To overcome the large time-delay in measuring the hardness of mixed rubber, rheological parameters were used to predict the hardness. A novel Q-based model updating strategy was proposed as a universal platform to tra...To overcome the large time-delay in measuring the hardness of mixed rubber, rheological parameters were used to predict the hardness. A novel Q-based model updating strategy was proposed as a universal platform to track time-varying properties. Using a few selected support samples to update the model, the strategy could dramat- ically save the storage cost and overcome the adverse influence of low signal-to-noise ratio samples. Moreover, it could be applied to any statistical process monitoring system without drastic changes to them, which is practical for industrial practices. As examples, the Q-based strategy was integrated with three popular algorithms （partial least squares （PIE）, recursive PIE （RPLS）, and kernel PIE （KPIE）） to form novel regression ones, QPLS, QRPIE and QKPLS, respectively. The applications for predicting mixed rubber hardness on a large-scale tire plant in east China prove the theoretical considerations.展开更多
The core objectives of intelligent manufacturing are to enhance product quality,reduce production costs,and improve manufacturing efficiency.One of the key technologies to achieve this goal is the monitoring and contr...The core objectives of intelligent manufacturing are to enhance product quality,reduce production costs,and improve manufacturing efficiency.One of the key technologies to achieve this goal is the monitoring and control of the machining process.Traditional offline tool condition monitoring(TCM)methods are prone to human error and require additional downtime.By contrast,tool condition online monitoring technology enables real-time monitoring throughout the machining process.This study reviews the progress of research on online monitoring of tool conditions and process parameter control based on tool status.It provides a detailed analysis from three perspectives:tool condition perception,algorithms for monitoring and control,and applications of monitoring and control.In terms of tool condition perception,the advantages and drawbacks of various sensing methods are explored.In terms of monitoring and control algorithms,developments from traditional monitoring algorithms to intelligent monitoring and parameter control algorithms are progressively reviewed.With regard to applications,the review focuses on how to adjust process parameters online on the basis of TCM by building on abnormal detection,tool wear monitoring,and life prediction to protect tools and improve machining efficiency.Then,the main development trends in tool condition online monitoring and control are introduced.Unlike previous reviews,this work extends the discussion beyond TCM to include recent progress in process parameter control on the basis of tool condition.The integration of tool online monitoring and process parameter control is recognized as one of the essential technologies for realizing intelligent manufacturing.展开更多
文摘To overcome the large time-delay in measuring the hardness of mixed rubber, rheological parameters were used to predict the hardness. A novel Q-based model updating strategy was proposed as a universal platform to track time-varying properties. Using a few selected support samples to update the model, the strategy could dramat- ically save the storage cost and overcome the adverse influence of low signal-to-noise ratio samples. Moreover, it could be applied to any statistical process monitoring system without drastic changes to them, which is practical for industrial practices. As examples, the Q-based strategy was integrated with three popular algorithms （partial least squares （PIE）, recursive PIE （RPLS）, and kernel PIE （KPIE）） to form novel regression ones, QPLS, QRPIE and QKPLS, respectively. The applications for predicting mixed rubber hardness on a large-scale tire plant in east China prove the theoretical considerations.
文摘The core objectives of intelligent manufacturing are to enhance product quality,reduce production costs,and improve manufacturing efficiency.One of the key technologies to achieve this goal is the monitoring and control of the machining process.Traditional offline tool condition monitoring(TCM)methods are prone to human error and require additional downtime.By contrast,tool condition online monitoring technology enables real-time monitoring throughout the machining process.This study reviews the progress of research on online monitoring of tool conditions and process parameter control based on tool status.It provides a detailed analysis from three perspectives:tool condition perception,algorithms for monitoring and control,and applications of monitoring and control.In terms of tool condition perception,the advantages and drawbacks of various sensing methods are explored.In terms of monitoring and control algorithms,developments from traditional monitoring algorithms to intelligent monitoring and parameter control algorithms are progressively reviewed.With regard to applications,the review focuses on how to adjust process parameters online on the basis of TCM by building on abnormal detection,tool wear monitoring,and life prediction to protect tools and improve machining efficiency.Then,the main development trends in tool condition online monitoring and control are introduced.Unlike previous reviews,this work extends the discussion beyond TCM to include recent progress in process parameter control on the basis of tool condition.The integration of tool online monitoring and process parameter control is recognized as one of the essential technologies for realizing intelligent manufacturing.
