CN102539159A - Fault diagnosis method for valve mechanism of diesel engine - Google Patents
Fault diagnosis method for valve mechanism of diesel engine Download PDFInfo
- Publication number
- CN102539159A CN102539159A CN2010106125657A CN201010612565A CN102539159A CN 102539159 A CN102539159 A CN 102539159A CN 2010106125657 A CN2010106125657 A CN 2010106125657A CN 201010612565 A CN201010612565 A CN 201010612565A CN 102539159 A CN102539159 A CN 102539159A
- Authority
- CN
- China
- Prior art keywords
- diesel engine
- operator
- redundant
- fault
- time domain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a fault diagnosis method for a valve mechanism of a diesel engine. The method comprises the following steps of: decomposing a vibration signal acquired from a cylinder cover of the diesel engine by using redundant second generation wavelet packet transform to extract a time domain statistical characteristic of the decomposed signal to constitute a fault characteristic vector; and constructing a multi-fault multi-class support vector machine model based on two classes of multi-class support vectors to realize classification identification of a fault state of the valve mechanism of the diesel engine. By using the method, the validity of extracted characteristic parameters can be improved, and the generalization capacity during fault classification can also be improved; and a practical new technology is provided or fault diagnosis of the valve mechanism of the diesel engine.
Description
Technical field
The present invention relates to the power-equipment fault diagnosis technology, be specifically related to diesel engine spiracle mechanism-trouble diagnostic method.
Background technology
Diesel engine is a kind of common power-equipment, has vital role in national economy and military field, in case break down, will bring enormous economic loss.The valve mechanism fault is the modal fault of diesel engine, and the diesel engine output power will be descended, and parts depreciation is quickened, and produces strong noise simultaneously.Therefore, diesel engine spiracle mechanism is carried out effective fault diagnosis is a research focus always.
Effective extraction of fault signature is the key issue of diesel engine spiracle mechanism-trouble diagnosis.Usually the method that adopts at present is to utilize first generation small echo or wavelet package transforms that the vibration signal that covers collection from cylinder of diesel engine is decomposed, and extracts time domain statistical nature parameter the subband signal that after small echo or WAVELET PACKET DECOMPOSITION, forms then as the fault signature vector that characterizes diesel engine spiracle mechanism state.Research shows that first generation small echo and method of wavelet packet can produce the frequency alias problem in conversion process, thereby can reduce the accuracy and the validity of the fault signature vector that extracts the subband signal that after small echo or WAVELET PACKET DECOMPOSITION, forms.In addition, the realization of first generation small echo and wavelet package transforms is based on the method for convolution algorithm, and operand is relatively large.Second generation wavelet method is a kind of small wave converting method of flexibility, can use linearity, nonlinear predictive operator and renewal operator to come signal is analyzed, and can guarantee the reversibility of conversion simultaneously.Second generation wavelet method is compared with the wavelet method of classics, and its building method is more flexible, and efficiency of algorithm is higher.But there is the frequency alias problem equally in second generation wavelet method.
Aspect fault mode classification, in the diagnosis of diesel engine spiracle mechanism-trouble, obtained widespread use based on Artificial Neural Network model.But; Artificial Neural Network is a kind of based on the minimized learning method of empiric risk; It is absorbed in local minimum in learning process easily; And the study phenomenon can appear, therefore the generalization ability when this type of processing machine fault diagnosis small sample pattern recognition problem is relatively poor, thereby has influence on the precision of fault diagnosis.SVMs proposes for solving small sample study and classification problem; It is based on the structural risk minimization of Statistical Learning Theory; Can obtain the classifying face of a global optimum; Therefore can overcome traditional mode sorting technique such as neural network intrinsic mistake learn and owe problem concerning study, have very strong non-linear classification simultaneously.
Summary of the invention
The objective of the invention is to overcome the deficiency that prior art exists, a kind of diesel engine spiracle mechanism-trouble diagnostic method is provided.This method utilizes redundant second generation method of wavelet packet to extract the fault signature parameter, can suppress the frequency alias problem of wavelet transformation effectively, improves the correctness and the validity of the fault signature parameter of extracting; Utilize support vector machine method as sorter, avoided the local optimum problem of traditional mode sorting technique, improved the precision of diesel engine spiracle mechanism-trouble diagnosis.
The objective of the invention is to realize that through following technical scheme it comprises the steps:
Step 1: obtain the vibration signal sample under the diesel engine spiracle mechanism different operating state through test simulation, with this training sample as fault mode classification;
Step 2: utilize redundant second generation method of wavelet packet that diesel engine spiracle mechanism vibrations sample of signal is decomposed, obtain each subband signal on the different frequency range;
Step 3: calculate the time domain statistical nature that the vibration signal sample decomposes each subband signal, the set of eigenvectors that forms is carried out normalization;
Step 4: set up the multi-category support vector machines model, the fault signature vector is carried out pattern classification.
Described step 2 comprises the steps:
1, calculates initial predicted operator and initially upgrade operator;
2, calculate redundant predictive operator and the redundant operator that upgrades;
3, the vibration signal sample is carried out redundant second generation WAVELET PACKET DECOMPOSITION.
Described step 3 comprises the steps:
1, calculates the time domain statistical nature of vibration signal sample WAVELET PACKET DECOMPOSITION signal, comprise one or more in peak value, mean value, variance, root mean square, skewness index, kurtosis index, waveform factor, pulse factor, the peak factor.If adopt redundant second generation wavelet packet that the vibration signal sample is decomposed the l layer, obtain 2 of l layer
lIndividual subband signal calculates the individual time domain statistical nature of I (I≤9) respectively to each subband signal, then obtains 2
l* I time domain statistical nature;
2, the fault signature vector set that the time domain statistical nature by whole valve mechanism vibration signal samples is generated carries out normalization.
Described step 4 comprises the steps:
1, sets up corresponding to the individual two class support vector machines sorter SVM (1) of the n of n kind diesel engine spiracle mechanism-trouble pattern～SVM (n); N two types of sorters are made up by the binary tree form, construct the multi-category support vector machines model that can separate n kind fault mode;
2, utilize multi-category support vector machines that the fault signature vector is classified.
Because the present invention adopts based on integrated on algorithm of the feature extraction of redundant second generation method of wavelet packet and support vector machine classification method, compared with prior art, its advantage and beneficial effect are:
The frequency alias problem that 1, can suppress wavelet transformation based on the fault signature extractive technique of redundant second generation method of wavelet packet has effectively improved correctness and the validity of from decompose subband signal, extracting the fault signature parameter.
2, can avoid tradition to be absorbed in local minimum problem easily based on the fault mode classification of SVMs, improve the precision and the generalization ability of fault diagnosis based on the method for classifying modes of empiric risk minimization principle.
3, the present invention constructs in time domain fully, and the algorithm real-time is good, and a kind of new technology of practicality is provided for the fault diagnosis of diesel engine spiracle mechanism.
Description of drawings
Below will combine accompanying drawing and embodiment that the present invention is done further explain.
Fig. 1 is a diesel engine spiracle mechanism-trouble simulation test device synoptic diagram
Fig. 2 is diesel engine spiracle mechanism vibrations time domain plethysmographic signal figure
Fig. 3 is a multiple faults category support vector machines model
Embodiment
Like Fig. 1, shown in 2 and 3, concrete grammar of the present invention is following:
1, obtains the vibration signal sample under the diesel engine spiracle mechanism different operating state through test simulation, with this training sample as fault mode classification.
With reference to Fig. 1, diesel engine spiracle mechanism-trouble simulation test device comprises diesel engine, signal acquiring system, vibration acceleration sensor, pulse transducer, A/D transition card and microcomputer.All vibration signals record through the vibration acceleration sensor that is installed in the cylinder head upper surface, and SF is 24kHz.The pulse signal that produces with the 4th cylinder top dead centre in the test is as the basic point of vibration signal sample, and each vibration signal sample comprises the sampled point in 720 ° of crank angles.Diesel motor is unloaded during test, and rotating speed is 1400r/min.
The fault simulation test adopts the method that diesel motor valve clearance fault artificially is set to simulate 4 kinds of valve malfunctions, adds normal condition, has obtained the vibration signal sample of valve mechanism under 5 kinds of duties altogether.The illustrated in table 1 of valve mechanism duty.
With reference to Fig. 2, the vibration signal sample of diesel engine spiracle mechanism in the next complete working cycle of 5 kinds of duties, each waveform is corresponding to a sample of the listed valve mechanism duty of table 1.
The state description of table 1 diesel engine spiracle mechanism analog
2, utilize redundant second generation method of wavelet packet that diesel engine spiracle mechanism vibrations sample of signal is decomposed, obtain each subband signal on the different frequency range.
2a. calculate initial predicted operator and the initial operator that upgrades
The initial predicted operator P=[p of redundant second generation wavelet package transforms
1, p
2..., p
M] and the initial operator U=[u that upgrades
1, u
2..., u
N], M and N are the initial length of upgrading operator and initial predicted operator coefficient, M ∈ Z, and N ∈ Z, computing method are following:
P obtains through following formula
VP＝[1，0，...，0]
T (1)
[V]
i，j＝[2j-M-1]
i-1 (2)
I=1 in the formula, 2 ..., M, j=1,2 ..., M.
If Q={Q
(k),-M-N+2≤k≤M+N-2}, the relation of Q and P, U is represented as follows
Q
(2l+M-2)＝u(l)l＝1，2，...，N (4)
When l gets other value, Q
(2l)=0
Construct the dimension of a M * (2M+2N-1) matrix W, its element representation is following
[W]
m，n＝n
m (5)
N=-M-N+2 wherein ,-M-N+3 ..., M+N-3, M+N-2, m=0,1 ..., N-1.
U obtains through following formula
WQ＝0 (6)
In the present embodiment, the initial predicted operator is chosen as 4 and 2 respectively with the initial length of upgrading operator, and its corresponding coefficient is respectively P=[0.0625,0.5625,0.5625 ,-0.0625] and U=[0.5,0.5].
2b. calculate redundant operator and the redundant predictive operator of upgrading
Redundant second generation wavelet package transforms decomposes the redundant predictive operator P that adopts at the l layer
lUpgrade operator U with redundancy
lBe to obtain with the initial basic enterprising row interpolation zero padding of upgrading operator U at initial predicted operator P, computing method are following:
2c. vibration signal is carried out redundant second generation WAVELET PACKET DECOMPOSITION, obtains each subband signal on the different frequency range
Redundant second generation wavelet packet decomposes each subband signal that obtains at the l layer and obtains through following formula
X in the formula
L, kRepresent k subband signal of l layer.
In the present embodiment, utilize redundant second generation wavelet package transforms that each the vibration signal sample under every kind of duty is carried out 3 layers of decomposition.
3, calculate the time domain statistical nature that the vibration signal sample decomposes each subband signal, the set of eigenvectors that forms is carried out normalization.
3a. calculate the time domain statistical nature of vibration signal sample decomposed signal, comprise one or more in peak value, mean value, variance, root mean square, skewness index, kurtosis index, waveform factor, pulse factor, the peak factor
In the present embodiment; To each vibration signal sample; Utilize 3 layers of redundant second generation WAVELET PACKET DECOMPOSITION; Obtain 8 wavelet packet subband signals, each subband signal is calculated 9 time domain statistical natures such as peak value, mean value, variance, root mean square, skewness index, kurtosis index, waveform factor, pulse factor, peak factor respectively, obtain 72 time domain statistical natures altogether;
3b. the fault signature vector set that the time domain statistical nature by whole valve mechanism vibration signal samples is generated carries out normalization
4, set up SVMs multiple faults disaggregated model, the fault signature vector is classified.
4a. set up n two class support vector machines sorter SVM (1)～SVM (n) corresponding to n kind diesel engine spiracle mechanism mode of operation; N two types of sorters are made up by the binary tree form, construct a multi-category support vector machines model that separates n kind fault mode
With reference to Fig. 3, SVMs is the sorter of two types of problems, and the present invention adopts the tree classification method to set up SVMs multiple faults disaggregated model.At first, foundation is corresponding to 5 two class support vector machines sorter SVM (the 1)～SVM (5) of 5 kinds of diesel engine spiracle mechanism duties.Then, 5 two class support vector machines sorters are made up by binary tree form shown in Figure 3, promptly become 1 multi-category support vector machines model that can separate 5 kinds of diesel engine spiracle mechanism mode of operations.
4b. utilizing multi-category support vector machines classifies to the fault signature vector.
The classification process in, at first the fault signature vector with vibration signal sample x to be tested is input to SVM (1), as if discriminant f (x) be output as+1, think that then sample belongs to " state 1 ", EOT; Otherwise input to SVM (2) automatically.And the like, up to SVM (5).If output is not+1, think that then the vibration signal sample belongs to other state.
In the present embodiment, adopt the inventive method that each vibration signal sample is carried out 3 layers of redundant second generation WAVELET PACKET DECOMPOSITION, the initial predicted operator is chosen as 4 and 2 respectively with the initial length of upgrading operator; Coefficient is respectively [0.0625,0.5625,0.5625;-0.0625] and [0.5,0.5].To calculating 9 time domain statistical natures such as peak value, mean value, variance, root mean square, skewness index, kurtosis index, waveform factor, pulse factor and peak factor respectively in 8 subband wavelet packet coefficients that generate after the redundant second generation WAVELET PACKET DECOMPOSITION; Promptly each vibration signal sample extraction is gone out 72 time domain statistical natures as the fault signature vector, adopt C4.5 decision tree (C4.5), radial basis function neural network (RBFNN) and SVMs (SVM) to carry out fault mode classification then respectively.In order to compare; Adopt second generation method of wavelet packet that each vibration signal sample is carried out 3 layers of second generation WAVELET PACKET DECOMPOSITION, extract same time domain statistical nature in 8 subband wavelet packet coefficients that after second generation WAVELET PACKET DECOMPOSITION, generate then to form the fault signature vector.The predictive operator of second generation wavelet packet is chosen as 4 and 2 respectively with the length of upgrading operator, and coefficient is respectively [0.0625,0.5625,0.5625 ,-0.0625] and [0.5,0.5].Table 2 has been listed and has been adopted two kinds of distinct methods to carry out the test findings of diesel engine spiracle mechanism-trouble pattern classification.
The result can find out from diesel engine spiracle mechanism-trouble class test; No matter select which sorter; The fault diagnosis precision that adopts the inventive method to obtain all is superior to adopting the diagnostic method of second generation wavelet packet, has therefore verified the validity of the inventive method aspect the fault signature parameter extraction.On the other hand; For C4.5, RBFNN and three sorters of SVM; The fault signature vector of no matter selecting which kind of fault signature parameter extracting method to generate; Adopt SVM to classify and all can obtain higher nicety of grading, thereby verified the superiority that the inventive method selects SVMs that diesel engine spiracle mechanism-trouble pattern is classified.
Table 2 diesel engine spiracle mechanism-trouble nicety of grading
Claims (4)
1. a diesel engine spiracle mechanism-trouble diagnostic method is characterized in that comprising the steps:
(a) obtain the vibration signal sample under the diesel engine spiracle mechanism different operating state through test simulation, with this training sample as fault mode classification;
(b) utilize redundant second generation method of wavelet packet that diesel engine spiracle mechanism vibrations sample of signal is decomposed, obtain each subband signal on the different frequency range;
(c) calculate the time domain statistical nature that the vibration signal sample decomposes each subband signal, the set of eigenvectors that forms is carried out normalization;
(d) set up the multi-category support vector machines model, the fault signature vector is carried out pattern classification.
2. diesel engine spiracle mechanism-trouble diagnostic method according to claim 1 is characterized in that said step 1-(b) comprises the steps:
1) calculates initial predicted operator and the initial operator that upgrades
The initial predicted operator P=[p of redundant second generation wavelet package transforms
1, p
2..., p
M] and the initial operator U=[u that upgrades
1, u
2..., u
N], M and N are the initial length of upgrading operator and initial predicted operator coefficient, M ∈ Z, and N ∈ Z, computing method are following:
P obtains through following formula
VP＝[1，0，...，0]
T (1)
[V]
i，j＝[2j-M-1]
i-1 (2)
I=1 in the formula, 2 ..., M, j=1,2 ..., M.
If Q={Q
(k),-M-N+2≤k≤M+N-2}, the relation of Q and P, U is represented as follows
Q
(2l+M-2)＝u(l)l＝1，2，...，N (4)
When l gets other value, Q
(2l)=0
Construct the dimension of a M * (2M+2N-1) matrix W, its element representation is following
[W]
m，n＝n
m (5)
N=-M-N+2 wherein ,-M-N+3 ..., M+N-3, M+N-2, m=0,1 ..., N-1.
U obtains through following formula
WQ＝0 (6)
2) calculate redundant operator and the redundant predictive operator of upgrading
Redundant second generation wavelet package transforms decomposes the redundant predictive operator P that adopts at the l layer
lUpgrade operator U with redundancy
lBe to obtain with the initial basic enterprising row interpolation zero padding of upgrading operator U at initial predicted operator P, computing method are following:
3) vibration signal is carried out redundant second generation WAVELET PACKET DECOMPOSITION, obtain on the different frequency range the redundant second generation wavelet packet of each subband signal and decompose each subband signal that obtains at the l layer and obtain through following formula
X in the formula
L, kRepresent k subband signal of l layer.
3. diesel engine spiracle mechanism-trouble diagnostic method according to claim 1 is characterized in that said step 1-(c) comprises the steps:
1) the time domain statistical nature of calculating vibration signal sample WAVELET PACKET DECOMPOSITION signal; Comprise one or more in peak value, mean value, variance, root mean square, skewness index, kurtosis index, waveform factor, pulse factor, the peak factor; If adopt redundant second generation wavelet packet that the vibration signal sample is decomposed the l layer, obtain 2 of l layer
lIndividual subband signal calculates the individual time domain statistical nature of I (I≤9) respectively to each subband signal, then obtains 2
l* I time domain statistical nature;
2) the fault signature vector set that the time domain statistical nature by whole valve mechanism vibration signal samples is generated carries out normalization.
4. diesel engine spiracle mechanism-trouble diagnostic method according to claim 1 is characterized in that said step 1-(d) comprises the steps:
1) sets up corresponding to the individual two class support vector machines sorter SVM (1) of the n of n kind diesel engine spiracle mechanism-trouble pattern～SVM (n); N two types of sorters are made up by the binary tree form, construct the multi-category support vector machines model that can separate n kind fault mode;
2) utilize multi-category support vector machines that the fault signature vector is classified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106125657A CN102539159A (en) | 2010-12-24 | 2010-12-24 | Fault diagnosis method for valve mechanism of diesel engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010106125657A CN102539159A (en) | 2010-12-24 | 2010-12-24 | Fault diagnosis method for valve mechanism of diesel engine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102539159A true CN102539159A (en) | 2012-07-04 |
Family
ID=46346599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010106125657A Pending CN102539159A (en) | 2010-12-24 | 2010-12-24 | Fault diagnosis method for valve mechanism of diesel engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102539159A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743585A (en) * | 2013-12-27 | 2014-04-23 | 柳州职业技术学院 | Mechanical failure diagnosing method |
| CN104198184A (en) * | 2014-08-11 | 2014-12-10 | 中国人民解放军空军工程大学 | Bearing fault diagnostic method based on second generation wavelet transform and BP neural network |
| CN105352738A (en) * | 2015-12-10 | 2016-02-24 | 广西玉柴机器股份有限公司 | Method for enabling jitter fault of diesel engine to reappear during no load |
| CN107367358A (en) * | 2017-07-26 | 2017-11-21 | 安庆市鼎立汽车配件有限公司 | A kind of sealing intelligent detecting method based on the analysis of more valves |
| CN108537260A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | A kind of crane transmission axis method for diagnosing faults and system |
| CN109839185A (en) * | 2017-11-29 | 2019-06-04 | 宝沃汽车（中国）有限公司 | Engine noise test method and device |
| CN109839265A (en) * | 2019-03-28 | 2019-06-04 | 西安建筑科技大学 | It is a kind of based on the mechanical Rubbing faults diagnostic method of m ultiwavelet core-support vector regression |
| CN110500217A (en) * | 2019-07-23 | 2019-11-26 | 南京航空航天大学 | Based on can measured data feature common rail for diesel engine system oil pump fault detection method |
| US20200118358A1 (en) * | 2018-10-11 | 2020-04-16 | Hyundai Motor Company | Failure diagnosis method for power train components |
| CN111626144A (en) * | 2020-05-08 | 2020-09-04 | 湖南挚新科技发展有限公司 | Impact feature vector construction method and device, terminal equipment and storage medium |
| CN114185321A (en) * | 2021-08-30 | 2022-03-15 | 华北电力大学 | Electric actuator fault diagnosis method for improving multi-classification twin support vector machine |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1811367A (en) * | 2006-03-03 | 2006-08-02 | 西安交通大学 | Integrated supporting vector machine mixed intelligent diagnosing method for mechanical fault |
| US20090326754A1 (en) * | 2008-06-30 | 2009-12-31 | Honeywell International Inc. | Systems and methods for engine diagnosis using wavelet transformations |
| CN101706370A (en) * | 2009-04-29 | 2010-05-12 | 深圳市普禄科智能检测设备有限公司 | Device and method for diagnosing cylinder of diesel engine |
-
2010
- 2010-12-24 CN CN2010106125657A patent/CN102539159A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1811367A (en) * | 2006-03-03 | 2006-08-02 | 西安交通大学 | Integrated supporting vector machine mixed intelligent diagnosing method for mechanical fault |
| US20090326754A1 (en) * | 2008-06-30 | 2009-12-31 | Honeywell International Inc. | Systems and methods for engine diagnosis using wavelet transformations |
| CN101706370A (en) * | 2009-04-29 | 2010-05-12 | 深圳市普禄科智能检测设备有限公司 | Device and method for diagnosing cylinder of diesel engine |
Non-Patent Citations (4)
| Title |
|---|
| RUI ZHOU ET AL: ""Mechanical equipment fault diagnosis based on redundant second generation wavelet packet transform"", 《DIGITAL SIGNAL PROCESSING》, vol. 20, 31 January 2010 (2010-01-31), pages 276 - 288, XP026764650, DOI: doi:10.1016/j.dsp.2009.04.005 * |
| 何正嘉 等: ""基于混合小波分析的振动信号奇异性识别与设备维修"", 《设备检测与诊断技术及其应用——第十二届全国设备检测与诊断学术会议论文集》, 1 November 2005 (2005-11-01), pages 145 - 151 * |
| 张梅军 等: ""小波包变换和支持向量机相结合在发动机气门间隙故障诊断中的应用"", 《机械研究与应用》, no. 6, 31 December 2009 (2009-12-31) * |
| 苟博 等: ""支持向量机多类分类方法"", 《数据采集与处理》, vol. 21, no. 3, 30 September 2006 (2006-09-30), pages 334 - 339 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103743585A (en) * | 2013-12-27 | 2014-04-23 | 柳州职业技术学院 | Mechanical failure diagnosing method |
| CN104198184A (en) * | 2014-08-11 | 2014-12-10 | 中国人民解放军空军工程大学 | Bearing fault diagnostic method based on second generation wavelet transform and BP neural network |
| CN105352738A (en) * | 2015-12-10 | 2016-02-24 | 广西玉柴机器股份有限公司 | Method for enabling jitter fault of diesel engine to reappear during no load |
| CN105352738B (en) * | 2015-12-10 | 2018-01-30 | 广西玉柴机器股份有限公司 | The method of diesel engine jitterbug when reappearing unloaded |
| CN107367358A (en) * | 2017-07-26 | 2017-11-21 | 安庆市鼎立汽车配件有限公司 | A kind of sealing intelligent detecting method based on the analysis of more valves |
| CN109839185A (en) * | 2017-11-29 | 2019-06-04 | 宝沃汽车（中国）有限公司 | Engine noise test method and device |
| CN109839185B (en) * | 2017-11-29 | 2021-03-26 | 宝沃汽车（中国）有限公司 | Engine noise testing method and device |
| CN108537260A (en) * | 2018-03-29 | 2018-09-14 | 上海交通大学 | A kind of crane transmission axis method for diagnosing faults and system |
| US20200118358A1 (en) * | 2018-10-11 | 2020-04-16 | Hyundai Motor Company | Failure diagnosis method for power train components |
| CN109839265A (en) * | 2019-03-28 | 2019-06-04 | 西安建筑科技大学 | It is a kind of based on the mechanical Rubbing faults diagnostic method of m ultiwavelet core-support vector regression |
| CN110500217A (en) * | 2019-07-23 | 2019-11-26 | 南京航空航天大学 | Based on can measured data feature common rail for diesel engine system oil pump fault detection method |
| CN111626144A (en) * | 2020-05-08 | 2020-09-04 | 湖南挚新科技发展有限公司 | Impact feature vector construction method and device, terminal equipment and storage medium |
| CN111626144B (en) * | 2020-05-08 | 2023-08-29 | 湖南挚新科技发展有限公司 | Impact feature vector construction method, device, terminal equipment and storage medium |
| CN114185321A (en) * | 2021-08-30 | 2022-03-15 | 华北电力大学 | Electric actuator fault diagnosis method for improving multi-classification twin support vector machine |
| CN114185321B (en) * | 2021-08-30 | 2023-12-22 | 华北电力大学 | Electric actuator fault diagnosis method for improving multi-classification twin support vector machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102539159A (en) | Fault diagnosis method for valve mechanism of diesel engine | |
| Li et al. | Mechanical fault diagnosis based on redundant second generation wavelet packet transform, neighborhood rough set and support vector machine | |
| Wang et al. | Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox: A review | |
| CN103728551B (en) | A kind of analog-circuit fault diagnosis method based on cascade integrated classifier | |
| CN111523509B (en) | Equipment fault diagnosis and health monitoring method integrating physical and depth expression characteristics | |
| Lin et al. | Detection and classification of multiple power-quality disturbances with wavelet multiclass SVM | |
| CN101750210B (en) | Fault diagnosis method based on OLPP feature reduction | |
| CN105760839A (en) | Bearing fault diagnosis method based on multi-feature manifold learning and support vector machine | |
| CN105841961A (en) | Bearing fault diagnosis method based on Morlet wavelet transformation and convolutional neural network | |
| CN105678343B (en) | Hydropower Unit noise abnormality diagnostic method based on adaptive weighted group of sparse expression | |
| CN104504403B (en) | A kind of rotating machinery fault Forecasting Methodology based on scattering conversion | |
| CN101949895B (en) | Method for identifying fine crack impact signal of metal deep drawing part | |
| CN105572501A (en) | Power quality disturbance identification method based on SST conversion and LS-SVM | |
| CN102889987A (en) | Gear fault diagnosis platform and gear fault diagnosis method | |
| CN110503025A (en) | A kind of analog circuit Incipient Fault Diagnosis method based on semi-supervised coorinated training | |
| Zhu et al. | Complex disturbances identification: A novel PQDs decomposition and modeling method | |
| CN113255458A (en) | Bearing fault diagnosis method based on multi-view associated feature learning | |
| CN111562105A (en) | Wind turbine generator gearbox fault diagnosis method based on wavelet packet decomposition and convolutional neural network | |
| Han et al. | Data-enhanced stacked autoencoders for insufficient fault classification of machinery and its understanding via visualization | |
| CN103776901A (en) | Visco-elastic interlayer structure aging state identification method based on vibration response message | |
| Tasnim et al. | Wind power prediction using cluster based ensemble regression | |
| CN104280253A (en) | Immune detector based fault diagnosis method and system | |
| Dubaish et al. | Comparative Analysis of SVM and ANN for Machine Condition Monitoring and Fault Diagnosis in Gearboxes. | |
| CN103577877A (en) | Ship motion prediction method based on time-frequency analysis and BP neural network | |
| CN116340812A (en) | Transformer partial discharge fault mode identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120704 |