Operation fault intelligent identification system of electrical automation control system

Abstract

The invention relates to the technical field of fault identification, in particular to an intelligent operation fault identification system of an electrical automation control system, which comprises a current feature extraction module, a frequency spectrum adaptive adjustment module, a fault signal monitoring module, a filter optimization module and a fault mode identification module. According to the invention, by calculating the skewness and kurtosis values of the current signal, the system not only can recognize the symmetry and sharpness of the current waveform, but also can carefully capture the tiny change of the signal, thereby greatly improving the recognition capability of a nonlinear fault. Self-adaptive adjustment of spectral analysis can dynamically optimize the window size and the sliding step length according to the characteristics of real-time waveforms, signal fluctuation in the electrical environment is effectively dealt with, the precision of spectral analysis is guaranteed, errors caused by fixed parameter setting are avoided, and the accuracy of spectral analysis is improved in combination with monitoring of sudden change and fluctuation aggravation of current waveforms. The system is more sensitive in capturing and processing of fault signals, and can identify potential faults in an early stage.

Description

Technical Field

[0001] The present invention relates to the technical field of fault identification, and in particular to an intelligent identification system for operation faults of an electrical automation control system. Background Art

[0002] Fault identification technology mainly involves the technology of detecting, identifying and diagnosing abnormal conditions of systems, equipment or machines during operation. It is widely used in industrial automation, machine learning, artificial intelligence and other fields. By monitoring the operating status of equipment in real time, it automatically detects potential faults and anomalies, and analyzes the causes of faults through intelligent algorithms or predetermined rules. Its application can help to provide timely warnings, reduce equipment downtime, improve equipment reliability and safety, and optimize maintenance strategies.

[0003] Among them, the intelligent identification system for operational faults of electrical automation control systems refers to an intelligent fault identification technology applied to electrical automation control systems. Its purpose is to automatically detect and identify faults that may occur in the electrical system during operation. The system monitors the operating status of control equipment in real time and analyzes the collected data. It can promptly detect system anomalies and predict the occurrence of faults, helping users to perform maintenance in advance to avoid production interruptions or equipment damage.

[0004] Existing systems are based on fixed rules or low-order statistical methods, making it difficult to cope with complex nonlinear faults and unable to capture tiny changes in current waveforms in a timely manner, resulting in potential faults being overlooked. In addition, existing systems lack the ability to adapt to changes in the electrical environment, and the spectrum analysis and filtering effects are poor, and they cannot effectively remove noise interference, resulting in low fault diagnosis accuracy in complex electrical environments, affecting maintenance and operation efficiency, and increasing the risk of damage to the electrical automation control system. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an intelligent identification system for operation failures of an electrical automation control system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: an intelligent identification system for operation faults of an electrical automation control system, the system comprising: The current feature extraction module obtains real-time current waveform data, calculates the skewness and kurtosis of the current signal based on its instantaneous value, analyzes the nonlinear change trend of the current waveform, identifies potential fault signs in the current signal, and obtains the current nonlinear feature identification; The spectrum adaptive adjustment module obtains real-time current waveform data, calculates the time domain characteristics of the current waveform, analyzes the size of the spectrum window and the sliding step, dynamically adjusts the spectrum analysis window based on the amplitude and stability of the current waveform fluctuation, and then dynamically analyzes the frequency characteristics of the current waveform to obtain dynamic spectrum feature output results; The fault signal monitoring module monitors the change of the current waveform based on the current nonlinear characteristic identifier, analyzes the dynamic characteristics of the current waveform, determines whether the current waveform has abnormal changes, marks the signal abnormality event, and generates a fault signal change identifier; The filter optimization module obtains the filter parameters of the operating fault intelligent identification system according to the fault signal change identifier, adjusts the bandwidth and gain settings of the filter according to the sudden change and abnormality of the current waveform, eliminates noise interference in the current signal, and obtains the optimized filter configuration.

[0007] The present invention has improvements in that the current nonlinear characteristic identifier includes waveform symmetry measurement, signal sharpness evaluation information, and waveform mutation characteristics; the dynamic spectrum characteristic output result includes spectrum smoothness, spectrum resolution, and frequency change rate; the fault signal change identifier includes mutation occurrence time, fluctuation amplitude change, and abnormal event identifier; the filter optimization configuration includes filter bandwidth range, gain adjustment coefficient, and noise filtering efficiency.

[0008] The present invention is improved in that the current feature extraction module includes: The current signal acquisition submodule acquires real-time current waveform data, processes the current data, removes noise and frequency interference, and verifies the integrity of the current data to obtain processed current data; The skewness and kurtosis calculation submodule calculates the skewness and kurtosis of the current signal based on the processed current data and the instantaneous value of the current signal, analyzes the symmetry of the current waveform, and measures the sharpness of the signal waveform to obtain the current waveform characteristics; The current waveform analysis submodule analyzes the nonlinear change trend of the current waveform based on the current waveform characteristics, detects whether the current waveform has undergone a sudden change or increased fluctuation, and identifies potential fault signs in the current signal using the formula: ; The current nonlinear characteristic mark NLP is obtained, where SK represents the skewness of the current waveform and KE represents the kurtosis of the current waveform. represents the instantaneous current at moment i, represents the average value of the current waveform, Represents the total number of current data points.

[0009] The present invention is improved in that the spectrum adaptive adjustment module includes: The current feature extraction submodule obtains real-time current waveform data, extracts the current peak value, cycle mean, and waveform deviation within each cycle based on the time series, calculates the time domain amplitude fluctuation and stability within the current cycle, and generates the current waveform amplitude evaluation result; The fluctuation decision calculation submodule calculates the amplitude fluctuation change rate and stability offset range based on the current waveform amplitude evaluation result, and determines whether the amplitude fluctuation exceeds the standard fluctuation range. If it exceeds, the window length is increased and the sliding step is shortened. If it does not exceed, the window length is shortened and the sliding step is increased. The formula is: ; Get the current volatility decision degree , get the spectrum sliding control parameters, where, is the average current amplitude of the current cycle, is the average current amplitude of the previous cycle, Represents the degree of stability deviation in the Zth cycle, Represents the current deviation degree of the Zth cycle, Represents the frequency center of the window after the jth adjustment, is the mean of all frequency centers, is the number of cycles, is the number of adjustments; The dynamic spectrum generation submodule calls the spectrum sliding control parameters, performs segmented windowing on the current current waveform sequence, calculates the dominant frequency and energy concentration of the frequency distribution within each segment, obtains the rate of change and degree of change of the central tendency of each spectrum segment, and obtains the dynamic spectrum feature output result.

[0010] The present invention is improved in that the fault signal monitoring module includes: The current waveform monitoring submodule monitors the change of the current waveform based on the current nonlinear characteristic identifier, obtains the current time domain change data, analyzes the nonlinear characteristics of the current waveform, extracts the current mutation point, fluctuation amplitude and response rate, and constructs the current nonlinear characteristic vector; The dynamic change identification submodule calls the current nonlinear characteristic vector and obtains the current change amplitude, adjacent point change rate and peak spacing based on the response range of the time interval using the formula: ; Obtaining dynamic nonlinear fluctuations ,in, represents the current response value at the i-th moment, represents the current response value at the i+1th moment, Represents the timestamp of the i-th moment, Represents the timestamp of the i+1th moment, represents the total number of time points; The abnormal mark generation submodule determines whether the current waveform has undergone abnormal changes based on the dynamic nonlinear fluctuation degree, and marks the signal abnormal event in combination with the sudden change and intensified fluctuation of the current waveform to generate a fault signal change mark.

[0011] The present invention is improved in that the filter optimization module includes: The fault signal acquisition submodule detects the change trend of the fault signal according to the fault signal change identifier and the sudden change and abnormality of the current waveform to obtain the change characteristics of the fault signal; The filter parameter adjustment submodule adjusts the bandwidth and gain settings of the filter according to the variation characteristics of the fault signal, targeting waveform mutations and abnormal conditions, optimizes the signal filtering process, and obtains the adjusted filter parameters; The filter optimization configuration submodule optimizes the filter based on the adjusted filter parameters to remove noise interference in the current signal using the formula: ; Calculate the optimized adjustment value FV to obtain the optimized filter configuration, where represents the original current signal amplitude, represents the current signal amplitude after filter adjustment, BV represents the adjusted filter bandwidth, GV represents the filter gain adjustment parameter, RV represents the noise interference elimination coefficient, and KV represents the weighting coefficient of the optimized configuration.

[0012] The present invention is improved in that the system further comprises: The fault pattern recognition module determines the fault characteristics in the current waveform based on the filter optimization configuration and dynamic spectrum feature output results, and then identifies potential faults based on the current waveform changes and known fault modes, determines the fault type of the electrical automation control system, and obtains fault diagnosis results; The fault diagnosis results include fault type identification results, fault location accuracy, and fault impact assessment results.

[0013] The present invention is improved in that the fault mode identification module includes: The fault identification submodule performs a preliminary analysis on the current waveform based on the filter optimization configuration and the dynamic spectrum feature output result, extracts the time-frequency features in the current waveform, obtains the amplitude and frequency information of the current waveform, and generates the current waveform feature value; The fault diagnosis submodule compares the current waveform characteristics with the known fault mode based on the current waveform characteristics, determines the matching degree between the known fault mode and the current waveform characteristics, identifies potential faults, determines the fault type, and obtains a fault diagnosis result.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by calculating the skewness and peak value of the current signal, the system can not only identify the symmetry and sharpness of the current waveform, but also capture the subtle changes in the signal in detail, greatly improving the ability to identify nonlinear faults. The adaptive adjustment of the spectrum analysis can dynamically optimize the window size and sliding step size according to the characteristics of the real-time waveform, effectively responding to signal fluctuations in the electrical environment, ensuring the accuracy of the spectrum analysis, and avoiding the errors caused by fixed parameter settings. Combined with the monitoring of sudden changes and intensified fluctuations in the current waveform, the system is more sensitive in capturing and processing fault signals, and can identify potential faults in the early stages, thereby providing timely warnings. The optimization of the filter further enhances the system's anti-interference ability, ensuring that the fault signal can still be accurately identified in a high-noise environment, thereby enhancing the safety and operation efficiency of the electrical automation control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a system flow chart of the present invention; Figure 2 This is a flow chart of the current feature extraction module in the present invention; Figure 3 This is a flow chart of the spectrum adaptive adjustment module in the present invention; Figure 4 This is a flow chart of the fault signal monitoring module in the present invention; Figure 5 This is a flow chart of the filter optimization module in the present invention; Figure 6 This is a flow chart of the fault mode identification module in the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description. They do not indicate or imply that the devices or elements referred to must have a specific direction, be constructed and operate in a specific direction, and therefore should not be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined. Example

[0018] See also Figure 1The present invention provides a technical solution: an intelligent identification system for operation faults of an electrical automation control system includes: The current feature extraction module obtains real-time current waveform data from the electrical automation control system. Based on the instantaneous value of the current signal, it calculates its skewness and kurtosis. It determines the symmetry of the current waveform based on the skewness value and the sharpness of the current waveform based on the kurtosis value. It analyzes the nonlinear change trend of the current waveform, detects whether the current waveform has undergone sudden changes or increased fluctuations, identifies potential fault signs in the current signal, and obtains the current nonlinear feature identification. The spectrum adaptive adjustment module obtains real-time current waveform data from the electrical automation control system, calculates the time domain characteristics of the current waveform, analyzes the size of the spectrum window and the sliding step size, and dynamically adjusts the spectrum analysis window based on the amplitude and stability of the current waveform fluctuations. If the waveform fluctuations are too large, the window length is increased and the sliding step size is reduced. If the waveform is stable, the window length is reduced and the sliding step size is increased. The frequency characteristics of the current waveform are then dynamically analyzed to obtain the dynamic spectrum feature output results. The fault signal monitoring module monitors the changes in the current waveform based on the nonlinear characteristic of the current, analyzes the dynamic characteristics of the current waveform, determines whether the current waveform has undergone abnormal changes, and combines the sudden changes and increased fluctuations of the current waveform to mark abnormal signal events and generate a fault signal change indicator; The filter optimization module obtains the filter parameters of the operating fault intelligent identification system based on the fault signal change indicator. Based on the sudden changes and abnormal conditions of the current waveform, it adjusts the filter bandwidth and gain settings to eliminate noise interference in the current signal and obtain the optimal filter configuration. The fault pattern recognition module determines the fault characteristics in the current waveform based on the filter optimization configuration and dynamic spectrum feature output results. Then, based on the current waveform changes and known fault modes, it identifies potential faults, determines the fault type of the electrical automation control system, and obtains fault diagnosis results.

[0019] The identification of current nonlinear characteristics includes waveform symmetry measurement, signal sharpness assessment information, and waveform mutation characteristics. The dynamic spectrum feature output results include spectrum smoothness, spectrum resolution, and frequency change rate. The fault signal change identification includes the mutation occurrence time, fluctuation amplitude change, and abnormal event identification. The filter optimization configuration includes the filter bandwidth range, gain adjustment coefficient, and noise filtering efficiency. The fault diagnosis results include fault type identification results, fault location accuracy, and fault impact assessment results.

[0020] See also Figure 2 , the current feature extraction module includes: The current signal acquisition submodule acquires real-time current waveform data, processes the current data, removes noise and frequency interference, and verifies the integrity of the current data to obtain processed current data; Real-time current data is collected through sensors. The data contains detailed information about current fluctuations in the power system. To remove noise, low-pass filters or Kalman filters are usually used to remove high-frequency interference. In addition, frequency analysis tools (such as Fourier transform) are used to identify and remove noise in specific frequency bands. At this time, the current data has been processed and integrity verification (such as matching the data with a preset time window or current waveform shape) is used to confirm whether the data is complete. In this process, the current signal data is collected and processed, making the current waveform data set the basis for subsequent analysis. For example, if you look at the waveform graph of the collected data, you can see that the instantaneous current value fluctuates greatly, but after filtering, the fluctuation will be smoothed, leaving a more realistic current waveform, ensuring that the integrity of the data is not lost due to external interference. Finally, after this series of processing, the current data becomes a reliable data source for subsequent feature extraction.

[0021] The skewness and kurtosis calculation submodule calculates the skewness and kurtosis of the current signal based on the processed current data and the instantaneous value of the current signal, analyzes the symmetry of the current waveform, and measures the sharpness of the signal waveform to obtain the current waveform characteristics; Based on the processed current data, its instantaneous value is analyzed, and then the skewness and kurtosis of the current signal are calculated. The skewness reflects the symmetry of the waveform distribution, and the kurtosis reflects the sharpness of the waveform peak. First, by extracting the instantaneous value of the processed current waveform, that is, the current value at each specific moment, the skewness and kurtosis are calculated for the data value. The calculation of skewness requires comparing the deviation degree between the mean value and the instantaneous value of the current signal. By performing mathematical calculations on all data points (such as third-order moment calculation), its asymmetry can be quantified. For example, if the current in a certain period of time is The current waveform presents a relatively sharp peak, and the left part of the waveform is steeper than the right part. The skewness value will be positive. The kurtosis is determined by calculating the sharpness of the current waveform, which is usually achieved using the fourth-order moment. For example, when analyzing a current signal, assuming its instantaneous value is [2.5, 3.0, 3.5] and the mean is 3.0, if the kurtosis is high, it means that the peak of the current waveform is sharper, indicating the instability of the current signal. It can quantitatively analyze the symmetry and sharpness characteristics of the current waveform, providing key features for subsequent waveform analysis.

[0022] The current waveform analysis submodule analyzes the nonlinear change trend of the current waveform based on the current waveform characteristics, detects whether the current waveform has undergone a sudden change or increased fluctuation, and identifies potential fault signs in the current signal using the formula: ; The current nonlinear characteristic mark NLP is obtained, where SK represents the skewness of the current waveform, which is an indicator that describes the asymmetry of the current waveform distribution and reflects the degree of deviation from the left and right sides of the waveform. KE represents the kurtosis of the current waveform, which is an indicator that measures the sharpness of the current waveform and reflects the sharpness of the waveform peak. Represents the instantaneous current at the i-th moment, that is, the current data measured at a certain moment, represents the average value of the current waveform, Represents the total number of current data points; By calculating the skewness and kurtosis of the current waveform, we can analyze whether the current waveform has undergone a sudden change or increased fluctuation, thereby detecting potential fault signs. To calculate the skewness and kurtosis, we first need to collect data on the current signal at multiple time points and calculate its average value. , assuming that the instantaneous value of the current signal in a certain period of time is {2.5, 3.0, 3.5}, then is 3.0. Next, calculate the skewness and kurtosis. Assuming that the skewness Sk is 0.5 and the kurtosis KE is 2.0, we can get it by the formula , for each current value, subtract the mean to get the deviation, for example: , , ; Calculate the difference between each instantaneous value and the mean: ; ; ; Then, the total current deviation is obtained by summing: ; therefore, Calculated as: ; The results show that although there are certain deviations and sharp peaks in this current waveform (characteristics provided by skewness and kurtosis), its nonlinear characteristics are not significant, and the current waveform does not show signs of sudden changes or increased fluctuations.

[0023] See also Figure 3 , the spectrum adaptive adjustment module includes: The current feature extraction submodule obtains real-time current waveform data, extracts the current peak value, cycle mean, and waveform deviation within each cycle based on the time series, calculates the time domain amplitude fluctuation and stability within the current cycle, and generates the current waveform amplitude evaluation result; The current signal of each cycle is analyzed through the time series to extract the current peak, cycle mean and waveform deviation. First, the current signal is sampled and a data point is recorded at a certain time interval to form a continuous current waveform data sequence. Through the data, the system can calculate the current peak in each cycle. This process includes finding the maximum value of the current waveform from the original data sequence and recording it as the peak value of the cycle. The cycle mean is obtained by calculating the average value of all data points in each cycle, and the waveform deviation is evaluated by calculating the difference between the current value and the mean within the cycle. Next, The system will analyze the time-domain amplitude fluctuation and stability of the current signal within the cycle through statistical values. The specific operations are as follows: calculate the fluctuation range of the current amplitude in each cycle, evaluate its changes within the cycle, and the stability of the waveform, and obtain the amplitude evaluation result of the current waveform by comparing the mean and fluctuation amplitude. For example, in a certain cycle, the current peak is 5A, the cycle mean is 3A, and the waveform deviation is 1A. This shows that the current waveform of the cycle has a certain fluctuation amplitude, and the fluctuation amplitude is relatively large, which affects the stability of the system. Therefore, the output current waveform amplitude evaluation result indicates the stability level of the current waveform.

[0024] The fluctuation decision calculation submodule calculates the amplitude fluctuation change rate and stability offset range based on the current waveform amplitude evaluation results, and determines whether the amplitude fluctuation exceeds the standard fluctuation range. If it exceeds, the window length is increased and the sliding step is shortened. If it does not exceed, the window length is shortened and the sliding step is increased. The formula is: ; Get the current fluctuation decision degree WD and obtain the spectrum sliding control parameters, where, is the average current amplitude of the current cycle, is the average current amplitude of the previous cycle, Represents the degree of stability deviation in the Zth cycle, Represents the current deviation degree of the Zth cycle, Represents the frequency center of the window after the jth adjustment, indicating the frequency center value of the window, which is used to specify the frequency range of the window during spectrum analysis. is the mean of all frequency centers, is the number of cycles, is the number of adjustments; Set the number of cycles and number of adjustments , the average amplitude of the current in the current cycle is 5A, the average amplitude of the current in the previous cycle The amplitude fluctuation rate is 3A. Based on this data, we first calculate the amplitude fluctuation rate: , the amplitude fluctuation rate is 2A, assuming: Stability deviation degree of the first cycle , current offset degree ; Stability deviation degree of the second cycle , current offset degree ; Stability deviation degree of the third cycle , current offset degree ; Based on the value, calculate : First cycle calculation: ; Second cycle calculation: ; The third cycle calculation: ; Sum up the results of all cycles: ; Adjustment times , after each adjustment the frequency center The changes are as follows: The window frequency center after the first adjustment is ; The window frequency center after the second adjustment is ; The window frequency center after the third adjustment is ; Frequency center mean The calculation is as follows: ; Next, calculate the absolute value of the difference between the frequency center and the mean after each adjustment and sum them: ; ; ; After summing: ; Substitute all the calculation results into the formula of the fluctuation decision degree WD for calculation: ; The results show that the current fluctuation decision degree WD = 1.35, which means that the amplitude of the current waveform fluctuates greatly. It is necessary to adjust the spectrum sliding control parameters accordingly, such as increasing the window length and reducing the sliding step size, to stabilize the fluctuation.

[0025] The dynamic spectrum generation submodule calls the spectrum sliding control parameters to perform segmented windowing on the current waveform sequence, calculates the dominant frequency and energy concentration of the frequency distribution within each segment, obtains the rate of change and degree of change of the central tendency of each spectrum segment, and obtains the dynamic spectrum feature output result; According to the spectrum sliding control parameters obtained from the above calculation (such as the adjusted window length and step size), the current waveform is divided to generate multiple spectrum segments. Then, the main frequency and energy concentration in each spectrum segment are calculated. The main frequency represents the frequency peak of the current signal in the segment, and the energy concentration is evaluated by calculating the energy distribution of the frequency components near the frequency peak to evaluate whether the energy is concentrated near the main frequency. Then, the rate of change of each spectrum segment is calculated, that is, the frequency characteristics and energy concentration of the two spectrum segments before and after are compared to obtain the degree of change. Through the data, the concentration trend of the spectrum is further analyzed to determine whether the signal has changed significantly, and the current signal processing strategy is adjusted according to the change trend to obtain the dynamic spectrum feature output result. In this process, the purpose of spectrum analysis is to accurately capture the frequency fluctuations and changes in the current signal and provide data support for subsequent optimization decisions. For example, if the main frequency of a certain spectrum segment changes significantly, a more refined frequency adjustment strategy will be adopted for this signal segment to ensure the stable operation of the entire system.

[0026] See also Figure 4 , the fault signal monitoring module includes: The current waveform monitoring submodule monitors the changes in the current waveform based on the current nonlinear characteristic identification, obtains the current time domain change data, analyzes the nonlinear characteristics of the current waveform, extracts the current mutation point, fluctuation amplitude and response rate, and constructs the current nonlinear characteristic vector; Monitor the changes in current waveform. The current waveform monitoring process usually relies on real-time monitoring of sensor data streams. For example, current sensors or acquisition devices collect changes in current signals, obtain time domain data of current and further analyze it. In the monitoring process, it is first necessary to record the time domain changes of the current signal, that is, to collect the current response value of the current signal at each time point. The current response value is analyzed based on the waveform characteristics of the current, so as to extract the nonlinear characteristics. Taking a certain instantaneous current waveform as an example, if the current signal shows a mutation point, that is, the current changes significantly in a short period of time, then this point will be identified as a current mutation point, and the current fluctuation amplitude (such as jumping from 10A to 30A) can be calculated. Next, the response rate of the current waveform is calculated, which is usually based on the rate of change of the current in the time interval. For example, if the current increases from 10A to 20A within one second, the response rate is 10A / s. Through the monitoring process, the current nonlinear characteristic vector of the current waveform is constructed. This characteristic vector comprehensively reflects the change law of the current waveform and can ultimately provide data support for further subsequent analysis.

[0027] The dynamic change identification submodule calls the current nonlinear characteristic vector and obtains the current change amplitude, adjacent point change rate and peak spacing based on the response range of the time interval using the formula: ; Get dynamic nonlinear fluctuation ,in, Represents the current response value at the i-th moment, that is, the value of the current at the i-th time point, represents the current response value at the i+1th moment, Represents the timestamp of moment i, that is, the time corresponding to current value i, Represents the timestamp of the i+1th moment, represents the total number of time points; First, extract the response range of the current waveform in different time intervals and calculate the current change amplitude. In order to identify the dynamic fluctuation characteristics, it is necessary to select a certain time interval (for example, every 0.1 second is a time interval) and monitor the change of the current value within this time period. For example, if the current at moment i is , the current at the i+1th moment is , the current change amplitude is , then, calculate the rate of change between adjacent points, that is, calculate the current change rate, which often depends on the current difference in each time period divided by the time difference, expressed as For example, if the current at time i is 5A and at time i+1 is 15A, and the time difference is 0.5 seconds, then the rate of change is In addition, the peak spacing is calculated, that is, the time difference between two adjacent peaks. When the current waveform is periodic, the peak spacing can help identify the periodic changes of the current waveform. For the formula calculation, if the total time number is 2, that is , then consider the current data at the first and second moments: , Seconds and Seconds, substitute into the formula to calculate: ; Therefore, the calculated dynamic nonlinear fluctuation is , which helps to evaluate the dynamic change intensity of the current waveform and thus infer whether there is a fault signal.

[0028] The abnormal mark generation submodule determines whether the current waveform has undergone abnormal changes based on the dynamic nonlinear fluctuation degree. It then marks the abnormal signal event and generates a fault signal change mark based on the sudden change and increased fluctuation of the current waveform. By monitoring the mutations and fluctuations of the current waveform, it is determined whether the current has undergone abnormal changes. For the current waveform, if the rate of change at a certain point in time exceeds the preset mutation judgment reference value (such as 5A / s), it is marked as a mutation point. Next, combined with the dynamic nonlinear fluctuation of the current waveform, if the fluctuation exceeds the set threshold (for example, set to 0.1), it is marked as an abnormal event. This process is judged by comparing the dynamic fluctuation and mutation rate with the preset threshold. Finally, based on the information, it is determined whether the current waveform has undergone abnormal changes. Assuming that the current mutation exceeds 5A / s and the fluctuation exceeds 0.1 at a certain moment, the signal at that moment will be marked as an abnormal event, thereby generating a fault signal change mark, and performing corresponding early warning or fault processing on the system.

[0029] See also Figure 5 , the filter optimization module includes: The fault signal acquisition submodule detects the changing trend of the fault signal based on the fault signal change mark, the sudden change and abnormality of the current waveform, and obtains the changing characteristics of the fault signal; Sensors monitor current signals, collect current data in real time, and preprocess it. During this process, the sensors record information such as current amplitude, frequency, and phase in real time. If the system detects a sudden change in the current signal, such as a sudden increase in current amplitude or a waveform interruption, it triggers the generation of a fault signal change flag. For example, if the system monitors a current amplitude jump from 5A to 10A, it automatically determines this as a sudden change and identifies the location as a fault signal. By further tracking the waveform change trend, the system classifies the waveform change according to preset thresholds to determine whether it is a normal fluctuation or an abnormal fault. For example, if the current signal changes by more than 5A, this amplitude can be set as a fault signal change flag. Using this flag, the system can further track and identify the specific characteristics of the current fault and ultimately determine the fault signal change trend. This process is based on specific threshold settings to ensure accurate fault signal identification. For example, in an industrial application, the current fluctuates between 1-2A during normal operation, but a sudden change is detected, causing the current to rise rapidly to 6A. In this case, the system automatically generates a fault signal flag.

[0030] The filter parameter adjustment submodule adjusts the bandwidth and gain settings of the filter according to the changing characteristics of the fault signal, waveform mutations and abnormal conditions, optimizes the signal filtering process, and obtains the adjusted filter parameters; Based on the fault signal's change signature, the current signal is analyzed to identify the specific location and magnitude of the sudden change. Subsequently, the filter bandwidth and gain are adjusted in real time to optimize the signal filtering process. For example, if the current signal waveform experiences a significant sudden change, the filter bandwidth is increased to capture a wider range of the sudden change. If the abnormal amplitude is smaller, the bandwidth can be appropriately reduced to avoid noise interference. Furthermore, filter gain adjustment plays a key role. The system automatically adjusts the gain factor based on the current signal's changing characteristics, amplifying the useful signal and suppressing noise. For example, in a specific application, if a current signal experiences a 20% fluctuation, the filter adjusts the bandwidth accordingly to effectively filter out the signal's high-frequency noise. Simultaneously, the gain adjustment ensures that the useful components of the signal are appropriately amplified. Through this process, the system adjusts the filter parameters to optimize the current signal processing, resulting in the adjusted filter parameters. For example, the bandwidth can be adjusted from 50Hz to 200Hz, and the gain from 1.0 to 1.5, ensuring more accurate signal transmission.

[0031] The filter optimization configuration submodule optimizes the filter based on the adjusted filter parameters to remove noise interference in the current signal using the formula: ; Calculate optimization adjustment value , and get the filter optimization configuration, where represents the original current signal amplitude, Represents the current signal amplitude after filter adjustment, which refers to the current signal amplitude after filter parameter adjustment. Represents the adjusted filter bandwidth, which indicates the bandwidth setting selected by the filter during the optimization process. Represents the filter gain adjustment parameter, which indicates the parameter for adjusting the filter gain. The gain determines the degree of signal amplification. Setting the gain too high will amplify the noise, while setting it too low will not effectively process the signal. represents the noise interference elimination coefficient, represents the weighting coefficient of the optimal configuration; After obtaining the adjusted filter bandwidth and gain value, the system will comprehensively process the parameters and optimize them. For example, if the bandwidth is too wide and the noise is not effectively filtered out, the system will reduce the bandwidth to enhance the noise suppression effect of the signal; if the gain is too high and the effective signal is over-amplified, the system will lower the gain value accordingly. In this process, the optimization setting of the filter is calculated by the formula to optimize the adjustment value. , obtain the filter optimization configuration process, if there are the following data: Raw current signal amplitude (original value), after normalization (normalized value); Adjusted current signal amplitude (original value), after normalization (normalized value); Adjusted filter bandwidth (original value), after normalization (normalized value); Filter gain (original value), after normalization (normalized value); Noise interference elimination coefficient (original value), after normalization (normalized value); Weighted coefficient of optimized configuration (original value), after normalization (normalized value); Substitute into the formula to calculate: ; Therefore, the optimization adjustment value of the filter optimization configuration process is 1.8333 (normalized value), which represents the result after the filter optimization configuration, and is used to eliminate noise interference in the current signal.

[0032] See also Figure 6 , the fault mode recognition module includes: The fault identification submodule performs a preliminary analysis of the current waveform based on the filter optimization configuration and dynamic spectrum feature output results, extracts the time-frequency features in the current waveform, obtains the amplitude and frequency information of the current waveform, and generates the current waveform feature value; First, the current waveform is analyzed through filter optimization configuration and dynamic spectrum characteristics. In practical applications, assuming that the current waveform of a motor is being monitored, the current waveform data of the motor is first collected through the sensor. Then, based on the filter optimization configuration, the noise in the current waveform is filtered out to ensure that the collected data is clearer and can reflect the actual working status of the motor. Next, the time-frequency characteristics of the current waveform are analyzed through dynamic spectrum characteristics, and the amplitude and frequency information of the current are analyzed to obtain the time-frequency characteristic values ​​of the current. Taking the motor current data as an example, assuming that the current amplitude is 20A and the frequency is 50Hz during the collection process, a specific benchmark value can be set according to the working characteristics of the motor. If the deviation between the actual amplitude and frequency exceeds a certain threshold, it indicates that there is a problem with the current waveform. At this time, by comparing with the set threshold, the current waveform characteristic quantity is generated to provide data support for subsequent fault diagnosis.

[0033] The fault diagnosis submodule compares the current waveform characteristics with the known fault mode based on the current waveform characteristics, determines the matching degree between the known fault mode and the current waveform characteristics, identifies potential faults, determines the fault type, and obtains the fault diagnosis results; Based on the obtained current waveform characteristics and combined with the known fault mode library, further analysis is carried out. In actual operation, it is assumed that a current waveform different from the standard model appears during the operation of the motor. First, the spectrum characteristic value of the current is obtained by waveform feature extraction. If a certain pattern in the known fault mode library has a high degree of matching with the current current waveform characteristics, the system will judge that the motor has a certain fault type based on this pattern. For example, if the matching degree of a certain fault mode in the library is more than 80%, and it has a high similarity with the spectrum characteristics of the current waveform, it can be identified as a potential fault. Assume that through comparison, the current waveform matches the "overload fault" mode for 85%. This result indicates that the motor has an overload fault. After this series of comparisons and judgments, the fault diagnosis result is finally generated, and the fault type of the motor is determined.

[0034] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. The intelligent identification system for operation failure of electrical automation control system is characterized by: The system comprises: The current feature extraction module obtains real-time current waveform data, calculates its skewness and kurtosis based on the instantaneous value of the current signal, analyzes the nonlinear change trend of the current waveform, identifies potential fault signs in the current signal, and obtains the current nonlinear feature identification; The spectrum adaptive adjustment module obtains real-time current waveform data, calculates the time domain characteristics of the current waveform, analyzes the size of the spectrum window and the sliding step, dynamically adjusts the spectrum analysis window based on the amplitude and stability of the current waveform fluctuation, and then dynamically analyzes the frequency characteristics of the current waveform to obtain dynamic spectrum feature output results; The fault signal monitoring module monitors the change of the current waveform based on the current nonlinear characteristic identifier, analyzes the dynamic characteristics of the current waveform, determines whether the current waveform has abnormal changes, marks the signal abnormality event, and generates a fault signal change identifier; The filter optimization module obtains the filter parameters of the operating fault intelligent identification system according to the fault signal change identifier, adjusts the bandwidth and gain settings of the filter according to the sudden change and abnormality of the current waveform, eliminates noise interference in the current signal, and obtains the optimized filter configuration.

2. The intelligent identification system for operation failure of an electrical automation control system according to claim 1 is characterized in that: The current nonlinear feature identifier includes waveform symmetry measurement, signal sharpness assessment information, and waveform mutation characteristics. The dynamic spectrum feature output results include spectrum smoothness, spectrum resolution, and frequency change rate. The fault signal change identifier includes the mutation occurrence time, fluctuation amplitude change, and abnormal event identifier. The filter optimization configuration includes the filter bandwidth range, gain adjustment coefficient, and noise filtering efficiency.

3. The intelligent identification system for operation failure of an electrical automation control system according to claim 1, characterized in that: The current feature extraction module includes: The current signal acquisition submodule acquires real-time current waveform data, processes the current data, removes noise and frequency interference, and verifies the integrity of the current data to obtain processed current data; The skewness and kurtosis calculation submodule calculates the skewness and kurtosis of the current signal based on the processed current data and the instantaneous value of the current signal, analyzes the symmetry of the current waveform, and measures the sharpness of the signal waveform to obtain the current waveform characteristics; The current waveform analysis submodule analyzes the nonlinear change trend of the current waveform based on the current waveform characteristics, detects whether the current waveform has undergone a sudden change or increased fluctuation, and identifies potential fault signs in the current signal using the formula: ; Obtain the current nonlinear characteristic identification ,in, represents the skewness of the current waveform, represents the peak value of the current waveform, Representative The instantaneous amount of current at a moment, represents the average value of the current waveform, Represents the total number of current data points.

4. The intelligent identification system for operation failure of an electrical automation control system according to claim 1, characterized in that: The spectrum adaptive adjustment module includes: The current feature extraction submodule obtains real-time current waveform data, extracts the current peak value, cycle mean, and waveform deviation within each cycle based on the time series, calculates the time domain amplitude fluctuation and stability within the current cycle, and generates the current waveform amplitude evaluation result; The fluctuation decision calculation submodule calculates the amplitude fluctuation change rate and stability offset range based on the current waveform amplitude evaluation result, and determines whether the amplitude fluctuation exceeds the standard fluctuation range. If it exceeds, the window length is increased and the sliding step is reduced. If it does not exceed, the window length is reduced and the sliding step is increased. The formula is: ; Get the current volatility decision degree , get the spectrum sliding control parameters, where, is the average current amplitude of the current cycle, is the average current amplitude of the previous cycle, Representative The degree of stability of the cycle offset, Representative The degree of current deviation in the cycle, Representative The adjusted window frequency center, is the mean of all frequency centers, is the number of cycles, is the number of adjustments; The dynamic spectrum generation submodule calls the spectrum sliding control parameters, performs segmented windowing on the current current waveform sequence, calculates the dominant frequency and energy concentration of the frequency distribution within each segment, obtains the rate of change and degree of change of the concentration trend of each spectrum segment, and obtains the dynamic spectrum feature output result.

5. The intelligent identification system for operation failure of an electrical automation control system according to claim 1, characterized in that: The fault signal monitoring module includes: The current waveform monitoring submodule monitors the change of the current waveform based on the current nonlinear characteristic identifier, obtains the current time domain change data, analyzes the nonlinear characteristics of the current waveform, extracts the current mutation point, fluctuation amplitude and response rate, and constructs the current nonlinear characteristic vector; The dynamic change identification submodule calls the current nonlinear characteristic vector and obtains the current change amplitude, adjacent point change rate and peak spacing based on the response range of the time interval using the formula: ; Obtaining dynamic nonlinear fluctuations ,in, Representative Current response value at the moment, Representative Current response value at the moment, Representative Timestamp of the moment, Representative Timestamp of the moment, represents the total number of time points; The abnormal mark generation submodule determines whether the current waveform has undergone abnormal changes based on the dynamic nonlinear fluctuation degree, and marks the signal abnormal event in combination with the sudden change and intensified fluctuation of the current waveform to generate a fault signal change mark.

6. The intelligent identification system for operation failure of an electrical automation control system according to claim 1, characterized in that: The filter optimization module includes: The fault signal acquisition submodule detects the change trend of the fault signal according to the fault signal change identifier and the sudden change and abnormality of the current waveform to obtain the change characteristics of the fault signal; The filter parameter adjustment submodule adjusts the bandwidth and gain settings of the filter according to the variation characteristics of the fault signal, targeting waveform mutations and abnormal conditions, optimizes the signal filtering process, and obtains the adjusted filter parameters; The filter optimization configuration submodule optimizes the filter based on the adjusted filter parameters to remove noise interference in the current signal using the formula: ; Calculate optimization adjustment value , and get the filter optimization configuration, where represents the original current signal amplitude, Represents the current signal amplitude after filter adjustment, represents the adjusted filter bandwidth, represents the filter gain adjustment parameter, represents the noise interference elimination coefficient, Represents the weighting coefficient of the optimized configuration.

7. The intelligent identification system for operation failure of an electrical automation control system according to claim 1, characterized in that: The system further comprises: The fault pattern recognition module determines the fault characteristics in the current waveform based on the filter optimization configuration and dynamic spectrum feature output results, and then identifies potential faults based on the current waveform changes and known fault modes, determines the fault type of the electrical automation control system, and obtains fault diagnosis results; The fault diagnosis results include fault type identification results, fault location accuracy, and fault impact assessment results.

8. The intelligent identification system for operation failure of an electrical automation control system according to claim 7, characterized in that: The fault mode identification module includes: The fault identification submodule performs a preliminary analysis on the current waveform based on the filter optimization configuration and the dynamic spectrum feature output result, extracts the time-frequency features in the current waveform, obtains the amplitude and frequency information of the current waveform, and generates the current waveform feature value; The fault diagnosis submodule compares the current waveform characteristics with the known fault mode based on the current waveform characteristics, determines the matching degree between the known fault mode and the current waveform characteristics, identifies potential faults, determines the fault type, and obtains a fault diagnosis result.

Images