CN111520231B - Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP - Google Patents

Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP Download PDF

Info

Publication number
CN111520231B
CN111520231B CN201911396075.5A CN201911396075A CN111520231B CN 111520231 B CN111520231 B CN 111520231B CN 201911396075 A CN201911396075 A CN 201911396075A CN 111520231 B CN111520231 B CN 111520231B
Authority
CN
China
Prior art keywords
composite
proximity
pwfp
entropy
common rail
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201911396075.5A
Other languages
Chinese (zh)
Other versions
CN111520231A (en
Inventor
宋恩哲
柯赟
姚崇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Harbin Engineering University
Original Assignee
Harbin Engineering University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Harbin Engineering University filed Critical Harbin Engineering University
Priority to CN201911396075.5A priority Critical patent/CN111520231B/en
Publication of CN111520231A publication Critical patent/CN111520231A/en
Application granted granted Critical
Publication of CN111520231B publication Critical patent/CN111520231B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F02—COMBUSTION ENGINES; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS
    • F02B—INTERNAL-COMBUSTION PISTON ENGINES; COMBUSTION ENGINES IN GENERAL
    • F02B77/00—Component parts, details or accessories, not otherwise provided for
    • F02B77/08—Safety, indicating or supervising devices

Abstract

The invention aims to provide a method for extracting sensitive fault characteristics of a common rail fuel injector based on CHDE and PWFP, which comprises the steps of firstly collecting pressure signals of a high-pressure fuel pipe by using a high-precision pressure sensor; then calculating the composite level discrete entropy of the fuel pressure signal; then, calculating the proximity between the discrete entropies of each layer, and scoring according to the proximity, wherein the scores are arranged in an ascending order, and the lower the score is, the more sensitive the discrete entropies of the layers to fault characteristics; and finally, inputting the test sample into the trained binary tree support vector machine multi-classifier for fault diagnosis and pattern recognition, and outputting a fault diagnosis result. The method is suitable for extracting the sensitive fault characteristics of the common rail fuel injector under the complex working conditions, and has a good fault diagnosis effect.

Description

Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP
Technical Field
The invention relates to a diesel engine fault extraction method, in particular to a diesel engine common rail fuel injector fault extraction method.
Background
The electric control high-pressure common rail fuel injection technology is taken as the third diesel engine technology after the high-pressure injection technology and the supercharging technology, and becomes the hot spot of the competition of countries in the world in the aspect of the marine diesel engine technology. Because the common rail fuel system has increasingly complex functions and structures and severe working environment, the reliability of the common rail diesel fuel system becomes the key point of the research of the electric control fuel system. The engine management research of the Japan Ship east Association shows that the failure rate of the fuel injector accounts for 17.1% of the main engine failure, and the fuel injector failure causes the combustion deterioration, the power performance, the economic performance and the reliability performance of the diesel engine to be reduced, and the harmful emissions to be increased. Therefore, the method has important significance in timely and accurately diagnosing the fault of the common rail oil injector.
The concept of Composite Hierarchical Dispersion Entropy (CHDE) is used to measure the complexity of a fuel pressure wave time series at different scales or frequencies. The information of all sequences under the same scale is fully considered in the CHDE method, the entropy values of the nodes are the average value of the entropy values of all the sequences, and the entropy value mutation problem caused by sequence shortening can be well inhibited. Then, when the fault information of the original time series is reflected by taking the composite-level discrete entropy as a feature, redundant information and insensitive information are often contained in the fault feature, so that the selection of the fault feature is essential. For high-dimensional low-sample data, the processing effect of the existing dimension reduction method is not obvious enough.
Disclosure of Invention
The invention aims to provide a method for extracting sensitive fault characteristics of a common rail injector based on CHDE and PWFP, which solves the problems that the fault characteristics of the common rail injector are difficult to extract or the extraction precision is not high in the complex working condition environment.
The purpose of the invention is realized as follows:
the invention discloses a CHDE and PWFP-based common rail fuel injector sensitive fault feature extraction method, which is characterized by comprising the following steps of:
(1) collecting fuel pressure fluctuation signals of a high-pressure oil pipe through a pressure sensor, and dividing the collected signals into training signals and testing signals;
(2) respectively calculating the composite level discrete entropy of the training signal and the test signal;
(3) calculating the proximity between discrete entropies of each layer, scoring by taking the proximity as a reference, and arranging the scores according to an ascending order;
(4) selecting composite level discrete entropy in a training sample to form a feature vector subset, and inputting the feature vector subset into a binary tree support vector machine multi-classifier for training;
(5) and carrying out fault diagnosis and pattern recognition on the test sample by adopting the trained binary tree support vector machine multi-classifier, and outputting a fault diagnosis result.
The present invention may further comprise:
1. the pressure fluctuation signals of the high-pressure oil pipe in the step (1) comprise three types of normal state of the oil sprayer, clamping stagnation of a needle valve of the oil sprayer and blockage of a spray hole of the oil sprayer.
2. The calculation steps of the composite level discrete entropy in the step (2) are as follows:
A. let a time series { x (i), i ═ 1, 2., N }, of length N, define an operator
Figure BDA0002346345160000021
And
Figure BDA0002346345160000022
the following were used:
Figure BDA0002346345160000023
Figure BDA0002346345160000024
j＝0,1,...,2n-1，
Figure BDA0002346345160000025
and
Figure BDA0002346345160000026
representing the low frequency components of the time series decomposed at the first layer,
Figure BDA0002346345160000027
and
Figure BDA0002346345160000028
representing the high frequency components of the time series decomposition at the first layer,
Figure BDA0002346345160000029
and
Figure BDA00023463451600000210
representing two different layering modes of time series under the same scale;
B. defining the time series x (i) the node components of each layer decomposition are as follows:
Figure BDA00023463451600000211
C. calculating the discrete entropy of the hierarchical sequence obtained by each node, and then averaging the entropy values of different k of the same node to obtain the composite level discrete entropy of each level, which is marked as CHDEn,e。
3. In the step (3), scores are assigned according to the proximity degree of the samples in the same category, the maximum distance between the samples in other categories is kept, then each feature is assigned with a score to perform feature selection, and the flow of the PWFP algorithm is described as follows:
a. keeping β features out of d:
Figure BDA0002346345160000031
b. let q bejk＝[b1,b2,...,bd]T,biE {0,1} is (x)j,xk) Features of the opposite edge; similar features are found by:
Figure BDA0002346345160000032
c. information is collected from all possible pairs, denoted by P and Q respectively, as:
Figure BDA0002346345160000033
Figure BDA0002346345160000034
d. the criterion for selecting the feature is minimization, as follows:
Figure BDA0002346345160000035
4. in the steps (4) and (5), the binary tree SVM adopts an RBF kernel function to classify, and the penalty factor C is 1000.
The invention has the advantages that: the method is suitable for extracting the sensitive fault characteristics of the common rail fuel injector under the complex working conditions, and has a good fault diagnosis effect.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a block diagram of a high pressure common rail fuel system test platform;
FIG. 3 is a signal diagram of fuel pressure in the high pressure rail for three fuel injector states under different operating conditions;
FIG. 4 is a flowchart of CHDE calculation;
FIG. 5 is a chart of CHDE calculations for three injectors under different operating conditions.
Detailed Description
The invention will now be described in more detail by way of example with reference to the accompanying drawings in which:
with reference to fig. 1-5, a method for extracting sensitive fault characteristics of a common rail injector based on a channel and a power supply unit (PWFP) includes the following steps:
s1, collecting fuel pressure fluctuation signals of the high-pressure oil pipe by using a high-precision pressure sensor, and dividing the collected signals into training signals and testing signals;
s2, respectively calculating the composite level discrete entropy of the training signal and the test signal;
s3, calculating the proximity between discrete entropies of each layer, and scoring by taking the proximity as a reference, wherein the scores are arranged in an ascending order, and the lower the score is, the more sensitive the fault characteristics are;
s4, selecting the composite level discrete entropy in the training sample with the top rank to form a feature vector subset, and inputting the feature vector subset into a binary tree support vector machine multi-classifier for training;
and S5, performing fault diagnosis and pattern recognition on the test sample by adopting the trained binary tree support vector machine multi-classifier, and outputting a fault diagnosis result.
The high-pressure oil pipe pressure fluctuation signals in the step S1 comprise three types of normal state of the oil sprayer, clamping stagnation of the oil sprayer needle valve and blockage of the oil sprayer spray hole.
The calculation steps of the composite-level discrete entropy in step S2 are as follows:
the first step is as follows: let a time series { x (i), i ═ 1, 2., N }, of length N, define an operator
Figure BDA0002346345160000041
And
Figure BDA0002346345160000042
the following were used:
Figure BDA0002346345160000043
Figure BDA0002346345160000044
j＝0,1,...,2n-1
in fact, it is possible to use,
Figure BDA0002346345160000045
and
Figure BDA0002346345160000046
representing the low frequency components of the time series decomposed at the first layer,
Figure BDA0002346345160000047
and
Figure BDA0002346345160000048
represents the high frequency components of the time series decomposed at the first layer, and
Figure BDA0002346345160000049
and
Figure BDA00023463451600000410
representing two different hierarchical modes of time series under the same scale.
The second step is that: defining the time series x (i) the node components of each layer decomposition are as follows:
Figure BDA00023463451600000411
the third step: calculating the discrete entropy of the hierarchical sequence obtained by each node, and then averaging the different entropy values of k of the same node to obtain the composite hierarchical discrete entropy of each hierarchy, which is marked as CHDEn,e。
The core idea of the pairwise proximity (PWFP) in step S3 is to assign scores based on proximity to samples of the same category while maintaining the maximum distance to samples of other categories, and then assign scores to each feature for feature selection. The PWFP algorithm flow can be described as follows:
the first step is as follows: it is necessary to keep the β features out of d for (x)j,xk) Close to each other:
Figure BDA00023463451600000412
the second step is that: similarly, let q bejk＝[b1,b2,...,bd]T,biE {0,1} is (x)j,xk) Features of the opposite edge; if b isi＝1，yj≠ykIs the most distant. The method for finding similar features can be found by the following ways:
Figure BDA0002346345160000051
the third step: information is collected from all possible pairs, denoted by P and Q respectively, as:
Figure BDA0002346345160000052
Figure BDA0002346345160000053
the fourth step: is well characterized in that
Figure BDA0002346345160000058
And
Figure BDA0002346345160000059
the feature with higher probability appears in the middle. A reasonable criterion for selecting good features is to minimize the difference between the following equation:
Figure BDA0002346345160000054
in steps S4 and S5, the binary tree SVM performs classification by using an RBF kernel function, and the penalty factor C is 1000.
The invention discloses a CHDE and PWFP-based common rail injector sensitive fault feature extraction method, which comprises the following specific steps:
s1, collecting fuel pressure fluctuation signals of the high-pressure oil pipe by using the high-precision pressure sensor, dividing the collected signals into training signals and testing signals, wherein the test platform is shown in figure 2, and the collected signals are shown in figure 3.
And S2, respectively calculating the composite level discrete entropy of the training signal and the test signal. The CHDE calculation flow is shown in FIG. 4, the calculation result is shown in FIG. 5, and the specific steps are as follows:
the first step is as follows: let a time series { x (i), i ═ 1, 2., N }, of length N, define an operator
Figure BDA0002346345160000055
And
Figure BDA0002346345160000056
the following were used:
Figure RE-GDA0002565953660000055
Figure RE-GDA0002565953660000061
wherein
Figure BDA0002346345160000062
And
Figure BDA0002346345160000063
the form depends on the length of the time series, j being 0 or 1. Will be provided with
Figure BDA0002346345160000064
And
Figure BDA0002346345160000065
acting on time series x (i) respectively, thus having
Figure BDA0002346345160000066
Figure BDA0002346345160000067
j＝0,1,...,2n-1
In fact, it is possible to use,
Figure BDA0002346345160000068
and
Figure BDA0002346345160000069
representing the low frequency components of the time series decomposed at the first layer,
Figure BDA00023463451600000610
and
Figure BDA00023463451600000611
represents the high frequency components of the time series decomposed at the first layer, and
Figure BDA00023463451600000612
and
Figure BDA00023463451600000613
representing two different layering modes of time series under the same scale.
The second step is that: constructing an n-dimensional vector
Figure BDA00023463451600000618
The integer e can be represented as
Figure BDA00023463451600000614
Wherein the vector corresponding to the positive integer e is
Figure BDA00023463451600000619
The third step: based on vectors
Figure BDA00023463451600000620
The node components of each layer decomposition of the time series x (i) are defined as follows
Figure BDA00023463451600000615
The fourth step: calculating the discrete entropy of the hierarchical sequence obtained by each node, and then averaging the different entropy values of k of the same node to obtain the composite hierarchical discrete entropy of each hierarchy, which is marked as CHDEn,e。
For the low frequency part, the time series is defined by the following way for the time series { x (i), i ═ 1,2,.. N }, with scale factor τ
Figure BDA00023463451600000616
Namely, it is
Figure BDA00023463451600000617
j＝1,2,...,[N/τ],p＝1,2,...,τ
Then, for each scale factor τ, each time series is calculated
Figure BDA0002346345160000071
Then calculating the average value of the scale to obtain the discrete entropy under the scale factor, namely
Figure BDA0002346345160000072
And S3, calculating the proximity between the discrete entropies of each layer, and scoring by taking the proximity as a reference, wherein the scores are arranged in an ascending order, and the lower the score is, the more sensitive the fault characteristics are. The method comprises the following specific steps:
the first step is as follows: it is necessary to keep the β features out of d for (x)j,xk) Close to each other:
Figure BDA0002346345160000073
the second step is that: similarly, let q bejk＝[b1,b2,...,bd]T,biE {0,1} is (x)j,xk) Features of the opposite edge; if b isi＝1，yj≠ykIs the most distant. The method for finding similar features can be found by the following ways:
Figure BDA0002346345160000074
the third step: information is collected from all possible pairs, denoted by P and Q respectively, as:
Figure BDA0002346345160000075
Figure BDA0002346345160000076
the fourth step: good characteristics are that when P ═ P1,p2,...,pd]And Q ═ Q1,q2,...,qd]The feature with higher probability appears in the middle. A reasonable criterion for selecting good features is to minimize the difference between the following equation:
Figure BDA0002346345160000077
s4, selecting the composite-level discrete entropy in the training sample with the top rank to form a feature vector subset, and inputting the feature vector subset into a binary tree support vector machine multi-classifier for training;
and S5, performing fault diagnosis and pattern recognition on the test sample by adopting the trained binary tree support vector machine multi-classifier, and outputting a fault diagnosis result.

Claims (3)

1. A common rail fuel injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP is characterized by comprising the following steps:
(1) collecting fuel pressure fluctuation signals of a high-pressure oil pipe through a pressure sensor, and dividing the collected signals into training signals and testing signals;
(2) respectively calculating the composite level discrete entropy CHDE of the training signal and the test signal;
(3) calculating the proximity PWFP among the discrete entropies of each layer, scoring by taking the proximity as a reference, and arranging the scores according to an ascending order;
(4) selecting composite level discrete entropy in a training sample to form a feature vector subset, and inputting the feature vector subset into a binary tree support vector machine multi-classifier for training;
(5) performing fault diagnosis and pattern recognition on the test sample by adopting the trained binary tree support vector machine multi-classifier, and outputting a fault diagnosis result; the calculation steps of the composite level discrete entropy in the step (2) are as follows:
A. let a time series { x (i), i ═ 1, 2., N }, of length N, define an operator
Figure FDA0003550353340000011
And
Figure FDA0003550353340000012
the following were used:
Figure FDA0003550353340000013
Figure FDA0003550353340000014
Figure FDA0003550353340000015
and
Figure FDA0003550353340000016
representing the low frequency components of the time series decomposed at the first layer,
Figure FDA0003550353340000017
and
Figure FDA0003550353340000018
representing the high frequency components of the time series decomposition at the first layer,
Figure FDA0003550353340000019
and
Figure FDA00035503533400000110
representing two different layering modes of time series under the same scale;
B. defining the time series x (i) the node components of each layer decomposition are as follows:
Figure FDA00035503533400000111
C. calculating the discrete entropy of the hierarchical sequence obtained by each node, and then averaging the entropy values of different k of the same node to obtain the composite level discrete entropy of each level, which is marked as CHDEn,e；
e is a positive integer, the vector corresponding to the positive integer e is [ gamma ]1,γ2,...,γn]；
In the step (3), scores are assigned according to the proximity degree of the samples in the same category, the maximum distance between the samples in other categories is kept, then each feature is assigned with a score to perform feature selection, and the flow of the PWFP algorithm is described as follows:
a. keeping β features out of d:
Figure FDA00035503533400000112
b. let q bejk＝[b1,b2,...,bd]T,biE {0,1} is (x)j,xk) Features of the opposite edge; similar features are found by:
Figure FDA00035503533400000113
c. information is collected from all possible pairs, denoted by P and Q respectively, as:
Figure FDA0003550353340000021
Figure FDA0003550353340000022
d. a good feature is that when P ═ P1,p2,...,pd]And Q ═ Q1,q2,...,qd]The criterion for selecting the features is minimization, which is expressed by the following formula
Figure FDA0003550353340000023
。
2. The method for extracting the sensitive fault features of the common rail injector based on the composite-level discrete entropy CHED and the pairwise proximity PWFP as claimed in claim 1, is characterized in that: the pressure fluctuation signals of the high-pressure oil pipe in the step (1) comprise three types of normal state of the oil sprayer, clamping stagnation of a needle valve of the oil sprayer and blockage of a spray hole of the oil sprayer.
3. The method for extracting the sensitive fault features of the common rail injector based on the composite-level discrete entropy CHED and the pairwise proximity PWFP according to claim 1 is characterized in that: in the steps (4) and (5), the binary tree SVM adopts an RBF kernel function to classify, and the penalty factor C is 1000.
CN201911396075.5A 2019-12-30 2019-12-30 Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP Active CN111520231B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911396075.5A CN111520231B (en) 2019-12-30 2019-12-30 Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911396075.5A CN111520231B (en) 2019-12-30 2019-12-30 Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP

Publications (2)

Publication Number Publication Date
CN111520231A CN111520231A (en) 2020-08-11
CN111520231B true CN111520231B (en) 2022-06-21

Family

ID=71900394

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911396075.5A Active CN111520231B (en) 2019-12-30 2019-12-30 Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP

Country Status (1)

Country Link
CN (1) CN111520231B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112610344B (en) * 2020-12-11 2022-12-13 哈尔滨工程大学 Common rail fuel injector fault diagnosis method based on CEEMD and improved level discrete entropy
CN115387903B (en) * 2022-05-20 2024-04-19 潍柴动力股份有限公司 Fault detection method and device, power device and medium for diesel engine
CN114925787B (en) * 2022-07-19 2022-10-11 山东鑫亚格林鲍尔燃油系统有限公司 Intelligent common rail oil injector fault identification method

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE2501771A1 (en) * 1975-01-17 1976-07-22 Kloeckner Humboldt Deutz Ag PROCEDURE FOR STARTING AN EMERGENCY GENERATION MACHINE
US8732112B2 (en) * 2011-12-19 2014-05-20 GM Global Technology Operations LLC Method and system for root cause analysis and quality monitoring of system-level faults
CN106253910A (en) * 2016-09-22 2016-12-21 山东华旗新能源科技有限公司 A kind of compaction coding method
CN108446202B (en) * 2018-03-07 2021-03-26 武汉物联远科技有限公司 Method for judging safety condition of machine room equipment
CN110259616B (en) * 2019-06-19 2021-02-12 南京航空航天大学 Diesel engine common rail system fuel injector fault detection method based on measurable data characteristics

Also Published As

Publication number Publication date
CN111520231A (en) 2020-08-11

Similar Documents

Publication Publication Date Title
CN111520231B (en) Common rail injector sensitive fault feature extraction method based on composite-level discrete entropy CHDE and pairwise proximity PWFP
CN112131760B (en) CBAM model-based prediction method for residual life of aircraft engine
CN111175054B (en) Aeroengine fault diagnosis method based on data driving
CN109115501A (en) A kind of Civil Aviation Engine Gas path fault diagnosis method based on CNN and SVM
Wang et al. Research on the fault monitoring method of marine diesel engines based on the manifold learning and isolation forest
CN112948566B (en) Construction method and device of chemical knowledge graph and intelligent question-answering method and device
CN111368885A (en) Aero-engine gas circuit fault diagnosis method based on deep learning and information fusion
CN111042917B (en) Common rail fuel injector weak fault diagnosis method based on GOA-MCKD and hierarchical discrete entropy
CN111520267A (en) Common rail fuel injector fault diagnosis method based on FOA-VMD and HDE
CN111339297A (en) Network asset anomaly detection method, system, medium, and device
CN113538353B (en) Five-phase asynchronous motor rolling bearing fault diagnosis method based on single-channel diagram data enhancement and migration training residual error network
Wang et al. DPGCN model: a novel fault diagnosis method for marine diesel engines based on imbalanced datasets
CN111624570B (en) Radar target identification method based on two-dimensional convolutional neural network
Zhang et al. Intelligent machine fault diagnosis using convolutional neural networks and transfer learning
Cervantes-Bobadilla et al. Multiple fault detection and isolation using artificial neural networks in sensors of an internal combustion engine
CN114169091A (en) Method for establishing prediction model of residual life of engineering mechanical part and prediction method
Salah et al. OCR performance prediction using cross-OCR alignment
CN115660198B (en) Method for predicting residual service life of rolling bearing
CN105677664A (en) Compactness determination method and device based on web search
CN116610935A (en) Mechanical fault detection method based on engine vibration signal multi-mode analysis
CN115130617B (en) Detection method for continuous increase of self-adaptive satellite data mode
Betta et al. ANN-based sensor fault accommodation techniques
CN113537010B (en) Fifteen-phase asynchronous motor rolling bearing fault diagnosis method based on single-channel diagram data enhancement and migration training residual error network
CN116028865A (en) Aeroengine fault diagnosis method based on feature amplification
Wang et al. A novel scheme for intelligent fault diagnosis of marine diesel engine using the multi-information fusion technology

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