Dear CAST Colleagues,


Special Issue on Big Data for Process Control and Operations - Call for Papers


With the recent development of smart manufacturing, internet of things, smart and wireless sensors, wireless communication, and smart devices, the amount of data collected and stored has grown exponentially. The explosion of data size has made all sectors including engineering, medicine, business, finance, and even science to endorse the power of big-data based decision-making and analytics. The promise of big data to science, engineering, and commerce leads to numerous successful applications where, by using a complete set of historical data rather than a sample, one can now analyze the data set in its entirety for knowledge discovery, fault and fraud detection, and decision-making.

In process systems operations, emerging or abnormal situations often happen, which are neither desirable nor expected in the design. In these situations data become indispensable assets for the safe and efficient operations. In the last 25 years, multivariate statistical process data analytic tools, such as principal component analysis and partial least squares, have been effectively used in process operations and control. However, big data analytics such as data mining and machine learning techniques have enjoyed tremendous development in computer science and management information science.

The aim of this Special Issue on Big Data for Process Control and Operations is to call for contributions that apply and develop bag data analytics and modeling for the purpose of process operation, monitoring, and control. Contributions are especially sought on how machine learning, data mining, and multivariate statistical methods might be developed and applied to a paradigm of data-enhanced operations and control. The perspective contributions might include but not limited to the following aspects relevant to process control, operation, modeling, and monitoring: i) mining of time series data for event discovery and decision-making; ii) causality analysis; iii) exploring the power of new machine learning techniques that have enjoyed tremendous development in nearly two decades; iv) robust data modeling methods; v) unsupervised and supervised learning techniques; vi) latent data modeling; vii) deep learning; and viii) new system architecture towards data-friendly information processing and computing.

Instructions for submission

Papers are due by April 15, 2016, and should be submitted online, but early submissions are highly encouraged. Please use Elsevier electronic submission system at and make sure to select “SI: Big Data” when you reach the “Article Type” step in the submission process.


Guest Editor

S. Joe Qin

Department of Chemical Engineering and Materials Science

University of Southern California

925 Bloom Walk

Los Angeles, CA 90089

[log in to unmask]

(Editorial Assistant: Ms. Catherine Zhu, [log in to unmask])


Best Regards,

Joe Qin, Fluor  Professor
IEEE Fellow, IFAC Fellow