Santhosh kumar Varanasi

Indian Institute of Technology Jodhpur | IITJ · Chemical Engineering

In this paper, a method of designing control inputs for stochastic nonlinear processes under state-feedback is proposed. The objective is to determine a control input that minimizes the expected value of the integral of error between the set-point and the states. Since the states may not be measured, they are estimated using a particle filtering al...

The main objective of this paper is to develop a soft sensor for predictions of the residue element concentrations of feed mixture in a KIVCET furnace, since such measurements are not available online and are crucial in achieving the objective of real-time optimization. To realize this, a wavelet neural network is considered owing to its high accur...

In this paper, a self-optimization algorithm is developed to find both the optimal operating point and the path from the current condition to the optimal point. Being a model-based strategy, a generalized locally weighted probabilistic principal component regression (PPCR) model that is robust to outliers and can handle missing data, is developed t...

Multi-agent systems are usually large-scaled with a growing degree of intelligence and integration. Direct applications of traditional (centralized) methods will become incompetent for effective process monitoring of multi-agent systems. It necessitates the cognitive learning strategies that determine the effective interactions among subsystems or...

Causal analysis plays a vital role in determining the underlying relationship among the variables in a system from the data. In this article, the sparse inverse covariance (SIC) estimation is coupled with likelihood score, and a two-step approach is proposed to address the problem of causal analysis. The estimation of SIC matrix for undirected spar...

Industrial processes often operate in multiple operating modes. In most cases, the outputs are measured at a slower rate than the inputs due to various reasons, such as the unavailability of real-time sensors. In some cases, measurements of inputs are also not available and/or there are outliers in the measurements due to sensor failures. Furthermo...

A method of designing control inputs for tracking problems when models considered in the form of stochastic differential equations is proposed. Using the ideas of control vector parameterization, the control input identification problem is formulated as a parameter identification problem, which is solved using homotopy optimization. To further obta...

Bitumen in the oil sands industry is separated from sand using a water-based gravity separation process in a Primary Separation Vessel (PSV). The interface between the froth and the middlings layer is an important parameter to control for optimal operation of the PSV unit. In this paper, a method using computer vision based on Convolutional Neural...

In the existing literature, convergence results for particle filters are given explicitly only for the case when the underlying dynamic model is a Markov process. When output feedback control is used, the evolution of the state process is no longer Markovian due to the dependence of inputs on the outputs. In this paper, it is shown that the random...

Subspace identification methods using Generalized Poisson Moment Functionals (GPMF) have been proposed previously to tackle the problem of derivative estimation in continuous time (CT) systems. In this paper, a convergence result underpinning the GPMF methods for continuous time identification is detailed. Based on this, a CT-MOESP method is propos...

Electrical Impedance Tomography (EIT) can be used to study the hydrodynamic characteristics in multi-phase flows such as gas holdup in bubble columns, air-core in hydro-cyclone, etc. In EIT, the main objective is to estimate the electrical properties (conductivity distribution) of an object in a region of interest based on the surface voltage measu...

In this paper, the problem of input design for identification of continuous time output error models is considered. The input design problem is formulated as maximization of a measure of the Fisher Information Matrix, which defines the accuracy with which the system parameters can be estimated. The optimization problem involving the Fisher Informat...

The main problem in identification of continuous LTI systems is the lack of derivative information of the outputs. If all the derivatives are known exactly, a least squares approach is sufficient to obtain the parameter estimates. In this paper, we propose a method which can provide theoretical bounds on the error in the parameter estimates assumin...

Neuronal network reconstruction is an important problem in neuroscience as it helps understanding neuronal circuit and function. With the advancements of the calcium imaging technique, the dynamic activity of hundreds of neurons can be observed, which also provides a foundation for modelling and inferring network connectivity directly from data. In...

Electrical Impedance Tomography (EIT) can be used to obtain phase boundaries and gas holdups in multiphase flows. The main challenge in image reconstruction using EIT is the low spatial resolution. In this paper, a reconstruction algorithm using sparse optimization techniques is presented. For multiphase flows, gradients in the conductivity vector...

Identifying lower order models is desirable both for control design and prediction purposes. In a few cases, a lower order model can be further reduced so that it contains the fewest number of parameters. In this paper, a sparsity seeking optimization method is proposed to identify such parsimonious continuous time (CT) linear time invariant (LTI)...

Subspace identification techniques derive approximate models rather than models that are optimal with respect to a goodness of fit criterion. To obtain low rank models, a nuclear norm minimization method for estimating the system matrices of linear time invariant continuous time state-space models in the presence of measurement noise is proposed. I...

Subspace identification techniques derive approximate models rather than models that are optimal with respect to a goodness of fit criterion. To obtain low rank models, a nuclear norm minimization method for estimating the system matrices of linear time invariant continuous time state-space models in the presence of measurement noise is proposed. I...

In this paper, topology identification of dynamic systems in the continuous time (CT) framework is considered. The main objective is to identify the direction of information flow and to estimate the transfer function of each node simultaneously. The output of each node is affected by the outputs of the other nodes along with transportation delay an...

In this paper, a sparsity seeking optimization method for estimating the parameters along with the order of output error models of single-input and single-output (SISO), linear time invariant (LTI) system is proposed. It is demonstrated with the help of simulations that the proposed algorithm gives accurate parameter and order estimates on a variet...