CN117951633B - Photovoltaic power generation equipment fault diagnosis method and system - Google Patents
Photovoltaic power generation equipment fault diagnosis method and system Download PDFInfo
- Publication number
- CN117951633B CN117951633B CN202410356092.0A CN202410356092A CN117951633B CN 117951633 B CN117951633 B CN 117951633B CN 202410356092 A CN202410356092 A CN 202410356092A CN 117951633 B CN117951633 B CN 117951633B
- Authority
- CN
- China
- Prior art keywords
- data
- power generation
- photovoltaic power
- generation equipment
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000003745 diagnosis Methods 0.000 title claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 87
- 230000008569 process Effects 0.000 claims abstract description 52
- 238000012098 association analyses Methods 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 238000007621 cluster analysis Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 230000033228 biological regulation Effects 0.000 claims abstract description 8
- 238000012423 maintenance Methods 0.000 claims description 25
- 230000006978 adaptation Effects 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 5
- 239000006185 dispersion Substances 0.000 claims description 5
- 230000001105 regulatory effect Effects 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 5
- 238000005192 partition Methods 0.000 claims description 4
- 230000006641 stabilisation Effects 0.000 claims description 4
- 238000011105 stabilization Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000013450 outlier detection Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims 1
- 239000013598 vector Substances 0.000 description 11
- 239000011159 matrix material Substances 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000010187 selection method Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000000540 analysis of variance Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a method and a system for diagnosing faults of photovoltaic power generation equipment, in particular relates to the technical field of diagnosis of the photovoltaic power generation equipment, and is used for solving the problem of inaccurate analysis of the switching state of the photovoltaic power generation equipment; the method comprises the steps of collecting operation data of the photovoltaic power generation equipment, preprocessing the operation data to obtain a stable operation data set and an abnormal switching data set, combining the two data sets, carrying out feature extraction and cluster analysis on the combined data sets, determining the association relation of data items in clusters, extracting new features of the data sets by using feature engineering based on the results of the cluster and the association analysis, finally, analyzing the state switching process of the photovoltaic power generation equipment through an established model, determining the abnormal condition during the state switching of the photovoltaic power generation equipment, and carrying out timely tracing regulation and control on equipment generating abnormal signals, thereby increasing the accuracy of identifying abnormal faults of the photovoltaic power generation equipment in the operation mode switching process and further improving the power generation efficiency.
Description
Technical Field
The invention relates to the technical field of photovoltaic power generation equipment diagnosis, in particular to a photovoltaic power generation equipment fault diagnosis method and system.
Background
A photovoltaic power generation apparatus is an apparatus that converts solar energy into electric energy using a photoelectric effect. The system is generally composed of a solar panel, an inverter, a support structure, a connecting line and the like, and fault diagnosis of photovoltaic power generation equipment is one of key links for maintenance and management of the photovoltaic power generation equipment, and is a necessary means for ensuring efficient operation and long-term stable power generation of a photovoltaic system along with wide application and popularization of photovoltaic power generation technology.
The prior art has the following defects:
The fault diagnosis of the photovoltaic power generation equipment is an important link for ensuring the stable operation and effective power generation of the photovoltaic system. However, the photovoltaic power generation device may undergo different state switching during operation, such as from a normal operation state to a maintenance mode, from full power generation to partial power generation, from an on-grid to an off-grid, etc., which may be affected by various factors, and relatively few analyses and diagnostics during the state switching process may result in some potential problems that may not be found and resolved in time during the system state switching, thereby affecting the stability and reliability of the photovoltaic power generation device.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, embodiments of the present invention provide a method and a system for diagnosing faults of a photovoltaic power generation device, which collect and process operation data of the photovoltaic power generation device, obtain a stable operation data set and an abnormal switching data set, combine the two data sets, perform feature extraction and cluster analysis, determine an association relationship of data items in a cluster, extract new features of the data sets by using feature engineering based on the results of the cluster and the association analysis, and finally determine abnormal conditions during state switching of the photovoltaic power generation device and perform timely tracing regulation and control by using an established model to solve the problems set forth in the background art.
In order to achieve the above purpose, the present invention provides the following technical solutions:
A fault diagnosis method of photovoltaic power generation equipment comprises the following steps:
Collecting operation data of the photovoltaic power generation equipment, preprocessing the collected data, taking the preprocessed operation data as a stable operation data set, and taking abnormal data in a state switching time interval of the photovoltaic power generation equipment as an abnormal switching data set;
Merging the steady operation data set and the abnormal switching data set, carrying out feature extraction and cluster analysis on the merged data set, dividing the data into different categories or clusters, carrying out association analysis on the cluster clusters to determine the association relation of data items in the clusters, and extracting new features of the data set by using feature engineering based on the results of the clustering and association analysis;
establishing a model according to the new characteristics of the combined data set, analyzing the operation state switching process of the photovoltaic power generation equipment through the model, and determining the abnormal condition of the data generated during the state switching of the photovoltaic power generation equipment;
And tracing and regulating the equipment generating the abnormal signal according to the analysis result during the state switching of the photovoltaic power generation equipment.
In a preferred embodiment, the collected data is preprocessed, and the preprocessed operation data is used as a stable operation data set, which specifically includes the following steps:
smoothing the data sequence of the collected operation data by using moving average filtering and removing noise;
starting at a starting point of the data sequence, selecting a data point of the first window as an initial window, and calculating an average of the data points as an initial output of the filter,
Sequentially moving the filter window backwards from an initial window of the data sequence, moving one data point each time, updating the data points in the window to the latest data at each new position, then recalculating the average value of the data points in the window, and taking the finally obtained output sequence as smooth data;
performing time alignment on the collected operation data by using interpolation processing or time stamp alignment;
And taking the preprocessed operation data as a stable operation data set.
In a preferred embodiment, the abnormal data in the state switching time interval of the photovoltaic power generation device is used as an abnormal switching data set, and the specific process is as follows:
detecting a state switching process by using a mutation point detection algorithm, and determining a time interval containing occurrence of state switching;
Performing anomaly detection on the monitored data points by using an outlier detection algorithm to determine anomaly data;
And in the state switching time interval, extracting the detected abnormal data, recording the time stamp and the numerical value of the abnormal data, and summarizing the time stamp and the numerical value as an abnormal switching data set.
In a preferred embodiment, a steady operation data set and an abnormal switching data set are combined, feature extraction and cluster analysis are carried out on the combined data set, the data is divided into different categories or clusters, association analysis is carried out on the clusters to determine the association relation of data items in the clusters, and based on the results of the clustering and the association analysis, new features of the data set are extracted by using feature engineering, wherein the specific process is as follows:
using Fourier transform to the combined data set, converting the time domain signals into frequency domain signals, calculating the energy spectrum density of the frequency domain signals, and determining the frequency domain characteristics of the data set;
and determining the time domain characteristics of the data set by using trend analysis, periodicity analysis and time interval on the combined data set.
In a preferred embodiment, the optimal number of clusters is selected using a partition clustering criterion, and the closeness of the clustering result is determined based on the sum of square errors of intra-group and inter-group dispersion;
After clustering, carrying out association analysis on each cluster, determining the relation among the clusters, calculating the support degree and the confidence coefficient of the association rule, and determining the rule through the support degree and the confidence coefficient;
and extracting new features of the data set by using feature engineering according to the clustering and association analysis results.
In a preferred embodiment, the data anomalies generated during the state switching of the photovoltaic power plant are determined by a model analysis of the photovoltaic power plant operating state switching process, the specific process being as follows:
Acquiring switching stability information of the photovoltaic power generation equipment during state switching, wherein the switching stability information comprises cooperative switching information and clustering fluctuation information;
The collaborative switching information comprises a state switching stability index, and the clustering fluctuation information comprises a hierarchical clustering adaptation index;
and calculating the acquired state switching stability index and hierarchical clustering adaptation index to acquire an operation state estimation coefficient, and comparing the generated operation state estimation coefficient with a maintenance threshold value to generate different signals.
In a preferred embodiment, the tracing regulation and control are performed on the device generating the abnormal signal according to the analysis result during the state switching of the photovoltaic power generation device, and the specific process is as follows:
Comparing the running state estimation coefficient with a maintenance threshold;
If the running state estimation coefficient is greater than or equal to the maintenance threshold value, generating a device switching state stabilization signal, and carrying out normal device running;
if the running state estimation coefficient is smaller than the maintenance threshold value, generating an equipment switching state abnormal signal, stopping the equipment operation and performing fault tracing and management.
A photovoltaic power generation equipment fault diagnosis system is used for the photovoltaic power generation equipment fault diagnosis method, and comprises the following steps:
the data set preprocessing module is used for acquiring the operation data of the photovoltaic power generation equipment, preprocessing the acquired data, taking the preprocessed operation data as a stable operation data set and taking the abnormal data in the state switching time interval of the photovoltaic power generation equipment as an abnormal switching data set;
The association feature extraction module is used for merging the steady operation data set and the abnormal switching data set, carrying out feature extraction and cluster analysis on the merged data set, dividing the data into different categories or clusters, carrying out association analysis on the cluster clusters to determine the association relation of data items in the clusters, and extracting new features of the data set by using feature engineering based on the results of the clustering and the association analysis;
The state switching determining module is used for establishing a model according to the new characteristics of the combined data set, analyzing the operation state switching process of the photovoltaic power generation equipment through the model, and determining the abnormal condition of the data generated during the state switching of the photovoltaic power generation equipment;
And the fault diagnosis module is used for performing traceable regulation and control on the equipment generating the abnormal signal according to the analysis result of the state switching period of the photovoltaic power generation equipment.
The invention has the technical effects and advantages that:
The method comprises the steps of collecting operation data of the photovoltaic power generation equipment, preprocessing the collected data to obtain a stable operation data set and an abnormal switching data set, merging the two data sets, carrying out feature extraction and cluster analysis on the merged data set, determining the association relation of data items in clusters, extracting new features of the data sets by using feature engineering based on the results of the cluster and the association analysis, finally, analyzing the state switching process of the photovoltaic power generation equipment through an established model, determining the abnormal condition during the state switching of the photovoltaic power generation equipment, and carrying out timely tracing regulation and control on equipment generating abnormal signals, thereby increasing the accuracy of identifying abnormal faults of the photovoltaic power generation equipment in the operation mode switching process and further improving the power generation efficiency.
Drawings
Fig. 1 is a flowchart of a fault diagnosis method for a photovoltaic power generation device according to the present invention.
Fig. 2 is a schematic structural diagram of a fault diagnosis system for photovoltaic power generation equipment according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment 1, as shown in fig. 1, a method for diagnosing faults of a photovoltaic power generation apparatus, the method comprising:
Collecting operation data of the photovoltaic power generation equipment, preprocessing the collected data, taking the preprocessed operation data as a stable operation data set, and taking abnormal data in a state switching time interval of the photovoltaic power generation equipment as an abnormal switching data set;
Merging the steady operation data set and the abnormal switching data set, carrying out feature extraction and cluster analysis on the merged data set, dividing the data into different categories or clusters, carrying out association analysis on the cluster clusters to determine the association relation of data items in the clusters, and extracting new features of the data set by using feature engineering based on the results of the clustering and association analysis;
establishing a model according to the new characteristics of the combined data set, analyzing the operation state switching process of the photovoltaic power generation equipment through the model, and determining the abnormal condition of the data generated during the state switching of the photovoltaic power generation equipment;
And tracing and regulating the equipment generating the abnormal signal according to the analysis result during the state switching of the photovoltaic power generation equipment.
The photovoltaic power generation equipment can be subjected to various different states in the operation process, and is in a normal power generation state under the condition of sufficient sunlight in the daytime, and solar energy is converted into electric energy to be supplied to a power grid or a load for use as the normal power generation state; when the system needs maintenance, maintenance or faults, the photovoltaic power generation equipment may need to be switched to a shutdown state, power generation is stopped, and corresponding maintenance work is performed, wherein the shutdown state is used; after the shutdown state, the system may need to be restarted to restore the photovoltaic power generation device to a normal operating state;
Grid-connected and off-grid states: the photovoltaic power generation equipment can be connected with a power grid (grid-connected state), the generated electric energy is transmitted into the power grid, and the photovoltaic power generation equipment can also independently operate without the power grid (off-grid state) to supply the electric energy to outdoor or independent load equipment;
Fault state: when the photovoltaic power generation equipment fails, the equipment possibly enters a failure state and needs to be diagnosed and repaired;
the switching between these states is typically controlled automatically by a system controller or monitoring system according to set conditions and policies, and may also be controlled and adjusted manually by an operator.
For example, the normal operation state is changed into the fault state to be used as a maintenance mode, and the grid-connected state is changed into the shutdown state, and the like, and the state switching is influenced by various factors including weather conditions, system loads, equipment faults and the like, so that the system performance is changed and the faults occur, namely, in the state switching process, the factors influencing the system performance are more complex, including the characteristics of the equipment, the change of external environment and the like;
Some common photovoltaic power generation devices, such as a photovoltaic panel, which is a device for converting sunlight into direct current electric energy, are composed of a plurality of photovoltaic cells, and are usually installed in photovoltaic power stations, roofs, solar chargers and the like for generating electricity, and are used for storing the electric energy generated by the photovoltaic panel through a battery energy storage system so as to continue to supply electricity at night or under low light conditions, and an inverter is a device for converting the direct current output by the photovoltaic panel into alternating current.
The operation data of the photovoltaic power generation equipment are collected in real time by using equipment such as a sensor, and the operation data of the photovoltaic power generation equipment, including power generation power, voltage, current, temperature and the like, are collected in real time. Preprocessing the acquired data, removing noise, interpolating, aligning the data and the like to ensure the quality and usability of the acquired data;
Noise is irregular fluctuation in data caused by factors such as sensor errors, environmental interference and the like, common methods for removing noise include filtering techniques, such as moving average filtering, median filtering and the like, smoothing a data sequence of collected operation data by using the moving average filtering and removing noise, and the specific steps are as follows:
the window size N of the moving average filter, i.e. the number of data points used to calculate the average, is determined and the choice of window size is typically dependent on the sampling frequency of the data and the desired degree of smoothness. A larger window may smooth more noise but may lead to hysteresis effects;
starting from the starting point of the data sequence, selecting the data point of the first window size as the initial window and calculating the average of these data points as the initial output of the filter, for the ith data point, calculating the moving average: In the above, the ratio of/> Values representing the i-j data points;
Sequentially moving the filtering window backwards from the first window of the data sequence, moving one data point each time, updating the data points in the window to the latest data at each new position, discarding the oldest data points, then recalculating the average value of the data points in the window, and repeating the step of calculating the average value, wherein the finally obtained output sequence is smooth data subjected to moving average filtering processing, so that the noise removing effect is realized;
Because the situation that sampling intervals are inconsistent or data are missing possibly exists in the data acquisition process, interpolation processing is needed to fill the missing data or smooth processing is needed to be carried out on the data, and common interpolation methods comprise linear interpolation, polynomial interpolation, spline interpolation and the like;
Because sampling frequencies of different sensors may be inconsistent or have time deviation, time alignment needs to be performed on collected operation data to ensure the consistency of the data in time, and the time alignment of the data is realized through methods such as interpolation processing or time stamp alignment.
Taking the preprocessed operation data as a stable operation data set, wherein the data in the stable operation data set represent data acquired by the photovoltaic power generation equipment during operation;
Determining the stage of abnormal data when the operation data of the photovoltaic power generation equipment are acquired and acquiring the abnormal data in a switching time interval when the operation data are in the state switching time interval of the photovoltaic power generation equipment;
the state switching process is detected by using a mutation point detection algorithm, such as a first order difference based method, If/>If the absolute value of (i) is greater than a preset threshold value, i represents the point position of the data, if the state switching is considered to occur, determining a time interval containing the occurrence of the state switching, detecting abnormal data of the monitored data, and using an outlier detection algorithm, such as a method based on the 3 sigma principle,/>, for example，/>N is the number of data points collected,/>，/>If data points/>If the data point exceeds up or is lower than down, the data point is considered to be abnormal data, the detected abnormal data is extracted in a state switching time interval, and the time stamp and the numerical value of the detected abnormal data are recorded and used as an abnormal switching data set.
The combined analysis of the stable operation data set and the abnormal switching data set can help understand the operation characteristics of the photovoltaic power generation equipment in different states and the abnormal data conditions in the state switching process, and the following steps are carried out:
combining the steady operation data set and the abnormal switching data set to form a complete data set, wherein the complete data set is used as a combined data set, and the combined data set is ensured to contain information such as a time stamp, collected various parameter data, abnormal identification (whether the data are abnormal data) and the like;
And extracting the characteristics of the combined data set, wherein the data characteristic extraction is to extract representative and distinguishing characteristics from the original data so as to be used for subsequent tasks such as data analysis, model establishment and the like. In the data analysis of the photovoltaic power generation equipment, the process of extracting data features involves extracting features related to system states, performances and the like from a stable operation data set and an abnormal switching data set, and proper feature types are selected according to the requirements of problems and the properties of the data, in the data analysis of the photovoltaic power generation equipment, common feature types comprise statistical features, frequency domain features, time domain features and the like, the statistical features are features describing the statistical properties of the data and comprise mean values, variances, standard deviations, maximum values, minimum values, median values, skewness, kurtosis and the like, and the distribution and concentration degree of the data can be determined by calculating the statistical features, for example, the mean values and standard deviations of a data sequence x= [ x1, x2, the term xn ] can be calculated;
The frequency domain features are features obtained by performing fourier transform or wavelet transform on the data and are used for describing the characteristics of the data on the frequency domain, common frequency domain features comprise frequency spectrum energy, frequency distribution, power spectrum density and the like, one or more frequency domain feature analysis methods are selected to determine the data features, for example, fourier transform can be used for converting a time domain signal into a frequency domain signal, and then the energy spectrum density of the frequency domain signal is calculated, so that the energy changes of different frequency components in the photovoltaic power generation equipment can be monitored to evaluate the performance difference of the system under different working states.
The time domain features are features extracted directly for time sequence data and are used for describing dynamic changes and trends of the data. Common time domain features include trend analysis, periodicity analysis, time intervals, etc., for example, the slope, rate of change, periodicity, etc. of the data may be calculated to describe the trend and regularity of the data;
after a large number of features are extracted, the feature selection method may be used to select the most representative and distinguishing features. Common feature selection methods include analysis of variance, correlation coefficient analysis, principal component analysis, and the like, and then, the extracted features are subjected to normalization processing to eliminate dimensional differences and size differences between different features, so that the features have the same scale and weight.
And carrying out cluster analysis on the combined data set by using a clustering algorithm, dividing the data into different categories or clusters, and using an unsupervised learning algorithm such as K-means clustering, hierarchical clustering and the like.
Using a criterion function to evaluate the optimized clustering result, selecting the optimal clustering number, and using a partition clustering criterion to analyze;
In the partition clustering criterion, based on Sum of Square Error (SSE) of intra-group dispersion and inter-group dispersion or variation thereof, the criterion function measures the compactness of the clustering result, namely, the smaller the distance between data points in the group is, the smaller the SSE value is, the better the clustering result is, and the specific formula is: where k is the number of clusters,/> Is the data point set of the ith cluster,/>Is the center point of the i-th cluster,
Using a method for maximizing the inter-class variance as a criterion function, wherein the method for maximizing the inter-class variance is used for the condensed hierarchical clustering, and the inter-class variance is maximized as follows: where μ is the mean vector of the overall dataset.
After clustering, carrying out association analysis on each cluster to find the association relation between data items in the clusters, determining the characteristics of each cluster and the relation between members, and analyzing the support degree and the confidence degree of association rules, wherein the support degree represents the occurrence frequency of the rules, and the confidence degree represents the occurrence probability of conclusions under the condition of occurrence. The importance and confidence of the rules may be evaluated by the support and confidence to determine common patterns and associations between steady operation data and abnormal switching data, e.g., whether certain particular steady operation data may result in the occurrence of abnormal switching data.
Based on the results of the previous clustering and association analysis, feature engineering is carried out, relevant features are extracted or new features are built for describing the features of the data, the performance of the model can be improved by selecting and building proper features, the good features can better capture the mode and rule of the data, the model can more accurately predict the state switching or abnormal data classification in the future, the dimension of the data can be reduced, the influence of redundant information and noise is reduced, the complexity of the model is simplified, the generalization capability of the model is improved, the training and prediction speed of the model is accelerated, and the efficiency of the model is improved;
And establishing a model according to the obtained new characteristics of the data set, dividing the combined data set into a training set, a verification set and a test set, training the selected model by using the training set, and adjusting the mode and the relation among the learning data by using a supervised learning algorithm, such as a decision tree and a support vector machine, during the training process, adjusting the fault analysis model by using the verification set and adjusting the super-parameters or the characteristic selection strategy of the model.
According to the established fault analysis model, the operation state switching process of the photovoltaic power generation equipment is analyzed, and the specific steps are as follows:
analyzing data generated before and after the operation state switching process of the photovoltaic power generation equipment, and determining whether the data generated during the state (mode) switching of the photovoltaic power generation equipment are abnormal or not, namely acquiring switching stability information during the state switching of the photovoltaic power generation equipment, wherein the switching stability information comprises cooperative switching information and clustering fluctuation information;
The collaborative switching information comprises a state switching stability index and is calibrated to ZTQ, and the clustering fluctuation information comprises a hierarchical clustering adaptation index and is calibrated to CCJ;
The state switching stability index in the collaborative switching information is used for indicating the stability degree of the photovoltaic power generation equipment in the switching process, the state switching stability index is obtained by monitoring and analyzing parameters in the switching process, the lower stability index indicates that the stability of the photovoltaic power generation equipment in the switching mode is poor, the equipment state is unstable or abnormal easily exists, the higher state switching stability index indicates that the stability of the equipment in the switching mode is better, the switching process is smoothly carried out, and the state switching stability index has an effect on the following aspects:
Energy loss: the unstable or abnormal state of the equipment in the switching process can cause energy loss, the energy utilization efficiency of the photovoltaic power generation system is affected, the problem of unstable state of the equipment can be found and solved in time by monitoring and analyzing the state switching stability index in the switching process, and the energy loss is reduced;
Maintenance requirements: the equipment state is unstable or abnormal and can need extra maintenance and repair work, the maintenance cost and the downtime are increased, the maintenance requirement of the equipment can be reduced, the maintenance cost and the downtime are reduced by improving the stability in the switching process, the safety of the photovoltaic power generation system can be influenced by the equipment state is unstable or abnormal, the safety risk is increased, the safety of equipment and personnel can be guaranteed by the stable switching process, the fault equipment can be timely processed, and the occurrence probability of safety accidents is reduced.
The state switching stability index is obtained by the following steps:
acquiring data generated by the predicted switching state of the photovoltaic power generation equipment and actually generated data, acquiring the quantity SL and switching time of the photovoltaic power generation equipment related to the switching state, determining the switching time period of the photovoltaic power generation equipment, namely the switching starting and ending time points, acquiring an actually generated data value vector SJ and a model predicted data value vector YC for each switching time period, calculating a state switching value, and calculating the expression as follows: Num represents the total number of switching periods, and the predicted data value vector average/> And the vector mean of the data values actually generated/>And calculating a relevant consistent value, wherein the calculation expression is as follows: /(I)Calculating a state switching stability index, wherein the calculation expression is as follows: /(I)。
It should be noted that, the data generated by the switching state of the photovoltaic power generation device may include key parameters (such as voltage, current, power output, temperature, etc.) in the switching process, different parameter setting ranges are provided between different switching modes, the processed data are organized into a matrix or a data frame according to time sequence, wherein each column represents a key parameter, each row represents a time point, so that the key parameter data in the switching process can be converted into a matrix with an actual value, and each column of data in the matrix is extracted to be combined into a vector. Each vector element corresponds to an actual value of a key parameter at a certain point in time. For example, if there are m key parameters, each of which has n time points, a matrix of m×n can be formed, each column is extracted to form m vectors, each vector contains the actual values of the parameter at all time points, and the vectors are combined together to form a vector of actual values.
The hierarchical clustering adaptation index in the clustering fluctuation information represents the clustering adaptation degree on the data set, the purity of the clustering result and the consistency with the real label are represented, the hierarchical clustering adaptation index reflects the purity of the clustering result generated by the hierarchical clustering algorithm on the given data set and the consistency with the real label, the higher the value of the index is, the better the hierarchical clustering algorithm is represented on the data set, the generated clustering result is pure and consistent with the real label, and the hierarchical clustering adaptation index has an effect on the following aspects:
The hierarchical clustering adaptation index provides comprehensive evaluation of the clustering result, not only considers the purity of the clustering result, but also considers the consistency with the real label, and the performance of the hierarchical clustering algorithm on a given data set can be judged by evaluating the size of the index, so that whether the clustering result is reliable or not is determined.
The accuracy of the fault diagnosis of the photovoltaic power generation equipment is affected by a clustering algorithm, the hierarchical clustering adaptation index can be used as an evaluation index to help determine the effect of the hierarchical clustering algorithm on the fault diagnosis, further guide the subsequent improvement and optimization work, and the photovoltaic power generation equipment has multiple fault modes which possibly correspond to different clustering results. By analyzing hierarchical clustering adaptation indexes, which fault modes can be well identified by a clustering algorithm can be identified, so that the establishment of a fault diagnosis strategy is guided.
The hierarchical clustering adaptation index is obtained by the following steps:
Constructing a pair comparison matrix, obtaining the consistent sample number a and the inconsistent sample pair number b in the pair comparison matrix, and calculating to obtain a consistency measurement value: ，/> And (3) representing the number of all possible samples formed by selecting two samples from n samples, comparing each cluster in the clustering result with each category in the real label to obtain the category most similar to each cluster, counting the number of samples of the same category in the category of the real label most similar to each cluster, and calculating to obtain a purity value, wherein the calculation expression is as follows: /(I) N is the total number of samples in the dataset,/>Is the set of samples in the kth cluster,/>The method is a sample set of the j-th category in the real label, and is used for calculating hierarchical clustering adaptation indexes, wherein the calculation expression is as follows: /(I)。
It should be noted that, the rows and columns of the matrix respectively correspond to the samples in the dataset, the elements of the matrix represent the relationship between pairs of samples, if two samples belong to the same cluster and belong to the same category in the real label, the value of the element is 1, otherwise, 0, a consistent pair of samples refers to a pair of samples belonging to the same cluster in both the clustering result and the real label, and an inconsistent pair of samples refers to a pair of samples belonging to different clusters in both the clustering result and the real label.
The operation state estimation coefficient is obtained after the obtained state switching stability index ZTQ and the hierarchical clustering adaptation index CCJ are comprehensively calculated, and the expression is as follows: In the above, the ratio of/> For running state estimation coefficient,/>、/>Preset proportionality coefficients for state switching stability index ZTQ and hierarchical clustering adaptation index CCJ, and/>、/>Are all greater than 0.
It should be noted that, the size of the preset scaling factor is a specific numerical value obtained by quantizing each parameter, and in order to facilitate the subsequent comparison, the size of the scaling factor depends on the number of sample data and the person skilled in the art to initially set a corresponding preset scaling factor for each group of sample data; and the method is not unique, and the proportional relation between the parameter and the quantized numerical value is not influenced, as is the proportional relation between the state switching stability index and the running state estimation coefficient.
The larger the state switching stability index is, the larger the hierarchical clustering adaptation index is, namely the larger the expression value of the running state estimation coefficient is, which indicates that the more stable the photovoltaic power generation equipment is in the state switching process, the more consistent the overall parameter fluctuation and the expected of the photovoltaic power generation equipment in the state switching process are, the more stable and stable the state switching is, and the more accurate the data feature classification is;
The smaller the state switching stability index and the smaller the hierarchical clustering adaptation index, namely the smaller the expression value of the operation state estimation coefficient, the worse the stability of the photovoltaic power generation equipment in the state switching process is indicated. This means that the more easily the device is subject to larger fluctuations or instabilities during the switching process, the more likely it is to cause problems such as reduced device performance, increased energy loss, reduced system reliability, etc. Therefore, smaller running state estimation coefficient values suggest a need for further attention and improvement of the stability of the plant during state switching to ensure proper operation and performance optimization of the photovoltaic power generation system.
Comparing the generated running state estimation coefficient with a maintenance threshold value, generating different regulating signals, and correspondingly adjusting according to the generated regulating signals;
After the running state estimation coefficient is obtained, comparing the running state estimation coefficient with a maintenance threshold;
If the running state estimation coefficient is greater than or equal to the maintenance threshold value, generating a device switching state stabilization signal, wherein the device switching state stabilization signal indicates that the state of the photovoltaic power generation device is stable after the photovoltaic power generation device is switched to a mode, and the signal can be used for indicating an operator or an automation system to perform the next operation or scheduling;
If the running state estimation coefficient is smaller than the maintenance threshold value, generating an equipment switching state abnormal signal, wherein the abnormal signal indicates that the photovoltaic power generation equipment is inconsistent with the expected state in the mode switching process, and the abnormal or unstable condition to a certain extent exists, which may be caused by the fact that the equipment itself has faults or damages, so that the running state is abnormal, the equipment needs to be overhauled or maintained in time, or the equipment is abnormal due to factors such as external environment changes or bad weather, and the like, and sending an early warning to related maintenance personnel.
After the abnormal signal of the switching state of the equipment is received, corresponding measures are timely taken to ensure the normal and stable operation of the photovoltaic power generation equipment, for example, a real-time monitoring system is immediately started to monitor and diagnose each key parameter of the photovoltaic power generation equipment in real time so as to determine the specific reason and the influence range of the abnormality, if serious faults or potential safety hazards exist in the equipment, an emergency shutdown program is immediately started to stop the operation of the equipment so as to prevent further damage or accidents, corresponding fault elimination measures are taken for the fault reason determined by the diagnosis result, damaged parts are repaired or replaced, the normal operation of the equipment is recovered, detailed information of the abnormal events including occurrence time, abnormal phenomena, treatment measures and the like is recorded, deep analysis and summary are carried out, and references are provided for future fault prevention and improvement.
It should be noted that, the setting of the maintenance threshold may be determined according to a specific scenario and requirement, and is generally adjusted and optimized according to factors such as historical data and performance indexes.
According to the invention, the operation data of the photovoltaic power generation equipment is collected, the collected data is preprocessed to obtain a stable operation data set and abnormal data which are used as an abnormal switching data set, then the stable operation data set and the abnormal switching data set are combined, the combined data set is subjected to feature extraction and cluster analysis to determine the association relation of data items in clusters, based on the result of the cluster and association analysis, new features of the data sets are extracted by using feature engineering, finally, the abnormal condition of the data generated during the state switching of the photovoltaic power generation equipment is determined by analyzing the operation state switching process of the photovoltaic power generation equipment through a model, and the equipment for generating abnormal signals is subjected to timely tracing regulation, so that the accuracy of identifying abnormal faults of the photovoltaic power generation equipment in the operation mode switching process is improved, and the power generation efficiency is further improved.
Embodiment 2, which is a system embodiment of embodiment 1, is configured to implement a method for diagnosing a fault of a photovoltaic power generation device described in embodiment 1, as shown in fig. 2, and specifically includes:
the data set preprocessing module is used for acquiring the operation data of the photovoltaic power generation equipment, preprocessing the acquired data, taking the preprocessed operation data as a stable operation data set and taking the abnormal data in the state switching time interval of the photovoltaic power generation equipment as an abnormal switching data set;
The association feature extraction module is used for merging the steady operation data set and the abnormal switching data set, carrying out feature extraction and cluster analysis on the merged data set, dividing the data into different categories or clusters, carrying out association analysis on the cluster clusters to determine the association relation of data items in the clusters, and extracting new features of the data set by using feature engineering based on the results of the clustering and the association analysis;
The state switching determining module is used for establishing a model according to the new characteristics of the combined data set, analyzing the operation state switching process of the photovoltaic power generation equipment through the model, and determining the abnormal condition of the data generated during the state switching of the photovoltaic power generation equipment;
And the fault diagnosis module is used for performing traceable regulation and control on the equipment generating the abnormal signal according to the analysis result of the state switching period of the photovoltaic power generation equipment.
The above formulas are all formulas for removing dimensions and taking numerical calculation, and specific dimensions can be removed by adopting various means such as standardization, and the like, which are not described in detail herein, wherein the formulas are formulas for acquiring a large amount of data and performing software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, ATA hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state ATA hard disk.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application 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 foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (2)
1. The fault diagnosis method for the photovoltaic power generation equipment is characterized by comprising the following steps of:
Collecting operation data of the photovoltaic power generation equipment, preprocessing the collected data, taking the preprocessed operation data as a stable operation data set, and taking abnormal data in a state switching time interval of the photovoltaic power generation equipment as an abnormal switching data set;
Merging the steady operation data set and the abnormal switching data set, carrying out feature extraction and cluster analysis on the merged data set, dividing the data into different categories or clusters, carrying out association analysis on the cluster clusters to determine the association relation of data items in the clusters, and extracting new features of the data set by using feature engineering based on the results of the clustering and association analysis;
establishing a model according to the new characteristics of the combined data set, analyzing the operation state switching process of the photovoltaic power generation equipment through the model, and determining the abnormal condition of the data generated during the state switching of the photovoltaic power generation equipment;
according to the analysis result of the state switching period of the photovoltaic power generation equipment, tracing and regulating the equipment generating the abnormal signal;
Preprocessing the acquired data, taking the preprocessed operation data as a stable operation data set, wherein the specific process is as follows:
smoothing the data sequence of the collected operation data by using moving average filtering and removing noise;
starting at a starting point of the data sequence, selecting a data point of the first window as an initial window, and calculating an average of the data points as an initial output of the filter,
Sequentially moving the filter window backwards from an initial window of the data sequence, moving one data point each time, updating the data points in the window into the latest data at each new position, recalculating the average value of the data points in the window, and taking the finally obtained average value output sequence as smooth data;
performing time alignment on the collected operation data by using interpolation processing or time stamp alignment;
Taking the preprocessed operation data as a stable operation data set;
The abnormal data in the state switching time interval of the photovoltaic power generation equipment is used as an abnormal switching data set, and the specific process is as follows:
Detecting a state switching process of the photovoltaic power generation equipment by using a mutation point detection algorithm, and determining a time interval containing occurrence of state switching;
Performing anomaly detection on the monitored data points by using an outlier detection algorithm to determine anomaly data;
Extracting the detected abnormal data in the state switching time interval, recording the time stamp and the numerical value of the abnormal data, and summarizing the time stamp and the numerical value as an abnormal switching data set;
Merging the steady operation data set and the abnormal switching data set, carrying out feature extraction and cluster analysis on the merged data set, dividing the data into different categories or clusters, carrying out association analysis on the cluster clusters to determine the association relation of data items in the clusters, and extracting new features of the data set by using feature engineering based on the results of the cluster and the association analysis, wherein the specific process is as follows:
using Fourier transform to the combined data set, converting the time domain signals into frequency domain signals, calculating the energy spectrum density of the frequency domain signals, and determining the frequency domain characteristics of the data set;
Using trend analysis, periodic analysis and time interval to the combined data set to determine the time domain characteristics of the data set;
Further comprises:
Selecting the optimal cluster number by using a partition clustering criterion, and determining the compactness of a clustering result based on the sum of square errors of intra-group dispersion and inter-group dispersion;
After clustering, carrying out association analysis on each cluster, determining the relation among the clusters, calculating the support degree and the confidence coefficient of the association rule, and determining the rule through the support degree and the confidence coefficient;
Extracting new features of the data set by using feature engineering according to the clustering and association analysis results;
analyzing the operation state switching process of the photovoltaic power generation equipment through a model, and determining the abnormal condition of data generated during the state switching of the photovoltaic power generation equipment, wherein the specific process is as follows:
Acquiring switching stability information of the photovoltaic power generation equipment during state switching, wherein the switching stability information comprises cooperative switching information and clustering fluctuation information;
The collaborative switching information comprises a state switching stability index, and the clustering fluctuation information comprises a hierarchical clustering adaptation index;
Calculating the acquired state switching stability index and hierarchical clustering adaptation index to acquire an operation state estimation coefficient, and comparing the generated operation state estimation coefficient with a maintenance threshold value to generate different signals;
according to the analysis result of the state switching period of the photovoltaic power generation equipment, the equipment generating the abnormal signal is subjected to traceability regulation and control, and the specific process is as follows:
Comparing the running state estimation coefficient with a maintenance threshold;
If the running state estimation coefficient is greater than or equal to the maintenance threshold value, generating a device switching state stabilization signal, and carrying out normal device running;
if the running state estimation coefficient is smaller than the maintenance threshold value, generating an equipment switching state abnormal signal, stopping the equipment operation and performing fault tracing and management.
2. A photovoltaic power generation equipment fault diagnosis system, characterized by comprising: the system comprises a data set preprocessing module, a correlation characteristic extraction module, a state switching determination module and a fault diagnosis module, wherein the data set preprocessing module is used for realizing the fault diagnosis method of the photovoltaic power generation equipment in claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410356092.0A CN117951633B (en) | 2024-03-27 | 2024-03-27 | Photovoltaic power generation equipment fault diagnosis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410356092.0A CN117951633B (en) | 2024-03-27 | 2024-03-27 | Photovoltaic power generation equipment fault diagnosis method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117951633A CN117951633A (en) | 2024-04-30 |
| CN117951633B true CN117951633B (en) | 2024-06-11 |
Family
ID=90799850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410356092.0A Active CN117951633B (en) | 2024-03-27 | 2024-03-27 | Photovoltaic power generation equipment fault diagnosis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117951633B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10826428B1 (en) * | 2019-12-06 | 2020-11-03 | King Abdulaziz University | Monitoring and fault detection method and system for photovoltaic plants |
| CN113888353A (en) * | 2021-09-29 | 2022-01-04 | 华能(浙江)能源开发有限公司清洁能源分公司 | Energy efficiency diagnosis method, system and medium for distributed photovoltaic power generation equipment |
| CN115496153A (en) * | 2022-09-26 | 2022-12-20 | 福州大学 | Multi-head self-attention deep convolution embedded clustering wind-light-load combined scene method |
| CN115822887A (en) * | 2022-12-05 | 2023-03-21 | 中国华能集团清洁能源技术研究院有限公司 | Performance evaluation and energy efficiency diagnosis method and system of wind turbine generator |
| CN116187027A (en) * | 2023-01-09 | 2023-05-30 | 广西桂冠电力股份有限公司 | Intelligent prediction and early warning method and system for photovoltaic power generation faults |
| CN116432006A (en) * | 2023-05-04 | 2023-07-14 | 国网河南省电力公司安阳供电公司 | Photovoltaic grid-connected inverter fault diagnosis method based on CEEMDAN-SE-IHHO-LSTM model |
| CN117171657A (en) * | 2023-08-22 | 2023-12-05 | 华能托里风力发电有限公司 | Wind power generation equipment fault diagnosis method and device, electronic equipment and storage medium |
| CN117318614A (en) * | 2023-10-07 | 2023-12-29 | 冯志宏 | Photovoltaic inverter fault prediction method |
| CN117764547A (en) * | 2022-09-15 | 2024-03-26 | 阿特斯阳光电力集团股份有限公司 | Photovoltaic string fault diagnosis method and system |
-
2024
- 2024-03-27 CN CN202410356092.0A patent/CN117951633B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10826428B1 (en) * | 2019-12-06 | 2020-11-03 | King Abdulaziz University | Monitoring and fault detection method and system for photovoltaic plants |
| CN113888353A (en) * | 2021-09-29 | 2022-01-04 | 华能(浙江)能源开发有限公司清洁能源分公司 | Energy efficiency diagnosis method, system and medium for distributed photovoltaic power generation equipment |
| CN117764547A (en) * | 2022-09-15 | 2024-03-26 | 阿特斯阳光电力集团股份有限公司 | Photovoltaic string fault diagnosis method and system |
| CN115496153A (en) * | 2022-09-26 | 2022-12-20 | 福州大学 | Multi-head self-attention deep convolution embedded clustering wind-light-load combined scene method |
| CN115822887A (en) * | 2022-12-05 | 2023-03-21 | 中国华能集团清洁能源技术研究院有限公司 | Performance evaluation and energy efficiency diagnosis method and system of wind turbine generator |
| CN116187027A (en) * | 2023-01-09 | 2023-05-30 | 广西桂冠电力股份有限公司 | Intelligent prediction and early warning method and system for photovoltaic power generation faults |
| CN116432006A (en) * | 2023-05-04 | 2023-07-14 | 国网河南省电力公司安阳供电公司 | Photovoltaic grid-connected inverter fault diagnosis method based on CEEMDAN-SE-IHHO-LSTM model |
| CN117171657A (en) * | 2023-08-22 | 2023-12-05 | 华能托里风力发电有限公司 | Wind power generation equipment fault diagnosis method and device, electronic equipment and storage medium |
| CN117318614A (en) * | 2023-10-07 | 2023-12-29 | 冯志宏 | Photovoltaic inverter fault prediction method |
Non-Patent Citations (2)
| Title |
|---|
| 基于滑动标准差计算的光伏阵列异常数据清洗办法;时珉;尹瑞;胡傲宇;吴骥;;电力***保护与控制;20200316(第06期);全文 * |
| 混合聚类分析算法在发电设备故障模式识别中的应用;王娜;李号彩;张德利;;电力信息与通信技术;20171215(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117951633A (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742053B (en) | Wind turbine generator set abnormity identification method and device | |
| CN111669123B (en) | Method and device for fault diagnosis of photovoltaic string | |
| CN111639921A (en) | Intelligent equipment fault judgment and auxiliary disposal method based on expert system | |
| CN114580666A (en) | Multi-mode fusion motor intelligent maintenance system | |
| CN113239132A (en) | Online out-of-tolerance identification method for voltage transformer | |
| Abbasi et al. | Development of predictive maintenance interface using multiple linear regression | |
| CN111275295A (en) | Distributed photovoltaic fault diagnosis method based on inverse distance weight interpolation | |
| Huang et al. | Wind turbine health assessment framework based on power analysis using machine learning method | |
| CN114487705A (en) | Power grid equipment fault positioning detection method | |
| CN117728587A (en) | Real-time monitoring system and method for operation data of new energy power generation equipment | |
| CN117408162A (en) | Power grid fault control method based on digital twin | |
| CN117674249A (en) | Distributed photovoltaic-containing power distribution network fault self-healing control and evaluation method | |
| CN117331790A (en) | Machine room fault detection method and device for data center | |
| Liu et al. | Hierarchical context-aware anomaly diagnosis in large-scale PV systems using SCADA data | |
| CN117494009A (en) | Electrical equipment state evaluation method based on insulating material pyrolysis analysis and cloud platform | |
| CN117951633B (en) | Photovoltaic power generation equipment fault diagnosis method and system | |
| CN116720983A (en) | Power supply equipment abnormality detection method and system based on big data analysis | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN117131321A (en) | Electric energy data acquisition method | |
| CN117074852A (en) | Power distribution network electric energy monitoring and early warning management method and system | |
| CN113435228A (en) | Motor bearing service life prediction and analysis method based on vibration signal modeling | |
| CN114400776B (en) | Digital mirror image-based substation automation equipment state diagnosis method and system | |
| CN117808456B (en) | Equipment fault early warning method and device based on intelligent operation management | |
| CN115711206B (en) | Wind driven generator blade icing state monitoring system based on clustering weight | |
| CN113806495B (en) | Outlier machine detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |