基于非刚性特征的发动机积碳程度判别模型  

The Discriminative Model of Carbon Deposit Degree of Engine Based on Non⁃Rigid Features

作　　者：黄倩 王召巴[1] 陈香 张航佳 陈友兴[1] HUANG Qian;WANG Zhaoba;CHEN Xiang;ZHANG Hangjia;CHEN Youxing(College of Information and Communication Engineering,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学信息与通信工程学院,山西太原030051

出　　处：《测试技术学报》2024年第4期441-447,共7页Journal of Test and Measurement Technology

基　　金：山西省回国留学人员科研资助项目(2022-145);中北大学研究生科技立项资助课题(2022180506)。

摘　　要：汽车发动机积碳的长期累积会引起发动机动力下降、油耗上升、排放性能降低等问题,对发动机及时的检测和清理可以有效缓解积碳造成的影响。本文提出了一种新的基于非刚性特征的模型,用于积碳程度的判别。首先,在模型中使用可变形卷积调整卷积核的偏移位置和偏移幅度,提高网络的有效感受野,提取非刚性特征信息;其次,根据核区域中像素的相关性,使用自适应指数度量池化核对神经元进行加权,以此捕获更好的细节特征信息;最后,添加基于自注意机制的特征增强模块,获取特征图的上下文信息。经过实验测试,本文方法的测试准确率为87.1%,各项指标相较原始模型平均提高2.5%,证明本文方法可以提取有效的积碳程度判别特征。Long-term accumulation of carbon deposit in car engines can result in decreased engine power,increased fuel consumption,and diminished emission performance,highlighting the critical importance of timely engine detection and cleaning for effectively mitigating the impact of carbon deposit.A novel model based on non-rigid features has been proposed to discriminate the degree of carbon deposit.Firstly,deformable convolution is employed in the model to adjust the offset position and amplitude of the convolu⁃tion kernel,enhancing the effective receptive field of the network and extracting non-rigid feature informa⁃tion.Subsequently,neurons are weighted based on the correlation of pixels within the kernel region using an adaptive exponential metric pooling kernel to capture more precise feature information.Finally,a fea⁃ture improvement module based on a self-attention mechanism is incorporated to extract comprehensive contextual information from feature maps.The model’s test accuracy after experimental testing is 87.1%,and the indexes have increased by 2.5%on average compared to the original model.Demonstrat⁃ing the capability of our proposed method to extract effective features for carbon deposit degree discrimina⁃tion. The approach has the potential to theoretically justify the widespread promotion of the degree modeldiscrimination for carbon deposit.

关 键 词：积碳程度识别 非刚性特征 可变形卷积 下采样 自注意机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]