Skip to main content
placeholder image

Reconstructing cylinder pressure from vibration signals based on radial basis function networks

Journal Article


Abstract


  • This paper presents an approach to reconstruct internal combustion engine cylinder pressure from the engine cylinder head vibration signals, using radial basis function (RBF) networks. The relationship between the cylinder pressure and the engine cylinder head vibration signals is analysed first. Then, an RBF network is applied to establish the non-parametric mapping model between the cylinder pressure time series and the engine cylinder head vibration signal frequency series. The structure of the RBF network model is presented. The fuzzy c-means clustering method and the gradient descent algorithm are used for selecting the centres and training the output layer weights of the RBF network respectively. Finally, the validation of this approach to cylinder pressure reconstruction from vibration signals is demonstrated on a two-cylinder, four-stroke direct injection diesel engine, with data from a wide range of speed and load settings. The prediction capabilities of the trained RBF network model are validated against measured data.

Publication Date


  • 2001

Citation


  • Du, H., Zhang, L., & Shi, X. (2001). Reconstructing cylinder pressure from vibration signals based on radial basis function networks. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 215(6), 761-767. doi:10.1243/0954407011528338

Scopus Eid


  • 2-s2.0-0035735888

Start Page


  • 761

End Page


  • 767

Volume


  • 215

Issue


  • 6

Abstract


  • This paper presents an approach to reconstruct internal combustion engine cylinder pressure from the engine cylinder head vibration signals, using radial basis function (RBF) networks. The relationship between the cylinder pressure and the engine cylinder head vibration signals is analysed first. Then, an RBF network is applied to establish the non-parametric mapping model between the cylinder pressure time series and the engine cylinder head vibration signal frequency series. The structure of the RBF network model is presented. The fuzzy c-means clustering method and the gradient descent algorithm are used for selecting the centres and training the output layer weights of the RBF network respectively. Finally, the validation of this approach to cylinder pressure reconstruction from vibration signals is demonstrated on a two-cylinder, four-stroke direct injection diesel engine, with data from a wide range of speed and load settings. The prediction capabilities of the trained RBF network model are validated against measured data.

Publication Date


  • 2001

Citation


  • Du, H., Zhang, L., & Shi, X. (2001). Reconstructing cylinder pressure from vibration signals based on radial basis function networks. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 215(6), 761-767. doi:10.1243/0954407011528338

Scopus Eid


  • 2-s2.0-0035735888

Start Page


  • 761

End Page


  • 767

Volume


  • 215

Issue


  • 6