Electrical equipment state monitoring method and system

Data is collected through multi-function sensors and smart meters, outliers are eliminated and outliers are used to predict using LSTM models, and sampling frequency is dynamically adjusted, which solves the problems of data loss and noise interference in electrical equipment status monitoring, and improves monitoring efficiency and data quality.

CN119025841AActive Publication Date: 2024-11-26GUANGZHOU YANGCHENG ELECTRICAL EQUIP CO LTD

Patent Information

Application Number
CN202411432475.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-14
Publication Date
2024-11-26
Estimated Expiration
2044-10-14

AI Technical Summary

Technical Problem

The existing electrical equipment status monitoring system is prone to data loss and noise interference during data acquisition and processing, resulting in a decrease in monitoring data quality and a decrease in the accuracy of the prediction model. As the detection item data increases, the sampling frequency cannot be dynamically adjusted, which reduces the Monitor efficiency.

Method used

Data is collected through multi-function sensors and smart meters, outlier value removal and interpolation processing are carried out, and a long and short-term memory network LSTM model is built for time series prediction, risk scores are calculated and sampling frequency is dynamically adjusted, combining visual display and secure storage management.

Benefits of technology

It improves the data quality and efficiency of electrical equipment status monitoring, ensures dynamic adjustment of sampling frequency according to real-time data changes, and improves the stability and reliability of the monitoring system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025841A_ABST
    Figure CN119025841A_ABST
Patent Text Reader

Abstract

The invention discloses an electrical equipment state monitoring method and system, and relates to the technical field of electrical equipment monitoring, and the method comprises the steps: carrying out the data collection according to a monitored electrical equipment collection item, and carrying out the elimination of an abnormal value; setting an initial acquisition frequency, respectively carrying out linear interpolation and spline interpolation based on the acquisition items, and filling the data of the acquisition items; and constructing a long short-term memory (LSTM) network model to carry out time sequence prediction. According to the method, through comprehensive data acquisition of the multifunctional sensor and the intelligent electric meter, comprehensive monitoring of electrical equipment states and environmental factors is ensured, interpolation operation is carried out through a linear interpolation method and a cubic spline interpolation method, the effect of carrying out interpolation of different complexities according to different data types is achieved, and the method is suitable for popularization and application. The accuracy and smoothness of the interpolation result are improved, smooth transition of the electrical data on the time sequence is ensured, and risk assessment calculation can be carried out by calculating the comprehensive deviation value with the predicted value of the LSTM model.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electrical equipment monitoring, and in particular to an electrical equipment state monitoring method and system. Background Art

[0002] Electrical equipment condition monitoring technology usually refers to recording multiple data of the monitored equipment. With the rapid development of information technology and sensor technology, modern electrical equipment condition monitoring systems have gradually introduced advanced technologies such as smart sensors, the Internet of Things (IoT) and big data analysis, making the condition monitoring of electrical equipment more intelligent and efficient, and able to achieve real-time monitoring and remote data collection. In recent years, the application of artificial intelligence (AI) and machine learning (ML) technologies in electrical equipment condition monitoring has begun to show great potential, which can not only improve monitoring accuracy and response speed, but also realize intelligent decision-making support, providing a strong guarantee for the safe and stable operation of the power system.

[0003] Although modern electrical equipment condition monitoring technology has made great progress, the existing monitoring system often faces problems of missing data and noise interference during data collection and processing, depending on the different collection item data and the collection frequency of the collection equipment. Data missing and noise will not only affect the quality of monitoring data, but also lead to a decrease in the accuracy of the prediction model. At the same time, with the increase of detection item data, the existing electrical equipment condition monitoring leads to a complex data volume and inconvenience in comprehensive dynamic adjustment based on the current monitoring risk. It is impossible to dynamically adjust the sampling frequency according to real-time monitoring data and risk scores, which reduces the monitoring efficiency of electrical equipment status. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing electrical equipment status monitoring methods and systems, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that in the process of data collection and processing, the existing monitoring system often faces the problems of missing data and noise interference depending on the different collection item data and the collection frequency of the collection equipment. Missing data and noise will not only affect the quality of the monitoring data, but also lead to a decrease in the accuracy of the prediction model. At the same time, with the increase of detection item data, the existing electrical equipment status monitoring leads to a complicated data volume and inconvenience in comprehensive dynamic adjustment based on the current monitoring risk. The sampling frequency cannot be dynamically adjusted according to the real-time monitoring data and risk score, which reduces the monitoring efficiency of the electrical equipment status.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for monitoring the state of electrical equipment, comprising:

[0007] Collect data based on the monitored electrical equipment collection items and remove abnormal values;

[0008] Set the initial acquisition frequency and perform linear interpolation and spline interpolation based on the acquisition items to fill in the acquisition item data;

[0009] Construct a long short-term memory network (LSTM) model for time series prediction, comprehensively analyze the deviation between the actual value and the predicted value, calculate the risk score, set the sampling period, and dynamically adjust the sampling frequency based on the risk score to analyze the efficiency of equipment status monitoring;

[0010] Based on the visualization of collected data and risk score data, the data is securely stored and managed.

[0011] As a preferred solution of the electrical equipment status monitoring method of the present invention, wherein: the data collection according to the monitored electrical equipment collection items and the outlier removal include:

[0012] The electrical equipment collects data according to collection items through multifunctional sensors and smart meters, and the collection items include electrical data and environmental data, wherein the electrical data includes voltage deviation and frequency deviation, and the environmental data includes temperature, vibration and noise and the monitoring frequency of the corresponding collection items;

[0013] A low-pass filter is used to smooth the data, retaining the low-frequency effective signal and removing the high-frequency noise;

[0014] Use the three sigma rule to eliminate outliers, calculate the mean and standard deviation of the collected data, and eliminate outliers, expressed as:

[0015]

[0016] Where X represents the data of the collection item, μ represents the mean of the collection item, and σ represents the standard deviation of the collection item;

[0017] Values ​​outside the range are considered outliers and removed.

[0018] As a preferred solution of the electrical equipment status monitoring method of the present invention, wherein: the initial acquisition frequency is set and linear interpolation and spline interpolation are performed based on the acquisition items to fill the acquisition item data, including:

[0019] The maximum monitoring frequency of the collection item is used as the initial collection frequency;

[0020] Time series synchronization is performed based on the collected item data, and the environmental data is filled using linear interpolation, which is expressed as:

[0021]

[0022] Where X t and X t+nrepresents the collected environmental data of events t and t+n, X t+i represents the collected environmental data after interpolation, i represents the interpolation position, and n represents the time step;

[0023] The electrical data based on the collected items is filled with data using spline interpolation method, which is expressed as:

[0024] S i (x) = a i +b i (xx i )+c i (xx i ) 2 +d i (xx i ) 3 ;

[0025] where a i 、b i 、c i and d i is the coefficient of the cubic spline function, x represents the independent variable time, x i represents the i-th electrical data collection time point, S i (x) represents the interpolation result of the i-th segment interval;

[0026] The time point that needs to be interpolated is determined by the initial acquisition frequency, and the interval to which the time point that needs to be interpolated belongs is determined based on the acquisition time of the electrical data, and the interpolation result is calculated by the spline function.

[0027] As a preferred solution of the electrical equipment status monitoring method of the present invention, wherein: the long short-term memory network LSTM model is constructed to perform time series prediction, and the deviation between the actual value and the predicted value is comprehensively analyzed and collected to calculate the risk score, including:

[0028] Arrange the interpolated data series in chronological order and standardize the data;

[0029] Construct a long short-term memory network LSTM model for time series prediction, including input layer, hidden layer and output layer. The input layer receives the collected data of the collection item, the hidden layer and the output layer recognize the time series through the LSTM unit, and the output of the last LSTM unit is used as the predicted value of the future time.

[0030] Based on the collection item data at time t as the actual collection value, the predicted value of the long short-term memory network LSTM model at time t is compared, and the absolute value of the difference between the actual collection value and the predicted value is calculated as the absolute deviation value;

[0031] Based on the absolute deviation value, the relative deviation and trend deviation between the actual value and the predicted value are comprehensively considered and expressed as:

[0032]

[0033] CDI t Indicates the comprehensive deviation value, AE t Indicates the absolute deviation value at time t, Y t-1 represents the actual collected value at time t-1, Represents the LSTM model prediction value at time t-1, Y t represents the actual collected value at time t, Represents the LSTM model prediction value at time t;

[0034] Based on the Comprehensive Deviation Index (CDI) t The linear regression model is used to determine the risk score, which is expressed as:

[0035] R t =α+β·CDI t ;

[0036] Where α represents the baseline value of the risk score, R t represents the risk score at time t, β represents the weight of the comprehensive deviation index;

[0037] Analyze the data distribution of risk scores in historical data, based on the 95th percentile as the risk threshold;

[0038] If the calculated risk score is greater than or equal to the risk threshold, it is determined to be high risk, and the maximum frequency of the monitoring frequency data of the collection item is set as the collection frequency;

[0039] If the calculated risk score is less than the risk threshold, it is judged as low risk and the collection frequency is dynamically set.

[0040] As a preferred solution of the electrical equipment status monitoring method of the present invention, wherein: the setting of the sampling period and the dynamic adjustment of the sampling frequency based on the risk score to analyze the efficiency of equipment status monitoring include:

[0041] The sampling period is set based on the current acquisition frequency, expressed as:

[0042]

[0043] Where T t represents the sampling period of the risk score at time t, F' t Indicates the acquisition frequency at the current time t;

[0044] During the risk score sampling period, based on the risk score R t The dynamic adjustment sampling frequency is expressed as:

[0045]

[0046] where F t Represents the dynamic sampling frequency, R min represents the minimum risk score within the sampling period, R 95 represents the 95th percentile of the risk score within the sampling period, F max Indicates the maximum sampling frequency within the sampling period, F min Indicates the minimum sampling frequency within the sampling period;

[0047] The calculation based on the dynamic sampling frequency replaces the initial sampling frequency, analyzes the dynamic energy consumption, and calculates the interpolation between the dynamic energy and the benchmark energy consumption, which is expressed as:

[0048]

[0049] ΔE=E d -E d ;

[0050] Where E d represents the dynamic energy consumption within the sampling period, ΔE represents the energy consumption difference, and E b Indicates the baseline energy consumption during the sampling period;

[0051] The efficiency of equipment status monitoring is analyzed based on the energy consumption difference of the sampling period, which is expressed as:

[0052]

[0053] Where η is the efficiency of equipment status monitoring, N is the total number of sampling cycles, and ΔE i Represents the energy consumption difference of the i-th sampling period, E b,i Represents the benchmark energy consumption of the i-th sampling period.

[0054] As a preferred solution of the electrical equipment status monitoring method of the present invention, wherein: the visual display based on the collected data and the risk score data includes:

[0055] Use the Seaborn visualization library in Python to collect and confirm that the data to be displayed includes the risk score R t , sampling frequency F t , Comprehensive Deviation Value CDI t , energy consumption difference ΔE, efficiency of state monitoring η, actual collection value Y t And the LSTM model predicted value

[0056] Use Matplotlib to plot the risk score and sampling frequency change graph, use a line graph to show the data changes, and mark the 95 percentile threshold line. Then draw a comparison chart of the actual value and the predicted value, add legends and annotations, mark the key data points in the chart, and use Matplotlib to mark them.

[0057] As a preferred solution of the electrical equipment status monitoring method of the present invention, the secure storage and management of data refers to using the relational database PostgreSQL for structured data storage and management, using ETL tools for data storage and management, and regularly updating the risk score R t , efficiency η of state monitoring, sampling frequency F t , Comprehensive Deviation Value CDI t , energy consumption difference ΔE, actual collection value Y t And the LSTM model predicted value Store in the database, use the database backup tool mysqldump for regular backups, and use the database security tool AWS RDS to protect database security and access control.

[0058] Another object of the present invention is to provide a system for monitoring the state of an electrical device, which comprises:

[0059] The data acquisition module collects monitoring data of electrical equipment through acquisition equipment, including electrical data and environmental data;

[0060] The outlier removal module calculates the mean and standard deviation of the data and removes abnormal data that exceeds 3 standard deviations;

[0061] The data interpolation module performs linear interpolation and spline interpolation to fill the missing data based on the initial collection frequency of the collection items;

[0062] LSTM model prediction module, which builds a long short-term memory network LSTM model for time series prediction, analyzes the deviation between the actual value and the predicted value, and calculates the risk score;

[0063] Frequency adjustment module, which sets the sampling period and dynamically adjusts the sampling frequency based on the risk score;

[0064] Visual display module, which performs visual display based on collected data and risk score data;

[0065] The data management module is used to store and manage data securely.

[0066] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned electrical equipment status monitoring method when executing the computer program.

[0067] A computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned electrical equipment status monitoring method when executed by a processor.

[0068] The beneficial effects of the present invention are as follows: comprehensive data collection by multifunctional sensors and smart meters ensures comprehensive monitoring of electrical equipment status and environmental factors; interpolation operations performed by linear interpolation and cubic spline interpolation achieve the effect of interpolation of different complexities according to different data types, improve the accuracy and smoothness of the interpolation results, ensure smooth transition of electrical data in time series; risk assessment calculations can be performed by calculating the comprehensive deviation value between the predicted value and the LSTM model, and the sampling frequency can be adjusted dynamically, thereby timely adjusting the sampling frequency to achieve the effect of adjusting the sampling frequency according to changes in timely monitoring data, and further improving the utilization efficiency of electrical equipment status monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0070] Figure 1 The figure is a flow chart of the method for monitoring the condition of electrical equipment.

[0071] Figure 2 This is a structural diagram of the electrical equipment condition monitoring system. DETAILED DESCRIPTION

[0072] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0073] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0074] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0075] Example 1, reference Figure 1 , which is the first embodiment of the present invention, and provides an electrical equipment status monitoring method, the electrical equipment status monitoring method comprising:

[0076] S1, collect data according to the monitored electrical equipment collection items and remove abnormal values;

[0077] Preferably, data collection is performed according to the monitored electrical equipment collection items, and outliers are eliminated, including:

[0078] The electrical equipment collects data according to collection items through multifunctional sensors and smart meters, and the collection items include electrical data and environmental data, wherein the electrical data includes voltage deviation and frequency deviation, and the environmental data includes temperature, vibration and noise and the monitoring frequency of the corresponding collection items;

[0079] A low-pass filter is used to smooth the data, retaining the low-frequency effective signal and removing the high-frequency noise;

[0080] Use the three sigma rule to eliminate outliers, calculate the mean and standard deviation of the collected data, and eliminate outliers, expressed as:

[0081]

[0082] Where X represents the data of the collection item, μ represents the mean of the collection item, and σ represents the standard deviation of the collection item;

[0083] Values ​​outside the range are considered outliers and removed.

[0084] Comprehensive data collection by multifunctional sensors and smart meters ensures comprehensive monitoring of electrical equipment status and environmental factors. Low-pass filters are used for data smoothing to effectively remove high-frequency noise, retain useful signals, and improve data accuracy. After removing outliers, the mean and standard deviation of the data can more accurately reflect the actual situation, providing a reliable data basis for subsequent data analysis and decision-making. Combined with data collection, smoothing, and outlier removal, the monitoring system can reflect the operating status of electrical equipment and environmental changes in real time and accurately, thereby improving the stability and reliability of the system.

[0085] S2, setting the initial acquisition frequency and performing linear interpolation and spline interpolation based on the acquisition items to fill in the acquisition item data;

[0086] Preferably, the initial acquisition frequency is set and linear interpolation and spline interpolation are performed based on the acquisition items to fill the acquisition item data, including:

[0087] The maximum monitoring frequency of the collection item is used as the initial collection frequency;

[0088] Time series synchronization is performed based on the collected item data, and the environmental data is filled using linear interpolation, which is expressed as:

[0089]

[0090] Where X t and X t+n represents the collected environmental data of events t and t+n, X t+i represents the collected environmental data after interpolation, i represents the interpolation position, and n represents the time step;

[0091] The electrical data based on the acquisition items are filled using the spline interpolation method, which is expressed as:

[0092] S i (x) = a i +b i (xx i )+c i (xx i ) 2 +d i (xx i ) 3 ;

[0093] where a i , b i 、c i and d i is the coefficient of the cubic spline function, x represents the independent variable time, x i represents the i-th electrical data collection time point, S i (x) represents the interpolation result of the i-th segment interval, where the acquisition time x i and x i+1 between as interval;

[0094] The spline function is determined by the data collected from the electrical data and is expressed as:

[0095] S i (x i )=V i ;

[0096] S i (x i +1)=V i+1 ;

[0097] Where V i and V i+1 Respectively represent the acquisition time x i and x i+1 The electrical appliance data collection value;

[0098] The continuity of the first-order derivative and the continuity of the second-order derivative are performed separately, and a system of equations is formed, which is expressed as:

[0099] S' i (x i+1 )=S' i+1 (x i+1 );

[0100] b i +2c i (xx i )+3d i (xx i ) 2 =S' i (x);

[0101] S”(x i+1 )=S” i+1 (x i+1 );

[0102] 2c i +6d i (xx i )=S” i (x);

[0103] Where S' i (x) represents the first derivative of the i-th segment interval, S” i (x) represents the second derivative of the i-th segment interval;

[0104] Set the natural boundary conditions, expressed as:

[0105] S'0(x0) = 0;

[0106] S” n-1 (x n )=0;

[0107] Where S'0(x0) represents the second derivative at the starting point of the first segment interval, S' n-1 (x n ) indicates the end point x of the last segment interval n The second derivative at ;

[0108] Solve the system of equations using linear algebra to determine the coefficients of all spline functions;

[0109] The time point that needs to be interpolated is determined by the initial acquisition frequency, and the interval to which the time point that needs to be interpolated belongs is determined based on the acquisition time of the electrical data, and the interpolation result is calculated by the spline function.

[0110] By setting the initial collection frequency through the maximum frequency, the time series synchronization of each collection item data is achieved, ensuring the consistency of data on the same time axis, which is convenient for subsequent data analysis and processing. The linear interpolation method is used to adapt to the environmental data in the collected data and perform interpolation filling. The interpolation results can be calculated quickly to improve the continuity and integrity of the data. The cubic spline interpolation method is used to fill the electrical data to improve the accuracy and smoothness of the interpolation results, ensure the smooth transition of the electrical data in the time series, reduce the interpolation error, ensure the smoothness and natural transition of the interpolation curve, and improve the credibility of the interpolation results. Through data synchronization, smoothing processing and outlier elimination, the data quality of the monitoring system is improved, providing a reliable data basis for subsequent trend analysis and dynamic risk assessment.

[0111] S3, build a long short-term memory network LSTM model for time series prediction, comprehensively analyze the deviation between the actual value and the predicted value, calculate the risk score, set the sampling period, and dynamically adjust the sampling frequency based on the risk score to analyze the efficiency of equipment status monitoring;

[0112] Preferably, a long short-term memory network LSTM model is constructed to perform time series prediction, and the deviation between the actual value and the predicted value is comprehensively analyzed and the risk score is calculated, including:

[0113] Arrange the interpolated data series in chronological order and standardize the data;

[0114] Construct a long short-term memory network LSTM model for time series prediction, including input layer, hidden layer and output layer. The input layer receives the collected data of the collection item, the hidden layer and the output layer recognize the time series through the LSTM unit, and the output of the last LSTM unit is used as the predicted value of the future time.

[0115] Use the training set and the mean square error loss function to calculate the loss, expressed as:

[0116]

[0117] Where k represents the total number of samples, Y i Indicates the actual collected value. Represents the LSTM model prediction value;

[0118] The Adam optimizer is used to iteratively optimize the model parameters by using the gradient descent method. When the loss of the LSTM model no longer decreases significantly during the continuous iteration process, the iteration is stopped and the model parameters are output to update the LSTM model.

[0119] Based on the collection item data at time t as the actual collection value, the predicted value of the long short-term memory network LSTM model at time t is compared, and the absolute value of the difference between the actual collection value and the predicted value is calculated as the absolute deviation value;

[0120] Based on the absolute deviation value, the relative deviation and trend deviation between the actual value and the predicted value are comprehensively considered and expressed as:

[0121]

[0122] CDI t Indicates the comprehensive deviation value, AE t Indicates the absolute deviation value at time t, Y t-1 represents the actual collected value at time t-1, Represents the LSTM model prediction value at time t-1, Y t represents the actual collected value at time t, Represents the LSTM model prediction value at time t;

[0123] Based on the Comprehensive Deviation Index (CDI) t The linear regression model is used to determine the risk score, which is expressed as:

[0124] R t =α+β·CDI t ;

[0125] Where α represents the baseline value of the risk score, R t represents the risk score at time t, β represents the weight of the comprehensive deviation index;

[0126] Use the least squares method to optimize α and β using the training set, and define the optimization objective function, which is expressed as:

[0127]

[0128] Where G represents the output of the objective function, T represents the total number of samples, and R' t Indicates actual value;

[0129] Determine α and β based on minimizing the output of the objective function;

[0130] Analyze the data distribution of risk scores in historical data, based on the 95th percentile as the risk threshold;

[0131] If the calculated risk score is greater than or equal to the risk threshold, it is determined to be high risk, and the maximum frequency of the monitoring frequency data of the collection item is set as the collection frequency;

[0132] If the calculated risk score is less than the risk threshold, it is judged as low risk and the collection frequency is dynamically set.

[0133] By constructing and training the LSTM model, the long-term dependencies in the time series data can be effectively captured. The status of the electrical equipment can be predicted based on the interpolated collected data. At the same time, based on the actual collected data of the electrical equipment, by calculating the comprehensive deviation value between the data and the LSTM model prediction value, the accuracy of the LSTM model prediction can be further analyzed, and risk assessment calculations can be performed. When the comprehensive deviation is large, it can be judged that the data collection risk of the electrical equipment by the collection equipment increases, and when the comprehensive deviation is small, it can be judged that the risk decreases. Therefore, the status of the electrical equipment can be monitored only from the interpolated collected data and the LSTM model. Through the linear regression model and historical data analysis, the risk score threshold is scientifically set to ensure the rationality and accuracy of the risk assessment.

[0134] Furthermore, the sampling period is set, and the sampling frequency is dynamically adjusted based on the risk score to analyze the efficiency of equipment status monitoring, including:

[0135] The sampling period is set based on the current acquisition frequency, expressed as:

[0136]

[0137] Where T t represents the sampling period of the risk score at time t, F' t Indicates the acquisition frequency at the current time t;

[0138] During the risk score sampling period, based on the risk score R t The dynamic adjustment sampling frequency is expressed as:

[0139]

[0140] where F t Represents the dynamic sampling frequency, R min represents the minimum risk score within the sampling period, R 95 represents the 95th percentile of the risk score within the sampling period, F max Indicates the maximum sampling frequency within the sampling period, F min Indicates the minimum sampling frequency within the sampling period;

[0141] The calculation based on the dynamic sampling frequency replaces the initial sampling frequency, analyzes the dynamic energy consumption, and calculates the interpolation between the dynamic energy and the benchmark energy consumption, which is expressed as:

[0142]

[0143] ΔE=E d -E d ;

[0144] Where E drepresents the dynamic energy consumption within the sampling period, ΔE represents the energy consumption difference, and E b Indicates the baseline energy consumption during the sampling period;

[0145] The efficiency of equipment status monitoring is analyzed based on the energy consumption difference of the sampling period, which is expressed as:

[0146]

[0147] Where η is the efficiency of equipment status monitoring, N is the total number of sampling cycles, and E d,i represents the dynamic energy consumption of the i-th sampling period, E b,i represents the benchmark energy consumption of the i-th sampling period;

[0148] When calculating the dynamic energy consumption within the sampling period, the dynamic energy consumption formula is used to calculate R t is a dynamically changing value that reflects the risk level of the device status at time t. In order to better capture the impact of risk score on energy consumption, the use of logarithmic function can compress a large range of values ​​into a smaller range, making the impact of high risk score on energy consumption more significant, while the impact of low risk score is appropriately weakened. This can more realistically reflect the energy consumption changes of the device at different risk levels, while avoiding the mathematical problems caused by the logarithmic function when it is zero or negative, thereby ensuring the stability and accuracy of energy consumption calculation;

[0149] Then, through the F t Multiply, comprehensively consider the impact of dynamic sampling frequency on energy consumption, considering that the adjustment of dynamic sampling frequency depends on the sampling period, the energy consumption at each time point in the entire sampling period can be accumulated through integration to obtain a total energy consumption value. This method can better reflect the cumulative energy consumption in actual operation, so that the calculation of dynamic energy consumption not only considers the energy consumption at a certain moment, but also considers the changing trend of energy consumption in the entire period;

[0150] Compared with the calculation of dynamic energy consumption, the benchmark energy consumption formula extracts the mean value of the maximum dynamic sampling frequency and the minimum dynamic sampling frequency as the benchmark energy consumption within the sampling period. In the process of calculating the energy consumption difference, it can better reflect the trend change of dynamic energy consumption calculation. In the calculation of equipment status monitoring efficiency, the efficiency of equipment status monitoring is comprehensively evaluated by the ratio of cumulative energy savings or added value to the benchmark energy consumption.

[0151] By setting the sampling period based on the current collection frequency, the system can flexibly adapt to different changes in collection frequency, improve the efficiency and flexibility of data collection, dynamically adjust the sampling period according to actual needs, optimize the use of data collection resources, avoid unnecessary high-frequency sampling, and save system resources. By dynamically adjusting the sampling frequency, the system can respond to changes in risk scores in real time, increase the sampling frequency when the risk is high, and ensure that changes in equipment status are captured in a timely manner. When the risk score is high, increase the sampling frequency, improve the density of data collection, ensure the accuracy and timeliness of monitoring data, and help to detect potential faults in a timely manner. When the risk score is low, reduce the sampling frequency, optimize the use of data collection resources, reduce data redundancy, and reduce the system burden. By dynamically adjusting the sampling frequency, ensure the stable operation of the system under different risk conditions, and improve the reliability and stability of the monitoring system.

[0152] S4, based on the visualization of collected data and risk score data, securely stores and manages the data;

[0153] Preferably, a visual display based on the collected data and risk score data includes:

[0154] Use the Seaborn visualization library in Python to collect and confirm that the data to be displayed includes the risk score R t , sampling frequency F t , Comprehensive Deviation Value CDI t , actual collected value Y t And the LSTM model predicted value

[0155] Use Matplotlib to plot the risk score and sampling frequency changes, use a line chart to show data changes, and mark the 95 percentile threshold line. Then draw a comparison chart of actual values ​​and predicted values, add legends and annotations to help understand data changes, mark key data points in the chart, and use Matplotlib to mark them.

[0156] By displaying the changes in the sampling frequency, we can intuitively understand the dynamic adjustment strategy of the system under different risk conditions. By marking the 95th percentile risk threshold line, it is easy to identify and distinguish between high-risk and low-risk situations and provide a basis for decision-making. By intuitively displaying the comparison between actual values ​​and predicted values, it is easy to evaluate the prediction performance and accuracy of the LSTM model. By marking key data points in the chart, highlighting outliers or important changing trends, and helping to analyze the data in depth, adding legends and annotations helps to understand the chart content and data changes, thereby improving the readability and information transmission effect of the visual chart.

[0157] Furthermore, secure data storage and management refers to using the relational database PostgreSQL for structured data storage and management, using ETL tools for data storage and management, and regularly updating risk scores R t , sampling frequency F t , Comprehensive Deviation Value CDI t , actual collected value Y t And the LSTM model predicted value Store in the database, use the database backup tool mysqldump for regular backups, and use the database security tool AWS RDS to protect database security and access control.

[0158] By using PostgreSQL for structured data storage and management, the efficiency of data organization and query is improved, which facilitates multi-dimensional data analysis and mining. The ETL tool realizes the automated processing of data extraction, conversion and loading, reduces manual intervention, improves data processing efficiency and data quality, ensures data security and recoverability through regular backup, and can restore the database in time in the event of failure or data loss to ensure data security. Through the security management function of AWS RDS, the access rights and data encryption of the database are set to protect data privacy and security, and improve the transparency and security of data management.

[0159] Example 2, reference Figure 2 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a system for an electrical equipment status monitoring method, including:

[0160] The data acquisition module collects monitoring data of electrical equipment through acquisition equipment, including electrical data and environmental data;

[0161] The outlier removal module calculates the mean and standard deviation of the data and removes abnormal data that exceeds 3 standard deviations;

[0162] The data interpolation module performs linear interpolation and spline interpolation to fill the missing data based on the initial collection frequency of the collection items;

[0163] LSTM model prediction module, which builds a long short-term memory network LSTM model for time series prediction, analyzes the deviation between the actual value and the predicted value, and calculates the risk score;

[0164] Frequency adjustment module, which sets the sampling period and dynamically adjusts the sampling frequency based on the risk score;

[0165] Visual display module, which performs visual display based on collected data and risk score data;

[0166] The data management module is used to store and manage data securely.

[0167] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0168] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0169] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0170] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0171] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring the state of electrical equipment, Features: include, Collect data based on the monitored electrical equipment collection items and remove abnormal values; Set the initial acquisition frequency and perform linear interpolation and spline interpolation based on the acquisition items to fill in the acquisition item data; Construct a long short-term memory network (LSTM) model for time series prediction, comprehensively analyze the deviation between the actual value and the predicted value, calculate the risk score, set the sampling period, and dynamically adjust the sampling frequency based on the risk score to analyze the efficiency of equipment status monitoring; Based on the visualization of collected data and risk score data, the data is securely stored and managed.

2. The electrical equipment status monitoring method according to claim 1, Features: The data collection is performed according to the monitored electrical equipment collection items, and outlier removal is performed, including: The electrical equipment collects data according to collection items through multifunctional sensors and smart meters, and the collection items include electrical data and environmental data, wherein the electrical data includes voltage deviation and frequency deviation, and the environmental data includes temperature, vibration and noise and the monitoring frequency of the corresponding collection items; A low-pass filter is used to smooth the data, retaining the low-frequency effective signal and removing the high-frequency noise; Use the three sigma rule to eliminate outliers, calculate the mean and standard deviation of the collected data, and eliminate outliers, expressed as: Where X represents the data of the collection item, μ represents the mean of the collection item, and σ represents the standard deviation of the collection item; Values ​​outside the range are considered outliers and removed.

3. The electrical equipment status monitoring method according to claim 2, Features: The setting of the initial acquisition frequency and performing linear interpolation and spline interpolation based on the acquisition items to fill the acquisition item data include: The maximum monitoring frequency of the collection item is used as the initial collection frequency; Time series synchronization is performed based on the collected item data, and the environmental data is filled using linear interpolation, which is expressed as: Where X t and X t+n represents the collected environmental data of events t and t+n, X t+i represents the collected environmental data after interpolation, i represents the interpolation position, and n represents the time step; The electrical data based on the acquisition items are filled using the spline interpolation method, which is expressed as: S i (x)=a i +b i (x-x i )+c i (x-x i ) 2 +d i (x-x i ) 3 ; where a i , b i 、c i and d i is the coefficient of the cubic spline function, x represents the independent variable time, x i represents the i-th electrical data collection time point, S i (x) represents the interpolation result of the i-th segment interval; The time point that needs to be interpolated is determined by the initial acquisition frequency, and the interval to which the time point that needs to be interpolated belongs is determined based on the acquisition time of the electrical data, and the interpolation result is calculated by the spline function.

4. The electrical equipment status monitoring method according to claim 3, Features: The long short-term memory network LSTM model is constructed to perform time series prediction, comprehensively analyze the deviation between the actual value and the predicted value, and calculate the risk score, including: Arrange the interpolated data series in chronological order and standardize the data; Construct a long short-term memory network LSTM model for time series prediction, including input layer, hidden layer and output layer. The input layer receives the collected data of the collection item, the hidden layer and the output layer recognize the time series through the LSTM unit, and the output of the last LSTM unit is used as the predicted value of the future time. Based on the collection item data at time t as the actual collection value, the predicted value of the long short-term memory network LSTM model at time t is compared, and the absolute value of the difference between the actual collection value and the predicted value is calculated as the absolute deviation value; Based on the absolute deviation value, the relative deviation and trend deviation between the actual value and the predicted value are comprehensively considered and expressed as: CDI t Indicates the comprehensive deviation value, AE t Indicates the absolute deviation value at time t, Y t-1 represents the actual collected value at time t-1, Represents the LSTM model prediction value at time t-1, Y t represents the actual collected value at time t, Represents the LSTM model prediction value at time t; Based on the Comprehensive Deviation Index (CDI) t The linear regression model is used to determine the risk score, which is expressed as: R t =α+β·CDI t ; Where α represents the baseline value of the risk score, R t represents the risk score at time t, β represents the weight of the comprehensive deviation index; Analyze the data distribution of risk scores in historical data, based on the 95th percentile as the risk threshold; If the calculated risk score is greater than or equal to the risk threshold, it is determined to be high risk, and the maximum frequency of the monitoring frequency data of the collection item is set as the collection frequency; If the calculated risk score is less than the risk threshold, it is judged as low risk and the collection frequency is dynamically set.

5. The method for monitoring the state of electrical equipment according to claim 4, Features: The sampling period is set, and the sampling frequency is dynamically adjusted based on the risk score to analyze the efficiency of equipment status monitoring. include, The sampling period is set based on the current acquisition frequency, expressed as: Where T t represents the sampling period of the risk score at time t, F' t Indicates the acquisition frequency at the current time t; During the risk score sampling period, based on the risk score R t The dynamic adjustment sampling frequency is expressed as: Among them, F t Represents the dynamic sampling frequency, R min represents the minimum risk score within the sampling period, R 95 represents the 95th percentile of the risk score within the sampling period, F max Indicates the maximum sampling frequency within the sampling period, F min Indicates the minimum sampling frequency within the sampling period; The calculation based on the dynamic sampling frequency replaces the initial sampling frequency, analyzes the dynamic energy consumption, and calculates the interpolation between the dynamic energy and the benchmark energy consumption, which is expressed as: ΔE=E d -E d ; Where E d represents the dynamic energy consumption within the sampling period, ΔE represents the energy consumption difference, and E b Indicates the baseline energy consumption during the sampling period; The efficiency of equipment status monitoring is analyzed based on the energy consumption difference of the sampling period, which is expressed as: Where η is the efficiency of equipment status monitoring, N is the total number of sampling cycles, and ΔE i Represents the energy consumption difference of the i-th sampling period, E b,i Represents the benchmark energy consumption of the i-th sampling period.

6. The method for monitoring the state of electrical equipment according to claim 5, Features: The visual display based on the collected data and risk score data includes: Use the Seaborn visualization library in Python to collect and confirm that the data to be displayed includes the risk score R t , sampling frequency F t , Comprehensive Deviation Value CDI t , energy consumption difference ΔE, efficiency of state monitoring η, actual collection value Y t And the LSTM model predicted value Use Matplotlib to plot the risk score and sampling frequency change graph, use a line graph to show the data changes, and mark the 95 percentile threshold line. Then draw a comparison chart of the actual value and the predicted value, add legends and annotations, mark the key data points in the chart, and use Matplotlib to mark them.

7. The method for monitoring the state of electrical equipment according to claim 6, Features: The secure storage and management of data refers to using the relational database PostgreSQL for structured data storage and management, using ETL tools for data storage and management, and regularly updating the risk score R t , efficiency η of state monitoring, sampling frequency F t , Comprehensive Deviation Value CDI t , energy consumption difference ΔE, actual collection value Y t And the LSTM model predicted value Store in the database, use the database backup tool mysqldump for regular backups, and use the database security tool AWS RDS to protect database security and access control.

8. A system based on the electrical equipment status monitoring method according to any one of claims 1 to 7, Features: include, The data acquisition module collects monitoring data of electrical equipment through acquisition equipment, including electrical data and environmental data; The outlier removal module calculates the mean and standard deviation of the data and removes abnormal data that exceeds 3 standard deviations; The data interpolation module performs linear interpolation and spline interpolation to fill the missing data based on the initial collection frequency of the collection items; LSTM model prediction module, which builds a long short-term memory network LSTM model for time series prediction, analyzes the deviation between the actual value and the predicted value, and calculates the risk score; Frequency adjustment module, which sets the sampling period and dynamically adjusts the sampling frequency based on the risk score; Visual display module, which performs visual display based on collected data and risk score data; The data management module is used to store and manage data securely.

9. A computer device, include: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the electrical equipment status monitoring method described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, Features: When the computer program is executed by a processor, the steps of the method for monitoring the state of an electrical device according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Data center performance index anomaly detection method, device and system and medium

    CN115473830A

  • Power distribution network stability operation and maintenance method based on LSTM

    CN116739562A

  • Fire-fighting equipment detection and evaluation system and method based on video processing and deep learning

    CN118095867A

  • Power grid equipment operation state prediction method based on machine learning

    CN118739296A

  • Method for evaluating mechanical state of high-voltage shunt reactor on the basis of vibration feature

    WO2021232655A1

Cited By

  • Electrical signal acquisition system based on intelligent dynamic sampling

    CN119510879A

  • An electrical signal acquisition system based on intelligent dynamic sampling

    CN119510879B

  • Verification frequency determination method and device based on device score, device and medium

    CN119537120A

  • Method, apparatus, device and medium for determining verification frequency based on device score

    CN119537120B

  • Multi-sensor fusion security monitoring method and system

    CN119939480A