation strategy, wherein the target operation strategy is used to control the substation equipment to operate according to the target safety conditions.

2. The substation equipment control method according to claim 1, characterized in that: The ensemble Kalman filter algorithm is used to perform data fusion analysis on the operation data to obtain the target state information including: Performing denoising on the operating data to obtain initial state information, wherein the initial state information includes: an initial state estimate and an initial error covariance matrix; Using a state transition model, predicting the initial state information to obtain a prediction result, wherein the prediction result includes a prediction state and a prediction error covariance matrix; The Kalman gain is calculated according to the measurement information and the prediction result, wherein the measurement information includes: a measurement value corresponding to the operation data, a measurement matrix and a measurement error covariance matrix, and the measurement matrix and the measurement error covariance matrix are determined by the performance parameters of the multiple sensors and the power system characteristic parameters of the substation; The prediction result is recursively updated using the Kalman gain to obtain target state information, wherein the target state information includes: a target state estimation and a target error covariance matrix.

3. The substation equipment control method according to claim 1, characterized in that: Using the abnormal data set detection algorithm, feature anomaly detection is performed on the target state information and the operation data, and the anomaly detection result obtained includes: Performing feature extraction on the target state information and the operation data to obtain feature values; The target state information and the operation data are subjected to data detection using an abnormal data detection algorithm and the characteristic value to obtain an abnormality detection result.

4. The substation equipment control method according to claim 3, characterized in that: The abnormality detection result includes a first abnormality data set, and the first abnormality data set is used to characterize the accidental abnormality corresponding to the substation equipment; Using the abnormal data detection algorithm and the characteristic value to perform data detection on the target state information and the operating data, and obtaining the abnormal detection result includes: The first abnormal data set is selected from the target state information and the operating data using a target filter and the eigenvalue, wherein the target filter is used to determine whether the target data point belongs to the first abnormal data set based on an absolute deviation of an eigenvalue between a target data point and a median of an adjacent data point.

5. The substation equipment control method according to claim 3 or 4, characterized in that: The abnormality detection result includes a second abnormality data set, and the second abnormality data set is used to characterize the continuity abnormality corresponding to the substation equipment; Using the abnormal data detection algorithm and the characteristic value to perform data detection on the target state information and the operating data, and obtaining the abnormal detection result includes: The second abnormal data set is selected from the target state information and the operating data using a target clustering algorithm and the characteristic value, wherein the target clustering algorithm is used to determine whether the multiple data points belong to the second abnormal data set based on the overall similarity of multiple data points within a target time window and a data density index corresponding to the target time window.

6. The substation equipment control method according to claim 1, characterized in that: Based on the operation data, the target state information and the abnormality detection result, the substation equipment is evaluated to obtain the safety evaluation index vector including: Based on the operation data and the abnormality detection result, establishing a time series state variable vector corresponding to the substation equipment; Calculating predicted state information of the substation equipment under a plurality of operation strategies using the target state information, the time series state variable vector and a dynamic simulation model, wherein the dynamic simulation model is used to characterize the time series relationship between the time series state variable vector and each operation strategy; Based on the safety assessment model, the multiple operation strategies and the predicted state information, a safety assessment index vector corresponding to the substation equipment is determined.

7. The substation equipment control method according to claim 6, characterized in that: Based on the operation data and the abnormality detection result, establishing the time series state variable vector corresponding to the substation equipment includes: Acquire a time sequence operation record of the substation equipment corresponding to the operation data; Determining the timing environment parameters corresponding to the substation equipment using the operation data; Determine the timing device status corresponding to the substation equipment using the abnormality detection result; The timing state variable vector is created based on the timing operation record, the timing environment parameter and the timing device state.

8. The substation equipment control method according to claim 6, characterized in that: The operation strategy of the substation equipment is checked and adjusted according to the safety assessment index vector to obtain the target operation strategy, which includes: Determining the target safety condition according to the safety boundary thresholds corresponding to the multiple operation strategies; Using the safety assessment index vector and the target safety condition, verify the operation strategy of the substation equipment to obtain a verification result; The multiple operation strategies are dynamically adjusted according to the verification results to obtain a target operation strategy.

9. The substation equipment control method according to claim 8, characterized in that: The safety assessment index vector includes: a reliability component, a failure rate component and an operating cost component; the safety boundary threshold includes: a reliability threshold, a failure rate threshold and an operating cost threshold; using the safety assessment index vector and the target safety condition, the operation strategy of the substation equipment is checked, and the check result includes: In response to the reliability component being greater than or equal to the reliability threshold, the failure rate component being less than or equal to the failure rate threshold and the operating cost component being less than or equal to the operating cost threshold, the verification result is determined to be that the safety assessment index vector satisfies the target safety condition.

10. The substation equipment control method according to claim 8, characterized in that: The target operation strategy includes at least one second operation strategy; The multiple operation strategies are dynamically adjusted according to the verification results to obtain the target operation strategy, including: In response to the safety assessment index vector corresponding to at least one first operation strategy among the multiple operation strategies not satisfying the target safety condition, determining a feedback control gain matrix corresponding to the first operation strategy; The feedback control gain matrix is ​​superimposed on the first operation strategy to obtain the second operation strategy.

Images