Active Enhancement Detection Method for Line Fault Characteristics of Distribution Box

Abstract

The present invention discloses an active enhancement detection method for line fault characteristics of a distribution box, which relates to the technical field of power system detection, and includes the following steps: Collect electrical signals in the distribution box in real time, and process the signals through an active enhancement strategy to highlight fault characteristics, and at the same time obtain the enhanced electrical signal data. The present invention ensures that the enhanced signal spectrum does not overlap with the system operating frequency through real-time signal acquisition, enhancement, feature extraction, frequency overlap analysis, machine learning evaluation, and digital signal processing (DSP) frequency shift operation, avoiding signal distortion or misjudgment of fault signals caused by spectrum interference. Combining a machine learning model with a DSP algorithm, dynamically adjust signal processing, automatically identify and correct frequency overlap problems, improve the performance and stability of the fault detection system, provide an intelligent and accurate fault detection solution, and enhance the safety and reliability of the power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power system detection, and particularly to an active enhancement detection method for line fault characteristics of a distribution box. Background Art

[0002] "Active enhancement detection of line fault characteristics of a distribution box" refers to the process of actively extracting and enhancing the characteristics of electrical signals (such as current, voltage, temperature rise, harmonics, etc.) collected during the fault detection of the internal lines of a distribution box by using certain technical means, so as to amplify or highlight the key characteristic signals related to faults, and improve the sensitivity and accuracy of fault detection. Different from the traditional passive detection method, active enhancement not only includes the suppression of noise interference, but may also combine means such as signal processing algorithms, feature transformation, pattern recognition or artificial intelligence models to strengthen the potential fault characteristics in the original data, so that even slight, early or hidden fault characteristics can be effectively identified, and the response ability and diagnostic efficiency to abnormal states are improved. This method is particularly applicable to multi-type fault detection scenarios in complex load environments of low-voltage distribution systems.

[0003] The prior art has the following deficiencies: During the fault detection of a distribution box, active enhancement strategies (such as non-linear transformation or signal superposition) are usually used to process the collected electrical signals in order to highlight and amplify the characteristics related to faults. However, these enhancement strategies may cause spectral resonance or mutual interference with the natural working frequency of the power distribution system (for example, the power grid frequency of 50 Hz) in some cases. In particular, processing methods such as non-linear transformation and signal superposition may change the frequency components of the signal, resulting in the overlap of the enhanced signal spectrum with the working frequency band of the power system. At this time, the normal working frequency components of the system may interfere with or resonate with the enhanced signal frequency, resulting in the distortion or morphological deformation of the signal characteristics.

[0004] This kind of spectral resonance or mutual interference not only affects the accuracy of the signal characteristics, but may also make it difficult to distinguish the fault signal from the normal working signal, resulting in the failure of the fault detection system to effectively identify potential faults, or misjudging the normal signal as a fault signal, affecting the stability and safety of the system.

[0005] The above information disclosed in the background art section is only used to strengthen the understanding of the background of the present disclosure, and therefore it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0006] The object of the present invention is to provide an active enhanced detection method for line fault characteristics of a distribution box. Through real-time signal acquisition, enhancement, feature extraction, frequency overlap analysis, machine learning evaluation, and digital signal processing (DSP) frequency shift operation, it is ensured that the enhanced signal spectrum does not overlap with the system operating frequency, avoiding the distortion or misjudgment of fault signals caused by spectrum interference. Combining a machine learning model with a DSP algorithm, dynamically adjusting signal processing, automatically identifying and correcting frequency overlap problems, improving the performance and stability of the fault detection system, providing an intelligent and accurate fault detection solution, and enhancing the safety and reliability of the power system to solve the problems in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solution: An active enhanced detection method for line fault characteristics of a distribution box, including the following steps:

[0008] Real-time collect the electrical signals in the distribution box, and process the signals through an active enhancement strategy to highlight the fault characteristics, and at the same time obtain the enhanced electrical signal data;

[0009] Store the real-time obtained enhanced electrical signal data into a data set, extract the key features reflecting the overlap between the signal frequency and the normal operating frequency of the power distribution system from the data set through feature engineering technology, comprehensively analyze the extracted key features, and quantify the degree of frequency overlap;

[0010] Input the key features after comprehensive analysis into a pre-trained machine learning model for further evaluation to determine whether the enhanced signal overlaps with the normal operating frequency;

[0011] When it is identified that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a digital signal processing algorithm is used to introduce a frequency shift operation in the enhanced signal to shift the frequency bandwidth of the signal to a frequency band outside the operating frequency of the power distribution system to avoid frequency overlap; Subsequently, further analyze the frequency-shifted signal to confirm that its frequency no longer overlaps with the operating frequency of the power distribution system, and on this basis, complete the identification of the fault signal.

[0012] Preferably, the specific steps of real-time collecting the electrical signals in the distribution box and processing the signals through an active enhancement strategy to highlight the fault characteristics are as follows:

[0013] Real-time collect the electrical signals from the electrical equipment in the distribution box to provide the original data for subsequent processing;

[0014] Apply an active enhancement strategy to the collected electrical signals to highlight the potential fault characteristics;

[0015] After applying the enhancement strategy, obtain the enhanced electrical signal data to provide an optimized signal input for subsequent analysis and processing.

[0016] Preferably, key features reflecting the overlap between the signal frequency and the normal operating frequency of the power distribution system are extracted from the data set through feature engineering techniques. The extracted features include the amplitude and phase changes of the signal and the enhanced power distribution of the signal in the frequency spectrum. The amplitude and phase changes of the signal and the enhanced power distribution of the signal in the frequency spectrum are comprehensively analyzed under the detection window to generate an amplitude-phase error reference value and a power spectral density fluctuation reference value respectively, and the degree of frequency overlap is quantified through the amplitude-phase error reference value and the power spectral density fluctuation reference value.

[0017] Preferably, the specific steps for comprehensively analyzing the amplitude and phase changes of the signal under the detection window to generate an amplitude-phase error reference value are as follows:

[0018] Quantify the amplitude change of the signal, analyze the amplitude error between the enhanced signal and the ideal signal, define the amplitude distortion factor, and measure the amplitude difference of the signal in the frequency space to quantify the degree of amplitude change. The calculation expression of the amplitude distortion factor is as follows: , where is the amplitude distortion factor, is the frequency at the amplitude value of the enhanced signal at the th frequency point, is the frequency amplitude value of the ideal signal at the th frequency point, is the number of frequencies, is a very small positive number used to avoid division by zero,

[0019] Analyze the phase error of the signal, quantify the phase change of the signal, judge whether the phase of the signal has changed by calculating the difference in phase between the enhanced signal and the ideal signal, and define the phase distortion factor. The calculation expression of the phase distortion factor is as follows: , where is the phase distortion factor, is the adjustment parameter, is the frequency at the phase angle of the enhanced signal at the th frequency point, is the frequency phase angle of the ideal signal at the th frequency point, is the phase index parameter,

[0020] Finally, the amplitude distortion factor and the phase distortion factor Combined, the amplitude-phase error reference value is obtained, quantifying the amplitude and phase changes of the enhanced signal. The calculation expression is as follows: , where is the amplitude-phase error reference value.

[0021] Preferably, the specific steps for comprehensively analyzing the power distribution of the enhanced signal in the spectrum to generate the power spectral density fluctuation reference value are as follows:

[0022] During the spectrum analysis of the signal, first calculate the power spectral density of the enhanced electrical signal to understand the energy distribution of the signal in different frequency ranges, and calculate the power of each frequency band. The calculation expression is as follows: , where is the power spectral density of the th frequency band, is the center frequency of the th frequency band, is the bandwidth, is the energy distribution of the signal at different frequencies .

[0023] After obtaining the power spectral density of each frequency band, further analyze the fluctuation degree of the power in the spectrum to quantify the change of the signal frequency. The calculation expression of the power spectral density fluctuation reference value is as follows: , where is the power spectral density fluctuation reference value, is the power spectral density of the previous frequency band, is the weight factor, indicating the contribution degree of the th frequency band to the power fluctuation, is the total number of frequency bands.

[0024] Preferably, input the amplitude-phase error reference value and the power spectral density fluctuation reference value obtained through comprehensive analysis into a pre-trained machine learning model for further evaluation. Generate a frequency overlap risk coefficient through the machine learning model, and judge whether the enhanced signal overlaps with the normal operating frequency based on the frequency overlap risk coefficient.

[0025] Preferably, compare and analyze the frequency overlap risk coefficient generated when judging whether the enhanced signal overlaps with the normal operating frequency through a pre-trained machine learning model with a pre-set frequency overlap risk coefficient reference threshold to judge whether the enhanced signal overlaps with the normal operating frequency. The judgment logic is as follows:

[0026] If the frequency overlap risk coefficient is greater than a pre-set reference threshold of the frequency overlap risk coefficient, it is determined that the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system; if the frequency overlap risk coefficient is less than or equal to the pre-set reference threshold of the frequency overlap risk coefficient, it is determined that the frequency of the enhanced signal does not overlap with the normal operating frequency of the power distribution system.

[0027] Preferably, when it is identified that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a digital signal processing algorithm is used to introduce a frequency shift operation in the enhanced signal to shift the frequency bandwidth of the signal to a frequency band outside the operating frequency of the power distribution system; subsequently, the specific steps for further analyzing the frequency-shifted signal are as follows:

[0028] After identifying the frequency overlap, a digital signal processing algorithm is used to perform a frequency shift on the enhanced signal to shift its frequency components from within the operating frequency bandwidth of the power distribution system to an external frequency band to avoid frequency overlap. The calculation expression is as follows:

[0029] When it is determined that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a frequency shift operation is introduced through digital signal processing technology to shift the frequency bandwidth of the signal out of the operating frequency band of the power distribution system. The frequency shift calculation expression is as follows: , where is the frequency-domain representation of the frequency-shifted signal, is the frequency-domain representation of the original enhanced signal, that is, the spectrum of the enhanced signal, is the complex exponential function, is the imaginary unit, is the frequency shift amount, is the natural base;

[0030] After the frequency shift operation is completed, it is necessary to further analyze the frequency-shifted signal to ensure that the frequency of the signal has been completely decoupled and no longer overlaps with the operating frequency of the power distribution system. The calculation expression is as follows: , where is the frequency overlap risk coefficient recalculated after the frequency shift, is the frequency overlap risk coefficient calculation model used to analyze the frequency characteristics of the frequency-shifted signal, is the feature extraction function;

[0031] If , where is the reference threshold of the frequency overlap risk coefficient.

[0032] In the above technical solution, the technical effects and advantages provided by the present invention:

[0033] Through a series of steps such as real-time acquisition and enhancement of signals, feature extraction and frequency overlap analysis, evaluation of machine learning models, and frequency shift operations in digital signal processing (DSP), the present invention ensures that the spectrum of the enhanced signal does not overlap with the operating frequency of the system. This process avoids problems such as distorted or misjudged fault signals caused by spectrum interference, enabling clear and accurate identification of fault signals. In addition, by combining machine learning models and DSP algorithms, the signal processing process can be dynamically adjusted to automatically identify and correct the impact of frequency overlap, thereby improving the overall performance and stability of the fault detection system. Finally, this solution provides a more intelligent and accurate solution for distribution system fault detection, contributing to enhancing the safety and reliability of the power system. Description of the Drawings

[0034] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings.

[0035] Figure 1 It is a method flow chart of the method for actively enhancing the detection of line fault characteristics for the distribution box of the present invention. Detailed Embodiments

[0036] Now, the exemplary embodiments will be described more comprehensively with reference to the drawings. However, the exemplary embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these exemplary embodiments are provided so that the present disclosure will be more complete and comprehensive, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art.

[0037] The present invention provides a method for actively enhancing the detection of line fault characteristics for a distribution box as shown in Figure 1 and includes the following steps:

[0038] Real-time collect the electrical signals in the distribution box and process the signals through an active enhancement strategy to highlight the fault characteristics, and at the same time obtain the enhanced electrical signal data;

[0039] The specific steps for real-time collecting the electrical signals in the distribution box and processing the signals through an active enhancement strategy to highlight the fault characteristics are as follows:

[0040] Real-time collect the electrical signals from the electrical equipment in the distribution box to provide the original data for subsequent processing;

[0041] In a distribution box, it is first necessary to install sensors (such as current and voltage sensors) to collect electrical signals in real time. Common electrical signals include current, voltage, power, frequency, etc. These signals usually reflect the working state of the power distribution system. The sensors can continuously monitor the current and voltage waveforms in the power grid and obtain electrical signal data at different time points. These data usually include signals in the normal working state and may also include abnormal waveforms caused by faults. Through this real-time signal acquisition, the system can track the state of the power system in real time and provide the original materials for subsequent fault diagnosis.

[0042] Apply an active enhancement strategy to the collected electrical signals to highlight potential fault characteristics;

[0043] After obtaining the real-time electrical signals, an active enhancement strategy is applied to the signal processing process. Common active enhancement strategies include non-linear transformation (such as using methods for extracting higher-order harmonics) and signal superposition (such as enhancing certain frequency components by superposing multiple signals). The purpose of these strategies is to make the fault signals more prominent in the background noise by increasing the characteristic frequency components in the signals. For example, specific frequency components may be added to the current signal to amplify the fluctuations related to faults. This enhancement not only helps the detection system to more sensitively identify potential faults but also makes the characteristics of the faults more obvious. However, there may be an overlap with the normal operating frequencies during this process, which needs to be processed in subsequent steps.

[0044] After applying the enhancement strategy, obtain the enhanced electrical signal data to provide optimized signal input for subsequent analysis and processing.

[0045] After being processed by the active enhancement strategy, the enhanced electrical signals contain more obvious fault characteristics, especially highlighting the fluctuations related to faults in terms of frequency. At this time, the enhanced signal data need to be further recorded and stored through the data acquisition module in the system. These enhanced data will serve as the basis for subsequent analysis, for spectrum analysis, feature extraction, and further signal processing. The enhanced signal data are more diagnostically valuable than the original signals, so they become the key input data for subsequent fault detection and fault diagnosis models. Through this process, the system can track the enhanced signals in real time and ensure providing accurate signal data support for fault detection.

[0046] Fault signals in a power distribution system are usually overwhelmed by background noise. Therefore, an active enhancement strategy is adopted to process the signals, aiming to amplify potential fault features and thus enhance the sensitivity of fault identification. Common enhancement methods include using non - linear transformations (such as adding harmonic components) or signal superposition (for example, adding multiple signals to strengthen certain frequency components). These enhancement strategies make the fault feature signals outside the normal operating frequency range more obvious, but may also introduce frequency overlap or interference problems.

[0047] The purpose of enhancement is to highlight and amplify fault - related features through specific signal - processing methods (such as non - linear transformation, signal superposition, etc.). By enhancing the signal, the system's ability to identify weak fault signals can be improved, making the fault features more prominent against the noise background.

[0048] The enhanced electrical signal data obtained in real - time is stored in a data set. Key features reflecting the overlap between the signal frequency and the normal operating frequency of the power distribution system are extracted from the data set through feature engineering techniques. The extracted key features are comprehensively analyzed, and the degree of frequency overlap is quantified.

[0049] The data set is a structured data set that stores all enhanced electrical signals. By pooling enhanced signal data at different time points, different device locations, and different fault conditions, the data set provides rich information for subsequent signal analysis. This step ensures that all enhanced signal data can be effectively compared and mined during the analysis process. The purpose of establishing the data set is to facilitate the extraction and quantitative analysis of enhanced signal features, and at the same time provide sufficient samples for the training and real - time application of machine - learning models.

[0050] Key features reflecting the overlap between the signal frequency and the normal operating frequency of the power distribution system are extracted from the data set through feature engineering techniques. The extracted features include the amplitude and phase changes of the signal and the power distribution of the enhanced signal in the frequency spectrum. The amplitude and phase changes of the signal and the power distribution of the enhanced signal in the frequency spectrum are comprehensively analyzed under a detection window to generate an amplitude - phase error reference value and a power - spectral density fluctuation reference value respectively. The degree of frequency overlap is quantified through the amplitude - phase error reference value and the power - spectral density fluctuation reference value.

[0051] Abnormal changes in the amplitude and phase of the signal may indeed indicate that the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system. The reason is that the operating frequency of the power system (such as 50Hz or 60Hz) is the fundamental frequency signal in the system and usually occupies the main component in the signal. If the enhancement strategy (such as non-linear transformation or signal superposition) changes the frequency components of the signal, and the frequency components of these enhanced signals are close to or overlap with the normal operating frequency, it will lead to frequency interference or resonance phenomena. Frequency overlap may cause abnormal changes in the amplitude and phase of the signal. First, the amplitude of the signal may show abnormal enhancement or suppression because frequency overlap may cause resonance, that is, the amplitude of a certain frequency component is over-amplified or weakened. Second, the abnormal change in phase usually means that there is interference between the frequency components of the signal and the operating frequency, resulting in phase shift or distortion of the signal. Usually, when there are obvious fluctuations in the amplitude and phase of the signal, this reflects that the signal frequency interferes with or overlaps with the normal operating frequency of the system, thus affecting the authenticity and accuracy of the signal. This phenomenon is extremely unfavorable for the further processing and fault detection of the signal and may lead to misjudgment or missed judgment.

[0052] The specific steps for comprehensively analyzing the amplitude and phase changes of the signal under the detection window to generate the amplitude-phase error reference value are as follows:

[0053] Quantify the amplitude change of the signal, analyze the amplitude error between the enhanced signal and the ideal signal (i.e., the signal at the normal operating frequency), define the amplitude distortion factor, and measure the amplitude difference of the signal in the frequency space to quantify the amplitude change degree. The calculation expression of the amplitude distortion factor is as follows: , where is the amplitude distortion factor, is the frequency amplitude value of the enhanced signal at the th frequency point, is the frequency amplitude value of the ideal signal at the th frequency point, is the number of frequencies, is a very small positive number used to avoid division by zero, is the exponential parameter used to non-linearly amplify the amplitude difference;

[0054] The above steps quantify the amplitude difference between the enhanced signal and the ideal signal, and identify the abnormal changes of the signal in the frequency space through the amplitude distortion factor to detect whether the signal has significant amplitude changes due to frequency overlap or interference, so as to provide a basis for subsequent processing.

[0055] Analyze the phase error of the signal, quantify the phase change of the signal, judge whether the phase of the signal changes by calculating the difference in phase between the enhanced signal and the ideal signal, define the phase distortion factor, and the calculation expression of the phase distortion factor is as follows: , where is the phase distortion factor, is the adjustment parameter used to control the sensitivity of the phase change to the exponent, is the frequency of the enhanced signal at the th frequency point at the phase angle, is the frequency of the ideal signal at the th frequency point at the phase angle, is the phase exponent parameter used for non-linearly amplifying the phase error, is the exponential change of the phase error, reflecting the change in the phase deviation between the enhanced signal and the ideal signal;

[0056] Through this formula, we can obtain a phase distortion factor with a value between 0 and 1. The closer the value is to 1, the greater the phase change of the signal, indicating that the frequency of the signal may overlap or interfere with the normal operating frequency of the system.

[0057] Finally, combine the amplitude distortion factor and the phase distortion factor to obtain the amplitude-phase error reference value, which quantifies the amplitude and phase changes of the enhanced signal. The calculation expression is as follows: , where is the amplitude-phase error reference value.

[0058] The amplitude-phase error reference value can effectively synthesize the amplitude and phase changes of the signal and reflect whether the signal overlaps with the normal operating frequency of the system. When the value is large, it indicates that both the amplitude and phase of the signal have undergone large abnormal changes, which may cause interference or resonance with the normal operating frequency. Conversely, when the value is small, it indicates that the signal does not overlap with the normal frequency and the signal state is relatively normal.

[0059] Through the above steps and formulas, the amplitude and phase changes of the signal can be systematically analyzed, so as to accurately judge whether the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system.

[0060] After comprehensively analyzing the amplitude and phase changes of the signal under the detection window, an amplitude-phase error reference value is generated. By using this amplitude-phase error reference value to analyze the amplitude and phase changes of the signal, it is indeed possible to determine whether the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system. When the signal frequency overlaps with the system operating frequency, it usually causes abnormal changes in the amplitude and phase of the signal because frequency interference or resonance phenomena may lead to drastic changes in amplitude and obvious shifts in phase. The amplitude-phase error reference value can reflect the degree of these changes by quantifying the amplitude error and phase error of the signal. When the measured value of the amplitude-phase error reference value is large, it means that the amplitude and phase changes of the signal are significant, usually indicating that the frequency of the enhanced signal overlaps with the normal operating frequency of the system (such as 50 Hz or 60 Hz). This overlap will cause spectral resonance and signal distortion. When the amplitude-phase error reference value is small, it indicates that the amplitude and phase changes of the signal are small, that is, the frequency of the enhanced signal does not overlap with the normal operating frequency, and the signal is relatively stable and not affected by frequency interference. Therefore, the larger the amplitude-phase error reference value, the more it can indicate the possibility of frequency overlap, and vice versa, it means that the signal does not have frequency overlap.

[0061] When there are abnormal fluctuations in the power distribution of the enhanced signal in the frequency spectrum, it often indicates that the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system. This is because in spectral analysis, the power spectral density of a signal usually represents the energy distribution of each frequency component. The operating frequency of the power distribution system (such as 50 Hz or 60 Hz) corresponds to the position of the stable fundamental wave energy. When active enhancement processing is performed on the signal, if the frequency enhancement strategy (such as harmonic amplification, signal superposition, etc.) amplifies some frequency components and makes them coincide with the system fundamental wave frequency region, then the power spectrum in this frequency band will increase significantly, forming an unnatural peak or fluctuation. This fluctuation is the "abnormal fluctuation". Its essence is that the energy of the enhanced signal is abnormally concentrated near the system operating frequency, breaking the balance of the normal spectral energy distribution, indicating that the enhanced signal frequency overlaps with the system frequency. This overlap may cause spectral resonance, energy leakage, or signal feature distortion, seriously interfering with the identification of fault features. Therefore, the spectral power fluctuation is an important indirect feature for discriminating frequency overlap.

[0062] The specific steps for comprehensively analyzing the power distribution of the enhanced signal in the frequency spectrum under the detection window to generate a power spectral density fluctuation reference value are as follows:

[0063] In the process of signal spectral analysis, first calculate the power spectral density of the enhanced electrical signal to understand the energy distribution of the signal in different frequency ranges. The power spectral density is an important indicator of the signal frequency components, which is extracted from the time-domain signal through the fast Fourier transform (FFT) or other frequency-domain conversion methods, calculate the power of each frequency band, and the calculation expression is as follows: , where is the power spectral density of the th frequency band, is the center frequency of the th frequency band,

[0064] The function of the above steps is to calculate the power value within each frequency band, reflecting the energy concentration degree of the signal in that frequency band. The key to this step lies in being able to capture the fluctuation characteristics of the signal in different frequency bands by dividing the frequency band of the signal and calculating the power value within each frequency band.

[0065] After obtaining the power spectral density of each frequency band, further analyze the fluctuation degree of the power in the spectrum to quantify the change of the signal frequency. The calculation expression of the reference value of the power spectral density fluctuation is as follows: , where is the reference value of the power spectral density fluctuation, is the power spectral density of the previous frequency band, is the weight factor, indicating the contribution degree of the th frequency band to the power fluctuation,

[0066] By calculating the power difference between adjacent frequency bands and weighted summation, the above steps can quantify the volatility of the spectrum. If the power difference of some frequency bands is significant, it indicates that the frequency components of the signal have changed greatly in these frequency bands, which may be caused by the overlap of the signal frequency with the normal operating frequency of the system (such as 50Hz or 60Hz). Finally, the larger the value of the reference value of the power spectral density fluctuation, the more obvious the overlap between the signal frequency and the normal operating frequency of the system, and the more significant the spectrum fluctuation.

[0067] The larger the reference value of the power spectral density fluctuation generated by comprehensively analyzing the power distribution of the enhanced signal in the frequency spectrum under the detection window, the more it indicates that the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system. Specifically, the reference value of the power spectral density fluctuation is used to measure whether the power distribution in the signal spectrum is stable. When the signal frequency overlaps with the normal operating frequency of the power system (such as 50 Hz or 60 Hz), abnormal fluctuations may occur in the spectrum of the enhanced signal, which means that the frequency components accumulate in the region close to the operating frequency, resulting in an abnormal increase or fluctuation of the power spectral density in this frequency band. The increase in the reference value means that the energy distribution fluctuation of the spectrum on these frequency components increases, indicating a higher degree of frequency overlap. When the frequency of the enhanced signal does not overlap with the operating frequency, the power spectrum distribution of the signal is relatively stable, and the fluctuation reference value is low. Therefore, this reference value can be used to effectively judge whether the enhanced signal overlaps with the system frequency.

[0068] Input the key features obtained through comprehensive analysis into a pre-trained machine learning model for further evaluation to determine whether the enhanced signal overlaps with the normal operating frequency;

[0069] Input the reference value of the amplitude-phase error and the reference value of the power spectral density fluctuation obtained through comprehensive analysis into a pre-trained machine learning model for further evaluation. Generate a frequency overlap risk coefficient through the machine learning model, and judge whether the enhanced signal overlaps with the normal operating frequency based on the frequency overlap risk coefficient.

[0070] A pre-trained machine learning model refers to a machine learning model that has been trained with historical data, samples, and annotations, and is used to process new input data and make predictions or classifications in practical applications. During the training process of the model, through learning a large amount of annotated data, it has learned the correlation between various features in the signal and the target output (such as frequency overlap risk). Therefore, a pre-trained machine learning model is capable of automatically identifying key patterns, regularities, and anomalies in the signal, and thus can accurately judge whether the enhanced signal overlaps with the normal operating frequency of the system. The process of model training includes selecting appropriate features (such as amplitude-phase error, power spectral density fluctuation, etc.), and fitting the data through supervised learning algorithms (such as support vector machines, decision trees, neural networks, etc.). The training dataset usually includes different states of various electrical signals (including normal operating states and fault states with frequency overlap), and each sample is equipped with a label indicating whether frequency overlap has occurred in this sample.

[0071] After training is completed, the machine learning model continuously adjusts its internal parameters through optimization algorithms, enabling the model to predict new, unseen data as accurately as possible. In practical applications, when newly acquired signals are subjected to feature extraction and analysis, these feature values (such as amplitude-phase error reference values and power spectral density fluctuation reference values) are passed as inputs to the pre-trained model. The model evaluates the input features based on the previously learned rules and patterns and calculates a frequency overlap risk coefficient. This risk coefficient represents the likelihood and severity of the enhanced signal overlapping with the normal operating frequency. Based on the value of the frequency overlap risk coefficient, the system can determine whether the signal has overlapped with the system's normal operating frequency and further decide whether measures need to be taken (such as frequency shifting or signal adjustment). By using the trained model, the fault detection system can achieve intelligent and automated signal analysis and judgment, improving the accuracy and response speed of fault detection and avoiding the deficiencies that may exist in manual intervention or traditional methods.

[0072] The machine learning model is not limited here. It can comprehensively analyze the amplitude-phase error reference value and the power spectral density fluctuation reference value to generate a frequency overlap risk coefficient. Any machine learning model that can do this is acceptable. To implement the technical solution of the present invention, the present invention provides a specific implementation method:

[0073] The frequency overlap risk coefficient is generated according to the following formula: , where and are respectively the preset proportionality coefficients of the amplitude-phase error reference value and the power spectral density fluctuation reference value , and and are both greater than 0.

[0074] The preset proportionality coefficient refers to the coefficient set in the model through prior knowledge or experience to weight the importance of different features, thereby affecting the model's learning and calculation of these features. Specifically in this formula, the preset proportionality coefficients and are used to weight the contributions of the amplitude-phase error reference value and the power spectral density fluctuation reference value respectively. These two coefficients determine the degree of influence of each feature on the final calculation result of the frequency overlap risk coefficient .

[0075] In practical applications, and The size may be set based on historical data, experimental results, or expert experience. These proportionality coefficients can help the model more accurately adjust and evaluate the contributions of different factors in the signal to the frequency overlap risk, while ensuring the stability and reliability of the model. Ideally, and should be adjusted according to the characteristics of the actual signal, and their sum usually equals 1 to ensure that the weighted sum of the signal does not distort during the calculation process.

[0076] From the frequency overlap risk coefficient, the larger the amplitude-phase error reference value generated by comprehensively analyzing the amplitude and phase changes of the signal under the detection window, and the larger the power spectral density fluctuation reference value generated by comprehensively analyzing the power distribution of the enhanced signal in the spectrum under the detection window, it indicates that the larger the frequency overlap risk coefficient generated when judging whether the enhanced signal overlaps with the normal operating frequency through a pre-trained machine learning model, which means the greater the probability that the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system. Conversely, it indicates that the probability that the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system is smaller.

[0077] Compare and analyze the frequency overlap risk coefficient generated when judging whether the enhanced signal overlaps with the normal operating frequency through a pre-trained machine learning model with the pre-set frequency overlap risk coefficient reference threshold to determine whether the enhanced signal overlaps with the normal operating frequency. The judgment logic is as follows:

[0078] If the frequency overlap risk coefficient is greater than the pre-set frequency overlap risk coefficient reference threshold, it is judged that the frequency of the enhanced signal overlaps with the normal operating frequency of the power distribution system; if the frequency overlap risk coefficient is less than or equal to the pre-set frequency overlap risk coefficient reference threshold, it is judged that the frequency of the enhanced signal does not overlap with the normal operating frequency of the power distribution system.

[0079] When it is identified that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a digital signal processing (DSP) algorithm is used to introduce a frequency shift operation into the enhanced signal to shift the frequency bandwidth of the signal to a frequency band outside the operating frequency of the power distribution system to avoid frequency overlap; subsequently, the frequency-shifted signal is further analyzed to confirm that its frequency no longer overlaps with the operating frequency of the power distribution system, and based on this, the identification of the fault signal is completed;

[0080] By introducing a frequency shift operation through a digital signal processing (DSP) algorithm, the problem of the enhanced signal frequency overlapping with the normal operating frequency of the power distribution system (such as 50 Hz or 60 Hz) is effectively solved, thus avoiding fault detection errors caused by spectral resonance or frequency interference. In the fault detection of the power distribution system, when an active enhancement strategy is used to process electrical signals, the enhanced signal may be distorted or interfered due to the overlap between the signal frequency and the system operating frequency, making it difficult to accurately identify the fault characteristics. This overlap affects the spectral structure of the signal, causing the system to be unable to correctly distinguish between normal operating signals and potential fault signals, thereby increasing the risk of misjudgment or missed judgment.

[0081] To effectively solve this problem, a digital signal processing (DSP) algorithm is used for the frequency shift operation. The frequency shift operation ensures that the frequency of the signal no longer overlaps with the system operating frequency by translating the frequency components of the enhanced signal. Specifically, the DSP algorithm shifts the frequency bandwidth of the enhanced signal to an area outside the operating frequency of the power system, thus avoiding spectral resonance and eliminating interference between signals. The signal after the frequency shift operation will be in a non-interfering frequency band, thereby maintaining the characteristics and stability of the enhanced signal.

[0082] Subsequently, by further analyzing the frequency-shifted signal, it can be confirmed that the spectrum of the signal no longer overlaps with the operating frequency, ensuring the authenticity and accuracy of the signal. This process helps the system to more accurately identify fault signals and ensures the reliability of the fault detection results. Through the frequency shift operation, not only the interference caused by frequency overlap is effectively avoided, but also the effectiveness of the enhanced signal is guaranteed, providing a clearer and more accurate signal basis for subsequent fault diagnosis.

[0083] When it is recognized that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a digital signal processing (DSP) algorithm is used to introduce a frequency shift operation in the enhanced signal, shifting the frequency bandwidth of the signal to a frequency band outside the operating frequency of the power distribution system; subsequently, the specific steps for further analyzing the frequency-shifted signal are as follows:

[0084] After identifying the frequency overlap, a digital signal processing (DSP) algorithm is used to perform a frequency shift on the enhanced signal, shifting its frequency components from within the operating frequency bandwidth of the power distribution system to an external frequency band to avoid frequency overlap. The calculation expression is as follows:

[0085] When it is determined that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a frequency shift operation is introduced through digital signal processing (DSP) technology, shifting the frequency bandwidth of the signal out of the operating frequency band of the power distribution system. The frequency shift operation is achieved by applying a phase rotation factor in the frequency domain to translate the signal and avoid overlapping with the operating frequency (such as 50 Hz). The frequency shift calculation expression is as follows: , where is the frequency-domain representation of the frequency-shifted signal, that is, the spectrum of the enhanced signal after frequency shifting. is the frequency-domain representation of the original enhanced signal, that is, the spectrum of the enhanced signal. is the complex exponential function. is the imaginary unit. is the frequency shift amount (offset). is the natural base.

[0086] Through the above steps, the overall signal frequency is shifted to an area far from the working frequency band, avoiding resonance or interference with the distribution system frequency. This ensures that the characteristics of the enhanced signal are not interfered by the distribution system frequency, and subsequent signal analysis and fault diagnosis can continue.

[0087] After the frequency shift operation is completed, further analysis of the frequency-shifted signal is required to ensure that the signal frequency has been completely decoupled and no longer overlaps with the working frequency of the distribution system. The specific operation is to recalculate the frequency overlap risk coefficient and determine whether it is lower than the reference threshold, so as to confirm the processing effect of the signal and identify the fault signal. The calculation expression is as follows: , where is the recalculated frequency overlap risk coefficient after frequency shift, used to evaluate whether the frequency-shifted signal still overlaps with the distribution system working frequency. is the frequency overlap risk coefficient calculation model, used to analyze the frequency characteristics of the frequency-shifted signal. is the feature extraction function, used to extract new frequency-domain features from the frequency-shifted signal for risk coefficient calculation.

[0088] If , where is the frequency overlap risk coefficient reference threshold.

[0089] Through this step, the frequency overlap risk coefficient of the frequency-shifted signal is re-evaluated, and the fault signal is identified. If , it means that the signal frequency has successfully separated from the system working frequency band and there is no longer overlap, and fault diagnosis and location can be carried out according to the frequency-shifted signal.

[0090] Through a series of steps such as real-time signal acquisition and enhancement, feature extraction and frequency overlap analysis, machine learning model evaluation, and frequency shift operation in digital signal processing (DSP), the present invention ensures that the spectrum of the enhanced signal does not overlap with the operating frequency of the system. This process avoids problems such as distorted or misjudged fault signals caused by spectrum interference, enabling clear and accurate identification of fault signals. In addition, through the combination of machine learning models and DSP algorithms, the signal processing process can be dynamically adjusted to automatically identify and correct the impact of frequency overlap, thereby improving the overall performance and stability of the fault detection system. Finally, this solution provides a more intelligent and accurate solution for distribution system fault detection, contributing to enhancing the safety and reliability of the power system.

[0091] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0092] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, the described embodiments can be modified in various different ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

[0093] It should be noted that in this article, if there are relational terms such as first and second, they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the existence of additional identical elements in the process, method, article or device comprising the element.

[0094] It should be understood that in various embodiments of the present application, the magnitude of the sequence numbers of the above processes does not mean the order of execution is prior or subsequent. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0095] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0096] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0097] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0098] In addition, in each embodiment of this application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0099] As described above, only the specific implementation manners of this application are provided, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0100] Only some exemplary embodiments of the present invention have been described by way of illustration above. Undoubtedly, for those of ordinary skill in the art, without departing from the spirit and scope of the present invention, the described embodiments can be modified in various different ways. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the protection scope of the claims of the present invention.

Claims

1. An active enhancement detection method for line fault characteristics of a distribution box, characterized in that, Including the following steps: Collect electrical signals in the distribution box in real time, and process the signals through an active enhancement strategy to highlight fault features, while obtaining the enhanced electrical signal data; Store the enhanced electrical signal data obtained in real time into a data set, extract key features reflecting the overlap between the signal frequency and the normal operating frequency of the power distribution system from the data set through feature engineering techniques, comprehensively analyze the extracted key features, and quantify the degree of frequency overlap; Input the key features that have been comprehensively analyzed into a pre-trained machine learning model for further evaluation to determine whether the enhanced signal overlaps with the normal operating frequency; When it is identified that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a digital signal processing algorithm is used to introduce a frequency shift operation into the enhanced signal to shift the frequency bandwidth of the signal to a frequency band outside the operating frequency of the power distribution system to avoid frequency overlap; Subsequently, the frequency-shifted signal is further analyzed to confirm that its frequency no longer overlaps with the operating frequency of the power distribution system, and based on this, the identification of the fault signal is completed; Extract key features reflecting the overlap between the signal frequency and the normal operating frequency of the power distribution system from the data set through feature engineering techniques. The extracted features include the amplitude and phase changes of the signal and the power distribution of the enhanced signal in the frequency spectrum. The amplitude and phase changes of the signal and the power distribution of the enhanced signal in the frequency spectrum are comprehensively analyzed under the detection window to generate an amplitude-phase error reference value and a power spectral density fluctuation reference value respectively, and the degree of frequency overlap is quantified through the amplitude-phase error reference value and the power spectral density fluctuation reference value.

2. The active enhanced detection method for line fault characteristics of a distribution box according to claim 1, characterized in that, The specific steps for collecting electrical signals in the distribution box in real time and processing the signals through an active enhancement strategy to highlight fault features are as follows: Collect electrical signals from electrical equipment in the distribution box in real time to provide raw data for subsequent processing; Apply an active enhancement strategy to the collected electrical signals to highlight potential fault features; After applying the enhancement strategy, obtain the enhanced electrical signal data to provide an optimized signal input for subsequent analysis and processing.

3. The active enhanced detection method for line fault characteristics of a distribution box according to claim 1, wherein The specific steps for comprehensively analyzing the amplitude and phase changes of the signal under the detection window to generate an amplitude-phase error reference value are as follows: Quantify the amplitude change of the signal, analyze the amplitude error between the enhanced signal and the ideal signal, define the amplitude distortion factor, measure the amplitude difference of the signal in the frequency space to quantify the degree of amplitude change, and the calculation expression of the amplitude distortion factor is as follows: , where is the amplitude distortion factor, is the frequency amplitude value of the enhanced signal at the th frequency point, is the frequency amplitude value of the ideal signal at the th frequency point, is the number of frequencies, is a very small positive number used to avoid division by zero, is the exponential parameter used to non-linearly amplify the amplitude difference; Analyze the phase error of the signal, quantify the phase change of the signal, judge whether the phase of the signal has changed by calculating the difference in phase between the enhanced signal and the ideal signal, define the phase distortion factor, and the calculation expression of the phase distortion factor is as follows: , where is the phase distortion factor, is the adjustment parameter, is the frequency of the enhanced signal at the th frequency point at the phase angle, is the frequency of the ideal signal at the th frequency point at the phase angle, is the phase index parameter, is the exponential change of the phase error; Finally, combine the amplitude distortion factor and the phase distortion factor to obtain the amplitude-phase error reference value, quantify the amplitude and phase changes of the enhanced signal, and the calculation expression is as follows: , where is the amplitude-phase error reference value.

4. The active enhanced detection method for line fault characteristics of a distribution box according to claim 1, characterized in that The specific steps for comprehensively analyzing the power distribution of the enhanced signal in the frequency spectrum under the detection window to generate a power spectral density fluctuation reference value are as follows: In the process of spectral analysis of the signal, first calculate the power spectral density of the enhanced electrical signal to understand the energy distribution of the signal in different frequency ranges, calculate the power of each frequency band, and the calculation expression is as follows: , where is the power spectral density of the th frequency band, is the center frequency of the th frequency band, is the bandwidth, is the energy distribution of the signal at different frequencies . After obtaining the power spectral density of each frequency band, further analyze the degree of power fluctuation in the spectrum to quantify the change in signal frequency. The calculation expression of the reference value of power spectral density fluctuation is as follows: , where is the reference value of power spectral density fluctuation, is the power spectral density of the previous frequency band, is the weight factor, indicating the contribution degree of the th frequency band to power fluctuation, is the total number of frequency bands.

5. The active enhanced detection method for line fault characteristics of a distribution box according to claim 1, characterized in that, Input the amplitude-phase error reference value and the power spectral density fluctuation reference value that have been comprehensively analyzed into a pre-trained machine learning model for further evaluation. A frequency overlap risk coefficient is generated through the machine learning model, and it is determined whether the enhanced signal overlaps with the normal operating frequency through the frequency overlap risk coefficient.

6. The active enhanced detection method for line fault characteristics of a distribution box according to claim 5, characterized in that, Compare and analyze the frequency overlap risk coefficient generated when determining whether the enhanced signal overlaps with the normal operating frequency through the pre-trained machine learning model with a pre-set frequency overlap risk coefficient reference threshold to determine whether the enhanced signal overlaps with the normal operating frequency. The judgment logic is as follows: If the frequency overlap risk coefficient is greater than a pre-set reference threshold of the frequency overlap risk coefficient, it is determined that the frequency of the enhanced signal overlaps with the normal operating frequency of the distribution system; if the frequency overlap risk coefficient is less than or equal to the pre-set reference threshold of the frequency overlap risk coefficient, it is determined that the frequency of the enhanced signal does not overlap with the normal operating frequency of the distribution system.

7. The active enhanced detection method for line fault characteristics of a distribution box according to claim 6, characterized in that When it is recognized that the frequency of the enhanced signal overlaps with the operating frequency of the distribution system, a digital signal processing algorithm is used to introduce a frequency shift operation in the enhanced signal to shift the frequency bandwidth of the signal to a frequency band outside the operating frequency of the distribution system; subsequently, the specific steps for further analyzing the frequency-shifted signal are as follows: After identifying the frequency overlap, a digital signal processing algorithm is used to shift the frequency of the enhanced signal, shifting its frequency components from within the operating frequency bandwidth of the distribution system to an external frequency band to avoid frequency overlap, and the calculation expression is as follows: When it is determined that the frequency of the enhanced signal overlaps with the operating frequency of the power distribution system, a frequency shift operation is introduced through digital signal processing technology to shift the frequency bandwidth of the signal out of the operating frequency band of the power distribution system. The frequency shift calculation expression is as follows: , where is the frequency-domain representation of the signal after frequency shift, is the frequency-domain representation of the original enhanced signal, that is, the spectrum of the enhanced signal, is the complex exponential function, is the imaginary unit, is the frequency shift amount, is the natural base; After the frequency shift operation is completed, further analysis of the frequency-shifted signal is required to ensure that the frequency of the signal has been fully decoupled and no longer overlaps with the operating frequency of the power distribution system. The calculation expression is as follows: , where is the frequency overlap risk coefficient recalculated after the frequency shift, is the frequency overlap risk coefficient calculation model, which is used to analyze the frequency characteristics of the frequency-shifted signal, is the feature extraction function; If , where is the reference threshold of the frequency overlap risk coefficient.

Images