Advanced Process Monitoring for Industry 4.0

doi:10.3390/books978-3-0365-2074-2

Download Url(s)

https://mdpi.com/books/pdfview/book/4369

Contributor(s)

Reis, Marco S. (editor)

Gao, Furong (editor)

Language

English

Show full item record

Abstract

This book reports recent advances on Process Monitoring (PM) to cope with the many challenges raised by the new production systems, sensors and “extreme data” conditions that emerged with Industry 4.0. Concepts such as digital-twins and deep learning are brought to the PM arena, pushing forward the capabilities of existing methodologies to handle more complex scenarios. The evolution of classical paradigms such as Latent Variable modeling, Six Sigma and FMEA are also covered. Applications span a wide range of domains such as microelectronics, semiconductors, chemicals, materials, agriculture, as well as the monitoring of rotating equipment, combustion systems and membrane separation processes.

URI

https://directory.doabooks.org/handle/20.500.12854/76899

Keywords

spatial-temporal data; pasting process; process image; convolutional neural network; Industry 4.0; auto machine learning; failure mode effects analysis; risk priority number; rolling bearing; condition monitoring; classification; OPTICS; statistical process control; control chart pattern; disruptions; disruption management; fault diagnosis; construction industry; plaster production; neural networks; decision support systems; expert systems; failure mode and effects analysis (FMEA); discriminant analysis; non-intrusive load monitoring; load identification; membrane; data reconciliation; real-time; online; monitoring; Six Sigma; multivariate data analysis; latent variables models; PCA; PLS; high-dimensional data; statistical process monitoring; artificial generation of variability; data augmentation; quality prediction; continuous casting; multiscale; time series classification; imbalanced data; combustion; optical sensors; spectroscopy measurements; signal detection; digital processing; principal component analysis; curve resolution; data mining; semiconductor manufacturing; quality control; yield improvement; fault detection; process control; multi-phase residual recursive model; multi-mode model; process monitoring; n/a