Tdnn-Based Engine In-Cylinder Pressure Estimation from Shaft Velocity Spectral Representation

Abstract

Pressure is one of the essential variables to give information about engine condition and monitoring. Direct recording of this signal is complex and invasive, while angular velocity can be measured. Nonetheless, the challenge is to predict the cylinder pressure using the shaft kinematics accurately. In this paper, a time-delay neural network (TDNN), interpreted as a finite pulse response (FIR) filter, is proposed to estimate the in-cylinder pressure of a single-cylinder internal combustion engine (ICE) from fluctuations in shaft angular velocity. The experiments are conducted over data obtained from an ICE operating in 12 different states by changing the angular velocity and load. The TDNN’s delay is adjusted to get the highest possible correlation-based score. Our methodology can predict pressure with an R2 >0.9, avoiding complicated pre-processing steps.

Procesamiento de señales no intrusivas para el monitoreo de condición de emisiones y análisis energético en un motor de combustión interna diésel

“…Un adecuado diagnóstico del MCI, a partir de las señales intrínsecas, debe estar anclado al estudio del funcionamiento holístico del motor, debe relacionar las variables dinámicas y termodinámicas del mismo (Romero-Piedrahita y Quintero-Riaza, 2003;Zapata-Mina et al, 2020) y debe implementar técnicas para determinar la presión en la cámara de combustión a partir de señales no intrusivas (Grajales et al, 2016). En la Universidad Tecnológica de Pereira, especialmente en el programa de Ingeniería Mecánica, se han realizado estudios relacionados con el motor de combustión interna (Quintero et al, 2020;Mejía et al, 2021;Valencia-Duque et al, 2021;Torres Morimtsu et al, 2019;Grajales y Quintero Riaza, 2019).…”

“…Héctor Fabio Quintero Riaza -Carlos Alberto Romero Piedrahita -Edison Henao Castañeda Alvaro Hernan Restrepo Victoria -Juan Esteban Tibaquira Giraldo Quelbis Román Quintero Bertel -Carlos Alberto Graterón Santos Valencia-Duque et al, 2021;Torres Morimtsu et al, 2019;Grajales y Quintero Riaza, 2019).…”

Reduced Scale Laboratory for Training and Research in Condition-Based Maintenance Strategies for Combustion Engine Power Plants and a Novel Method for Monitoring of Inlet and Exhaust Valves

“…According to d'Ambrosio et al [11], the in-cylinder pressure has been the principal diagnostic tool for ICEs. It is important to notice that the recent literature presents methods for the estimation of the in-cylinder pressure, such as the works of Romani [12], who performed an indirect measurement of the in-cylinder pressure through the measurement of the force transferred through the cylinder head, using a strain washer; Wang et al [13], who estimated the in-cylinder pressure from a model based on extended Kalman filter using the crankshaft speed); and Valencia-Duque et al [14], who used a neural network to predict the pressure from crankshaft angular position fluctuations). However, in order to maintain compatibility with the commercial equipment and in order to have more accurate results, the proposed system uses direct measurement of the in-cylinder pressure.…”