Abstract:

To solve the wear recognition problem of machine tool guide surfaces, a new machine tool guide surface recognition method was presented herein based on the radar-graph barycentre feature. Firstly, the gray mean value, skewness, kurtosis, flat degrees and projection variance features of the guide surface image data were defined as primary characteristics. Secondly, data visualization technology based on radar graph was used. The visual barycentre graphical feature was demonstrated based on the radar plot of multi-dimensional data. Thirdly, a classifier based on the support vector machine technology was used, the radar-graph barycentre feature and wear original feature were put into the classifier separately for classification and comparative analysis of classification and experimental results. The calculation and experimental outcomes show that the method based on the radar-graph barycentre feature can detect the guide surface effectively. 

Key words: guide surface, wear defect, feature extraction, data visualization, graphical representation

摘要：

为解决精密机床导轨面磨损缺陷及缺陷程度的识别问题，提出一种基于导轨面图像数据雷达图重心特征的表面磨损识别方法。首先提取导轨面图像数据的灰度均值、歪度、峭度、扁度和投影方差作为磨损状况识别的原始特征；然后采用雷达图技术将特征数据可视化，并提取雷达图的重心特征；最后采用支持向量机技术设计分类器，同时采用雷达图重心特征和磨损缺陷原始特征进行分类,并与实验检测的导轨面磨损数据进行对比分析。计算和实验结果表明: 基于雷达图的图像数据重心特征可有效地识别导轨面是否磨损,并能在一定程度上判别导轨面的磨损程度。

关键词: 导轨面, 磨损缺陷, 特征提取, 数据可视化, 图表示