<p>Cutting-tool wear in CNC machining degrades part quality, increases scrap, and risks unexpected downtime, making real-time tool wear monitoring (TWM) essential. However, existing AI-based TWM approaches suffer from limited generalization and poor robustness under varying conditions. They also rely on static feature-importance scores, unable to capture evolving sensor–wear dynamics. To address these limitations, this paper introduces a hybrid data-driven TWM framework called the <i>Domain-informed Stacked-Temporal LinearSVR model with Monotonicity enforcement and Physics-constrained Kalman smoothing</i> (D-STL-MPK). In this framework, tool-wear progression over machining cycles is partitioned into fixed-length temporal segments. A domain-informed Linear Support Vector Regression (LinearSVR) model is trained on each segment to predict the degree of tool wear. Predictions are concatenated, enforced to be non-decreasing, and smoothed via a physics-constrained Kalman filter for realistic wear-progression estimate. Unlike traditional methods, the proposed framework applies cross-validation within each temporal segment to automatically identify the most informative sensor features for wear prediction in that phase. This enhances interpretability by revealing how the relevance of sensor modalities (such as force, vibration, and acoustic signals) evolves across wear phases. Experimental validation on the publicly available (PHM2010 and HMoTP) datasets shows that D-STL-MPK achieves root-mean-square errors (RMSEs) of 1.41 <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\upmu\)</EquationSource> </InlineEquation>m and 4.75 <InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(\upmu\)</EquationSource> </InlineEquation>m, respectively. It delivers inference latency below 2 ms, requires under 650 FLOPs, and occupies less than 12 KB for model storage, demonstrating its suitability for real-time smart manufacturing applications. Thus, the proposed framework empowers manufacturers to shift from reactive maintenance to predictive tool management, enhancing operational efficiency, minimizing unplanned downtime, and ensuring consistent product quality</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

A reliable real-time tool wear monitoring framework based on temporal segmentation using domain-informed stacked AI models with physics-constrained predictions

  • Deep Patel,
  • Sreekumar Muthuswamy

摘要

Cutting-tool wear in CNC machining degrades part quality, increases scrap, and risks unexpected downtime, making real-time tool wear monitoring (TWM) essential. However, existing AI-based TWM approaches suffer from limited generalization and poor robustness under varying conditions. They also rely on static feature-importance scores, unable to capture evolving sensor–wear dynamics. To address these limitations, this paper introduces a hybrid data-driven TWM framework called the Domain-informed Stacked-Temporal LinearSVR model with Monotonicity enforcement and Physics-constrained Kalman smoothing (D-STL-MPK). In this framework, tool-wear progression over machining cycles is partitioned into fixed-length temporal segments. A domain-informed Linear Support Vector Regression (LinearSVR) model is trained on each segment to predict the degree of tool wear. Predictions are concatenated, enforced to be non-decreasing, and smoothed via a physics-constrained Kalman filter for realistic wear-progression estimate. Unlike traditional methods, the proposed framework applies cross-validation within each temporal segment to automatically identify the most informative sensor features for wear prediction in that phase. This enhances interpretability by revealing how the relevance of sensor modalities (such as force, vibration, and acoustic signals) evolves across wear phases. Experimental validation on the publicly available (PHM2010 and HMoTP) datasets shows that D-STL-MPK achieves root-mean-square errors (RMSEs) of 1.41 \(\upmu\) m and 4.75 \(\upmu\) m, respectively. It delivers inference latency below 2 ms, requires under 650 FLOPs, and occupies less than 12 KB for model storage, demonstrating its suitability for real-time smart manufacturing applications. Thus, the proposed framework empowers manufacturers to shift from reactive maintenance to predictive tool management, enhancing operational efficiency, minimizing unplanned downtime, and ensuring consistent product quality