Research on Discrimination Method of Carbon Deposit Degree of Automobile Engine Based on Deep Learning

Authors

  • Qian Huang School of Information and Communication Engineering, North University of China, Taiyuan, 030051, China
  • Youxing Chen School of Information and Communication Engineering, North University of China, Taiyuan, 030051, China
  • Zhaoba Wang School of Information and Communication Engineering, North University of China, Taiyuan, 030051, China
  • Xiang Chen School of Information and Communication Engineering, North University of China, Taiyuan, 030051, China
  • Asoke Nandi Brunel University London, Uxbridge, UB8 3PH, UK
  • Maozhen Li Brunel University London, Uxbridge, UB8 3PH, UK
  • Yong Jin School of Information and Communication Engineering, North University of China, Taiyuan, 030051, China

DOI:

https://doi.org/10.31577/cai_2024_1_126

Keywords:

Determination of carbon deposit degree, small datasets, fine-grained images, feature enhancement, deep learning

Abstract

The detection of carbon deposit degree is of great significance to the maintenance of automobile engine. Due to issues with poor feature aggregation, inter-class similarity, and intra-class variance in carbon deposit data with a small number of samples, model-based discriminative approaches cannot be widely implemented in the market. In order to overcome this technical barrier, the article examines the impact of DCNNs (Deep Convolutional Neural Networks) level on the recognition effect of the degree of carbon deposit, introduces a dropout structure and data enhancement strategy to lower the risk of overfitting brought on by the small dataset, and suggests a recognition method based on the kernel of dual-dimensional multiscale-multifrequency information features to enhance the differentiation characteristic. After experimental testing, the accuracy of this method is 86.9 %, the F1-score is 87.2 %, and the inference speed is 190 FPS, which can meet the practical requirements and provide basic support for the large-scale promotion of the model discrimination.

Downloads

Download data is not yet available.

Downloads

Published

2024-04-29

How to Cite

Huang, Q., Chen, Y., Wang, Z., Chen, X., Nandi, A., Li, M., & Jin, Y. (2024). Research on Discrimination Method of Carbon Deposit Degree of Automobile Engine Based on Deep Learning. Computing and Informatics, 43(1), 126–148. https://doi.org/10.31577/cai_2024_1_126

Issue

Vol. 43 No. 1 (2024): Computing and Informatics

Section

Articles

Most read articles by the same author(s)