As part of the fourth industrial revolution-Industry 4.0, the manufacturing systems are striving themselves to become “smart factories" which are intelligent enough to synchronize the physical operations and information technology by extracting information embedded in the historical operational data. On the other hand, emission norms of industrial processes are continuously getting stringent to reduce the carbon foot prints, forcing the process industries to operate more efficiently without moving away operating region where the profit is high. Hence our researach group focuses developing process models from data using adavanced analytic approaches, employ them Advance Process Control (APC) strategies which are" smart" or "intelligent" and also develop process monitoring methods such that the holistic paradigm including all these components play a key role to achieve higher process efficiency and safety by satisfying operational constraints.
The specic areas of our research:
1. Process data analyitcs: The focus here would be the development of various data analytic appraoches to develop suitable process models from laboratory/ industrial data employing Bayesian principles. The emphasis would be given to theory, development and synthesis of static/dynamic process models that employ features extracted from data.
2. Intellingent Advanced Process Control strategies: Once the process model is built, they can be deoployed in control framework for acheiving better operational efficiency. The key research problems include developement model based control strategies using the synthesized models, study of their stability related aspect and also sysnthesis of novel algorithms that employ learning based appraoches for solving them.
3. Process monitoring: Process monitoring is imperative to ensure and improve product quality, process safety and equipment reliability of a process. The key research thrust would be given to (i) fault detection; (ii) fault diagnosis; (iii) fault estimation; and (iv) fault isolation using the derived models by synthesizing various performance indices to statistically detect anomalies in process dynamics.