CN114638384A - Fault diagnosis method and system based on machine learning - Google Patents
Fault diagnosis method and system based on machine learning Download PDFInfo
- Publication number
- CN114638384A CN114638384A CN202210531762.9A CN202210531762A CN114638384A CN 114638384 A CN114638384 A CN 114638384A CN 202210531762 A CN202210531762 A CN 202210531762A CN 114638384 A CN114638384 A CN 114638384A
- Authority
- CN
- China
- Prior art keywords
- fault
- fault diagnosis
- sample data
- data
- equipment
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention provides a fault diagnosis method and a fault diagnosis system based on machine learning, which belong to the technical field of fault diagnosis of mechanical equipment, and comprise the following steps: acquiring fault sample data and preprocessing the fault sample data; constructing a fault diagnosis model by utilizing the XGboost algorithm by utilizing the preprocessed fault sample data; and acquiring real-time equipment operation data, analyzing the real-time equipment operation data by using the fault diagnosis model, and outputting an equipment fault diagnosis result. The invention effectively reduces the potential safety hazard of equipment, and has the advantages of automation, intellectualization and high diagnosis precision compared with the traditional equipment fault diagnosis method.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis of mechanical equipment, and particularly relates to a fault diagnosis method and system based on machine learning.
Background
With the rapid increase of the industrial modernization level, mechanical equipment is rapidly developed towards the directions of high speed, precision, automation and integration. Parts in mechanical equipment are prone to various faults due to the fact that the parts are overloaded and variable in load and are influenced by external extreme working environments. If the fault can not be diagnosed and removed timely and effectively, along with the deterioration and further development of the fault, a great potential safety hazard is brought, and a great loss is caused. The traditional fault diagnosis method for mechanical equipment mainly comprises diagnosis based on vibration signal processing and diagnosis based on a fault mechanism. The two fault diagnosis methods can solve the mechanical equipment fault types with simple mechanisms and obvious fault characteristics, but have complex fault occurrence mechanisms, and the traditional fault diagnosis method has poor diagnosis effect and low accuracy.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the fault diagnosis method and the fault diagnosis system based on machine learning, and aims to solve the problems of poor equipment fault diagnosis effect and low accuracy in the traditional technology.
In order to achieve the above purpose, the invention adopts the technical scheme that:
the scheme provides a fault diagnosis method based on machine learning, which comprises the following steps:
s1, acquiring fault sample data and preprocessing the fault sample data;
s2, constructing a fault diagnosis model by utilizing the XGboost algorithm and utilizing the preprocessed fault sample data;
and S3, acquiring the real-time equipment operation data, analyzing the real-time equipment operation data by using the fault diagnosis model, and outputting an equipment fault diagnosis result.
Further, the step S1 includes the steps of:
s101, acquiring historical fault data of equipment, marking the equipment data according to the historical fault data, and taking the marked equipment data as fault sample data;
s102, clearing abnormal data of fault sample data;
s103, extracting the characteristics of the fault sample data after the abnormal data are removed, and finishing preprocessing the fault sample data.
Still further, the step S103 includes the steps of:
s1031, respectively extracting time domain features, frequency domain features and time-frequency domain features according to fault sample data after the abnormal data are removed;
s1032, normalizing the time domain characteristics, the frequency domain characteristics and the time-frequency domain characteristics to obtain characteristic vectors, and finishing preprocessing of fault sample data.
Still further, the expression of the normalization is as follows:
wherein the content of the first and second substances,representing normalized feature vectors, xiThe ith eigenvalue of the eigenvector is represented, N represents the number of faulty samples,the variance is represented as a function of time,represents a constant, takes 10-8。
Still further, the step S2 includes the steps of:
s201, customizing a loss function of the XGboost algorithm according to the preprocessed fault sample data;
s202, initializing a predicted value of each fault sample data;
s203, calculating a derivative of the loss function to each fault sample data predicted value;
s204, establishing an XGboost decision tree according to the derivative information;
and S205, judging whether an iteration threshold is reached, if so, obtaining a fault diagnosis model according to an XGboost decision tree obtained by iteration, and otherwise, returning to the step S203.
Still further, the loss function is expressed as follows:
wherein the content of the first and second substances,representing the loss function, n representing the total number of fault samples, yiThe true category of the fault is represented,representing the predicted value of the fault for t-1 iterations,representing a regularization term, C a constant term, ft(xi) Representing the objective function at the t-th iteration,andall represent a pre-designed hyper-parameter, TtRepresenting the number of leaf nodes, wjAnd the node weight of j leaves is represented, and T represents the number of leaf nodes.
Still further, the expression of the loss function value reduction amount of the fault diagnosis model is as follows:
wherein the content of the first and second substances,represents the amount of loss function value reduction of the failure diagnosis model,andall represent pre-designed hyper-parameters, I represents an index set of all fault samples on the root node, ILAnd IRIndex sets, g, representing fault samples in left and right child nodes after splitting, respectivelyiAnd hiRespectively, represent a quadratic function of a single variable,denotes the firstThe number of each leaf point.
The invention also provides a fault diagnosis system based on machine learning, which comprises:
the preprocessing module is used for acquiring fault sample data and preprocessing the fault sample data;
the model construction module is used for constructing a fault diagnosis model by utilizing the XGboost algorithm by utilizing the preprocessed fault sample data;
and the diagnosis module is used for acquiring the real-time equipment operation data, analyzing the real-time equipment operation data by using the fault diagnosis model and outputting an equipment fault diagnosis result.
The invention has the beneficial effects that:
(1) the invention establishes the fault diagnosis model based on the machine learning method, thereby realizing the intelligent diagnosis of the equipment.
(2) In order to improve the accuracy of equipment fault diagnosis, firstly, acquired fault sample data is preprocessed, including abnormal data clearing and dimension reduction, meanwhile, a loss function of an XGboost algorithm is defined, a decision tree is constructed, a fault diagnosis model is constructed, and fault diagnosis is carried out on equipment by combining a feature vector after dimension reduction, so that equipment fault diagnosis with a complex fault mechanism can be solved, and potential safety hazards of the equipment are effectively reduced.
(3) According to the method, the abnormal data of the fault sample data are eliminated, so that the effectiveness of the sample data is improved, and the accuracy of model training is facilitated.
(4) According to the method, a fault diagnosis model is constructed by self-defining a loss function of an XGboost algorithm, the position index of a fault sample at a leaf node of a tree is determined by using the internal structure of the tree, and meanwhile, the regularization term is used for smoothly learning the weight, so that the fault diagnosis model is prevented from being over-fitted, and the trained fault diagnosis model has strong generalization capability.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a schematic diagram of the system of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined by the appended claims, and all changes that can be made by the invention using the inventive concept are intended to be protected.
Example 1
As shown in fig. 1, the present invention provides a fault diagnosis method based on machine learning, which is implemented as follows:
s1, acquiring fault sample data, and preprocessing the fault sample data, wherein the method comprises the following steps:
s101, acquiring historical fault data of equipment, marking the equipment data according to the historical fault data, and taking the marked equipment data as fault sample data;
s102, clearing abnormal data of fault sample data;
s103, extracting the characteristics of the fault sample data after the abnormal data are removed, and finishing the preprocessing of the fault sample data, wherein the method for realizing the preprocessing comprises the following steps:
s1031, respectively extracting time domain features, frequency domain features and time-frequency domain features according to fault sample data after the abnormal data are removed;
s1032, normalizing the time domain characteristics, the frequency domain characteristics and the time-frequency domain characteristics to obtain characteristic vectors, and finishing preprocessing fault sample data;
the expression for the normalization is as follows:
wherein the content of the first and second substances,representing normalized feature vectors, xiThe ith eigenvalue of the eigenvector is represented, N represents the number of faulty samples,the variance is represented as a function of time,represents a constant, takes 10-8;
S2, constructing a fault diagnosis model by utilizing the preprocessed fault sample data and the XGboost algorithm, wherein the method comprises the following steps:
s201, according to the preprocessed fault sample data, customizing a loss function:
wherein the content of the first and second substances,representing the loss function, n representing the total number of fault samples, yiThe true category of the fault is represented,representing the predicted value of the fault for t-1 iterations,representing a regularization term, C a constant term, ft(xi) Representing the objective function at the t-th iteration,andall represent a pre-designed hyper-parameter, TtRepresenting the number of leaf nodes, wjRepresenting the weight of the node of j leaves, and T representing the number of the leaf nodes;
s202, initializing a predicted value of each fault sample data;
s203, calculating a derivative of the loss function to each predicted value of the fault sample data;
s204, establishing an XGboost decision tree according to the derivative information;
s205, judging whether an iteration threshold is reached, if so, obtaining a fault diagnosis model according to an XGboost decision tree obtained by iteration, otherwise, returning to the step S203;
an expression of the loss function value reduction amount of the failure diagnosis model is as follows:
wherein, the first and the second end of the pipe are connected with each other,represents the amount of loss function value reduction of the failure diagnosis model,andall represent pre-designed hyper-parameters, I represents an index set of all fault samples on the root node, ILAnd IRIndex sets, g, representing fault samples in left and right child nodes after splitting, respectivelyiAnd hiRespectively, represent a quadratic function of a single variable,denotes the firstOne leaf pointThe number of the cells;
and S3, acquiring the real-time equipment operation data, analyzing the real-time equipment operation data by using the fault diagnosis model, and outputting an equipment fault diagnosis result.
The invention establishes the fault diagnosis model based on the machine learning method, thereby realizing the intelligent diagnosis of the equipment.
Example 2
As shown in fig. 2, the present invention provides a fault diagnosis system based on machine learning, including:
the preprocessing module is used for acquiring fault sample data and preprocessing the fault sample data;
the model construction module is used for constructing a fault diagnosis model by utilizing the XGboost algorithm by utilizing the preprocessed fault sample data;
and the diagnosis module is used for acquiring the real-time equipment operation data, analyzing the real-time equipment operation data by using the fault diagnosis model and outputting an equipment fault diagnosis result.
The fault diagnosis system based on machine learning provided by the embodiment shown in fig. 2 can execute the technical scheme shown in the fault diagnosis method based on machine learning in the above method embodiment, and the implementation principle and the beneficial effect are similar, and are not described herein again.
In the embodiment of the invention, the functional units can be divided according to the fault diagnosis method based on machine learning, for example, each function can be divided into each functional unit, or two or more functions can be integrated into one processing unit. The integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software functional unit. It should be noted that the division of the cells in the present invention is schematic, and is only a logical division, and there may be another division manner in actual implementation.
In the embodiment of the invention, in order to realize the principle and the beneficial effect of the fault diagnosis method based on machine learning, the fault diagnosis system based on machine learning comprises a hardware structure and/or a software module which are corresponding to each function. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware and/or combinations of hardware and computer software, where a function is performed in a hardware or computer software-driven manner, and that the function described may be implemented in any suitable manner for each particular application depending upon the particular application and design constraints imposed on the technology, but such implementation is not to be considered as beyond the scope of the present application.
In the embodiment of the invention, in order to improve the accuracy of equipment fault diagnosis, acquired fault sample data is preprocessed firstly, including abnormal data removal and dimension reduction, meanwhile, a loss function of an XGboost algorithm of the XGboost is defined, a decision tree is constructed to construct a fault diagnosis model, and fault diagnosis is carried out on equipment by combining a feature vector after dimension reduction, so that the equipment fault diagnosis with a complex fault mechanism can be solved, the potential safety hazard of the equipment is effectively reduced, and compared with the traditional equipment fault diagnosis method, the method has the advantages of automation, intellectualization and high diagnosis accuracy.
Claims (8)
1. A fault diagnosis method based on machine learning is characterized by comprising the following steps:
s1, acquiring fault sample data and preprocessing the fault sample data;
s2, constructing a fault diagnosis model by utilizing the XGboost algorithm and utilizing the preprocessed fault sample data;
and S3, acquiring the real-time equipment operation data, analyzing the real-time equipment operation data by using the fault diagnosis model, and outputting an equipment fault diagnosis result.
2. The machine learning-based fault diagnosis method according to claim 1, wherein the step S1 includes the steps of:
s101, acquiring historical fault data of equipment, marking the equipment data according to the historical fault data, and taking the marked equipment data as fault sample data;
s102, clearing abnormal data of fault sample data;
s103, extracting the characteristics of the fault sample data after the abnormal data are removed, and finishing preprocessing the fault sample data.
3. The machine learning-based fault diagnosis method according to claim 2, wherein the step S103 includes the steps of:
s1031, respectively extracting time domain features, frequency domain features and time-frequency domain features according to fault sample data after the abnormal data are removed;
s1032, normalizing the time domain characteristics, the frequency domain characteristics and the time-frequency domain characteristics to obtain characteristic vectors, and finishing preprocessing of fault sample data.
4. The machine learning-based fault diagnosis method according to claim 3, wherein the expression of the normalization is as follows:
5. The machine-learning-based fault diagnosis method according to claim 1, wherein the step S2 includes the steps of:
s201, customizing a loss function of the XGboost algorithm according to the preprocessed fault sample data;
s202, initializing a predicted value of each fault sample data;
s203, calculating a derivative of the loss function to each fault sample data predicted value;
s204, establishing a decision tree according to the derivative information;
and S205, judging whether an iteration threshold is reached, if so, obtaining a fault diagnosis model according to a decision tree obtained by iteration, and otherwise, returning to the step S203.
6. The machine-learning-based fault diagnosis method according to claim 5, wherein the loss function is expressed as follows:
wherein the content of the first and second substances,representing the loss function, n representing the total number of fault samples, yiThe true category of the fault is represented,representing the predicted value of the fault for t-1 iterations,representing a regularization term, C a constant term, ft(xi) Representing the objective function at the t-th iteration,andall represent pre-designed hyper-parametersNumber, TtRepresenting the number of leaf nodes, wjAnd the node weight of j leaves is represented, and T represents the number of leaf nodes.
7. The machine-learning-based fault diagnosis method according to claim 5, wherein the expression of the amount of reduction of the loss function value of the fault diagnosis model is as follows:
wherein the content of the first and second substances,represents the amount of loss function value reduction of the failure diagnosis model,andall represent pre-designed hyper-parameters, I represents an index set of all fault samples on the root node, ILAnd IRIndex sets, g, representing fault samples in left and right child nodes after splitting, respectivelyiAnd hiRespectively, represent a quadratic function of a single variable,is shown asThe number of each leaf point.
8. A machine learning based fault diagnosis system, comprising:
the preprocessing module is used for acquiring fault sample data and preprocessing the fault sample data;
the model construction module is used for constructing a fault diagnosis model by utilizing the XGboost algorithm by utilizing the preprocessed fault sample data;
and the diagnosis module is used for acquiring the real-time equipment operation data, analyzing the real-time equipment operation data by using the fault diagnosis model and outputting an equipment fault diagnosis result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210531762.9A CN114638384A (en) | 2022-05-17 | 2022-05-17 | Fault diagnosis method and system based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210531762.9A CN114638384A (en) | 2022-05-17 | 2022-05-17 | Fault diagnosis method and system based on machine learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114638384A true CN114638384A (en) | 2022-06-17 |
Family
ID=81952933
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210531762.9A Pending CN114638384A (en) | 2022-05-17 | 2022-05-17 | Fault diagnosis method and system based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114638384A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115169650A (en) * | 2022-06-20 | 2022-10-11 | 四川观想科技股份有限公司 | Equipment health prediction method for big data analysis |
CN115328076A (en) * | 2022-07-19 | 2022-11-11 | 北京普利永华科技发展有限公司 | Quality detection method and system suitable for detecting aircraft control system |
CN115600695A (en) * | 2022-09-06 | 2023-01-13 | 北京航天计量测试技术研究所(Cn) | Fault diagnosis method of metering equipment |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109829236A (en) * | 2019-01-31 | 2019-05-31 | 浙江工业大学 | A kind of Compressor Fault Diagnosis method based on XGBoost feature extraction |
CN109840541A (en) * | 2018-12-05 | 2019-06-04 | 国网辽宁省电力有限公司信息通信分公司 | A kind of network transformer Fault Classification based on XGBoost |
CN111947928A (en) * | 2020-08-10 | 2020-11-17 | 山东大学 | Multi-source information fusion bearing fault prediction system and method |
CN111967535A (en) * | 2020-09-04 | 2020-11-20 | 安徽大学 | Fault diagnosis method and device for temperature sensor in grain storage management scene |
CN112304613A (en) * | 2020-10-30 | 2021-02-02 | 浙江运达风电股份有限公司 | Wind turbine generator bearing early warning method based on feature fusion |
CN112508053A (en) * | 2020-11-10 | 2021-03-16 | 泽恩科技有限公司 | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework |
CN112926400A (en) * | 2021-01-29 | 2021-06-08 | 华南理工大学 | Intelligent diagnosis method and system for leakage fault in hydraulic cylinder based on data driving |
-
2022
- 2022-05-17 CN CN202210531762.9A patent/CN114638384A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109840541A (en) * | 2018-12-05 | 2019-06-04 | 国网辽宁省电力有限公司信息通信分公司 | A kind of network transformer Fault Classification based on XGBoost |
CN109829236A (en) * | 2019-01-31 | 2019-05-31 | 浙江工业大学 | A kind of Compressor Fault Diagnosis method based on XGBoost feature extraction |
CN111947928A (en) * | 2020-08-10 | 2020-11-17 | 山东大学 | Multi-source information fusion bearing fault prediction system and method |
CN111967535A (en) * | 2020-09-04 | 2020-11-20 | 安徽大学 | Fault diagnosis method and device for temperature sensor in grain storage management scene |
CN112304613A (en) * | 2020-10-30 | 2021-02-02 | 浙江运达风电股份有限公司 | Wind turbine generator bearing early warning method based on feature fusion |
CN112508053A (en) * | 2020-11-10 | 2021-03-16 | 泽恩科技有限公司 | Intelligent diagnosis method, device, equipment and medium based on integrated learning framework |
CN112926400A (en) * | 2021-01-29 | 2021-06-08 | 华南理工大学 | Intelligent diagnosis method and system for leakage fault in hydraulic cylinder based on data driving |
Non-Patent Citations (1)
Title |
---|
吴定会 等: "基于多特征融合与XGBoost的风机轴承故障诊断", 《传感器与微系统》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115169650A (en) * | 2022-06-20 | 2022-10-11 | 四川观想科技股份有限公司 | Equipment health prediction method for big data analysis |
CN115169650B (en) * | 2022-06-20 | 2022-11-22 | 四川观想科技股份有限公司 | Equipment health prediction method for big data analysis |
CN115328076A (en) * | 2022-07-19 | 2022-11-11 | 北京普利永华科技发展有限公司 | Quality detection method and system suitable for detecting aircraft control system |
CN115600695A (en) * | 2022-09-06 | 2023-01-13 | 北京航天计量测试技术研究所(Cn) | Fault diagnosis method of metering equipment |
CN115600695B (en) * | 2022-09-06 | 2023-10-17 | 北京航天计量测试技术研究所 | Fault diagnosis method for metering equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114638384A (en) | Fault diagnosis method and system based on machine learning | |
Ren et al. | A novel model with the ability of few-shot learning and quick updating for intelligent fault diagnosis | |
CN109639739B (en) | Abnormal flow detection method based on automatic encoder network | |
Xu et al. | CFCNN: A novel convolutional fusion framework for collaborative fault identification of rotating machinery | |
Zheng et al. | Research on rolling bearing fault diagnosis of small dataset based on a new optimal transfer learning network | |
Chen et al. | Deep balanced cascade forest: An novel fault diagnosis method for data imbalance | |
WO2023151488A1 (en) | Model training method, training device, electronic device and computer-readable medium | |
Zhang et al. | A novel data-driven method based on sample reliability assessment and improved CNN for machinery fault diagnosis with non-ideal data | |
CN115791174B (en) | Rolling bearing abnormality diagnosis method, system, electronic equipment and storage medium | |
Liu et al. | Dynamic deep learning algorithm based on incremental compensation for fault diagnosis model | |
Liu et al. | A novel method for diagnosis of bearing fault using hierarchical multitasks convolutional neural networks | |
CN114609994A (en) | Fault diagnosis method and device based on multi-granularity regularization rebalance incremental learning | |
CN115112372A (en) | Bearing fault diagnosis method and device, electronic equipment and storage medium | |
CN110187206B (en) | Fault detection method for suspension system in non-Gaussian process under complex working condition | |
CN117591950A (en) | Rolling bearing variable working condition fault diagnosis method, device, terminal and storage medium | |
CN115293201A (en) | Bearing fault diagnosis method and system based on multi-information fusion | |
Wang et al. | A novel rolling bearing fault diagnosis method based on adaptive denoising convolutional neural network under noise background | |
CN111766513B (en) | Capsule network-based variable-working-condition multi-fault diagnosis method for three-phase induction motor | |
Zheng et al. | An unsupervised transfer learning method based on SOCNN and FBNN and its application on bearing fault diagnosis | |
CN117390411A (en) | Variable working condition bearing fault diagnosis method based on meta-shift learning | |
CN112422546A (en) | Network anomaly detection method based on variable neighborhood algorithm and fuzzy clustering | |
WO2023231374A1 (en) | Semi-supervised fault detection and analysis method and apparatus for mechanical device, terminal, and medium | |
CN116738338A (en) | Small sample fault diagnosis method based on multi-scale integrated LightGBM | |
CN113610148B (en) | Fault diagnosis method based on bias weighted AdaBoost | |
CN116304587A (en) | Rolling bearing degradation trend prediction method based on CAE and AGRU |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220617 |