CN114997332A - Fault diagnosis method for wavelet packet analysis and sparrow algorithm optimization correlation vector machine - Google Patents
Fault diagnosis method for wavelet packet analysis and sparrow algorithm optimization correlation vector machine Download PDFInfo
- Publication number
- CN114997332A CN114997332A CN202210743966.9A CN202210743966A CN114997332A CN 114997332 A CN114997332 A CN 114997332A CN 202210743966 A CN202210743966 A CN 202210743966A CN 114997332 A CN114997332 A CN 114997332A
- Authority
- CN
- China
- Prior art keywords
- fault
- packet analysis
- wavelet packet
- vector machine
- sparrow
- 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.)
- Pending
Links
- 239000013598 vector Substances 0.000 title claims abstract description 45
- 238000004458 analytical method Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 39
- 241000287127 Passeridae Species 0.000 title claims abstract description 38
- 238000003745 diagnosis Methods 0.000 title claims abstract description 30
- 238000005457 optimization Methods 0.000 title claims abstract description 19
- 238000010845 search algorithm Methods 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000013145 classification model Methods 0.000 claims description 9
- 238000002474 experimental method Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000002265 prevention Effects 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 8
- 238000002790 cross-validation Methods 0.000 description 5
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R27/00—Arrangements for measuring resistance, reactance, impedance, or electric characteristics derived therefrom
- G01R27/02—Measuring real or complex resistance, reactance, impedance, or other two-pole characteristics derived therefrom, e.g. time constant
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a fault diagnosis method for a wavelet packet analysis and sparrow algorithm optimization correlation vector machine, which comprises the following steps of: s1: acquiring fault data; s2: preprocessing the collected fault data by wavelet packet analysis; s3: identifying and classifying by a relevant vector machine optimized by a sparrow search algorithm; the method has the characteristics of quickly and accurately identifying different fault types under different conditions, and having excellent performances such as effectiveness and superiority. The invention can provide a new and more means for detecting the electrical fault in the operation process of the intelligent building for the building electrical industry practitioners, improve the discrimination and prevention capability of the building electrical industry practitioners on the accident occurring in the operation process of the intelligent building, avoid the occurrence of major accidents caused by the failure of the building electrical equipment, ensure the safety of the building electrical industry practitioners and ensure the normal operation of the intelligent building.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis, and particularly relates to a fault diagnosis method for a wavelet packet analysis and sparrow algorithm optimization correlation vector machine.
Background
With the ever higher demands on production quality and the continuous advancement of technology, the automation level of the industries such as machine building, power supply networks, building and electrical industry is increasing, and the structure of a large-scale system is becoming more and more complicated. For example, in a power system, there are many electrical components on many lines, such as transformers, motors, user equipment, etc., and in a large system composed of a plurality of subsystems, it is very important to monitor these components in real time. If a certain link fails, the system can operate quickly after the fault position needs to be detected and eliminated, if hidden dangers cannot be eliminated in time, the fault is likely to be enlarged, all interconnected subsystems are seriously damaged, normal economic production and quality requirements are affected, and even more, personal safety is endangered. Therefore, how to find and effectively predict faults in time to ensure safe, economic and reliable operation of equipment has been a problem faced by many complex systems for a long time.
The computer is used for replacing manual work to detect and calculate the fault, and the method is the fastest and the highest choice, and when the fault diagnosis technology is applied to a large complex system, once the fault diagnosis technology has self-learning capacity, the environment can be monitored in real time, so that the fault can be timely eliminated. At present, the diagnosis technology is still in a development stage, particularly in China, the intelligent fault diagnosis technology of the building electrical system starts late, and the stability and the efficiency of the intelligent fault diagnosis technology need to be improved, so that the idea of researching new diagnosis has huge application prospects in the future, and the intelligent fault diagnosis technology has high research value. Therefore, a fault diagnosis method of a wavelet packet analysis and sparrow algorithm optimization correlation vector machine is provided to solve the problems mentioned in the background technology.
Disclosure of Invention
The invention aims to provide a fault diagnosis method of a wavelet packet analysis and sparrow algorithm optimization related vector machine, which can quickly and accurately detect the faults of a building electrical system in various complex environments, ensures the normal operation of an intelligent building, perfects a scientific detection system of the building electrical industry, avoids the occurrence of major accidents, also improves the safety of the intelligent building, realizes the minimization of fault-tolerant operation, has important significance for reducing the performance reduction to the maximum extent and avoiding dangerous situations, and solves the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: a fault diagnosis method for a wavelet packet analysis and sparrow algorithm optimization correlation vector machine comprises the following steps:
s1: acquiring fault data;
s2: preprocessing the collected fault data by wavelet packet analysis;
s3: identifying and classifying by a relevant vector machine optimized by a sparrow search algorithm;
the fault data acquisition and wavelet packet analysis are connected with the preprocessing of the acquired fault data and used for obtaining fault characteristic vectors;
the wavelet packet analysis is used for preprocessing the collected fault data and is connected with a relevant vector machine identification classification optimized by a sparrow search algorithm for identifying and outputting results.
The fault data acquisition comprises fault setting, line connection and connection of a sensor and a data acquisition unit Eurotest61557, resistance signals of different fault types are acquired at the same position of the experiment platform by the data acquisition unit Eurotest61557, and the fault data acquisition comprises 50 fault acquisition points in each group of data.
The pretreatment of the wavelet packet analysis on the collected fault data comprises the steps of obtaining wavelet coefficients of each frequency band by subjecting one group of data to wavelet packet analysis, obtaining node energy by subjecting the wavelet coefficients of each frequency band to a corresponding normalization process of each wavelet coefficient, and taking the node energy as a group of fault characteristic vectors.
The relevant vector machine recognition classification optimized by the sparrow search algorithm is to select a self-contained parameter gamma in an optimal Gaussian radial basis kernel function through the optimized sparrow search algorithm so as to train an optimal classification model and better classify.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a fault diagnosis method of a wavelet packet analysis and sparrow algorithm optimization correlation vector machine for the first time, which has the characteristics of rapid and accurate identification of different fault types under different conditions, and excellent performances such as effectiveness and superiority. The method combines wavelet packet analysis with relevant vector machines optimized by a sparrow search algorithm to construct a new building electrical system fault diagnosis framework, and compared with the traditional intelligent optimization algorithm combined with the relevant vector machines, the wavelet packet analysis theory combined and the like, the method has the advantages and provides a new idea for intelligent fault diagnosis. In a word, the invention can provide a new and more means for detecting the electrical fault in the operation process of the intelligent building for a building electrical industry practitioner, improve the discrimination and prevention capability of the building electrical industry practitioner on the accident occurring in the operation process of the intelligent building, avoid the occurrence of major accidents caused by the failure of building electrical equipment, ensure the safety of the building electrical industry practitioner and ensure the normal operation of the intelligent building.
Drawings
Fig. 1 is a schematic flow chart of a fault diagnosis method of a wavelet packet analysis and sparrow algorithm optimization correlation vector machine according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a fault diagnosis method of a wavelet packet analysis and sparrow algorithm optimization correlation vector machine as shown in figure 1, which comprises the following steps:
s1: acquiring fault data;
s2: preprocessing the collected fault data by wavelet packet analysis;
s3: identifying and classifying by a relevant vector machine optimized by a sparrow search algorithm;
the fault data acquisition and wavelet packet analysis are connected with the preprocessing of the acquired fault data and used for obtaining fault characteristic vectors;
the wavelet packet analysis is used for preprocessing the collected fault data and is connected with a relevant vector machine identification classification optimized by a sparrow search algorithm for identifying and outputting results.
The fault data acquisition comprises fault setting, line connection and connection of a sensor and a data acquisition unit Eurotest61557, resistance signals of different fault types are acquired at the same position of an experiment platform by the data acquisition unit Eurotest61557, and the fault data acquisition comprises 50 fault acquisition points of each group of data.
The pretreatment of the wavelet packet analysis on the collected fault data comprises the steps of obtaining wavelet coefficients of each frequency band by subjecting one group of data to wavelet packet analysis, obtaining node energy by subjecting the wavelet coefficients of each frequency band to a corresponding normalization process of each wavelet coefficient, and taking the node energy as a group of fault characteristic vectors.
The relevant vector machine recognition classification optimized by the sparrow search algorithm is to select a self-contained parameter gamma in an optimal Gaussian radial basis kernel function through the optimized sparrow search algorithm so as to train an optimal classification model and better classify.
The method comprises the steps of fault data acquisition and wavelet packet analysis, preprocessing connection of acquired fault data is used for acquiring resistance signals of different fault types at the same position of an experiment platform, acquiring that each group of data comprises 50 fault acquisition points, one type of fault data comprises 30 groups of data, performing wavelet coefficient extraction on each group of data through wavelet packet analysis on each type of original signals, acquiring energy of each node to obtain a fault characteristic vector serving as a new fault data set, and dividing the new fault data set into a training set and a testing set according to the proportion of 80% to 20%.
The relevant vector machine recognition classification optimized by the sparrow search algorithm is characterized in that the optimized sparrow search algorithm is used for selecting a self-contained parameter gamma in the optimal Gaussian radial basis kernel function so as to train an optimal classification model, and fault recognition and classification can be better carried out.
In the embodiment of the invention, the data set acquisition comprises resistance data with the sampling frequency of 256, fault data is acquired through a sensor, and every 50 data are a group of data. Wavelet packet analysis processes the acquired data set, wavelet coefficients including approximation coefficients and detail coefficients can be extracted from the signals by utilizing wavelet basis functions and scale functions and correspond to a low frequency band and a high frequency band respectively, and therefore the situation that important information possibly included in original signals due to the fact that the low frequency band is omitted is avoided. And then solving the energy of each node by the wavelet coefficient through a process of solving the norm to obtain a fault characteristic vector.
And further dividing the fault feature vector serving as a new sample data set plan into a fault 1 sample and a fault 2 sample.
And finally, relevant vector machine recognition and classification optimized by a sparrow search algorithm is realized by selecting a self-contained parameter gamma in an optimal Gaussian radial basis kernel function through the optimized sparrow search algorithm so as to train an optimal classification model and better recognize and classify faults.
The fault diagnosis method for optimizing the relevant vector machine by the wavelet packet analysis and sparrow search algorithm has the advantages that faults of a building electrical system can be accurately and quickly detected under various complex environments, accurate detection under various complex environments refers to that the wavelet packet analysis theory is utilized, and the wavelet packet analysis method and the previous wavelet analysis method only aim at high frequency band analysis, so that important information described by a low frequency band on original signals can be omitted, and the problem that diagnosis results are uncertain is caused. Compared with the traditional intelligent optimization algorithm, the sparrow search algorithm has the characteristics of high convergence rate and high accuracy in the aspect of optimization problem, and can determine hyper-parameters, weight vectors and penalty factors through continuous iteration in the process of training the relevant vector machine model, so that the setting operation of excessive parameters can be eliminated, and the fault identification and classification can be more effectively and rapidly carried out. Therefore, the invention can diagnose the faults of various building electrical systems in an all-round and all-weather way.
And calculating the obtained fault characteristic vector by wavelet packet analysis through a wavelet basis function and a scale function to obtain a wavelet coefficient, wherein the wavelet coefficient comprises an approximation coefficient and a detail coefficient, and the energy of each node is obtained by utilizing a norm calculation function corresponding to a low frequency band and a high frequency band. The invention provides a method for analyzing the fault data signal through the wavelet packet to obtain the fault characteristic vector, and the problem of missing important information described by a low frequency band on the original signal is solved.
The wavelet basis functions may be selected according to the degree of similarity of the original signal waveforms. Experimental results show that the 10-order Daubechies wavelet is adopted, so that the denoising capability is better.
The decomposition layer number of the scale function is selected according to the comparison of the identification results, and the experimental result shows that when the decomposition layer number is 11, the fault classification identification precision is higher, so that the scheme of adopting 10-order Daubechies wavelet basis functions and the decomposition layer number of 11 is selected. The scheme can obtain good results in the classification model.
The obtained parameter gamma of the self-contained parameter gamma in the optimal Gaussian radial basis kernel function is obtained by continuously iterating and updating the positions of the sparrows through a sparrow searching algorithm, the current optimal solution and the global optimal solution can be obtained through a fitness function, the current optimal solution corresponds to a local extreme value, the global optimal solution corresponds to a global maximum value, the comparison size of the current optimal solution obtained in the current iteration process and the global optimal solution obtained in the whole iteration process is judged, the global optimal solution is updated, and the optimal solution is output when the maximum iteration times are reached.
The fitness function adopts a root mean square error value of cross validation, K-fold cross validation is carried out by using a relevant vector machine model, then the accuracy of each cross validation is obtained, and the accuracy is converted into the root mean square error value. Wherein, the emphasis is to emphasize that the goodness of the RMS error value estimation model is an important index.
K-fold cross-validation may be performed how many times depending on the choice of K. The K is selected by comparing the identification results after multiple tests. The experimental result shows that when K is selected for 10 times, the identification result can reach 100% accuracy, so the scheme that the number of times of cross validation K is 10 is selected. The scheme can obtain a good classification model.
In conclusion, compared with the prior art, the invention provides the fault diagnosis method of the wavelet packet analysis and sparrow algorithm optimization correlation vector machine for the first time, and the fault diagnosis method has the characteristics of fast and accurately identifying different fault types under different conditions, and has excellent performances such as effectiveness and superiority. The method combines wavelet packet analysis, a sparrow search algorithm and a related vector machine for the first time to construct a new building electrical system fault diagnosis framework, and compared with a traditional classification model and a traditional intelligent optimization algorithm optimized classification model, the method has the advantages and provides a new idea for intelligent fault diagnosis. In a word, the invention can provide a new and more means for detecting the building electrical fault of the intelligent building safe operation for the intelligent building industry practitioners, improve the distinguishing capability and the precaution capability of the intelligent building industry practitioners on the accident occurring in the intelligent building safe operation process, avoid the occurrence of major accidents caused by the failure of the building electrical system, ensure the safety of the intelligent building industry practitioners and ensure the safe and stable operation in the intelligent building field.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments or portions thereof without departing from the spirit and scope of the invention.
Claims (4)
1. A fault diagnosis method for a wavelet packet analysis and sparrow algorithm optimization correlation vector machine is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring fault data;
s2: preprocessing the collected fault data by wavelet packet analysis;
s3: identifying and classifying by a relevant vector machine optimized by a sparrow search algorithm;
the fault data acquisition and wavelet packet analysis are connected with the preprocessing of the acquired fault data and used for obtaining fault characteristic vectors;
and the wavelet packet analysis is used for carrying out identification and classification connection on the collected fault data by preprocessing and the relevant vector machine optimized by the sparrow search algorithm and used for identifying and outputting results.
2. The fault diagnosis method of the wavelet packet analysis and sparrow algorithm optimization relevance vector machine according to claim 1, characterized in that: the fault data acquisition comprises fault setting, line connection and connection of a sensor and a data acquisition unit Eurotest61557, resistance signals of different fault types are acquired at the same position of an experiment platform by the data acquisition unit Eurotest61557, and the fault data acquisition comprises 50 fault acquisition points of each group of data.
3. The fault diagnosis method of the wavelet packet analysis and sparrow algorithm optimization relevance vector machine according to claim 1, characterized in that: the pretreatment of the wavelet packet analysis on the collected fault data comprises the steps of obtaining wavelet coefficients of each frequency band by subjecting one group of data to wavelet packet analysis, obtaining node energy by subjecting the wavelet coefficients of each frequency band to a corresponding normalization process of each wavelet coefficient, and taking the node energy as a group of fault characteristic vectors.
4. The fault diagnosis method of the wavelet packet analysis and sparrow algorithm optimization relevance vector machine according to claim 1, characterized in that: the relevant vector machine recognition classification optimized by the sparrow search algorithm is characterized in that the optimized sparrow search algorithm is used for selecting a self-contained parameter gamma in the optimal Gaussian radial basis kernel function so as to train an optimal classification model and better classify.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210743966.9A CN114997332A (en) | 2022-06-27 | 2022-06-27 | Fault diagnosis method for wavelet packet analysis and sparrow algorithm optimization correlation vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210743966.9A CN114997332A (en) | 2022-06-27 | 2022-06-27 | Fault diagnosis method for wavelet packet analysis and sparrow algorithm optimization correlation vector machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114997332A true CN114997332A (en) | 2022-09-02 |
Family
ID=83037417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210743966.9A Pending CN114997332A (en) | 2022-06-27 | 2022-06-27 | Fault diagnosis method for wavelet packet analysis and sparrow algorithm optimization correlation vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114997332A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118194090A (en) * | 2024-03-18 | 2024-06-14 | 科达(西安)自控科技有限公司 | Improved VMD-based rock wall hardness identification method, system and storage medium |
| CN118337851A (en) * | 2024-04-30 | 2024-07-12 | 深圳鸿元智通科技有限公司 | Automatic device discovery method, device and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107505133A (en) * | 2017-08-10 | 2017-12-22 | 滁州学院 | The probability intelligent diagnosing method of rolling bearing fault based on adaptive M RVM |
| CN111860241A (en) * | 2020-07-07 | 2020-10-30 | 国网山东省电力公司威海供电公司 | Power equipment discharge fault identification method based on wavelet packet analysis |
| CN113805060A (en) * | 2021-05-21 | 2021-12-17 | 电子科技大学 | Lithium battery residual life detection method based on relevance vector regression |
-
2022
- 2022-06-27 CN CN202210743966.9A patent/CN114997332A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107505133A (en) * | 2017-08-10 | 2017-12-22 | 滁州学院 | The probability intelligent diagnosing method of rolling bearing fault based on adaptive M RVM |
| CN111860241A (en) * | 2020-07-07 | 2020-10-30 | 国网山东省电力公司威海供电公司 | Power equipment discharge fault identification method based on wavelet packet analysis |
| CN113805060A (en) * | 2021-05-21 | 2021-12-17 | 电子科技大学 | Lithium battery residual life detection method based on relevance vector regression |
Non-Patent Citations (1)
| Title |
|---|
| N LI , ET AL.: "Gear fault detection based on adaptive wavelet packet feature extraction and relevance vector machine", 《MECHANICAL ENGINEERING SCIENCE》, 26 January 2011 (2011-01-26) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118194090A (en) * | 2024-03-18 | 2024-06-14 | 科达(西安)自控科技有限公司 | Improved VMD-based rock wall hardness identification method, system and storage medium |
| CN118337851A (en) * | 2024-04-30 | 2024-07-12 | 深圳鸿元智通科技有限公司 | Automatic device discovery method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111768082A (en) | Power equipment state evaluation method based on big data analysis | |
| CN108333468B (en) | The recognition methods of bad data and device under a kind of active power distribution network | |
| CN114997332A (en) | Fault diagnosis method for wavelet packet analysis and sparrow algorithm optimization correlation vector machine | |
| CN112557826A (en) | Ship electric power system fault diagnosis method | |
| CN109389325B (en) | Method for evaluating state of electronic transformer of transformer substation based on wavelet neural network | |
| CN108435819B (en) | Energy consumption abnormity detection method for aluminum profile extruder | |
| CN107491783B (en) | Transformer fault type classification method based on improved density peak value clustering algorithm | |
| CN113485244A (en) | Numerical control machine tool control system and method based on cutter wear prediction | |
| CN101738998A (en) | System and method for monitoring industrial process based on local discriminatory analysis | |
| CN116956215A (en) | Fault diagnosis method and system for transmission system | |
| CN112036087A (en) | Multi-strategy fused nuclear power key equipment fault diagnosis method and system | |
| CN112464439A (en) | Three-layer data mining-based power system fault type analysis method and device | |
| CN113435759A (en) | Primary equipment risk intelligent evaluation method based on deep learning | |
| CN112633315A (en) | Electric power system disturbance classification method | |
| CN115017828A (en) | Power cable fault identification method and system based on bidirectional long-short-time memory network | |
| CN116092525A (en) | Electrical equipment state voice recognition method considering time-frequency domain feature fusion | |
| CN115511387A (en) | Oil immersed transformer state evaluation method and system based on multi-source information fusion | |
| CN111737993A (en) | Method for extracting health state of equipment from fault defect text of power distribution network equipment | |
| CN111209955A (en) | Airplane power supply system fault identification method based on deep neural network and random forest | |
| CN116011982A (en) | Online monitoring method and system for breakage of grinding roller of coal mill | |
| CN115880472A (en) | Intelligent diagnosis and analysis system for electric power infrared image data | |
| CN115556099B (en) | Sustainable learning industrial robot fault diagnosis system and method | |
| CN118551259B (en) | Method and device for integrating unsupervised instability detection and fault module positioning | |
| CN117371623B (en) | Electric energy meter running state early warning method and system | |
| Jianbin et al. | Research on data processing of power terminal plug and play system based on convolutional neural network |
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 |