期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 19, 期 4, 页码 5711-5721出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2022.3199259
关键词
Engines; Feature extraction; Soft sensors; Correlation; Artificial neural networks; Finite impulse response filters; Principal component analysis; Accelerated particle swarm optimization (PSO); deep neural network; engine soft sensors; feature selection
Accurately predicting soft sensors is crucial for the development of modern combustion engines to achieve better performance, lower emissions, and reduced fuel consumption. In this article, a novel data-driven approach called statistics-guided accelerated swarm feature selection is proposed to find the most effective features for engine soft sensors.
The accurate prediction of soft sensors is essential for the development of modern combustion engines to achieve better performance, lower emissions, and reduced fuel consumption. To precisely predict engine performance, i.e., indicated thermal efficiency, volumetric efficiency, and fuel consumption rate of a hybrid engine, in this article, we propose a novel data-driven approach of statistics-guided accelerated swarm feature selection to find the most effective features for engine soft sensors. Differing from the existing filter or wrapper feature selection approaches, this approach uses external measure information to direct velocity updates in the accelerated swarm feature selection. Several filter and wrapper methods are developed and comprehensively compared. The experimental dataset is collected from a BYD 1.5 L gasoline engine. Validated by bench test, the results demonstrate that the proposed approach finds the most effective features and optimal network structure for data-driven performance prediction of the hybrid engine that was studied.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据