Scholarlink

<p>In the modern manufacturing technologies, the Computer Numerical Control (CNC) mill industry has gained increased attention in numerous applications like aerospace, automotive, electronics and medical devices. Therefore, early defect detection in the CNC mill industry is vital for ensuring product quality and maintain brand reputation. Also, robotics automation is the promising factor in defect detection in the CNC mill industry. However, none of the traditional approaches focused on machine performance factor and environmental condition factor. Hence, this paper proposes an innovative model called robotics industry-assisted HS-Fuzzy and LD-TS-LSTM-based timely defect identification in CNC Mill industry. Initially, the machine performance data is gathered and pre-processed. Next, the ESM-SOA algorithm performs the map-reduce process, followed by pattern analysis using CH-DBSCAN. Likewise, the environmental sensor data is acquired, followed by time series alignment. Then, the features are extracted and then the trend is analysed. Afterward, the defect identification is done using HS-Fuzzy. Finally, the robot task is predicted via LD-TS-LSTM. The experimental results showed that the proposed work achieved performance with 98.96% accuracy.</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

Robotics industry automation-assisted an effective Hs-fuzzy and LD-TS-LSTM-based timely defect identification in CNC mill industry

  • 期刊论文

  • 发表日期：

    2026年1月13日

查看全文
  • Raj Kumar Gudivaka,
  • Sri Harsha Grandhi,
  • Basava Ramanjaneyulu Gudivaka,
  • Dinesh Kumar Reddy Basani,
  • Rajya Lakshmi Gudivaka,
  • Pugalenthi Ramamurthy

摘要

In the modern manufacturing technologies, the Computer Numerical Control (CNC) mill industry has gained increased attention in numerous applications like aerospace, automotive, electronics and medical devices. Therefore, early defect detection in the CNC mill industry is vital for ensuring product quality and maintain brand reputation. Also, robotics automation is the promising factor in defect detection in the CNC mill industry. However, none of the traditional approaches focused on machine performance factor and environmental condition factor. Hence, this paper proposes an innovative model called robotics industry-assisted HS-Fuzzy and LD-TS-LSTM-based timely defect identification in CNC Mill industry. Initially, the machine performance data is gathered and pre-processed. Next, the ESM-SOA algorithm performs the map-reduce process, followed by pattern analysis using CH-DBSCAN. Likewise, the environmental sensor data is acquired, followed by time series alignment. Then, the features are extracted and then the trend is analysed. Afterward, the defect identification is done using HS-Fuzzy. Finally, the robot task is predicted via LD-TS-LSTM. The experimental results showed that the proposed work achieved performance with 98.96% accuracy.