Power distribution terminal alarm system and alarm method based on adaptive filtering

Abstract

The invention discloses a power distribution terminal alarm system and method based on adaptive filtering, and relates to the technical field of power distribution automation. In order to overcome the defects that an existing power distribution terminal alarm system depends on a single signal and is high in false alarm rate and poor in anti-interference capability, multi-source signals are collected and fused; the environmental noise is monitored, and the anti-shake time is adaptively and dynamically adjusted; and determining a fault type through the matching of the time domain feature and the frequency domain feature, and giving an alarm according to the confidence of the fault. The method is mainly used for improving the abnormal signal detection precision of the power distribution terminal and reducing false alarms.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution automation, and particularly to a distribution terminal alarm system and an alarm method based on adaptive filtering. Background Art

[0002] The alarm system of traditional distribution terminals relies on single signal threshold judgment (such as overcurrent, zero current), and is easily affected by instantaneous interference or signal jitter, resulting in a high rate of missed alarms and false alarms. In the prior art, signal anti-shake mostly adopts fixed-delay filtering and cannot adapt to the noise changes under different working conditions. In addition, the general signal of accidents is usually synthesized by simple logic, lacking comprehensive analysis of multi-source signals (such as voltage, current, equipment status), and it is difficult to accurately reflect the real faults.

[0003] Therefore, there is a need for a distribution terminal alarm system and an alarm method based on adaptive filtering that can accurately identify distribution terminal faults, have a low rate of missed alarms and false alarms, strong anti-interference ability, and high intelligence. Summary of the Invention

[0004] In order to solve the defects that the existing distribution terminal alarm system relies on a single signal, has a high rate of missed alarms and false alarms, and poor anti-interference ability, the present invention provides a distribution terminal alarm system and an alarm method based on adaptive filtering that can accurately identify distribution terminal faults, have a low rate of missed alarms and false alarms, strong anti-interference ability, and high intelligence.

[0005] A distribution terminal alarm system based on adaptive filtering according to the present invention includes a multi-source signal fusion module, an anti-shake module, and an alarm decision module; The multi-source signal fusion module is used to collect multi-source signals, extract the time-domain features and frequency-domain features of the multi-source signals; and fuse the time-domain features and frequency-domain features of the collected multi-source signals; The anti-shake module is used to monitor the environmental noise and adaptively and dynamically adjust the anti-shake time; The alarm decision module is used to determine the fault type by matching the time-domain features and frequency-domain features, and perform an alarm according to the confidence level of the fault.

[0006] Further: The multi-source signal fusion module includes a signal acquisition module, a feature extraction module, and a fusion model; The signal acquisition module is used to collect multi-source signals, and the multi-source signals include current, voltage, switch position, and equipment temperature; The feature extraction module is used to extract the time-domain features and frequency-domain features of the multi-source signals; The fusion model is used to dynamically allocate the weights of the time-domain features and frequency-domain features of each multi-source signal in the total accident synthesis according to the signal type of the multi-source signal and the credibility of historical data, and fuse the time-domain features and frequency-domain features of the multi-source signal according to the weights.

[0007] Further: The anti-shake module includes an environmental noise monitoring module and a filtering module; The environmental noise monitoring module is used to sample the background noise signal, calculate the noise intensity in real time, and dynamically adjust the anti-shake time; The filtering module is used to suppress the interference of instantaneous pulses through an optoelectronic isolation module and Kalman filtering.

[0008] Further: The alarm decision module includes a fault mode matching module, a confidence evaluation module, and a recorded wave data self-diagnosis module; The fault mode matching module is used to determine the fault type through feature matching according to the built-in typical fault mode library; The confidence evaluation module is used to calculate the alarm confidence of the fault based on signal consistency and duration, and trigger a warning when the alarm confidence is lower than a preset threshold; The recorded wave data self-diagnosis module is used to automatically select the recorded wave length according to the signal mutation rate corresponding to the warning, compare the recorded wave data with the data in the historical waveform library, identify hidden abnormal waveforms, and generate alarm information.

[0009] The power distribution terminal alarm method based on adaptive filtering disclosed by the present invention adopts the power distribution terminal alarm system based on adaptive filtering, and the specific steps are as follows: S1. Collect multi-source signals, extract the time-domain features and frequency-domain features of the multi-source signals; fuse the multi-source signals; S2. Monitor the environmental noise and adaptively and dynamically adjust the anti-shake time; S3. Determine the fault type through the matching of the time-domain features and frequency-domain features, and give an alarm according to the confidence of the fault.

[0010] Further: In S1, the fusion of the multi-source signals includes the following steps: S11. Collect multi-source signals, extract the time-domain features and frequency-domain features of the multi-source signals; S12. Dynamically allocate the weights of the time-domain features and frequency-domain features of each multi-source signal in the total accident synthesis according to the signal type of the multi-source signal and the credibility of historical data. If the fluctuation of the time-domain feature or frequency-domain feature of the current multi-source signal exceeds the preset threshold, then execute S13. If the fluctuation of the time-domain feature or frequency-domain feature of the current multi-source signal does not exceed the threshold, then execute S14; S13. Modify the weight ratio of the current multi-source signal according to the deviation and credibility exceeding the preset threshold; fuse the time-domain characteristics and frequency-domain characteristics of the multi-source signal according to the weight; S14. Repeat S11 - S13 to re-collect the multi-source signal; S15. If the fluctuation range of the multi-source signal received by the system is smaller than the fixed threshold compared with the signal received last time, it is determined that the state is maintained. The CPU maintains the current operating state, maintains the numerical states of each signal collected last time, and repeats S11 - S13 to continue collecting the multi-source signal; if the exit condition is met, the collection of the multi-source signal ends.

[0011] Further: In S2, the adaptive dynamic adjustment of the anti-shake time includes the following steps: S21. Collect the noise signal of the background environment; S22. Monitor the noise signal, calculate the noise intensity. If the noise intensity exceeds the preset threshold, execute S23; if the noise intensity does not exceed the preset threshold, use the anti-shake time used in the previous calculation; S23. Dynamically adjust the anti-shake time. If the anti-shake time is adjusted successfully, update the determination time of the signal state recognition; if the anti-shake time adjustment fails, repeat S21 - S22 to continue collecting the noise signal of the background environment; S24. If the adaptive filtering function remains enabled, repeat S21 - S23 to continue collecting the multi-source signal; if the exit condition is met, end the collection of the noise signal of the background environment.

[0012] Further: In S3, the alarm according to the confidence level of the fault includes the following steps: S31. Collect the recorded wave data and preprocess the recorded wave data; S32. Compare the recorded wave data with the data in the historical waveform library to identify hidden abnormal waveforms; if the waveform is abnormal, execute S33; if the waveform is normal, repeat S31 - S32 to continue collecting the recorded wave data of the multi-source signal; S33. Generate an alarm message according to the hidden abnormal waveform, light up the alarm indicator or perform a self-healing operation; S34. If the system self-healing is successful or the alarm information is manually reset, repeat S31 - S33 to continue collecting the recorded wave data of the multi-source signal; if the self-healing fails, give an alarm.

[0013] The beneficial effects of the present invention are: The distribution terminal alarm system based on adaptive filtering can achieve high-precision fault detection and low false alarm rate by dynamically adjusting anti-shake parameters and comprehensively integrating multi-dimensional signal features. This invention is mainly used to improve the detection accuracy of abnormal signals in the distribution terminal and reduce false alarms. The advantages of this invention are as follows: High precision: The fusion of multi-source signals reduces misjudgment of single signals. As shown in the embodiments, the fault recognition accuracy can be increased to over 99%.

[0014] Low omission and false alarm rates: The adaptive anti-shake algorithm reduces noise interference. As described in the embodiments, the omission rate can be reduced by over 70% and the false alarm rate can be reduced by over 60%.

[0015] Intelligence: Fault mode matching and confidence evaluation support hierarchical alarm (early warning / severe alarm).

[0016] Compatibility: Supports the hardware transformation of existing distribution terminals. Brief Description of the Drawings

[0017] Figure 1 is the system architecture diagram; Figure 2 is the schematic diagram of multi-source signal weight distribution; Figure 3 is the flowchart of the adaptive anti-shake algorithm; Figure 4 is the flowchart of the self-diagnosis of the oscillogram data. Detailed Embodiments

[0018] The following are only the preferred specific embodiments of this invention, but the protection scope of this invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by this invention should be covered by the protection scope of this invention. The following embodiments are only used to explain this invention and cannot be construed as a limitation of this invention. The protection scope of this invention should be subject to the protection scope of the claims. The embodiments of this invention are described in detail below. For the convenience of describing this invention and simplifying the description, the technical terms used in the description of this invention should be interpreted in a broad sense, including but not limited to the conventional replacement schemes not mentioned in this application, and including both direct implementation methods and indirect implementation methods.

[0019] Embodiment 1 Combined with Figures 1-4 to illustrate this embodiment, the distribution terminal alarm system based on adaptive filtering disclosed in this embodiment includes a multi-source signal fusion module, an anti-shake module, and an alarm decision module; The multi-source signal fusion module is used to collect multi-source signals, extract the time-domain features and frequency-domain features of the multi-source signals; and fuse the time-domain features and frequency-domain features of the collected multi-source signals; The anti-shake module is used to monitor environmental noise and adaptively adjust the anti-shake time dynamically; The alarm decision module is used to determine the fault type by matching the time-domain features and frequency-domain features, and make an alarm according to the confidence level of the fault.

[0020] The multi-source signal fusion module includes a signal acquisition module, a feature extraction module and a fusion model; as Figure 1 shown, the signal acquisition, fusion model, anti-shake module and alarm decision process are demonstrated.

[0021] The signal acquisition module is used to acquire multi-source signals, and the multi-source signals include current, voltage, switch position and equipment temperature; the signal acquisition module adopts a multi-channel signal acquisition module. Taking the substation distribution terminal as an example, the main control chip selects T3, which has a built-in double-precision floating-point arithmetic unit and is responsible for signal preprocessing; a 16-bit 16-channel synchronous sampling ADC chip with the model number AD7616BSTZ is used to transmit the AC sampling data to the main control chip through the SPI interface, and the following input channels are configured: Current signal: 4 channels (phase A / B / C / 0), connected through the secondary side of the CT, range 0~5A, sampling rate 12.8kHz; Voltage signal: 4 channels (phase A / B / C / 0), input after resistance voltage division, range 0-100V, sampling rate 12.8kHz; Digital input: 9 channels (breaker position, earthing switch status, etc.), opto-isolated input; Temperature signal: 2 sensors with the model number PT100, accessed through module type communication; The feature extraction module is used to extract the time-domain features (such as amplitude, slope) and frequency-domain (such as harmonic content) features of the multi-source signals; Time-domain features: calculated using a sliding window (window length 200ms), root mean square value of current: ; wherein, is the root mean square value of current, N is the harmonic order, is the root mean square value of the nth harmonic current.

[0022] Voltage mutation rate: ; wherein, is the voltage mutation rate (voltage change amount per unit time), is the voltage value at the tth sampling, is the voltage sampling value at the (t-1)th time, is the time interval.

[0023] Frequency domain features: Analyze the 0 - 2 kHz spectrum through FFT (Fast Fourier Transform) and calculate the THD (Total Harmonic Distortion) value; The fusion model is used to dynamically allocate the weights of the time - domain features and frequency - domain features of each multi - source signal in the total accident synthesis according to the signal type and historical data credibility of the multi - source signals, and fuse the time - domain features and frequency - domain features of the multi - source signals according to the weights. Dynamically allocate the weights of each signal in the total accident synthesis according to the signal type and historical data credibility (such as the weight of the current signal is 50% and the weight of the temperature signal is 20%).

[0024] Figure 2 It is a schematic diagram of multi - source signal weight allocation, showing the dynamic weights of signals such as current, voltage, and temperature.

[0025] Dynamic weight allocation: Establish a historical credibility database and count the number of false alarms of each signal in the past 30 days; Weight The calculation formula of: ; Where, is the number of false alarms, is the current signal mutation significance score, is the sum of the signal mutation significance scores statistically in the past 30 days; The anti - jitter module includes an environmental noise monitoring module and a filtering module; The environmental noise monitoring module is used to sample the background noise signal (such as the electromagnetic interference spectrum), calculate the noise intensity in real - time, and dynamically adjust the anti - jitter time (adjustable from 10 ms to 1000 ms); Figure 3 It is a flowchart of the adaptive anti - jitter algorithm, including the noise monitoring and anti - jitter time dynamic adjustment logic.

[0026] The hardware circuit of the anti - jitter module sets double isolation in the digital input channel: The front - stage uses a high - speed optocoupler of model HCPL181 (transmission delay < 3 μs), and the rear - stage is configured with an RC low - pass filter (cut - off frequency adjustable at 1 kHz); Configure an electromagnetic interference monitoring module: The electromagnetic interference monitoring module collects the noise in the 0.1 GHz - 6 GHz frequency band in real - time and transmits the noise power spectrum data to the main control chip through the communication interface.

[0027] The filtering module is used to suppress the interference of instantaneous pulses through the opto - electrical isolation module and Kalman filtering.

[0028] The parameter dynamic adjustment of the Kalman filtering: The process noise covariance Adapts to the signal change rate: ; Among them, .

[0029] Table 1: Noise intensity classification table;

[0030] The alarm decision-making module is used to determine the fault type by matching the time-domain features and frequency-domain features, and issue an alarm according to the confidence level of the fault.

[0031] Table 2: Example of a typical fault feature library;

[0032] Calculation model of confidence level C: ; Among them, is the time decay factor (default 0.1), is the time interval, is the signal strength participating in the calculation of the decision-making confidence level, is the weight of the signal participating in the confidence level calculation.

[0033] The alarm decision-making module includes a fault mode matching module, a confidence level evaluation module, and a recording data self-diagnosis module; The fault mode matching module is used to determine the fault type by feature matching according to the built-in typical fault mode library (such as short circuit, grounding, equipment overheating); The confidence level evaluation module is used to calculate the alarm confidence level of the fault based on signal consistency and duration, and trigger a warning when the alarm confidence level is lower than the threshold; The recording data self-diagnosis module is used to automatically select the recording length (the first 4 cycles + the next 8 cycles or user-defined) according to the signal mutation rate corresponding to the warning, and support storage in Comtrade format. Compare the recording data with the historical waveform library, identify hidden abnormalities (such as initial characteristics of insulation deterioration), and issue an alarm for the waveform signal with self-healing failure.

[0034] Figure 4 is the flow chart of the recording data self-diagnosis, including the steps of waveform comparison and hidden abnormality identification.

[0035] The recording data is stored in the recording storage unit, which is an externally expanded EMMC (Embedded Multimedia Card) for waveform storage, supports the Comtrade2013 standard format, and configures two recording modes: Conventional recording: the first 4 cycles (80ms) + the next 8 cycles (160ms); Long-term recording: user-defined duration (maximum 60s).

[0036] Example 2 This example will be described in combination with Example 1. The method for alarming a distribution terminal based on adaptive filtering disclosed in this example adopts the system for alarming a distribution terminal based on adaptive filtering, and the specific steps are as follows: S1. Collect multi-source signals, extract the time-domain features and frequency-domain features of the multi-source signals; fuse the multi-source signals; including the following steps: S11. Collect multi-source signals, extract the time-domain features and frequency-domain features of the multi-source signals; S12. Dynamically allocate the weights of the time-domain features and frequency-domain features of each multi-source signal in the total accident synthesis according to the signal type and historical data credibility of the multi-source signals. If the fluctuation of the time-domain feature or frequency-domain feature of the current multi-source signal exceeds the preset threshold, then execute S13. If the fluctuation of the time-domain feature or frequency-domain feature of the current multi-source signal does not exceed the threshold, then execute S14; S13. Modify the weight ratio of the current multi-source signal according to the deviation and credibility exceeding the preset threshold; fuse the time-domain features and frequency-domain features of the multi-source signals according to the weights; S14. Repeat S11-S13 to collect multi-source signals again; S15. If the fluctuation range of the multi-source signal received by the system is smaller than the fixed threshold compared with the signal received last time, it is determined that the state is maintained. The CPU maintains the current operating state, maintains the numerical states of each signal collected last time, and repeats S11-S13 to continue collecting multi-source signals; if the exit condition is met, the collection of multi-source signals ends.

[0037] S2. Monitor the environmental noise and adaptively and dynamically adjust the anti-shake time; The adaptive and dynamic adjustment of the anti-shake time includes the following steps: S21. Collect the noise signals of the background environment; S22. Monitor the noise signals, calculate the noise intensity. If the noise intensity exceeds the threshold, then execute S23. If the noise intensity does not exceed the threshold, then use the anti-shake time used in the last calculation; S23. Dynamically adjust the anti-shake time. If the adjustment of the anti-shake time is successful, then update the determination time of the signal state recognition. If the adjustment of the anti-shake time fails, then repeat S21-S22 to continue collecting the noise signals of the background environment; S24. If the adaptive filtering function remains enabled, then repeat S21-S23 to continue collecting multi-source signals; if the exit condition is met, the collection of the noise signals of the background environment ends.

[0038] S3. Determine the fault type by matching the time-domain features and frequency-domain features, and issue an alarm according to the confidence level of the fault. The step of issuing an alarm according to the confidence level of the fault includes the following steps: S31. Collect the oscillogram data and preprocess the oscillogram data; S32. Compare the oscillogram data with the data in the historical waveform library to identify hidden abnormal waveforms; if the waveform is abnormal, execute S33, if the waveform is normal, repeat S31 - S32 to continue collecting multi-source signal oscillogram data; For example: when the joint temperature curve rises, the harmonic current increases, and the voltage fluctuation increases, each waveform alone is within the normal operating range, but combined, it can be inferred that there is a trend of cable terminal head damage. Such waveforms that are actually operating normally but may be abnormal when analyzed in combination are defined as hidden abnormal waveforms; S33. Generate an alarm message based on the hidden abnormal waveform, turn on the alarm indicator light or perform a self-healing operation; The self-healing operation includes tripping and isolating, disconnecting the abnormal line, or switching the standby power supply according to a preset logic, etc.; S34. If the system self-healing is successful or the alarm message is manually reset, repeat S31 - S33 to continue collecting multi-source signal oscillogram data; if the self-healing fails, issue an alarm.

[0039] Embodiment 3 This embodiment is described in combination with Embodiment 2. The power distribution terminal alarm method based on adaptive filtering disclosed in this embodiment takes the power distribution automation terminal of a K-type station (switching station) as an example: Hardware deployment: Integrate a multi-channel signal acquisition module in the terminal main control plug-in, and connect the current transformer, voltage sensor, and temperature probe.

[0040] Algorithm configuration: Set the signal weight parameters through the LCD menu, and select the fault mode library (such as the cable station special library, overhead line special library).

[0041] Operation process: Collect signals in real time and extract features, and calculate the environmental noise intensity; Dynamically adjust the anti-shake time to filter out instantaneous interference; Match the fault mode after multi-source signal fusion, evaluate the confidence level, and trigger a hierarchical alarm; Automatically record and store the waveform when abnormal for subsequent analysis.

[0042] Take the overload warning of the cable branch box as an example; Scenario: The temperature of the cable joint in an industrial park rises abnormally; System response: At 15:00:00, the temperature sensor detected that the joint temperature rose from 45°C to 58°C (temperature rise rate 13K / h); At 15:00:05, the current harmonic content increased from 5% to 18%, and the voltage fluctuation rate increased to 2% / s; Fusion calculation: Temperature weight 30%, current weight 40%, voltage weight 30%; Confidence level C = 0.78 (warning threshold 0.7); Trigger a secondary warning, record the waveform for 10s and upload it to the master station; Result: The on-site inspection by the operation and maintenance personnel found that the joint was oxidized, avoiding a cable burning accident.

[0043] Taking the treatment of lightning interference on overhead lines as an example; Scenario: Thunderstorm weather causes instantaneous pulse interference; System response: The adaptive anti-shake module detected that the noise in the 6GHz band reached -95dBm / Hz; Automatically adjust the anti-shake time to 80ms; The current instantaneous pulse (amplitude 8In, duration 2ms) was suppressed by double filtering; No false alarm was triggered, only the event log was recorded; Comparison: The traditional fixed 50ms anti-shake system generates false alarms in this scenario.

[0044] Parameter configuration method: Enter the "Advanced Settings → Signal Weight" menu through the terminal maintenance software or the LCD; Table 3: Three preset modes;

[0045] Supports user customization, and the sum of each weight needs to meet the 100% constraint.

[0046] Performance test data: In a pilot project of a provincial power grid, comparative tests were conducted on 10 sites: Table 4: Statistical table of performance test data

[0047] The test results show that the system has significantly improved in key performance indicators, especially in a high-noise environment (areas where electromagnetic interference in substation buildings exceeds the standard), and the false alarm rate has decreased by 72%.

[0048] The present invention is also applicable to scenarios such as new energy power stations and rail transit power supply systems, and only needs to adjust the characteristic thresholds in the fault mode library to adapt to different application environments.

Claims

1. A distribution terminal alarm system based on adaptive filtering, characterized in that, It includes a multi-source signal fusion module, an anti-shake module, and an alarm decision-making module; The multi-source signal fusion module is used to collect multi-source signals and extract the time-domain features and frequency-domain features of the multi-source signals; Fuse the time-domain features and frequency-domain features of the collected multi-source signals; The anti-shake module is used to monitor environmental noise and adaptively and dynamically adjust the anti-shake time; The alarm decision-making module is used to determine the fault type by matching the time-domain features and frequency-domain features, and issue an alarm according to the confidence level of the fault.

2. The distribution terminal alarm system based on adaptive filtering according to claim 1, wherein, The multi-source signal fusion module includes a signal acquisition module, a feature extraction module, and a fusion model; The signal acquisition module is used to collect multi-source signals, and the multi-source signals include current, voltage, switch position, and device temperature; The feature extraction module is used to extract the time-domain features and frequency-domain features of multi-source signals; The fusion model is used to dynamically allocate the weights of the time-domain features and frequency-domain features of each multi-source signal in the total accident synthesis according to the signal type of the multi-source signal and the credibility of historical data, and fuse the time-domain features and frequency-domain features of the multi-source signal according to the weights.

3. The distribution terminal alarm system based on adaptive filtering according to claim 1, wherein, The anti-shake module includes an environmental noise monitoring module and a filtering module; The environmental noise monitoring module is used to sample the background noise signal, calculate the noise intensity in real time, and dynamically adjust the anti-shake time; The filtering module is used to suppress the interference of instantaneous pulses through an optoelectronic isolation module and Kalman filtering.

4. The distribution terminal alarm system based on adaptive filtering according to claim 1, characterized in that, The alarm decision-making module includes a fault mode matching module, a confidence level evaluation module, and a recorded wave data self-diagnosis module; The fault mode matching module is used to determine the fault type by feature matching according to the built-in typical fault mode library; The confidence level evaluation module is used to calculate the alarm confidence level of the fault based on signal consistency and duration, and trigger a warning when the alarm confidence level is lower than a preset threshold; The recorded wave data self-diagnosis module is used to automatically select the recorded wave length according to the signal mutation rate corresponding to the warning, compare the recorded wave data with the data in the historical waveform library, identify hidden abnormal waveforms, and generate alarm information.

5. A distribution terminal alarm method based on adaptive filtering, characterized in that, Adopt the distribution terminal alarm system based on adaptive filtering as described in any one of claims 1-4, and the specific steps are as follows: S1. Collect multi-source signals, and extract the time-domain features and frequency-domain features of the multi-source signals; Fuse the multi-source signals; S2. Monitor environmental noise and adaptively and dynamically adjust the anti-shake time; S3. Determine the fault type by matching the time-domain features and frequency-domain features, and issue an alarm according to the confidence level of the fault.

6. The distribution terminal alarm method based on adaptive filtering according to claim 5, wherein In S1, the fusion of the multi-source signals includes the following steps: S11. Collect multi-source signals, and extract the time-domain features and frequency-domain features of the multi-source signals; S12. Dynamically allocate the weights of the time-domain features and frequency-domain features of each multi-source signal in the total accident synthesis according to the signal type of the multi-source signal and the credibility of historical data. If the fluctuation of the time-domain feature or frequency-domain feature of the current multi-source signal exceeds the preset threshold, then execute S13. If the fluctuation of the time-domain feature or frequency-domain feature of the current multi-source signal does not exceed the threshold, then execute S14; S13. Modify the weight ratio of the current multi-source signal according to the deviation and credibility exceeding the preset threshold; fuse the time-domain features and frequency-domain features of the multi-source signal according to the weight; S14. Repeat S11 - S13 to re-collect the multi-source signal; S15. If the fluctuation range of the multi-source signal received by the system is smaller than the fixed threshold compared with the signal received last time, it is determined that the state is maintained. The CPU maintains the current operating state, maintains the numerical state of each signal collected last time, and repeats S11 - S13 to continue collecting the multi-source signal; if the exit condition is met, the collection of the multi-source signal ends.

7. The distribution terminal alarm method based on adaptive filtering according to claim 5, characterized in that In S2, the adaptive dynamic adjustment of the anti-shake time includes the following steps: S21. Collect the noise signal of the background environment; S22. Monitor the noise signal, calculate the noise intensity. If the noise intensity exceeds the preset threshold, execute S23; if the noise intensity does not exceed the preset threshold, use the anti-shake time calculated last time; S23. Dynamically adjust the anti-shake time. If the adjustment of the anti-shake time is successful, update the determination time of the signal state recognition; if the adjustment of the anti-shake time fails, repeat S21 - S22 to continue collecting the noise signal of the background environment; S24. If the adaptive filtering function remains enabled, repeat S21 - S23 to continue collecting the multi-source signal; if the exit condition is met, end the collection of the noise signal of the background environment.

8. The distribution terminal alarm method based on adaptive filtering according to claim 5, characterized in that, In S3, the alarm according to the confidence level of the fault includes the following steps: S31. Collect the recorded wave data and preprocess the recorded wave data; S32. Compare the recorded wave data with the data in the historical waveform library to identify hidden abnormal waveforms; if the waveform is abnormal, execute S33; if the waveform is normal, repeat S31 - S32 to continue collecting the recorded wave data of the multi-source signal; S33. Generate an alarm message according to the hidden abnormal waveform, light up the alarm indicator or perform a self-healing operation; S34. If the system self-healing is successful or the alarm message is manually reset, repeat S31 - S33 to continue collecting the recorded wave data of the multi-source signal; if the self-healing fails, give an alarm.

Images