A study on automatic adjustment of the HCCI engine controller using machine learning
An automatic adjustment method of the model-based controller of an HCCI engine was designed in this study. As modeling errors are inevitable, feedback control is usually introduced to reduce the effect of the modeling errors. However, especially under transient conditions, the control performance ma...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | Japanese |
| Published: |
The Japan Society of Mechanical Engineers
2022-06-01
|
| Series: | Nihon Kikai Gakkai ronbunshu |
| Subjects: | |
| Online Access: | https://www.jstage.jst.go.jp/article/transjsme/88/911/88_22-00005/_pdf/-char/en |
| _version_ | 1798019103330402304 |
|---|---|
| author | Akihiro TAKESHITA Yudai YAMASAKI Mitsuhiro MUTO Takayuki HIKITA Takuma FUJII Saori MIZUNO |
| author_facet | Akihiro TAKESHITA Yudai YAMASAKI Mitsuhiro MUTO Takayuki HIKITA Takuma FUJII Saori MIZUNO |
| author_sort | Akihiro TAKESHITA |
| collection | DOAJ |
| description | An automatic adjustment method of the model-based controller of an HCCI engine was designed in this study. As modeling errors are inevitable, feedback control is usually introduced to reduce the effect of the modeling errors. However, especially under transient conditions, the control performance may deteriorate, because this is a control with the information of the previous cycle. The transient control performance is thought to be improved by taking modeling errors into consideration. Therefore, an algorithm to adjust the feedback input based on the prediction of the modeling error was developed. The modeling error was learned and predicted by ReOS-ELM (Regularized Online Sequential Extreme Learning Machine), which is a method of online machine learning with low computational load. The modeling error learning was conducted every engine cycle. The feedback input was adjusted so that the output prediction by the engine model including its modeling error prediction coincided with the output reference. The reference tracking performance was improved by the proposed method. |
| first_indexed | 2024-04-11T16:35:13Z |
| format | Article |
| id | doaj.art-cdda92ff79c74d26a4f88f4d119facfd |
| institution | Directory Open Access Journal |
| issn | 2187-9761 |
| language | Japanese |
| last_indexed | 2024-04-11T16:35:13Z |
| publishDate | 2022-06-01 |
| publisher | The Japan Society of Mechanical Engineers |
| record_format | Article |
| series | Nihon Kikai Gakkai ronbunshu |
| spelling | doaj.art-cdda92ff79c74d26a4f88f4d119facfd2022-12-22T04:13:52ZjpnThe Japan Society of Mechanical EngineersNihon Kikai Gakkai ronbunshu2187-97612022-06-018891122-0000522-0000510.1299/transjsme.22-00005transjsmeA study on automatic adjustment of the HCCI engine controller using machine learningAkihiro TAKESHITA0Yudai YAMASAKI1Mitsuhiro MUTO2Takayuki HIKITA3Takuma FUJII4Saori MIZUNO5Department of Mechanical Engineering, The University of TokyoDepartment of Human Engineered Environmental Studies, The University of TokyoMazda Motor CorporationMazda Motor CorporationMazda Motor CorporationMazda Motor CorporationAn automatic adjustment method of the model-based controller of an HCCI engine was designed in this study. As modeling errors are inevitable, feedback control is usually introduced to reduce the effect of the modeling errors. However, especially under transient conditions, the control performance may deteriorate, because this is a control with the information of the previous cycle. The transient control performance is thought to be improved by taking modeling errors into consideration. Therefore, an algorithm to adjust the feedback input based on the prediction of the modeling error was developed. The modeling error was learned and predicted by ReOS-ELM (Regularized Online Sequential Extreme Learning Machine), which is a method of online machine learning with low computational load. The modeling error learning was conducted every engine cycle. The feedback input was adjusted so that the output prediction by the engine model including its modeling error prediction coincided with the output reference. The reference tracking performance was improved by the proposed method.https://www.jstage.jst.go.jp/article/transjsme/88/911/88_22-00005/_pdf/-char/enhomogeneous charge compression ignitioncontrolmodeling errorautomatic adjustmentonline machine learning |
| spellingShingle | Akihiro TAKESHITA Yudai YAMASAKI Mitsuhiro MUTO Takayuki HIKITA Takuma FUJII Saori MIZUNO A study on automatic adjustment of the HCCI engine controller using machine learning Nihon Kikai Gakkai ronbunshu homogeneous charge compression ignition control modeling error automatic adjustment online machine learning |
| title | A study on automatic adjustment of the HCCI engine controller using machine learning |
| title_full | A study on automatic adjustment of the HCCI engine controller using machine learning |
| title_fullStr | A study on automatic adjustment of the HCCI engine controller using machine learning |
| title_full_unstemmed | A study on automatic adjustment of the HCCI engine controller using machine learning |
| title_short | A study on automatic adjustment of the HCCI engine controller using machine learning |
| title_sort | study on automatic adjustment of the hcci engine controller using machine learning |
| topic | homogeneous charge compression ignition control modeling error automatic adjustment online machine learning |
| url | https://www.jstage.jst.go.jp/article/transjsme/88/911/88_22-00005/_pdf/-char/en |
| work_keys_str_mv | AT akihirotakeshita astudyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT yudaiyamasaki astudyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT mitsuhiromuto astudyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT takayukihikita astudyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT takumafujii astudyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT saorimizuno astudyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT akihirotakeshita studyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT yudaiyamasaki studyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT mitsuhiromuto studyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT takayukihikita studyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT takumafujii studyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning AT saorimizuno studyonautomaticadjustmentofthehccienginecontrollerusingmachinelearning |