基于表面二维PCA重构图像的刀具磨损分形特征研究

Fractal Analysis of PCA Reconstruction for Tool Wear Monitoring

根据加工表面纹理图像与刀具几何形状之间的内在联系,提出利用计算机视觉技术进行刀具磨损状态监测,设计了基于表面微观纹理图像的刀具磨损状态监测实验系统。提出从二维PCA重构图像中提取分形特征值来判断刀具的磨损状态,给出了二维PCA图像重构算法。理论分析和实验证明:PCA重构图像消除了原始图像信息中的冗余和噪声,从重构图像中提取出来的分形布朗运动维数与刀具磨损有着很强的相关性,可以间接判断刀具磨损情况,从而达到对刀具状态进行监测的目的。

In order to take advantage of computer vision technology for cutting tool condition monitoring, the experimental system for state monitoring of a cutting tool is designed, and the image processing technology is introduced into the condition monitoring of cutting tool wear. A new method for judging the cutting tool state is proposed by extracting the fractal character. Both theoretical analysis and experimental results prove that the algorithm can extract the principal components, reconstruct the images, and eliminate the redundancy and noise. The fractal Brownian motion dimension which is extracted from the reconstructed images has a strong correlation with tool wear, and the cutting tool wear can be estimated indirectly. Therefore, the objective of monitoring the cutting tool condition is achieved. By this algorithm, the fractal dimension of Brownian motion can be used to express the trend of the tool wear effectively.