Breaker operation state monitoring method and system based on big data

Abstract

The invention relates to the technical field of data processing, in particular to a circuit breaker operation state monitoring method and system based on big data, and the method comprises the steps: obtaining an operation state vector; obtaining a gain influence at each acquisition moment by using a filtering algorithm, and determining a fluctuation characteristic value based on a curve fitting result in a data space constructed by the gain influence; determining the fluctuation degree of the monitoring data at the acquisition moment according to the influence degree of the data fluctuation at the data abnormal moment on the monitoring data at the acquisition moment and the fluctuation characteristic value, and completing the updating of the Kalman gain matrix at the acquisition moment; and obtaining a prediction result of the operation state vector based on the updated Kalman gain matrix by using an extended Kalman filtering algorithm, and obtaining a monitoring result of the operation state of the circuit breaker based on the prediction result. According to the invention, through more accurately predicting the operation state monitoring data of the circuit breaker, the accuracy of monitoring the operation state change of the circuit breaker is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a circuit breaker operating status monitoring method and system based on big data. Background Art

[0002] As an important power equipment in the power system, the safe and stable operation of the circuit breaker is the premise of the stable operation of the power system. Therefore, monitoring the circuit breaker status is particularly important. Usually, sensors are used to monitor the working environment parameters and electrical parameters of the circuit breaker, and the circuit breaker operation status is judged from a variety of data analysis.

[0003] Wireless sensor network technology is a circuit breaker status monitoring technology that has been widely used in recent years. By deploying various sensors around the circuit breaker, a large amount of monitoring data is transmitted to the monitoring terminal through wireless communication, and big data analysis technology is used to achieve real-time monitoring of the circuit breaker operating status.

[0004] At the monitoring terminal, the existing technology uses the Extended Kalman Filter (EKF) algorithm to predict and analyze the historical monitoring data of the circuit breaker, determine whether the circuit breaker's operating status is abnormal, and check the abnormal status in advance to ensure the safety of the power system. When the EKF algorithm analyzes the historical monitoring data of the circuit breaker to determine the current operating status, it will cover up the outlier fluctuations caused by local abnormal change data due to the long-term stable operation, which will lead to the predicted value obtained when the local data selection range is inappropriate. There is a large deviation from the actual situation, which reduces the accuracy of abnormal monitoring of the circuit breaker operating status. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a circuit breaker operating status monitoring method and system based on big data.

[0006] In a first aspect, an embodiment of the present invention provides a circuit breaker operating status monitoring method based on big data, the method comprising the following steps: Sensors are placed around the circuit breaker to obtain the operating state vector at each acquisition moment; Determine the gain influence at each acquisition moment based on the running state vector at each acquisition moment by using a filtering algorithm, and determine the fluctuation characteristic value at each acquisition moment based on the curve fitting result in the data space constructed based on the gain influence; Determine the degree of fluctuation of each monitoring data at each collection moment according to the influence of the data fluctuation at the abnormal point of each monitoring data in the collection period on each monitoring data at each collection moment, and the fluctuation characteristic value at each collection moment; construct the updated Kalman gain matrix at each collection moment using the fluctuation degree of all monitoring data at each collection moment; The extended Kalman filter algorithm is used to obtain the prediction result of the operating state vector at each acquisition moment based on the updated Kalman gain matrix at each acquisition moment, and the monitoring result of the circuit breaker operating state is obtained based on the prediction result of the operating state vector at each acquisition moment.

[0007] In one embodiment, the determining of the gain impact at each acquisition moment includes the following specific methods: Taking the running state vector at each acquisition moment as input, using the extended Kalman filter algorithm to respectively obtain the Kalman gain matrix and the first prediction vector at each acquisition moment, wherein the first prediction vector is the prediction result of the running state vector; Determine the predictability of the running state vector at each collection moment based on the change in the similarity between the running state vector at each collection moment and the previous moment and the first prediction vector; The accumulated result of the product of the running state vector at each acquisition moment and the column vector in the Kalman gain matrix at each acquisition moment is used as the numerator; The sum of the predictability of the operating state vector at each acquisition moment and the constant parameter is used as the denominator; The ratio of the numerator to the denominator is taken as the gain impact at each acquisition moment.

[0008] In one embodiment, the determining of the predictability of the running state vector at each acquisition moment includes the following specific methods: The absolute value of the difference between the cosine similarity between the operating state vector at each acquisition moment and the adjacent previous moment and the cosine similarity between the first prediction vector at each acquisition moment and the adjacent previous moment is used as the input of the Singer function, and the absolute value of the output function value is used as the predictability of the operating state vector at each acquisition moment.

[0009] In one embodiment, the determining of the fluctuation characteristic value at each acquisition moment includes the following specific methods: The data space is constructed with all acquisition moments as the horizontal coordinate and the gain influence of all acquisition moments as the vertical coordinate, the gain influence of all acquisition moments is mapped into the data space to obtain a number of data points, and the fitting curve of all data points is obtained by curve fitting; Determine the deviation weight of each acquisition moment based on the fitting deviation of all acquisition moments on the fitting curve; The product of the absolute value of the difference between the fitting value on the fitting curve at each acquisition moment and the gain influence at each acquisition moment and the deviation weight at each acquisition moment is calculated as the fluctuation characteristic value at each acquisition moment.

[0010] In one embodiment, the determining of the deviation weight at each acquisition moment includes the following specific methods: The ratio of the fitting deviation on the fitting curve at each acquisition moment to the cumulative sum of the fitting deviations on the fitting curve at all acquisition moments is calculated as the deviation weight of each acquisition moment.

[0011] In one embodiment, the determination of the fluctuation degree of each monitoring data at each collection time includes the following specific methods: Take each monitoring data at all collection moments in the collection cycle as input, use anomaly detection to determine all abnormal points in each monitoring data, and take the collection moment corresponding to each abnormal point as a data abnormal moment; Determine the abnormal impact weight of each collection moment based on the degree to which each collection moment is affected by the data fluctuation at the adjacent data abnormal moments; Taking each collection moment as the center, taking a preset number of adjacent collection moments on the left and right as neighboring moments, calculating the discrete characteristic index of each monitoring data at each collection moment and all neighboring moments as the first characteristic value of each monitoring data at each collection moment; The product of the ratio of the first eigenvalue of each monitoring data at each collection moment to the distribution variance of each monitoring data in the collection period, the abnormal impact weight at each collection moment and the fluctuation eigenvalue at each collection moment is taken as the fluctuation degree of each monitoring data at each collection moment.

[0012] In one embodiment, the specific method of determining the abnormal impact weight of each acquisition moment includes: For each data anomaly moment, all monitoring data of all neighboring moments taken around each data anomaly moment are arranged in the order of value size to obtain a local monitoring data sequence for each data anomaly moment; Calculate the difference measurement results between the local monitoring data sequence at the data anomaly moment with the shortest time interval between each acquisition moment and the local monitoring data sequences at the remaining data anomaly moments, and take the average of the accumulated results of the difference measurement results at all data anomaly moments as the anomaly impact weight of each acquisition moment.

[0013] In one embodiment, the construction of the updated Kalman gain matrix at each acquisition moment includes the following specific methods: For any collection time, the fluctuation degree of all monitoring data in the running state vector at each collection time is linearly normalized, and each normalized fluctuation degree is used as a fluctuation evaluation factor; All the fluctuation evaluation factors at each collection moment are used as the main diagonal elements in the fluctuation evaluation factor matrix at each collection moment; all elements except the main diagonal in the fluctuation evaluation factor matrix at each collection moment are filled with 0 to obtain the fluctuation evaluation factor matrix at each collection moment; The product of the fluctuation evaluation factor matrix at each acquisition moment and the Kalman gain matrix at each acquisition moment is used as the updated Kalman gain matrix at each acquisition moment.

[0014] In one embodiment, the monitoring result of the circuit breaker operating state is obtained based on the prediction result of the operating state vector at each acquisition moment, and the specific method includes: Input the running state vector at each acquisition moment and the updated Kalman gain matrix at each acquisition moment into the extended Kalman filter algorithm to obtain the predicted running state vector at each acquisition moment; Calculate the absolute value of the difference between the running state vector at each acquisition moment and the same monitoring data in the predicted running state vector, and use the ratio of the absolute value of the difference to the same monitoring data in the running state vector as the deviation ratio of the same monitoring data; The deviation ratio of each type of monitoring data is compared with the preset warning threshold value. When the deviation ratio of any type of monitoring data is greater than or equal to the warning threshold value, it is considered that the operating state of the circuit breaker has changed significantly, and the collection results and deviation ratios of all types of monitoring data are sent to the circuit breaker maintenance personnel at the same time; when the deviation ratios of all types of monitoring data are less than the warning threshold value, it is considered that the operating state of the circuit breaker has not changed.

[0015] In the second aspect, an embodiment of the present application also provides a circuit breaker operating status monitoring system based on big data, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements the steps of any one of the above-mentioned circuit breaker operating status monitoring methods based on big data.

[0016] The beneficial effects of the technical solution of the present invention are: The present invention obtains the fluctuation characteristic value at each collection moment according to the fluctuation characteristic value and the change of each monitoring data in the operating state vector at each collection moment at all corresponding historical moments; reflects the difference degree of the operating state vector at each moment compared with the operating state vectors at other collection moments when performing data prediction through the fluctuation characteristic value; then, using the characteristic that the same abnormal state change will not occur repeatedly in a short period of time during the actual monitoring cycle of the circuit breaker operating state, resulting in different local fluctuations of data at the data abnormal moment, determines the fluctuation degree of each monitoring data at each collection moment, and uses the fluctuation degree to complete the update of the Kalman gain matrix, so that the EKF algorithm affects the outlier fluctuation generated by the local abnormal change data when analyzing the historical monitoring data of the circuit breaker to judge the current operating state, thereby improving the accuracy of the operating state vector prediction result, and further improving the accuracy of the circuit breaker carrying state monitoring result. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] 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.

[0018] Figure 1 The present invention is a flowchart of the steps of the circuit breaker operation status monitoring method based on big data. DETAILED DESCRIPTION

[0019] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the circuit breaker operation status monitoring method and system based on big data proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0021] The specific scheme of the circuit breaker operation status monitoring method and system based on big data provided by the present invention is described in detail below with reference to the accompanying drawings.

[0022] See also Figure 1 , which shows a flowchart of a method for monitoring the operation status of a circuit breaker based on big data provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Acquire the operation state vectors of a circuit breaker at several acquisition moments during operation.

[0023] The present invention aims to determine whether the operating state of the circuit breaker is normal by analyzing the monitoring data collected by various sensors when the circuit breaker is running. When the monitoring data is analyzed by the EKF algorithm, the Kalman gain matrix of each acquisition moment is calculated by analyzing the change characteristics of the monitoring data at adjacent acquisition moments and the change of each monitoring data at all acquisition moments, and the operating state of the circuit breaker is predicted based on the Kalman gain matrix to determine the moment when the operating state is abnormal. Therefore, the present application first needs to deploy sensors to collect a large amount of monitoring data.

[0024] Specifically, the sensors are arranged around the circuit breaker to ensure that the frequency of the sensors collecting monitoring data is consistent and the collection time is the same. The sensors include but are not limited to voltage sensors, current sensors, temperature sensors, and humidity sensors. In one embodiment of the present invention, the collection period is 5 minutes and the data collection frequency is 100 Hz. In other embodiments, the collection period and the collection frequency can be set by the implementer, and this application does not impose any special restrictions on this. For any collection moment, the vector composed of the monitoring data collected by all sensors at each collection moment is used as the operating state vector of each collection moment.

[0025] Step S002: Obtain the gain influence of each acquisition moment according to the difference of the running state vector between each acquisition moment and the adjacent acquisition moment; obtain the fluctuation characteristic value of each acquisition moment according to the difference of the gain influence between each acquisition moment and the adjacent acquisition moment.

[0026] During the operation of the circuit breaker, the different operating states of the circuit breaker will lead to different changes in the same monitoring data at different collection times. Therefore, the present invention obtains the gain impact at each collection time based on the fluctuation of each monitoring data in the operating state vector and the deviation between the predicted value and the observed value caused by the change of the Kalman gain between the collection times.

[0027] Specifically, for any collection time, taking the tth collection time as an example, the operation state vector of the tth collection time is input into the extended Kalman filter algorithm to obtain the Kalman gain matrix and the first prediction vector of the tth collection time, wherein the first prediction vector is the prediction result of the operation state vector; according to the difference between the operation state vectors of the tth collection time and the adjacent collection time, the gain influence of the tth collection time is obtained. Among them, the extended Kalman filter algorithm is a prior art, and this embodiment will not be described in detail here.

[0028] As an example, the calculation method for obtaining the gain influence at the t-th acquisition moment is as follows: In the formula, represents the gain influence at the tth acquisition moment; Represents the total number of all column vectors in the Kalman gain matrix at the tth acquisition moment; represents the jth column vector in the Kalman gain matrix at the tth acquisition moment; Represents the operating state vector at the tth acquisition moment; Represents the operating state vector at the t-1th acquisition time; represents the first prediction vector at the t-th acquisition moment; represents the first prediction vector at the t-1th acquisition time; represents the symplectic function; Indicates taking the absolute value; represents the cosine similarity between the running state vector at the t-th acquisition time and the running state vector at the t-1-th acquisition time; Represents the cosine similarity between the first prediction vector at the t-th acquisition time and the first prediction vector at the t-1-th acquisition time.

[0029] Among them, the molecule It reflects the deviation of the monitoring data at the tth collection moment. The operating state vector at the tth collection moment is multiplied by all column vectors in the Kalman gain matrix at the tth collection moment and accumulated. The larger the value of the numerator, the greater the difference between the monitoring data at the tth collection moment and the adjacent moments, and the greater the change in the operating state of the circuit breaker at the tth collection moment compared with the adjacent collection moments; the denominator reflects the predictability of the operating state vector at the tth collection moment, which is judged by the similarity between the change in the predicted value at the previous moment and the change in the observed value between the tth collection moment and the previous moment. The larger the denominator, the closer the change in the predicted value is to the change in the observed value, the smaller the possibility of deviation of the circuit breaker operating state at the tth collection moment compared with the t-1th collection moment, and the stronger the predictability.

[0030] It should be further explained that the magnitude of the gain effect reflects the deviation of the predicted value from the actual observed value at each acquisition moment. However, when there are noise points in the acquisition process of multiple sensors, the noise points will affect the predicted value and observed value measured at a certain acquisition moment, resulting in the calculated gain effect being inconsistent with the actual situation. Therefore, in order to avoid the influence of noise points on the predicted value during data acquisition, the gain effect at each acquisition moment is weighted according to the gain effect at adjacent acquisition moments to obtain the fluctuation characteristic value at each acquisition moment.

[0031] Specifically, a two-dimensional coordinate system is constructed with the acquisition time as the horizontal coordinate and the gain influence as the vertical coordinate, and the gain influence of each acquisition time is mapped to the two-dimensional coordinate system to obtain a collection data point, and a plurality of collection data points are obtained, and a fitting curve of all the collection data points is obtained by curve fitting. And the fitting deviation of each acquisition time on the fitting curve is calculated respectively.

[0032] Among them, curve fitting is a common technology in the field of data analysis, and the specific process is not repeated in this application. Commonly used curve fitting includes but is not limited to curve fitting based on local weighted regression, least squares fitting, and polynomial fitting. This application does not limit the specific method of curve fitting. Preferably, as an embodiment of the present application, the fitting curve is obtained by using the least squares fitting method.

[0033] First, the deviation weight of each acquisition moment is calculated according to the size of the fitting deviation at each acquisition moment, which is used to characterize the distribution outliers of the gain influence at each acquisition moment compared with other moments. The calculation process of the deviation weight at the tth acquisition moment is as follows: In the formula, is the bias weight at the tth acquisition moment, is the fitting deviation at the tth acquisition moment; m is the number of acquisition moments.

[0034] Afterwards, the fluctuation characteristic value of each acquisition moment is determined in combination with the size of the fitting deviation at each acquisition moment. The larger the fluctuation characteristic value, the more significant the fluctuation difference between the data fitting result at the acquisition moment and the gain influence, and the greater the difference between the operating state vector at this moment and the operating state vector at other acquisition moments.

[0035] In the formula, is the fluctuation characteristic value at the tth acquisition moment, It is the absolute value of the difference between the fitting value on the fitting curve at the t-th acquisition moment and the gain effect at the t-th acquisition moment.

[0036] Step S003: Obtain the fluctuation degree of each monitoring data at each collection moment according to the abnormal points of each monitoring data within the collection period and the influence of data fluctuation at the abnormal moment on each monitoring data at each collection moment; obtain the updated Kalman gain matrix at each collection moment according to the fluctuation degree.

[0037] It should be noted that in the operating state vector at each acquisition moment, each type of monitoring data can reflect whether there is an abnormality in the operating state of the circuit breaker, but different types of monitoring data have different data sensitivities to abnormal operating states of the circuit breaker. For example, under normal circumstances, the operating voltage range of the circuit breaker is usually between 70%-110% of the rated voltage; and the installation environment temperature range of the circuit breaker is usually -40℃-40℃. When the operating state of the circuit breaker is abnormal, it is usually manifested as a change in electrical parameters that is more significant than the change in temperature and humidity. Therefore, if a certain type of monitoring data has large data fluctuations at multiple acquisition moments, it is necessary to analyze the data fluctuations to evaluate whether the corresponding operating state of the circuit breaker has changed.

[0038] Furthermore, for any type of monitoring data, if the monitoring data produces a large number of collection moments when the monitoring data changes significantly, it means that the monitoring data is more likely to produce larger data fluctuations, and there should be a larger fluctuation range in the entire data collection cycle. If the fluctuation range of a certain type of monitoring data is small as a whole, and only has a large degree of fluctuation at the collection moment within a certain time period, it means that the data fluctuation within this time period is more likely to be caused by abnormal operation of the circuit breaker.

[0039] Specifically, for any type of monitoring data, taking the yth type of monitoring data as an example, anomaly detection is used to detect abnormal points in all the yth type of monitoring data, and the collection time corresponding to the abnormal point is marked as the data abnormal time.

[0040] It should be noted that data anomaly detection is a commonly used technology in the field of data processing, and the specific process will not be repeated. Commonly used data anomaly detection methods include but are not limited to outlier factor LOF detection, isolation forest detection, and 3sigma criterion detection. This application does not impose any special restrictions on the method of anomaly detection. Preferably, as an embodiment of this application, LOF detection is used to obtain abnormal points in the yth type of monitoring data.

[0041] Furthermore, for each acquisition moment, the closer the time interval between the data abnormal moment is, the more likely it is that the circuit breaker is in the same operating state as the data abnormal moment. Normally, when a circuit breaker failure causes an abnormal operating state, maintenance personnel will perform targeted maintenance based on the cause of the failure, and the same failure will not recur in a short period of time. Therefore, if a data abnormal moment is inconsistent with the local fluctuation of the yth type of monitoring data at the adjacent data abnormal moment, the data abnormal moment is more likely to correspond to the change in operating state when the circuit breaker fails.

[0042] Specifically, with each acquisition moment as the center, k adjacent acquisition moments are taken on the left and right as neighboring moments, and the discrete characteristic indicators of 2k+1 y-th monitoring data at each acquisition moment and 2k neighboring moments are calculated as the first characteristic value of the y-th monitoring data at each acquisition moment. The larger the discrete characteristic indicator, the more complex the data fluctuation degree at the acquisition moment within the time period. Secondly, for each data abnormal moment, the 2k+1 y-th monitoring data taken with each data abnormal moment as the center are arranged in the order of value size to obtain the local monitoring data sequence of each data abnormal moment. In this embodiment, the size of k is set to an empirical value of 10. In other embodiments, the implementer can set the size of k according to the data acquisition frequency, and this application does not impose any special restrictions on this.

[0043] The discrete characteristic index is used to evaluate the degree of discreteness of the distribution of the 2k+1 y-th monitoring data. The greater the degree of discreteness, the greater the value of the corresponding discrete characteristic index. Under the premise of achieving this purpose, in different embodiments, different evaluation indicators such as information entropy, distribution variance, and coefficient of variation can be used as the discrete characteristic index.

[0044] Here, the fluctuation degree of each monitoring data at each collection time is calculated to characterize the local fluctuation degree of each monitoring data at each collection time compared with the distribution of monitoring data in the collection period. The calculation process of the fluctuation degree of the yth monitoring data at the tth collection time is as follows: In the formula, is the abnormal impact weight of the tth collection moment, M is the number of abnormal data moments in the collection period, is the local monitoring data sequence with the shortest time interval between the data anomaly and the t-th acquisition moment, is the local monitoring data sequence at the bth data abnormal moment in the acquisition period, is a local monitoring data series , The difference measurement results between .

[0045] The difference measurement result is used to measure the local monitoring data sequence , The greater the difference, the greater the value of the corresponding difference measurement result. Under the premise of achieving this purpose, in different embodiments, different measurement results such as DTW distance, Euclidean distance, value variance, etc. can be used as the difference measurement result.

[0046] Afterwards, the fluctuation degree of the yth monitoring data at the tth collection moment is determined by combining the influence of the adjacent data abnormal moments on the tth collection moment: In the formula, is the fluctuation degree of the y-th monitoring data at the t-th collection time, is the first eigenvalue of the yth type of monitoring data at the tth collection time, It is the distribution variance of the y-th monitoring data at all collection times within the collection period.

[0047] Among them, the smaller the overall data fluctuation range of the y-th monitoring data in the entire cycle, the more prominent the local fluctuation of the y-th monitoring data at the t-th collection moment, indicating that the y-th monitoring data in the local time period of the t-th collection moment reflects that the operating status of the circuit breaker is more likely to change to a greater extent; at the same time, the stronger the difference between the local monitoring data sequences at the shortest data abnormal moment and the other data abnormal moments, it means that the circuit breaker may have a fault that causes a large change in the operating status, and the greater the impact on the monitoring data at the t-th collection moment.

[0048] Furthermore, for any collection moment, the degree of fluctuation of all monitoring data in the operating state vector at each collection moment is linearly normalized, and each normalized degree of fluctuation is recorded as a fluctuation evaluation factor. Secondly, the fluctuation evaluation factors of all monitoring data in the operating state vector at each collection moment are used as the main diagonal elements in the fluctuation evaluation factor matrix at each collection moment; all elements except the main diagonal in the fluctuation evaluation factor matrix at each collection moment are set to 0, and the fluctuation evaluation factor matrix at each collection moment is obtained; then, the product of the fluctuation evaluation factor matrix at each collection moment and the Kalman gain matrix at each collection moment is used as the updated Kalman gain matrix at each collection moment.

[0049] Step S004: Perform real-time monitoring of the circuit breaker operating status according to the updated Kalman gain matrix.

[0050] Specifically, for any collection time, each collection time is recorded as a target collection time; the operation state vector at the target collection time and the updated Kalman gain matrix at the target collection time are input into the extended Kalman filter algorithm to obtain the predicted operation state vector at the target collection time. The extended Kalman filter algorithm is a well-known technology, and the specific process is not repeated here.

[0051] Furthermore, in order to ensure the safe operation of the circuit breaker, when any monitoring data of the circuit breaker operating state has a predicted deviation, it should be considered that the circuit breaker operating state has changed, and the maintenance personnel should be reminded to perform on-site maintenance. Therefore, in this application, the absolute value of the difference between the operating state vector at the target acquisition time and the same monitoring data in the predicted operating state vector is calculated respectively, and the ratio of the absolute value of the difference to the same monitoring data in the operating state vector is used as the deviation ratio of the same monitoring data to obtain the deviation ratio of all types of monitoring data at the target acquisition time. And compared with the preset early warning threshold, when the deviation ratio of any type of monitoring data is greater than or equal to the early warning threshold, it is considered that the circuit breaker operating state has changed significantly, and the collection results and deviation ratios of all types of monitoring data are sent to the circuit breaker maintenance personnel at the same time; when the deviation ratios of all types of monitoring data are less than the early warning threshold, it is considered that the circuit breaker operating state has not changed.

[0052] The present invention also proposes a circuit breaker operating status monitoring system based on big data, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the circuit breaker operating status monitoring method based on big data in steps S001 to S004 are implemented.

[0053] It should be noted that the above-described embodiments 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, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the 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.

[0054] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A circuit breaker operation status monitoring method based on big data, characterized in that: The method comprises the following steps: Sensors are placed around the circuit breaker to obtain the operating state vector at each acquisition moment; Determine the gain influence at each acquisition moment based on the running state vector at each acquisition moment by using a filtering algorithm, and determine the fluctuation characteristic value at each acquisition moment based on the curve fitting result in the data space constructed based on the gain influence; Determine the degree of fluctuation of each monitoring data at each collection moment according to the influence of the data fluctuation at the abnormal point of each monitoring data in the collection period on each monitoring data at each collection moment, and the fluctuation characteristic value at each collection moment; construct the updated Kalman gain matrix at each collection moment using the fluctuation degree of all monitoring data at each collection moment; The extended Kalman filter algorithm is used to obtain the prediction result of the operating state vector at each acquisition moment based on the updated Kalman gain matrix at each acquisition moment, and the monitoring result of the circuit breaker operating state is obtained based on the prediction result of the operating state vector at each acquisition moment.

2. The circuit breaker operation status monitoring method based on big data according to claim 1 is characterized in that: The specific method of determining the gain influence at each acquisition moment includes: Taking the running state vector at each acquisition moment as input, using the extended Kalman filter algorithm to respectively obtain the Kalman gain matrix and the first prediction vector at each acquisition moment, wherein the first prediction vector is the prediction result of the running state vector; Determine the predictability of the running state vector at each collection moment based on the change in the similarity between the running state vector at each collection moment and the previous moment and the first prediction vector; The accumulated result of the product of the running state vector at each acquisition moment and the column vector in the Kalman gain matrix at each acquisition moment is used as the numerator; The sum of the predictability of the operating state vector at each acquisition moment and the constant parameter is used as the denominator; The ratio of the numerator to the denominator is taken as the gain impact at each acquisition moment.

3. The circuit breaker operation status monitoring method based on big data according to claim 2 is characterized in that: The specific method of determining the predictability of the operating state vector at each acquisition moment is as follows: The absolute value of the difference between the cosine similarity between the operating state vector at each acquisition moment and the adjacent previous moment and the cosine similarity between the first prediction vector at each acquisition moment and the adjacent previous moment is used as the input of the Singer function, and the absolute value of the output function value is used as the predictability of the operating state vector at each acquisition moment.

4. The circuit breaker operation status monitoring method based on big data according to claim 1 is characterized in that: The specific method of determining the fluctuation characteristic value at each acquisition moment includes: The data space is constructed with all acquisition moments as the horizontal coordinate and the gain influence of all acquisition moments as the vertical coordinate, the gain influence of all acquisition moments is mapped into the data space to obtain a number of data points, and the fitting curve of all data points is obtained by curve fitting; Determine the deviation weight of each acquisition moment based on the fitting deviation of all acquisition moments on the fitting curve; The product of the absolute value of the difference between the fitting value on the fitting curve at each acquisition moment and the gain influence at each acquisition moment and the deviation weight at each acquisition moment is calculated as the fluctuation characteristic value at each acquisition moment.

5. The circuit breaker operation status monitoring method based on big data according to claim 4 is characterized in that: The specific method of determining the deviation weight at each acquisition moment includes: The ratio of the fitting deviation on the fitting curve at each acquisition moment to the cumulative sum of the fitting deviations on the fitting curve at all acquisition moments is calculated as the deviation weight of each acquisition moment.

6. The circuit breaker operation status monitoring method based on big data according to claim 1 is characterized in that: The specific method for determining the fluctuation degree of each monitoring data at each collection moment includes: Take each monitoring data at all collection moments in the collection cycle as input, use anomaly detection to determine all abnormal points in each monitoring data, and take the collection moment corresponding to each abnormal point as a data abnormal moment; Determine the abnormal impact weight of each collection moment based on the degree to which each collection moment is affected by the data fluctuation at the adjacent data abnormal moments; Taking each collection moment as the center, taking a preset number of adjacent collection moments on the left and right as neighboring moments, calculating the discrete characteristic index of each monitoring data at each collection moment and all neighboring moments as the first characteristic value of each monitoring data at each collection moment; The product of the ratio of the first eigenvalue of each monitoring data at each collection moment to the distribution variance of each monitoring data in the collection period, the abnormal impact weight at each collection moment and the fluctuation eigenvalue at each collection moment is taken as the fluctuation degree of each monitoring data at each collection moment.

7. The circuit breaker operation status monitoring method based on big data according to claim 6 is characterized in that: The specific method of determining the abnormal impact weight of each acquisition moment includes: For each data anomaly moment, all monitoring data of all neighboring moments taken around each data anomaly moment are arranged in the order of value size to obtain a local monitoring data sequence for each data anomaly moment; Calculate the difference measurement results between the local monitoring data sequence at the data anomaly moment with the shortest time interval between each acquisition moment and the local monitoring data sequences at the remaining data anomaly moments, and take the average of the accumulated results of the difference measurement results at all data anomaly moments as the anomaly impact weight of each acquisition moment.

8. The circuit breaker operation status monitoring method based on big data according to claim 1 is characterized in that: The specific method of constructing the updated Kalman gain matrix at each acquisition moment includes: For any collection time, the fluctuation degree of all monitoring data in the running state vector at each collection time is linearly normalized, and each normalized fluctuation degree is used as a fluctuation evaluation factor; All the fluctuation evaluation factors at each collection moment are used as the main diagonal elements in the fluctuation evaluation factor matrix at each collection moment; Fill all elements except the main diagonal in the fluctuation evaluation factor matrix at each collection moment with 0 to obtain the fluctuation evaluation factor matrix at each collection moment; The product of the fluctuation evaluation factor matrix at each acquisition moment and the Kalman gain matrix at each acquisition moment is used as the updated Kalman gain matrix at each acquisition moment.

9. The circuit breaker operation status monitoring method based on big data according to claim 1 is characterized in that: The monitoring result of the circuit breaker operating state is obtained based on the prediction result of the operating state vector at each acquisition moment, and the specific method includes: Input the running state vector at each acquisition moment and the updated Kalman gain matrix at each acquisition moment into the extended Kalman filter algorithm to obtain the predicted running state vector at each acquisition moment; Calculate the absolute value of the difference between the running state vector at each acquisition moment and the same monitoring data in the predicted running state vector, and use the ratio of the absolute value of the difference to the same monitoring data in the running state vector as the deviation ratio of the same monitoring data; The deviation ratio of each type of monitoring data is compared with the preset warning threshold value. When the deviation ratio of any type of monitoring data is greater than or equal to the warning threshold value, it is considered that the operating state of the circuit breaker has changed significantly, and the collection results and deviation ratios of all types of monitoring data are sent to the circuit breaker maintenance personnel at the same time; when the deviation ratios of all types of monitoring data are less than the warning threshold value, it is considered that the operating state of the circuit breaker has not changed.

10. A circuit breaker operation status monitoring system based on big data, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the circuit breaker operating status monitoring method based on big data as described in any one of claims 1 to 9 are implemented.

Images