基于卷积神经网络的发动机主轴承盖姿态识别算法

Posture Recognition Algorithm of Engine Main Bearing Cover Based on Convolutional Neural Network

针对传统姿态识别算法识别精度不高,通用性不强,易受环境因素的影响,且需要对检测图像进行复杂的图像预处理操作的问题。基于卷积神经网络的特征提取能力和识别分类能力,提出一种基于卷积神经网络的发动机主轴承盖姿态识别算法,所提算法去除了传统复杂的预处理操作,通过提取轴承盖4个面的特征,对轴承盖4个面进行识别。实验结果表明:所提算法不仅可以正确识别发动机主轴承盖的4个面,而且平均识别精度为100%,平均识别时间为3.80 s,具有识别精度高,识别时间短,抗干扰能力强的特点。

Aiming at the problems of low recognition accuracy and low versatility of traditional gesture recognition algorithms,is easily affected by environmental factors,and complex image preprocessing operations are required for the detected images.Based on the feature extraction capabilities and recognition and classification capabilities of the convolutional neural network,a convolutional neural network-based recognition algorithm for the engine main bearing cover surface was proposed.The proposed algorithm removed the traditional complex preprocessing operations and extracts four surfaces of the bearing cover.To identify the four faces of the bearing cap.Experimental results show that the proposed algorithm can correctly identify the four faces of the main bearing cover of the engine,with an average recognition accuracy of 100%and an average recognition time of 3.80 s.It has the characteristics of high recognition accuracy,short recognition time,and strong anti-interference ability.