基于激光散斑成像的零件表面粗糙度建模

发布时间：2018-10-20 18:37

【摘要】：表面粗糙度是衡量机械表面加工水平的重要参数.通过构建一套激光散斑成像采集系统,获取了不同表面加工类型和不同粗糙度值的零件表面激光散斑图像.应用Tamura纹理特征理论提取图像的纹理粗糙度、对比度、方向度特征,并分析了这三个特征与表面粗糙度的关系.发现了纹理粗糙度特征与表面粗糙度的单调关系,推导出平磨、外磨、研磨三种表面加工工艺的粗糙度值与图像纹理粗糙度特征的数学函数关系,实现了表面粗糙度的测量.同时,利用Tamura纹理特征与加工工艺的依赖关系,建立了基于贝叶斯网络的工艺识别推理模型,推理出了零件表面加工工艺.通过为多种加工类型表面建立粗糙度测量模型,为粗糙度测量提供了新思路.实验证明所提的粗糙度测量模型能以较高的准确率识别出零件表面加工类型并测量出其表面粗糙度值.
[Abstract]:Surface roughness is an important parameter to measure the machining level of mechanical surface. By constructing a laser speckle imaging acquisition system, laser speckle images of parts with different surface processing types and different roughness values were obtained. Tamura texture feature theory is applied to extract the texture roughness, contrast and orientation features of the image, and the relationship between the three features and the surface roughness is analyzed. The monotonic relationship between texture roughness and surface roughness is found, and the mathematical function relationship between roughness value and texture roughness feature of image is deduced, and the measurement of surface roughness is realized. At the same time, the reasoning model of process recognition based on Bayesian network is established by using the dependence between Tamura texture features and machining process, and the machining process of parts surface is inferred. A new method for roughness measurement is provided by establishing a roughness measurement model for various machined surfaces. The experimental results show that the proposed roughness measurement model can identify the machining types of parts and measure their surface roughness values with high accuracy.
【作者单位】：南京信息工程大学江苏省气象探测与信息处理重点实验室;中国人民解放军94654部队;
【基金】：国家自然科学基金(批准号:61302188) 中国博士后特别资助基金(批准号:2012 T50510) 中国博士后科学基金(批准号:2011M500940) 江苏省高校重大自然科学基金(批准号:12KJA510001) 江苏高校优势学科建设工程项目资助的课题~~
【分类号】：TG84

【相似文献】