Ayan Mukherjee

Saptarshi Das, Sayan Saha, Ayan Mukherjee et al.

Gain and order scheduling of fractional order (FO) PIλDμ controllers are studied in this paper considering four different classes of higher order processes. The mapping between the optimum PID/FOPID controller parameters and the reduced order process models are done using Radial Basis Function (RBF) type Artificial Neural Network (ANN). Simulation studies have been done to show the effectiveness of the RBFNN for online scheduling of such controllers with random change in set-point and process parameters.

Ayan Mukherjee, Anindya Pakhira, Saptarshi Das et al.

The paper presents a Stateflow based network test-bed to validate real-time optimal control algorithms. Genetic Algorithm (GA) based time domain performance index minimization is attempted for tuning of PI controller to handle a balanced lag and delay type First Order Plus Time Delay (FOPTD) process over network. The tuning performance is validated on a real-time communication network with artificially simulated stochastic delay, packet loss and out-of order packets characterizing the network.

Snehasis Banerjee, Tanushyam Chattopadhyay, Ayan Mukherjee

This paper presents an automated approach for interpretable feature recommendation for solving signal data analytics problems. The method has been tested by performing experiments on datasets in the domain of prognostics where interpretation of features is considered very important. The proposed approach is based on Wide Learning architecture and provides means for interpretation of the recommended features. It is to be noted that such an interpretation is not available with feature learning approaches like Deep Learning (such as Convolutional Neural Network) or feature transformation approaches like Principal Component Analysis. Results show that the feature recommendation and interpretation techniques are quite effective for the problems at hand in terms of performance and drastic reduction in time to develop a solution. It is further shown by an example, how this human-in-loop interpretation system can be used as a prescriptive system.