Manifold absolute pressure estimation using neural network with hybrid training algorithm
In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP) sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measure...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science
2017
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/74847/1/MohdTaufiqMuslim2017_ManifoldAbsolutePressureEstimationusingNeuralNetwork.pdf |
| _version_ | 1796862267704213504 |
|---|---|
| author | Muslim, M. T. Selamat, H. Alimin, A. J. Haniff, M. F. |
| author_facet | Muslim, M. T. Selamat, H. Alimin, A. J. Haniff, M. F. |
| author_sort | Muslim, M. T. |
| collection | ePrints |
| description | In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP) sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM) algorithm, Bayesian Regularization (BR) algorithm and Particle Swarm Optimization (PSO) algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS). The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value. |
| first_indexed | 2024-03-05T20:09:01Z |
| format | Article |
| id | utm.eprints-74847 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T20:09:01Z |
| publishDate | 2017 |
| publisher | Public Library of Science |
| record_format | dspace |
| spelling | utm.eprints-748472018-03-21T00:22:29Z http://eprints.utm.my/74847/ Manifold absolute pressure estimation using neural network with hybrid training algorithm Muslim, M. T. Selamat, H. Alimin, A. J. Haniff, M. F. T Technology (General) In a modern small gasoline engine fuel injection system, the load of the engine is estimated based on the measurement of the manifold absolute pressure (MAP) sensor, which took place in the intake manifold. This paper present a more economical approach on estimating the MAP by using only the measurements of the throttle position and engine speed, resulting in lower implementation cost. The estimation was done via two-stage multilayer feed-forward neural network by combining Levenberg-Marquardt (LM) algorithm, Bayesian Regularization (BR) algorithm and Particle Swarm Optimization (PSO) algorithm. Based on the results found in 20 runs, the second variant of the hybrid algorithm yields a better network performance than the first variant of hybrid algorithm, LM, LM with BR and PSO by estimating the MAP closely to the simulated MAP values. By using a valid experimental training data, the estimator network that trained with the second variant of the hybrid algorithm showed the best performance among other algorithms when used in an actual retrofit fuel injection system (RFIS). The performance of the estimator was also validated in steady-state and transient condition by showing a closer MAP estimation to the actual value. Public Library of Science 2017 Article PeerReviewed application/pdf en http://eprints.utm.my/74847/1/MohdTaufiqMuslim2017_ManifoldAbsolutePressureEstimationusingNeuralNetwork.pdf Muslim, M. T. and Selamat, H. and Alimin, A. J. and Haniff, M. F. (2017) Manifold absolute pressure estimation using neural network with hybrid training algorithm. PLoS ONE, 12 (11). ISSN 1932-6203 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85036465986&doi=10.1371%2fjournal.pone.0188553&partnerID=40&md5=414bb385cd6854a8adf228c930de366c DOI:10.1371/journal.pone.0188553 |
| spellingShingle | T Technology (General) Muslim, M. T. Selamat, H. Alimin, A. J. Haniff, M. F. Manifold absolute pressure estimation using neural network with hybrid training algorithm |
| title | Manifold absolute pressure estimation using neural network with hybrid training algorithm |
| title_full | Manifold absolute pressure estimation using neural network with hybrid training algorithm |
| title_fullStr | Manifold absolute pressure estimation using neural network with hybrid training algorithm |
| title_full_unstemmed | Manifold absolute pressure estimation using neural network with hybrid training algorithm |
| title_short | Manifold absolute pressure estimation using neural network with hybrid training algorithm |
| title_sort | manifold absolute pressure estimation using neural network with hybrid training algorithm |
| topic | T Technology (General) |
| url | http://eprints.utm.my/74847/1/MohdTaufiqMuslim2017_ManifoldAbsolutePressureEstimationusingNeuralNetwork.pdf |
| work_keys_str_mv | AT muslimmt manifoldabsolutepressureestimationusingneuralnetworkwithhybridtrainingalgorithm AT selamath manifoldabsolutepressureestimationusingneuralnetworkwithhybridtrainingalgorithm AT aliminaj manifoldabsolutepressureestimationusingneuralnetworkwithhybridtrainingalgorithm AT haniffmf manifoldabsolutepressureestimationusingneuralnetworkwithhybridtrainingalgorithm |