Charging pile fault intelligent diagnosis method and system, storage medium and electronic equipment

Abstract

The invention discloses a charging pile fault intelligent diagnosis method and system, a storage medium and electronic equipment, and relates to the technical field of new energy. Comprising the steps that under the condition that a contactor of a charging pile is connected or disconnected, feature extraction is conducted on current waveforms, infrared thermal image data and electromagnetic radiation signals, and current feature parameters, temperature feature parameters and electromagnetic feature parameters are obtained; determining a dynamic characteristic parameter set based on the time domain relevance between the current characteristic parameters and the electromagnetic characteristic parameters; determining a contact performance parameter set based on a coupling relationship between the temperature characteristic parameter and the electromagnetic characteristic parameter; performing fusion calculation on the dynamic characteristic parameter set and the contact performance parameter set to obtain a current contact quality score; and obtaining a historical contact quality score, and determining a fault detection result according to the attenuation characteristics of the historical contact quality score and the current contact quality score. By implementing the technical scheme provided by the invention, the timeliness of fault diagnosis of the charging pile is effectively improved, and safe and stable operation of the charging pile is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy, in particular to a charging pile fault intelligent diagnosis method and system, a storage medium and an electronic device. BACKGROUND

[0002] With the rapid development of new energy vehicle industry, the scale of charging infrastructure construction is expanding. As the key equipment for charging new energy vehicles, the reliability and safety of charging piles directly affect the charging experience of users and the safety of vehicle use. Among the various components of the charging pile, the contactor bears the important function of large current on-off control and is one of the core components most prone to failure in the charging pile.

[0003] Currently, the fault diagnosis of the contactor of the charging pile mainly relies on periodic detection and single parameter monitoring. Common diagnosis methods include measuring the contact current of the contactor, observing the surface temperature change of the contactor, and other ways to determine the working state of the contactor. However, due to the gradual and hidden nature of contactor failures, relying solely on threshold values of a single parameter cannot timely detect potential faults, and cannot fully reflect the performance degradation process of the contactor, which can cause fault warning lag or misjudgment, affecting the safe operation of the charging pile. SUMMARY

[0004] Therefore, the present application provides a charging pile fault intelligent diagnosis method and system, a storage medium and an electronic device.

[0005] In a first aspect, the present application provides a charging pile fault intelligent diagnosis method, which comprises: In the current state of the contactor of the charging pile being turned on or turned off, acquiring the current waveform, electromagnetic radiation signal generated by the contactor, and infrared thermal image data of the contact point of the contactor; Respectively extracting features from the current waveform, infrared thermal image data and electromagnetic radiation signal to obtain current feature parameters, temperature feature parameters and electromagnetic feature parameters; Based on the time domain correlation between the current feature parameters and the electromagnetic feature parameters, determining a dynamic feature parameter set of the contactor; Based on the coupling relationship between the temperature feature parameters and the electromagnetic feature parameters, determining a contact performance parameter set of the contactor; Fusing and calculating the dynamic feature parameter set and the contact performance parameter set to obtain a current contact quality score of the contactor in the current state; Acquiring the historical contact quality scores corresponding to the turning on or turning off of the contactor a preset number of times before the current state, and determining a fault detection result according to the attenuation characteristics of the historical contact quality scores and the current contact quality score.

[0006] By adopting the technical scheme, when the charging pile contactor is turned on or turned off, current waveform, electromagnetic radiation signal and infrared thermal image data are synchronously acquired, current characteristic parameters, temperature characteristic parameters and electromagnetic characteristic parameters are obtained by performing feature extraction on the three signals, a dynamic characteristic parameter set is determined based on the time domain correlation between the current characteristic parameters and the electromagnetic characteristic parameters, a contact performance parameter set is determined based on the coupling relationship between the temperature characteristic parameters and the electromagnetic characteristic parameters, a current contact quality score of the contactor in the current state is obtained by performing fusion calculation on the dynamic characteristic parameter set and the contact performance parameter set, and fault detection is performed in combination with the attenuation feature of the historical contact quality score. The scheme breaks through the limitation of traditional single parameter monitoring, can comprehensively reflect the dynamic characteristics and contact performance of the contactor through fusion analysis of multi-source information, effectively identifies the gradual fault features in the performance degradation process of the contactor, and simultaneously, through establishing a feature extraction model based on time domain correlation and coupling relationship, the extraction accuracy of the fault features is improved, and the residual life of the contactor is evaluated and predicted through historical data analysis, thereby effectively improving the accuracy and timeliness of the fault diagnosis of the charging pile and ensuring the safe and stable operation of the charging pile.

[0007] In a second aspect of the present application, a charging pile fault intelligent diagnosis system is provided, which comprises: A data acquisition module is configured to acquire current waveform, electromagnetic radiation signal and infrared thermal image data of a contactor of a charging pile in a current state in which the contactor is turned on or turned off. A feature extraction module is configured to perform feature extraction on the current waveform, infrared thermal image data and electromagnetic radiation signal respectively to obtain current characteristic parameters, temperature characteristic parameters and electromagnetic characteristic parameters. A characteristic parameter determination module is configured to determine a dynamic characteristic parameter set of the contactor based on the time domain correlation between the current characteristic parameters and the electromagnetic characteristic parameters. A performance parameter determination module is configured to determine a contact performance parameter set of the contactor based on the coupling relationship between the temperature characteristic parameters and the electromagnetic characteristic parameters. A quality score calculation module is configured to perform fusion calculation on the dynamic characteristic parameter set and the contact performance parameter set to obtain a current contact quality score of the contactor in the current state. A detection result generation module is configured to acquire historical contact quality scores corresponding to a preset number of times of turning on or turning off of the contactor before the current state, and determine a fault detection result according to the attenuation feature of the historical contact quality scores and the current contact quality score.

[0008] In a third aspect of the present application, a computer storage medium is provided, which stores a plurality of instructions adapted to be loaded by a processor and execute the method steps described above.

[0009] In a fourth aspect of the present application, an electronic device is provided, comprising a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and execute the method steps described above.

[0010] In summary, the one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: The present application synchronously acquires current waveform, electromagnetic radiation signal and infrared thermal image data when the charging pile contactor is turned on or turned off, extracts features from the three signals to obtain current feature parameters, temperature feature parameters and electromagnetic feature parameters, determines a dynamic feature parameter set based on the time domain correlation between the current feature parameters and the electromagnetic feature parameters, determines a contact performance parameter set based on the coupling relationship between the temperature feature parameters and the electromagnetic feature parameters, and obtains a current contact quality score by fusion calculation of the dynamic feature parameter set and the contact performance parameter set, and detects faults in combination with the decay characteristics of historical contact quality scores. The present application breaks through the limitations of traditional single parameter monitoring, can comprehensively reflect the dynamic characteristics and contact performance of the contactor through fusion analysis of multi-source information, effectively identifies the gradual fault characteristics in the performance degradation process of the contactor, establishes a feature extraction model based on time domain correlation and coupling relationship to improve the extraction accuracy of fault features, and realizes the evaluation and prediction of the remaining life of the contactor through historical data analysis, thereby effectively improving the accuracy and timeliness of the fault diagnosis of the charging pile and ensuring the safe and stable operation of the charging pile. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 is a flowchart of a charging pile fault intelligent diagnosis method provided by the embodiments of the present application; Figure 2 is a module schematic diagram of a charging pile fault intelligent diagnosis system provided by the embodiments of the present application; Figure 3 is a structural schematic diagram of an electronic device provided by the embodiments of the present application.

[0012] Explanation of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0013] In order for those skilled in the art to better understand the technical solutions in the specification, the technical solutions in the specification will be clearly and completely described below in combination with the drawings in the specification. Obviously, the described embodiments are only some of the embodiments of the present application, not all.

[0014] In the description of the embodiments of the present application, the words such as "for example" or "for instance" are used to represent an example, illustration or description. Any embodiment or design scheme described as "for example" or "for instance" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words such as "for example" or "for instance" are intended to present the relevant concept in a specific manner.

[0015] In the description of the embodiments of the present application, the term "a plurality of" means two or more. For example, a plurality of systems means two or more systems, and a plurality of screen terminals means two or more screen terminals. In addition, the terms "first" and "second" are used for description purposes only and should not be interpreted as indicating or implying relative importance or implicitly indicating the indicated technical features. Therefore, the features defined with "first" and "second" can explicitly or implicitly include one or more features. The terms "include", "contain", "have" and their variants mean "include but are not limited to", unless otherwise specifically emphasized.

[0016] The technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all.

[0017] Please refer to Figure 1 , a flowchart of a charging pile fault intelligent diagnosis method is presented, which can be realized by a computer program, can be realized by a single-chip microcomputer, and can run on a charging pile fault intelligent diagnosis system. The computer program can be integrated in a computer device or run as an independent tool application. Specifically, the method includes steps 10 to 60, which are as follows. Step 10: In the current state of the contactor of the charging pile being turned on or turned off, the current waveform, electromagnetic radiation signal and infrared thermal image data of the contact point of the contactor generated by the contactor are acquired.

[0018] In the embodiments of the present application, the current state refers to the working state of the contactor at a certain specific time, indicating the contactor action state of this diagnosis, and specifically includes the contactor on state and the contactor off state.

[0019] The current waveform refers to a curve graph of current flowing through the contactor changing with time during the on or off process of the contactor. The electromagnetic radiation signal refers to an electromagnetic wave signal generated when the contactor operates, mainly derived from electromagnetic interference generated by mechanical operation of the contactor, electromagnetic radiation in the arc discharge process, and electromagnetic pulses when the contact point is in contact or separated, etc. The infrared thermal image data refers to a temperature distribution image of the contact point and the surrounding area of the contactor.

[0020] Specifically, as the core switching device of the charging pile, the failure of the contactor is often a gradual degradation process, and a single parameter cannot comprehensively reflect its health status. The current waveform can reflect the change of the electrical characteristics of the contactor, the electromagnetic radiation signal can reveal the mechanical action and arc characteristics of the contactor, and the infrared thermal image data can show the contact resistance and heat dissipation condition. The combination of the three can comprehensively monitor the working state of the contactor from different physical dimensions.

[0021] When the contactor operation instruction is issued by the charging pile control system, the system first starts the data acquisition module and records various parameters in real time during the complete process of the contactor on or off operation. For the acquisition of the current waveform, a high-precision Hall current sensor installed in the main circuit of the contactor is used to monitor the current change flowing through the contactor in real time. The sensor can capture the complete current change process such as the inrush current at the moment of contactor closing, the steady-state operating current, and the arc current when the contactor is opened, and the sampling frequency is set to 10 kHz to ensure that the details of the current waveform can be accurately recorded. At the same time, a wideband electromagnetic signal detection antenna is arranged near the contactor to capture the electromagnetic radiation signals generated during the operation of the contactor. The detection device covers a frequency range of 1 MHz to 1 GHz and can effectively capture various electromagnetic interference signals generated during the mechanical operation, arc discharge, and contact point collision of the contactor. In addition, a high-resolution infrared thermal imager is used to continuously image the contact point area of the contactor. The device has a temperature resolution of 0.1°C and a response time of milliseconds, and can record the temperature distribution changes of the contact point and its surrounding area in real time. During the synchronous data acquisition process, the system uses a unified time stamp marker to ensure the accurate correspondence of the three types of data on the time axis. The acquisition time window covers the complete period of 100 ms before the contactor operation, the operation process, and 200 ms after the operation, to capture the whole process characteristics of the contactor state change.

[0022] Step 20: respectively extracting features from the current waveform, infrared thermal image data and electromagnetic radiation signal to obtain current characteristic parameters, temperature characteristic parameters and electromagnetic characteristic parameters.

[0023] In the embodiments of the present application, the current characteristic parameters refer to key numerical indicators extracted by time-frequency domain analysis of the current waveform generated by the contactor, including but not limited to current peak value, current change rate, and harmonic components of the current waveform, etc.

[0024] The temperature characteristic parameter refers to a thermal characteristic quantity obtained by analyzing the temperature field of the infrared thermal image data of the contactor contact point, and mainly includes but is not limited to the contact point temperature, the temperature gradient, and the temperature distribution uniformity index.

[0025] The electromagnetic characteristic parameter refers to an electromagnetic characteristic index extracted by performing frequency spectrum analysis on the electromagnetic radiation signal generated in the action process of the contactor, and includes but is not limited to the characteristic frequency amplitude, the frequency spectrum energy distribution, and the frequency offset.

[0026] Specifically, the embodiment adopts a parallel feature extraction strategy to process the three types of signals respectively. For the feature extraction of the current waveform, the system first performs fast Fourier transform on the collected current time domain signal, converts the time domain waveform into a frequency domain signal, then identifies and extracts the current peak value in the time domain as a direct index of the current carrying capacity of the contactor, obtains the current change rate by calculating the ratio of the current difference between adjacent sampling points to the time interval, and analyzes the amplitudes of the main harmonic components such as 2nd, 3rd, 5th, etc. in the frequency domain as the harmonic components of the current waveform. The processing of the infrared thermal image data adopts a temperature field analysis algorithm, locates the contact point area through image processing technology and calculates the average temperature value of the area as the contact point temperature, calculates the temperature gradient by using the gradient operator to calculate the temperature difference between the contact point and the surrounding area, and quantifies the temperature distribution uniformity index by calculating the standard deviation and coefficient of variation of the temperature distribution. The electromagnetic radiation signal adopts a power spectrum density analysis method, identifies the dominant frequency in the signal and extracts its corresponding amplitude as the characteristic frequency amplitude, calculates the energy proportion of each frequency band to form the frequency spectrum energy distribution, and obtains the frequency offset by comparing with the standard frequency template. This parallel processing method can quickly extract the three types of characteristic parameters, providing accurate data basis for subsequent fusion analysis.

[0027] On the basis of the above embodiment, as another optional embodiment, the feature extraction is performed on the current waveform, the infrared thermal image data and the electromagnetic radiation signal respectively to obtain the current characteristic parameter, the temperature characteristic parameter and the electromagnetic characteristic parameter, and the step of obtaining the current characteristic parameter, the temperature characteristic parameter and the electromagnetic characteristic parameter can further include steps 201-203: Step 201: performing time-frequency domain analysis on the current waveform to extract the current peak value, the current change rate and the harmonic components of the current waveform as the current characteristic parameter.

[0028] Specifically, time-frequency domain analysis of current waveform is to comprehensively capture the electrical characteristic changes of contactor in different working stages, because contactor failure often shows abnormal fluctuation of current characteristics. Firstly, the original current waveform data collected is preprocessed, and a Butterworth low-pass filter is used to remove high-frequency noise, and the filter cutoff frequency is set to 1 / 4 of the sampling frequency to retain the effective signal components. In the current peak extraction process, the system uses a sliding window maximum value detection algorithm, and the window size is set to 100 sampling points. The global maximum value is found by traversing the entire current waveform data as the current peak, and the time position of the peak is recorded for subsequent time domain correlation analysis. For the calculation of current rate of change, the system uses five-point difference method for numerical differentiation of current waveform, and the specific formula is: where I(n) is the current value of the nth sampling point, and At is the sampling time interval. This method can effectively suppress the influence of noise on the differential operation. In terms of harmonic component extraction, the system first performs 4096-point fast Fourier transform (FFT) on the current waveform to convert the time domain signal to the frequency domain. Then, based on the power frequency of 50 Hz, the main harmonic frequency points of 2nd harmonic 100 Hz, 3rd harmonic 150 Hz, 5th harmonic 250 Hz, etc. are identified, and the amplitude of these frequency points is extracted as the harmonic component of the current waveform. The total harmonic distortion (THD) is calculated as a comprehensive evaluation index of current quality.

[0029] Step 202: Temperature field analysis of infrared thermal image data, extracting contact point temperature, temperature gradient, and temperature distribution uniformity index as temperature characteristic parameters.

[0030] Specifically, the purpose of temperature field analysis on infrared thermal image data is to evaluate the contact quality and heat dissipation performance of the contactor from a thermal perspective, as increased contact resistance and poor contact can lead to localized overheating. First, the original infrared thermal image undergoes image enhancement processing, employing a histogram equalization algorithm to improve its contrast, facilitating subsequent temperature feature extraction. In the contact point temperature extraction stage, the system uses a temperature threshold-based region segmentation algorithm to automatically identify contact point regions. Specifically, pixels in the thermal image with temperatures exceeding the ambient temperature by 15°C are marked as candidate contact points. Then, connected component analysis is used to identify the largest connected region as the primary contact point. The weighted average temperature of all pixels within this region is calculated as the contact point temperature, with the weights determined based on the distance from the pixel to the region center. The temperature gradient is calculated using the Sobel edge detection operator, calculating the temperature gradients Gx and Gy in the x and y directions respectively. The total temperature gradient is then obtained using the formula G=sqrt(Gx²+Gy²), and the maximum gradient value at the boundary of the contact point region is extracted as a feature parameter. To calculate the temperature distribution uniformity index, the system first divides the contact area into a 3×3 grid, calculates the average temperature of each sub-region, and then calculates the standard deviation and coefficient of variation of these nine temperature values. The standard deviation reflects the dispersion of the temperature distribution, while the coefficient of variation eliminates the influence of the absolute temperature value. The combination of the two can objectively evaluate the uniformity of the contact surface.

[0031] Step 203: Perform spectrum analysis on the electromagnetic radiation signal and extract the characteristic frequency amplitude, spectrum energy distribution, and frequency offset as electromagnetic characteristic parameters.

[0032] Specifically, spectral analysis of electromagnetic radiation signals aims to reveal the dynamic characteristics and potential fault features of contactors from an electromagnetic perspective, as the mechanical actions and arc discharges of contactors generate characteristic electromagnetic radiation. First, the acquired electromagnetic radiation signals are preprocessed, using a bandpass filter to remove low-frequency interference below 1MHz and high-frequency noise above 1GHz, retaining the effective frequency bands relevant to contactor operation. In the characteristic frequency amplitude extraction process, the system uses a 2048-point Hanning window FFT to perform spectral analysis. A peak detection algorithm identifies the main peaks in the spectrum; specifically, it calculates the first and second derivatives of the spectrum. Peaks are marked when the first derivative crosses zero and the second derivative is negative. The frequencies and amplitudes corresponding to the top five most significant peaks are then selected as characteristic frequency amplitudes, sorted by amplitude. The spectral energy distribution is calculated using a sub-band energy analysis method, dividing the 1MHz-1GHz frequency band into 10 equal sub-bands. The power spectral density integral value within each sub-band is calculated and then normalized to obtain the energy proportion of each sub-band, forming a 10-dimensional spectral energy distribution vector. The frequency offset measurement employs correlation analysis technology. The system pre-establishes a standard spectrum template under normal conditions. By calculating the cross-correlation function between the current signal spectrum and the standard template, the frequency offset corresponding to the correlation peak is found. At the same time, a phase correlation algorithm is used to improve the accuracy of the offset measurement, achieving a measurement accuracy at the Hz level. Through this comprehensive spectrum analysis method, subtle changes in the electromagnetic characteristics of the contactor can be effectively captured.

[0033] Step 30: Determine the set of dynamic characteristic parameters of the contactor based on the time-domain correlation between the current characteristic parameters and the electromagnetic characteristic parameters.

[0034] In this embodiment of the application, the dynamic characteristic parameter set refers to a set of parameters that characterize the dynamic operating characteristics of the contactor, constructed by analyzing the time-domain correlation between current characteristic parameters and electromagnetic characteristic parameters.

[0035] Specifically, to uncover the intrinsic relationship between the electrical and electromagnetic responses of a contactor and thus more accurately evaluate its dynamic performance, the system first calculates the time-series ratio of the peak current to the characteristic frequency amplitude. This is achieved by arranging the peak current in chronological order to form a time-series vector Ic(t), and arranging the characteristic frequency amplitude in the same chronological order to form a time-series vector Vf(t). The ratio sequence R(t) = Ic(t) / Vf(t) is then calculated, and statistical analysis of this sequence yields the amplitude matching coefficient, which reflects the degree of coordination between the current and electromagnetic responses. Next, the system analyzes the relationship between the rate of change of current and the frequency offset. The time delay between the two is calculated using a cross-correlation function. Specifically, a sliding correlation operation is performed on the current rate of change sequence and the frequency offset sequence, and the time lag corresponding to the maximum correlation coefficient is identified as the time delay value. Finally, the signal synchronization coefficient is calculated based on the harmonic components and spectral energy distribution of the current waveform. The degree of synchronization is quantified by aligning the two signal sequences in the time domain and calculating their overlap. Finally, the system uses a weighted fusion algorithm to generate a numerical sequence characterizing the contactor's dynamic properties, based on the amplitude matching coefficient, time delay value, and signal synchronization coefficient. The weights are determined according to the information entropy of each parameter. This time-domain correlation-based analysis method can effectively identify abnormal changes in the contactor's dynamic performance.

[0036] Based on the above embodiments, as an optional embodiment, the step of determining the dynamic characteristic parameter set of the contactor based on the time-domain correlation between current characteristic parameters and electromagnetic characteristic parameters may further include steps 301-304: Step 301: Calculate the time-series ratio of the peak current to the amplitude of the characteristic frequency to obtain the amplitude matching coefficient.

[0037] Specifically, calculating the time-series ratio of peak current to characteristic frequency amplitude to obtain the amplitude matching coefficient is to quantify the correlation between the contactor's electrical and electromagnetic responses in the amplitude dimension, because a normally functioning contactor should maintain a relatively stable proportional relationship between its peak current and electromagnetic radiation intensity. First, the peak current data and characteristic frequency amplitude data are time-aligned. Since the sampling frequencies of the two types of data may differ, the system uses a linear interpolation algorithm to resample the data to a unified time base, ensuring that each time point has corresponding peak current and characteristic frequency amplitude data. Then, the system establishes a time-series ratio calculation model. For the i-th time point, the time-series ratio R(i) = Ipeak(i) / Vfreq(i) is calculated, where Ipeak(i) is the peak current at the i-th time point, and Vfreq(i) is the corresponding characteristic frequency amplitude. To eliminate the influence of instantaneous fluctuations, a moving average filter is used to smooth the time-series ratio sequence, with the filter window size set to 10 data points. Next, the system calculates the statistical characteristics of the time-series ratio sequence, including the mean μR, standard deviation σR, and coefficient of variation CVR = σR / μR. Then, through normalization, the amplitude matching coefficient AMC = 1 / (1+CVR) is obtained. This coefficient ranges from 0 to 1; the closer the value is to 1, the higher the degree of matching between the peak current and the characteristic frequency amplitude. To improve calculation accuracy, the system also employs an outlier detection algorithm to remove abnormal data points other than those defined by the 3σ criterion, avoiding the influence of occasional interference on the matching coefficient calculation.

[0038] Step 302: Calculate the time delay value based on the correspondence between the rate of change of current and the frequency offset.

[0039] Specifically, the time delay value is calculated based on the correspondence between the current change rate and the frequency offset. The purpose is to quantify the timing relationship between the contactor's electrical and electromagnetic responses, as anomalies in the contactor's internal structure or operating mechanism can cause a time delay between the two. First, the current change rate data sequence dI / dt and the frequency offset data sequence Δf are preprocessed. Median filtering is used to remove impulse noise, and then a third-order Butterworth low-pass filter is used to smooth the data. Next, cross-correlation analysis is used to calculate the time delay between the two sequences. Specifically, the cross-correlation function Rxy(τ) = ∫x(t)y(t+τ)dt is calculated, where x(t) is the current change rate sequence, y(t) is the frequency offset sequence, and τ is the time delay parameter. The system calculates the cross-correlation function value in 1ms steps within the range of -50ms to +50ms, and the τ value that makes Rxy(τ) reach its maximum value is identified as the time delay value TD. To improve computational accuracy, the system employs parabolic interpolation to perform fine interpolation on data points near the cross-correlation peak, improving the measurement accuracy of time delay to the 0.1ms level. Simultaneously, the system calculates the peak value of the cross-correlation coefficient as a measure of the strength of the temporal correlation; when the peak value is less than 0.3, the two signals are considered to lack effective correlation, and the time delay value is set to invalid. Furthermore, to handle multi-peak cases, the system uses a peak detection algorithm to identify all significant peaks, selects the delay corresponding to the largest peak as the primary time delay value, and records the information of the second-highest peak for subsequent anomaly analysis.

[0040] Step 303: Obtain the signal synchronization coefficient based on the time-domain overlap between the harmonic components of the current waveform and the spectral energy distribution.

[0041] Specifically, the signal synchronization coefficient is obtained based on the time-domain overlap of the harmonic components of the current waveform and the spectral energy distribution. This is to evaluate the consistency between the contactor's electrical signal and electromagnetic signal in the frequency domain, since both should exhibit similar spectral characteristic changes within the same time period. First, the harmonic component data of the current waveform and the spectral energy distribution data are converted into time-varying vectors. For the harmonic components, the amplitude changes of the 2nd, 3rd, and 5th harmonics over time are extracted to form a 3D time-varying vector H(t)=[H2(t), H3(t), H5(t)]. For the spectral energy distribution, the energy proportion of the corresponding frequency band is selected to form a 3D time-varying vector E(t)=[E2(t), E3(t), E5(t)]. The system then calculates the temporal overlap of two time-varying vectors using a sliding window technique with a window size of 100ms. Within each time window, the cosine similarity CS(t) of vectors H(t) and E(t) is calculated as CS(t) = H(t)·E(t) / (||H(t)||×||E(t)||). This similarity reflects the degree of consistency between the two vectors in direction. Next, the system performs statistical analysis on the similarity values ​​of the entire time series, calculating the mean μCS and standard deviation σCS. The signal synchronization coefficient is then obtained using the formula SSC = μCS×(1-σCS / μCS), which comprehensively considers both the average level and stability of the similarity. To enhance the robustness of the algorithm, the system also employs the Dynamic Time Warping (DTW) algorithm to handle potential time offset issues, improving the accuracy of overlap calculation by finding the optimal time alignment path.

[0042] Step 304: Generate a numerical sequence characterizing the dynamic characteristics of the contactor based on the amplitude matching coefficient, time delay value, and signal synchronization coefficient, and use the numerical sequence as a set of dynamic characteristic parameters.

[0043] Specifically, generating a numerical sequence characterizing the contactor's dynamic characteristics based on the amplitude matching coefficient, time delay value, and signal synchronization coefficient is to integrate multiple independent characteristic parameters into a comprehensive dynamic characteristic descriptor, facilitating subsequent fault diagnosis and performance evaluation. First, the three characteristic parameters are normalized. Since the amplitude matching coefficient (AMC) and signal synchronization coefficient (SSC) both range from 0 to 1, while the time delay value (TD) ranges from -50ms to +50ms, the system uses a minimum-maximum normalization method to map the time delay value to the range of 0 to 1. The normalization formula is: The system then constructs a dynamic feature vector DFV=[AMC, TD_norm, SSC], a 3D vector containing the main information about the contactor's dynamic characteristics. To generate a numerical sequence with time-series characteristics, the system employs a sliding window technique with a 10ms step size and a 50ms window size. Within each time window, a weighted average of the dynamic feature vector is calculated, with weights determined based on the data's recentity—newer data has a higher weight. Next, the system uses Principal Component Analysis (PCA) to reduce the dimensionality of the feature vectors from multiple time windows, extracting the first principal component as the main representation of the dynamic characteristics, forming a one-dimensional numerical sequence. To retain more feature information, the system also calculates the combined features of the first two principal components, obtaining a comprehensive dynamic feature sequence using the formula DTS=α×PC1+β×PC2, where α and β are weight coefficients determined based on the principal component variance contribution rate. Finally, the system outputs the generated numerical sequence as a dynamic feature parameter set, which comprehensively reflects the changes in the contactor's dynamic characteristics.

[0044] Step 40: Based on the coupling relationship between temperature characteristic parameters and electromagnetic characteristic parameters, determine the contact performance parameter set of the contactor.

[0045] In this embodiment of the application, the contact performance parameter set refers to a set of parameters that characterize the contact quality and performance of the contactor, determined by analyzing the coupling relationship between temperature characteristic parameters and electromagnetic characteristic parameters. This parameter set mainly consists of two parts: contact state vector and contact stability index.

[0046] Specifically, to comprehensively evaluate the contact quality and performance of the contactor from a thermoelectric coupling perspective, the system first calculates the correlation between the changing trends of temperature gradient and frequency offset. This is achieved by performing a first-order difference on the two parameter sequences to obtain the trend vector. Then, the Pearson correlation coefficient is calculated as the thermoelectric coupling coefficient, reflecting the synchronicity between temperature changes and electromagnetic characteristic changes. Next, the system analyzes the correspondence between contact point temperature and characteristic frequency amplitude, establishing a linear regression model T = k × V + b, where k is the regression slope, i.e., temperature response sensitivity, characterizing the contactor's thermal response capability to electromagnetic changes. Subsequently, the system calculates contact uniformity parameters based on temperature distribution uniformity and spectral energy distribution. A mapping relationship is established between the spatial segmentation of temperature distribution and the frequency band segmentation of spectral energy, and the correlation coefficients between corresponding regions are calculated and averaged. Finally, the system constructs a three-dimensional contact state vector from the thermoelectric coupling coefficient, temperature response sensitivity, and contact uniformity parameters, and performs time-series accumulation calculations on this vector. An exponentially weighted moving average algorithm is used to calculate the contact stability index, with a weight decay factor set to 0.9 to highlight the importance of recent data. The final system combines the contact state vector and contact stability index to form a set of contact performance parameters, which can comprehensively reflect the contactor's contact quality, thermal stability and long-term reliability.

[0047] Based on the above embodiments, as an optional embodiment, the step of determining the contact performance parameter set of the contactor based on the coupling relationship between temperature characteristic parameters and electromagnetic characteristic parameters may further include steps 401-404: Step 401: Calculate the correlation between the temperature gradient and the frequency offset to obtain the thermoelectric coupling coefficient.

[0048] Specifically, to assess the correlation between contactor temperature changes and electromagnetic characteristic changes, the temperature gradient data was first divided into time windows, and the temperature change rate was calculated within each window. Simultaneously, the frequency offset data was divided into the same time windows, and the offset change rate was calculated. Using the Pearson correlation coefficient method, a sliding correlation analysis was performed on the two sets of change rate data. Specifically, the thermoelectric coupling coefficient, reflecting the consistency between temperature and electromagnetic characteristic changes, was obtained by calculating the product of the covariance of the two time series and their respective standard deviations. This coefficient ranges from -1 to 1, with a value closer to 1 indicating a stronger coupling.

[0049] Step 402: Obtain the temperature response sensitivity based on the correspondence between the contact point temperature and the characteristic frequency amplitude.

[0050] Specifically, the contact point temperature data CT(t) and characteristic frequency amplitude data FA(t) are processed synchronously and outlier removal is performed. The 3σ criterion is used to remove data points outside the normal range to ensure data quality. Then, the system establishes a regression analysis model for the contact point temperature and characteristic frequency amplitude, using the least squares method to fit a linear relationship CT = α × FA + β, where α is the regression coefficient (temperature response sensitivity) and β is the intercept term. To improve fitting accuracy, the system employs a robust regression algorithm to reduce the influence of outliers, specifically using the Huber loss function instead of the traditional squared loss function, which is insensitive to outliers. Next, the system calculates the statistical indicators of the regression model, including the correlation coefficient R, the coefficient of determination R², and the standard error SE, to evaluate the fitting quality. When R² is less than 0.8, the linear relationship is considered insignificant, and multinomial regression is used for refitting. Simultaneously, the system performs residual analysis to verify the effectiveness of the regression model, and a scatter plot of the residuals versus the fitted values ​​is used to determine if there is any systematic bias. To enhance the algorithm's adaptability, the system employs a sliding window technique, using 100 data points as the window size to calculate the local temperature response sensitivity. Then, an exponentially weighted moving average is used to obtain the global temperature response sensitivity (TRS), with a weight decay factor set to 0.85. Furthermore, the system also calculates the rate of change of temperature response sensitivity as an auxiliary indicator; an anomaly alarm is triggered when the rate of change exceeds 10%.

[0051] Step 403: Calculate the contact uniformity parameter based on the regional mapping relationship between the temperature distribution uniformity index and the spectral energy distribution.

[0052] Specifically, a mapping relationship is established between the temperature spatial domain and the frequency spectrum domain. The temperature distribution uniformity index is divided into a 3×3 grid area according to spatial location, with each area corresponding to a temperature uniformity value. Simultaneously, the frequency spectrum energy distribution is divided into 9 sub-bands according to frequency bands, establishing a one-to-one correspondence with the 9 temperature distribution areas. Then, the system calculates the correlation between each corresponding area pair. For the i-th area, the correlation coefficient between the temperature uniformity index TU(i) and the corresponding frequency band energy distribution SE(i) is calculated: ri=Cov(TU(i),SE(i)) / [σTU(i)×σSE(i)], where Cov represents the covariance and σ represents the standard deviation. Next, the system performs a comprehensive analysis of the correlation coefficients of the 9 areas, using a weighted average method to calculate the contact uniformity parameter. The weights are determined based on the information entropy of each area; areas with higher information entropy have higher weights. The weight calculation formula is CUP=Σ[Hi×ri] / ΣHi, where Hi is the information entropy of the i-th area.

[0053] Step 404: Construct a contact state vector from the thermoelectric coupling coefficient, temperature response sensitivity, and contact uniformity parameters.

[0054] Specifically, the three parameters are standardized. Since the thermoelectric coupling coefficient (TEC) ranges from -1 to 1, the temperature response sensitivity (TRS) ranges depending on the specific physical unit, and the contact uniformity parameter (CUP) ranges from 0 to 1, the system uses the Z-score standardization method to unify the three parameters to the same numerical range. The standardization formula is X_norm=(X-μ) / σ, where μ is the mean and σ is the standard deviation. Then, the system constructs a three-dimensional contact state vector CSV=[TEC_norm, TRS_norm, CUP_norm], which contains three key dimensions of the contactor's contact performance. To ensure the vector's validity, the system checks the validity of each component. If any component exceeds ±3σ, it is marked as an outlier and interpolated for correction. Next, the system calculates the magnitude and orientation angle of the contact state vector; these geometric features provide additional information about the contact state.

[0055] Step 405: Perform time-series accumulation operation on the contact state vector to obtain the contact stability index, and combine the contact state vector and the contact stability index to form a contact performance parameter set.

[0056] Specifically, to evaluate the stability of the contactor, a cumulative calculation is performed on the contact state vector over a sliding time window. This is achieved by calculating the rate of change of the Euclidean distance for N consecutive state vectors and then performing an exponentially weighted average of these rates to obtain a scalar index characterizing the stability of the contact state. Finally, this stability index is combined with the contact state vectors to form a complete set of contact performance parameters for subsequent quality assessment. This cumulative calculation method effectively reflects the dynamic changing trend of the contactor's performance.

[0057] Step 50: Combine the dynamic characteristic parameter set and the contact performance parameter set to calculate the current contact quality score of the contactor in the current state.

[0058] Specifically, dimensional matching processing is performed on the dynamic characteristic parameter set DTS and the contact performance parameter set CPS. The one-dimensional numerical sequence of the dynamic characteristic parameter set is then statistically analyzed to extract three feature values: mean, variance, and rate of change. , The mean of the numerical sequence of dynamic feature parameters. Standard deviation, The rate of change is related to the contact state vector in the contact performance parameter set. The three components form a corresponding relationship. Then, the system uses a weighted fusion algorithm to calculate the fused feature vector: Where FV is the fused feature vector, w1=0.4 is the dynamic feature weight, and w2 = 0.6 is the contact performance weight. The weights are determined based on the influence of dynamic and static characteristics on contact quality. The system then uses the Contact Stability Index (CSI) as an adjustment factor to calculate the current contact quality score using the following formula: Where QS is the quality score, ||FV|| is the magnitude of the fused feature vector, k = 0.2 is the adjustment coefficient, and CSI is the contact stability index. For ease of understanding and application, the system maps the quality score to a standardized range of 0-100: QS norm For the standardized current contact quality score, QS min and QS max These are the minimum and maximum values ​​of the quality score, respectively.

[0059] Based on the above embodiments, as another optional embodiment, the step of fusing and calculating the dynamic characteristic parameter set and the contact performance parameter set to obtain the current contact quality score of the contactor in the current state may further include steps 501-506: Step 501: Calculate the root mean square value of the features based on the numerical sequence representing the dynamic characteristics of the contactor extracted from the set of dynamic feature parameters.

[0060] Specifically, firstly, a numerical sequence DTS = [d_1, d_2, ..., d_n] representing the dynamic characteristics of the contactor is extracted from the dynamic feature parameter set, where d_i is the i-th dynamic feature value and n is the sequence length. Then, the system preprocesses the numerical sequence, using median filtering to remove outliers. The filtering window size is set to 5 data points, and the filtered sequence is denoted as... Next, the system calculates the root mean square value of the feature, using the following formula: RMS feature d represents the root mean square value of the feature. i Let be the i-th dynamic feature value and n be the sequence length. This calculation method can reflect the overall change range of dynamic features.

[0061] Step 502: Calculate the root mean square value of the performance based on the contact state vector and contact stability index extracted from the contact performance parameter set.

[0062] Specifically, in order to compress multidimensional contact performance information into a single numerical index for easier unified numerical calculation with dynamic features, a contact state vector is extracted from the contact performance parameter set: And the contact stability index (CSI), and calculate the root mean square value of performance: This method unifies multidimensional performance parameters into a single numerical index.

[0063] Step 503: Calculate the phase factor and coupling factor based on the feature root mean square value and the performance root mean square value.

[0064] Specifically, the system calculates the phase factor and coupling factor based on two root mean square values. The formula for calculating the phase factor is: ,in This is the phase factor, ranging from 0 to 1. The coupling factor is calculated using the following formula: ;in This is the coupling factor, reflecting the degree of coordination between the two root mean square values.

[0065] Step 504: Calculate the current contact quality score of the contactor in the current state based on the phase factor and the coupling factor.

[0066] Specifically, the system uses a linear combination method to calculate the current contact quality score: CQS is the current contact quality score, w1 = 0.4 is the phase factor weight, and w2 = 0.6 is the coupling factor weight. This score directly reflects the overall performance status of the contactor and has a value range of 0-100.

[0067] Step 60: Obtain the historical contact quality score corresponding to the contactor under the preset number of on or off conditions before the current state, and determine the fault detection result based on the decay characteristics of the historical contact quality score and the current contact quality score.

[0068] Specifically, extract the historical contact quality score sequence corresponding to the preset number N=50 connection or disconnection operations prior to the current state from the historical database: Then, the system uses an exponential fitting method to analyze the decay characteristics of historical contact quality scores. The fitting model is as follows: Where A is the initial amplitude, Let B be the attenuation coefficient, B be the steady-state value, and t be the number of operations. The system determines the fitting parameters using the least squares method and calculates the goodness-of-fit R^2 to evaluate the effectiveness of the attenuation model. Then, the system compares the current contact quality score (CQS) with the predicted value of the fitted model and calculates the deviation rate. When the deviation rate Furthermore, if the current score is lower than the predicted value, it is judged as abnormal decay; when the decay coefficient If the degradation is detected, it is considered rapid deterioration. Ultimately, the system determines the fault detection result based on the degradation characteristics and the current score, classifying it into three levels: normal, warning, and fault.

[0069] Based on the above embodiments, as another optional embodiment, the step of determining the fault detection result based on the attenuation characteristics of historical contact quality scores and the current contact quality score may further include steps 601-605: Step 601: Extract the periodic variation characteristics of historical contact quality scores to obtain the quality fluctuation sequence.

[0070] Specifically, historical contact quality score data {QON_i} and {QOFF_i} from the last 100 connection and disconnection operations of the contactor were collected, and wavelet transform decomposition was performed on the two sets of data sequences respectively: The Morlet wavelet basis function ψ is used, and the scale parameter a=4 is selected. After decomposition, the on-state quality fluctuation sequence WON(t) and the off-state quality fluctuation sequence WOFF(t) are obtained. For example, the on-state score fluctuates between 80 and 90 points, with a mean of 85 points; the off-state score fluctuates between 90 and 95 points, with a mean of 92 points, but the fluctuation amplitude of the on-state (±5 points) is significantly greater than that of the off-state (±2.5 points).

[0071] Step 602: Calculate the contact performance degradation rate based on the peak-valley difference of the quality fluctuation sequence.

[0072] Specifically, peak and valley values ​​are extracted for WON(t) and WOFF(t) respectively, with threshold conditions set: the time interval between adjacent extreme points is not less than 4 hours, the amplitude difference in the on state is greater than 2 minutes, and the amplitude difference in the off state is greater than 1 minute. Local maxima {PON_i}, {POFF_i} and local minima {VON_i}, {VOFF_i} are extracted, and the peak-valley differences are calculated. Then, the contact performance degradation rate under the two conditions was calculated: Where n is the number of cycles and T is the sampling period (24 hours). For example, after 5 cycles, the on-state decay rate ηON = 0.03 minutes / day and the off-state decay rate ηOFF = 0.01 minutes / day, indicating that the on-state has a greater impact on the contactor performance.

[0073] Step 603: Compare the current contact quality score with the mean of the quality fluctuation sequence to obtain the performance deviation.

[0074] Specifically, calculate the mean of the mass fluctuation sequences for the two states respectively: , The quality score Q for the current connected and disconnected status. ON Q OFF Compare with the corresponding mean to calculate the performance deviation: For example, the current connection score Q ON =82 points, disconnected score Q OFF =94 points, corresponding to the mean μW ON =85 points, μW OFF When the score is 92, the calculated values ​​are δON=0.035 and δOFF=0.022.

[0075] Step 604: Use the product of the contact performance attenuation rate and the performance deviation as the fault warning coefficient.

[0076] Specifically, performance parameters for the connected and disconnected states are obtained separately. For example, when the performance degradation rate ηON = 0.03 minutes / day and the performance deviation δON = 0.035 in the connected state, and the performance degradation rate ηOFF = 0.01 minutes / day and the performance deviation δOFF = 0.022 in the disconnected state, the fault warning coefficients for the two states are calculated respectively: Connectivity Fault Warning Coefficient Disconnection fault warning coefficient Where k=100 is the amplification factor, used to adjust the warning factor to a suitable numerical range. Substituting the values, we get: λON = 0.03 × 0.035 ×100 = 0.105; λOFF = 0.01 × 0.022 × 100 = 0.022.

[0077] Step 605: Generate fault detection results by combining fault early warning coefficients.

[0078] Specifically, in this embodiment, a preset safety threshold λth = 0.05 is set. When the on-state fault warning coefficient λON > λth or the off-state fault warning coefficient λOFF > λth, the system outputs an on-state fault alarm; when the off-state fault warning coefficient λOFF > λth, the system outputs an off-state fault alarm. For states where λOFF < λth or λON < λth, the system initiates the remaining lifetime assessment process for the corresponding state. Taking the off-state as an example (the calculation method for the on-state is the same): the off-state quality fluctuation sequence WOFF(t) is integrated piecewise, with the integration interval [ti, ti+1] set to 4 hours. For example, by segmenting and integrating the fluctuation sequence over a 24-hour period, the performance loss values ​​{Li}={45,42,40,38,36,35} are obtained for six time periods. The numerical values ​​of the performance loss values ​​represent the cumulative performance loss of the contactor within that time period; a larger value indicates more severe performance loss within that period. A feature matrix M is then constructed based on the obtained performance loss values ​​{Li}. OFF : ; where L OFF _i and L OFF _j represents the performance loss in the i-th and j-th time periods, respectively. For example, for the loss sequence {45,42,40,38,36,35}, the constructed 6×6 feature matrix is ​​as follows: The diagonal elements of this feature matrix reflect the autocorrelation characteristics of performance degradation over different time periods. The sum of the diagonal elements is used as the performance degradation benchmark BOFF. Next, assign the current disconnection status quality score Q. OFF =94 Substitute this into the quadratic equation corresponding to the characteristic matrix: The projected distance D in the characteristic matrix space is obtained. OFF =102.5. Based on the performance degradation baseline BOFF and the projected distance DOFF, and then combined with the disconnected state performance degradation rate ηOFF=0.01, the remaining lifetime assessment value is calculated: The remaining lifespan assessment value, which is approximately 258 days, is added to the fault detection results.

[0079] Please see Figure 2 This is a schematic diagram of a module of an intelligent fault diagnosis system for charging piles provided in an embodiment of this application, wherein the system includes: The data acquisition module is used to acquire the current waveform, electromagnetic radiation signal and infrared thermal image data of the contact point of the contactor when the contactor of the charging pile is in the current state of being connected or disconnected. The feature extraction module is used to extract features from the current waveform, infrared thermal image data and electromagnetic radiation signal respectively, to obtain current feature parameters, temperature feature parameters and electromagnetic feature parameters; The feature parameter determination module is used to determine the dynamic feature parameter set of the contactor based on the time-domain correlation between the current feature parameters and the electromagnetic feature parameters; The performance parameter determination module is used to determine the contact performance parameter set of the contactor based on the coupling relationship between the temperature characteristic parameter and the electromagnetic characteristic parameter; The quality score calculation module is used to fuse the dynamic feature parameter set and the contact performance parameter set to obtain the current contact quality score of the contactor in the current state. The detection result generation module is used to obtain the historical contact quality score corresponding to the contactor under the preset number of on or off conditions before the current state, and to determine the fault detection result based on the decay characteristics of the historical contact quality score and the current contact quality score.

[0080] Optionally, the feature extraction module is also used to perform time-frequency domain analysis on the current waveform and extract the current peak value, current rate of change and harmonic components of the current waveform as current feature parameters. Temperature field analysis was performed on the infrared thermal image data to extract contact point temperature, temperature gradient, and temperature distribution uniformity as temperature characteristic parameters. The electromagnetic radiation signal is subjected to spectral analysis to extract characteristic frequency amplitude, spectral energy distribution, and frequency offset as electromagnetic characteristic parameters.

[0081] Optionally, the feature parameter determination module is also used to calculate the time-series ratio of the peak current to the amplitude of the feature frequency to obtain the amplitude matching coefficient; The time delay value is calculated based on the correspondence between the current change rate and the frequency offset; The signal synchronization coefficient is obtained based on the time-domain overlap between the harmonic components of the current waveform and the spectral energy distribution. Based on the amplitude matching coefficient, time delay value, and signal synchronization coefficient, a numerical sequence characterizing the dynamic characteristics of the contactor is generated, and the numerical sequence is used as a set of dynamic characteristic parameters.

[0082] Optionally, the performance parameter determination module is also used to calculate the correlation between the temperature gradient and the frequency offset to obtain the thermoelectric coupling coefficient; The temperature response sensitivity is obtained based on the correspondence between the contact point temperature and the characteristic frequency amplitude. Based on the regional mapping relationship between the temperature distribution uniformity index and the spectral energy distribution, the contact uniformity parameter is calculated; The thermoelectric coupling coefficient, temperature response sensitivity, and contact uniformity parameters are used to construct a contact state vector; A time-series accumulation operation is performed on the contact state vector to obtain a contact stability index, and the contact state vector and the contact stability index are combined to form a contact performance parameter set.

[0083] Optionally, the quality score calculation module is also used to calculate the root mean square value of the features based on the numerical sequence representing the dynamic characteristics of the contactor extracted from the set of dynamic feature parameters. The root mean square value of the performance is calculated based on the contact state vector and contact stability index extracted from the set of contact performance parameters. Based on the root mean square value of the features and the root mean square value of the performance, the phase factor and coupling factor are calculated. The current contact quality score of the contactor in the current state is calculated based on the phase factor and the coupling factor.

[0084] Optionally, the detection result generation module is also used to extract the periodic variation characteristics of the historical contact quality score to obtain a quality fluctuation sequence; The contact performance degradation rate is calculated based on the peak-valley difference of the quality fluctuation sequence. The current contact quality score is compared with the mean of the quality fluctuation sequence to obtain the performance deviation. The product of the contact performance attenuation rate and the performance deviation is used as the fault warning coefficient; The fault detection results are generated by combining the aforementioned fault warning coefficients.

[0085] Optionally, the detection result generation module is also used to output fault alarm information if the fault warning coefficient is greater than a preset safety threshold. If the fault warning coefficient is not greater than the preset safety threshold, then the quality fluctuation sequence is subjected to segmented integration to obtain the performance loss in each time period. A feature matrix is ​​constructed based on the performance loss, and the sum of the diagonal elements of the feature matrix is ​​calculated as the performance degradation benchmark. The remaining life assessment value of the contactor is calculated based on the projection distance of the current contact quality score in the feature matrix and combined with the performance degradation benchmark, and then added to the fault detection result.

[0086] It should be noted that the system provided in the above embodiments is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0087] This application also provides a computer storage medium that can store multiple instructions. The instructions are adapted to be loaded and executed by a processor as described in the above embodiment of an intelligent fault diagnosis method for charging piles. For the specific execution process, please refer to the detailed description of the above embodiment, which will not be repeated here.

[0088] Please refer to Figure 3 This application also discloses an electronic device. Figure 3 This is a schematic diagram of the structure of an electronic device disclosed in an embodiment of this application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0089] The communication bus 302 is used to enable communication between these components.

[0090] The user interface 303 may include a display screen and a camera. Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0091] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0092] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 305, and by calling data stored in memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 301 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.

[0093] The memory 305 may include random access memory (RAM) or read-only memory. Optionally, the memory 305 may include a non-transitory computer-readable storage medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. (Refer to...) Figure 3 The memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for an intelligent fault diagnosis method for charging piles.

[0094] exist Figure 3In the illustrated electronic device 300, the user interface 303 is mainly used to provide an input interface for the user and acquire user input data; while the processor 301 can be used to call an application program stored in the memory 305 for intelligent diagnosis of charging pile faults. When executed by one or more processors 301, the electronic device 300 performs one or more methods as described in the above embodiments. It should be noted that, for the foregoing method embodiments, for the sake of simplicity, they are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0095] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0096] In the various embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.

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

[0098] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0099] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0100] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will readily conceive of those skilled in the art upon consideration of the specification and the disclosure of practical truths.

[0101] This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described in this disclosure. The specification and embodiments are to be regarded as exemplary only.

Claims

1. A method for intelligent diagnosis of charging pile failure, characterized in that, The method comprises: In the current state of the contactor of the charging pile being turned on or turned off, acquiring current waveform, electromagnetic radiation signal generated by the contactor and infrared thermal image data of the contact point of the contactor; Respectively extracting features of the current waveform, infrared thermal image data and electromagnetic radiation signal to obtain current characteristic parameters, temperature characteristic parameters and electromagnetic characteristic parameters; Based on the time domain correlation between the current characteristic parameters and the electromagnetic characteristic parameters, determining a dynamic characteristic parameter set of the contactor; Based on the coupling relationship between the temperature characteristic parameters and the electromagnetic characteristic parameters, determining a contact performance parameter set of the contactor; Fusion calculation of the dynamic characteristic parameter set and the contact performance parameter set to obtain a current contact quality score of the contactor in the current state; Acquiring historical contact quality scores corresponding to the turning on or turning off of the contactor a preset number of times before the current state, and determining a fault detection result according to the attenuation characteristics of the historical contact quality scores and the current contact quality score. 2.The method of claim 1, wherein, The respective feature extraction of the current waveform, infrared thermal image data and electromagnetic radiation signal to obtain current characteristic parameters, temperature characteristic parameters and electromagnetic characteristic parameters comprises: Time-frequency domain analysis of the current waveform to extract current peak value, current change rate and harmonic component of the current waveform as current characteristic parameters; Temperature field analysis of the infrared thermal image data to extract contact point temperature, temperature gradient and temperature distribution uniformity index as temperature characteristic parameters; Frequency spectrum analysis of the electromagnetic radiation signal to extract characteristic frequency amplitude, frequency spectrum energy distribution and frequency offset as electromagnetic characteristic parameters. 3.The method of claim 2, wherein, The determination of the dynamic characteristic parameter set of the contactor based on the time domain correlation between the current characteristic parameters and the electromagnetic characteristic parameters comprises: Calculating the time sequence ratio of the current peak value and the characteristic frequency amplitude to obtain an amplitude matching coefficient; According to the corresponding relationship between the current change rate and the frequency offset, calculating a time delay value; Based on the time domain overlap degree of the harmonic component of the current waveform and the frequency spectrum energy distribution, a signal synchronization coefficient is obtained; According to the amplitude matching coefficient, time delay value and signal synchronization coefficient, a numerical sequence representing the dynamic characteristics of the contactor is generated, and the numerical sequence is taken as the dynamic characteristic parameter set.

4. The method of claim 2, wherein, The determination of the contact performance parameter set of the contactor based on the coupling relationship between the temperature characteristic parameters and the electromagnetic characteristic parameters comprises: Calculating the correlation degree of the change trend of the temperature gradient and the frequency offset to obtain a thermoelectric coupling coefficient; According to the corresponding relationship between the contact point temperature and the characteristic frequency amplitude, a temperature response sensitivity is obtained; Based on the regional mapping relationship between the temperature distribution uniformity index and the frequency spectrum energy distribution, a contact uniformity parameter is calculated; The thermoelectric coupling coefficient, temperature response sensitivity and contact uniformity parameter are constructed into a contact state vector; Time sequence accumulation operation is performed on the contact state vector to obtain a contact stability index, and the contact state vector and the contact stability index are combined to form the contact performance parameter set.

5. The method of claim 1, wherein, The fusion calculation of the dynamic characteristic parameter set and the contact performance parameter set obtains a current contact quality score of the contactor in the current state, including: A feature mean square root value is calculated based on a numerical sequence representing the dynamic characteristics of the contactor extracted from the dynamic characteristic parameter set; A performance mean square root value is calculated based on a contact state vector and a contact stability index extracted from the contact performance parameter set; A phase factor and a coupling factor are calculated based on the feature mean square root value and the performance mean square root value; The current contact quality score of the contactor in the current state is calculated according to the phase factor and the coupling factor.

6. The method of claim 1, wherein, The determination of the fault detection result according to the attenuation characteristics of the historical contact quality score and the current contact quality score includes: Periodic variation characteristics of the historical contact quality score are extracted to obtain a quality fluctuation sequence; A contact performance attenuation rate is calculated based on the peak-valley value difference of the quality fluctuation sequence; A performance deviation degree is obtained by comparing the current contact quality score with the mean value of the quality fluctuation sequence; A fault warning coefficient is obtained according to the product of the contact performance attenuation rate and the performance deviation degree; The fault detection result is generated in combination with the fault warning coefficient.

7. The method according to claim 6, characterized in that, The generation of the fault detection result in combination with the fault warning coefficient includes: If the fault warning coefficient is greater than a preset safety threshold, fault alarm information is output; If the fault warning coefficient is not greater than the preset safety threshold, segmented integral operation is performed on the quality fluctuation sequence to obtain the performance loss amount of each time period; A feature matrix is constructed based on the performance loss amount, and the sum of the diagonal elements of the feature matrix is calculated as a performance attenuation reference; The remaining life evaluation value of the contactor is calculated according to the projection distance of the current contact quality score in the feature matrix in combination with the performance attenuation reference, and the remaining life evaluation value is added to the fault detection result.

8. A charging pile fault intelligent diagnosis system, characterized in that, The system includes: A data acquisition module is configured to acquire current waveform, electromagnetic radiation signal and infrared thermal image data of a contactor in a current state in which the contactor is turned on or turned off; A feature extraction module is configured to extract current feature parameters, temperature feature parameters and electromagnetic feature parameters from the current waveform, infrared thermal image data and electromagnetic radiation signal respectively; A feature parameter determination module is configured to determine a dynamic characteristic parameter set of the contactor based on the time domain correlation between the current feature parameters and the electromagnetic feature parameters; A performance parameter determination module is configured to determine a contact performance parameter set of the contactor based on the coupling relationship between the temperature feature parameters and the electromagnetic feature parameters; A quality score calculation module is configured to perform fusion calculation on the dynamic characteristic parameter set and the contact performance parameter set to obtain a current contact quality score of the contactor in the current state. The detection result generation module is configured to acquire a historical contact quality score corresponding to a preset number of on or off states of the contactor before the current state, and determine a fault detection result according to an attenuation characteristic of the historical contact quality score and the current contact quality score.

9. A computer-readable storage medium, characterized in that, A computer readable storage medium stores a plurality of instructions, the instructions being adapted to be loaded and executed by a processor to perform the method of any one of claims 1-7.

10. An electronic device, comprising: An electronic device includes a processor, a memory, a user interface, and a network interface, the memory is configured to store instructions, the user interface and the network interface are configured to communicate with other devices, and the processor is configured to execute the instructions stored in the memory to cause the electronic device to perform the method of any one of claims 1-7.

Images