CN116881661A

CN116881661A - Performance automatic analysis method and system based on low-voltage power capacitor

Info

Publication number: CN116881661A
Application number: CN202310897222.7A
Authority: CN
Inventors: 陈娟娟; 王光照; 陈刚; 郑笑静
Original assignee: Huazhiyuan Electric Group Co ltd
Current assignee: Huazhiyuan Electric Group Co ltd
Priority date: 2023-07-20
Filing date: 2023-07-20
Publication date: 2023-10-13

Abstract

The invention relates to the technical field of power automation, and discloses a performance automatic analysis method and system based on a low-voltage power capacitor, wherein the method comprises the following steps: performing signal conversion on the operation data to obtain an operation signal, and extracting multi-mode characteristics of the operation signal; monitoring the power factor of the low-voltage power capacitor according to the multi-mode characteristics, and determining the electric energy quality of the low-voltage power capacitor according to the power factor index; calculating the fault probability of the low-voltage power capacitor according to the multi-mode characteristics, and calculating the service life index of the low-voltage power capacitor according to the operation data; generating a performance visual cloud picture according to the power factor, the electric energy quality, the fault probability and the life index, and calculating the performance membership of the performance visual cloud picture; and calculating the performance value of the low-voltage power capacitor according to the performance membership and the performance weight, and determining the performance of the low-voltage power capacitor according to the performance value and the performance threshold. The invention can improve the accuracy of the performance automatic analysis of the low-voltage power capacitor.

Description

Performance automatic analysis method and system based on low-voltage power capacitor

Technical Field

The invention relates to the technical field of power automation, in particular to a performance automatic analysis method and system based on a power capacitor.

Background

With the wide application of modern electrical equipment, low-voltage power capacitors are also continuously improved and applied, but potential problems, such as voltage fluctuation, current harmonics and the like, occur in the low-voltage power capacitors, which affect the power quality, so that the performance index of the low-voltage power capacitors needs to be analyzed to improve the power quality of the low-voltage power capacitors.

The existing low-voltage power capacitor performance automatic analysis technology is to test each performance of the low-voltage power capacitor one by setting an automatic test script so as to analyze the performance index of the low-voltage power capacitor. In practical application, when the automatic test script tests the performance, the performance index can not be missed completely, and the performance index can not be tested comprehensively, so that the accuracy of the performance automatic analysis of the low-voltage power capacitor is lower.

Disclosure of Invention

The invention provides a performance automatic analysis method and system based on a low-voltage power capacitor, and mainly aims to solve the problem of low accuracy in performance automatic analysis of the low-voltage power capacitor.

In order to achieve the above object, the present invention provides a performance automation analysis method based on a low-voltage power capacitor, comprising:

s1, acquiring operation data of a low-voltage power capacitor in real time, performing signal conversion on the operation data by using a preset signal conversion algorithm to obtain an operation signal, and extracting multi-mode characteristics of the operation signal by using a preset multi-mode characteristic algorithm;

s2, monitoring the power factor of the low-voltage power capacitor according to the multi-mode characteristics through a preset automatic factor mode, and determining the power quality of the low-voltage power capacitor according to the power factor index;

s3, calculating the fault probability of the low-voltage power capacitor according to the multi-mode characteristics by using a preset mode matching algorithm, and calculating the life index of the low-voltage power capacitor according to the operation data through a pre-constructed time sequence cycle life model;

s4, generating a performance visual cloud chart of the power capacitor according to the power factor, the electric energy quality, the fault probability and the life index, and calculating the performance membership of the performance visual cloud chart by 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 the calculating the performance value of the low-voltage power capacitor according to the performance membership and the preset performance weight comprises the following steps:

s51, determining the performance grade of the low-voltage power capacitor according to the performance weight;

s52, carrying out level quantization on the performance level to obtain a performance quantization level;

s53, calculating the performance value of the piezoelectric capacitor according to the performance quantization level and the performance membership degree by using the following performance value calculation formula:

wherein, psi is the performance value, delta is the performance quantization level, mu _r The membership degree of the performance index of the r is that of the performance index of the r, T is the number of the performance indexes, and ln is a logarithmic function.

Optionally, 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 time sequence data according to a preset time interval;

converting the operation time sequence data into operation frequency domain data by using a preset signal conversion algorithm, wherein the signal conversion algorithm is as follows:

F(w)＝∫[f(t)×e ^-wt ]dt

Wherein F (w) is the operation frequency domain data, F (t) is the operation time sequence data at the t-th moment, e is a constant, w is an angular frequency, and dt is a derivative of t;

performing signal components on the operation frequency domain data to obtain operation frequency domain components;

and generating the operation signal according to the operation frequency domain component.

Optionally, the extracting the multi-modal feature of the operation signal through a preset multi-modal feature algorithm includes:

calculating the instantaneous energy mean value of the running signal through an instantaneous energy mean value calculation formula in the multi-mode characteristic algorithm:

wherein ,A_k Is the instantaneous energy mean value of the kth operating signal,the amplitude value of the kth component in the ith operation signal is represented by n, the number of sampling points is represented by m, and the number of components is represented by m;

calculating harmonic components of the operation signal through a signal harmonic component calculation formula in the multi-modal feature algorithm:

wherein B is a harmonic signal value, p, in the harmonic component _u The frequency of the u-th harmonic in the harmonic component is represented by D, which is the amplitude, pi is the circumference ratio, g is the frequency, t is the signal time,is phase, U is constant, p ₀ Is the fundamental frequency;

and carrying out feature fusion on the instantaneous energy mean value and the harmonic component to obtain the multi-mode feature of the running signal.

Optionally, the monitoring the power factor of the low voltage power capacitor according to the multi-modal feature through a preset automation factor model includes:

extracting instantaneous energy mean value and harmonic components in the multi-mode characteristics in real time according to a preset time stamp through the automatic factor model;

extracting a current signal phase and a voltage signal phase in the multi-mode feature according to the instantaneous energy mean value and the harmonic component;

determining useful power and useless power of the voltage capacitor according to the phase difference between the current signal phase and the voltage signal phase;

and calculating the power factor of the low-voltage power capacitor according to the useful power and the useless power.

Optionally, the 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 electrical energy loss of the low-voltage power capacitor according to the power factor level;

and determining the power quality of the low-voltage power capacitor according to the power loss.

Optionally, the calculating the fault probability of the piezoelectric capacitor according to the multi-mode feature by using a preset mode matching algorithm includes:

Extracting key features in the multi-modal features according to preset fault associated features;

performing pattern matching on the key features and a preset fault rule by using the pattern matching algorithm to obtain a pattern matching logic value, wherein the pattern matching algorithm is as follows:

M＝(X _v ≥X _vmin )V(X _v ≤X _vmax )

wherein M is the pattern matching logic value, X _v Is the characteristic value of the v-th characteristic in the key characteristics, X _vmin Is the feature minimum value of the v-th feature in the fault rule, X _vmax A feature maximum value of the v-th feature in the fault rule;

calculating the fault probability of the low-voltage power capacitor according to the pattern matching logic value and the preset fault association quantity, wherein the fault probability calculation formula is as follows:

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 correlations.

Optionally, the calculating, by using a pre-constructed time sequence cyclic life model, a life index of the piezoelectric capacitor according to the operation data includes:

extracting life characteristics in the operation data according to a preset sliding window;

calculating a life characteristic time sequence of the piezoelectric capacitor according to the life characteristic by using the time sequence cycle life model, wherein the time sequence cycle life model is as follows:

wherein ,for the lifetime feature of step e at time t, +.>For the lifetime characteristic of step e-p at time t, +.>Autoregressive coefficients for the p-th model;

and determining the life index of the power capacitor according to the life characteristic time sequence and a preset life threshold value.

Optionally, the generating the performance visualization cloud image of the piezoelectric capacitor according to the power factor, the power quality, the fault probability and the life index includes:

performing color coding on the power factor to obtain a power factor distinguishing degree, and generating a power visualization cloud picture of the power factor according to the power factor distinguishing degree;

performing shape coding on the electric energy quality to obtain electric energy quality differentiation, and generating a quality visual cloud picture of the electric energy quality according to the electric energy quality differentiation;

performing density coding on the fault probability to obtain fault differentiation degree, and generating a fault visualization cloud picture of the fault probability according to the fault differentiation degree;

performing line coding on the life index to obtain life index distinction, and generating a life visual cloud picture of the life index according to the life index distinction;

And aggregating the power visualization cloud picture, the quality visualization cloud picture, the fault visualization cloud picture and the service life visualization cloud picture into a performance visualization cloud picture of the power capacitor.

Optionally, the calculating the performance membership of the performance visualization cloud chart by using a preset membership algorithm includes:

calculating the membership of the performance index in the performance visualization cloud chart one by using the membership algorithm, wherein the membership algorithm is as follows:

wherein ,μ_r For the r-th performance indexThe degree, e, is a constant, S _r The performance value of the r-th performance index is represented by a Gaussian membership mean value, and y is a Gaussian membership variance;

and superposing the membership degrees to obtain the performance membership degree of the performance visual cloud chart.

In order to solve the above problems, the present invention also provides a performance automation analysis system based on a piezoelectric capacitor, the system comprising:

the multi-modal feature extraction module is used for acquiring the operation data of the power capacitor in real time, performing signal conversion on the operation data by using a preset signal conversion algorithm to obtain an operation signal, and extracting multi-modal features of the operation signal by using the preset multi-modal feature algorithm;

The power factor monitoring module is used for monitoring the power factor of the low-voltage power capacitor according to the multi-mode characteristics through a preset automatic factor model and determining the power quality of the low-voltage power capacitor according to the power factor index;

the life index calculation module is used for calculating the fault probability of the low-voltage power capacitor according to the multi-mode characteristics by using a preset mode matching algorithm, and calculating the life index of the low-voltage power capacitor according to the operation data through a pre-constructed time sequence cycle life model;

the performance membership calculation module is used for generating a performance visual cloud picture of the power capacitor according to the power factor, the power quality, the fault probability and the service life index, and calculating the performance membership of the performance visual cloud picture by using a preset membership algorithm;

and the performance analysis module is used for calculating the performance value of the low-voltage power capacitor according to the performance membership and the preset performance weight and determining the performance of the low-voltage power capacitor according to the performance value and the preset performance threshold.

According to the embodiment of the invention, the information of different aspects of the signal is disclosed by extracting the multi-mode characteristics of the operation data of the low-voltage power capacitor so as to obtain more comprehensive and accurate information; the power factor of the low-voltage power capacitor is monitored according to the multi-mode characteristics, and the electric energy quality of the low-voltage power capacitor is determined according to the power factor, so that the accurate analysis of the electric energy utilization efficiency, the line loss and the potential problems is facilitated, and the stability and the quality of electric energy supply are ensured; the fault probability and the service life index of the low-voltage power capacitor are calculated according to the multi-mode characteristics, so that the multi-dimensional performance of the low-voltage power capacitor is analyzed, and the accuracy of performance analysis is improved; the performance visualization cloud picture is generated by the power factor, the electric energy quality, the fault probability and the life index, and is presented in a visualization mode, so that the performance of the capacitor can be more comprehensively evaluated; the performance value of the low-voltage power capacitor is calculated through the performance membership and the performance weight of the performance visualization cloud chart, and then the performance of the low-voltage power capacitor is analyzed according to the performance value, so that the performance of the low-voltage power capacitor can be optimized and improved in a targeted manner according to the feedback of the performance value, the overall performance of the low-voltage power capacitor is improved, and the decision making process can be assisted. Therefore, the performance automatic analysis method and system based on the low-voltage power capacitor can solve the problem of lower accuracy in performance automatic analysis of the low-voltage power capacitor.

Drawings

FIG. 1 is a flow chart of an automated analysis method for performance based on a low voltage capacitor according to an embodiment of the present application;

FIG. 2 is a flow chart of monitoring power factor according to an embodiment of the present application;

FIG. 3 is a flow chart illustrating the calculation of failure probability according to an embodiment of the present application;

FIG. 4 is a functional block diagram of an automated analysis system for performance based on a low voltage power capacitor according to an embodiment of the present application.

The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The embodiment of the application provides a performance automatic analysis method based on a piezoelectric capacitor. The execution subject of the performance automation analysis method based on the low-voltage power capacitor comprises, but is not limited to, at least one of a server, a terminal and the like which can be configured to execute the method provided by the embodiment of the application. In other words, the performance automation analysis method based on the piezoelectric capacitor may be performed by software or hardware installed in a terminal device or a server device, and the software may be a blockchain platform. The service end includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like. The server may be an independent server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

Referring to fig. 1, a flow chart of a performance automation analysis method based on a low-voltage power capacitor according to an embodiment of the invention is shown. In this embodiment, the performance automation analysis method based on the low-voltage power capacitor includes:

s1, acquiring operation data of a low-voltage power capacitor in real time, performing signal conversion on the operation data by using a preset signal conversion algorithm to obtain an operation signal, and extracting multi-mode characteristics of the operation signal by using a preset multi-mode characteristic algorithm.

In the embodiment of the invention, the operation data comprise the current, the voltage, the power and the like of the low-voltage power capacitor, wherein the operation data of the low-voltage power capacitor, such as a current sensor, a voltage sensor and the like, can be acquired in real time by selecting corresponding sensor equipment.

Further, to improve the information content and usability of the operational data, to help in understanding the operational state of the power capacitor in depth, it is necessary to convert the operational data into an operational signal for analysis.

In the embodiment of the invention, the operation signal is a form of converting current, voltage, power and the like in operation data into signals, and represents the real-time operation state of the low-voltage power capacitor.

In the embodiment of the present invention, the signal conversion is performed on the operation data by using a preset signal conversion algorithm to obtain an operation signal, including:

F(w)＝∫[f(t)×e ^-wt ]dt

In detail, the running time of a preset time interval is counted, so that the running time sequence time is obtained, for example, the real-time change state of current and the real-time change state of voltage are counted in the preset time interval, the running time sequence data of the voltage and the current are obtained, and the running time sequence data are converted into frequency domain data represented on a frequency domain through a signal conversion algorithm.

Specifically, the signal conversion algorithm is based on fourier transformation, which converts a function (represented in the time domain) into its spectral representation (represented in the frequency domain), by which the spectral characteristics of a signal can be analyzed, the frequency components contained in the signal and their amplitudes are known, and fourier transformation, which can represent a signal in a continuous time domain as a spectrum in a continuous frequency domain, or a signal in a discrete time domain as a spectrum in a discrete frequency domain. And then the converted operation frequency domain data is subjected to signal component, so that frequency spectrum components can be obtained, and further the frequency spectrum components corresponding to the operation characteristics of different operation data are determined as operation signals.

Further, the operation state, the fault characteristics, the performance index, and the like of the low-voltage power capacitor can be analyzed according to the operation signal, and therefore, the operation characteristics in the operation signal need to be extracted to realize the analysis of the performance index of the low-voltage power capacitor.

In the embodiment of the invention, the multi-mode feature is a plurality of types of feature information corresponding to the running signal, and the multi-mode feature can be selected according to the nature of the signal and the different application requirements so as to reveal information of different aspects of the signal and acquire more comprehensive and accurate information.

In the embodiment of the present invention, the extracting the multi-modal feature of the operation signal by a preset multi-modal feature algorithm includes:

wherein B is a harmonic signal value, p, in the harmonic component _u The frequency of the u-th harmonic in the harmonic component is represented by D, which is the amplitude, pi is the circumference ratio, g is the frequency, t is the signal time,is phase, U is constant，p ₀ Is the fundamental frequency;

In detail, the instantaneous energy mean value reflects the change characteristics of the operation signal in the time direction and can reflect the change condition of the signal in the time domain, and then the instantaneous energy mean value performs hilbert spectrum analysis on each component signal of the decomposed operation signal, which can obtain the information in the frequency domain and the change of the amplitude thereof, so as to calculate the instantaneous energy for the sampling signal of each channel. The change of the operation signal in the time domain is reflected through the instantaneous energy mean value, and then the operation waveform of the operation signal is required to be reflected, so that the power quality of the power capacitor is analyzed according to the operation waveform, and the stability and the operation efficiency of the capacitor are ensured.

Specifically, the harmonic component includes the frequency, phase, and amplitude of the operation signal, and the harmonic is a periodic fluctuation with respect to the fundamental wave, and the frequency thereof is an integer multiple of the fundamental wave frequency. In signal processing, harmonic analysis is often used to analyze frequency components and harmonic content of a signal, and by performing spectral analysis on the signal, a spectrogram of the signal can be obtained, and the intensity and relative proportion of each frequency component in the signal are intuitively displayed. The harmonic component can be distinguished from the spectrogram, and the frequency, phase and amplitude of the harmonic component can be calculated, so that the frequency and harmonic signal value of the operation signal need to be calculated according to a signal harmonic component calculation formula.

Further, the instantaneous energy average value A _k And the harmonic components { B, p } _u Feature fusion is carried out to obtain the multi-mode feature { A } of the operation signal _k ,B,p _u Therefore, fusing multi-modal features may provide more comprehensive, accurate information with better performance.

Further, the performance index of the power capacitor can be monitored according to the multi-mode characteristics, so that the performance automation of the power capacitor can be evaluated more accurately.

S2, monitoring the power factor of the low-voltage power capacitor according to the multi-mode characteristics through a preset automatic factor mode, and determining the power quality of the low-voltage power capacitor according to the power factor index.

In the embodiment of the invention, the power factor is used for describing the relation between active power and apparent power in the active circuit, and represents how much power is effectively utilized in the alternating current circuit to do effective work instead of being wasted, and the good power factor means that more electric energy is converted into useful power, so that the loss of reactive power is reduced, and the energy efficiency of the circuit is improved.

In an embodiment of the present invention, referring to fig. 2, the monitoring, by a preset automation factor module, the power factor of the low voltage power capacitor according to the multi-mode feature includes:

S21, extracting instantaneous energy mean values and harmonic components in the multi-mode features in real time according to preset time stamps through the automatic factor model;

s22, extracting a current signal phase and a voltage signal phase in the multi-mode characteristic according to the instantaneous energy mean value and the harmonic component;

s23, determining useful power and useless power of the voltage capacitor according to the phase difference between the current signal phase and the voltage signal phase;

s24, calculating the power factor of the power capacitor according to the useful power and the useless power.

In detail, the automatic factor mode is a self-setting custom script, and is used for executing the custom script to monitor the data operation data of the power capacitor in real time according to different time stamps, so as to obtain an instantaneous energy mean value and a harmonic component in the multi-mode characteristic, and determine the change characteristics of a current signal and a voltage signal in a time sequence range according to the instantaneous energy mean value, thereby determining a current signal phase and a voltage signal phase according to the voltage signal and the signal value of the current signal in the harmonic component.

In particular, due to the presence of inductance and capacitance in the ac circuit, there may be a phase difference in the waveforms of the current and voltage, thereby generating reactive power, resulting in a power factor of less than 1. When the current and voltage waveforms are completely in phase, the power factor reaches a maximum of 1, indicating that all power in the circuit is useful work. The power factor is typically represented in scalar or angular form, where a range of values for the power factor is 0 to 1, with closer to 1 representing a higher power factor, i.e., more power is effectively utilized; in the angular form, the power factor is represented by the cosine value of the phase difference between the active power and the reactive power, and 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. Thus, the useful power and the useless power of the low-voltage power capacitor can be determined according to the phase difference of the current signal phase and the voltage signal phase, and the useful power is divided by the useless power to obtain the power factor.

Further, the power factor is one of the important indicators for measuring the quality of electric energy, and it represents the ratio of active power to apparent power in the circuit. The power quality of the power capacitor can be determined according to the power factor index.

In the embodiment of the invention, the electric energy quality refers to the characteristics of stability and reliability of electric energy in the electric power system, and is used for describing the capability of the power supply system to meet the requirements of users and provide the required electric energy, and the high-quality electric energy quality ensures the stability of electric power supply, the reliability of working equipment and protects the user equipment from the influence of the abnormality and interference of the electric power system.

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

In detail, the power factor levels are classified into low power factor, high power factor and ultra high power factor; when the power factor approaches 0, it means that the reactive power in the circuit is higher and the active power is lower, which means that the loss of electric energy in the transmission is larger and the efficiency of the circuit is lower, and the low power factor may indicate potential electric energy quality problems, such as energy waste, line overload, etc.; when the power factor approaches 1, it means that the active power in the circuit is higher and the reactive power is lower, which means that the loss of electric energy in the transmission is less, the efficiency of the circuit is higher, and a high power factor is generally considered as one of the better characterization of the electric energy quality; when the power factor exceeds 1, harmonic pollution problems may be indicated in the circuit, and the ultra-high power factor may cause problems such as line overload, equipment damage and the like in some cases, so as to influence the power quality.

In particular, for power quality assessment of a power capacitor, it is important to pay attention to the power factor. The reasonable control and maintenance of the power factor can improve the utilization efficiency of the electric energy, reduce the line loss and potential problems, and ensure the stability and quality of the electric energy supply.

Further, the performance of the low-voltage power capacitor is evaluated, so that not only is the electric energy quality required to be evaluated, but also the fault occurrence probability and the service life index of the low-voltage power capacitor are required to be evaluated, the multi-aspect evaluation of the power capacitor is realized, and the accuracy of the performance evaluation is improved.

S3, calculating the fault probability of the low-voltage power capacitor according to the multi-mode characteristics by using a preset mode matching algorithm, and calculating the life index of the low-voltage power capacitor according to the operation data through a pre-constructed time sequence cycle life model.

In the embodiment of the invention, the fault probability refers to the probability that the power capacitor may fail.

In the embodiment of the present invention, referring to fig. 3, the calculating, by using a preset pattern matching algorithm, the fault probability of the piezoelectric capacitor according to the multi-mode feature includes:

s31, extracting key features in the multi-mode features according to preset fault associated features;

S32, carrying out pattern matching on the key features and a preset fault rule by using the pattern matching algorithm to obtain a pattern matching logic value, wherein the pattern matching algorithm is as follows:

M＝(X _v ≥X _vmin )V(X _v ≤X _vmax )

s33, calculating the fault probability of the low-voltage power capacitor according to the pattern matching logic value and the preset fault association number, wherein the fault probability calculation formula is as follows:

In detail, the fault correlation features refer to features which can influence faults of the low-voltage power capacitor, such as voltage and current, and further screen features in the multi-mode features according to the fault correlation features, so that the features which are more prominent in faults can be screened out, key features, such as current and voltage, are obtained, and therefore the fault identification of the low-voltage power capacitor is more accurate and efficient.

Specifically, the matching process may combine multiple conditions using logical operators by matching selected key features with conditional parts of the rule set by a pattern matching algorithm. If the condition part of a certain rule is successfully matched with the feature, a corresponding fault type is given out according to the conclusion part of the rule; if a plurality of rules are successfully matched, a priority, confidence or other rule selection strategy can be adopted to determine the final fault type, and then the key features are compared with feature values with the same features in the rule set to obtain a pattern matching logic value, wherein the pattern matching logic value comprises 1 and 0, and when the pattern matching logic value is 1, the pattern matching logic value indicates that the matching is successful; when the pattern matching logic value is 0, a matching failure is indicated. And further, calculating the fault probability of the low-voltage power capacitor according to the pattern matching logic value and the preset fault association number, wherein the number L of the first identifiers refers to the number with the value of 1 in the pattern matching logic value.

Illustratively, the key features are { a, b, c, d }, and the fault feature values in the fault rule are { [ a } _min ,a _max ],[b _min ,b _max ],[c _min ,c _max ],[d _min ,d _max ]Comparing the characteristic value in the key characteristic with the fault characteristic one by one, and setting the pattern matching logic value to 0 if the characteristic value is in the fault range of the fault characteristic value; if the feature value is not in the fault range of the fault feature value, the pattern matching logic value is set to be 1, and if the pattern matching logic value is {1, 0}, the number of the logic values being 1 in the pattern matching logic value is compared with the total fault association number, so that the fault probability is 2/4.

Further, the performance of the power capacitor is evaluated, and the life index of the power capacitor needs to be analyzed, so that a customized management plan can be formulated according to the life index, the capacitor to be disabled or aged can be preferentially maintained or replaced, and the capacitor with the life still being prolonged can be periodically checked and maintained to ensure the normal operation of the capacitor.

In the embodiment of the invention, the time sequence cyclic life model is generated based on LSTM training, and LSTM (long-short-term memory network) is a cyclic neural network (RNN) model suitable for modeling sequence data. It can be used in machine life prediction to process data with timing relationships, serialize extracted feature data for training and prediction using the LSTM model, and input the serialized feature data into the LSTM model for training. The goal of the LSTM model is to learn potential patterns and relationships in the input sequence, and for life prediction, life can be used as a target value for training using a supervised learning method, thereby obtaining a time-series cyclic life model that can evaluate the life index of the piezoelectric capacitor.

In the embodiment of the present invention, the calculating, by using the pre-constructed time-series cycle life model, the life index of the low-voltage power capacitor according to the operation data includes:

In detail, the life characteristics are factors which can influence the life of the low-voltage power capacitor, including voltage, current, temperature, frequency, running time, cycle number and the like, and the life characteristics under one sliding window are extracted according to a preset sliding window, so that life data sequences corresponding to a plurality of life characteristics are formed, and the life of the low-voltage power capacitor can be evaluated more accurately.

Specifically, according to the time sequence formula in the time sequence cyclic life model, the life characteristic time sequence of the next moment can be predicted according to the life characteristic, for example, the characteristic value of the life characteristic of the next moment is predicted based on the voltage, the current, the temperature and the like in the life characteristic, so that the life characteristic time sequence is obtained, and further, the life phase of the piezoelectric capacitor is obtained by comparing the life characteristic time sequence with a preset life threshold value, wherein the life phase comprises a normal phase, a degradation phase and a failure phase. If the characteristic value in the life characteristic time sequence is compared with the alarm threshold value in the preset life threshold value, the life characteristic time sequence is a normal period when the characteristic value is smaller than the alarm threshold value, if an abnormal point appears in a continuous period of time, the next time is taken as a degradation starting point, the capacitor starts to degrade in a certain period of time when the capacitor operates, the degradation coefficient gradually increases, when the failure threshold value is exceeded, the capacitor cannot continue to work at the moment, and the life of the capacitor at the moment is 0.

Further, by integrating the power factor, power quality, probability of failure, and life indicators together and presenting them in a visual manner, the performance of the capacitor can be more fully evaluated. The cloud chart can show the relation and the change trend among the indexes, and the overall performance of the capacitor can be quickly known.

And S4, generating a performance visual cloud chart of the power capacitor according to the power factor, the electric energy quality, the fault probability and the service life index, and calculating the performance membership of the performance visual cloud chart by using a preset membership algorithm.

In the embodiment of the invention, the performance visualization cloud image type graphical display mode helps a user intuitively understand and analyze the performance condition of a system, equipment or process by presenting data of different performance indexes as graphs, charts or images on one visualization plane.

In the embodiment of the present invention, the generating the performance visualization cloud image of the low-voltage capacitor according to the power factor, the power quality, the fault probability and the life index includes:

In detail, the power visualization cloud refers to using color coding or chromatograms to represent the degree of differentiation of different power factors, for example, using thermodynamic diagrams to display the distribution of different power factors, the areas with higher power factors can be represented by lighter colors, and the areas with lower power factors by darker colors; the quality visualization cloud chart refers to the case of using shape codes to represent different power quality, for example, using different shapes (such as circles, squares, triangles, etc.) to represent the level of the power quality, and the size of the different shapes may represent the degree of the power quality, for example, a larger shape represents a better power quality and a smaller shape represents a worse power quality; the fault visualization cloud chart refers to the case that different densities or sizes of different points are used for representing different fault probabilities, for example, a region with lower fault probability can be represented by more points or larger points, and a region with higher fault probability can be represented by fewer points or smaller points; the life visualization cloud chart refers to that values of different life indexes are represented by lines or labels, for example, lines connecting different areas are drawn on the cloud chart, and colors, thickness or virtual reality of the lines can represent the level of the life indexes. In addition, labels can be added on the cloud pictures, the service life index values of different areas are marked, and then the dimensions are combined, so that a multi-dimensional cloud picture can be generated, and the performance characteristics of the low-voltage power capacitor can be intuitively displayed. The performance visualization cloud image can better understand and analyze the performance of the power capacitor and support decision making and optimization work.

Further, the performance can be converted from subjective descriptive concepts to specific numerical values by mapping the data of the performance index to specific membership values, objective evaluation and quantification of the performance can be achieved to a certain extent, and the membership values of the performance can provide more accurate measurement, so that the evaluation of the performance is more credible.

In the embodiment of the invention, the performance membership is a concept of measuring the degree or quality of a performance index, and represents the attribution degree or adaptation degree of a performance index value in a specific range.

In the embodiment of the present invention, the calculating the performance membership degree of the performance visualization cloud image by using a preset membership degree algorithm includes:

wherein ,μ_r Membership degree of the r-th performance index, e is a constant, S _r The performance value of the r-th performance index is represented by a Gaussian membership mean value, and y is a Gaussian membership variance;

In detail, the membership of each performance index in the performance visualization cloud chart is calculated one by one according to the membership algorithm, wherein the membership algorithm is based on a Gaussian membership function, the membership is presented in a Gaussian distribution curve form through the membership for describing continuous performance indexes, and the membership value of the performance index is calculated according to a specified central value and standard deviation by the Gaussian membership function. By using the Gaussian membership function, the membership value of each index value can be calculated according to the distribution characteristics of the performance index values, so that the membership of the performance indexes can be presented in the performance visual cloud chart, and the relative quality of different performance indexes can be understood and compared.

Specifically, the performance membership corresponding to each performance index is overlapped to obtain the overall performance membership of the performance visual cloud chart, so that the overall performance membership of the low-voltage power capacitor is determined, and the overall performance value of the low-voltage power capacitor is calculated according to the performance membership, so that comprehensive evaluation, quantitative comparison, optimization improvement, decision support and prediction monitoring can be performed. The method can help to know the performance of the power capacitor more comprehensively and accurately, and support corresponding decision making and optimizing behaviors.

S5, calculating the performance value of the low-voltage power capacitor according to the performance membership degree and the preset performance weight, and determining the performance of the low-voltage power capacitor according to the performance value and the preset performance threshold.

In the embodiment of the invention, the performance value is a measure of the performance index of the low-voltage power capacitor and is used for quantifying the relative quality or the quality of the low-voltage power capacitor on each performance index.

In the 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:

determining the performance level of the power capacitor according to the performance weight;

Performing level quantization on the performance level to obtain a performance quantization level;

calculating the performance value of the low-voltage power capacitor according to the performance quantization level and the performance membership degree by using the following performance value calculation formula:

wherein, psi is the performance value, delta is the performance quantization level, mu _r Is the membership degree of the r-th performance index, T is the number of the performance indexesLn is a logarithmic function.

In detail, the performance weight represents the importance degree of each performance in the overall evaluation, and can be customized based on application requirements, industry standards or user preferences, and the performance value calculated according to the weight can provide an integrated performance evaluation to more accurately reflect the performance of the piezoelectric capacitor on each performance index. Further, the performance level is quantized to a level, and a performance quantization level can be obtained, for example, a high performance level is quantized to 1, a medium performance level is quantized to 0, and a low performance level is quantized to-1.

Specifically, according to the performance quantization level and the performance membership, the overall performance index of the low-voltage power capacitor can be calculated, the overall performance of the low-voltage power capacitor can be determined according to the performance value, namely, the automatic performance of the low-voltage power capacitor is evaluated, and further, the performance of the low-voltage power capacitor is determined according to the performance value and a preset performance threshold, and when the performance value is larger than the preset performance threshold, the performance of the low-voltage power capacitor is determined to be high-level performance; when the performance value is equal to a preset performance threshold, determining the performance of the low-voltage power capacitor as a medium-level performance; and when the performance value is smaller than a preset performance threshold value, determining the performance of the low-voltage power capacitor as low-level performance.

Further, by calculating the performance values, deficiencies or advantages of the power capacitor in certain performance metrics may be found. According to the feedback of the performance value, the power capacitor can be optimized and improved in a targeted manner so as to improve the overall performance of the power capacitor and assist in the decision making process. In addition, according to the weight settings of different application scenes and requirements, corresponding decisions can be made according to the calculated performance values, such as selecting the most suitable power capacitor, scheduling maintenance and replacement plans, and the like.

As shown in fig. 4, a functional block diagram of an automated performance analysis system based on a piezoelectric capacitor according to an embodiment of the present invention is provided.

The performance automation analysis system 100 based on the low-voltage power capacitor of the present invention may be installed in an electronic device. Depending on the functions implemented, the performance automation analysis system 100 based on the piezoelectric capacitors may include a multi-modal 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 module of the invention, which may also be referred to as a unit, refers to a series of computer program segments, which are stored in the memory of the electronic device, capable of being executed by the processor of the electronic device and of performing a fixed function.

In the present embodiment, the functions concerning the respective modules/units are as follows:

the multi-modal feature extraction module 101 is configured to collect operation data of the low-voltage power capacitor in real time, perform signal conversion on the operation data by using a preset signal conversion algorithm to obtain an operation signal, and extract multi-modal features of the operation signal by using the preset multi-modal feature algorithm;

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

the life index calculation module 103 is configured to calculate, according to the multi-mode feature, a failure probability of the low-voltage power capacitor by using a preset mode matching algorithm, and calculate, according to the operation data, a life index of the low-voltage power capacitor by using a pre-constructed time-sequence cyclic life model;

the performance membership calculation module 104 is configured to generate a performance visualization cloud image of the power capacitor according to the power factor, the power quality, the fault probability and the life index, and calculate a performance membership of the performance visualization cloud image by using a preset membership algorithm;

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 a performance of the low-voltage power capacitor according to the performance value and a preset performance threshold.

In detail, each module in the performance automation analysis system 100 based on a low-voltage power capacitor in the embodiment of the present invention adopts the same technical means as the performance automation analysis method based on a low-voltage power capacitor described in fig. 1 to 3, and can generate the same technical effects, which are not described herein.

In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the modules is merely a logical function division, and other manners of division may be implemented in practice.

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

In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units can be realized in a form of hardware or a form of hardware and a form of software functional modules.

It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof.

The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference signs in the claims shall not be construed as limiting the claim concerned.

The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.

Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Multiple units or systems as set forth in the system claims may also be implemented by means of one unit or system in software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.

Finally, it should be noted that the above-mentioned embodiments are merely for illustrating the technical solution of the present application and not for limiting the same, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the technical solution of the present application without departing from the spirit and scope of the technical solution of the present application.

Claims

1. A method for automatically analyzing performance based on a low-voltage power capacitor, the method comprising:

2. The method for automatically analyzing performance of a capacitor based on voltage power according to claim 1, wherein the step of performing signal conversion on the operation data by using a preset signal conversion algorithm to obtain an operation signal comprises:

3. The method for automatically analyzing performance of a capacitor based on voltage power according to claim 1, wherein the extracting the multi-modal characteristics of the operation signal by a preset multi-modal characteristic algorithm comprises:

4. The automated performance analysis method based on a low-voltage power capacitor according to claim 1, wherein the monitoring the power factor of the low-voltage power capacitor according to the multi-modal characteristics through a preset automated factor model comprises:

5. The automated performance analysis method based on a low-voltage power capacitor according to claim 1, wherein the determining the power quality of the low-voltage power capacitor according to the power factor index comprises:

6. The automated performance analysis method based on a low-voltage power capacitor according to claim 1, wherein the calculating the failure probability of the low-voltage power capacitor according to the multi-modal feature using a preset pattern matching algorithm comprises:

M＝(X _v ≥X _vmin )V(X _v ≤X _vmax )

7. The automated performance analysis method based on a low-voltage power capacitor according to claim 1, wherein the calculating a life index of the low-voltage power capacitor from the operation data by a time-series cyclic life model constructed in advance comprises:

8. The automated performance analysis method based on a low-voltage power capacitor according to claim 1, wherein the generating the performance visualization cloud for the low-voltage power capacitor according to the power factor, the power quality, the failure probability, and the life index comprises:

9. The method of claim 1, wherein the calculating the performance membership of the performance visualization cloud using a preset membership algorithm comprises:

10. A performance automatic analysis system based on a low-voltage power capacitor is characterized in that,