Scholarlink

Purpose <p>A cutting tool plays a crucial role in the material removal process, and effective tool condition monitoring has gained significant attention in the industry. In-process development of any kind of tool fault leads to a reduction in machining accuracy, degradation of surface-finish, and causes interruptions, to name a few. Such faults are untraceable using the conventional condition monitoring approach and need to be addressed smartly.</p> Methods <p>In an attempt to characterize such unknown moments, a machine learning based framework is proposed herein. In order to generate data sets, change in spindle acceleration was acquired for various configurations focusing on failure modes of a tipped tool, during the face milling process. The current investigation focuses on monitoring of defects such as wearing of flank face &amp; nose radius, crater &amp; notch wear, and fracturing of cutting edge. In the beginning, the distinction between the damaged and damaged-free classes was estimated in terms of descriptive statistics and the training dataset was established using 16 features. The logic of the decision tree (DT) has assisted the selection of significant features</p> Results and Conclusion <p>The SMO algorithm (Sequential Minimal Optimization) is then deployed for training the data through kernels of the SVM (Support vector machine) and the classification model is constructed. Further, robustness analysis is presented to examine the performance of the SMO-SVM model. Finally, tipped tool fault classification for test &amp; blind datasets was carried out considering the proposed framework. The SMO-SVM classifier by considering the ‘polynomial’ &amp; ‘Pearson VII’ kernel functions have exhibited 92.33% classification accuracy thereby confirming the apt training of the model.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Diagnosing Anomalous Events Leading To Cutting Tool Faults Through Vibration Signals Trained on SMO-SVM

  • 期刊论文

  • 发表日期：

    2025年3月26日

查看全文
  • Revati M. Wahul,
  • Vaishali H. Kamble,
  • Dinesh Salunke

摘要

Purpose

A cutting tool plays a crucial role in the material removal process, and effective tool condition monitoring has gained significant attention in the industry. In-process development of any kind of tool fault leads to a reduction in machining accuracy, degradation of surface-finish, and causes interruptions, to name a few. Such faults are untraceable using the conventional condition monitoring approach and need to be addressed smartly.

Methods

In an attempt to characterize such unknown moments, a machine learning based framework is proposed herein. In order to generate data sets, change in spindle acceleration was acquired for various configurations focusing on failure modes of a tipped tool, during the face milling process. The current investigation focuses on monitoring of defects such as wearing of flank face & nose radius, crater & notch wear, and fracturing of cutting edge. In the beginning, the distinction between the damaged and damaged-free classes was estimated in terms of descriptive statistics and the training dataset was established using 16 features. The logic of the decision tree (DT) has assisted the selection of significant features

Results and Conclusion

The SMO algorithm (Sequential Minimal Optimization) is then deployed for training the data through kernels of the SVM (Support vector machine) and the classification model is constructed. Further, robustness analysis is presented to examine the performance of the SMO-SVM model. Finally, tipped tool fault classification for test & blind datasets was carried out considering the proposed framework. The SMO-SVM classifier by considering the ‘polynomial’ & ‘Pearson VII’ kernel functions have exhibited 92.33% classification accuracy thereby confirming the apt training of the model.