CN112232366A - Electrical equipment fault early warning method and system based on RFID monitoring - Google Patents
Electrical equipment fault early warning method and system based on RFID monitoring Download PDFInfo
- Publication number
- CN112232366A CN112232366A CN202010941484.5A CN202010941484A CN112232366A CN 112232366 A CN112232366 A CN 112232366A CN 202010941484 A CN202010941484 A CN 202010941484A CN 112232366 A CN112232366 A CN 112232366A
- Authority
- CN
- China
- Prior art keywords
- early warning
- fault early
- warning information
- time
- temperature data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 74
- 238000013528 artificial neural network Methods 0.000 claims abstract description 41
- 230000015654 memory Effects 0.000 claims abstract description 38
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 230000006870 function Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 230000000737 periodic effect Effects 0.000 claims description 6
- 230000002159 abnormal effect Effects 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000012937 correction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005672 electromagnetic field Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013021 overheating Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K1/00—Details of thermometers not specially adapted for particular types of thermometer
- G01K1/02—Means for indicating or recording specially adapted for thermometers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/28—Testing of electronic circuits, e.g. by signal tracer
- G01R31/302—Contactless testing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Testing Electric Properties And Detecting Electric Faults (AREA)
Abstract
The invention relates to an electrical equipment fault early warning method and system based on RFID monitoring, and the method specifically comprises the following steps: acquiring a time sequence temperature data set of the electrical equipment through an RFID temperature acquisition system, preprocessing the time sequence temperature data set, inputting a trained denoising self-coding network and a long-time and short-time memory neural network, respectively obtaining first fault early warning information and first prediction fault early warning information, and inputting a trained Xgboost model to obtain a fault early warning grade; the method comprises the steps of obtaining historical time sequence temperature data of the electrical equipment and corresponding historical fault early warning information, preprocessing the historical time sequence temperature data, using the preprocessed historical time sequence temperature data and the corresponding historical fault early warning information as a training set by a denoising self-coding network and a long-time and short-time memory neural network, and using the historical fault early warning information and the corresponding fault early warning grade as the training set by an Xgboost model. Compared with the prior art, the method has the advantages of avoiding overfitting, being high in precision and the like.
Description
Technical Field
The invention relates to an electrical equipment monitoring technology, in particular to an electrical equipment fault early warning method and system based on RFID monitoring.
Background
In the power system, the safe and stable operation of the power equipment is the basis for the stability of the power system. However, in an actual power system, various factors such as loose connection of electrical equipment, poor contact, magnetic flux leakage, overcurrent and the like can cause equipment overheating and cause equipment failure. Temperature detection is therefore one of the main ways to determine whether an electrical device is abnormal. Aiming at the power equipment temperature detection system based on the ultrahigh frequency radio frequency identification technology, the abnormal trend identification of the time sequence temperature data is realized by utilizing the power equipment temperature time sequence data obtained by system detection and fusing the deep learning technology, so that the prediction and early warning of the power equipment fault are realized.
The temperature acquisition data of the power equipment temperature acquisition system based on the RFID technology has the following problems: due to collision among multiple tags and multiple readers, abnormal data such as data point missing, data dislocation and the like exist in the data set; the RFID realizes data communication and transmission based on reverse electromagnetic waves, the working environment of the power equipment in an actual scene is complex, and the electromagnetic field in the external environment interferes with data transmission to generate data noise; when the RFID equipment is in failure, temperature data is lacked in a long time scale, and the change trend is abnormal. The temperature data has obvious time sequence characteristics, the prediction of the time sequence data is realized by adopting a Recurrent Neural Network (RNN), a Convolutional Neural Network (CNN) or a long-time memory neural network (LSTM) in the prediction of the time sequence data, and based on the characteristics, the problems of overfitting, low prediction precision and the like are easily caused by the traditional method applying the RNN, CNN and LSTM technologies.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, and provides an electrical equipment fault early warning method and system based on RFID monitoring, which avoid over-fitting and have high precision.
The purpose of the invention can be realized by the following technical scheme:
an electrical equipment fault early warning method based on RFID monitoring specifically comprises the following steps:
the method comprises the steps of acquiring a time sequence temperature data set of the electrical equipment in real time through an RFID temperature acquisition system and preprocessing the time sequence temperature data set, inputting the preprocessed time sequence temperature data set into a trained denoising self-coding network and a long-time memory neural network, respectively obtaining first fault early warning information and first predicted fault early warning information, inputting the first fault early warning information and the second fault early warning information into a trained Xgboost model, obtaining a fault early warning grade, realizing fault prediction and early warning of the electrical equipment, avoiding greater economic loss of the electrical equipment due to sudden faults, and having high prediction precision.
The method comprises the steps that historical time sequence temperature data of electrical equipment and corresponding historical fault early warning information are obtained, the historical time sequence temperature data are preprocessed, and the denoising self-coding network and the long-time and short-time memory neural network are trained by taking the preprocessed historical time sequence temperature data and the corresponding historical fault early warning information as training sets;
the fault early warning information corresponding to the historical time sequence temperature data is divided into a plurality of fault early warning levels according to severity, the Xgboost model takes the historical fault early warning information and the corresponding fault early warning levels as a training set, a meta learner is obtained after the training set is summarized, and the fault early warning levels are comprehensively judged according to the first fault early warning information and the second fault early warning information, so that the precision is high.
Further, the preprocessing corrects the time sequence temperature data set through an adjacent propagation clustering algorithm, and the process specifically comprises the following steps:
301) integrating each temperature sequence T in a time series temperature data setN＝{L1,L2,…,LNEqually dividing into X periodic sequences
L is a temperature value, r is an element of [1, X ]]Each of
Are all a-dimensional sequences, each calculated
Temperature trend series of
Wherein,
302) each will be
Forming K by AP clusteringrThe cluster center of the ith cluster is recorded as Vi，i∈[1，kr],i＝N+；
303) Calculate each
Is/are as follows
And each ViSimilarity sim ofn,i，simn,i∈[0,1]；
304) Determining
Regarding the membership degree of each population, the population with the largest membership degree is taken as the population
A population of affiliates;
305) setting a membership threshold value as in the population
Is less than a membership threshold
The outliers are identified and corrected.
Furthermore, a newly obtained time sequence temperature data set, first fault early warning information and second fault early warning information are merged into a training set of the denoising self-coding network and the long-time and short-time memory neural network, and the denoising self-coding network and the long-time and short-time memory neural network are trained by utilizing the new training set;
and merging the newly obtained first fault early warning information, second fault early warning information and fault early warning grade into a training set of the Xgboost model, training the Xgboost model by using the new training set, so that the denoising self-coding network, the long-time and short-time memory neural network and the Xgboost model can realize feedback correction, and parameters are continuously corrected to improve the prediction precision.
Further, the self-coding network, the long-time and short-time memory neural network and the Xgboost model are trained by adopting a symmetric embedded metric learning method, and the formula of a trained loss function J is as follows:
wherein lmn∈{0,1}，(xm,xn) For a sample pair, h (x) max (0, x) is the cross-over loss function, α1As a penalty term, α1Is a constant, d (x)m,xn) Is (x)m,xn) F (x) is the feature extracted for sample x.
The utility model provides an electrical equipment trouble early warning system based on RFID monitoring, includes data acquisition module, data processing module, first prediction module, second prediction module, trouble early warning module and model training module:
the data acquisition module is used for acquiring a time sequence temperature data set of the electrical equipment through the RFID temperature acquisition system, and acquiring historical fault early warning information and corresponding historical fault early warning grades of the electrical equipment at the same time, wherein the fault early warning grades are divided into a plurality of grades according to the severity of the fault early warning information;
the data processing module is used for preprocessing the acquired time sequence temperature data set;
the first prediction module is used for inputting the preprocessed time sequence temperature data set into a trained denoising self-coding network to obtain first fault early warning information;
the second prediction module is used for inputting the preprocessed time sequence temperature data set into a trained long-time and short-time memory neural network to obtain second fault early warning information;
the fault early warning module is used for inputting the first fault early warning information and the second fault early warning information into the trained Xgboost model to obtain a fault early warning grade,
the model training module is used for training a preprocessed historical time sequence temperature data set of the electrical equipment and corresponding fault early warning information as a training set of a denoising self-coding network and a long-time and short-time memory neural network; and the model training module takes the historical fault early warning information and the corresponding fault early warning grade of the electrical equipment as a training set of the Xgboost model for training.
Further, the data processing module corrects the time sequence temperature data set through a neighbor propagation clustering algorithm, and the process specifically comprises the following steps:
801) integrating each temperature sequence T in a time series temperature data setN＝{L1,L2,…,LNEqually dividing into X periodic sequences
L is a temperature value, r is an element of [1, X ]]Each of
Are all a-dimensional sequences, each calculated
Temperature trend series of
Wherein,
802) each will be
Forming K by AP clusteringrThe cluster center of the ith cluster is recorded as Vi，i∈[1，kr],i＝N+；
803) Calculate each
Is/are as follows
And each ViSimilarity sim ofn,i，simn,i∈[0,1]；
804) Determining
Regarding the membership degree of each population, the population with the largest membership degree is taken as the population
A population of affiliates;
805) setting a membership threshold value as in the population
Is less than a membership threshold
The outliers are identified and corrected.
Furthermore, the model training module incorporates a newly acquired time sequence temperature data set, first fault early warning information and second fault early warning information into a training set of the denoising self-coding network and the long-time and short-time memory neural network, and trains the denoising self-coding network and the long-time and short-time memory neural network by using the new training set;
and the model training module is used for merging the newly obtained first fault early warning information, the second fault early warning information and the fault early warning grade into a training set of the Xgboost model and training the Xgboost model by using the new training set.
Further, the self-coding network, the long-time and short-time memory neural network and the Xgboost model are trained by adopting a symmetric embedded metric learning method, and the formula of a trained loss function J is as follows:
wherein lmn∈{0,1}，(xm,xn) For a sample pair, h (x) max (0, x) is the cross-over loss function, α1As a penalty term, α1Is a constant, d (x)m,xn) Is (x)m,xn) F (x) is the feature extracted for sample x.
Compared with the prior art, the invention has the following beneficial effects:
(1) according to the method, a time sequence temperature data set of electrical equipment is acquired through an RFID temperature acquisition system and is preprocessed, the preprocessed time sequence temperature data set is input into a trained denoising self-coding network and a long-time memory neural network, first fault early warning information and first predicted fault early warning information are obtained respectively, an Xgboost model comprehensively judges the fault early warning grade according to the first fault early warning information and the second fault early warning information, abnormal data including data noise and data loss frequently occur in the time sequence temperature data set acquired by the RFID temperature acquisition system, the fault early warning grade is comprehensively analyzed through the first fault early warning information and the first predicted fault early warning information, overfitting is avoided, and the result is more accurate;
(2) according to the method, data are preprocessed after a time sequence temperature data set is acquired, clustering is carried out by adopting a neighbor propagation clustering algorithm, abnormal data in the data are corrected, overfitting is further avoided, and the prediction precision is improved;
(3) the method comprises the steps of merging a newly obtained time sequence temperature data set, first fault early warning information and second fault early warning information into a training set of a denoising self-coding network and a long-time and short-time memory neural network, and training the denoising self-coding network and the long-time and short-time memory neural network by using the new training set; the newly obtained first fault early warning information, second fault early warning information and fault early warning grade are merged into a training set of the Xgboost model, the Xgboost model is trained by the aid of the new training set, training samples can be continuously expanded, feedback correction is achieved, and prediction accuracy is high;
(4) the method adopts a symmetric embedded metric learning method to train the self-coding network, the long-time memory neural network and the Xgboost model, can further increase the training process of the model, captures the time sequence characteristics implied by the temperature data more carefully, and further improves the fault early warning accuracy rate.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic structural diagram of a denoised self-coding network;
FIG. 3 is a schematic structural diagram of a deep learning network;
fig. 4 is a schematic diagram of symmetric embedding.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Example 1
An electrical equipment fault early warning method based on RFID monitoring includes the following steps as shown in FIG. 1, FIG. 2 and FIG. 3:
the method comprises the steps of collecting and preprocessing a time sequence temperature data set of the electrical equipment through an RFID temperature collection system, dividing the preprocessed time sequence temperature data set S into a training set E and a testing set R, equally dividing the training set E into 2 subsets, and respectively recording the subsets as D1And D2The set relationship is as follows:
S＝E∪R
E＝D1∪D2
obtaining and D from history1Corresponding failure warning information and2corresponding fault warning information, using D1And with D1Training a denoising self-coding network AE by corresponding fault early warning information, and utilizing D2And with D2The corresponding fault early warning information is trained, and the long time and the short time memorize a neural network LSTM; dividing fault early warning information corresponding to historical time sequence temperature data into 4 fault early warning levels according to severity, wherein the first level is the most severe, acquiring fault early warning information of the electrical equipment and the fault early warning level corresponding to the fault early warning information according to historical records, and training an Xgboost model by utilizing the fault early warning information and the fault early warning level corresponding to the fault early warning information;
inputting the test set R into a trained denoising self-coding network and a long-term memory neural network, respectively obtaining first fault early warning information and first predicted fault early warning information, and inputting the first fault early warning information and the second fault early warning information into a trained Xgboost model to obtain a fault early warning grade;
the method comprises the steps of merging a newly obtained time sequence temperature data set, first fault early warning information and second fault early warning information into a training set of a denoising self-coding network and a long-time and long-time memory neural network, training the denoising self-coding network and the long-time and long-time memory neural network by using the new training set, merging the newly obtained first fault early warning information, second fault early warning information and fault early warning grade into a training set of an Xgboost model, training the Xgboost model by using the new training set, achieving feedback correction of AE, LSTM and Xgboost models, and improving prediction accuracy.
Wherein denoised self-encoding network stack NeThe number of the hidden layers of the layer and the long-time memory neural network is set as NL。
Because the sequence temperature data that RFID temperature acquisition system gathered can appear abnormal data, like data loss and noise interference, need revise, most clustering methods, like K mean value cluster and fuzzy clustering etc. all need to realize appointed group's data, and preprocessing revises the time sequence temperature data set through neighbor propagation clustering algorithm in this embodiment, can discern abnormal data point, specifically is:
301) integrating each temperature sequence T in a time series temperature data setN＝{L1,L2,…,LNEqually dividing into X periodic sequences
L is a temperature value, r is an element of [1, X ]]Each of
Are all a-dimensional sequences, each calculated
Temperature trend series of
Wherein,
302) each will be
Forming K by AP clusteringrThe cluster center of the ith cluster is recorded as Vi，i∈[1，kr],i＝N+；
303) Calculate each
Is/are as follows
And each ViSimilarity sim ofn,i，simn,i∈[0,1]；
304) Determining
Regarding the membership degree of each population, the population with the largest membership degree is taken as the population
A population of affiliates;
305) setting a membership threshold value as in the population
Is less than a membership threshold
The outliers are identified and corrected.
The self-coding network, the long-time and short-time memory neural network and the Xgboost model are trained by adopting a symmetric embedded metric learning method, sample pairs connected by solid lines in the graph 4 belong to the same category, sample pairs connected by dotted lines belong to different categories, and the formula of a trained loss function J is as follows:
wherein lmn∈{0,1}，(xm,xn) For a sample pair, h (x) max (0, x) is the cross-over loss function, α1As a penalty term, α1Is a constant, d (x)m,xn) Is (x)m,xn) F (x) is the extracted feature of the input sample x.
Example 2
The utility model provides an electrical equipment trouble early warning system based on RFID monitoring, includes data acquisition module, data processing module, first prediction module, second prediction module, trouble early warning module and model training module:
the data acquisition module is used for acquiring a time sequence temperature data set of the electrical equipment through the RFID temperature acquisition system, and acquiring historical fault early warning information and corresponding historical fault early warning grades of the electrical equipment at the same time, wherein the fault early warning grades are divided into a plurality of grades according to the severity of the fault early warning information;
the data processing module is used for preprocessing the acquired time sequence temperature data set;
the first prediction module is used for inputting the preprocessed time sequence temperature data set into a trained denoising self-coding network to obtain first fault early warning information;
the second prediction module is used for inputting the preprocessed time sequence temperature data set into a trained long-time and short-time memory neural network to obtain second fault early warning information;
the fault early warning module is used for inputting the first fault early warning information and the second fault early warning information into the trained Xgboost model to obtain a fault early warning grade,
the model training module is used for training a preprocessed historical time sequence temperature data set of the electrical equipment and corresponding fault early warning information as a training set of a denoising self-coding network and a long-time and short-time memory neural network; and the model training module takes the historical fault early warning information and the corresponding fault early warning grade of the electrical equipment as a training set of the Xgboost model for training.
Wherein denoised self-encoding network stack NeThe number of the hidden layers of the layer and the long-time memory neural network is set as NL。
The pretreatment process specifically comprises the following steps: and the data processing module corrects the time sequence temperature data set through a clustering algorithm.
The clustering algorithm is a neighbor propagation clustering algorithm, and the preprocessing process specifically comprises the following steps:
801) integrating each temperature sequence T in a time series temperature data setN＝{L1,L2,…,LNEqually dividing into X periodic sequences
L is a temperature value, r is an element of [1, X ]]Each of
Are all a-dimensional sequences, each calculated
Temperature trend series of
Wherein,
802) each will be
Forming K by AP clusteringrThe cluster center of the ith cluster is recorded as Vi，i∈[1，kr],i＝N+；
803) Calculate each
Is/are as follows
And each ViSimilarity sim ofn,i，simn,i∈[0,1]；
804) Determining
Regarding the membership degree of each population, the population with the largest membership degree is taken as the population
A population of affiliates;
805) setting membership thresholdValue, when in the population
Is less than a membership threshold
The outliers are identified and corrected.
The model training module merges a newly obtained time sequence temperature data set, first fault early warning information and second fault early warning information into a training set of the denoising self-coding network and the long-time and short-time memory neural network, and trains the denoising self-coding network and the long-time and short-time memory neural network by using the new training set;
and the model training module merges the newly obtained first fault early warning information, second fault early warning information and fault early warning grade into a training set of the Xgboost model, and trains the Xgboost model by using the new training set.
The self-coding network, the long-time memory neural network and the Xgboost model are trained by adopting a symmetric embedded metric learning method, and the formula of a trained loss function J is as follows:
wherein lmn∈{0,1}，(xm,xn) For a sample pair, h (x) max (0, x) is the cross-over loss function, α1As a penalty term, α1Is a constant, d (x)m,xn) Is (x)m,xn) F (x) is the feature extracted for sample x,
the embodiment 1 and the embodiment 2 provide an electrical equipment fault early warning method and system based on RFID monitoring, abnormal data including data noise and data loss often occur in a time sequence temperature data set acquired by an RFID temperature acquisition system, and the fault early warning level is comprehensively analyzed through first fault early warning information and first prediction fault early warning information, so that overfitting is avoided, and the result is more accurate.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. An electrical equipment fault early warning method based on RFID monitoring is characterized by specifically comprising the following steps:
acquiring and preprocessing a time sequence temperature data set of the electrical equipment through an RFID temperature acquisition system, inputting the preprocessed time sequence temperature data set into a trained denoising self-coding network and a long-time and short-time memory neural network, respectively obtaining first fault early warning information and first predicted fault early warning information, and inputting the first fault early warning information and the second fault early warning information into a trained Xgboost model to obtain a fault early warning grade;
the method comprises the steps that historical time sequence temperature data of electrical equipment and corresponding historical fault early warning information are obtained, the historical time sequence temperature data are preprocessed, and the denoising self-coding network and the long-time and short-time memory neural network are trained by taking the preprocessed historical time sequence temperature data and the corresponding historical fault early warning information as training sets;
and dividing the fault early warning information corresponding to the historical time sequence temperature data into a plurality of fault early warning levels according to the severity, and training the Xgboost model by taking the historical fault early warning information and the corresponding fault early warning levels as a training set.
2. The electrical equipment fault early warning method based on RFID monitoring as claimed in claim 1, wherein the preprocessing process specifically comprises: and correcting the time sequence temperature data set through a clustering algorithm.
3. The electrical equipment fault early warning method based on RFID monitoring as claimed in claim 2, wherein the clustering algorithm is a neighbor propagation clustering algorithm, and the preprocessing process specifically comprises:
301) integrating each temperature sequence T in a time series temperature data setN＝{L1,L2,…,LNEqually dividing into X periodic sequences
L is a temperature value, r is an element of [1, X ]]Each of
Are all a-dimensional sequences, each calculated
Temperature trend series of
Wherein,
302) each will be
Forming K by AP clusteringrThe cluster center of the ith cluster is recorded as Vi，i∈[1，kr],i＝N+；
303) Calculate each
Is/are as follows
And each ViSimilarity sim ofn,i，simn,i∈[0,1]；
304) Determining
Regarding the membership degree of each population, the population with the largest membership degree is taken as the population
A population of affiliates;
305) setting a membership threshold value as in the population
Is less than a membership threshold
The outliers are identified and corrected.
4. The electrical equipment fault early warning method based on RFID monitoring as claimed in claim 1, wherein the newly obtained time sequence temperature data set, the first fault early warning information and the second fault early warning information are incorporated into a training set of a de-noising self-coding network and a long-and-short time memory neural network, and the de-noising self-coding network and the long-and-short time memory neural network are trained by the new training set;
and merging the newly obtained first fault early warning information, second fault early warning information and fault early warning grade into a training set of the Xgboost model, and training the Xgboost model by using the new training set.
5. The electrical equipment fault early warning method based on RFID monitoring of claim 1, wherein the self-coding network, the long-time and short-time memory neural network and the Xgboost model are trained by a symmetric embedded metric learning method, and the formula of a trained loss function J is as follows:
wherein lmn∈{0,1}，(xm,xn) For a sample pair, h (x) max (0, x) is the cross-over loss function, α1As a penalty term, α1Is a constant, d (x)m,xn) Is (x)m,xn) F (x) is the feature extracted for sample x.
6. An electrical equipment fault early warning system based on RFID monitoring, its characterized in that includes:
the data acquisition module is used for acquiring a time sequence temperature data set of the electrical equipment through the RFID temperature acquisition system, and acquiring historical fault early warning information and corresponding historical fault early warning grades of the electrical equipment at the same time, wherein the fault early warning grades are divided into a plurality of grades according to the severity of the fault early warning information;
the data processing module is used for preprocessing the acquired time sequence temperature data set;
the first prediction module is used for inputting the preprocessed time sequence temperature data set into a trained denoising self-coding network to obtain first fault early warning information;
the second prediction module is used for inputting the preprocessed time sequence temperature data set into a trained long-time and short-time memory neural network to obtain second fault early warning information;
a fault early warning module for inputting the first fault early warning information and the second fault early warning information into the trained Xgboost model to obtain a fault early warning grade,
and the model training module is used for training the preprocessed historical time sequence temperature data set of the electrical equipment and the corresponding fault early warning information as a training set of a denoising self-coding network and a long-time and short-time memory neural network, and training the historical fault early warning information of the electrical equipment and the corresponding fault early warning grade as a training set of the Xgboost model.
7. The electrical equipment fault early warning system based on RFID monitoring of claim 6, wherein the preprocessing process specifically comprises: and the data processing module corrects the time sequence temperature data set through a clustering algorithm.
8. The electrical equipment fault early warning system based on RFID monitoring of claim 6, wherein the clustering algorithm is a neighbor propagation clustering algorithm, and the preprocessing process specifically comprises:
801) integrating each temperature sequence T in a time series temperature data setN＝{L1,L2,…,LNEqually dividing into X periodic sequences
L is a temperature value, r is an element of [1, X ]]Each of
Are all a-dimensional sequences, each calculated
Temperature trend series of
Wherein,
802) each will be
Forming K by AP clusteringrThe cluster center of the ith cluster is recorded as Vi，i∈[1，kr],i＝N+；
803) Calculate each
Is/are as follows
And each ViSimilarity sim ofn,i，simn,i∈[0,1]；
804) Determining
Regarding the membership degree of each population, the population with the largest membership degree is taken as the population
A population of affiliates;
805) setting a membership threshold value as in the population
Is less than a membership threshold
The outliers are identified and corrected.
9. The electrical equipment fault early warning system based on RFID monitoring of claim 6, wherein the model training module incorporates a newly obtained time sequence temperature data set, first fault early warning information and second fault early warning information into a training set of the denoising self-coding network and the long-and-short time memory neural network, and trains the denoising self-coding network and the long-and-short time memory neural network by using the new training set;
and the model training module is used for merging the newly obtained first fault early warning information, the second fault early warning information and the fault early warning grade into a training set of the Xgboost model and training the Xgboost model by using the new training set.
10. The electrical equipment fault early warning system based on RFID monitoring of claim 6, wherein the self-coding network, the long-time and short-time memory neural network and the Xgboost model are trained by a symmetric embedded metric learning method, and the formula of a trained loss function J is as follows:
wherein lmn∈{0,1}，(xm,xn) For a sample pair, h (x) max (0, x) is the cross-over loss function, α1As a penalty term, α1Is a constant, d (x)m,xn) Is (x)m,xn) F (x) is the feature extracted for sample x.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010941484.5A CN112232366B (en) | 2020-09-09 | 2020-09-09 | Electrical equipment fault early warning method and system based on RFID monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010941484.5A CN112232366B (en) | 2020-09-09 | 2020-09-09 | Electrical equipment fault early warning method and system based on RFID monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112232366A true CN112232366A (en) | 2021-01-15 |
| CN112232366B CN112232366B (en) | 2024-04-16 |
Family
ID=74115453
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010941484.5A Active CN112232366B (en) | 2020-09-09 | 2020-09-09 | Electrical equipment fault early warning method and system based on RFID monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112232366B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570862A (en) * | 2021-07-28 | 2021-10-29 | 太原理工大学 | XGboost algorithm-based large traffic jam early warning method |
| CN114550902A (en) * | 2022-01-13 | 2022-05-27 | 重庆医科大学附属第一医院 | Hospital power utilization equipment management system and method based on RFID |
| CN115178752A (en) * | 2022-09-13 | 2022-10-14 | 广东银纳增材制造技术有限公司 | Fault early warning method and device for 3D printing metal powder production equipment |
| CN115574963A (en) * | 2022-12-08 | 2023-01-06 | 南京智联达科技有限公司 | Wireless temperature acquisition system and temperature acquisition method based on IOT technology |
| CN115860106A (en) * | 2022-12-23 | 2023-03-28 | 四川物通科技有限公司 | Intelligent transformer substation capacitor fault early warning method based on deep Q learning |
| CN115901003A (en) * | 2022-11-23 | 2023-04-04 | 南京乾鑫电器设备有限公司 | Temperature monitoring method and system for environment-friendly gas switch cabinet |
| CN115950557A (en) * | 2023-03-08 | 2023-04-11 | 深圳市特安电子有限公司 | Intelligent temperature compensation method based on pressure transmitter |
| CN117171517A (en) * | 2023-11-02 | 2023-12-05 | 无锡尚航数据有限公司 | Dynamic early warning method for operation fault risk of data center |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104697653A (en) * | 2015-02-10 | 2015-06-10 | 上海交通大学 | Temperature pre-warning system for key equipment of ultrahigh-pressure power distributing station based on web |
| WO2015158198A1 (en) * | 2014-04-17 | 2015-10-22 | 北京泰乐德信息技术有限公司 | Fault recognition method and system based on neural network self-learning |
| CN108803576A (en) * | 2018-07-24 | 2018-11-13 | 广东工业大学 | A kind of fault early warning method and relevant apparatus of temperature control system |
| CN109840666A (en) * | 2017-11-29 | 2019-06-04 | 中国电力科学研究院有限公司 | A kind of model building method and system for predicting that the following Wind turbines break down |
| CN110210495A (en) * | 2019-05-21 | 2019-09-06 | 浙江大学 | The XGBoost soft-measuring modeling method extracted based on parallel LSTM self-encoding encoder behavioral characteristics |
| US20190325334A1 (en) * | 2018-04-23 | 2019-10-24 | National Chung-Shan Institute Of Science And Technology | Method for predicting air quality with aid of machine learning models |
| CN110737952A (en) * | 2019-09-17 | 2020-01-31 | 太原理工大学 | prediction method for residual life of key parts of mechanical equipment by combining AE and bi-LSTM |
| CN110763929A (en) * | 2019-08-08 | 2020-02-07 | 浙江大学 | Intelligent monitoring and early warning system and method for convertor station equipment |
| CN110909782A (en) * | 2019-11-15 | 2020-03-24 | 湘潭大学 | Method for diagnosing machine tool spindle fault based on multi-feature combined deep learning |
| CN111237134A (en) * | 2020-01-14 | 2020-06-05 | 上海电力大学 | Offshore double-fed wind driven generator fault diagnosis method based on GRA-LSTM-stacking model |
| CN111582298A (en) * | 2020-03-18 | 2020-08-25 | 宁波送变电建设有限公司永耀科技分公司 | Sensing abnormal data real-time detection method based on artificial intelligence |
-
2020
- 2020-09-09 CN CN202010941484.5A patent/CN112232366B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015158198A1 (en) * | 2014-04-17 | 2015-10-22 | 北京泰乐德信息技术有限公司 | Fault recognition method and system based on neural network self-learning |
| CN104697653A (en) * | 2015-02-10 | 2015-06-10 | 上海交通大学 | Temperature pre-warning system for key equipment of ultrahigh-pressure power distributing station based on web |
| CN109840666A (en) * | 2017-11-29 | 2019-06-04 | 中国电力科学研究院有限公司 | A kind of model building method and system for predicting that the following Wind turbines break down |
| US20190325334A1 (en) * | 2018-04-23 | 2019-10-24 | National Chung-Shan Institute Of Science And Technology | Method for predicting air quality with aid of machine learning models |
| CN108803576A (en) * | 2018-07-24 | 2018-11-13 | 广东工业大学 | A kind of fault early warning method and relevant apparatus of temperature control system |
| CN110210495A (en) * | 2019-05-21 | 2019-09-06 | 浙江大学 | The XGBoost soft-measuring modeling method extracted based on parallel LSTM self-encoding encoder behavioral characteristics |
| CN110763929A (en) * | 2019-08-08 | 2020-02-07 | 浙江大学 | Intelligent monitoring and early warning system and method for convertor station equipment |
| CN110737952A (en) * | 2019-09-17 | 2020-01-31 | 太原理工大学 | prediction method for residual life of key parts of mechanical equipment by combining AE and bi-LSTM |
| CN110909782A (en) * | 2019-11-15 | 2020-03-24 | 湘潭大学 | Method for diagnosing machine tool spindle fault based on multi-feature combined deep learning |
| CN111237134A (en) * | 2020-01-14 | 2020-06-05 | 上海电力大学 | Offshore double-fed wind driven generator fault diagnosis method based on GRA-LSTM-stacking model |
| CN111582298A (en) * | 2020-03-18 | 2020-08-25 | 宁波送变电建设有限公司永耀科技分公司 | Sensing abnormal data real-time detection method based on artificial intelligence |
Non-Patent Citations (3)
| Title |
|---|
| 刘耀巍;刘向军;: "基于综合预警算法的开关柜温度预警系统设计", 电器与能效管理技术, no. 05, 15 March 2018 (2018-03-15) * |
| 杨济海: "基于并行的F⁃LSTM 模型及其在电力通信设备故障 预测中的应用", 武汉大学学报（理学版）, vol. 65, no. 3, pages 263 - 268 * |
| 陈鹏飞: "基于状态预测的风力发电机控制策略分析", 中国优秀硕士学位论文全文数据库（电子期刊）, pages 042 - 272 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113570862A (en) * | 2021-07-28 | 2021-10-29 | 太原理工大学 | XGboost algorithm-based large traffic jam early warning method |
| CN113570862B (en) * | 2021-07-28 | 2022-05-10 | 太原理工大学 | XGboost algorithm-based large traffic jam early warning method |
| CN114550902A (en) * | 2022-01-13 | 2022-05-27 | 重庆医科大学附属第一医院 | Hospital power utilization equipment management system and method based on RFID |
| CN115178752A (en) * | 2022-09-13 | 2022-10-14 | 广东银纳增材制造技术有限公司 | Fault early warning method and device for 3D printing metal powder production equipment |
| CN115901003A (en) * | 2022-11-23 | 2023-04-04 | 南京乾鑫电器设备有限公司 | Temperature monitoring method and system for environment-friendly gas switch cabinet |
| CN115901003B (en) * | 2022-11-23 | 2024-04-09 | 南京乾鑫电器设备有限公司 | Temperature monitoring method and system for environment-friendly gas switch cabinet |
| CN115574963A (en) * | 2022-12-08 | 2023-01-06 | 南京智联达科技有限公司 | Wireless temperature acquisition system and temperature acquisition method based on IOT technology |
| CN115860106A (en) * | 2022-12-23 | 2023-03-28 | 四川物通科技有限公司 | Intelligent transformer substation capacitor fault early warning method based on deep Q learning |
| CN115950557A (en) * | 2023-03-08 | 2023-04-11 | 深圳市特安电子有限公司 | Intelligent temperature compensation method based on pressure transmitter |
| CN117171517A (en) * | 2023-11-02 | 2023-12-05 | 无锡尚航数据有限公司 | Dynamic early warning method for operation fault risk of data center |
| CN117171517B (en) * | 2023-11-02 | 2024-01-26 | 无锡尚航数据有限公司 | Dynamic early warning method for operation fault risk of data center |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112232366B (en) | 2024-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112232366A (en) | Electrical equipment fault early warning method and system based on RFID monitoring | |
| CN111898634B (en) | Intelligent fault diagnosis method based on depth-to-reactance-domain self-adaption | |
| US11586913B2 (en) | Power equipment fault detecting and positioning method of artificial intelligence inference fusion | |
| CN111273623B (en) | Fault diagnosis method based on Stacked LSTM | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN113673346B (en) | Motor vibration data processing and state identification method based on multiscale SE-Resnet | |
| CN111353373A (en) | Correlation alignment domain adaptive fault diagnosis method | |
| CN113469219A (en) | Rotary machine fault diagnosis method under complex working condition based on element transfer learning | |
| CN117579101B (en) | Control method and system for carrier communication module | |
| CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
| CN117076955A (en) | Fault detection method and system for high-voltage frequency converter | |
| CN112305379A (en) | Mode identification method and system for GIS insulation defect | |
| CN114492534B (en) | Construction method and application of cross-size motor bearing fault diagnosis model | |
| CN113298178A (en) | Transformer substation high-voltage equipment fault identification method based on thermal infrared image | |
| CN117332352B (en) | Lightning arrester signal defect identification method based on BAM-AlexNet | |
| CN117437933A (en) | Feature cluster combination generation type learning-based unsupervised detection method for fault of voiceprint signal of transformer | |
| CN115146675B (en) | Rotary machine migration diagnosis method under variable working condition of depth multi-feature dynamic countermeasure | |
| CN116543538A (en) | Internet of things fire-fighting electrical early warning method and early warning system | |
| CN114692683B (en) | Fall detection method and device based on CSI and storage medium | |
| CN113887633B (en) | Malicious behavior identification method and system for closed source power industrial control system based on IL | |
| CN115588124A (en) | Fine-grained classification denoising training method based on soft label cross entropy tracking | |
| Zhao et al. | Fault Diagnosis of Rolling Bearings based on GA-SVM model | |
| CN118211124B (en) | Transformer fault prediction method and system | |
| CN117909852B (en) | Monitoring data state division method for hydraulic loop ecological data analysis | |
| CN113808755B (en) | Method for training prediction model of infected population, prediction method, device and equipment |
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 |