CN111539374A - Rail train bearing fault diagnosis system and method based on multidimensional data space - Google Patents
Rail train bearing fault diagnosis system and method based on multidimensional data space Download PDFInfo
- Publication number
- CN111539374A CN111539374A CN202010384367.3A CN202010384367A CN111539374A CN 111539374 A CN111539374 A CN 111539374A CN 202010384367 A CN202010384367 A CN 202010384367A CN 111539374 A CN111539374 A CN 111539374A
- Authority
- CN
- China
- Prior art keywords
- data
- train
- sample
- multidimensional
- space
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
-
- 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
- G01M13/045—Acoustic or vibration analysis
-
- 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention relates to a rail train bearing fault diagnosis method based on a multidimensional data space, which comprises the following steps: 1) collecting sample data of normal operation of a train; 2) preprocessing and automatically labeling the collected sample data, constructing a classification model for training to obtain a classification recognition result, and dividing a data class corresponding to the operation state; 3) constructing a sample multidimensional data space by mapping the data classes with the same running state; 4) collecting sample data to be detected, identifying the sample data to be detected to obtain a classification identification result, dividing a data class corresponding to the operation state in the sample data to be detected, and mapping the data class to a sample multi-dimensional data space; 5) and calculating the distance between the detected sample data point and the center or the mass center, comparing the distance with a set distance threshold value, and performing fault alarm according to the comparison result. Compared with the prior art, the invention has the advantages of expanding the information acquisition and application range, improving the detection accuracy and reliability, high diagnosis accuracy and the like.
Description
Technical Field
The invention relates to the field of rail train bearing fault diagnosis, in particular to a rail train bearing fault diagnosis system and method based on a multidimensional data space.
Background
With the rapid striding development of urban rail transit in China, rail transit faces a severe safety problem. The rail vehicle has the characteristics of complex and variable running states, large noise interference, complex fault modes, high reliability requirements and the like, and provides higher requirements for fault diagnosis, the rolling bearing is one of the most vulnerable important parts in a high-speed train, the working environment is complex, and when the rolling bearing is influenced by factors such as excessive load impact, improper installation and design, poor lubrication state and the like, faults are likely to occur, so that great potential safety hazards and great economic loss are caused, and therefore, the fault diagnosis is rapidly and accurately carried out on the train bearing, the faults are timely positioned, and the rail vehicle has important significance in ensuring safe, reliable and stable running of a rail transit system.
At present, the fault diagnosis of the bearing is mainly based on vibration signal analysis, abundant bearing diagnosis technologies such as envelope spectrum analysis, wavelet analysis, empirical mode decomposition and the like have been developed in the last decade, and the methods play a certain role in the field of engineering application through continuous optimization, and the accuracy is continuously improved. There are still limitations, including: the type of the acquired information is limited, the actual running state of the vehicle and the characteristics of different vehicles are not considered comprehensively, a large amount of effective information is wasted, and the universal applicability is lacked; the adoption of a single-dimensional physical signal is difficult to adapt to complex working conditions, falls into a local diagnosis error region, has insufficient diagnosis reliability and easily causes potential safety hazards; the diagnosis real-time performance of early failure is still to be improved due to insufficient diagnosis experience.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a rail train bearing fault diagnosis system and method based on a multidimensional data space.
The purpose of the invention can be realized by the following technical scheme:
a rail train bearing fault diagnostic system based on a multidimensional data space, the system comprising:
a data acquisition unit: the system is used for acquiring bearing detection signals and train state identification auxiliary information data;
a data transmission unit: the data acquisition unit is used for acquiring data of the running state of the running machine;
an operation state recognition unit: receiving data transmitted by the data transmitting unit, preprocessing the acquired data, and obtaining the running state of the train through classification and identification;
a calculation unit: the system is used for calculating the centroid and the central value, and the distance or the difference value between each detection sample data point and the centroid or the center of the normal sample, and transmitting the result to the result display unit;
a result display unit: the abnormal data are sent to the abnormal alarm unit for fault alarm.
A rail train bearing fault diagnosis method based on a multidimensional data space comprises the following steps:
1) collecting sample data of normal operation of a train;
2) preprocessing and automatically labeling the acquired sample data to form a parameter training sample set, constructing a classification model and training by using the parameter training sample set to obtain a classification recognition result, namely a train running state label, and dividing a data class corresponding to a running state in the parameter training sample set;
3) constructing a sample multidimensional data space for the data classes with the same operation state through mapping, and determining a center or a mass center corresponding to each class of data class with a normal operation state in the multidimensional data space;
4) collecting sample data to be detected, adopting a trained classification model to identify and obtain a classification identification result, dividing a data class corresponding to the operation state in the sample data to be detected, and mapping the data class into a sample multidimensional data space to obtain a corresponding detection sample;
5) and calculating the distance between the detected sample data point and the center or the mass center, comparing the distance with a set distance threshold, and performing fault alarm and outputting according to the comparison result.
In the step 1), the sample data includes a bearing detection signal and train state identification auxiliary information.
The bearing detection signal comprises a motor bearing vibration signal, a gear bearing vibration signal and/or a gear meshing vibration signal.
The train state identification auxiliary information comprises train load, train running state, train posture, train speed and train acceleration information, and the train running state comprises starting, constant speed, acceleration, deceleration, curve and braking states.
In the step 2), the pretreatment specifically comprises the following steps:
21) data arrangement: sorting the fault diagnosis sample set, and eliminating redundant and invalid data;
22) normalization treatment: and normalization processing is performed by adopting dispersion standardization so as to reduce data errors and ensure the reliability of subsequent classification recognition results.
In the step 2), an SVM classifier or a neural network classifier is adopted as the classification model.
In the step 3), when the data classes with the same operation state are one-dimensional data, the center of the one-dimensional data is used as a fault judgment basis, and if the data classes with the same operation state are multidimensional data, the centroid of the multidimensional data is used as a fault judgment basis.
The center of the one-dimensional data is specifically an average value of the one-dimensional data, in a multi-dimensional data space, the distance between a point mapped by a detection sample and the center is compared with a distance threshold, data within the distance threshold is judged as normal data, data outside the distance threshold is judged as fault data, and fault alarm is performed.
And the multi-dimensional data is formed by weighting a plurality of one-dimensional data, in a multi-dimensional data space, the Euclidean distance between a point mapped by the detection sample and the centroid is compared with a distance threshold, the data within the distance threshold is judged as normal data, the data outside the distance threshold is judged as fault data, and fault alarm is performed.
Compared with the prior art, the invention has the following advantages:
firstly, improving the data utilization rate: by adopting the diagnosis method based on the multidimensional data space, more dimensional data can be utilized to the maximum extent on the premise of ensuring the accuracy, and the false alarm rate of faults is reduced.
Secondly, the reliability of fault diagnosis is high: under the conditions of complex actual working conditions and low detection data quality, a multidimensional data space weighting matrix is constructed by corresponding weights to detection signals, a sample multidimensional coordinate space is created for data classes with the same motion state, in addition, the weighting matrix and the automatic label classification are applied, the characteristics of the whole data set are considered, the dimensional difference among the attributes of the data sets is eliminated, the influence of noise data on distance measurement is weakened to a certain extent, the distance measurement is applied to intrusion detection, the interference of secondary data classes on the result can be eliminated for the complex data sets, and the reliability of the system is improved.
Thirdly, improving the calculation speed of the classification algorithm: the data set is subjected to normalized processing, so that the calculation speed of a classification algorithm is accelerated, and the attribute with a larger initial value range and the attribute with a smaller initial value range are prevented from being subjected to overlarge weight so as to influence the accuracy of distance measurement.
Fourthly, controlling in multiple layers: the rail train bearing fault diagnosis system based on the multidimensional data space is divided into a plurality of layers of processing units, then the real-time performance is strong according to the real-time motion state of the train, and the system can be further optimized according to the signal difference caused by different motion states of the train.
Drawings
Fig. 1 is a block diagram of a rail train bearing fault diagnosis system according to the present invention.
Fig. 2 is a flow chart of an implementation of the rail train bearing fault diagnosis method of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
Examples
The invention provides a rail train bearing fault diagnosis system and method based on a multidimensional data space, aiming at the problems mentioned in the background technology, and the system and method can be used for alarming and positioning the abnormal state information of a rail train bearing component by establishing a sample multidimensional data space, thereby expanding the range of information acquisition and application, improving the detection accuracy and reliability and having stronger practical value.
As shown in fig. 1, the present invention includes a block diagram of a rail train bearing fault diagnosis system, which includes a data acquisition unit, a data transmission unit, an operation state identification unit, a calculation unit, a result display unit, and an abnormality alarm unit. The input end of the data sending unit is a data acquisition unit, the output end of the data sending unit is an operation state identification unit, the calculation unit comprises a mass center calculation module, a central value calculation module, a distance calculation module and a difference value calculation module, the input end of the data sending unit is an operation state identification unit, vibration detection data are respectively output to the mass center calculation module and the central value calculation module, the input end of the result display unit is a calculation unit, if a diagnosis result is normal, a data set is fed back to the calculation unit for recalculation, and an abnormal result is output to the abnormal alarm unit.
The data acquisition unit is used for acquiring bearing detection signals and train state identification auxiliary information data; the data sending unit is used for sending the acquired data to the operation state identification unit; the running state identification unit is used for receiving the data transmitted by the data transmission unit and processing the acquired data to obtain the running state of the train; the calculating unit is used for calculating a mass center and a central value, respectively calculating the distance and the difference between each data point and the mass center and the central value, and transmitting the result to the result display unit; the result display unit is used for judging the threshold value, transmitting the data in the normal threshold value back to the calculation unit, and transmitting the abnormal information to the abnormal alarm unit for fault alarm.
Fig. 2 is a flow chart of the implementation of the rail train bearing fault diagnosis method of the present invention, the method establishes a fault diagnosis model of a rail train bearing based on a data space determination method, and introduces a threshold determination method of a multidimensional detection signal coordinate space for accurate classification aiming at the conditions of insufficient utilization rate of bearing state acquisition information and insufficient reliability of fault determination under complex conditions, and the method comprises the following steps:
step 1, collecting samples including bearing detection signals and train state identification auxiliary information;
step 2, preprocessing and automatically labeling the original data;
step 3, training the obtained data by a classification recognition algorithm, recognizing the running state of the train and determining the data class;
step 4, based on the data classes with the same labels obtained by train operation state identification, constructing a multidimensional data space weighting matrix according to the corresponding weight of each detection signal and obtaining the space coordinates of synchronous detection data vectors, and creating a sample multidimensional data space comprising one-dimensional detection signal vectors and multidimensional detection signal vector groups;
step 5, calculating the central value of the one-dimensional vector and the difference value between each data point and the central value of the detection sample for the one-dimensional detection signal vector, and comparing and judging the signal to be detected and the single-parameter central value difference threshold value; for a multi-dimensional detection signal vector group, obtaining a sample multi-dimensional data space calculation centroid coordinate, calculating Euclidean distances between each data point of a single synchronous acquisition signal to be detected and a centroid, and comparing and judging the Euclidean distances with a centroid distance threshold;
and 6, obtaining an abnormal detection result, alarming and outputting an abnormal detection point.
The detailed description of each step is as follows:
step 1, collecting a sample: the method comprises the steps of acquiring bearing detection signals in the running process of a train in real time through a sensor, wherein the bearing detection signals mainly comprise single or multiple motor bearing vibration signals, single or multiple gear bearing vibration signals and single or multiple gear meshing vibration signals (corresponding to one-dimensional or multi-dimensional detection signals), and train state identification auxiliary information mainly comprises train load, train running state records, train postures, train speed and train acceleration.
Step 2, train state identification: adopting a classification recognition algorithm to recognize the running state of the train, and preprocessing the original acquisition sample obtained in the step 1, wherein the data preprocessing mainly comprises the following steps:
step 2.1, data arrangement: sorting the fault diagnosis sample set, and eliminating redundant and invalid data;
step 2.2, normalization treatment: because dimensions and orders of magnitude are different among different detection signals, normalization processing needs to be carried out on data, deviation of data analysis results is reduced, and reliability of subsequent results is guaranteed.
The calculation formula is as follows:
where i is 1, 2.. times, i, the number of times a single acquisition signal is acquired in a sample.
And 3, selecting an identification algorithm to respectively train parameter training samples in different motion states to obtain a classification model for train operation state identification and division of the acquired data, and identifying the train operation state of the sample data to be detected by using the obtained classification model to divide specific data classes.
Step 4, creating a sample multidimensional data space: and 2, adopting the data classes with the same labels and subjected to train running state identification in the step 2, constructing a multidimensional data weighting matrix according to the corresponding weight of each detection signal, obtaining corresponding coordinates of synchronous detection data vectors in a multidimensional data space, and establishing a sample multidimensional data space for the data classes with the same motion state.
The method comprises the following specific steps: a vector of one-dimensional detection signals,
[X(t0),X(t1),X(t2),…,X(tn)]
wherein, [ t ]0,t1,t2,…,tn]Representing a synchronous acquisition time sequence. A multidimensional data weighting matrix is formed by a plurality of groups of one-dimensional detection signal vectors,
where 1,2,3, …, j is the multidimensional data space dimension, [ omega ] created from the samples0,ω1,ω2,…,ωn]Is the weight of the detection parameter of each dimension.
And 5, judging based on the multidimensional data space. Step 5.1, calculating a one-dimensional data center value:
let X (t)0),X(t1),X(t2),…,X(tn) N observed values of j-dimensional detection signals of the parameter training samples, the central value of the one-dimensional data is measured by taking a mean value or a median value as a numerical value, and a formula is calculated according to the mean value
Calculating the difference value between the same-dimension sample data to be detected and the central value, namely:
step 5.2, calculating the coordinate of the mass center of the multidimensional data space according to the parameter training sample set, wherein the calculation formula is as follows:
wherein k ∈ 1,2, …, n. is the centroid coordinate obtained from the parameter training sample set
The data to be examined is mapped to the coordinate (omega) in the multi-dimensional space1X1，ω2X2，…，ωjXj) Calculating the distance value between the sample data to be detected and the centroid by adopting the Euclidean distance, namely:
step 5.3, judging a parameter threshold value: including a one-dimensional threshold SsjJudgment, and judgment of the multidimensional threshold Sm.
Based on a parameter training sample set and bearing detection vibration signals detected in the normal running state of the train, setting a corresponding normal threshold range on a single dimension
If calculated ejThe difference value with the central value is less than-SsjOr greater than + SsjThen, the abnormal condition is judged.
And setting a corresponding normal threshold value in the multidimensional data space based on the parameter training sample set, namely taking the centroid as the center and being within the range from the centroid Sm. And if the Euclidean distance between the sample data to be detected and the centroid is larger than Sm, judging that the sample data is abnormal.
And 6, obtaining an abnormal detection result, alarming and outputting an abnormal detection point.
The above description is only a preferred embodiment of the present invention and should not be taken as limiting the invention, as it is within the spirit and scope of the present invention
Any modifications, equivalents, improvements and the like made within the scope of the present invention should be included.
Claims (10)
1. A rail train bearing fault diagnostic system based on a multidimensional data space, the system comprising:
a data acquisition unit: the system is used for acquiring bearing detection signals and train state identification auxiliary information data;
a data transmission unit: the data acquisition unit is used for acquiring data of the running state of the running machine;
an operation state recognition unit: receiving data transmitted by the data transmitting unit, preprocessing the acquired data, and obtaining the running state of the train through classification and identification;
a calculation unit: the system is used for calculating the centroid and the central value, and the distance or the difference value between each detection sample data point and the centroid or the center of the normal sample, and transmitting the result to the result display unit;
a result display unit: the abnormal data are sent to the abnormal alarm unit for fault alarm.
2. A rail train bearing fault diagnosis method based on a multidimensional data space is characterized by comprising the following steps:
1) collecting sample data of normal operation of a train;
2) preprocessing and automatically labeling the acquired sample data to form a parameter training sample set, constructing a classification model and training by using the parameter training sample set to obtain a classification recognition result, namely a train running state label, and dividing a data class corresponding to a running state in the parameter training sample set;
3) constructing a sample multidimensional data space for the data classes with the same operation state through mapping, and determining a center or a mass center corresponding to each class of data class with a normal operation state in the multidimensional data space;
4) collecting sample data to be detected, adopting a trained classification model to identify and obtain a classification identification result, dividing a data class corresponding to the operation state in the sample data to be detected, and mapping the data class into a sample multidimensional data space to obtain a corresponding detection sample;
5) and calculating the distance between the detected sample data point and the center or the mass center, comparing the distance with a set distance threshold, and performing fault alarm and outputting according to the comparison result.
3. The rail train bearing fault diagnosis method based on the multidimensional data space of claim 2, wherein in the step 1), the sample data comprises a bearing detection signal and train state identification auxiliary information.
4. The rail train bearing fault diagnosis method based on the multidimensional data space, as claimed in claim 3, wherein the bearing detection signal comprises a motor bearing vibration signal, a gear bearing vibration signal and/or a gear mesh vibration signal.
5. The rail train bearing fault diagnosis method based on the multidimensional data space as claimed in claim 3, wherein the train state identification auxiliary information comprises train load, train operation state, train attitude, train speed and train acceleration information, and the train operation state comprises start, constant speed, acceleration, deceleration, curve and brake states.
6. The rail train bearing fault diagnosis method based on the multidimensional data space as claimed in claim 2, wherein the preprocessing specifically comprises the following steps in the step 2):
21) data arrangement: sorting the fault diagnosis sample set, and eliminating redundant and invalid data;
22) normalization treatment: and normalization processing is performed by adopting dispersion standardization so as to reduce data errors and ensure the reliability of subsequent classification recognition results.
7. The rail train bearing fault diagnosis method based on the multidimensional data space as claimed in claim 2, wherein in the step 2), the classification model adopts an SVM classifier or a neural network classifier.
8. The rail train bearing fault diagnosis method based on the multidimensional data space as claimed in claim 2, wherein in the step 3), when the data class with the same operation state is the one-dimensional data, the center of the one-dimensional data is used as the fault judgment basis, and when the data class with the same operation state is the multidimensional data, the center of mass of the multidimensional data is used as the fault judgment basis.
9. The rail train bearing fault diagnosis method based on the multidimensional data space as claimed in claim 8, wherein the center of the one-dimensional data is specifically an average value of the one-dimensional data, in the multidimensional data space, the distance between the point and the center mapped by the detection sample is compared with a distance threshold, data within the distance threshold is determined as normal data, data outside the distance threshold is determined as fault data, and a fault alarm is performed.
10. The rail train bearing fault diagnosis method based on the multidimensional data space of claim 8, wherein the multidimensional data is formed by weighting a plurality of one-dimensional data, and in the multidimensional data space, the Euclidean distance between a point and a centroid mapped by a detection sample is compared with a distance threshold, data within the distance threshold is determined as normal data, data outside the distance threshold is determined as fault data, and a fault alarm is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010384367.3A CN111539374B (en) | 2020-05-07 | 2020-05-07 | Rail train bearing fault diagnosis method based on multidimensional data space |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010384367.3A CN111539374B (en) | 2020-05-07 | 2020-05-07 | Rail train bearing fault diagnosis method based on multidimensional data space |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111539374A true CN111539374A (en) | 2020-08-14 |
| CN111539374B CN111539374B (en) | 2022-05-20 |
Family
ID=71979182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010384367.3A Active CN111539374B (en) | 2020-05-07 | 2020-05-07 | Rail train bearing fault diagnosis method based on multidimensional data space |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111539374B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836896A (en) * | 2021-03-03 | 2021-05-25 | 西门子工厂自动化工程有限公司 | Method for maintaining equipment and system for maintaining equipment |
| CN113156913A (en) * | 2021-02-05 | 2021-07-23 | 深圳大雷汽车检测股份有限公司 | ABS fault diagnosis system and method |
| CN113569475A (en) * | 2021-07-21 | 2021-10-29 | 上海工程技术大学 | Subway axle box bearing fault diagnosis system based on digital twinning technology |
| CN115809435A (en) * | 2023-02-06 | 2023-03-17 | 山东星科智能科技股份有限公司 | Simulator-based automobile operation fault identification method |
| CN117332233A (en) * | 2023-10-07 | 2024-01-02 | 江苏丰昌机电科技有限公司 | Intelligent maintenance system for motor |
| CN117943891A (en) * | 2024-03-22 | 2024-04-30 | 济南二机床集团有限公司 | Method, device, equipment and medium for detecting fault of electric spindle bearing of numerical control machine tool |
| CN117332233B (en) * | 2023-10-07 | 2024-05-31 | 江苏丰昌机电科技有限公司 | Intelligent maintenance system for motor |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030105561A1 (en) * | 1997-09-12 | 2003-06-05 | New York Air Brake Corporation | Method of optimizing train operation and training |
| US20140365179A1 (en) * | 2013-06-11 | 2014-12-11 | Ypf Sociedad Anonima | Method and Apparatus for Detecting and Identifying Faults in a Process |
| CN104931263A (en) * | 2015-06-18 | 2015-09-23 | 东南大学 | Bearing fault diagnosis method based on symbolic probabilistic finite state machine |
| US20170015339A1 (en) * | 2014-12-12 | 2017-01-19 | Beijing Jiaotong University | Complex network-based high speed train system safety evaluation method |
| WO2018015127A1 (en) * | 2016-07-20 | 2018-01-25 | Thales Austria Gmbh | System and method for ascertaining at least one state of a train |
| CN109033582A (en) * | 2018-07-12 | 2018-12-18 | 西安英特迈思信息科技有限公司 | A kind of bullet train multi parameter intallingent threshold value criterion |
| CN109100143A (en) * | 2018-07-06 | 2018-12-28 | 华中科技大学 | Fault Diagnosis of Roller Bearings and equipment based on CEEMDAN and CFSFDP |
| CN110111446A (en) * | 2019-01-25 | 2019-08-09 | 东北大学 | A kind of adaptive acquisition system of high-speed rail train data and method based on operating condition |
| CN110503004A (en) * | 2019-07-29 | 2019-11-26 | 七彩安科智慧科技有限公司 | A kind of online method of discrimination of Switching Power Supply operating status |
-
2020
- 2020-05-07 CN CN202010384367.3A patent/CN111539374B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030105561A1 (en) * | 1997-09-12 | 2003-06-05 | New York Air Brake Corporation | Method of optimizing train operation and training |
| US20140365179A1 (en) * | 2013-06-11 | 2014-12-11 | Ypf Sociedad Anonima | Method and Apparatus for Detecting and Identifying Faults in a Process |
| US20170015339A1 (en) * | 2014-12-12 | 2017-01-19 | Beijing Jiaotong University | Complex network-based high speed train system safety evaluation method |
| CN104931263A (en) * | 2015-06-18 | 2015-09-23 | 东南大学 | Bearing fault diagnosis method based on symbolic probabilistic finite state machine |
| WO2018015127A1 (en) * | 2016-07-20 | 2018-01-25 | Thales Austria Gmbh | System and method for ascertaining at least one state of a train |
| CN109100143A (en) * | 2018-07-06 | 2018-12-28 | 华中科技大学 | Fault Diagnosis of Roller Bearings and equipment based on CEEMDAN and CFSFDP |
| CN109033582A (en) * | 2018-07-12 | 2018-12-18 | 西安英特迈思信息科技有限公司 | A kind of bullet train multi parameter intallingent threshold value criterion |
| CN110111446A (en) * | 2019-01-25 | 2019-08-09 | 东北大学 | A kind of adaptive acquisition system of high-speed rail train data and method based on operating condition |
| CN110503004A (en) * | 2019-07-29 | 2019-11-26 | 七彩安科智慧科技有限公司 | A kind of online method of discrimination of Switching Power Supply operating status |
Non-Patent Citations (2)
| Title |
|---|
| XIAODONG WANG ET AL: "Triplet Loss Guided Adversarial Domain Adaptation for Bearing Fault Diagnosis", 《SENSORS》 * |
| 魏永合: "基于LLE及其改进距离算法的轴承故障诊断模型", 《组合机床与自动化加工技术》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113156913A (en) * | 2021-02-05 | 2021-07-23 | 深圳大雷汽车检测股份有限公司 | ABS fault diagnosis system and method |
| CN112836896A (en) * | 2021-03-03 | 2021-05-25 | 西门子工厂自动化工程有限公司 | Method for maintaining equipment and system for maintaining equipment |
| CN113569475A (en) * | 2021-07-21 | 2021-10-29 | 上海工程技术大学 | Subway axle box bearing fault diagnosis system based on digital twinning technology |
| CN113569475B (en) * | 2021-07-21 | 2023-09-01 | 上海工程技术大学 | Subway axle box bearing fault diagnosis system based on digital twin technology |
| CN115809435A (en) * | 2023-02-06 | 2023-03-17 | 山东星科智能科技股份有限公司 | Simulator-based automobile operation fault identification method |
| CN117332233A (en) * | 2023-10-07 | 2024-01-02 | 江苏丰昌机电科技有限公司 | Intelligent maintenance system for motor |
| CN117332233B (en) * | 2023-10-07 | 2024-05-31 | 江苏丰昌机电科技有限公司 | Intelligent maintenance system for motor |
| CN117943891A (en) * | 2024-03-22 | 2024-04-30 | 济南二机床集团有限公司 | Method, device, equipment and medium for detecting fault of electric spindle bearing of numerical control machine tool |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111539374B (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539374B (en) | Rail train bearing fault diagnosis method based on multidimensional data space | |
| CN111353482B (en) | LSTM-based fatigue factor recessive anomaly detection and fault diagnosis method | |
| CN110567720A (en) | method for diagnosing depth confrontation of fault of fan bearing under unbalanced small sample scene | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN115809435B (en) | Automobile operation fault identification method based on simulator | |
| CN113887136B (en) | Electric automobile motor bearing fault diagnosis method based on improved GAN and ResNet | |
| CN113188794B (en) | Gearbox fault diagnosis method and device based on improved PSO-BP neural network | |
| CN108267312B (en) | A kind of subway train bearing intelligent diagnostic method based on fast search algorithm | |
| CN112036297A (en) | Typical and extreme scene division and extraction method based on internet vehicle driving data | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN111717753A (en) | Self-adaptive elevator fault early warning system and method based on multi-dimensional fault characteristics | |
| CN116702053B (en) | Agricultural machinery fault detection method based on multiple information and MCSA-SVM | |
| CN114564987A (en) | Rotary machine fault diagnosis method and system based on graph data | |
| CN114462480A (en) | Multi-source sensor rolling mill fault diagnosis method based on non-equilibrium data set | |
| CN115112372A (en) | Bearing fault diagnosis method and device, electronic equipment and storage medium | |
| CN114491828A (en) | Compound fault diagnosis method based on multi-gating hybrid expert multi-task learning | |
| CN113526282A (en) | Method, device, medium and equipment for diagnosing medium and long-term aging faults of elevator | |
| CN113758709A (en) | Rolling bearing fault diagnosis method and system combining edge calculation and deep learning | |
| CN110160781B (en) | Test set reconstruction and prediction method for rotary machine fault classification | |
| CN115356133A (en) | Bogie operation condition on-line monitoring, real-time classification and identification algorithm | |
| CN114861749A (en) | Low-sample bearing fault diagnosis method based on depth prototype network | |
| CN111351655A (en) | Method for diagnosing gear fault in locomotive gear box | |
| CN113807431A (en) | Intelligent spindle state evaluation method and system based on multi-source information fusion | |
| CN113505817A (en) | Self-adaptive weighting training method for bearing fault diagnosis model samples under unbalanced data | |
| CN111967364A (en) | Composite fault diagnosis method, device, electronic equipment and storage medium |
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 |