A performance automation analysis method and system based on low-voltage power capacitors

Abstract

The present invention relates to the field of power automation technology, and discloses a method and system for automated performance analysis based on low-voltage power capacitors, comprising: performing signal conversion on operating data to obtain an operating signal, and extracting multimodal features of the operating signal; monitoring the power factor of the low-voltage power capacitor based on the multimodal features, and determining the power quality of the low-voltage power capacitor based on the power factor index; calculating the failure probability of the low-voltage power capacitor based on the multimodal features, and calculating the life index of the low-voltage power capacitor based on the operating data; generating a performance visualization cloud map based on the power factor, power quality, failure probability, and life index, and calculating the performance membership of the performance visualization cloud map; calculating the performance value of the low-voltage power capacitor based on the performance membership and performance weight, and determining the performance of the low-voltage power capacitor based on the performance value and performance threshold. The present invention can improve the accuracy of automated performance analysis of low-voltage power capacitors.

Description

Technical Field

[0001] The present invention relates to the field of power automation technology, and in particular to a performance automation analysis method and system based on low-voltage power capacitors. Background Art

[0002] With the widespread application of modern electrical equipment, low-voltage power capacitors have also been continuously improved and applied. However, potential problems may arise in low-voltage power capacitors, such as voltage fluctuations and current harmonics, which affect the power quality. Therefore, it is necessary to analyze the performance indicators of low-voltage power capacitors in order to improve the power quality of low-voltage power capacitors.

[0003] Existing automated performance analysis technology for low-voltage power capacitors uses automated test scripts to test various performance indicators of low-voltage power capacitors one by one. In practice, these automated test scripts fail to fully test all performance indicators, often missing performance indicators. This can lead to incomplete performance testing and low accuracy in automated performance analysis of low-voltage power capacitors. Summary of the Invention

[0004] The present invention provides a method and system for automated performance analysis of low-voltage power capacitors, the main purpose of which is to solve the problem of low accuracy in automated performance analysis of low-voltage power capacitors.

[0005] To achieve the above objectives, the present invention provides a method for automated performance analysis of low-voltage power capacitors, comprising:

[0006] S1. Real-time collection of operating data of a low-voltage power capacitor, signal conversion of the operating data using a preset signal conversion algorithm to obtain an operating signal, and extraction of multimodal features of the operating signal using a preset multimodal feature algorithm;

[0007] S2. Monitoring the power factor of the low-voltage power capacitor according to the multimodal characteristics through a preset automation factor mode, and determining the power quality of the low-voltage power capacitor according to the power factor index;

[0008] S3. Calculate the failure probability of the low-voltage power capacitor according to the multimodal features using a preset pattern matching algorithm, and calculate the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model;

[0009] S4. Generate a performance visualization cloud map of the low-voltage power capacitor according to the power factor, the power quality, the failure probability, and the life index, and calculate the performance membership of the performance visualization cloud map using a preset membership algorithm;

[0010] S5. Calculating a performance value of the low-voltage power capacitor according to the performance membership and a preset performance weight, and determining the performance of the low-voltage power capacitor according to the performance value and a preset performance threshold, wherein calculating the performance value of the low-voltage power capacitor according to the performance membership and the preset performance weight includes:

[0011] S51. Determine the performance level of the low-voltage power capacitor according to the performance weight;

[0012] S52, quantifying the performance level to obtain a performance quantization level;

[0013] S53. Calculate the performance value of the low-voltage power capacitor according to the performance quantification level and the performance membership using the following performance value calculation formula:

[0014]

[0015] Wherein, ψ is the performance value, δ is the performance quantization level, μ r is the membership degree of the rth performance indicator, T is the number of performance indicators, and ln is the logarithmic function.

[0016] Optionally, performing signal conversion on the operating data using a preset signal conversion algorithm to obtain an operating signal includes:

[0017] Converting the operation data into operation series data according to a preset time interval;

[0018] The running time series data is converted into running frequency domain data using a preset signal conversion algorithm, wherein the signal conversion algorithm is:

[0019] F(w)=∫[f(t)×e -wt ]dt

[0020] Wherein, F(w) is the operating frequency domain data, f(t) is the operating time series data at time t, e is a constant, w is the angular frequency, and dt is the differential with respect to t;

[0021] Perform signal component analysis on the operating frequency domain data to obtain an operating frequency domain component;

[0022] The operation signal is generated according to the operation frequency domain component.

[0023] Optionally, the extracting the multimodal features of the operating signal by using a preset multimodal feature algorithm includes:

[0024] The instantaneous energy mean of the operating signal is calculated using the instantaneous energy mean calculation formula in the multimodal feature algorithm:

[0025]

[0026] Among them, A k is the instantaneous energy mean of the k-th running signal, is the amplitude of the kth component in the i-th running signal, n is the number of sampling points, and m is the number of components;

[0027] The harmonic component of the operating signal is calculated using the signal harmonic component calculation formula in the multimodal feature algorithm:

[0028]

[0029] Wherein, B is the harmonic signal value in the harmonic component, p u is the frequency of the u-th harmonic in the harmonic component, D is the amplitude, π is the circumference, g is the frequency, t is the signal time, is the phase, U is a constant, and p0 is the fundamental frequency;

[0030] The instantaneous energy mean and the harmonic component are subjected to feature fusion to obtain the multimodal features of the operating signal.

[0031] Optionally, monitoring the power factor of the low-voltage power capacitor according to the multimodal feature using a preset automation factor mode includes:

[0032] Extracting instantaneous energy mean and harmonic components in the multimodal features in real time according to a preset timestamp through the automated factor mode;

[0033] Extracting the current signal phase and the voltage signal phase in the multimodal feature according to the instantaneous energy mean and the harmonic component;

[0034] Determining the useful power and useless power of the low-voltage power capacitor according to the phase difference between the current signal phase and the voltage signal phase;

[0035] The power factor of the low-voltage power capacitor is calculated according to the useful power and the useless power.

[0036] Optionally, determining the power quality of the low-voltage power capacitor according to the power factor index includes:

[0037] determining a power factor level according to the power factor and a preset power factor threshold;

[0038] determining the power loss of the low-voltage power capacitor according to the power factor level;

[0039] The power quality of the low-voltage power capacitor is determined based on the power loss.

[0040] Optionally, the calculating the failure probability of the low-voltage power capacitor according to the multimodal features using a preset pattern matching algorithm includes:

[0041] Extracting key features from the multimodal features based on preset fault correlation features;

[0042] The key features are pattern matched with preset fault rules using the pattern matching algorithm to obtain a pattern matching logic value, wherein the pattern matching algorithm is:

[0043] M=(X v ≥X vmin )V(X v ≤X vmax )

[0044] Wherein, M is the pattern matching logic value, X v is the eigenvalue of the vth feature in the key feature, X vmin is the minimum value of the vth feature in the fault rule, X vmax is the maximum value of the feature of the vth feature in the fault rule;

[0045] The failure probability of the low-voltage power capacitor is calculated according to the pattern matching logic value and the preset fault association number, wherein the failure probability calculation formula is:

[0046]

[0047] Wherein, h is the fault probability, L is the number of first identifiers in the pattern matching logic value, and Z is the number of fault associations.

[0048] Optionally, the calculating the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model includes:

[0049] Extracting life characteristics from the operating data according to a preset sliding window;

[0050] The life characteristic time sequence of the low-voltage power capacitor is calculated according to the life characteristic using the time sequence cycle life model, wherein the time sequence cycle life model is:

[0051]

[0052] in, is the life characteristic of the ∈th step at time t, is the life characteristic of the ∈-pth step at time t, is the autoregressive coefficient of the pth model;

[0053] The life index of the low-voltage power capacitor is determined according to the life characteristic time sequence and a preset life threshold.

[0054] Optionally, generating a performance visualization cloud map of the low-voltage power capacitor according to the power factor, the power quality, the failure probability, and the life index includes:

[0055] Color-coding the power factors to obtain power factor differentiation, and generating a power visualization cloud map of the power factors according to the power factor differentiation;

[0056] Performing shape coding on the power quality to obtain a power quality discrimination degree, and generating a quality visualization cloud map of the power quality according to the power quality discrimination degree;

[0057] Density encoding is performed on the fault probability to obtain a fault discrimination degree, and a fault visualization cloud map of the fault probability is generated according to the fault discrimination degree;

[0058] Performing line coding on the life indicators to obtain a life indicator discrimination degree, and generating a life visualization cloud map of the life indicators according to the life indicator discrimination degree;

[0059] The power visualization cloud map, the quality visualization cloud map, the fault visualization cloud map and the life visualization cloud map are aggregated into a performance visualization cloud map of the low-voltage power capacitor.

[0060] Optionally, the calculating the performance membership of the performance visualization cloud graph by using a preset membership algorithm includes:

[0061] The membership degree of the performance indicators in the performance visualization cloud graph is calculated one by one using the membership degree algorithm, wherein the membership degree algorithm is:

[0062]

[0063] Among them, μ r is the membership degree of the rth performance index, e is a constant, S r is the performance value of the rth performance indicator, E is the Gaussian membership mean, and y is the Gaussian membership variance;

[0064] The memberships are superimposed to obtain the performance membership of the performance visualization cloud map.

[0065] In order to solve the above problems, the present invention also provides a performance automation analysis system based on low-voltage power capacitors, the system comprising:

[0066] A multimodal feature extraction module is used to collect operating data of a low-voltage power capacitor in real time, perform signal conversion on the operating data using a preset signal conversion algorithm to obtain an operating signal, and extract multimodal features of the operating signal using a preset multimodal feature algorithm;

[0067] A power factor monitoring module, configured to monitor the power factor of the low-voltage power capacitor according to the multimodal characteristics through a preset automation factor mode, and determine the power quality of the low-voltage power capacitor according to the power factor index;

[0068] A life index calculation module, configured to calculate the failure probability of the low-voltage power capacitor according to the multimodal characteristics using a preset pattern matching algorithm, and calculate the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model;

[0069] A performance membership calculation module is used to generate a performance visualization cloud map of the low-voltage power capacitor based on the power factor, the power quality, the failure probability and the life index, and calculate the performance membership of the performance visualization cloud map using a preset membership algorithm;

[0070] The performance analysis module is used to calculate the performance value of the low-voltage power capacitor according to the performance membership and the preset performance weight, and determine the performance of the low-voltage power capacitor according to the performance value and the preset performance threshold.

[0071] The embodiment of the present invention extracts multimodal features of the operating data of the low-voltage power capacitor to reveal information from different aspects of the signal to obtain more comprehensive and accurate information; monitors the power factor of the low-voltage power capacitor according to the multimodal features, and then determines the power quality of the low-voltage power capacitor based on the power factor, which is conducive to accurate analysis of power utilization efficiency, line loss and potential problems to ensure the stability and quality of power supply; calculates the failure probability and life index of the low-voltage power capacitor according to the multimodal features, which is conducive to analyzing the multi-dimensional performance of the low-voltage power capacitor and improving the accuracy of performance analysis; generates a performance visualization cloud map of the power factor, power quality, failure probability and life index, and presents it in a visual manner, which can more comprehensively evaluate the performance of the capacitor; calculates the performance value of the low-voltage power capacitor through the performance membership and performance weight of the performance visualization cloud map, and then analyzes the performance of the low-voltage power capacitor based on the performance value, so that according to the feedback of the performance value, targeted optimization and improvement can be carried out to improve the overall performance of the low-voltage power capacitor and assist in the decision-making process. Therefore, the method and system for automated performance analysis based on low-voltage power capacitors proposed in the present invention can solve the problem of low accuracy when performing automated performance analysis of low-voltage power capacitors. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A schematic diagram of a flow chart of a method for automated performance analysis of low-voltage power capacitors provided in one embodiment of the present invention;

[0073] Figure 2 A schematic diagram of a process for monitoring power factor according to an embodiment of the present invention;

[0074] Figure 3 A schematic diagram of a process for calculating a failure probability according to an embodiment of the present invention;

[0075] Figure 4 This is a functional module diagram of an automated performance analysis system based on low-voltage power capacitors provided by one embodiment of the present invention.

[0076] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0077] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0078] The embodiment of the present application provides a method for automated performance analysis based on low-voltage power capacitors. The execution subject of the method for automated performance analysis based on low-voltage power capacitors includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for automated performance analysis based on low-voltage power capacitors can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0079] Reference Figure 1 FIG. 1 is a flow chart of a method for automatically analyzing the performance of a low-voltage power capacitor according to an embodiment of the present invention. In this embodiment, the method for automatically analyzing the performance of a low-voltage power capacitor includes:

[0080] S1. Collect operating data of a low-voltage power capacitor in real time, perform signal conversion on the operating data using a preset signal conversion algorithm to obtain an operating signal, and extract multimodal features of the operating signal using a preset multimodal feature algorithm.

[0081] In an embodiment of the present invention, the operating data includes the current, voltage, power, etc. of the low-voltage power capacitor, wherein corresponding sensor equipment can be selected to collect the operating data of the low-voltage power capacitor in real time, such as a current sensor, a voltage sensor, etc.

[0082] Furthermore, in order to improve the information content and usability of the operating data and help to deeply understand the operating status of the low-voltage power capacitor, the operating data needs to be converted into operating signals for analysis.

[0083] In the embodiment of the present invention, the operation signal is a signal obtained by converting the current, voltage, power and the like in the operation data, and represents the real-time operation status of the low-voltage power capacitor.

[0084] In the embodiment of the present invention, the step of converting the operating data into a signal using a preset signal conversion algorithm to obtain an operating signal includes:

[0085] Converting the operation data into operation series data according to a preset time interval;

[0086] The running time series data is converted into running frequency domain data using a preset signal conversion algorithm, wherein the signal conversion algorithm is:

[0087] F(w)=∫[f(t)×e -wt ]dt

[0088] Wherein, F(w) is the operating frequency domain data, f(t) is the operating time series data at time t, e is a constant, w is the angular frequency, and dt is the differential with respect to t;

[0089] Perform signal component analysis on the operating frequency domain data to obtain an operating frequency domain component;

[0090] The operation signal is generated according to the operation frequency domain component.

[0091] In detail, the running time of the preset time interval is counted to obtain the running sequence time. For example, within the preset time interval, the real-time change state of the current and the real-time change state of the voltage are counted to obtain the running sequence data of the voltage and current, and then the running sequence data is converted into frequency domain data represented in the frequency domain through the signal conversion algorithm.

[0092] Specifically, the signal conversion algorithm is based on the Fourier transform, which converts a function (represented in the time domain) into its spectrum representation (represented in the frequency domain). Through the Fourier transform, the spectral characteristics of a signal can be analyzed to understand the frequency components and their amplitudes contained in the signal. The Fourier transform can represent a signal in the continuous time domain as a spectrum in the continuous frequency domain, or a signal in the discrete time domain as a spectrum in the discrete frequency domain. The converted operating frequency domain data is then subjected to signal component analysis to obtain spectral components, and the spectral components corresponding to the operating characteristics of different operating data are then determined as operating signals.

[0093] Furthermore, the operating status, fault characteristics, performance indicators, etc. of the low-voltage power capacitor can be analyzed based on the operating signal. Therefore, it is necessary to extract the operating characteristics in the operating signal to realize the analysis of the performance indicators of the low-voltage power capacitor.

[0094] In an embodiment of the present invention, the multimodal features are multiple types of feature information corresponding to the operating signal, which can be selected according to the nature of the signal and different application requirements to reveal information of different aspects of the signal to obtain more comprehensive and accurate information.

[0095] In an embodiment of the present invention, extracting the multimodal features of the operating signal using a preset multimodal feature algorithm includes:

[0096] The instantaneous energy mean of the operating signal is calculated using the instantaneous energy mean calculation formula in the multimodal feature algorithm:

[0097]

[0098] Among them, A k is the instantaneous energy mean of the k-th running signal, is the amplitude of the kth component in the i-th running signal, n is the number of sampling points, and m is the number of components;

[0099] The harmonic component of the operating signal is calculated using the signal harmonic component calculation formula in the multimodal feature algorithm:

[0100]

[0101] Wherein, B is the harmonic signal value in the harmonic component, p u is the frequency of the u-th harmonic in the harmonic component, D is the amplitude, π is the circumference, g is the frequency, t is the signal time, is the phase, U is a constant, and p0 is the fundamental frequency;

[0102] The instantaneous energy mean and the harmonic component are subjected to feature fusion to obtain the multimodal features of the operating signal.

[0103] Specifically, the instantaneous energy mean reflects the temporal variation of the operating signal and can reflect changes in the signal in the time domain. The instantaneous energy mean then performs Hilbert spectrum analysis on each component of the decomposed operating signal, obtaining information in the frequency domain and changes in its amplitude, thereby calculating the instantaneous energy of each channel's sampled signal. By reflecting the time-domain variations of the operating signal through the instantaneous energy mean, it is also necessary to reflect the operating waveform of the operating signal. This allows for analysis of the power quality of low-voltage power capacitors based on the operating waveform to ensure capacitor stability and operational efficiency.

[0104] Specifically, the harmonic components include the frequency, phase, and amplitude of the operating signal. Harmonics are periodic fluctuations relative to the fundamental wave, and their frequencies are integer multiples of the fundamental wave frequency. In signal processing, harmonic analysis is often used to analyze the frequency components and harmonic content of a signal. By performing spectral analysis on the signal, a spectrum diagram of the signal can be obtained, which intuitively displays the intensity and relative proportion of each frequency component in the signal. The harmonic components can be distinguished from the spectrum diagram, and their frequency, phase, and amplitude can be calculated. Therefore, the frequency and harmonic signal values of the operating signal need to be calculated according to the signal harmonic component calculation formula.

[0105] Furthermore, the instantaneous energy mean A k And the harmonic components {B,p u} Perform feature fusion to obtain the multimodal features of the running signal {A k ,B,p u}, therefore, fusing multimodal features can provide more comprehensive and accurate information and have better performance.

[0106] Furthermore, the performance indicators of the power capacitor can be monitored based on the multimodal characteristics, so that the performance of the power capacitor can be automatically evaluated more accurately.

[0107] S2. Monitor the power factor of the low-voltage power capacitor according to the multimodal characteristics through a preset automation factor mode, and determine the power quality of the low-voltage power capacitor according to the power factor index.

[0108] In the embodiment of the present invention, the power factor is used to describe the relationship between active power and apparent power in an active circuit, indicating how much power in the AC circuit is effectively utilized to do effective work rather than being wasted. A good power factor means that more electrical energy is converted into useful power, reducing reactive power loss and improving the energy efficiency of the circuit.

[0109] In the embodiment of the present invention, referring to Figure 2As shown, the power factor of the low-voltage power capacitor is monitored according to the multimodal characteristics through a preset automatic factor mode, including:

[0110] S21, extracting the instantaneous energy mean and harmonic components in the multimodal features in real time according to a preset timestamp using the automated factor mode;

[0111] S22. Extracting the current signal phase and the voltage signal phase in the multimodal feature according to the instantaneous energy mean and the harmonic component;

[0112] S23, determining the useful power and useless power of the low-voltage power capacitor according to the phase difference between the current signal phase and the voltage signal phase;

[0113] S24. Calculate the power factor of the low-voltage power capacitor according to the useful power and the useless power.

[0114] In detail, the automation factor mode is a self-set custom script, which is used to execute the custom script to monitor the data operation data of the power capacitor in real time according to different timestamps, so as to obtain the instantaneous energy mean and harmonic components in the multimodal characteristics, and determine the change characteristics of the current signal and voltage signal within the time series range according to the instantaneous energy mean, thereby determining the current signal phase and voltage signal phase according to the signal values of the voltage signal and current signal in the harmonic components.

[0115] Specifically, due to the influence of inductance and capacitance in the AC circuit, there may be a phase difference between the waveforms of current and voltage, which in turn generates reactive power, resulting in a power factor less than 1. When the current and voltage waveforms are completely in phase, the power factor reaches a maximum value of 1, indicating that all the power in the circuit is useful work. The power factor is usually expressed in scalar or angle form. In scalar form, the power factor ranges from 0 to 1. The closer to 1, the higher the power factor, that is, the more power is effectively utilized; in angle form, the power factor is represented by the cosine value of the phase difference between active power and reactive power. When the power factor is 1, the phase difference is 0 degrees; when the power factor is less than 1, the phase difference is greater than 0 degrees, indicating the presence of reactive power. Therefore, the useful power and useless power of the low-voltage power capacitor can be determined based on the phase difference between the current signal phase and the voltage signal phase, and the power factor can be obtained by dividing the useful power by the useless power.

[0116] Furthermore, power factor is one of the important indicators for measuring power quality. It represents the ratio of active power to apparent power in a circuit. The power quality of low-voltage power capacitors can be determined based on the power factor.

[0117] In the embodiment of the present invention, the power quality refers to the characteristics of the stability and reliability of electric energy in the power system, which is used to describe the ability of the power supply system to meet user needs and provide the required electric energy. High-quality power quality will ensure the stability of power supply, the reliability of working equipment, and protect user equipment from the impact of power system anomalies and interference.

[0118] In an embodiment of the present invention, determining the power quality of the low-voltage power capacitor according to the power factor index includes:

[0119] determining a power factor level according to the power factor and a preset power factor threshold;

[0120] determining the power loss of the low-voltage power capacitor according to the power factor level;

[0121] The power quality of the low-voltage power capacitor is determined based on the power loss.

[0122] In detail, the power factor levels are divided into low power factor, high power factor and ultra-high power factor; when the power factor is close to 0, it means that the reactive power in the circuit is high and the active power is low, which means that the loss of electric energy in transmission is large and the efficiency of the circuit is low. Low power factor may indicate potential power quality problems, such as energy waste, line overload, etc.; when the power factor is close to 1, it means that the active power in the circuit is high and the reactive power is low, which means that the loss of electric energy in transmission is small and the efficiency of the circuit is high. High power factor is generally considered to be one of the characteristics of good power quality; when the power factor exceeds 1, it may indicate that there is a harmonic pollution problem in the circuit. In some cases, ultra-high power factor may cause line overload, equipment damage and other problems, affecting power quality.

[0123] Specifically, when evaluating the power quality of low-voltage power capacitors, it is important to pay attention to the power factor. Properly controlling and maintaining the power factor can improve power utilization efficiency, reduce line losses and potential problems, and ensure the stability and quality of power supply.

[0124] Furthermore, the performance evaluation of low-voltage power capacitors requires not only the evaluation of power quality, but also the evaluation of the failure probability and life indicators of low-voltage power capacitors, so as to achieve a multi-faceted evaluation of power capacitors and improve the accuracy of performance evaluation.

[0125] S3. Calculate the failure probability of the low-voltage power capacitor according to the multimodal features using a preset pattern matching algorithm, and calculate the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model.

[0126] In the embodiment of the present invention, the failure probability refers to the probability that a low-voltage power capacitor may fail.

[0127] In the embodiment of the present invention, referring to Figure 3 As shown, the method of calculating the failure probability of the low-voltage power capacitor according to the multimodal features using a preset pattern matching algorithm includes:

[0128] S31, extracting key features from the multimodal features based on preset fault-related features;

[0129] S32. Perform pattern matching on the key features and preset fault rules using the pattern matching algorithm to obtain a pattern matching logic value, wherein the pattern matching algorithm is:

[0130] M=(X v ≥X vmin )V(X v ≤X vmax )

[0131] Wherein, M is the pattern matching logic value, X v is the eigenvalue of the vth feature in the key feature, X vmin is the minimum value of the vth feature in the fault rule, X vmax is the maximum value of the feature of the vth feature in the fault rule;

[0132] S33. Calculate the failure probability of the low-voltage power capacitor according to the pattern matching logic value and the preset fault association number, wherein the failure probability calculation formula is:

[0133]

[0134] Wherein, h is the fault probability, L is the number of first identifiers in the pattern matching logic value, and Z is the number of fault associations.

[0135] In detail, the fault-related characteristics refer to characteristics that can affect the occurrence of faults in low-voltage power capacitors, such as voltage, current, etc., and then the characteristics in the multimodal characteristics are filtered according to the fault-related characteristics to filter out the characteristics that can more prominently highlight the fault, and obtain key characteristics, such as current, voltage, etc., which is conducive to more accurate and efficient fault identification of low-voltage power capacitors.

[0136] Specifically, the selected key features are matched with the conditional part in the rule set through a pattern matching algorithm, and the matching process can use logical operators to combine multiple conditions. If the conditional part of a rule successfully matches the feature, the corresponding fault type is given according to the conclusion part of the rule; if multiple rules are successfully matched, the priority, confidence or other rule selection strategies can be used to determine the final fault type, and then the key features are compared with the feature values with the same features in the rule set to obtain a pattern matching logic value, wherein the pattern matching logic value includes 1 and 0. When the pattern matching logic value is 1, it indicates a successful match; when the pattern matching logic value is 0, it indicates a failed match. Then, the failure probability of the low-voltage power capacitor is calculated based on the pattern matching logic value and the preset fault association number, and the number L of the first identifier refers to the number of pattern matching logic values with a value of 1.

[0137] For example, the key features are {a, b, c, d}, and the fault feature value in the fault rule is {[a min ,a max ],[b min ,b max ],[c min ,c max ],[d min ,d max ]}, the characteristic values in the key characteristics are compared with the fault characteristics one by one. If the characteristic value is within the fault range of the fault characteristic value, the pattern matching logic value is set to 0; if the characteristic value is not within the fault range of the fault characteristic value, the pattern matching logic value is set to 1. If the pattern matching logic value is {1, 1, 0, 0}, the number of logic values 1 in the pattern matching logic value is compared with the total number of fault associations to obtain the fault probability of 2 / 4.

[0138] Furthermore, to evaluate the performance of power capacitors, it is also necessary to analyze the life indicators of low-voltage power capacitors so that a customized management plan can be formulated based on the life indicators. For capacitors that are about to fail or age, maintenance or replacement can be given priority, while for capacitors whose lifespan can still be extended, regular inspection and maintenance can be carried out to ensure their normal operation.

[0139] In an embodiment of the present invention, the time series cycle life model is generated based on LSTM training. LSTM (Long Short-Term Memory Network) is a recurrent neural network (RNN) model suitable for modeling sequence data. It can be used to process data with a time series relationship in machine life prediction. The extracted feature data is serialized so that it can be trained and predicted using the LSTM model, and the serialized feature data is input into the LSTM model for training. The goal of the LSTM model is to learn the underlying patterns and relationships in the input sequence. For life prediction, the life can be used as the target value and trained using a supervised learning method to obtain a time series cycle life model that can evaluate the life indicators of low-voltage power capacitors.

[0140] In an embodiment of the present invention, the calculating of the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model includes:

[0141] Extracting life characteristics from the operating data according to a preset sliding window;

[0142] The life characteristic time sequence of the low-voltage power capacitor is calculated according to the life characteristic using the time sequence cycle life model, wherein the time sequence cycle life model is:

[0143]

[0144] in, is the life characteristic of the ∈th step at time t, is the life characteristic of the ∈-pth step at time t, is the autoregressive coefficient of the pth model;

[0145] The life index of the low-voltage power capacitor is determined according to the life characteristic time sequence and a preset life threshold.

[0146] In detail, the life characteristics are factors that can affect the life of low-voltage power capacitors, including voltage, current, temperature, frequency, operating time, number of cycles, etc. The life characteristics under a sliding window are extracted according to a preset sliding window, thereby forming a life data sequence corresponding to multiple life characteristics, which can more accurately evaluate the life of low-voltage power capacitors.

[0147] Specifically, according to the time series formula in the time series cycle life model, the life characteristic time series of the next moment can be predicted based on the life characteristics, such as predicting the characteristic value of the life characteristic of the next moment based on the voltage, current, temperature, etc. in the life characteristics, thereby obtaining the life characteristic time series, and then comparing the life characteristic time series with the preset life threshold to obtain the life stage of the low-voltage power capacitor, wherein the life stage includes the normal period, the degradation period and the failure period. If the characteristic value in the life characteristic time series is compared with the alarm threshold in the preset life threshold, when it is less than the alarm threshold, it is a normal period. If an abnormal point appears within a continuous period of time, the next time is used as the degradation starting point. When the capacitor starts to degrade within a certain period of operation, as the degradation coefficient gradually increases, when it exceeds the failure threshold, the capacitor can no longer continue to work, and the capacitor life at this time is 0.

[0148] Furthermore, by combining power factor, power quality, failure probability, and lifespan indicators and presenting them in a visual format, a more comprehensive assessment of capacitor performance can be achieved. Cloud charts can show the relationship and changing trends between these indicators, allowing a quick understanding of the overall performance of the capacitor.

[0149] S4. Generate a performance visualization cloud map of the low-voltage power capacitor according to the power factor, the power quality, the failure probability and the life index, and calculate the performance membership of the performance visualization cloud map using a preset membership algorithm.

[0150] In an embodiment of the present invention, the performance visualization cloud map is a graphical display method that helps users intuitively understand and analyze the performance of systems, equipment or processes by presenting data of different performance indicators as graphs, charts or images on a visual plane.

[0151] In an embodiment of the present invention, generating a performance visualization cloud map of the low-voltage power capacitor according to the power factor, the power quality, the failure probability, and the life index includes:

[0152] Color-coding the power factors to obtain power factor differentiation, and generating a power visualization cloud map of the power factors according to the power factor differentiation;

[0153] Performing shape coding on the power quality to obtain a power quality discrimination degree, and generating a quality visualization cloud map of the power quality according to the power quality discrimination degree;

[0154] Density encoding is performed on the fault probability to obtain a fault discrimination degree, and a fault visualization cloud map of the fault probability is generated according to the fault discrimination degree;

[0155] Performing line coding on the life indicators to obtain a life indicator discrimination degree, and generating a life visualization cloud map of the life indicators according to the life indicator discrimination degree;

[0156] The power visualization cloud map, the quality visualization cloud map, the fault visualization cloud map and the life visualization cloud map are aggregated into a performance visualization cloud map of the low-voltage power capacitor.

[0157] In detail, the power visualization cloud map refers to the use of color coding or chromatogram to represent the distinction between different power factors. For example, a heat map is used to display the distribution of different power factors. Areas with higher power factors can be represented by brighter colors, while areas with lower power factors are represented by darker colors. The quality visualization cloud map refers to the use of shape coding to represent different power qualities. For example, different shapes (such as circles, squares, triangles, etc.) are used to represent the level of power quality. The sizes of different shapes can represent the degree of power quality. For example, larger shapes represent better power quality, and smaller shapes represent poorer power quality. The fault visualization cloud map refers to the use of the density or size of different points to represent different fault probabilities. For example, areas with lower fault probabilities can be represented by more points or larger points, while areas with higher fault probabilities are represented by fewer points or smaller points. The life visualization cloud map refers to the use of lines or labels to represent the values of different life indicators. For example, lines connecting different areas are drawn on the cloud map. The color, thickness or virtuality of the lines can represent the level of the life indicator. Additionally, labels can be added to the cloud map to indicate the life indicator values for different areas. Combining these dimensions creates a multi-dimensional cloud map that intuitively displays the performance characteristics of low-voltage power capacitors. This performance visualization cloud map allows for a better understanding and analysis of low-voltage power capacitor performance, supporting decision-making and optimization efforts.

[0158] Furthermore, mapping the data of performance indicators to specific membership values can transform performance from a subjective descriptive concept into a specific numerical value, and to a certain extent achieve objective evaluation and quantification of performance. The membership value of performance can provide a more accurate measurement, making the evaluation of performance more credible.

[0159] In the embodiment of the present invention, the performance membership is a concept for measuring the degree or quality of a performance indicator, and represents the degree of belonging or adaptability of a performance indicator value within a certain specific range.

[0160] In the embodiment of the present invention, the calculation of the performance membership of the performance visualization cloud map using a preset membership algorithm includes:

[0161] The membership degree of the performance indicators in the performance visualization cloud graph is calculated one by one using the membership degree algorithm, wherein the membership degree algorithm is:

[0162]

[0163] Among them, μ r is the membership degree of the rth performance index, e is a constant, S r is the performance value of the rth performance indicator, E is the Gaussian membership mean, and y is the Gaussian membership variance;

[0164] The memberships are superimposed to obtain the performance membership of the performance visualization cloud map.

[0165] In detail, the membership of each performance indicator in the performance visualization cloud map is calculated one by one according to the membership algorithm, wherein the membership algorithm is based on the Gaussian membership function, which is used to describe the membership of continuous performance indicators and is presented in the form of a Gaussian distribution curve. The Gaussian membership function calculates the membership value of the performance indicator based on the specified center value and standard deviation. By using the Gaussian membership function, the membership value of each indicator value can be calculated based on the distribution characteristics of the performance indicator value, and the membership of the performance indicator can be presented in the performance visualization cloud map, which helps to understand and compare the relative quality of different performance indicators.

[0166] Specifically, the performance membership corresponding to each performance indicator is superimposed to obtain the overall performance membership of the performance visualization cloud map, thereby determining the overall performance membership of the low-voltage power capacitor. Furthermore, the overall performance value of the low-voltage power capacitor is calculated based on the performance membership, which can be used for comprehensive evaluation, quantitative comparison, optimization and improvement, decision support, and predictive monitoring. This can help to more comprehensively and accurately understand the performance of low-voltage power capacitors and support corresponding decision-making and optimization behaviors.

[0167] S5. Calculate the performance value of the low-voltage power capacitor according to the performance membership and a preset performance weight, and determine the performance of the low-voltage power capacitor according to the performance value and a preset performance threshold.

[0168] In the embodiment of the present invention, the performance value is a measure of the performance index of the low-voltage power capacitor, and is used to quantify the relative quality or superiority of the low-voltage power capacitor in various performance indexes.

[0169] In an embodiment of the present invention, the calculating the performance value of the low-voltage power capacitor according to the performance membership and the preset performance weight includes:

[0170] determining a performance level of the low-voltage power capacitor according to the performance weight;

[0171] quantizing the performance level to obtain a performance quantization level;

[0172] The performance value of the low-voltage power capacitor is calculated according to the performance quantification level and the performance membership using the following performance value calculation formula:

[0173]

[0174] Wherein, ψ is the performance value, δ is the performance quantization level, μ r is the membership degree of the rth performance indicator, T is the number of performance indicators, and ln is the logarithmic function.

[0175] Specifically, the performance weights represent the importance of each performance factor in the overall evaluation and can be customized based on application requirements, industry standards, or user preferences. The performance values calculated based on the weights provide a comprehensive performance evaluation, more accurately reflecting the performance of low-voltage power capacitors across various performance indicators. Furthermore, the performance levels can be quantified to obtain a performance quantification grade, such as a high performance grade of 1, a medium performance grade of 0, and a low performance grade of -1.

[0176] Specifically, the overall performance index of the low-voltage power capacitor can be calculated according to the performance quantization level and the performance membership, and the overall performance of the low-voltage power capacitor can be determined according to the performance value, that is, the automation performance of the low-voltage power capacitor is evaluated, and then the performance of the low-voltage power capacitor is determined according to the performance value and the preset performance threshold. When the performance value is greater than the preset performance threshold, the performance of the low-voltage power capacitor is determined as high-level performance; when the performance value is equal to the preset performance threshold, the performance of the low-voltage power capacitor is determined as intermediate performance; when the performance value is less than the preset performance threshold, the performance of the low-voltage power capacitor is determined as low-level performance.

[0177] Furthermore, by calculating performance values, it's possible to identify the shortcomings or strengths of low-voltage power capacitors in certain performance indicators. Based on this performance feedback, targeted optimization and improvements can be made to enhance the overall performance of low-voltage power capacitors, assisting in the decision-making process. Furthermore, by weighting different application scenarios and requirements, decisions can be made based on the calculated performance values, such as selecting the most appropriate low-voltage power capacitor and scheduling maintenance and replacement plans.

[0178] The embodiment of the present invention extracts multimodal features of the operating data of the low-voltage power capacitor to reveal information from different aspects of the signal to obtain more comprehensive and accurate information; monitors the power factor of the low-voltage power capacitor according to the multimodal features, and then determines the power quality of the low-voltage power capacitor based on the power factor, which is conducive to accurate analysis of power utilization efficiency, line loss and potential problems to ensure the stability and quality of power supply; calculates the failure probability and life index of the low-voltage power capacitor according to the multimodal features, which is conducive to analyzing the multi-dimensional performance of the low-voltage power capacitor and improving the accuracy of performance analysis; generates a performance visualization cloud map of the power factor, power quality, failure probability and life index, and presents it in a visual manner, which can more comprehensively evaluate the performance of the capacitor; calculates the performance value of the low-voltage power capacitor through the performance membership and performance weight of the performance visualization cloud map, and then analyzes the performance of the low-voltage power capacitor based on the performance value, so that according to the feedback of the performance value, targeted optimization and improvement can be carried out to improve the overall performance of the low-voltage power capacitor and assist in the decision-making process. Therefore, the method and system for automated performance analysis based on low-voltage power capacitors proposed in the present invention can solve the problem of low accuracy when performing automated performance analysis of low-voltage power capacitors.

[0179] like Figure 4 , which is a functional module diagram of a performance automation analysis system based on low-voltage power capacitors provided by one embodiment of the present invention.

[0180] The automated performance analysis system 100 for low-voltage power capacitors described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the automated performance analysis system 100 for low-voltage power capacitors can include a multimodal feature extraction module 101, a power factor monitoring module 102, a life index calculation module 103, a performance membership calculation module 104, and a performance analysis module 105. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and perform fixed functions, and are stored in the memory of the electronic device.

[0181] In this embodiment, the functions of each module / unit are as follows:

[0182] The multimodal feature extraction module 101 is used to collect operating data of the low-voltage power capacitor in real time, perform signal conversion on the operating data using a preset signal conversion algorithm to obtain an operating signal, and extract multimodal features of the operating signal using a preset multimodal feature algorithm;

[0183] The power factor monitoring module 102 is configured to monitor the power factor of the low-voltage power capacitor according to the multimodal feature through a preset automation factor mode, and determine the power quality of the low-voltage power capacitor according to the power factor index;

[0184] The life index calculation module 103 is used to calculate the failure probability of the low-voltage power capacitor according to the multimodal characteristics using a preset pattern matching algorithm, and calculate the life index of the low-voltage power capacitor according to the operating data using a pre-built time series cycle life model;

[0185] The performance membership calculation module 104 is used to generate a performance visualization cloud map of the low-voltage power capacitor according to the power factor, the power quality, the failure probability and the life index, and calculate the performance membership of the performance visualization cloud map using a preset membership algorithm;

[0186] The performance analysis module 105 is configured to calculate a performance value of the low-voltage power capacitor according to the performance membership and a preset performance weight, and determine the performance of the low-voltage power capacitor according to the performance value and a preset performance threshold.

[0187] In detail, each module in the automatic performance analysis system 100 based on low-voltage power capacitors according to the embodiment of the present invention adopts the same Figures 1 to 3 The same technical means as the automated performance analysis method based on low-voltage power capacitors described in , and can produce the same technical effects, will not be repeated here.

[0188] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and actual implementation may employ other division methods.

[0189] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0190] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0191] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0192] Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the claims are intended to be embraced therein. Any reference to a figure in a claim should not be construed as limiting the claim to which it relates.

[0193] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0194] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems recited in a system claim may also be implemented by a single unit or system through software or hardware. Terms such as "first" and "second" are used to indicate names and do not imply any particular order.

[0195] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for automated performance analysis based on low-voltage power capacitors, characterized in that: The method comprises: S1. Collecting operating data of a low-voltage power capacitor in real time, performing signal conversion on the operating data using a preset signal conversion algorithm to obtain an operating signal, and extracting multimodal features of the operating signal using a preset multimodal feature algorithm; S2. Monitoring the power factor of the low-voltage power capacitor according to the multimodal characteristics through a preset automation factor mode, and determining the power quality of the low-voltage power capacitor according to the power factor index; S3. Calculate the failure probability of the low-voltage power capacitor according to the multimodal features using a preset pattern matching algorithm, and calculate the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model; S4. Generate a performance visualization cloud map of the low-voltage power capacitor according to the power factor, the power quality, the failure probability, and the life index, and calculate the performance membership of the performance visualization cloud map using a preset membership algorithm; S5. Calculating a performance value of the low-voltage power capacitor according to the performance membership and a preset performance weight, and determining the performance of the low-voltage power capacitor according to the performance value and a preset performance threshold, wherein calculating the performance value of the low-voltage power capacitor according to the performance membership and the preset performance weight includes: S51. Determine the performance level of the low-voltage power capacitor according to the performance weight; S52, quantifying the performance level to obtain a performance quantization level; S53. Calculate the performance value of the low-voltage power capacitor according to the performance quantification level and the performance membership using the following performance value calculation formula: Wherein, ψ is the performance value, δ is the performance quantization level, μ r is the membership degree of the rth performance indicator, T is the number of performance indicators, and ln is the logarithmic function.

2. The method for automated performance analysis based on a low-voltage power capacitor according to claim 1, wherein: The performing signal conversion on the operation data by using a preset signal conversion algorithm to obtain an operation signal includes: Converting the operation data into operation series data according to a preset time interval; The running time series data is converted into running frequency domain data using a preset signal conversion algorithm, wherein the signal conversion algorithm is: Wherein, F(w) is the operating frequency domain data, f(t) is the operating time series data at time t, e is a constant, w is the angular frequency, and dt is the differential with respect to t; Perform signal component analysis on the operating frequency domain data to obtain an operating frequency domain component; The operating signal is generated according to the operating frequency domain component.

3. The method for automated performance analysis based on a low-voltage power capacitor according to claim 1, wherein: The extracting the multimodal features of the operating signal by using a preset multimodal feature algorithm includes: The instantaneous energy mean of the operating signal is calculated using the instantaneous energy mean calculation formula in the multimodal feature algorithm: Among them, A k is the instantaneous energy mean of the k-th running signal, is the amplitude of the kth component in the i-th running signal, n is the number of sampling points, and m is the number of components; The harmonic component of the operating signal is calculated using the signal harmonic component calculation formula in the multimodal feature algorithm: Wherein, B is the harmonic signal value in the harmonic component, p u is the frequency of the u-th harmonic in the harmonic component, D is the amplitude, π is the circumference, g is the frequency, t is the signal time, is the phase, U is a constant, and p0 is the fundamental frequency; The instantaneous energy mean and the harmonic component are subjected to feature fusion to obtain the multimodal features of the operating signal.

4. The method for automated performance analysis based on a low-voltage power capacitor according to claim 1, wherein: The monitoring of the power factor of the low-voltage power capacitor according to the multimodal feature through a preset automation factor mode includes: Extracting instantaneous energy mean and harmonic components in the multimodal features in real time according to a preset timestamp through the automated factor mode; Extracting the current signal phase and the voltage signal phase in the multimodal feature according to the instantaneous energy mean and the harmonic component; Determining the useful power and useless power of the low-voltage power capacitor according to the phase difference between the current signal phase and the voltage signal phase; The power factor of the low-voltage power capacitor is calculated according to the useful power and the useless power.

5. The method for automated performance analysis based on low-voltage power capacitors according to claim 1, characterized in that: Determining the power quality of the low-voltage power capacitor according to the power factor index includes: determining a power factor level according to the power factor and a preset power factor threshold; determining the power loss of the low-voltage power capacitor according to the power factor level; The power quality of the low-voltage power capacitor is determined based on the power loss.

6. The method for automated performance analysis based on low-voltage power capacitors according to claim 1, characterized in that: The calculating the failure probability of the low-voltage power capacitor according to the multimodal features using a preset pattern matching algorithm includes: Extracting key features from the multimodal features based on preset fault correlation features; The key features are pattern matched with preset fault rules using the pattern matching algorithm to obtain a pattern matching logic value, wherein the pattern matching algorithm is: M=(X v ≥X vmin )V(X v ≤X vmax ) Wherein, M is the pattern matching logic value, X v is the eigenvalue of the vth feature in the key feature, X vmin is the minimum value of the vth feature in the fault rule, X vmax is the maximum value of the vth feature in the fault rule; The failure probability of the low-voltage power capacitor is calculated according to the pattern matching logic value and the preset fault association number, wherein the failure probability calculation formula is: Wherein, h is the fault probability, L is the number of first identifiers in the pattern matching logic value, and Z is the number of fault associations.

7. The method for automated performance analysis based on low-voltage power capacitors according to claim 1, characterized in that: The calculating the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model includes: Extracting life characteristics from the operating data according to a preset sliding window; The time series cycle life model is used to calculate the life characteristic time series of the low-voltage power capacitor according to the life characteristic, wherein the time series cycle life model is: in, is the life characteristic of the ∈th step at time t, is the life characteristic of the ∈-pth step at time t, is the autoregressive coefficient of the pth model; The life index of the low-voltage power capacitor is determined according to the life characteristic time sequence and a preset life threshold.

8. The method for automated performance analysis based on low-voltage power capacitors according to claim 1, wherein: Generating a performance visualization cloud map of the low-voltage power capacitor according to the power factor, the power quality, the failure probability, and the life index includes: Color-coding the power factors to obtain power factor differentiation, and generating a power visualization cloud map of the power factors according to the power factor differentiation; Performing shape coding on the power quality to obtain a power quality discrimination degree, and generating a quality visualization cloud map of the power quality according to the power quality discrimination degree; Density encoding is performed on the fault probability to obtain a fault discrimination degree, and a fault visualization cloud map of the fault probability is generated according to the fault discrimination degree; Performing line coding on the life indicators to obtain a life indicator discrimination degree, and generating a life visualization cloud map of the life indicators according to the life indicator discrimination degree; The power visualization cloud map, the quality visualization cloud map, the fault visualization cloud map and the life visualization cloud map are aggregated into a performance visualization cloud map of the low-voltage power capacitor.

9. The method for automated performance analysis based on low-voltage power capacitors according to claim 1, wherein: The calculating the performance membership of the performance visualization cloud graph by using a preset membership algorithm includes: The membership degree of the performance indicators in the performance visualization cloud graph is calculated one by one using the membership degree algorithm, wherein the membership degree algorithm is: Among them, μ r is the membership degree of the rth performance index, e is a constant, S r is the performance value of the rth performance indicator, E is the Gaussian membership mean, and y is the Gaussian membership variance; The memberships are superimposed to obtain the performance membership of the performance visualization cloud map.

10. A performance automation analysis system based on low-voltage power capacitors, characterized in that: A multimodal feature extraction module is used to collect operating data of a low-voltage power capacitor in real time, perform signal conversion on the operating data using a preset signal conversion algorithm to obtain an operating signal, and extract multimodal features of the operating signal using a preset multimodal feature algorithm; A power factor monitoring module, configured to monitor the power factor of the low-voltage power capacitor according to the multimodal characteristics through a preset automation factor mode, and determine the power quality of the low-voltage power capacitor according to the power factor index; A life index calculation module, configured to calculate the failure probability of the low-voltage power capacitor according to the multimodal characteristics using a preset pattern matching algorithm, and calculate the life index of the low-voltage power capacitor according to the operating data using a pre-built sequential cycle life model; A performance membership calculation module is used to generate a performance visualization cloud map of the low-voltage power capacitor based on the power factor, the power quality, the failure probability and the life index, and calculate the performance membership of the performance visualization cloud map using a preset membership algorithm; The performance analysis module is used to calculate the performance value of the low-voltage power capacitor according to the performance membership and the preset performance weight, and determine the performance of the low-voltage power capacitor according to the performance value and the preset performance threshold.

Images