CN111579243B - Rolling bearing intelligent diagnosis system based on deep migration learning - Google Patents
Rolling bearing intelligent diagnosis system based on deep migration learning Download PDFInfo
- Publication number
- CN111579243B CN111579243B CN202010554601.2A CN202010554601A CN111579243B CN 111579243 B CN111579243 B CN 111579243B CN 202010554601 A CN202010554601 A CN 202010554601A CN 111579243 B CN111579243 B CN 111579243B
- Authority
- CN
- China
- Prior art keywords
- data
- intelligent
- rolling bearing
- maintenance
- fault
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/04—Bearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/251—Fusion techniques of input or preprocessed data
-
- 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
- G06N3/045—Combinations of networks
Abstract
The invention provides a rolling bearing intelligent diagnosis system based on deep transfer learning, which comprises an intelligent sensing module, a communication module and an intelligent operation and maintenance module; the intelligent sensing module acquires the operation parameter information of the rolling bearing in a multilink mode, the operation parameter information is preprocessed through the Invitta TX2, and the preprocessed data are transmitted to the intelligent operation and maintenance module through the communication module to be subjected to intelligent diagnosis and operation and maintenance management. A fault identification and residual service life prediction component in the intelligent operation and maintenance module diagnoses the real-time operation state of the rolling bearing and predicts the residual service life; and according to the state identification and prediction result, the operation and maintenance management component carries out optimization management on the operation scheduling, the equipment resource and the spare part storage of the equipment. The invention can monitor the rolling bearing operation state in real time, provide intelligent operation, maintenance and management decision for enterprises, improve the operation efficiency of the equipment and realize the maximization of enterprise benefits.
Description
Technical Field
The invention discloses an intelligent rolling bearing diagnosis system based on deep migration learning, and belongs to the technical field of mechanical intelligent operation and maintenance.
Background
With the rapid development of the mechanical equipment industry in China, the structure of the equipment is increasingly refined and complicated. As the operating environment of mechanical equipment is more and more complex and changeable, the problems of part aging, reliability reduction and the like of the equipment inevitably occur in the long-term operation process, and a new challenge is provided for the health management and intelligent operation and maintenance of the equipment. The rolling bearing is one of the core parts of mechanical equipment, and the safe operation of the rolling bearing directly influences the normal operation of the equipment. How to identify the fault type of the bearing, predict the residual life and manage the operation and maintenance is always the key point of research on intelligent operation and maintenance of mechanical equipment. The service life of the rolling bearing is prolonged to the maximum extent, maintenance and component replacement are reasonably arranged, and the unplanned shutdown of equipment is reduced, which becomes more important.
In recent years, with the continuous development of sensor technology, deep learning technology has been applied to fault diagnosis and residual prediction of mechanical equipment by virtue of strong data processing capability. However, it is difficult to generalize the failure diagnosis knowledge learned from the source domain to the target domain due to a change in the operating conditions of the device, additional noise, and the like. In general, the robustness of a model trained for a large amount of time is poor, so that the rolling bearing fault diagnosis and residual life prediction model are difficult to meet the real-time performance, and the application of the rolling bearing fault diagnosis and residual life prediction model in rolling bearing fault identification and residual life prediction is limited.
Disclosure of Invention
The invention provides an intelligent diagnosis system for a rolling bearing based on deep migration learning, wherein an intelligent sensing module is used for collecting and preprocessing the operation information of the rolling bearing in real time; the data are transmitted to the cloud end through the communication module, and the intelligent operation and maintenance module is used for carrying out fault identification and residual life prediction on the health state of the rolling bearing; and according to the diagnosis and prediction results, the operation and maintenance management component carries out optimization management on the construction operation scheduling and the equipment resources of the equipment.
The technical scheme of the invention is as follows:
an intelligent rolling bearing diagnosis system based on deep migration learning comprises an intelligent sensing module, a communication module and an intelligent operation and maintenance module;
the intelligent sensing module comprises multilink data acquisition and Invitta TX 2; the multi-link data acquisition is used for acquiring multi-source data of each rolling bearing of the equipment and comprises a vibration signal, an image signal, an acoustic emission signal, a pressure signal, a current signal and a temperature signal;
the Yingvian TX2 is an embedded terminal capable of being developed secondarily, and has data preprocessing functions of denoising, data labeling, removing abnormal values (such as data acquired in a shutdown condition), correlation analysis, data compression and the like on acquired multilink information;
the communication module is mainly used for preprocessing multi-source data acquired in real time by using a field bus and an industrial Ethernet and then transmitting the preprocessed multi-source data to the cloud intelligent operation and maintenance module;
the intelligent operation and maintenance module comprises a fault identification and residual life prediction component and an operation and maintenance management component; the intelligent operation and maintenance module is packaged in the Ali cloud, so that the high efficiency of the intelligent operation and maintenance module on processing a large amount of data can be ensured, and the development cost of an enterprise is saved.
The specific steps of the fault identification and residual life prediction component work are as follows:
step 1: the Aliyun database stores two parts including historical data and online data, and multi-source heterogeneous data fusion processing is carried out on the historical data;
step 2: inputting the fused data into a depth self-adaptive network fault recognition model for training;
and step 3: meanwhile, inputting the fused data into a depth adaptive network prediction model for training;
the structure of the depth self-adaptive network is formed by 7 layers of networks; the first 4 layers are formed by convolution Gated recycling Unit (ConvGRU), the 5-6 layers are adaptation layers added with Multi-core Maximum Mean error (MK-MMD), and the last layer is a Softmax layer (for fault diagnosis) or a prediction layer (for residual life prediction). Wherein, the first 2 layers of the network are frozen (frozen) processed; and adding a Fine-tune (Fine-tune) technology between the 3 rd and 4 th layers for random initialization.
ConvGRU is defined as follows:
wherein sigma is an activation function of sigmoid; as Hadamard operation based on matrix elements; is a convolution operation; x is the number oftIs an input signal; r ist，zt，ht，
ht-1Respectively as a refresh gate, a reset gate, and a hidden gateHidden state, candidate hidden state and hidden state at the previous moment; wr，Wz，WhRespectively representing the weight matrixes among the input layer, the updating gate, the resetting gate and the hidden state; u shaper，Uz，UhA weight matrix which is a cyclic concatenation; br，bz，bhIs the corresponding deviation.
Reducing inter-domain differences by optimizing the maximum mean error of the source domain data and the target domain data on a Regenerative Kernel Hilbert Space (RKHS) through MK-MMD, and learning a feature representation with domain invariant characteristics, wherein the square expression of MK-MMD is:
where p and q are source domain data xsAnd target domain data xtThe probability value of (E [.]For mathematical expectation, φ (. eta.) is the feature map, HkIs a universal regenerative nuclear hilbert space with a characteristic nucleus k.
And 4, step 4: performing multi-source heterogeneous fusion processing on online data obtained in real time;
and 5: carrying out anomaly detection on the fused data, and judging whether the data exceeds an early warning threshold value;
if the fault does not exceed the early warning threshold, continuing to monitor the running condition of the rolling bearing, and if the fault exceeds the early warning threshold, performing fault diagnosis by using the fault recognition model trained in the step 2;
step 6: further judging the fault grade according to the fault model diagnosis result;
and 7: and (3) predicting the residual service life of the rolling bearing in real time by using the prediction model trained in the step (3), and transmitting the prediction result to the operation and maintenance management component for further analysis.
The operation and maintenance management component mainly realizes the functions of operation optimization scheduling, equipment resource management, spare part inventory management and the like of the rolling bearing.
And according to the prediction result, dynamic optimization management is carried out on the replacement of the rolling bearing and the utilization of equipment resources, so that the utilization rate and the action efficiency of the equipment are improved. Spare part scheduling and inventory management are dynamically optimized, downtime is reduced, and maximum utilization of enterprises is achieved.
The invention has the beneficial effects that: according to the intelligent operation and maintenance device, the intelligent sensing module is used for collecting multi-source data of the rolling bearing, and the communication module is used for transmitting the data to the intelligent operation and maintenance module for analysis and processing, so that the intelligent operation and maintenance of the device are realized. The intelligent operation and maintenance module is used for identifying the real-time state of a rolling bearing of the equipment and predicting the residual life of the rolling bearing; and the operation and maintenance management component performs optimal construction operation and spare part inventory management according to the prediction result, so that an operation and maintenance mechanism for complementing predictive operation and maintenance and operation and maintenance afterwards is established, the production and production efficiency of enterprises is improved, and the economic cost is saved.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
FIG. 2 is a flow chart of the operation of the intelligent operation and maintenance module of the present invention.
FIG. 3 is a schematic diagram of a deep adaptive neural network according to the present invention.
Detailed Description
In order to clearly illustrate the implementation of the present invention or the technical solutions in the prior art, the present invention will be further described and illustrated with reference to the accompanying drawings and examples, but the present invention is not limited to the scope.
Example (b): as shown in fig. 1, the rolling bearing intelligent diagnosis system based on deep migration learning includes an intelligent sensing module, a communication module and an intelligent operation and maintenance module. The intelligent sensing module collects multi-source data of the rolling bearing and carries out preprocessing, then the data are transmitted to the intelligent operation and maintenance module through the data transmission module, and finally intelligent monitoring and operation and maintenance management of equipment are carried out on the operation state of the rolling bearing in the intelligent operation and maintenance module.
Specifically, the intelligent sensing module comprises multilink data acquisition and invida TX 2.
Furthermore, the multilink data acquisition mainly has the function of acquiring real-time operation information of the rolling bearing, wherein the real-time operation information comprises key information such as vibration signals, image signals, acoustic emission signals, pressure signals, current signals, temperature signals and the like, and the operation state of the rolling bearing is comprehensively reflected.
The great TX2 is an embedded device capable of secondary development, and has the main functions of performing data preprocessing tasks such as denoising, data labeling, removing abnormal values (such as data acquired in a shutdown condition), correlation analysis and data compression on acquired multilink information.
The communication module mainly adopts a field bus and an industrial Ethernet technology to transmit data, and is a bridge for data transmission in the intelligent sensing module and the intelligent operation and maintenance module. The data transmission mode has the advantages of large data transmission quantity, convenient data transmission mode, low economic cost and the like.
The intelligent operation and maintenance module comprises a fault identification and residual life prediction component and an operation and maintenance management component, and the specific working steps are shown in fig. 2.
Further, the working steps of fault identification and residual life prediction are as follows:
step 1: the data in the intelligent operation and maintenance module database comprises two parts, namely historical data (source domain data) and online data (target domain data), and the multi-source heterogeneous data fusion processing is firstly carried out on the historical data stored by the intelligent operation and maintenance module;
step 2: inputting the fused data into a depth self-adaptive network fault recognition model for training;
and step 3: meanwhile, inputting the fused data into a depth adaptive network prediction model for training;
the structure of the deep neural adaptive network comprises a 7-layer structure, as shown in fig. 3. The first 4 layers are formed by convolution Gated recycling units (ConvGRUs), the 5-6 layers are adaptation layers added with Multi-core Maximum Mean error (MK-MMD), and the last layer is a Softmax layer (for fault diagnosis) or a prediction layer (for residual life prediction). Wherein the first 2 layers of the network are subjected to a freeze (frozen) process; and adding a Fine-tune (Fine-tune) technology between the 3 rd and 4 th layers for random initialization.
ConvGRU is defined as follows:
wherein sigma is an activation function of sigmoid; as Hadamard operation based on matrix elements; is a convolution operation; x is the number oftIs an input signal; r ist，zt，ht，
ht-1Respectively an update gate, a reset gate, a hidden state, a candidate hidden state and a hidden state at the previous moment; wr，Wz，WhRespectively representing the weight matrixes among the input layer, the updating gate, the resetting gate and the hidden state; u shaper，Uz，UhA weight matrix which is a cyclic concatenation; br，bz，bhIs the corresponding deviation.
Reducing inter-domain differences by optimizing the maximum mean error of the source domain data and the target domain data on a Regenerative Kernel Hilbert Space (RKHS) through MK-MMD, and learning a feature representation with domain invariant characteristics, wherein the square expression of MK-MMD is:
where p and q are source domain data xsAnd target domain data xtThe probability value of (E [.]For mathematical expectation, φ (. eta.) is the feature map, HkIs a universal regenerative nuclear hilbert space with a characteristic nucleus k.
And 4, step 4: performing multi-source heterogeneous fusion processing on online data obtained in real time to obtain the characteristics of signals;
and 5: carrying out abnormity detection on the characteristics of the online data, and judging whether the data exceeds an early warning threshold value;
if the early warning threshold value is 20% of the normal value, the equipment is abnormal, if the early warning threshold value is not exceeded, the running state of the rolling bearing is continuously monitored, and if the early warning threshold value is exceeded, the fault diagnosis is carried out by using the fault diagnosis model trained in the step 2;
step 6: judging the fault grade according to the recognition result of the fault recognition model;
and 7: meanwhile, the residual service life of the rolling bearing is predicted in real time by using the prediction model trained in the step 3, and the prediction result is transmitted to the operation and maintenance management component for further processing.
The functions of the operation and maintenance management component comprise: construction operation optimization scheduling, equipment resource management and spare part inventory intelligent management.
According to the output results of the intelligent fault identification and residual life prediction component, dynamic optimization management is performed on equipment resource utilization and construction operation scheduling, and the equipment utilization rate is improved; meanwhile, spare part scheduling and inventory management are dynamically optimized, the consistency of equipment operation is guaranteed, the downtime is reduced, and the maximum utilization of enterprises is realized.
The intelligent operation and maintenance module is arranged in Aliyun for packaging, and visual technical workers can perform intelligent diagnosis and equipment operation and maintenance management on the operation condition of the rolling bearing on site or through the intelligent terminal, so that the normal operation of the production work of enterprises is ensured.
While the present invention has been described in detail with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Claims (1)
1. The rolling bearing intelligent diagnosis system based on the deep migration learning is characterized by comprising an intelligent sensing module, a communication module and an intelligent operation and maintenance module;
the intelligent sensing module comprises a multilink data acquisition part and an English WEIDA TX 2; the multilink data acquisition part acquires multisource data of each rolling bearing of the equipment, wherein the multisource data comprises a vibration signal, an image signal, an acoustic emission signal, a pressure signal, a current signal and a temperature signal;
the Yingvian TX2 is an embedded terminal capable of being developed secondarily, and is used for denoising, data labeling, removing abnormal values, analyzing correlation and compressing collected multilink data information;
the communication module is mainly used for preprocessing multi-source data acquired in real time by using a field bus and an industrial Ethernet and then transmitting the preprocessed multi-source data to the cloud intelligent operation and maintenance module;
the intelligent operation and maintenance module comprises a fault identification and residual life prediction component and an operation and maintenance management component, and is packaged in the Aliskiu;
the specific steps of the fault identification and residual life prediction component work are as follows:
step 1: historical data and online data are stored in the Aliyun database, and the historical data is subjected to multi-source heterogeneous data fusion processing;
step 2: inputting the fused data into a depth self-adaptive network fault recognition model for training;
and step 3: meanwhile, inputting the fused data into a depth adaptive network prediction model for training;
the structure of the depth self-adaptive network is formed by 7 layers of networks; the first 4 layers are formed by convolution gating circulation unit layers, the 5-6 layers are adaptation layers added with the multi-core maximum mean error, and the last layer is a Softmax layer or a prediction layer; wherein, the first 2 layers of the network are frozen; adding a fine adjustment technology between the 3 rd and 4 th layers for random initialization;
ConvGRU is defined as follows:
wherein sigma is an activation function of sigmoid; as Hadamard operation based on matrix elements; is a convolution operation; x is the number oftTo input, rt，zt，ht，
ht-1Respectively an update gate, a reset gate, a hidden state, a candidate hidden state and a hidden state at the previous moment; wr，Wz，WhRespectively representing the weight matrixes among the input layer, the updating gate, the resetting gate and the hidden state; u shaper，Uz，UhA weight matrix which is a cyclic concatenation; br，bz，bhIs the corresponding deviation;
reducing inter-domain difference by optimizing the maximum mean error of the source domain data and the target domain data on a regenerative kernel Hilbert space through MK-MMD, and learning a feature representation with domain invariant characteristics, wherein the square expression of the MK-MMD is as follows:
where p and q are source domain data xsAnd target domain data xtThe probability value of (E [.]For mathematical expectation, φ (. eta.) is the feature map, HkIs a universal regenerative nuclear hilbert space with a characteristic nucleus k;
and 4, step 4: performing multi-source heterogeneous fusion processing on online data obtained in real time;
and 5: carrying out anomaly detection on the fused data, and judging whether the data exceeds an early warning threshold value;
if the fault does not exceed the early warning threshold, continuing to monitor the running condition of the rolling bearing, and if the fault exceeds the early warning threshold, performing fault diagnosis by using the fault recognition model trained in the step 2;
step 6: further judging the fault grade according to the fault model diagnosis result;
and 7: predicting the residual service life of the rolling bearing in real time by using the prediction model trained in the step 3, and transmitting a prediction result to an operation and maintenance management component for further analysis;
the operation and maintenance management component mainly realizes the operation optimization scheduling, equipment resource management and spare part inventory management of the rolling bearing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010554601.2A CN111579243B (en) | 2020-06-17 | 2020-06-17 | Rolling bearing intelligent diagnosis system based on deep migration learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010554601.2A CN111579243B (en) | 2020-06-17 | 2020-06-17 | Rolling bearing intelligent diagnosis system based on deep migration learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111579243A CN111579243A (en) | 2020-08-25 |
| CN111579243B true CN111579243B (en) | 2021-04-20 |
Family
ID=72125750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010554601.2A Active CN111579243B (en) | 2020-06-17 | 2020-06-17 | Rolling bearing intelligent diagnosis system based on deep migration learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111579243B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036547B (en) * | 2020-08-28 | 2023-09-22 | 徐工汉云技术股份有限公司 | Rolling bearing residual life prediction method combining automatic feature extraction with LSTM |
| CN112504678B (en) * | 2020-11-12 | 2022-12-23 | 重庆科技学院 | Motor bearing fault diagnosis method based on knowledge distillation |
| CN112465030B (en) * | 2020-11-28 | 2022-06-07 | 河南财政金融学院 | Multi-source heterogeneous information fusion fault diagnosis method based on two-stage transfer learning |
| CN112629863B (en) * | 2020-12-31 | 2022-03-01 | 苏州大学 | Bearing fault diagnosis method for dynamic joint distribution alignment network under variable working conditions |
| CN113051689B (en) * | 2021-04-25 | 2022-03-25 | 石家庄铁道大学 | Bearing residual service life prediction method based on convolution gating circulation network |
| CN113326590B (en) * | 2021-07-16 | 2021-10-29 | 北京博华信智科技股份有限公司 | Rolling bearing service life prediction method and device based on deep learning model |
| CN113867263A (en) * | 2021-08-27 | 2021-12-31 | 大唐互联科技(武汉)有限公司 | Intelligent cutter management system based on cloud edge cooperation and machine learning |
| CN113605984A (en) * | 2021-08-31 | 2021-11-05 | 中煤科工集团重庆研究院有限公司 | Method for judging alarm threshold value for water damage microseismic |
| CN114638060B (en) * | 2022-03-10 | 2023-02-17 | 重庆英科铸数网络科技有限公司 | Fault prediction method, system and electronic equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108414226B (en) * | 2017-12-25 | 2019-07-19 | 哈尔滨理工大学 | Fault Diagnosis of Roller Bearings under variable working condition based on feature transfer learning |
| CN108304927A (en) * | 2018-01-25 | 2018-07-20 | 清华大学 | Bearing fault modality diagnostic method and system based on deep learning |
| KR102235745B1 (en) * | 2018-08-10 | 2021-04-02 | 네이버 주식회사 | Method for training a convolutional recurrent neural network and for semantic segmentation of inputted video using the trained convolutional recurrent neural network |
| CN109376578A (en) * | 2018-08-27 | 2019-02-22 | 杭州电子科技大学 | A kind of small sample target identification method based on depth migration metric learning |
| CN110647867B (en) * | 2019-10-09 | 2022-05-13 | 中国科学技术大学 | Bearing fault diagnosis method and system based on self-adaptive anti-noise neural network |
-
2020
- 2020-06-17 CN CN202010554601.2A patent/CN111579243B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111579243A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111579243B (en) | Rolling bearing intelligent diagnosis system based on deep migration learning | |
| CN111596604B (en) | Intelligent fault diagnosis and self-healing control system and method for engineering equipment based on digital twinning | |
| CN102520697B (en) | Onsite information preprocessing method of remote cooperative diagnosis | |
| US20160299938A1 (en) | Anomaly detection system and method | |
| CN109872003B (en) | Object state prediction method, object state prediction system, computer device, and storage medium | |
| CN111340282B (en) | DA-TCN-based method and system for estimating residual service life of equipment | |
| CN112668237A (en) | Digital twin model based on industrial internet cloud platform and construction method thereof | |
| CN112906775B (en) | Equipment fault prediction method and system | |
| CN112926749A (en) | Intelligent power grid information equipment monitoring system and method | |
| Peco Chacón et al. | State of the art of artificial intelligence applied for false alarms in wind turbines | |
| CN116010900A (en) | Multi-scale feature fusion gearbox fault diagnosis method based on self-attention mechanism | |
| CN116308304A (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| Zhang et al. | A novel fault diagnosis method for wind turbine based on adaptive multivariate time-series convolutional network using SCADA data | |
| CN115114856A (en) | Intelligent manufacturing production line operation system based on digital twin | |
| CN116520806A (en) | Intelligent fault diagnosis system and method for industrial system | |
| CN108805427B (en) | Power distribution network running state risk early warning system based on big data | |
| Liu et al. | Hydraulic system fault diagnosis of the chain jacks based on multi-source data fusion | |
| Qin et al. | Dynamic weighted federated remaining useful life prediction approach for rotating machinery | |
| CN116880402A (en) | Intelligent factory cooperative control system and method thereof | |
| CN110794799A (en) | Big data system with fault diagnosis function applied to industrial production | |
| Han et al. | On fault prediction based on industrial big data | |
| Xu et al. | Total process of fault diagnosis for wind turbine gearbox, from the perspective of combination with feature extraction and machine learning: A review | |
| Yang et al. | Design of equipment online monitoring and fault diagnosis platform based on IoT | |
| Dix et al. | An AI-based alarm prediction in industrial process control systems | |
| CN113032916A (en) | Electromechanical device bearing fault prediction method based on Bayesian network of transfer learning |
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 |