CN114202198A - Cloud edge cooperative computing intelligent drive axle health monitoring system and method thereof - Google Patents
Cloud edge cooperative computing intelligent drive axle health monitoring system and method thereof Download PDFInfo
- Publication number
- CN114202198A CN114202198A CN202111508019.3A CN202111508019A CN114202198A CN 114202198 A CN114202198 A CN 114202198A CN 202111508019 A CN202111508019 A CN 202111508019A CN 114202198 A CN114202198 A CN 114202198A
- Authority
- CN
- China
- Prior art keywords
- data
- axle
- module
- cloud
- vehicle
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000036541 health Effects 0.000 title claims abstract description 25
- 238000004891 communication Methods 0.000 claims abstract description 38
- 238000004364 calculation method Methods 0.000 claims abstract description 22
- 238000007405 data analysis Methods 0.000 claims abstract description 4
- 230000004927 fusion Effects 0.000 claims description 27
- 238000007781 pre-processing Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 19
- 230000009467 reduction Effects 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000000513 principal component analysis Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 4
- 230000005484 gravity Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L12/40006—Architecture of a communication node
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L2012/40208—Bus networks characterized by the use of a particular bus standard
- H04L2012/40215—Controller Area Network CAN
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/40—Bus networks
- H04L2012/40267—Bus for use in transportation systems
- H04L2012/40273—Bus for use in transportation systems the transportation system being a vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Security & Cryptography (AREA)
- Databases & Information Systems (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Biology (AREA)
- Operations Research (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
Abstract
The invention provides a cloud edge collaborative computing intelligent drive axle health monitoring system and a method thereof, and the cloud edge collaborative computing intelligent drive axle health monitoring system comprises an axle running data acquisition module, a vehicle-mounted edge computing module, a communication module and an axle cloud fault prediction module; the axle operation data acquisition module acquires and stores data information of the drive axle housing; the vehicle-mounted edge calculation module is used for carrying out data arrangement and logic judgment on the data; the communication module is used for transmitting the data in the axle operation data acquisition module to the vehicle-mounted edge calculation module and transmitting the data in the vehicle-mounted edge calculation module to the axle cloud fault prediction module; the axle cloud fault prediction module is used for carrying out big data analysis on data and issuing fault prediction, so that the method and the device have the advantages that the running state of the automobile drive axle can be obtained in real time, the faults of easily damaged parts in the drive axle can be accurately predicted, and the intelligent and safe driving of the automobile is guaranteed.
Description
Technical Field
The invention belongs to the technical field of drive axle monitoring, and particularly relates to a cloud edge collaborative computing intelligent drive axle health monitoring system and a cloud edge collaborative computing intelligent drive axle health monitoring method.
Background
In order to meet the development requirements of automobile intellectualization and intelligence and achieve the aims of monitoring the real-time state of a drive axle and early warning, a method and a system for monitoring the health of the drive axle are researched. The drive axle of the heavy-duty car is positioned at the tail end of a power transmission system and is an important component for realizing safe and stable operation of the heavy-duty car. Their component structure is complex, the load carrying capacity is large and often abrupt, and they are one of the components of major interest in the operation of heavy vehicles and they are difficult to overhaul and monitor. Therefore, a real-time monitoring method and a real-time monitoring system are needed for researching the running state of the drive axle in the running process of the heavy-duty automobile. Meanwhile, a large number of transmission parts are arranged in the drive axle, so that problems often occur in the actual operation process, the driving safety is seriously damaged, the health state of the drive axle needs to be managed, namely, fault prediction is carried out, the safety service of the whole vehicle is favorably ensured, and sudden maintenance and accidents are avoided.
At present, a fast and accurate intelligent drive axle health monitoring method and system are also lacking. The drive axle is internally closed, a sensor cannot be directly installed to measure the operation condition of the transmission part, the fault prediction needs to be carried out by means of an indirect measurement technical method and a machine learning method, and the accuracy of the fault prediction is ensured. The machine learning method needs to occupy a large amount of computing resources for fault prediction, the vehicle-mounted controller of the heavy-duty vehicle cannot meet real-time computing conditions and mass data storage, and the intelligent drive axle health monitoring method and system based on cloud edge collaborative computing are researched by virtue of the advantage of high cloud computing capability, so that the 'maintenance according to the situation' decision after the heavy-duty vehicle is on the road can be realized, and the intelligence and the safety of the heavy-duty vehicle can be improved.
Disclosure of Invention
The invention provides a cloud edge cooperative computing intelligent drive axle health monitoring system and an operation method thereof, which can obtain the running state of an automobile drive axle in real time, accurately predict the failure of easily damaged parts in the drive axle and ensure the intelligent safe driving of an automobile.
The technical scheme of the invention is realized as follows: a cloud edge collaborative computing intelligent drive axle health monitoring system comprises an axle running data acquisition module, an on-vehicle edge computing module, a communication module and an axle cloud fault prediction module;
the axle operation data acquisition module acquires and stores data information of the drive axle housing;
the vehicle-mounted edge calculation module is used for carrying out data arrangement and logic judgment on the data;
the communication module is used for transmitting the data in the axle operation data acquisition module to the vehicle-mounted edge calculation module and transmitting the data in the vehicle-mounted edge calculation module to the axle cloud fault prediction module;
and the axle cloud fault prediction module is used for carrying out big data analysis on the data and issuing fault prediction.
As a preferred embodiment, the axle operation data acquisition module comprises a sensor and a data acquisition card, the sensor comprises a vibration sensor, an oil temperature sensor, a friction plate temperature sensor, an axle speed sensor and an axle torque sensor, and the data acquisition card is connected with the vibration sensor, the oil temperature sensor, the friction plate temperature sensor, the axle speed sensor and the axle torque sensor through cables and used for collecting multi-source signals of each path of the axle.
In a preferred embodiment, the communication module comprises a CAN communication line and a TCP/I P communication line, the CAN communication line transmits data in the axle operation data acquisition module to the vehicle-mounted edge calculation module through a CAN network according to a vehicle CAN communication protocol, and the TCP/I P communication line transmits data in the vehicle-mounted edge calculation module to the axle cloud fault prediction module through a TCP/I P network according to a vehicle TCP/I P communication protocol.
As a preferred embodiment, the communication module encrypts the data before data transmission, and the encryption method is to encrypt the data field by using an encryption algorithm and update the key at the cloud periodically or aperiodically to ensure the security and confidentiality of the data.
As a preferred embodiment, the vehicle-mounted edge calculation module is arranged in the edge controller, and the vehicle-mounted edge calculation module performs preprocessing, feature extraction, feature selection and feature fusion on original data in the axle operation data acquisition module;
the preprocessing comprises processing abnormal values, missing values, heterogeneous values and heterogeneous values in the original data;
the feature extraction comprises time domain features and frequency domain features;
the feature selection method comprises the steps of adopting feature dimension reduction processing after feature screening is carried out through a feature evaluation criterion;
the characteristic fusion comprises the steps of integrating all data sources and integrating and summarizing data with different structures and attributes into a whole.
In a preferred embodiment, the missing value is filled by means of multiple interpolation, the abnormal value is subjected to smooth noise by means of binning, the heterogeneous and heterogeneous values are repeated values, and the repeated values are processed by means of deletion;
the time domain features comprise a mean value, a standard deviation, an effective value, a kurtosis, a square root amplitude value, a form factor, an impulse coefficient and a margin factor, the frequency domain features comprise a center of gravity Frequency (FC), a Mean Square Frequency (MSF) and a Root Mean Square Frequency (RMSF), and the analysis methods of the time domain features and the frequency domain features comprise a short-time Fourier transform (STFT) method and a wavelet transform method;
the characteristic evaluation criterion comprises a Pearson correlation coefficient, a boundary width, an F i sher judgment and an information gain;
the feature dimension reduction method comprises principal component analysis, linear discriminant analysis, kernel principal component analysis, kernel discriminant analysis, local linear embedding and manifold learning.
As a preferred embodiment, the axle cloud prediction module comprises a database, a state monitoring module, a data preprocessing module and a model library;
historical original data collected by a sensor and field monitoring data are stored in a database;
the state monitoring module is used for classifying and collecting historical original data;
the data preprocessing module is used for respectively preprocessing, feature extraction, feature dimension reduction and feature fusion on the classified data set to obtain a multi-source information fusion feature set;
a neural network machine learning model and a fault prediction model are stored in the model library, and the fault prediction model is obtained by training a multi-source information fusion characteristic set.
As a preferred embodiment, the method for building the fault prediction model comprises the following steps:
step 1, dividing data in a multi-source information fusion characteristic set into a training set and a testing set;
step 2, carrying out prediction training on the training set by adopting a neural network machine learning model to obtain a fault prediction model, and outputting a prediction result: { y (t +1), y (t +2),.., y (t + k) };
step 3, inputting the test set into the fault prediction model for verification, judging whether the prediction result reaches the prediction precision through the calculation of the neural network machine learning model, and if the prediction result reaches the prediction precision, obtaining the prediction result, namely outputting a threshold value yThreshold valueAnd if the prediction precision is not achieved, returning the multi-source information fusion feature set and re-establishing the fault prediction model.
A cloud edge collaborative computing intelligent drive axle health monitoring method comprises the following steps:
step 1, acquiring data of each path of an axle through a vibration sensor, an oil temperature sensor, a friction plate temperature sensor, an axle rotating speed sensor and an axle torque sensor, and classifying and collecting signals of each path of the axle through a data acquisition card to obtain data A;
step 2, encrypting the data A through the communication module, and transmitting the data A to the vehicle-mounted edge computing module, wherein the vehicle-mounted edge computing module respectively performs preprocessing, feature extraction, feature dimension reduction and feature fusion on the data A to obtain data B, and the data transmission quantity is reduced while the data is perfected;
and 3, transmitting the data B serving as field monitoring data to an axle cloud fault prediction module through a communication module, inputting the data B into a fault prediction model, and obtaining an output prediction result: { y (t +1), y (t +2),.., y (t + k) };
and 4, comparing the prediction result with an output threshold value, wherein the comparison formula is as follows: y (t + k) > -, yThreshold valueIf the formula result is met, fault early warning is carried out, and if the formula result is not met, field monitoring is carried out continuously by inputting field monitoring data.
After the technical scheme is adopted, the invention has the beneficial effects that:
according to the invention, historical and real-time data are stored in the database, and signals can be displayed in real time, so that the cloud real-time monitoring of the running state of the drive axle is realized; the method has the advantages that the running state of the automobile drive axle can be obtained in real time, the faults of easily damaged parts in the drive axle can be accurately predicted, and the intelligent and safe driving of the automobile is guaranteed.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a system framework diagram of the present invention;
fig. 2 is a flow chart of failure prediction of the variable speed and load rolling bearing.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, a cloud edge collaborative computing intelligent drive axle health monitoring system includes an axle operation data acquisition module, an on-vehicle edge computing module, a communication module and an axle cloud fault prediction module;
the axle operation data acquisition module acquires and stores data information of the drive axle housing;
the vehicle-mounted edge calculation module is used for carrying out data arrangement and logic judgment on the data;
the communication module is used for transmitting the data in the axle operation data acquisition module to the vehicle-mounted edge calculation module and transmitting the data in the vehicle-mounted edge calculation module to the axle cloud fault prediction module;
and the axle cloud fault prediction module is used for carrying out big data analysis on the data and issuing fault prediction.
The axle operation data acquisition module comprises a sensor and a data acquisition card, the sensor comprises a vibration sensor, an oil temperature sensor, a friction plate temperature sensor, an axle rotating speed sensor and an axle torque sensor, and the data acquisition card is connected with the vibration sensor, the oil temperature sensor, the friction plate temperature sensor, the axle rotating speed sensor and the axle torque sensor through cables and used for collecting multi-source signals of each path of the axle.
The communication module comprises a CAN communication line and a TCP/I P communication line, the CAN communication line transmits data in the axle operation data acquisition module to the vehicle-mounted edge calculation module through a CAN network according to a vehicle CAN communication protocol, and the TCP/I P communication line transmits data in the vehicle-mounted edge calculation module to the axle cloud fault prediction module through a TCP/I P network according to a vehicle TCP/I P communication protocol.
The communication module encrypts data before data transmission, and the encryption method is to encrypt a data domain by adopting an encryption algorithm and update a secret key at the cloud end regularly or irregularly so as to ensure the safety and the confidentiality of the data.
The vehicle-mounted edge computing module is arranged in the edge controller and is used for preprocessing original data in the axle running data acquisition module, extracting features, selecting features and fusing the features;
the preprocessing comprises processing abnormal values, missing values, heterogeneous values and heterogeneous values in the original data;
the feature extraction comprises time domain features and frequency domain features;
the feature selection method comprises the steps of adopting feature dimension reduction processing after feature screening is carried out through a feature evaluation criterion;
the characteristic fusion comprises the steps of integrating all data sources and integrating and summarizing data with different structures and attributes into a whole.
Filling missing values in a multiple interpolation mode, smoothing noise of the abnormal values in a box dividing mode, wherein the heterogeneous values and the heterogeneous values are repeated values, and the repeated values are processed in a deleting mode;
the time domain features comprise a mean value, a standard deviation, an effective value, a kurtosis, a square root amplitude value, a form factor, an impulse coefficient and a margin factor, the frequency domain features comprise a center of gravity Frequency (FC), a Mean Square Frequency (MSF) and a Root Mean Square Frequency (RMSF), and the analysis methods of the time domain features and the frequency domain features comprise a short-time Fourier transform (STFT) method and a wavelet transform method;
the characteristic evaluation criterion comprises a Pearson correlation coefficient, a boundary width, Fi sher judgment and information gain;
the feature dimension reduction method comprises principal component analysis, linear discriminant analysis, kernel principal component analysis, kernel discriminant analysis, local linear embedding and manifold learning.
The axle cloud prediction module comprises a database, a state monitoring module, a data preprocessing module and a model library;
historical original data collected by a sensor and field monitoring data are stored in a database;
the state monitoring module is used for classifying and collecting historical original data;
the data preprocessing module is used for respectively preprocessing, feature extraction, feature dimension reduction and feature fusion on the classified data set to obtain a multi-source information fusion feature set;
a neural network machine learning model and a fault prediction model are stored in the model library, and the fault prediction model is obtained by training a multi-source information fusion characteristic set.
The construction method of the fault prediction model comprises the following steps:
step 1, dividing data in a multi-source information fusion characteristic set into a training set and a testing set;
step 2, carrying out prediction training on the training set by adopting a neural network machine learning model to obtain a fault prediction model, and outputting a prediction result: { y (t +1), y (t +2),.., y (t + k) };
step 3, inputting the test set into the fault prediction model for verification, judging whether the prediction result reaches the prediction precision through the calculation of the neural network machine learning model, and if so, judging whether the prediction result reaches the prediction precisionWhen the prediction precision is reached, a prediction result is obtained, namely the output threshold yThreshold valueAnd if the prediction precision is not achieved, returning the multi-source information fusion feature set and re-establishing the fault prediction model.
A cloud edge collaborative computing intelligent drive axle health monitoring method comprises the following steps:
step 1, acquiring data of each path of an axle through a vibration sensor, an oil temperature sensor, a friction plate temperature sensor, an axle rotating speed sensor and an axle torque sensor, and classifying and collecting signals of each path of the axle through a data acquisition card to obtain data A;
step 2, encrypting the data A through the communication module, and transmitting the data A to the vehicle-mounted edge computing module, wherein the vehicle-mounted edge computing module respectively performs preprocessing, feature extraction, feature dimension reduction and feature fusion on the data A to obtain data B, and the data transmission quantity is reduced while the data is perfected;
and 3, transmitting the data B serving as field monitoring data to an axle cloud fault prediction module through a communication module, inputting the data B into a fault prediction model, and obtaining an output prediction result: { y (t +1), y (t +2),.., y (t + k) };
and 4, comparing the prediction result with an output threshold value, wherein the comparison formula is as follows: y (t + k) > -, yThreshold valueIf the formula result is met, fault early warning is carried out, and if the formula result is not met, field monitoring is carried out continuously by inputting field monitoring data.
The method comprises the steps of operating abnormal values, missing values, repeated values and the like in original signals in an original data preprocessing module, eliminating noise in the signals, selecting corresponding time-frequency domain characteristics according to data and bearing performance characteristics, then reducing dimensionality of training data by selecting a dimensionality reduction method such as Local Linear Embedding (LLE) and the like, reducing complexity of algorithm calculation, fusing data characteristics according to characteristic importance degrees during characteristic fusion to obtain a comprehensive characteristic set which is more effective on a prediction result, dividing processed data into a training set and a testing set, then selecting a neural network machine learning model for prediction training, customizing model parameters according to needs or searching for optimal model parameters by using a machine learning algorithm contained in a software system to obtain a series of prediction results, judging algorithm prediction accuracy from a model output result, and obtaining a more accurate fault prediction algorithm through continuous iterative training of data, and storing the trained prediction algorithm into a model base, obtaining a current prediction result through the input of real-time monitoring data, and comparing the current prediction result with an output threshold value to realize the prediction of the drive axle fault. The method can provide guidance for a driver to make a correct maintenance decision, and reduce the maintenance cost of the drive axle of the heavy-duty car.
Example 1
As shown in fig. 2, the original data of the variable-speed variable-load rolling bearing in the database is extracted, and is divided into a vibration data set and a temperature data set according to characteristics to be monitored, the vibration data set is subjected to FFT data noise reduction and time domain feature extraction respectively, the temperature data set is combined into a comprehensive feature set after 2-order B-spline curve interpolation and quantity reduction respectively, and the comprehensive feature set is integrated into a multi-source information fusion feature set after LLE feature dimension reduction.
Dividing data in the multi-source information fusion characteristic set into a training set and a testing set, performing prediction training on the training set by adopting a neural network machine learning model to obtain a fault prediction model, and outputting a prediction result: { y (t +1), y (t +2),.. and y (t + k) }, inputting the test set into the fault prediction model for verification, judging whether the prediction result reaches the prediction precision through the calculation of the neural network machine learning model, and if the prediction result reaches the prediction precision, obtaining the prediction result, namely outputting a threshold value yThreshold valueAnd if the prediction precision is not achieved, returning the multi-source information fusion feature set and re-establishing the fault prediction model.
Example 2
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A cloud edge collaborative computing intelligent drive axle health monitoring system is characterized by comprising an axle operation data acquisition module, an on-vehicle edge computing module, a communication module and an axle cloud fault prediction module;
the axle operation data acquisition module acquires and stores data information of the drive axle housing;
the vehicle-mounted edge computing module is used for carrying out data sorting and logic judgment on data;
the communication module is used for transmitting the data in the axle operation data acquisition module to the vehicle-mounted edge calculation module and transmitting the data in the vehicle-mounted edge calculation module to the axle cloud fault prediction module;
the axle cloud fault prediction module is used for carrying out big data analysis on data and issuing fault prediction.
2. The cloud-edge-collaborative-computation intelligent drive axle health monitoring system according to claim 1, wherein the axle operation data acquisition module comprises a sensor and a data acquisition card, the sensor comprises a vibration sensor, an oil temperature sensor, a friction plate temperature sensor, an axle rotation speed sensor and an axle torque sensor, and the data acquisition card is connected with the vibration sensor, the oil temperature sensor, the friction plate temperature sensor, the axle rotation speed sensor and the axle torque sensor through cables and used for collecting multi-source signals of each axle.
3. The cloud-edge-collaborative-computation intelligent drive axle health monitoring system according to claim 1, wherein the communication module includes a CAN communication line and a TCP/IP communication line, the CAN communication line transmits data in the axle operation data acquisition module to the vehicle-mounted edge computation module via a CAN network in accordance with a vehicle CAN communication protocol, and the TCP/IP communication line transmits data in the vehicle-mounted edge computation module to the axle cloud fault prediction module via a TCP/IP network in accordance with a vehicle TCP/IP communication protocol.
4. The cloud-edge-collaborative-computing intelligent drive axle health monitoring system according to claim 3, wherein the communication module encrypts data before data transmission by using an encryption algorithm to encrypt a data field and periodically or aperiodically update a key at the cloud end to ensure security and confidentiality of the data.
5. The cloud-edge-collaborative-computing intelligent drive axle health monitoring system according to claim 1, wherein the vehicle-mounted edge computing module is disposed in the edge-end controller, and the vehicle-mounted edge computing module performs preprocessing, feature extraction, feature selection and feature fusion on raw data in the axle operation data acquisition module;
the preprocessing comprises processing abnormal values, missing values, heterogeneous values and heterogeneous values in the original data;
the feature extraction comprises time domain features and frequency domain features;
the feature selection method comprises the steps of adopting feature dimension reduction processing after feature screening is carried out through a feature evaluation criterion;
the characteristic fusion comprises the steps of integrating all data sources and integrating and summarizing data with different structures and attributes into a whole.
6. The cloud-edge-collaborative-computing intelligent drive axle health monitoring system according to claim 5, wherein the missing values are filled in a multi-interpolation manner, the abnormal values are smoothed in a binning manner, the heterogeneous and heterogeneous values are repeated values, and the repeated values are processed in a deleting manner;
the time domain features comprise a mean value, a standard deviation, an effective value, a kurtosis, a square root amplitude value, a form factor, an impulse coefficient and a margin factor, the frequency domain features comprise a center of gravity Frequency (FC), a Mean Square Frequency (MSF) and a Root Mean Square Frequency (RMSF), and the analysis methods of the time domain features and the frequency domain features comprise a short-time Fourier transform (STFT) method and a wavelet transform method;
the characteristic evaluation criterion comprises a Pearson correlation coefficient, a boundary width, Fisher judgment and information gain;
the feature dimension reduction method comprises principal component analysis, linear discriminant analysis, kernel principal component analysis, kernel discriminant analysis, local linear embedding and manifold learning.
7. The cloud-edge-collaborative-computing intelligent drive axle health monitoring system according to claim 1, wherein the axle cloud prediction module comprises a database, a state monitoring module, a data preprocessing module, and a model library;
historical original data collected by a sensor and field monitoring data are stored in a database;
the state monitoring module is used for classifying and collecting historical original data;
the data preprocessing module is used for respectively preprocessing, feature extraction, feature dimension reduction and feature fusion on the classified data set to obtain a multi-source information fusion feature set;
a neural network machine learning model and a fault prediction model are stored in the model library, and the fault prediction model is obtained by training a multi-source information fusion characteristic set.
8. The cloud-edge-collaborative-computing intelligent drive axle health monitoring system according to claim 7, wherein the fault prediction model is built by a method comprising:
step 1, dividing data in a multi-source information fusion characteristic set into a training set and a testing set;
step 2, carrying out prediction training on the training set by adopting a neural network machine learning model to obtain a fault prediction model, and outputting a prediction result: { y (t +1), y (t +2),.., y (t + k) };
step 3, inputting the test set into the fault prediction model for verification, judging whether the prediction result reaches the prediction precision through the calculation of the neural network machine learning model, and if the prediction result reaches the prediction precision, obtaining the prediction result, namely outputting a threshold value yThreshold valueAnd if the prediction precision is not achieved, returning the multi-source information fusion feature set and re-establishing the fault prediction model.
9. A cloud edge collaborative computing intelligent drive axle health monitoring method is characterized by comprising the following steps:
step 1, acquiring data of each path of an axle through a vibration sensor, an oil temperature sensor, a friction plate temperature sensor, an axle rotating speed sensor and an axle torque sensor, and classifying and collecting signals of each path of the axle through a data acquisition card to obtain data A;
step 2, encrypting the data A through the communication module, and transmitting the data A to the vehicle-mounted edge computing module, wherein the vehicle-mounted edge computing module respectively performs preprocessing, feature extraction, feature dimension reduction and feature fusion on the data A to obtain data B, and the data transmission quantity is reduced while the data is perfected;
and 3, transmitting the data B serving as field monitoring data to an axle cloud fault prediction module through a communication module, inputting the data B into a fault prediction model, and obtaining an output prediction result: { y (t +1), y (t +2),.., y (t + k) };
and 4, comparing the prediction result with an output threshold value, wherein the comparison formula is as follows: y (t + k) > -, yThreshold valueIf the formula result is met, fault early warning is carried out, and if the formula result is not met, field monitoring is carried out continuously by inputting field monitoring data.
10. The method for cloud-edge collaborative computing intelligent drive axle health monitoring according to claim 9, wherein y in step 3 means: and t has the meaning: y isThreshold valueThe meaning of (A) is: .
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111508019.3A CN114202198A (en) | 2021-12-10 | 2021-12-10 | Cloud edge cooperative computing intelligent drive axle health monitoring system and method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111508019.3A CN114202198A (en) | 2021-12-10 | 2021-12-10 | Cloud edge cooperative computing intelligent drive axle health monitoring system and method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114202198A true CN114202198A (en) | 2022-03-18 |
Family
ID=80652151
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111508019.3A Pending CN114202198A (en) | 2021-12-10 | 2021-12-10 | Cloud edge cooperative computing intelligent drive axle health monitoring system and method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114202198A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117914003A (en) * | 2024-03-19 | 2024-04-19 | 沈阳智帮电气设备有限公司 | Intelligent monitoring auxiliary method and system for box-type transformer based on cloud edge cooperation |
-
2021
- 2021-12-10 CN CN202111508019.3A patent/CN114202198A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117914003A (en) * | 2024-03-19 | 2024-04-19 | 沈阳智帮电气设备有限公司 | Intelligent monitoring auxiliary method and system for box-type transformer based on cloud edge cooperation |
| CN117914003B (en) * | 2024-03-19 | 2024-05-24 | 沈阳智帮电气设备有限公司 | Intelligent monitoring auxiliary method and system for box-type transformer based on cloud edge cooperation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Soualhi et al. | Pattern recognition method of fault diagnostics based on a new health indicator for smart manufacturing | |
| Lin et al. | Hyper-spherical distance discrimination: A novel data description method for aero-engine rolling bearing fault detection | |
| Zhang et al. | Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network | |
| CN112785016A (en) | New energy automobile maintenance and fault monitoring and diagnosis method based on machine learning | |
| CN103115789B (en) | Second generation small-wave support vector machine assessment method for damage and remaining life of metal structure | |
| CN103645052A (en) | Wind turbine set gearbox remote online state monitoring and life assessment method | |
| CN107003663A (en) | The monitoring of device with movable part | |
| CN115013261A (en) | State monitoring method and system for offshore wind farm | |
| CN112326280B (en) | Fault detection method and device for train bogie and computer readable medium | |
| JP2017077055A (en) | State diagnostic device and program | |
| CN105205569A (en) | Draught fan gear box state on-line evaluation model building method and on-line evaluation method | |
| CN111125895B (en) | On-line assessment method for service power characteristics of complete wind driven generator | |
| Zhang et al. | Feature engineering and artificial intelligence-supported approaches used for electric powertrain fault diagnosis: A review | |
| Attoui | Novel fast and automatic condition monitoring strategy based on small amount of labeled data | |
| CN114202198A (en) | Cloud edge cooperative computing intelligent drive axle health monitoring system and method thereof | |
| US20230133120A1 (en) | Big-data-based battery diagnostic system and control method therefor | |
| Davari et al. | A fault detection framework based on lstm autoencoder: A case study for volvo bus data set | |
| Zegrari et al. | Data-driven Diagnostics for Electric Traction Systems: A Study of Induction Motor | |
| CN113516023B (en) | Method and system for diagnosing equipment vibration abnormality | |
| CN114115199A (en) | Monitoring and fault diagnosis system for new energy sanitation vehicle | |
| CN109556862A (en) | Railway wheelset bearing safety monitoring system based on self-powered sensing network | |
| Liu et al. | Elevator traction machine fault diagnosis based on improved CEEMD and SVM Algorithm | |
| CN111381165A (en) | Vehicle power battery monitoring method, device and platform | |
| CN105651526B (en) | Vehicle working condition recognition methods based on analysis of vibration signal | |
| Gu et al. | Fault Diagnosis Method for Bearing of High‐Speed Train Based on Multitask Deep 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 |