当前位置: X-MOL 学术Eng. Res. Express › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Sensor based real-time information for monitoring and control of a manufacturing process
Engineering Research Express Pub Date : 2021-06-10 , DOI: 10.1088/2631-8695/ac0777
Debasish Mishra 1 , Abhinav Gupta 2 , Pranav Raj 2 , Aman Kumar 2 , Saad Anwer 2 , Surjya K Pal 3 , Debashish Chakravarty 4 , Srikanta Pal 2
Affiliation  

This paper demonstrates a real-time process monitoring and control framework for the implementation of Industry 4.0 in manufacturing. For a case study, friction stir welding (FSW) has been selected owing to its extensive usage of welding in various manufacturing sectors. Force data has been collected online during the welding and sent to a cloud server enabling telewelding. It is processed through several signal processing and machine learning (ML) techniques for assessment of the weld quality. A control system thereafter controls the weld quality for avoiding the occurrence of weld-defect in real-time. Two ML models have been built, one for assessment of the weld quality, and the other for forecasting the controlled parameters for avoiding defect occurrence. For manufacturing sectors involved in mass production, this technique will be useful to keep a track of the process in real-time and avoid rejection of material in case of occurrence of an anomaly in the process. It is always beneficial for the manufacturing industry to track the quality of a product in real-time, and control the rejection rate, both of which have been successfully shown in this paper.



中文翻译:

基于传感器的实时信息,用于监测和控制制造过程

本文展示了在制造业中实施工业 4.0 的实时过程监控框架。作为案例研究,选择搅拌摩擦焊 (FSW) 是因为其在各个制造部门中广泛使用焊接。在焊接过程中在线收集力数据并将其发送到云服务器以实现远程焊接。它通过多种信号处理和机器学习 (ML) 技术进行处理,以评估焊接质量。此后,控制系统实时控制焊接质量以避免焊接缺陷的发生。已经建立了两个 ML 模型,一个用于评估焊接质量,另一个用于预测控制参数以避免缺陷发生。对于涉及大规模生产的制造业,这种技术将有助于实时跟踪过程并避免在过程中发生异常时拒绝材料。实时跟踪产品质量和控制废品率对制造业来说总是有益的,这两者在本文中都得到了成功的展示。

更新日期:2021-06-10
down
wechat
bug