GB2622708A - SVM-based cold flow test detection method and system during diesel engine assembly - Google Patents
SVM-based cold flow test detection method and system during diesel engine assembly Download PDFInfo
- Publication number
- GB2622708A GB2622708A GB2318389.0A GB202318389A GB2622708A GB 2622708 A GB2622708 A GB 2622708A GB 202318389 A GB202318389 A GB 202318389A GB 2622708 A GB2622708 A GB 2622708A
- Authority
- GB
- United Kingdom
- Prior art keywords
- diesel engine
- exhaust pressure
- svm
- engine assembly
- cold test
- 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
- 238000012360 testing method Methods 0.000 title claims abstract description 89
- 238000001514 detection method Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000012549 training Methods 0.000 claims abstract description 12
- 238000007405 data analysis Methods 0.000 claims description 10
- 238000002790 cross-validation Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000010606 normalization Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 abstract description 64
- 239000013598 vector Substances 0.000 description 13
- 238000005516 engineering process Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/02—Details or accessories of testing apparatus
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/04—Testing internal-combustion engines
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/04—Testing internal-combustion engines
- G01M15/05—Testing internal-combustion engines by combined monitoring of two or more different engine parameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Combustion & Propulsion (AREA)
- Chemical & Material Sciences (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing Of Engines (AREA)
Abstract
An SVM-based cold flow test detection method and system during diesel engine assembly. The method comprises: acquiring the intake pressure, crankshaft torque and exhaust pressure of a diesel engine, and constructing a cold flow test database; determining a distribution pattern of exhaust pressure data by means of bigdata analysis; according to the distribution pattern of the exhaust pressure data, obtaining threshold values for a normal exhaust pressure, a smaller exhaust pressure and a larger exhaust pressure; and after the threshold values are determined, constructing a sample set for diesel engine assembly quality detection on the basis of the cold flow test database, performing training and testing by using a support vector machine (SVM) algorithm, so as to form a cold flow test quality detection support vector machine algorithm model, and identifying the diesel engine assembly quality by means of the support vector machine algorithm model, such that an SVM-based cold flow test detection method during diesel engine assembly is formed. By means of the detection method and system, the accuracy of detection of diesel engine assembly quality is improved, thereby effectively identifying diesel engine assembly quality.
Description
SVM-BASED COLD FLOW TEST DETECTION METHOD AND
SYSTEM DURING DIESEL ENGINE ASSEMBLY
The present disclosure claims the priority of the Chinese Patent Application 202111153792.2 filed on September 29, 2021 and entitled "METHOD AND SYSTEM FOR DIESEL ENGINE ASSEMBLY COLD TEST DETECTION BASED ON SVM", which is incorporated herein by reference in its entirety.
TECHNICAL FIELD
The present disclosure relates to the field of the diesel engine, and particularly relates to a method and a system for diesel engine assembly cold test detection based on SVM
BACKGROUND
The statements in this part only provide background information relevant to the present disclosure and do not necessarily constitute the prior art.
The diesel engine is very complicated power machinery, and can provide power sources for various kinds of transport equipment. With the increasing demand of the society on environmental protection, hot test in a diesel engine assembly process is gradually replaced by cold test, and how to improve the cold test detection technology in the assembly process becomes a research focus. The exhaust pressure of the engine is one of major parameters of diesel engine quality detection. The exhaust pressure in a cold test is influenced by assembly parameters of the intake system, the cylinder head, the engine body, the piston and the crankshaft connecting rod system. The inventor found that there is no method and device to judge the assembly quality according to the correlation between the exhaust distribution characteristics of diesel engine and the above parameters in the existing technology and it is impossible to accurately detect the assembly failure of diesel engine caused by it.
SUMMARY
In view of the shortcomings of the existing technology, the purpose of this invention is to provide a SVM-based diesel engine assembly cold test detection method, with exhaust pressure as the main parameter, and determine its normal threshold range, according to the exhaust pressure-related feature vectors such as intake parameters, crankshaft torque parameters are classified. It can be used to judge the quality of assembly, which plays an extremely important role in improving the assembly quality of diesel engines. In order to achieve the above purpose, the present disclosure is realized through the following technical solution: a method for diesel engine assembly cold test detection based on SVM includes the following contents: acquiring an intake pressure, a crankshaft torque and an exhaust pressure of a diesel engine, and building a cold test database; judging a distribution pattern of exhaust pressure data by the big data analysis; obtaining a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure according to the distribution pattern of the exhaust pressure data; and after the thresholds are determined, building a diesel engine assembly quality detection sample set based on the cold test database, performing training and testing by a support vector machine (SVM) algorithm to form a cold test quality detection SVM model, and identifying the diesel engine assembly quality through the SVM mod& to form the method for diesel engine assembly cold test detection based on SVM.
According to the method for diesel engine assembly cold test detection based on SVM, the intake pressure, the crankshaft torque and the exhaust pressure of the diesel engine are detected by a cold test device.
According to the method for diesel engine assembly cold test detection based on SVM, the cold test device acquires data of intake pressure and exhaust pressure of the diesel engine through a gas pressure sensor, and acquires crankshaft torque data of the diesel engine through a torque sensor, and the cold test database is obtained by acquiring data of tens of thousands of diesel engines.
According to the method for diesel engine assembly cold test detection based on SVM, the distribution pattern of the exhaust pressure data is judged by a ratio (Z-score) of a statistical magnitude of a parameter skewness value to a standard error.
According to the method for diesel engine assembly cold test detection based on SVM, the data is in normal distribution in a case that the ratio of the statistical magnitude of the parameter skewness value to the standard error EI-2,21; the data is in positively skew distribution in a case that the ratio of the statistical magnitude of the parameter skewness value to the standard error >2; and the data is in negatively skew distribution in a case that the ratio of the statistical magnitude of the parameter skewness value to the standard error <-2.
According to the method for diesel engine assembly cold test detection based on SVIVI, a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure are determined by a 3cs principle of the big data analysis According to the method for diesel engine assembly cold test detection based on SVM, a normalization processing is respectively performed on a value of the intake pressure and a value of the crankshaft torque, the values are combined with classified exhaust pressure data, and the diesel engine assembly quality detection sample set based on the cold test database is built.
According to the method for diesel engine assembly cold test detection based on SVM, the SVM model is trained and tested by selecting a radial basis kernel function, an optimum penalty factor C and an optimum variance g are found by a cross validation method, that is, an iteration length is determined in a set parameter range, the penalty factors and variances are combined in a pairwi se manner, and a combination with highest precision is selected in a plurality of groups of cross validation According to the method for diesel engine assembly cold test detection based on SVM, the built diesel engine assembly quality detection sample set is divided into a training set and a test set, the training set is trained by using the SVM algorithm, the cold test quality detection SVM model is obtained, and the accuracy of the SVM model on the assembly quality detection is determined by using the test set so as to identify the diesel engine assembly quality.
In a second aspect, the present disclosure further provides a system for diesel engine assembly cold test detection based on SVM, using the method for diesel engine assembly cold test detection based on SVM, including a data processing unit, configured to build the cold test database by using the intake pressure, the crankshaft torque and the exhaust pressure of the diesel engine, judge the distribution pattern of exhaust pressure data in assembly feature parameters by the big data analysis, and obtain a threshold of normal assembly exhaust pressure, a threshold of lower assembly exhaust pressure, and a threshold of higher assembly exhaust pressure according to the distribution pattern of the exhaust pressure data to build the diesel engine assembly quality detection sample set; and a model building unit, configured to build the SVM model after a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure are determined, train and test the SVM model, and identify the diesel engine assembly quality through the trained and tested SVM model.
The present disclosure has the following beneficial effects: 1) The present disclosure builds the cold test database based on the intake pressure, the crankshaft torque and the exhaust pressure of the diesel engine, obtains the distribution pattern of the exhaust pressure data by the big data analysis, further determines a plurality of thresholds of the assembly exhaust pressure to lay the foundation for the assembly quality identification, builds a feature vector and build the SVM model after the thresholds are determined, and forms the method for diesel engine assembly cold test detection based on SVM.
2) The present disclosure trains and tests the SVM model by selecting a kernel function and finding penalty factors and variances, and improves the assembly quality, so that the assembly reliability is improved, and the practicability is high.
3) The invention is helpful to improve the accuracy of model by labeling and classifying different feature vectors of diesel engine..
BRIEF DESCRIPTION OF THE DRAWINGS
The drawings attached to the specification constituting a part of the present disclosure are used to provide further understanding on the present disclosure, and the exemplary embodiments of the present disclosure and their descriptions are used to illustrate the present disclosure and do not constitute improper limitation to the present disclosure.
FIG. 1 is a flowchart of a method for diesel engine assembly cold test detection based on SVM according to one or more implementations of the present disclosure
DETAILED DESCRIPTION
It should be noted that the following detailed descriptions are illustrative and are intended to provide further illustration on the present disclosure. Unless otherwise specified, all technical and scientific terms used in the present disclosure have the same meaning as they are normally understood by an ordinary skilled in the art.
It needs to be noted that the terms used herein are only intended to describe the specific implementations and are not intended to limit exemplary implementations according to the present disclosure. As used herein, unless otherwise specified in the present disclosure, the singular form is also intended to include the plural form. In addition, it also should be understood that when the terms "include" and/or "comprise" are used in this specification, they indicate the existence of features, steps, operations, devices, components and/or combinations thereof As described in the background, there is a problem that the diesel engine assembly quality detection cannot be accurately identified in the prior art. In order to solve the above technical problems, the present disclosure provides a method for diesel engine assembly cold test detection based on SVM.
In a typical implementation of the present disclosure, as shown in FIG. 1, a method for diesel engine assembly cold test detection based on SVM includes the following contents: an intake pressure, a crankshaft torque and an exhaust pressure of a diesel engine are acquired. A cold test database is built.
A distribution pattern of exhaust pressure data is judged by a big data analysis.
A threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure are obtained according to the distribution pattern of the exhaust pressure data.
After the thresholds are determined, a diesel engine assembly quality detection sample set is built based on the cold test database. Training and testing are performed by using a support vector machine (SVM) algorithm to form a cold test quality detection SVM model. The diesel engine assembly quality is identified through the SVM model to form the method for diesel engine assembly cold test detection based on SVM.
Further, the intake pressure, the crankshaft torque and the exhaust pressure are detected by a cold test device.
Specifically, the cold test device acquires data of the intake pressure and the exhaust pressure of the diesel engine through a gas pressure sensor, and acquires crankshaft torque data of the diesel engine through a torque sensor, and the cold test database is obtained by acquiring data of tens of thousands of diesel engines.
For the distribution pattern of the exhaust pressure data, the distribution pattern of the exhaust pressure data is judged through a ratio (Z-score) of a statistical magnitude of a parameter skewness value to a standard error. A calculation formula of the skewness value is = 1 [( X, In the ) ], and a calculation formula of a standard error is n SE formula, 1/ represents a sample mean value, and a represents a sample standard deviation. In a case that Z-score [-2,2], the data is in normal distribution. In a case that Z-score >2, the data is in positively skew distribution. In a case that Z-score <-2, the data is in negatively skew distribution.
In a case that the data is in normal distribution, a mean value u and a standard deviation G are determined. According to (u-3G, u+3c)], a non-nal parameter range of the exhaust pressure is obtained For the condition that the data is in positively skew distribution, in a case that Z-score (2,3], the data needs to be integrally subjected to extraction of square root, i.e., X = sff In a case that Z-score >3, the data may be subjected to a natural logarithm (In) new taking operation, i.e., II =1nX, and the pattern is converted into normal distribution. For the condition that the data is in negatively skew distribution, in a case that Z-score e(-3,-2], a conversion formula needing to be used is X". = VX+1-X. In a case that Z-score <-3, a conversion formula needing to be used is X = ln(X",," +1-X) , and the pattern is converted into normal distribution. A threshold range may be determined through normal distribution. A value is an abnormal value when the exhaust pressure is equal to or lower than u-3G or higher than u+3G, wherein, the u-3G is the lower threshold of the exhaust pressure and the u+3G is the higher threshold of the exhaust pressure. Therefore, a corresponding threshold determining method is given by aiming at different data distribution patterns, and the foundation is laid for assembly quality identification.
In this embodiment, a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure are determined by a 3G principle of the big data analysis.
During building the SVM model, the feature vector needs to be built, and the feature vector is endowed with a label for classification. In some examples, the labels are respectively 0, 1 and 2. 0 represents a feature vector with the exhaust pressure lower than the threshold minimum value, 1 represents a feature vector with the exhaust pressure within a threshold range, and 2 represents a feature vector with the exhaust pressure higher than the threshold maximum value.
Further, a normalization processing is respectively performed on a value of the intake pressure and a value of the crankshaft torque, all values are mapped into a range [-1,1], a mapping operation formula is y = 2*(x-x)/(x -.x""" ) -1, the values are combined with the classified exhaust pressure data, and the diesel engine assembly quality detection sample set is built based on the cold test database. ;Further, the SVM model is trained and tested by selecting a kernel function. In this embodiment, the selected kernel function is a radial basis kernel function, and a formula is as follows: max - E 1(7)K(Xj, Xi k 2;4 f 1(k, -1(;)= 0, 0 k, cm0 In the formula, K(iv,,X, ) = exP(-glIX, X/112)'g>0 is the radial basis kernel function, and 6 represents an insensitive loss coefficient. The radial basis kernel function can effectively solve the problem that the sample type and the feature factor are in a nonlinear relationship, and an optimum penalty factor C and an optimum variance g are found by a cross validation method, that is, an iteration length is determined in a set parameter range, such as (-10, 10). The iteration length may be selected to be 0.5, the penalty factors and variances are combined in a pairwise manner, and a combination with highest precision is selected in a plurality of groups of cross validation. In this embodiment, the penalty factor C is selected to be 0.33, and the variance g is selected to be 1.32. ;Further, the built diesel engine assembly quality detection sample set is divided into a training set and a test set, the training set is trained by the SVM algorithm to obtain the cold test quality detection SVM model, and the accuracy of the SVM model on the assembly quality detection is determined by using the test set, so that the diesel engine assembly quality is identified According to the method for diesel engine assembly cold test detection based on SVM provided by the present disclosure, the diesel engine assembly exhaust pressure data is used as a basis to build the SVM model, and the SVM model is trained and tested. Additionally, other assembly feature parameters such as intake pressure and crankshaft torque are also considered, and the accuracy of the SVM model on the assembly quality detection is effectively ensured. Through the trained and tested SVM model, the accuracy on the diesel engine assembly quality identification can be improved, and the diesel engine assembly reliability is correspondingly improved. ;Embodiment II This embodiment provides a system for diesel engine assembly cold test detection based on SVM, using the method for diesel engine assembly cold test detection based on SVM, including: a data processing unit, configured to build the cold test database by using the intake pressure, the crankshaft torque and the exhaust pressure of the diesel engine, judge the distribution pattern of exhaust pressure data in assembly feature parameters by the big data analysis, and obtain a threshold of normal assembly exhaust pressure, a threshold of lower assembly exhaust pressure, and a threshold of higher assembly exhaust pressure according to the distribution pattern of the exhaust pressure data to build the diesel engine assembly quality detection sample set; and a model building unit, configured to build the SVM model after a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure are determined, train and test the SVM model, and identify the diesel engine assembly quality through the trained and tested SVM model. Therefore, the system for diesel engine assembly cold test detection based on SVM is formed through the data processing unit and the model building unit. ;It can be understood that the system for diesel engine assembly cold test detection based on SVM may be stored through a storage device such as a computer. ;Further, the model building unit builds the SVM model according to the determined a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure. ;In the built SVM model, the feature vector needs to be built, the feature vector is endowed with the labels of 0, 1 and 2 for classification. 0 represents a feature vector with the exhaust pressure lower than the threshold minimum value, 1 represents a feature vector with the exhaust pressure within a threshold range, and 2 represents a feature vector with the exhaust pressure higher than the threshold maximum value. ;Further, a normalization processing is respectively performed on a value of the intake pressure and a value of the crankshaft torque, all values are mapped into a range [-1,1], a mapping operation formula is y = 2*(x-x""")/(x""". -x"" ) -1, the values are combined with the classified exhaust pressure data, and the diesel engine assembly quality detection sample set is built based on the cold test database.
For the distribution pattern of the exhaust pressure data, the distribution pattern of the exhaust pressure data is judged through a ratio (Z-score) of a statistical magnitude of a parameter skewness value to a standard error. In a case that Z-score E[-2,2], the data is in normal distribution. In a case that Z-score >2, the data is in positively skew distribution. In a case that Z-score< -2, the data is in negatively skew distribution.
The SVIVI model is trained and tested by selecting the radial basis kernel function. The kernel function is a radial basis kernel function, an optimum penalty factor C and an optimum variance g are found by a cross validation method, that is, an iteration length is determined in a set parameter range, such as (-10, 10), the iteration length may be selected to be 0.5, the penalty factors and variances are combined in a pairwise manner, and a combination with highest precision is selected in a plurality of groups of cross validation.
Further, the built diesel engine assembly quality detection sample set is divided into a training set and a test set, the training set is trained by the SVM algorithm to obtain the cold test quality detection SVM model, and the accuracy of the SVM model on the assembly quality detection is determined by using the test set, so that the diesel engine assembly quality is identified.
The above descriptions are merely preferred embodiments of the present disclosure, but are not intended to limit the present disclosure. For those skilled in the art, various changes and variations may be made according to the present disclosure. Any modification, equivalent substitution, improvement, etc. made within the spirit and principles of the present disclosure shall fall within the protection scope of the present disclosure.
Claims (6)
- CLAIMSWhat is claimed is: I. A method for diesel engine assembly cold test detection based on SVM, comprising the following contents.acquiring an intake pressure, a crankshaft torque and an exhaust pressure of a diesel engine, and building a cold test database; judging a distribution pattern of exhaust pressure data by a big data analysis; obtaining a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure according to the distribution pattern of the exhaust pressure data; after the thresholds are determined, building a diesel engine assembly quality detection sample set based on the cold test database, performing training and testing by using a SVM algorithm to form a cold test quality detection SVM model, and identifying the diesel engine assembly quality through the SVM model to form the method for diesel engine assembly cold test detection based on SVM; judging the distribution pattern of the exhaust pressure data by a ratio of a statistical magnitude of a parameter skewness value to a standard error, obtaining a judging result that the data is in normal distribution in a case that the ratio of the statistical magnitude of the parameter skewness value to the standard error [-2,2]; obtaining a judging result that the data is in positively skew distribution in a case that the ratio of the statistical magnitude of the parameter skewness value to the standard error >2; obtaining a judging result that the data is in negatively skew distribution in a case that the ratio of the statistical magnitude of the parameter skewness value to the standard error <-2; determining a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure by a 3G principle of the big data analysis; and respectively performing normalization processing on a value of the intake pressure and a value of the crankshaft torque, respectively combining the values with classified exhaust pressure data, and building the diesel engine assembly quality detection sample set based on the cold test database.
- 2. The method for diesel engine assembly cold test detection based on SVM according to claim 1, wherein the intake pressure, the crankshaft torque and the exhaust pressure of the diesel engine are detected by a cold test device
- 3. The method for diesel engine assembly cold test detection based on SVM according to claim 2, wherein the cold test device acquires data of intake pressure and exhaust pressure of the diesel engine through a gas pressure sensor, and acquires crankshaft torque data of the diesel engine through a torque sensor.
- 4. The method for diesel engine assembly cold test detection based on SVM according to claim 1, wherein the SVM model is trained and tested by selecting a radial basis kernel function, an optimum penalty factor C and an optimum variance g are found by a cross validation method, that is, an iteration length is determined in a set parameter range, the penalty factors and variances are combined in a pairwise manner, and a combination with highest precision is selected in a plurality of groups of cross validation.
- 5. The method for diesel engine assembly cold test detection based on SVM according to claim 4, wherein the built diesel engine assembly quality detection sample set is divided into a training set and a test set, the training set is trained by using a SVM, the cold test quality detection SVM model is obtained, and the accuracy of the SVM model on the assembly quality detection is determined by using the test set so as to identify the diesel engine assembly quality.
- 6. A system for diesel engine assembly cold test detection based on SVM, using the method for diesel engine assembly cold test detection based on SVM according to claim 1 and comprising: a data processing unit, configured to build the cold test database by using the intake pressure, the crankshaft torque and the exhaust pressure of the diesel engine, judge the distribution pattern of exhaust pressure data in assembly feature parameters by the big data analysis, and obtain a threshold of normal assembly exhaust pressure, a threshold of lower assembly exhaust pressure, and a threshold of higher assembly exhaust pressure according to the distribution pattern of the exhaust pressure data to build the diesel engine assembly quality detection sample set; and a model building unit, configured to build the SVM model after a threshold of normal exhaust pressure, a threshold of lower exhaust pressure, and a threshold of higher exhaust pressure are determined, train and test the SVM model, and identify the diesel engine assembly quality through the trained and tested SVM model.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111153792.2A CN113884305B (en) | 2021-09-29 | 2021-09-29 | Diesel engine assembly cold test detection method and system based on SVM |
| PCT/CN2022/119171 WO2023051275A1 (en) | 2021-09-29 | 2022-09-16 | Svm-based cold flow test detection method and system during diesel engine assembly |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| GB202318389D0 GB202318389D0 (en) | 2024-01-17 |
| GB2622708A true GB2622708A (en) | 2024-03-27 |
Family
ID=79008371
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| GB2318389.0A Pending GB2622708A (en) | 2021-09-29 | 2022-09-16 | SVM-based cold flow test detection method and system during diesel engine assembly |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN113884305B (en) |
| GB (1) | GB2622708A (en) |
| WO (1) | WO2023051275A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884305B (en) * | 2021-09-29 | 2022-06-28 | 山东大学 | Diesel engine assembly cold test detection method and system based on SVM |
| CN116433111B (en) * | 2023-06-15 | 2023-10-20 | 潍柴动力股份有限公司 | Construction method and quality evaluation method of crankshaft assembly torque quality detection system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110093182A1 (en) * | 2008-05-08 | 2011-04-21 | Borgwarner Beru Systems Gmbh | Estimating engine parameters based on dynamic pressure readings |
| CN108492399A (en) * | 2018-02-11 | 2018-09-04 | 山东大学 | Bull-dozer fault diagnosis expert system for diesel engine based on big data analysis and method |
| CN109726230A (en) * | 2018-12-04 | 2019-05-07 | 重庆大学 | A kind of method of big data analysis model prediction engine performance |
| CN110261122A (en) * | 2019-06-20 | 2019-09-20 | 大连理工大学 | A kind of boat diesel engine fault monitoring method based on piecemeal |
| CN111351668A (en) * | 2020-01-14 | 2020-06-30 | 江苏科技大学 | Diesel engine fault diagnosis method based on optimized particle swarm algorithm and neural network |
| CN111562111A (en) * | 2020-06-05 | 2020-08-21 | 上海交通大学 | Engine cold state test fault diagnosis method |
| CN111832617A (en) * | 2020-06-05 | 2020-10-27 | 上海交通大学 | Engine cold state test fault diagnosis method |
| CN113884305A (en) * | 2021-09-29 | 2022-01-04 | 山东大学 | Diesel engine assembly cold test detection method and system based on SVM |
Family Cites Families (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0912880B1 (en) * | 1996-07-19 | 2009-09-30 | Toyota Jidosha Kabushiki Kaisha | Method of testing assembled internal combustion engine |
| JP2000199428A (en) * | 1998-10-29 | 2000-07-18 | Hitachi Metals Ltd | Evaluation model and evaluation method for exhaust manifold which connects catalytic carrier, and exhaust manifold obtained thereby |
| JP4776029B2 (en) * | 2007-03-28 | 2011-09-21 | Ｕｄトラックス株式会社 | Power test oil circulation system for cold test bench |
| CN201034820Y (en) * | 2007-04-10 | 2008-03-12 | 浙江大学鸣泉电子科技有限公司 | Gasoline vehicle extraction flow analyzer |
| FR2923546A1 (en) * | 2007-11-09 | 2009-05-15 | Renault Sas | Exhaust gas's mass flow measuring method for motor vehicle, involves performing gas analysis in pipes and in exhaust line for determining mass flow of exhaust gas so as to correctly adjust combustion parameters of engine |
| SE534475C2 (en) * | 2010-01-18 | 2011-09-06 | Scania Cv Ab | Method and apparatus for preventing fuel accumulation in an exhaust system of a motor vehicle |
| WO2011118095A1 (en) * | 2010-03-25 | 2011-09-29 | Ｕｄトラックス株式会社 | Engine exhaust purification device and engine exaust purification method |
| CN102680242B (en) * | 2012-06-06 | 2014-09-17 | 哈尔滨工程大学 | Fault diagnosing method for diesel engine based on swarm intelligence |
| JP6225934B2 (en) * | 2015-02-27 | 2017-11-08 | トヨタ自動車株式会社 | Control device for internal combustion engine |
| CN105319071B (en) * | 2015-09-21 | 2017-11-07 | 天津大学 | Diesel Engine Fuel System Fault Diagnosis method based on least square method supporting vector machine |
| JP2018115997A (en) * | 2017-01-19 | 2018-07-26 | 株式会社堀場製作所 | Exhaust gas flow rate measurement unit and exhaust gas analysis device |
| NL2019853B1 (en) * | 2017-11-03 | 2019-05-13 | Daf Trucks Nv | System and method for detecting malfunctioning turbo-diesel cylinders. |
| CN108387378B (en) * | 2018-01-22 | 2019-11-15 | 西安航天动力试验技术研究所 | A kind of engine test Propellant Supply low frequency pulsating suppressing method and system |
| CN110749450A (en) * | 2018-07-24 | 2020-02-04 | 上海华依科技集团股份有限公司 | Air inlet and exhaust plugging testing mechanism and method for engine cold test equipment |
| CN111175052A (en) * | 2018-11-13 | 2020-05-19 | 上海华依科技集团股份有限公司 | Engine gas distribution system fault testing system for engine cold test |
| CN109506942B (en) * | 2018-12-04 | 2020-08-04 | 重庆大学 | Method for analyzing correlation between engine cold test detection data and station by big data |
| CN110197222A (en) * | 2019-05-29 | 2019-09-03 | 国网河北省电力有限公司石家庄供电分公司 | A method of based on multi-category support vector machines transformer fault diagnosis |
| CN110308005A (en) * | 2019-06-12 | 2019-10-08 | 上海市环境科学研究院 | Fractions of Diesel Engine Exhaust Particulates object generation system and Fractions of Diesel Engine Exhaust Particulates object analogy method |
| CN111779573B (en) * | 2020-06-28 | 2022-02-11 | 河南柴油机重工有限责任公司 | Diesel engine online fault detection method and device |
-
2021
- 2021-09-29 CN CN202111153792.2A patent/CN113884305B/en active Active
-
2022
- 2022-09-16 WO PCT/CN2022/119171 patent/WO2023051275A1/en unknown
- 2022-09-16 GB GB2318389.0A patent/GB2622708A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110093182A1 (en) * | 2008-05-08 | 2011-04-21 | Borgwarner Beru Systems Gmbh | Estimating engine parameters based on dynamic pressure readings |
| CN108492399A (en) * | 2018-02-11 | 2018-09-04 | 山东大学 | Bull-dozer fault diagnosis expert system for diesel engine based on big data analysis and method |
| CN109726230A (en) * | 2018-12-04 | 2019-05-07 | 重庆大学 | A kind of method of big data analysis model prediction engine performance |
| CN110261122A (en) * | 2019-06-20 | 2019-09-20 | 大连理工大学 | A kind of boat diesel engine fault monitoring method based on piecemeal |
| CN111351668A (en) * | 2020-01-14 | 2020-06-30 | 江苏科技大学 | Diesel engine fault diagnosis method based on optimized particle swarm algorithm and neural network |
| CN111562111A (en) * | 2020-06-05 | 2020-08-21 | 上海交通大学 | Engine cold state test fault diagnosis method |
| CN111832617A (en) * | 2020-06-05 | 2020-10-27 | 上海交通大学 | Engine cold state test fault diagnosis method |
| CN113884305A (en) * | 2021-09-29 | 2022-01-04 | 山东大学 | Diesel engine assembly cold test detection method and system based on SVM |
Non-Patent Citations (2)
| Title |
|---|
| CHEN, Qinhe et al,"Study on Relevance between Engine Bolt Tightening...", pages 1662-1669,ISSN:1003-8728. * |
| YANG, Jia et al, "Normal Domain Design of Multi-Parameter...",Vol 29, No 03, 20.06.13, ISSN:1006-2343. * |
Also Published As
| Publication number | Publication date |
|---|---|
| GB202318389D0 (en) | 2024-01-17 |
| CN113884305B (en) | 2022-06-28 |
| CN113884305A (en) | 2022-01-04 |
| WO2023051275A1 (en) | 2023-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| GB2622708A (en) | SVM-based cold flow test detection method and system during diesel engine assembly | |
| CN104978522B (en) | A kind of method and apparatus for detecting malicious code | |
| CN110381079B (en) | Method for detecting network log abnormity by combining GRU and SVDD | |
| CN113489685B (en) | Secondary feature extraction and malicious attack identification method based on kernel principal component analysis | |
| CN113469230B (en) | Rotor system deep migration fault diagnosis method, system and medium | |
| Cai et al. | A novel improved local binary pattern and its application to the fault diagnosis of diesel engine | |
| Li et al. | An unsupervised learning framework for event detection, type identification and localization using pmus without any historical labels | |
| CN112333128A (en) | Web attack behavior detection system based on self-encoder | |
| Li et al. | Intelligent fault diagnosis of aeroengine sensors using improved pattern gradient spectrum entropy | |
| CN114722641A (en) | Lubricating oil state information integrated evaluation method and system for detection laboratory | |
| CN110686897A (en) | Variable working condition rolling bearing fault diagnosis method based on subspace alignment | |
| CN112464297B (en) | Hardware Trojan detection method, device and storage medium | |
| CN109000924B (en) | Method for monitoring state of ball screw pair based on K mean value | |
| Wang et al. | Temperature forecast based on SVM optimized by PSO algorithm | |
| CN107067034B (en) | Method and system for rapidly identifying infrared spectrum data classification | |
| CN114962173A (en) | Method and device for detecting yawing abnormity of wind driven generator and electronic equipment | |
| CN103616434B (en) | Mass Spectrometric Identification method of microorganism | |
| CN117647697B (en) | Knowledge graph-based fault positioning method and system for electric power metering assembly line | |
| Gu et al. | Research on intelligent detection technology of surface defects of nuclear fuel rods based on machine vision | |
| CN114091540B (en) | Method for constructing cold test intelligent detection model of diesel engine, detection method and system | |
| CN114580982B (en) | Method, device and equipment for evaluating data quality of industrial equipment | |
| CN107247662B (en) | Software defect detection method and device | |
| CN101788891A (en) | Quick and safe storage method based on disk and safe disk | |
| Xu et al. | Natural-Ordered Complex Hadamard Transform Based Shape Description and Retrieval | |
| KR20240039407A (en) | Robustness measurement system and application of ai model for malware variant analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 789A | Request for publication of translation (sect. 89(a)/1977) |
Ref document number: 2023051275 Country of ref document: WO |