Artificial neural network for predicting a turbocharged engine performance: an empirical study
Experiments to determine the performance and characteristics of an internal combustion engine related to turbocharger is costly, time intense andcomplex. Besides, it is very difficult to develop an accurate mathematic regression model for engine performance because it involves many independent and d...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2021
|
| Subjects: |
| _version_ | 1796867504286466048 |
|---|---|
| author | Chan, Christopher Yew Fai Yap, Alvin Chee Wei Thang, Ka Fei Soon, Chun Mein Tan, Feng Xian Chiong, Meng Soon Rajoo, Srithar |
| author_facet | Chan, Christopher Yew Fai Yap, Alvin Chee Wei Thang, Ka Fei Soon, Chun Mein Tan, Feng Xian Chiong, Meng Soon Rajoo, Srithar |
| author_sort | Chan, Christopher Yew Fai |
| collection | ePrints |
| description | Experiments to determine the performance and characteristics of an internal combustion engine related to turbocharger is costly, time intense andcomplex. Besides, it is very difficult to develop an accurate mathematic regression model for engine performance because it involves many independent and dependent variables. Using artificial neural network (ANN), a machine learning model are used to predict the vehicle's engine performance parameters. ANN model aims to minimize the cost and time required for an engine tuning experiment. However, the experimental data from engine tuning experiment is usually small because of its high cost and time intensive. Therefore, this work intent to reduce the optimization process for an ANN model with a small dataset. Optimization of an ANN is critical to prevent the model trapped within a local optimum solution. Systematic methods utilizing modified grid search and random search are suggested in tuning the model's hyperparameters. Moreover, the importance of each optimization steps is ranked based on the analysis of the tuning result. The most optimizedmodel has achieved an overall mean absolute error (MAE) of 4.92% for 7 output parameters. Finally, future works are suggested that can be applied such as building a model for each of the output parameter. |
| first_indexed | 2024-03-05T21:28:15Z |
| format | Conference or Workshop Item |
| id | utm.eprints-103661 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T21:28:15Z |
| publishDate | 2021 |
| record_format | dspace |
| spelling | utm.eprints-1036612023-11-20T03:34:55Z http://eprints.utm.my/103661/ Artificial neural network for predicting a turbocharged engine performance: an empirical study Chan, Christopher Yew Fai Yap, Alvin Chee Wei Thang, Ka Fei Soon, Chun Mein Tan, Feng Xian Chiong, Meng Soon Rajoo, Srithar TK Electrical engineering. Electronics Nuclear engineering Experiments to determine the performance and characteristics of an internal combustion engine related to turbocharger is costly, time intense andcomplex. Besides, it is very difficult to develop an accurate mathematic regression model for engine performance because it involves many independent and dependent variables. Using artificial neural network (ANN), a machine learning model are used to predict the vehicle's engine performance parameters. ANN model aims to minimize the cost and time required for an engine tuning experiment. However, the experimental data from engine tuning experiment is usually small because of its high cost and time intensive. Therefore, this work intent to reduce the optimization process for an ANN model with a small dataset. Optimization of an ANN is critical to prevent the model trapped within a local optimum solution. Systematic methods utilizing modified grid search and random search are suggested in tuning the model's hyperparameters. Moreover, the importance of each optimization steps is ranked based on the analysis of the tuning result. The most optimizedmodel has achieved an overall mean absolute error (MAE) of 4.92% for 7 output parameters. Finally, future works are suggested that can be applied such as building a model for each of the output parameter. 2021 Conference or Workshop Item PeerReviewed Chan, Christopher Yew Fai and Yap, Alvin Chee Wei and Thang, Ka Fei and Soon, Chun Mein and Tan, Feng Xian and Chiong, Meng Soon and Rajoo, Srithar (2021) Artificial neural network for predicting a turbocharged engine performance: an empirical study. In: International Conference on Edge Computing and Applications, ICECAA 2022, 13 October 2022 - 15 October 2022, Tamilnadu, India. http://dx.doi.org/10.1109/ICECAA55415.2022.9936387 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Chan, Christopher Yew Fai Yap, Alvin Chee Wei Thang, Ka Fei Soon, Chun Mein Tan, Feng Xian Chiong, Meng Soon Rajoo, Srithar Artificial neural network for predicting a turbocharged engine performance: an empirical study |
| title | Artificial neural network for predicting a turbocharged engine performance: an empirical study |
| title_full | Artificial neural network for predicting a turbocharged engine performance: an empirical study |
| title_fullStr | Artificial neural network for predicting a turbocharged engine performance: an empirical study |
| title_full_unstemmed | Artificial neural network for predicting a turbocharged engine performance: an empirical study |
| title_short | Artificial neural network for predicting a turbocharged engine performance: an empirical study |
| title_sort | artificial neural network for predicting a turbocharged engine performance an empirical study |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| work_keys_str_mv | AT chanchristopheryewfai artificialneuralnetworkforpredictingaturbochargedengineperformanceanempiricalstudy AT yapalvincheewei artificialneuralnetworkforpredictingaturbochargedengineperformanceanempiricalstudy AT thangkafei artificialneuralnetworkforpredictingaturbochargedengineperformanceanempiricalstudy AT soonchunmein artificialneuralnetworkforpredictingaturbochargedengineperformanceanempiricalstudy AT tanfengxian artificialneuralnetworkforpredictingaturbochargedengineperformanceanempiricalstudy AT chiongmengsoon artificialneuralnetworkforpredictingaturbochargedengineperformanceanempiricalstudy AT rajoosrithar artificialneuralnetworkforpredictingaturbochargedengineperformanceanempiricalstudy |