CN109110608A - A kind of elevator faults prediction technique based on big data study - Google Patents
A kind of elevator faults prediction technique based on big data study Download PDFInfo
- Publication number
- CN109110608A CN109110608A CN201811246445.2A CN201811246445A CN109110608A CN 109110608 A CN109110608 A CN 109110608A CN 201811246445 A CN201811246445 A CN 201811246445A CN 109110608 A CN109110608 A CN 109110608A
- Authority
- CN
- China
- Prior art keywords
- elevator
- big data
- prediction
- model
- elevator operation
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B5/00—Applications of checking, fault-correcting, or safety devices in elevators
- B66B5/0006—Monitoring devices or performance analysers
- B66B5/0037—Performance analysers
Landscapes
- Maintenance And Inspection Apparatuses For Elevators (AREA)
- Indicating And Signalling Devices For Elevators (AREA)
Abstract
The present invention relates to a kind of elevator faults prediction techniques based on big data study, the characteristics of running big data in conjunction with complex equipment and machine Learning Theory, the big data obtained when proposing based on elevator actual motion by sensor carries out prediction and diagnostic method to the failure of elevator, it is associated with including elevator operation characteristic big data with operation reason, the complex equipment operation troubles feature extraction based on big data analysis and the elevator operation troubles based on data study predict 3 aspects.The present invention carries out noise reduction process to big data, obtains more effective data；Parameters of elevator run is analyzed, characteristic parameter is obtained；Deep neural network prediction model is established, keeps failure predication more accurate.
Description
Technical field
The present invention relates to Elevator Fault Diagnosis and prediction field, specifically a kind of elevator event based on big data study
Hinder prediction technique.
Background technique
Fault diagnosis and failure predication technology be guarantee the safe and stable operation of complex equipments such as elevator important technology it
One.Fault diagnosis technology is handled by the analysis of monitoring and its corresponding data to equipment operating status, is realized and is run to equipment
The prediction and diagnosis of failure, judge the state of equipment whether be in the concrete position that abnormality or malfunction occur or
Even specific components, predict the development trend of failure, which is widely used to Large Steam Turbine Sets, aeroplane engine
The operational monitoring of the complex equipments such as machine, express elevator controls, and be listed in Chinese intelligence equipment industrial emphases development nine are big crucial
One of intelligent basis common technology.
With the increase of equipment complexity, for equipping the monitoring run the often more, monitoring point in the presence of equipment monitoring point
Sample frequency is high, the features such as data collection time is long so that complex equipment fault diagnosis system operation data to be treated
Explosive increase is presented in amount, and the big data that hundreds of too bit-levels even clap bit-level scale is commonplace.Magnanimity runs number
According to generation, it is meant that complex equipment failure predication diagnostic techniques has welcome its big data era, also to fault diagnosis technology
Development propose new challenge.Since big data often implies the deep knowledge and valence that do not have in small data quantity much
Value could be worth and be revealed only by the intelligent analysis of big data and excavation, therefore by big data analysis and machine
Device learning art is applied to the failure predication diagnosis of equipment operational process, by excavating from complex equipment operation characteristic big data
Be out of order information, realizes the quick diagnosis of operation troubles, be in recent years big data in one of the important application of equipment field.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of elevator faults prediction technique based on big data study, packet
Include following steps:
Step 1: obtaining the history big data of elevator operation；
Step 2: to big data analysis elevator operation troubles feature extraction, as training sample；
Step 3: according to the corresponding relationship of elevator operation characteristic parameter and elevator operation troubles reason, establishing and rolled up based on depth
The elevator operation troubles prediction model of product neural network；
Step 4: in running process of elevator, elevator is obtained in real time and runs big data, and does fault characteristic information extraction,
Using depth convolutional neural networks prediction model, out of order prediction is done.
Preferably, obtain elevator operation big data process and method the following steps are included:
Step 1: establishing the sensor network of data acquisition；
Step 2: acquiring the electric current of permanent magnetic synchronous traction machine, the vibration parameters of permanent magnetic synchronous traction machine, car speed, carriage
Acceleration, the load-carrying of carriage, car casing working environment noise；
Step 3: the method to collected information according to Wavelet Modulus Maxima carries out noise reduction process, and carries out characteristic information
It extracts, obtains the elevator history run big data that can be used as prediction model training parameter.
Preferably, according to elevator operation characteristic parameter and elevator operation troubles reason corresponding relationship the following steps are included:
Step 1: the various features parameter of elevator history feature big data is analyzed；
Step 2: tracing to its source, according to priori knowledge, obtain the corresponding relationship of failure cause and elevator operation characteristic parameter；
The mapping relations that prediction model inputs X to output Y are established with this；
Step 3: failure cause being encoded, the probability of the appearance of each failure cause is as fault prediction model
Output, input of the characteristic parameter as fault prediction model.
Preferably, it establishes and elevator operation troubles prediction model of the training based on depth convolutional neural networks includes following step
It is rapid:
Step 1: after features described above supplemental characteristic is normalized, as the defeated of depth convolutional neural networks model
Enter；
Step 2: building depth convolutional neural networks model using TensorFlow；
Step 3: the input vector X based on training data, characteristic parameter as model, the probability conduct that failure cause occurs
Y is exported, physical fault reason is as Y '；
Step 4: cross entropy is calculated according to true fault reason and model prediction failure cause, using this cross entropy as mould
The loss function of type；Calculation formula are as follows:
Step 5: using batch gradient descent method, model being trained, the weight and deviation of model are constantly updated, so that damage
Function minimization is lost, until obtaining elevator faults prediction model.
Preferably, made prediction using trained fault prediction model to elevator faults the following steps are included:
Step 1: utilizing sensor network, acquire all data when elevator operation in real time；
Step 2: data filtering being carried out using the method for Wavelet Modulus Maxima to data, and carries out characteristic parameter extraction；
Step 3: characteristic parameter is input in elevator faults prediction model, obtains possible Failure probability distribution, thus right
The failure of elevator is made prediction.
The present invention
(1) method for the reason of detailed analysis elevator operation troubles occurs establishes the association structure mould of operation troubles reason
Type acquires operation characteristic big data by sensor, establishes elevator operation characteristic parameter on the basis of based on the analysis of this data
With the corresponding relationship of operation troubles reason；
(2) feature information extraction of the elevator operation troubles based on big data analysis, due in the big number of elevator operation characteristic
There is the problem of more noise in, the complex equipment signal de-noising method based on Wavelet Modulus Maxima is proposed, to feature big data
It is handled, improves the signal-to-noise ratio of complex equipment operation data.It is more for complex equipment operation characteristic big data dimension, scale is big
The problems such as, it proposes the operation troubles feature extracting method based on rough set attribute reduction, screens superfluous in operation characteristic big data
Remaining attribute obtains characteristic parameter relevant to complex equipment operation troubles；
(3) elevator faults based on depth convolutional neural networks (DCNN) are predicted, are established pre- based on elevator operation troubles
Depth convolutional neural networks (DCNN) model of survey improves the accuracy of elevator faults prediction.
The invention has the following beneficial effects and advantage:
1. pair big data carries out noise reduction process, more effective data are obtained；
2. a pair parameters of elevator run is analyzed, characteristic parameter is obtained；
3. establishing deep neural network prediction model, keep failure predication more accurate.
Detailed description of the invention
Fig. 1 is car movement data acquisition hardware structure chart of the invention；
Fig. 2 is elevator faults reason and characteristic parameter correspondence analysis figure；
Fig. 3 is depth convolutional Neural model process chart.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and embodiments.
1. the present invention relates to a kind of elevator faults prediction techniques based on big data study, referring to Fig. 1-3, including following step
It is rapid:
Step 1: obtaining the history big data of elevator operation；
Step 2: to big data analysis elevator operation troubles feature extraction, as training sample；
Step 3: according to the corresponding relationship of elevator operation characteristic parameter and elevator operation troubles reason, establishing and rolled up based on depth
The elevator operation troubles prediction model of product neural network (DCNN)
Step 4: in running process of elevator, elevator is obtained in real time and runs big data, and does fault characteristic information extraction,
Using depth convolutional neural networks (DCNN) prediction model, out of order prediction is done.
Obtain elevator operation big data process and method the following steps are included:
Step 1: establishing the sensor network of data acquisition；
Step 2: acquiring the electric current of permanent magnetic synchronous traction machine, the vibration parameters of permanent magnetic synchronous traction machine, car speed, carriage
Acceleration, the load-carrying of carriage, car casing working environment noise；
Step 3: the method to collected information according to Wavelet Modulus Maxima carries out noise reduction process, and carries out characteristic information
It extracts, obtains the elevator history run big data that can be used as prediction model training parameter.
According to elevator operation characteristic parameter and elevator operation troubles reason corresponding relationship the following steps are included:
Step 1: the various features parameter of elevator history feature big data is analyzed；
Step 2: tracing to its source, according to priori knowledge, obtain the corresponding relationship of failure cause and elevator operation characteristic parameter；
The mapping relations that prediction model inputs X to output Y are established with this；
Step 3: failure cause being encoded, the probability of the appearance of each failure cause is as fault prediction model
Output, input of the characteristic parameter as fault prediction model.
It establishes and trains the elevator operation troubles prediction model based on depth convolutional neural networks (DCNN):
Step 1: after features described above supplemental characteristic is normalized, as depth convolutional neural networks (DCNN) mould
The input of type；
Step 2: building depth convolutional neural networks model using TensorFlow；
Step 3: being based on training data, input vector X of the characteristic parameter as model, the probability that failure cause is likely to occur
As output Y, physical fault reason is as Y '；
Step 4: cross entropy is calculated according to true fault reason and model prediction failure cause, using this cross entropy as mould
The loss function of type；Calculation formula are as follows:
Step 5: using batch gradient descent method, model being trained, the weight and deviation of model are constantly updated, so that damage
Function minimization is lost, until obtaining elevator faults prediction model.
Made prediction using trained fault prediction model to elevator faults the following steps are included:
Step 1: utilizing sensor network, acquire all data when elevator operation in real time；
Step 2: data filtering being carried out using the method for Wavelet Modulus Maxima to data, and carries out characteristic parameter extraction；
Step 3: characteristic parameter is input in elevator faults prediction model, obtains possible Failure probability distribution, thus right
The failure of elevator is made prediction.
Claims (5)
1. a kind of elevator faults prediction technique based on big data study, which comprises the following steps:
Step 1: obtaining the history big data of elevator operation；
Step 2: to big data analysis elevator operation troubles feature extraction, as training sample；
Step 3: according to the corresponding relationship of elevator operation characteristic parameter and elevator operation troubles reason, establishing based on depth convolution mind
Elevator operation troubles prediction model through network；
Step 4: in running process of elevator, obtaining elevator in real time and run big data, and do fault characteristic information extraction, utilize
Depth convolutional neural networks prediction model, does out of order prediction.
2. a kind of elevator faults prediction technique based on big data study according to claim 1, which is characterized in that obtain
Elevator operation big data process and method the following steps are included:
Step 1: establishing the sensor network of data acquisition；
Step 2: acquiring the electric current of permanent magnetic synchronous traction machine, the vibration parameters of permanent magnetic synchronous traction machine, car speed, carriage and accelerate
Degree, the load-carrying of carriage, car casing working environment noise；
Step 3: the method to collected information according to Wavelet Modulus Maxima carries out noise reduction process, and carries out characteristic information and mention
It takes, obtains the elevator history run big data that can be used as prediction model training parameter.
3. a kind of elevator faults prediction technique based on big data study according to claim 1, which is characterized in that foundation
The corresponding relationship of elevator operation characteristic parameter and elevator operation troubles reason the following steps are included:
Step 1: the various features parameter of elevator history feature big data is analyzed；
Step 2: tracing to its source, according to priori knowledge, obtain the corresponding relationship of failure cause and elevator operation characteristic parameter；With this
Establish the mapping relations that prediction model inputs X to output Y；
Step 3: failure cause being encoded, the probability of the appearance of each failure cause is as the defeated of fault prediction model
Out, input of the characteristic parameter as fault prediction model.
4. a kind of elevator faults prediction technique based on big data study according to claim 1, which is characterized in that establish
And training the elevator operation troubles prediction model based on depth convolutional neural networks the following steps are included:
Step 1: the input after features described above supplemental characteristic is normalized, as depth convolutional neural networks model；
Step 2: building depth convolutional neural networks model using TensorFlow；
Step 3: the input vector X based on training data, characteristic parameter as model, the probability that failure cause occurs is as output
Y, physical fault reason is as Y '；
Step 4: cross entropy is calculated according to true fault reason and model prediction failure cause, using this cross entropy as model
Loss function；Calculation formula are as follows:
Step 5: using batch gradient descent method, model being trained, the weight and deviation of model are constantly updated, so that loss letter
Number minimizes, until obtaining elevator faults prediction model.
5. a kind of elevator faults prediction technique based on big data study according to claim 1, which is characterized in that utilize
Trained fault prediction model make prediction to elevator faults the following steps are included:
Step 1: utilizing sensor network, acquire all data when elevator operation in real time；
Step 2: data filtering being carried out using the method for Wavelet Modulus Maxima to data, and carries out characteristic parameter extraction；
Step 3: characteristic parameter is input in elevator faults prediction model, obtains possible Failure probability distribution, thus to elevator
Failure make prediction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811246445.2A CN109110608A (en) | 2018-10-25 | 2018-10-25 | A kind of elevator faults prediction technique based on big data study |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811246445.2A CN109110608A (en) | 2018-10-25 | 2018-10-25 | A kind of elevator faults prediction technique based on big data study |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109110608A true CN109110608A (en) | 2019-01-01 |
Family
ID=64855201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811246445.2A Pending CN109110608A (en) | 2018-10-25 | 2018-10-25 | A kind of elevator faults prediction technique based on big data study |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109110608A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109693983A (en) * | 2019-01-02 | 2019-04-30 | 日立楼宇技术（广州）有限公司 | Elevator faults processing method, device, server, storage medium and system |
| CN109969895A (en) * | 2019-04-15 | 2019-07-05 | 淄博东升电梯工程有限公司 | A kind of failure prediction method based on parameters of elevator run, terminal and readable storage medium storing program for executing |
| CN110008565A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | A kind of industrial process unusual service condition prediction technique based on operating parameter association analysis |
| CN110775758A (en) * | 2019-10-09 | 2020-02-11 | 浙江大学 | Elevator running health degree evaluation method based on car acceleration signal analysis |
| CN110790101A (en) * | 2019-10-12 | 2020-02-14 | 虏克电梯有限公司 | Elevator trapping false alarm identification method based on big data analysis |
| CN111908288A (en) * | 2020-07-30 | 2020-11-10 | 上海繁易信息科技股份有限公司 | TensorFlow-based elevator safety system and method |
| CN112257988A (en) * | 2020-09-29 | 2021-01-22 | 中广核工程有限公司 | Complex accident feature identification and risk early warning system and method for nuclear power plant |
| CN112758782A (en) * | 2021-01-11 | 2021-05-07 | 浙江新再灵科技股份有限公司 | Elevator fault early warning method based on Internet of things technology and coupling graph neural network |
| CN112850408A (en) * | 2021-02-05 | 2021-05-28 | 浙江新再灵科技股份有限公司 | Elevator emergency stop trapped person fault detection method based on multi-model fusion |
| CN114538234A (en) * | 2022-02-14 | 2022-05-27 | 深圳市爱丰达盛科技有限公司 | Internet of things big data elevator safe operation standard AI self-building system and method |
| WO2022105266A1 (en) * | 2020-11-17 | 2022-05-27 | 日立楼宇技术（广州）有限公司 | Elevator fault prediction method, system and apparatus, computer device, and storage medium |
| CN115028036A (en) * | 2022-05-06 | 2022-09-09 | 北京中铁电梯工程有限公司 | Elevator management method based on big data |
| CN115650006A (en) * | 2022-10-24 | 2023-01-31 | 昆山广联发通信服务有限公司 | Elevator safety monitoring and early warning method and system based on big data |
| US11993488B2 (en) | 2019-09-27 | 2024-05-28 | Otis Elevator Company | Processing service requests in a conveyance system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5767461A (en) * | 1995-02-16 | 1998-06-16 | Fujitec Co., Ltd. | Elevator group supervisory control system |
| CN104944240A (en) * | 2015-05-19 | 2015-09-30 | 重庆大学 | Elevator equipment state monitoring system based on large data technology |
| CN105095963A (en) * | 2015-08-17 | 2015-11-25 | 中国空气动力研究与发展中心高速空气动力研究所 | Method for accurately diagnosing and predicting fault of wind tunnel equipment |
| KR20170075267A (en) * | 2015-12-23 | 2017-07-03 | 현대엘리베이터주식회사 | System for prognosticating failure of elevator |
| CN107934709A (en) * | 2016-10-13 | 2018-04-20 | 郑坤丰 | Make elevator safety diagnostic system and method using elevator driving recording big data |
| CN108083044A (en) * | 2017-11-21 | 2018-05-29 | 浙江新再灵科技股份有限公司 | A kind of elevator based on big data analysis maintenance system and method on demand |
| CN108178037A (en) * | 2017-12-30 | 2018-06-19 | 武汉大学 | A kind of elevator faults recognition methods based on convolutional neural networks |
| CN108466886A (en) * | 2017-02-23 | 2018-08-31 | 无锡鸿廷科技有限公司 | A kind of elevator big data statistics early-warning system |
-
2018
- 2018-10-25 CN CN201811246445.2A patent/CN109110608A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5767461A (en) * | 1995-02-16 | 1998-06-16 | Fujitec Co., Ltd. | Elevator group supervisory control system |
| CN104944240A (en) * | 2015-05-19 | 2015-09-30 | 重庆大学 | Elevator equipment state monitoring system based on large data technology |
| CN105095963A (en) * | 2015-08-17 | 2015-11-25 | 中国空气动力研究与发展中心高速空气动力研究所 | Method for accurately diagnosing and predicting fault of wind tunnel equipment |
| KR20170075267A (en) * | 2015-12-23 | 2017-07-03 | 현대엘리베이터주식회사 | System for prognosticating failure of elevator |
| CN107934709A (en) * | 2016-10-13 | 2018-04-20 | 郑坤丰 | Make elevator safety diagnostic system and method using elevator driving recording big data |
| CN108466886A (en) * | 2017-02-23 | 2018-08-31 | 无锡鸿廷科技有限公司 | A kind of elevator big data statistics early-warning system |
| CN108083044A (en) * | 2017-11-21 | 2018-05-29 | 浙江新再灵科技股份有限公司 | A kind of elevator based on big data analysis maintenance system and method on demand |
| CN108178037A (en) * | 2017-12-30 | 2018-06-19 | 武汉大学 | A kind of elevator faults recognition methods based on convolutional neural networks |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109693983A (en) * | 2019-01-02 | 2019-04-30 | 日立楼宇技术（广州）有限公司 | Elevator faults processing method, device, server, storage medium and system |
| CN110008565A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | A kind of industrial process unusual service condition prediction technique based on operating parameter association analysis |
| CN109969895B (en) * | 2019-04-15 | 2021-07-23 | 淄博东升电梯工程有限公司 | Fault prediction method based on elevator operation parameters, terminal and readable storage medium |
| CN109969895A (en) * | 2019-04-15 | 2019-07-05 | 淄博东升电梯工程有限公司 | A kind of failure prediction method based on parameters of elevator run, terminal and readable storage medium storing program for executing |
| US11993488B2 (en) | 2019-09-27 | 2024-05-28 | Otis Elevator Company | Processing service requests in a conveyance system |
| CN110775758A (en) * | 2019-10-09 | 2020-02-11 | 浙江大学 | Elevator running health degree evaluation method based on car acceleration signal analysis |
| CN110775758B (en) * | 2019-10-09 | 2020-12-18 | 浙江大学 | Elevator running health degree evaluation method based on car acceleration signal analysis |
| CN110790101A (en) * | 2019-10-12 | 2020-02-14 | 虏克电梯有限公司 | Elevator trapping false alarm identification method based on big data analysis |
| CN111908288A (en) * | 2020-07-30 | 2020-11-10 | 上海繁易信息科技股份有限公司 | TensorFlow-based elevator safety system and method |
| CN112257988A (en) * | 2020-09-29 | 2021-01-22 | 中广核工程有限公司 | Complex accident feature identification and risk early warning system and method for nuclear power plant |
| WO2022105266A1 (en) * | 2020-11-17 | 2022-05-27 | 日立楼宇技术（广州）有限公司 | Elevator fault prediction method, system and apparatus, computer device, and storage medium |
| CN112758782A (en) * | 2021-01-11 | 2021-05-07 | 浙江新再灵科技股份有限公司 | Elevator fault early warning method based on Internet of things technology and coupling graph neural network |
| CN112850408A (en) * | 2021-02-05 | 2021-05-28 | 浙江新再灵科技股份有限公司 | Elevator emergency stop trapped person fault detection method based on multi-model fusion |
| CN114538234A (en) * | 2022-02-14 | 2022-05-27 | 深圳市爱丰达盛科技有限公司 | Internet of things big data elevator safe operation standard AI self-building system and method |
| CN114538234B (en) * | 2022-02-14 | 2023-06-30 | 深圳市爱丰达盛科技有限公司 | Automatic construction system and method for safe operation standard AI of big data elevator of Internet of things |
| CN115028036A (en) * | 2022-05-06 | 2022-09-09 | 北京中铁电梯工程有限公司 | Elevator management method based on big data |
| CN115650006A (en) * | 2022-10-24 | 2023-01-31 | 昆山广联发通信服务有限公司 | Elevator safety monitoring and early warning method and system based on big data |
| CN115650006B (en) * | 2022-10-24 | 2023-12-12 | 昆山广联发通信服务有限公司 | Elevator safety monitoring and early warning method and system based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109110608A (en) | A kind of elevator faults prediction technique based on big data study | |
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| CN110849626B (en) | Self-adaptive sparse compression self-coding rolling bearing fault diagnosis system | |
| Zhang et al. | Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network | |
| CN107631867B (en) | A kind of rotating machinery fault intelligent method for classifying based on deep learning | |
| Camci et al. | Feature evaluation for effective bearing prognostics | |
| CN108760327B (en) | Diagnosis method for rotor fault of aircraft engine | |
| CN109211546B (en) | Rotary machine fault diagnosis method based on noise reduction automatic encoder and increment learning | |
| CN110376522A (en) | A kind of Method of Motor Fault Diagnosis of the deep learning network of data fusion | |
| CN108869145B (en) | Pump station unit diagnosis method based on composite characteristic index and depth limit learning machine | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| CN114004256A (en) | Fault diagnosis method for manufacturing equipment main bearing based on digital twin body | |
| CN112305388B (en) | On-line monitoring and diagnosing method for insulation partial discharge faults of generator stator winding | |
| CN115959549A (en) | Escalator fault diagnosis method based on digital twinning | |
| CN110879802A (en) | Log pattern extraction and matching method | |
| CN111380687B (en) | Industrial motor bearing fault diagnosis method based on multi-local model decision fusion | |
| CN114019935A (en) | Real-time detection and diagnosis system based on industrial Internet of things equipment | |
| CN106224224B (en) | A kind of Hydraulic pump fault feature extracting method based on Hilbert-Huang transform and moment of mass entropy | |
| CN117213856A (en) | Bearing residual life prediction method based on Yun Bian double-data-source fusion | |
| CN107766882A (en) | Epicyclic gearbox method for diagnosing faults based on the more granularities of data-driven quantization characteristic | |
| CN114781450B (en) | Train rolling bearing state identification method based on parameter optimization MOMEDA-MIA-CNN | |
| CN116186609A (en) | LSTM-based manned submersible sensor fault data enhancement method | |
| CN114135580B (en) | Position evaluation method and device for magnetic bearing rotor | |
| CN113822121B (en) | Turbine pump small sample fault judging method based on data expansion and deep transfer learning | |
| CN112418407B (en) | Real-time data early warning analysis method based on 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190101 |
|
| WD01 | Invention patent application deemed withdrawn after publication |