• Juan Carlos Peña
  • Grover Zurita Universidad Privada Boliviana

Palabras clave:

Neural Networks, Radial Basis, Generalized Regression Network, Cylinder Pressure


The cylinder pressure curve is a very important parameter for detection of malfunctioning of combustion process in diesel engines. It provides a considerable amount of information about the performance of the engine. The traditional method to get the cylinder pressure curve is to use a cylinder pressure transducer, which is inserted in the cylinder head of the engine. This method is both expensive because of the high cost of the transducer and lifetime limited due to the harsh working environment. Therefore, there is an increasing need of a new non-intrusive method, which can be applied for the reconstruction of the cylinder pressure.The main objective of this paper is to perform the reconstruction of the cylinder pressure curve from vibration measurements by using the Neural Network Method (NNM). The cylinder pressure data obtained with transducers on operating engines was simultaneously recorded with vibration data obtained with external accelerometers at Scania Acoustic Laboratory in Stockholm (Sweden). The measured data were used to train the Neural Networks (NN), thereafter a new data set of vibration signals was enter to the NNs to get the reconstructed cylinder pressure signal. Finally, the results showed high accuracy and precision. The standard deviation of the average maximum cylinder pressures (PMax) varied between 0.03 and 1.01 percent, much lower than those obtained with other methods i.e. Cepstrum Method and Multivariate Data Analysis (MVDA). The final goal to use the NNM for optimization of the combustion process and engine diagnostics was fulfilled.


Los datos de descargas todavía no están disponibles.


J. Yan et al. Diesel Combustion and Transient Emissions Optimization Using Taguchi Methods, SAE 930600, 1993.

V. G. Zurita and A. Ågren. “A new approach of the combustion process in diesel engines using vibration measurements. Part 1: Reconstruction of Cylinder Pressure from Vibration Measurements,” International Journal of Acoustics and Vibration, vol. 8, no. 4, 2003.

Dong-Soo Lim Bo-Suk Yang and Jing-Long An. “Vibration diagnostic system of rotating machinery using artificial neural network and wavelet transform.” Proceedings of COMADEM 2000, pp. 923–932. The MFPT Society, 6262 S. Kingery Highway Willowbrook, Illinois 60514, 2000.

Mo-Yuen Chow. Methodologies of using neural network and fuzzy logic technologies for motor incipient fault detection, WorldScientific Publishing Co., Farrer Road, Singapore 912805, 1997.

J. Peña. Reconstruccíon de la curva de combustión de un motor diesel basada en la vibración empleando el método de redes neuronales, TFG, No UPB-LIC-002/2004, UPB-Cochabamba.

Manual Matlab. Neural Network Toolbox, version 6.5

S. Haykin. NEURAL NETWORKS A Comprehensive Foundation, Prentice Hall, Upper Saddle River, New Jersey 07458, 2nd edition, 1999, pp. 66–74.

G. Zurita and D. Haupt. “Reconstruction of the cylinder pressure through multivariate data analysis: For prediction of noise and exhaust emissions,” Noise Control Engineering Journal, vol. 52, no. 4, 2004.

T. M. Cover. “Geometrical and statistical properties of systems of linear inequalities with applications in patern recognition,” IEEE Transactions on Electronic Computers, vol. EC-14, pp. 326-334.

P. Niyogi and F. Girosi. “On the relationship between generation error, hypotesis complexity , and sample complexity for radial basis function,” Neural Computation Journal, vol. 8, pp. 819-842.

A. Oppenheim et al. Signals and System, Prentice-Hall International, Upper Saddle River, N.J., 2nd edition, 1997.



Cómo citar

Peña, J. C., & Zurita, G. (2006). VIBRATION BASED RECONSTRUCTION OF THE CYLINDER PRESSURE IN DIESEL ENGINES BY USING NEURAL NETWORKS. Revista Investigación &Amp; Desarrollo, 1(5). Recuperado a partir de