Dynamic multimode process monitoring using recursive GMM and KPCA in a hot rolling mill process

نویسندگان

چکیده

The increasing competitive market has put forward higher demand for iron and steel production process, which is characterized by high-dimensional, nonlinear multi-scale coupling. newly rising internet of things (IoT) advanced communication technologies have promoted the widespread application data-driven process monitoring methods. To deal with multimode non-stationary properties hot rolling production, a dynamic method proposed based on recursive Gaussian mixture model (RGMM) kernel principal component analysis (RKPCA). approach applied to hot-rolled strip thickness oversizing, comparative experiments are conducted KPCA, GMM-KPCA actual data. Results show that shows better performance than conventional methods in terms fault detection rate false alarm when detecting time-varying faults. also been integrated into an system running smoothly large mills China.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Metallurgically Consistent Determination of Steel Hot Strength Using Process Data from Hot Strip Mill Rolling

It is not rare to observe an inverse relationship between hot strength determined from rolling load of the finishing stands of the hot strip mill and strain. This situation was already described in the literature and is explained by the use of inverse rolling load models that assumes sticking friction in the determination of hot strength. The aim of this work was to show that this “work softeni...

متن کامل

Modeling of Hot Rolling Industrial Process Using Fuzzy Logic

Steel making is known as a complex manufacturing industrial process. Automation of the process represents a challenge. Empirical mathematical modeling of the process was used to design mill equipment, ensure productivity and service quality. This modeling approach shows many problems associated to complexity and time consumption. Soft computing techniques show significant modeling capabilities ...

متن کامل

A Review and Evaluation of Statistical Process Control Methods in Monitoring Process Mean and Variance Simultaneously

In this paper, first the available single charting methods, which have been proposed to detect simultaneous shifts in a single process mean and variance, are reviewed. Then, by designing proper simulation studies these methods are evaluated in terms of in-control and out-ofcontrol average run length criteria (ARL). The results of these simulation experiments show that the EWMA and EWMS methods ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Systems Science & Control Engineering

سال: 2021

ISSN: ['2164-2583']

DOI: https://doi.org/10.1080/21642583.2021.1967220