CN111159646A - Grouping method for multi-working-condition performance data of oil injector - Google Patents
Grouping method for multi-working-condition performance data of oil injector Download PDFInfo
- Publication number
- CN111159646A CN111159646A CN201911341429.6A CN201911341429A CN111159646A CN 111159646 A CN111159646 A CN 111159646A CN 201911341429 A CN201911341429 A CN 201911341429A CN 111159646 A CN111159646 A CN 111159646A
- Authority
- CN
- China
- Prior art keywords
- data
- grouping
- condition
- unqualified
- working
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
- Fuel-Injection Apparatus (AREA)
Abstract
The invention belongs to the technical field of automobile power systems, and relates to a grouping method of multi-working-condition performance data of an oil sprayer; the method comprises the following steps: 1. cleaning data and analyzing main components of the data; 2. distributing a weight W to each main working condition; 3. summing the weighted working condition data; 4. sorting according to the summed values; 5. extracting corresponding quantity of oil injectors in sequence for grouping, and judging whether the grouping requirements are met; 6. if the data is not qualified, replacing the data according to the unqualified condition, and simultaneously recording the unqualified problem; 7. if the data is qualified, continuing to execute the step 5 until all the data is extracted; 8. calculating the grouping efficiency, if the grouping efficiency does not meet the set requirement, modifying the weight according to the unqualified record, and returning to the step 3 to continue the execution; 9. if the set target is satisfied, the routine is ended. The invention comprehensively considers all main characteristics of the data, avoids the bias brought by only paying attention to a single characteristic, saves a large amount of analysis time and improves the grouping efficiency.
Description
Technical Field
The invention belongs to the technical field of automobile power systems, and relates to a grouping method of multi-working-condition performance data of an oil sprayer.
Background
In order to make the injection of each cylinder of the engine uniform, the oil injectors installed on one engine are required to be as consistent as possible. Therefore, before shipping, the injectors need to be grouped according to their performance data, and as shown in fig. 1, each group includes 6 injectors (determined according to the number of cylinders of the engine). The grouping requirements are shown in table 1.
TABLE 1 Fuel injector grouping requirements
Because the performance consistency requirements of different engines on the fuel injector under different working conditions are inconsistent, the specific working condition points are replaced by the working conditions 1-6 respectively. The calculation formula of the oil injection quantity deviation delta is shown in a formula (1), wherein Max, Min and Average are respectively the maximum value, the minimum value and the Average value of the group of data under a certain working condition.
The current method 1: the grouping personnel operate the EXCEL software by observing and analyzing all data needing grouping, such as partial data listed in the table 2, select the data of 6 working conditions approximately similar, temporarily divide the data into one group, calculate whether the data meet the grouping requirement in the table 1, and continuously search for proper data if the data do not meet the grouping requirement.
TABLE 2 Fuel injector Multi-regime Performance data (40 pieces of data, intercept)
The current method 2: and sequencing the performance data of the oil injectors according to a certain working condition through program design, dividing every 6 oil injectors into a group in sequence, and finally judging whether the requirements are met.
The disadvantage of the method 1 is that: firstly, each time a group of fuel injector data is selected and analyzed, the EXCEL is required to be manually operated to copy and paste, and under the condition of a large amount of data, the time is long and the labor cost is high. Secondly, the data are estimated by manpower according to experience and are possibly grouped into one group, the randomness is high, the failure probability is high, and the time is wasted. And under long-time work and a large amount of data, the probability of errors in manual judgment is increased.
The disadvantage of the method 2 is that: although the data is processed quickly by the program, a large amount of time can be saved compared with manual work, the algorithm of the program is too simple, and the data is sequenced according to a working condition. The data of only one working condition can be similar, and the requirements of other working conditions cannot be guaranteed, so that the qualification rate is low, the grouping efficiency is low, and the grouping rate is far lower than that of manual grouping.
Disclosure of Invention
The invention aims to solve the technical problems that in the prior art, the manual operation time and labor cost are high, fatigue and errors are easy to occur, a program grouping algorithm is simple, and the grouping efficiency is low, and provides a grouping method of multi-working-condition performance data of an oil sprayer.
In order to solve the technical problems, the invention is realized by adopting the following technical scheme, which is described by combining the accompanying drawings as follows:
a grouping method for multi-condition performance data of an oil injector comprises the following steps:
1. cleaning data, analyzing principal components of the data, selecting principal characteristics by utilizing PCA (principal component analysis), and selecting main working conditions according to the principal characteristics;
2. distributing a weight W to each main working condition;
3. summing the weighted working condition data;
4. sorting according to the summed values;
5. extracting corresponding quantity of oil injectors in sequence for grouping, and judging whether the grouping requirements are met;
6. if the data is not qualified, replacing the data according to the unqualified condition, and simultaneously recording the unqualified problem;
7. if the data is qualified, continuing to execute the step 5 until all the data is extracted;
8. calculating the grouping efficiency, if the grouping efficiency does not meet the set requirement, modifying the weight according to the unqualified record, and returning to the step 3 to continue the execution;
9. if the set target is satisfied, the routine is ended.
The invention comprehensively considers the performance data of the fuel injectors under multiple working conditions, divides the fuel injectors with close performance into one group, improves the grouping efficiency and realizes the grouping of the performance data of the fuel injectors under multiple working conditions.
The data are cleaned in the step 1, principal components of the data are analyzed, Principal Component Analysis (PCA) is utilized to select principal characteristics, and main working conditions are selected according to the principal characteristics; the specific contents are as follows:
importing Data into a Data processing page of EXCEL through a program, wherein each row of Data represents Data of each working condition of an oil injector, columns represent different working conditions respectively, and Data represents all the Data; then calling a python script to obtain main components of all data; principal component analysis PCA in a data analysis package scimit-spare of Python can calculate the principal component of a given data set; extracting principal components by Principal Component Analysis (PCA), reducing the feature number to 2 features, and recording as X1,X2;
Python script code implementation:
from sklearn.decomposition import PCA
the extraction of the principal component from PCA (0.95) # represents 95% of the original data
Data_new=pca.fittransform(Data)。
In the step 2, a weight W is distributed to each main working condition; the specific contents are as follows:
initializing a weight value for each feature, and respectively recording the weight value as W1,W2Wherein 2 weights need to satisfy a condition, and the cumulative sum of the weights is 1; first time initializationThe value may be arbitrarily assigned, for example, (0.5 ).
Step 3, summing the weighted working condition data; the specific calculation method is as follows: calculating weighted data D, D ═ X1*W1+X2*W2;
extracting corresponding quantities in sequence for judgment, wherein the specific quantities are determined by the number of cylinders of the corresponding engine; judging whether the standard requirement of grouping is met; in order to save judgment logic, a large oil quantity working condition and a small oil quantity working condition are selected to replace all working conditions, such as Qmain,Qsmall(ii) a And according toCalculate QmainAnd QsmallThe actual fuel injection quantity deviation δ.
If the data is unqualified in the step 6, replacing the data according to the unqualified condition, and simultaneously recording the unqualified problem; the specific contents are as follows:
if delta is out of tolerance, finding out the minimum value of the delta, and replacing the data of the next row in sequence, wherein the new data extracted subsequently can only be larger, so that the minimum value of the data is removed.
Calculating the grouping efficiency in the step 8, if the grouping efficiency does not meet the set requirement, modifying the weight according to the unqualified record, and returning to the step 3 to continue executing; the specific contents are as follows:
and calculating whether all the working conditions meet the requirements, counting the grouping efficiency η of the current time as the grouping number/(total number |6), if the set requirements are not met, modifying the weight according to the unqualified records, and returning to the step 3 to continue executing.
Compared with the prior art, the invention has the beneficial effects that:
the characteristic weighting algorithm of the invention is combined with a VBA program to realize the algorithm, all main characteristics of the data are comprehensively considered, the bias brought by only paying attention to single characteristics is avoided, and the grouping process adopts a similar unstacking method to screen the data one by one for judgment, thereby avoiding the waste of the whole group of data caused by large deviation of individual data. The invention not only saves a large amount of analysis time, but also has the grouping rate higher than the program processing of manual processing and simple sequencing algorithm, thereby greatly improving the grouping efficiency of grouping.
Drawings
The invention is further described with reference to the accompanying drawings in which:
FIG. 1 is a schematic grouping diagram of fuel injectors;
FIG. 2 is a fuel injector grouping flow chart;
FIG. 3 is a user interface for data cleansing;
FIG. 4 is a user interface for fuel injector grouping.
Detailed Description
The invention is described in detail below with reference to the attached drawing figures:
the invention adopts VBA program to realize algorithm, designs window program, and is convenient for operators to directly operate EXCEL to process data. The program comprises the functions of data cleaning, data grouping, data judgment, data statistics, manual adjustment and the like.
1. Referring to fig. 3, firstly, Data is imported into a Data processing page of EXCEL through a program, each row of Data represents Data of each working condition of one fuel injector, columns represent different working conditions respectively, and Data represents all Data. And then calling a python script to obtain the main components of all the data. The PCA (principal component analysis) in the data analysis package scimit-spare of Python is able to calculate the principal component of a given data set; in the data in this example, principal components are extracted through PCA (principal component analysis), and the dimension is reduced to 2 features from the original feature number. Are respectively marked as X1,X2;
Python script code implementation:
from sklearn.decomposition import PCA
the extraction of the principal component PCA (0.95) # represents 95% of the original data.
Data_new=pca.fittransform(Data)
2. Referring to FIG. 2, each feature is initialized with a weight, denoted as W1,W2Wherein 2 weights need to satisfy a condition that their cumulative sum is 1. For the first initialization, the value can be arbitrarily assigned, for example, (0.5 );
3. calculating weighted data D, D ═ X1*W1+X2*W2;
4. Because the data of the original fuel injector corresponds to the data columns of the D one by one, after all the data are sorted according to the weighted data D, the original data are also sorted;
5. extracting corresponding quantity in sequence, extracting 6 oil injectors in the example for judgment, judging whether the quantity meets the grouping standard requirement according to the table 1, and selecting a working condition with large oil quantity and a working condition with small oil quantity to replace all working conditions, such as Q, in order to save the judgment logicmain,Qsmall. And calculating Q according to the formula (1)mainAnd QsmallThe actual fuel injection quantity deviation δ;
6. if the data is not qualified, finding out the minimum value of the data, and replacing the data of the next row in sequence (because the new data extracted subsequently can only be larger, the minimum value of the data is removed, the new data added in is combined with the original 5 remaining data, and the situation is possibly more consistent, otherwise, the situation is worse);
7. referring to FIG. 1, if the specification requirements are met, the 6 rows of data (6 injector data) are grouped and placed into the completion zone (another page). The program continues to execute step 5 until all data is extracted;
8. referring to fig. 4, it is calculated whether all the operating conditions meet the requirements, because only 2 operating conditions are considered in the determination process of step 6, although the qualification of 2 operating conditions does not completely guarantee the qualification of other operating conditions through the weighted sorting, W is1,W2The packet efficiency η is counted finally as the number of packets/(total number |6), if the set requirement is not met, the weight is modified according to the unqualified records, and the step 3 is returned to for further executionRecording in groups, if the number of large oil quantity working conditions is large, increasing W1If the number of the unqualified working conditions with small oil quantity is large, the W is increased2;
The symbol "|" indicates an integer division.
9. If the set target is satisfied, the routine is ended.
The invention is practically applied to the grouping of the fuel injectors of the engine common rail system in the subdivision field, and can also be applied to the grouping of multi-working condition data or multi-feature data according to the given grouping specification requirement in other fields.
Claims (7)
1. A grouping method for multi-working-condition performance data of an oil injector is characterized by comprising the following steps:
step 1: cleaning data, analyzing principal components of the data, selecting principal characteristics by using Principal Component Analysis (PCA), and selecting main working conditions according to the principal characteristics;
step 2: distributing a weight W to each main working condition;
and step 3: summing the weighted working condition data;
and 4, step 4: sorting according to the summed values;
and 5: extracting corresponding quantity of oil injectors in sequence for grouping, and judging whether the grouping requirements are met;
step 6: if the data is not qualified, replacing the data according to the unqualified condition, and simultaneously recording the unqualified problem;
and 7: if the data is qualified, continuing to execute the step 5 until all the data is extracted;
and 8: calculating the grouping efficiency, if the grouping efficiency does not meet the set requirement, modifying the weight according to the unqualified record, and returning to the step 3 to continue the execution;
and step 9: if the set target is satisfied, the routine is ended.
2. The method for grouping the multi-condition performance data of the fuel injector according to claim 1, characterized by comprising the following steps of:
the data are cleaned in the step 1, principal components of the data are analyzed, Principal Component Analysis (PCA) is utilized to select principal characteristics, and main working conditions are selected according to the principal characteristics; the specific contents are as follows:
importing Data into a Data processing page of EXCEL through a program, wherein each row of Data represents Data of each working condition of an oil injector, columns represent different working conditions respectively, and Data represents all the Data; then calling a python script to obtain main components of all data; principal component analysis PCA in a data analysis package scimit-spare of Python can calculate the principal component of a given data set; extracting principal components by Principal Component Analysis (PCA), reducing the feature number to 2 features, and recording as X1,X2;
Python script code implementation:
from sklearn.decomposition import PCA
the extraction of the principal component from PCA (0.95) # represents 95% of the original data
Data_new=pca.fittransform(Data)。
3. The method for grouping the multi-condition performance data of the fuel injector according to claim 2, characterized in that:
in the step 2, a weight W is distributed to each main working condition; the specific contents are as follows:
initializing a weight value for each feature, and respectively recording the weight value as W1,W2Wherein 2 weights need to satisfy a condition, and the cumulative sum of the weights is 1; for the first initialization, an arbitrary value may be assigned, for example, (0.5 ).
4. The method for grouping the multi-condition performance data of the fuel injector according to claim 3, characterized in that:
step 3, summing the weighted working condition data; the specific calculation method is as follows: calculating weighted data D, D ═ X1*W1+X2* W2。
5. The method for grouping the multi-condition performance data of the fuel injector according to claim 4, characterized in that:
step 5, extracting corresponding quantity of oil injectors in sequence to group the oil injectors, and judging whether the grouping requirements are met; the specific contents are as follows:
extracting corresponding quantities in sequence for judgment, wherein the specific quantities are determined by the number of cylinders of the corresponding engine; judging whether the standard requirement of grouping is met; in order to save judgment logic, a large oil quantity working condition and a small oil quantity working condition are selected to replace all working conditions, such as Qmain,Qsmall(ii) a And according toCalculate QmainAnd QsmallThe actual fuel injection quantity deviation δ.
6. The method for grouping the multi-condition performance data of the fuel injector according to claim 5, characterized in that:
if the data is unqualified in the step 6, replacing the data according to the unqualified condition, and simultaneously recording the unqualified problem; the specific contents are as follows:
if delta is out of tolerance, finding out the minimum value of the delta, and replacing the data of the next row in sequence, wherein the new data extracted subsequently can only be larger, so that the minimum value of the data is removed.
7. The method for grouping the multi-condition performance data of the fuel injector according to claim 6, characterized in that:
calculating the grouping efficiency in the step 8, if the grouping efficiency does not meet the set requirement, modifying the weight according to the unqualified record, and returning to the step 3 to continue executing; the specific contents are as follows:
and calculating whether all the working conditions meet the requirements, counting the grouping efficiency η of the current time as the grouping number/(total number |6), if the set requirements are not met, modifying the weight according to the unqualified records, and returning to the step 3 to continue executing.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911341429.6A CN111159646B (en) | 2019-12-24 | 2019-12-24 | Grouping method for multi-working-condition performance data of fuel injector |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911341429.6A CN111159646B (en) | 2019-12-24 | 2019-12-24 | Grouping method for multi-working-condition performance data of fuel injector |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111159646A true CN111159646A (en) | 2020-05-15 |
CN111159646B CN111159646B (en) | 2023-08-15 |
Family
ID=70558219
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911341429.6A Active CN111159646B (en) | 2019-12-24 | 2019-12-24 | Grouping method for multi-working-condition performance data of fuel injector |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111159646B (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101178773A (en) * | 2007-12-13 | 2008-05-14 | 北京中星微电子有限公司 | Image recognition system and method based on characteristic extracting and categorizer |
CN103390154A (en) * | 2013-07-31 | 2013-11-13 | 中国人民解放军国防科学技术大学 | Face recognition method based on extraction of multiple evolution features |
CN103488790A (en) * | 2013-10-08 | 2014-01-01 | 河海大学 | Polychronic time sequence similarity analysis method based on weighting BORDA counting method |
US20150185270A1 (en) * | 2012-12-28 | 2015-07-02 | State Grid Corporation Of China | Method for recognizing transformer partial discharge pattern based on singular value decomposition algorithm |
CN105528516A (en) * | 2015-12-01 | 2016-04-27 | 三门县人民医院 | Clinic pathology data classification method based on combination of principal component analysis and extreme learning machine |
CN107798696A (en) * | 2017-10-19 | 2018-03-13 | 北京联合大学 | A kind of three-dimensional point cloud method for registering based on guarantor office PCA |
CN109815990A (en) * | 2018-12-28 | 2019-05-28 | 天津大学 | Principal component analysis system based on centralization weight |
CN110021386A (en) * | 2017-07-27 | 2019-07-16 | 北大医疗信息技术有限公司 | Feature extracting method and feature deriving means, equipment, storage medium |
-
2019
- 2019-12-24 CN CN201911341429.6A patent/CN111159646B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101178773A (en) * | 2007-12-13 | 2008-05-14 | 北京中星微电子有限公司 | Image recognition system and method based on characteristic extracting and categorizer |
US20150185270A1 (en) * | 2012-12-28 | 2015-07-02 | State Grid Corporation Of China | Method for recognizing transformer partial discharge pattern based on singular value decomposition algorithm |
CN103390154A (en) * | 2013-07-31 | 2013-11-13 | 中国人民解放军国防科学技术大学 | Face recognition method based on extraction of multiple evolution features |
CN103488790A (en) * | 2013-10-08 | 2014-01-01 | 河海大学 | Polychronic time sequence similarity analysis method based on weighting BORDA counting method |
CN105528516A (en) * | 2015-12-01 | 2016-04-27 | 三门县人民医院 | Clinic pathology data classification method based on combination of principal component analysis and extreme learning machine |
CN110021386A (en) * | 2017-07-27 | 2019-07-16 | 北大医疗信息技术有限公司 | Feature extracting method and feature deriving means, equipment, storage medium |
CN107798696A (en) * | 2017-10-19 | 2018-03-13 | 北京联合大学 | A kind of three-dimensional point cloud method for registering based on guarantor office PCA |
CN109815990A (en) * | 2018-12-28 | 2019-05-28 | 天津大学 | Principal component analysis system based on centralization weight |
Non-Patent Citations (1)
Title |
---|
李潍: ""电控汽油喷射发动机的自诊断系统(下)"", 《北京汽车》 * |
Also Published As
Publication number | Publication date |
---|---|
CN111159646B (en) | 2023-08-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106599052B (en) | Apache Kylin-based data query system and method | |
CN108846555B (en) | Efficient and accurate filling method for large data missing value of power load | |
CN112101674B (en) | Resource allocation matching method, device, equipment and medium based on group intelligent algorithm | |
CN111159646A (en) | Grouping method for multi-working-condition performance data of oil injector | |
CN110263291B (en) | Industrial data trend identification method and system | |
CN110019152A (en) | A kind of big data cleaning method | |
CN114238360A (en) | User behavior analysis system | |
CN107194570A (en) | Screening technique and its system for individual enterprise's key decision point | |
CN105589900A (en) | Data mining method based on multi-dimensional analysis | |
CN117455222A (en) | Solving method based on distributed heterogeneous flow shop group scheduling problem | |
CN110362577B (en) | Data insertion method, device, equipment and storage medium | |
CN106547758B (en) | Data binning method and device | |
CN110516184B (en) | Simulation operation method for counting UV (ultraviolet) quantity | |
CN111680046B (en) | Fast storage method for high-frequency power data | |
CN114358924A (en) | Method and device for screening limit adjustment strategy, computer equipment and storage medium | |
CN103150349B (en) | Sample attribute analysis method, device and equipment | |
CN109992329A (en) | A kind of method grade method for analyzing performance based on rear end grain technology | |
CN111260085A (en) | Device replacement man-hour evaluation method, device, equipment and medium | |
CN108614954B (en) | Method and device for short sequence error correction of second-generation sequence | |
Lei et al. | The application of multidimensional data analysis in the EIA database of electric industry | |
CN104573077A (en) | Method and device for displaying data | |
CN111626649A (en) | Big data processing method and device | |
CN1193308C (en) | Method for searching characteristic vector data space | |
CN114139485B (en) | Netlist device parameter calculation method | |
CN113760489B (en) | Resource allocation method and device |
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 |