Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines
The standards for emissions from diesel engines are becoming more stringent and accurate emission modeling is crucial in order to control the engine to meet these standards. Soot emissions are formed through a complex process and are challenging to model. A comprehensive analysis of diesel engine so...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/23/7865 |
| _version_ | 1797507833817726976 |
|---|---|
| author | Saeid Shahpouri Armin Norouzi Christopher Hayduk Reza Rezaei Mahdi Shahbakhti Charles Robert Koch |
| author_facet | Saeid Shahpouri Armin Norouzi Christopher Hayduk Reza Rezaei Mahdi Shahbakhti Charles Robert Koch |
| author_sort | Saeid Shahpouri |
| collection | DOAJ |
| description | The standards for emissions from diesel engines are becoming more stringent and accurate emission modeling is crucial in order to control the engine to meet these standards. Soot emissions are formed through a complex process and are challenging to model. A comprehensive analysis of diesel engine soot emissions modeling for control applications is presented in this paper. Physical, black-box, and gray-box models are developed for soot emissions prediction. Additionally, different feature sets based on the least absolute shrinkage and selection operator (LASSO) feature selection method and physical knowledge are examined to develop computationally efficient soot models with good precision. The physical model is a virtual engine modeled in GT-Power software that is parameterized using a portion of experimental data. Different machine learning methods, including Regression Tree (RT), Ensemble of Regression Trees (ERT), Support Vector Machines (SVM), Gaussian Process Regression (GPR), Artificial Neural Network (ANN), and Bayesian Neural Network (BNN) are used to develop the black-box models. The gray-box models include a combination of the physical and black-box models. A total of five feature sets and eight different machine learning methods are tested. An analysis of the accuracy, training time and test time of the models is performed using the K-means clustering algorithm. It provides a systematic way for categorizing the feature sets and methods based on their performance and selecting the best method for a specific application. According to the analysis, the black-box model consisting of GPR and feature selection by LASSO shows the best performance with test <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.96. The best gray-box model consists of SVM-based method with physical insight feature set along with LASSO for feature selection with test <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.97. |
| first_indexed | 2024-03-10T04:55:01Z |
| format | Article |
| id | doaj.art-1fc1445dda8645dc90e571841efab4cb |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T04:55:01Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-1fc1445dda8645dc90e571841efab4cb2023-11-23T02:18:58ZengMDPI AGEnergies1996-10732021-11-011423786510.3390/en14237865Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition EnginesSaeid Shahpouri0Armin Norouzi1Christopher Hayduk2Reza Rezaei3Mahdi Shahbakhti4Charles Robert Koch5Mechanical Engineering Department, University of Alberta, Edmonton, AB T6G 1H9, CanadaMechanical Engineering Department, University of Alberta, Edmonton, AB T6G 1H9, CanadaIAV GmbH, 38518 Gifhorn, GermanyIAV GmbH, 38518 Gifhorn, GermanyMechanical Engineering Department, University of Alberta, Edmonton, AB T6G 1H9, CanadaMechanical Engineering Department, University of Alberta, Edmonton, AB T6G 1H9, CanadaThe standards for emissions from diesel engines are becoming more stringent and accurate emission modeling is crucial in order to control the engine to meet these standards. Soot emissions are formed through a complex process and are challenging to model. A comprehensive analysis of diesel engine soot emissions modeling for control applications is presented in this paper. Physical, black-box, and gray-box models are developed for soot emissions prediction. Additionally, different feature sets based on the least absolute shrinkage and selection operator (LASSO) feature selection method and physical knowledge are examined to develop computationally efficient soot models with good precision. The physical model is a virtual engine modeled in GT-Power software that is parameterized using a portion of experimental data. Different machine learning methods, including Regression Tree (RT), Ensemble of Regression Trees (ERT), Support Vector Machines (SVM), Gaussian Process Regression (GPR), Artificial Neural Network (ANN), and Bayesian Neural Network (BNN) are used to develop the black-box models. The gray-box models include a combination of the physical and black-box models. A total of five feature sets and eight different machine learning methods are tested. An analysis of the accuracy, training time and test time of the models is performed using the K-means clustering algorithm. It provides a systematic way for categorizing the feature sets and methods based on their performance and selecting the best method for a specific application. According to the analysis, the black-box model consisting of GPR and feature selection by LASSO shows the best performance with test <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.96. The best gray-box model consists of SVM-based method with physical insight feature set along with LASSO for feature selection with test <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>R</mi><mn>2</mn></msup></semantics></math></inline-formula> of 0.97.https://www.mdpi.com/1996-1073/14/23/7865diesel enginessoot emissionsmachine learninggray-box modelingdata-driven modeling |
| spellingShingle | Saeid Shahpouri Armin Norouzi Christopher Hayduk Reza Rezaei Mahdi Shahbakhti Charles Robert Koch Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines Energies diesel engines soot emissions machine learning gray-box modeling data-driven modeling |
| title | Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines |
| title_full | Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines |
| title_fullStr | Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines |
| title_full_unstemmed | Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines |
| title_short | Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines |
| title_sort | hybrid machine learning approaches and a systematic model selection process for predicting soot emissions in compression ignition engines |
| topic | diesel engines soot emissions machine learning gray-box modeling data-driven modeling |
| url | https://www.mdpi.com/1996-1073/14/23/7865 |
| work_keys_str_mv | AT saeidshahpouri hybridmachinelearningapproachesandasystematicmodelselectionprocessforpredictingsootemissionsincompressionignitionengines AT arminnorouzi hybridmachinelearningapproachesandasystematicmodelselectionprocessforpredictingsootemissionsincompressionignitionengines AT christopherhayduk hybridmachinelearningapproachesandasystematicmodelselectionprocessforpredictingsootemissionsincompressionignitionengines AT rezarezaei hybridmachinelearningapproachesandasystematicmodelselectionprocessforpredictingsootemissionsincompressionignitionengines AT mahdishahbakhti hybridmachinelearningapproachesandasystematicmodelselectionprocessforpredictingsootemissionsincompressionignitionengines AT charlesrobertkoch hybridmachinelearningapproachesandasystematicmodelselectionprocessforpredictingsootemissionsincompressionignitionengines |