CN113449897B - Method for optimizing engine bench test parameters and sweeping points - Google Patents
Method for optimizing engine bench test parameters and sweeping points Download PDFInfo
- Publication number
- CN113449897B CN113449897B CN202010219347.0A CN202010219347A CN113449897B CN 113449897 B CN113449897 B CN 113449897B CN 202010219347 A CN202010219347 A CN 202010219347A CN 113449897 B CN113449897 B CN 113449897B
- Authority
- CN
- China
- Prior art keywords
- parameters
- fine
- optimization
- scanning
- influence
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000012360 testing method Methods 0.000 title claims abstract description 45
- 238000010408 sweeping Methods 0.000 title claims abstract description 32
- 238000005457 optimization Methods 0.000 claims abstract description 103
- 238000012163 sequencing technique Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 45
- 238000007637 random forest analysis Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 4
- 238000010998 test method Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000003066 decision tree Methods 0.000 description 10
- 238000013461 design Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000036039 immunity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Of Engines (AREA)
Abstract
According to the engine bench test parameter optimization point sweeping method provided by the invention, a plurality of parameters affecting an optimization target are obtained through analysis of the original scanning data; sequencing a plurality of parameters according to the importance degree affecting the optimization target, and simultaneously obtaining influence values of the plurality of parameters on the optimization target; determining the range of a plurality of fine-sweeping parameters according to the influence value; and determining a fine scanning area; selecting a plurality of fine scanning points in the fine scanning area; determining an optimal value of the influence of the fine scanning parameters on an optimization target; the steps of the optimization point sweeping method are realized through self-programming, so that an automatic optimization process of an optimization target is realized, and an optimal value of influence on the optimization target can be obtained intelligently; in the engine bench test process, the influence of different parameters on the optimization target can be locked to determine the fine sweeping parameters and reject parameters with little influence on the optimization target, so that the workload of the bench test can be reduced, and the efficiency of the bench test can be improved.
Description
Technical Field
The invention relates to the technical field of test and test, in particular to an engine bench test parameter optimization point sweeping method.
Background
In the process of calibrating and optimizing the engine bench test, scanning work of multiple calibration parameters is carried out aiming at an optimization target (such as gaseous emission and the like), and a multi-parameter coarse-step scanning matrix is usually formulated by engineers through personal experience, wherein the size of the matrix is the product of the number of the calibration parameters. And selecting an area with better target parameters according to the rough scanning result, and finely scanning (fine scanning) the calibration parameters of the area, wherein the scanning range is the product of the number of the calibration parameters of the area. The engine bench test calibration optimization method cannot lock the influence of different calibration parameters (even if an experienced engineer faces the problem of multiple parameters, only a small number of parameters can be locked), so that the scanning density of the fine scanning parameters cannot be distributed according to the importance of the parameters, all the parameters can be scanned according to similar scanning density, even the calibration parameters with small influence on the optimization target can be erroneously increased to perform fine scanning, and the test workload of the fine scanning of the parameters is greatly increased.
Disclosure of Invention
The invention aims to provide an engine bench test parameter optimization sweeping method, which aims to solve the problems that a large amount of time and bench resources are consumed and an optimal parameter combination scheme is not easy to find because an optimal combination scheme is determined by means of manual experience in the prior art.
The invention provides an engine bench test parameter optimization sweeping method, which comprises the following steps:
acquiring original scanning data;
analyzing and processing the original scan data to obtain a plurality of parameters affecting an optimization target;
analyzing a plurality of parameters, sequencing the parameters according to importance degrees according to the degrees affecting the optimization target, and obtaining influence values of the parameters on the optimization target;
determining a plurality of fine-scanning parameters according to the order of the importance degrees of the parameters, and determining the range of the fine-scanning parameters according to the influence value;
determining a fine-sweeping area according to the fine-sweeping parameters and the ranges corresponding to the fine-sweeping parameters, and selecting a plurality of fine-sweeping points in the fine-sweeping area;
and determining an optimal value of the influence of the fine scanning parameters on the optimization target.
Optionally, in the method for optimizing the scan point of the test parameters of the engine bench, a random forest algorithm is adopted to analyze and process the original scan data, so as to obtain parameters affecting an optimization target.
Optionally, in the method for optimizing the scan point of the engine bench test parameters, the method for sequencing the parameters according to importance degrees according to the degrees affecting the optimization target includes the following steps:
establishing a random forest algorithm model;
taking a plurality of parameters and the optimization targets as input variables in a random forest algorithm;
and analyzing the input variables by adopting a random forest algorithm to obtain importance distribution of different parameters, and sequencing a plurality of parameters.
Optionally, in the method for optimizing the scan point of the engine bench test parameter, the method for obtaining the influence value of a plurality of parameters on the optimization target comprises the following steps:
establishing a random forest algorithm model;
taking a plurality of parameters and the optimization targets as input variables in a random forest algorithm;
and analyzing the input variables by adopting a random forest algorithm to obtain influence values of a plurality of parameters on the optimization target.
Optionally, in the engine bench test parameter optimization scan method, the method for determining the fine scan parameter includes the following steps:
and sequentially sorting according to importance of the parameters and taking a plurality of parameters which are sorted in front as the fine scanning parameters.
Optionally, in the method for optimizing the scan point of the engine bench test parameter, the method for determining the fine scan area includes the following steps:
acquiring a plurality of fine scanning parameters and influence values corresponding to the fine scanning parameters;
combining the influence values corresponding to the fine scanning parameters to obtain a better combination of a plurality of influence optimization targets;
and sequencing the plurality of preferred combinations, and selecting the optimal combination as a fine scanning area.
Optionally, in the method for optimizing the scanning points of the engine bench test parameters, the method for selecting a plurality of fine scanning points comprises the following steps:
determining different sweep point densities of different fine sweep parameters according to the importance ranking of the fine sweep parameters;
the sweep point density is proportional to the importance of the fine sweep parameter;
and the scanning point falling into the fine scanning area is the fine scanning point.
Optionally, in the method for optimizing the scan point of the engine bench test parameter, the method for determining the optimal value of the influence of the fine scan parameter on the optimization target includes the following steps:
combining the fine scanning areas to determine the scanning point range of each fine scanning parameter;
and determining an optimal value of the influence of the fine scanning parameters on the optimization target by combining the scanning point range and the scanning point density.
Optionally, in the method for optimizing the scan point of the test parameters of the engine bench, an orthogonal test method is adopted to determine an optimal value of the influence of the fine scan parameters on the optimization target.
Optionally, in the method for optimizing the scan point of the test parameters of the engine bench, an optimum value of the influence of the fine scan parameters on the optimization target is determined by adopting a factorial method.
In summary, according to the method for optimizing the scan point of the test parameters of the engine pedestal, a plurality of parameters affecting the optimization target are obtained through analysis of the original scan data; sequencing a plurality of parameters according to the importance degree affecting the optimization target, and simultaneously obtaining influence values of the plurality of parameters on the optimization target; determining the range of a plurality of fine-sweeping parameters according to the influence value; and determining a fine scanning area; selecting a plurality of fine scanning points in the fine scanning area; determining an optimal value of the influence of the fine scanning parameters on an optimization target; the steps of the optimization point sweeping method are realized through self-programming, so that an automatic optimization process of an optimization target is realized, and an optimal value of influence on the optimization target can be obtained intelligently; in the engine bench test process, the influence of different parameters on the optimization target can be locked to determine the fine sweeping parameters and reject parameters with little influence on the optimization target, so that the workload of the bench test can be reduced, and the efficiency of the bench test can be improved.
Drawings
FIG. 1 is a flowchart of an engine bench test parameter optimization sweep method provided by an embodiment of the invention;
FIG. 2 is a flow chart of a method provided by an embodiment of the present invention for ranking a plurality of such parameters by importance according to the degree of impact on an optimization objective;
FIG. 3 is a flow chart of a method for deriving a plurality of values of influence of the parameters on an optimization objective provided by an embodiment of the present invention;
FIG. 4 is a flow chart of a method of determining a fine sweep area provided by an embodiment of the present invention;
FIG. 5 is a flowchart of a method for selecting a plurality of fine scan points according to an embodiment of the present invention;
FIG. 6 is a flow chart of a method for determining an optimal value of the impact of the fine sweep parameter on an optimization objective provided by an embodiment of the present invention.
Detailed Description
In order to make the objects, advantages and features of the present invention more clear, the method for optimizing the scan point of the test parameters of the engine pedestal according to the present invention will be described in further detail with reference to fig. 1 to 6. It should be noted that the drawings are in a very simplified form and are all to a non-precise scale, merely for convenience and clarity in aiding in the description of embodiments of the invention.
Referring to fig. 1, the application provides a method for optimizing scan points of test parameters of an engine bench, which comprises the following steps:
step S110: acquiring original scanning data;
step S120: analyzing and processing the original scan data to obtain a plurality of parameters affecting an optimization target;
step S130: analyzing a plurality of parameters, sequencing the parameters according to importance degrees according to the degrees affecting the optimization target, and obtaining influence values of the parameters on the optimization target;
step S140: determining a plurality of fine-scanning parameters according to the order of the importance degrees of the parameters, and determining the range of the fine-scanning parameters according to the influence value;
step S150: determining a fine-sweeping area according to the fine-sweeping parameters and the ranges corresponding to the fine-sweeping parameters, and selecting a plurality of fine-sweeping points in the fine-sweeping area;
step S160: and determining an optimal value of the influence of the fine scanning parameters on the optimization target.
Obtaining a plurality of parameters affecting an optimization target through analysis of the original scan data; sequencing a plurality of parameters according to the importance degree affecting the optimization target, and simultaneously obtaining influence values of the plurality of parameters on the optimization target; determining the range of a plurality of fine-sweeping parameters according to the influence value; and determining a fine scanning area; selecting a plurality of fine scanning points in the fine scanning area; determining an optimal value of the influence of the fine scanning parameters on an optimization target; the steps of the optimization point sweeping method are realized through self-programming, so that an automatic optimization process of an optimization target is realized, and an optimal value of influence on the optimization target can be obtained intelligently; in the engine bench test process, the influence of different parameters on the optimization target can be locked to determine the fine sweeping parameters and reject parameters with little influence on the optimization target, so that the workload of the bench test can be reduced, and the efficiency of the bench test can be improved.
Preferably, the original scan data is analyzed and processed using a machine learning algorithm to obtain a plurality of parameters affecting the optimization objective, and the original scan data is analyzed and processed using a random forest algorithm, which is a multifunctional machine learning algorithm, belonging to a combined algorithm, i.e. a plurality of basis algorithms are used in combination, each basis algorithm is predicted separately, and the final conclusion is voted (for classification problems) or averaged (including weighted average, for regression problems) by all basis algorithms. The principle schematic diagram of the random forest algorithm is shown in the following chart, the basic algorithm generally adopts decision trees, a forest formed by a plurality of decision trees is adopted in the basic algorithm, algorithm classification results are obtained by voting the decision trees, random processes are respectively added to the decision trees in the row direction and the column direction in the generating process, the decision trees are constructed in the row direction, the training data is obtained by sampling the decision trees in a put-back mode, the feature subsets are obtained by sampling the random samples without put-back mode in the column direction, and the optimal cut points of the feature subsets are obtained according to the feature subsets. The random forest algorithm is a combined model, the interior is still based on decision trees, and the random forest algorithm is classified by a plurality of decision tree voting results, unlike single decision tree classification, so that the algorithm is not easy to have an overfitting problem, and therefore, the random forest algorithm is good at treating the multi-parameter problem. The core of the random forest algorithm is random, and the randomness of the random forest algorithm is represented in the following 3 aspects:
1) The number of the extracted data which is put back at random can be the same as that of the original data, or can be slightly smaller;
2) Randomly selecting N parameters, and selecting the best attribute for splitting;
3) Randomly selecting one parameter from N best splitting parameters to split;
due to the randomness of the above 3 aspects and the characteristics of the decision tree, the random forest algorithm has the following advantages:
the overfitting is not easy to cause;
the noise immunity and the robustness are good;
the data processing mode is simple and convenient;
input of a plurality of parameters is suitable;
the method can simultaneously calculate the influence value of the parameter on the optimization target and analyze the importance of the parameter;
simultaneously outputting the influence value and the importance of the parameter;
the algorithm has the advantages, and is suitable for the application condition of multi-parameter influence of the sweep point optimization of bench test parameters. Other similar intelligent algorithms can also be used as bench test parameter optimization scan point data analysis methods.
Wherein, as shown in fig. 2, the method for sorting the plurality of parameters according to the importance degree according to the degree affecting the optimization objective comprises the following steps:
step S131: establishing a random forest algorithm model;
step S132: taking a plurality of parameters and the optimization targets as input variables in a random forest algorithm;
step S133: and analyzing the input variables by adopting a random forest algorithm to obtain importance distribution of different parameters, and sequencing a plurality of parameters.
As shown in fig. 3, the method for deriving the influence value of a plurality of the parameters on the optimization target includes the following steps:
step S134: establishing a random forest algorithm model;
step S135: taking a plurality of parameters and the optimization targets as input variables in a random forest algorithm;
step S136: and analyzing the input variables by adopting a random forest algorithm to obtain influence values of a plurality of parameters on the optimization target.
The method for determining the fine scanning parameters comprises the following steps of:
and sequentially sorting according to importance of the parameters and taking a plurality of parameters which are sorted in front as the fine scanning parameters. Specifically, the intelligent machine algorithm is firstly used for fitting the rough-scanned bench test data, wherein the intelligent machine algorithm adopts a random forest algorithm, and the random forest algorithm can simultaneously output a plurality of influence values of parameters on an optimization target in the process of classifying the original data. The method comprises the specific process that a plurality of influence values of parameters affecting an optimization target in the random forest algorithm are formed into a parameter average influence value, namely the parameter average influence value is the influence value of the parameter on the optimization target. In general, the influence value of parameters on the optimization target is usually kept high in accuracy due to self-fitting through rough scan data. Therefore, whether the calibration parameter affects the target is judged to be larger or not by analyzing the influence value of each parameter on the optimization target, if the influence value of a certain parameter on the optimization target is larger, the influence of the parameter on the optimization target is larger under the working condition, namely, the importance of the parameter with larger influence on the optimization target is larger, namely, the parameter is more important, and the analysis of the calibration working condition and the next fine scanning point can be assisted by analyzing the influence values of different parameters under different working conditions.
As shown in fig. 4, the method of determining the fine sweep area includes the steps of:
step 151, obtaining a plurality of influence values corresponding to the fine scanning parameters;
step S152, combining the influence values corresponding to the fine scanning parameters to obtain a better combination of a plurality of influence optimization targets;
and step 153, sorting the plurality of preferred combinations, and selecting the preferred combinations as the fine scanning areas.
As shown in fig. 5, the method for selecting a plurality of fine scanning points includes the following steps:
step S154, determining different sweep point densities of different fine sweep parameters according to the importance ranking of the fine sweep parameters;
step S155, the scanning point density is in direct proportion to the importance of the fine scanning parameter;
step S156, the scanning point falling into the fine scanning area is the fine scanning point.
As shown in fig. 6, the method for determining the optimal value of the influence of the fine sweep parameter on the optimization target includes the steps of:
step S161: combining the fine scanning areas to determine the scanning point range of each fine scanning parameter;
step S162: and determining an optimal value of the influence of the fine scanning parameters on the optimization target by combining the scanning point range and the scanning point density.
Through the determined parameter importance ranking, the sweep point density of each fine sweep parameter is determined, namely, one fine sweep parameter corresponds to one sweep point density, and more important fine sweep parameters adopt denser sweep point density, otherwise, more sparse sweep point density is adopted, and even no sweep can be performed for non-fine sweep parameters.
And determining the optimal value of the influence of the fine scanning parameters on the optimization target by a DOE test design method in combination with the scanning point range and the density, and greatly optimizing the test quantity in the fine scanning range. The DOE test design method is an orthogonal test method or a factorial method, namely, an optimal value of influence of the fine scanning parameters on an optimization target is determined by adopting the orthogonal test method; or determining the optimal value of the influence of the fine scanning parameters on the optimization target by adopting a factorial method.
The above description is only illustrative of the preferred embodiments of the present invention and is not intended to limit the scope of the present invention, and any alterations and modifications made by those skilled in the art based on the above disclosure shall fall within the scope of the appended claims.
Claims (7)
1. The method for optimizing the scanning point of the test parameters of the engine bench is characterized by comprising the following steps of:
acquiring original scanning data;
analyzing and processing the original scan data to obtain a plurality of parameters affecting an optimization target;
analyzing a plurality of parameters by adopting a random forest algorithm, sequencing the parameters according to importance degrees according to the degrees affecting an optimization target, and obtaining influence values of the parameters on the optimization target;
determining a plurality of fine-scanning parameters according to the order of the importance degrees of the parameters, and determining the range of the fine-scanning parameters according to the influence value;
determining a fine-sweeping area according to the fine-sweeping parameters and the ranges corresponding to the fine-sweeping parameters, and selecting a plurality of fine-sweeping points in the fine-sweeping area;
determining an optimal value of the influence of the fine scanning parameters on an optimization target;
the method for determining the fine sweeping area comprises the following steps of:
acquiring a plurality of fine scanning parameters and influence values corresponding to the fine scanning parameters;
combining the influence values corresponding to the fine scanning parameters to obtain a better combination of a plurality of influence optimization targets;
sequencing the plurality of preferred combinations, and selecting the optimal combination as a fine scanning area;
the method for selecting the plurality of fine scanning points comprises the following steps:
determining different sweep point densities of different fine sweep parameters according to the importance ranking of the fine sweep parameters;
the sweep point density is proportional to the importance of the fine sweep parameter;
and the scanning point falling into the fine scanning area is the fine scanning point.
2. The engine mount trial parameter optimizing and spot-sweeping method of claim 1, wherein the method of ranking the plurality of parameters by importance according to the degree of influence on the optimization objective comprises the steps of:
establishing a random forest algorithm model;
taking a plurality of parameters and the optimization targets as input variables in a random forest algorithm;
and analyzing the input variables by adopting a random forest algorithm to obtain importance distribution of different parameters, and sequencing a plurality of parameters.
3. The engine bench test parameter optimization sweep method of claim 1, wherein the method of deriving a plurality of said parameter impact values on the optimization objective comprises the steps of:
establishing a random forest algorithm model;
taking a plurality of parameters and the optimization targets as input variables in a random forest algorithm;
and analyzing the input variables by adopting a random forest algorithm to obtain influence values of a plurality of parameters on the optimization target.
4. The engine bench test parameter optimization sweep method of claim 1, wherein the method of determining the fine sweep parameter comprises the steps of:
and sequentially sorting according to importance of the parameters and taking a plurality of parameters which are sorted in front as the fine scanning parameters.
5. The engine bench test parameter optimization sweep method of claim 1, wherein the method of determining an optimal value of the influence of the fine sweep parameter on the optimization objective comprises the steps of:
combining the fine scanning areas to determine the scanning point range of each fine scanning parameter;
and determining an optimal value of the influence of the fine scanning parameters on the optimization target by combining the scanning point range and the scanning point density.
6. The engine bench test parameter optimization scan method of claim 5, wherein an orthogonal test method is used to determine an optimal value of the impact of the fine scan parameter on the optimization objective.
7. The engine bench test parameter optimization scan method of claim 5, wherein a factorial method is used to determine an optimal value of the impact of the fine scan parameter on an optimization objective.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010219347.0A CN113449897B (en) | 2020-03-25 | 2020-03-25 | Method for optimizing engine bench test parameters and sweeping points |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010219347.0A CN113449897B (en) | 2020-03-25 | 2020-03-25 | Method for optimizing engine bench test parameters and sweeping points |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113449897A CN113449897A (en) | 2021-09-28 |
| CN113449897B true CN113449897B (en) | 2024-04-16 |
Family
ID=77807495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010219347.0A Active CN113449897B (en) | 2020-03-25 | 2020-03-25 | Method for optimizing engine bench test parameters and sweeping points |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113449897B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114320595B (en) * | 2021-11-30 | 2022-12-02 | 江铃汽车股份有限公司 | Control method for avoiding gasoline engine running in knocking area |
| CN115329508B (en) * | 2022-10-14 | 2023-03-21 | 潍柴动力股份有限公司 | Method for optimizing passive prechamber of equivalence ratio engine |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102337979A (en) * | 2011-08-11 | 2012-02-01 | 浙江大学 | Automatic calibration parameter optimization method of engine based on genetic algorithm |
| CN104089777A (en) * | 2014-07-07 | 2014-10-08 | 广州锦红源电子科技有限公司 | Engine pedestal automatic calibration system |
| CN107655692A (en) * | 2017-09-28 | 2018-02-02 | 广州锦红源电子科技有限公司 | Engine pedestal automatic calibration method, device and system |
| CN108088680A (en) * | 2016-11-22 | 2018-05-29 | 上海汽车集团股份有限公司 | A kind of engine pedestal rating test system |
| CN108515962A (en) * | 2018-05-07 | 2018-09-11 | 吉林大学 | A kind of whole car controller of hybrid electric car quick calibrating method |
| CN109597968A (en) * | 2018-12-29 | 2019-04-09 | 西安电子科技大学 | Paste solder printing Performance Influence Factor analysis method based on SMT big data |
| CN109918699A (en) * | 2018-12-03 | 2019-06-21 | 西安航天动力技术研究所 | The key parameter recognition methods of C/C composite material larynx lining performance |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102012014469A1 (en) * | 2012-07-23 | 2014-05-15 | Fev Gmbh | Improved trial procedure |
-
2020
- 2020-03-25 CN CN202010219347.0A patent/CN113449897B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102337979A (en) * | 2011-08-11 | 2012-02-01 | 浙江大学 | Automatic calibration parameter optimization method of engine based on genetic algorithm |
| CN104089777A (en) * | 2014-07-07 | 2014-10-08 | 广州锦红源电子科技有限公司 | Engine pedestal automatic calibration system |
| CN108088680A (en) * | 2016-11-22 | 2018-05-29 | 上海汽车集团股份有限公司 | A kind of engine pedestal rating test system |
| CN107655692A (en) * | 2017-09-28 | 2018-02-02 | 广州锦红源电子科技有限公司 | Engine pedestal automatic calibration method, device and system |
| CN108515962A (en) * | 2018-05-07 | 2018-09-11 | 吉林大学 | A kind of whole car controller of hybrid electric car quick calibrating method |
| CN109918699A (en) * | 2018-12-03 | 2019-06-21 | 西安航天动力技术研究所 | The key parameter recognition methods of C/C composite material larynx lining performance |
| CN109597968A (en) * | 2018-12-29 | 2019-04-09 | 西安电子科技大学 | Paste solder printing Performance Influence Factor analysis method based on SMT big data |
Non-Patent Citations (4)
| Title |
|---|
| Construction and Parameters Correction of Wheel Virtual Test Bench Based on Measurement;Zhang Zhi-yuan; Liu Yu-mei; Yao Wei-min; Chen Tao;;Journal of Northeastern University. Natural Science;20170630;第38卷(第06期);全文 * |
| 基于DOE设计实现DVVT的高效台架标定;姜坤;刘然;杨中华;乔佳伟;;小型内燃机与车辆技术;第44卷(第01期);全文 * |
| 基于台架标定软件calibrate的优化研究及应用;周冬林;;内燃机与配件(第22期);全文 * |
| 基于监督学习的机电复合传动换挡同步位置识别;鲍永; 钟再敏; 甄永成; 黄益伦;;同济大学学报(自然科学版);第47卷(第S1期);正文第1-6页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113449897A (en) | 2021-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113449897B (en) | Method for optimizing engine bench test parameters and sweeping points | |
| Arakeri | Computer vision based fruit grading system for quality evaluation of tomato in agriculture industry | |
| CN109597968B (en) | SMT big data-based solder paste printing performance influence factor analysis method | |
| CN105786860B (en) | Data processing method and device in data modeling | |
| CN109813717A (en) | Defect detecting method | |
| US7739064B1 (en) | Inline clustered defect reduction | |
| Mousavirad et al. | Design of an expert system for rice kernel identification using optimal morphological features and back propagation neural network | |
| CN111382875A (en) | Federal model parameter determination method, device, equipment and storage medium | |
| CN111860576A (en) | Endometrium tumor classification labeling method based on random forest | |
| CN111950795B (en) | Random forest-based prediction method for loosening and conditioning water adding proportion | |
| Santosa et al. | Wood Types Classification using Back-Propagation Neural Network based on Genetic Algorithm with Gray Level Co-occurrence Matrix for Features Extraction. | |
| CN117541095A (en) | Agricultural land soil environment quality classification method | |
| CN116502943A (en) | Quality tracing method for investment casting product | |
| CN113722230B (en) | Integrated evaluation method and device for vulnerability mining capability of fuzzy test tool | |
| CN113762394B (en) | Blasting block prediction method | |
| Sun et al. | A novel method for multi-feature grading of mango using machine vision | |
| Chtioui et al. | Rough sets theory as a pattern classification tool for quality assessment of edible beans | |
| CN109740667B (en) | Image quality evaluation method based on quality sorting network and semantic classification | |
| CA2480931C (en) | General method of classifying plant embryos using a generalized lorenz-bayes classifier | |
| CN113627531A (en) | Method for determining ring rot resistance of pear trees based on support vector machine classification algorithm | |
| CN113807384A (en) | Measuring sensitivity of an image classifier to input image variations | |
| CN112215355A (en) | Neural network model optimization system and method | |
| Rianasari et al. | The classification of mushroom types using Naïve Bayes and principal component analysis | |
| CN111143436A (en) | Data mining method for big data | |
| CN112949438B (en) | Fruit visual classification method and system based on Bayesian network |
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 |