Enhancement of Heavy-Duty Engines Performance and Reliability Using Cylinder Pressure Information

Brusa, Alessandro; Corti, Enrico; Rossi, Alessandro; Moro, Davide

doi:10.3390/en16031193

Cited by 1 publication

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Higher derivatives are important to theoretical research and engineering application [1][2][3][4][5][6] for deepening the understanding of physical processes and improving analysis efficiency [7,8]. However, it is difficult to obtain higher derivatives directly from a real signal because of measurement errors [9]. Though varied techniques such as the Savitzky-Golay polynomial [10,11], Fourier transform [12,13] and wavelet transform [14,15] have been developed to obtain higher derivatives of measured signals, the higher derivatives obtained with the above techniques often deviate from the real one in trends.…”

Section: Introductionmentioning

confidence: 99%

“…Though varied techniques such as the Savitzky-Golay polynomial [10,11], Fourier transform [12,13] and wavelet transform [14,15] have been developed to obtain higher derivatives of measured signals, the higher derivatives obtained with the above techniques often deviate from the real one in trends. It is a challenge and urgent demand [9] to develop a data fitting method without higher derivatives violating real trends.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Neural Network with the Ability to Express the Extreme Points Distribution Features of Higher Derivatives of Physical Processes

Wang

Gao

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Higher derivatives are important to interpret the physical process. However, higher derivatives calculated from measured data often deviate from the real ones because of measurement errors. A novel method for data fitting without higher derivatives violating the real physical process is developed in this paper. Firstly, the research on errors’ influence on higher derivatives and the typical functions’ extreme points distribution were conducted, which demonstrates the necessity and feasibility of adopting extreme points distribution features in neural networks. Then, we proposed a new neural network considering the extreme points distribution features, namely, the extreme-points-distribution-based neural network (EDNN), which contains a sample error calculator (SEC) and extreme points distribution error calculator (EDEC). With recursive automatic differentiation, a model calculating the higher derivatives of the EDNN was established. Additionally, a loss function, embedded with the extreme points distribution features, was introduced. Finally, the EDNN was applied to two specific cases to reduce the noise in a second-order damped free oscillation signal and an internal combustion engine cylinder pressure trace signal. It was found that the EDNN could obtain higher derivatives that are more compatible with physical trends without detailed differentiation equations. The standard deviation of derivatives’ error of the EDNN is less than 62.5 percent of that of traditional neural networks. The EDNN provides a novel method for the analysis of physical processes with higher derivatives compatible with real physical trends.

show abstract