Babji Srinivasan

Time-delay estimation in closed-loop systems is of critical value in the tasks of system identification, closed-loop performance assessment and process control, in general. In this work, we introduce the application of mutual information (MI) theory to estimate process delay under closed-loop conditions. The hallmark of the proposed method is that no exogenous (dither) signal is required to estimate the delay. Further, the method allows estimation of time-delays merely from the step response of the system. The method is based on the estimation of a quantity known as the average mutual information (AMI) computed between the input and output of the system. The estimation of AMI involves estimation of joint probability distribution of the input-output pair and therefore is a superset of the existing correlation-based methods, which only compute second-order moments of the joint distribution. Simulation studies are presented to demonstrate the practicality and utility of the proposed method.

The objective of the design and operation of any water distribution network (WDN) includes meeting the desired demand at sufficient pressure at all nodes. However, this requires situational awareness; in other words, the knowledge of system state variables such as pressure and flow throughout the network. In this work, a hybrid approach is developed for sensor placement (SP) and state estimation (SE) that exploits the underlying correlation structure in the data, along with the principles governing the flow through circular pipes. The problem of SP in WDN is addressed since measuring the state variables throughout the network is not practical. The problem of SE that maps to a matrix completion problem under certain physical and logical constraints is solved later. The completed matrix represents the state of WDN at any given time. Benchmark networks used in literature were used to evaluate the proposed approach. The mean absolute percentage error (MAPE) of less than 5% was obtained while estimating the head available at nodes. The knowledge of the states in the entire network could help operate the network adaptively.

Fault detection in linear systems is a fairly matured area where the well-known principal component analysis (PCA) and its variants are widely used. However, a large class of non-linear systems exist, especially chemical processes, on which such techniques cannot be applied. The present work aims at demonstrating the application of self-organising maps (SOM) for fault detection in non-linear processes. SOM belongs to the class of unsupervised and competitive learning algorithms and it is highly capable of handling nonlinear relationships. Application of SOM to fault detection involves generation of a reference template for the process under fault-free conditions. Online fault detection is performed by generating a new template using a windowing of the data, which is compared with the reference template using a novel metric based on the node weights obtained from SOM to detect possible faults in the process. Simulation studies on two non-linear systems, namely, (1) continuously stirred tank reactor (CSTR) and (2) bioreactor process demonstrate the practicality and utility of the proposed method. © 2010 Inderscience Enterprises Ltd.

Events such as pipe burst, pipe clogging, excess demand often disrupt the water distribution network operation. As a result, water utilities have to bear an extra financial burden. The knowledge of such events could help the water supply board formulate and operate the network with minimal loss. This work aims to identify the nature of such uncertain events with limited operational information using simple measures designed to monitor the network locally at nodes. Instead of acquiring information from all the nodes, a few nodes are identified for sensor placement by solving a Mixed Integer Linear Programming (MILP) problem. The objectives for solving MILP are to minimise total sensor cost and maximise the sensitivity of measurements to any given fault. Sensitivity is calculated from operational data generated by performing Monte Carlo simulations. These simulations generate data for each fault of different magnitude at different locations. Gradient boosting trees are trained using the limited operational information from the network. Accuracy of identification of faults of 78% on the passive network and over 81% on active networks was obtained using limited features with extreme gradient boosting (XGBoost) model.

Fouling degrades the overall efficiency of the heat exchanger networks (HENs), which results in a significant economic loss. The mitigation of fouling in an operational HEN is carried out by optimizing the cleaning schedules of the heat exchangers. Although such approach can save costs, it is subjected to the exact implementation of the optimal cleaning schedule. Usually, the small and medium-scale process industries face difficulties in implementing such solutions due to limited resources, which forces them to rely on suboptimal cleaning schedules, such as postponing or avoiding few cleaning tasks. This work addresses this gap by optimizing the cleaning schedule considering the maintenance resource limitation. Our approach considers a mixed-integer linear programming (MILP) based optimization considering groupings of heat exchangers based on their spatial locations for ease of maintenance The proposed formulation is applied on a HEN with linear and asymptotic fouling, with and without cleaning cost. The results show that the approach can prevent a considerable economic loss, which would incur due to suboptimal cleaning schedules due to resource limitations.

Safety in process plants is of paramount importance. With the predominant contributor to accidents in process industries being repeatedly identified as human error, it is necessary to have skilled operators to prevent accidents and minimise the impact of abnormal situations. Such knowledge and skills are imparted to operators using operator training simulator (OTS) which offer a simulated environment of the real process. However, these techniques emphasize on assessing operator's ability to follow standard guidelines – assessment of the operator's process knowledge and imparting an adequate mental model to the operator is not addressed. Further, understanding cognitive behavior of operators, identified as crucial to enhancing their skills and abilities is often neglected. In this work, we develop a systems engineering framework to operator training with emphasis on accounting for the cognitive abilities of the human-in-the-loop. The framework consists of three distinct components: (1) Design of suitable training tasks, (2) Measure and analyse operator's cognitive response while performing the tasks, and (3) Infer operator's mental model through knowledge and capability assessment. Consider the operator as a system whose input is information acquired from the process through the human machine interface (HMI) and output are actions taken on the process (such as manipulating valves). We demonstrate in this paper that the available input (from eye tracking) and output (operator actions) data when suitably analysed with respect to the process state can aid in inferring the operator's mental model at any given time. Based on the model, the operator's current knowledge can be deduced and gaps identified. New training tasks can then be designed to address these gaps. In this article, we describe the proposed framework for operator learning and illustrate it using experimental studies.

In this contribution we propose an active Fault Tolerant Control (FTC) strategy which enables the isolation and identification of valve stiction and valve blocking, in addition to the additive faults like sensor and actuator biases. The developed method is an extension of the original method proposed by Prakash et al. (2002). This method is based on the Kalman filter and is developed under the assumption that the monitored system is Linear Time Invariant (LTI). It has been shown to work well for additive faults such as sensor and actuator biases. Within this method the fault isolation and identification task is based on the Generalized Likelihood Ratio (GLR) test by which the most plausible fault type in a library of faults is selected following estimation of fault parameters. © 2010 Elsevier B.V.

Traditional matrix and tensor completion approaches utilize latent structures in data to impute missing entries. Recent works on distribution system state estimators employing such data imputation techniques have identified the need to incorporate fundamental system equations as constraints to improve state estimation accuracy. As a result, these techniques provide superior state estimation performance compared to their model-free counterparts and conventional state estimators. In practice, the data required for these estimators are provided by sensors/meters deployed in the network. However, prior efforts do not explore the placement of sensors that optimize the performance of the estimators. Moreover, constraints on entries of these matrices and tensors result in specific combinations of known measurements to provide better imputation results than others. Therefore, this work proposes two-meter placement approaches that leverage network parameters and linearized power flow equations to identify sensor locations. These approaches achieve this by iteratively placing sensors with the highest contribution towards minimizing the voltage residual in the selected reference cases. The first approach identifies buses that provide the highest reduction in voltage residuals. In contrast, the second approach identifies locations of a heterogeneous set of sensors that provide the highest reduction in voltage residual. The proposed approaches can also extend existing sensor deployments such as distribution phasor measurement units (D-PMU) and supervisory control and data acquisition (SCADA) sensing and measurement devices (e.g., Bellwether meters) to improve state estimation performance. The approaches have been evaluated on the IEEE 33-node distribution system and an unbalanced 3-phase 559-node distribution system.

Non-negative Matrix Factorization (NMF) has been used for source separation in various fields. However, the existing methods have ignored the presence of interactions among sources/measurements which leads to incorrect results. Interactions are common in a multivariate process where the variables are physically related/correlated with one another (for example: pressure-temperature dependency in an industrial process). In this work, conventional methods are extended to take into account the interactions. The contributions of this work are as follows: (i) an augmented NMF method to correctly determine the number of sources in the presence of multiple interactions; (ii) an algorithm to identify the correct signatures of the physical sources. The conventional method of NMF is shown to be a special case of the proposed method. Simulation studies are presented to demonstrate the practicality and utility of the proposed method. © 2009 Elsevier Inc. All rights reserved.

Operators' mental models play a central role in safety-critical domains like the chemical process industries. Accurate mental models, i.e., a correct understanding of the process and its causal linkages, are prerequisites for safe operation. Mental models are often defined and explained in abstract terms that make their interpretation subjective and prone to bias. In this work, we propose a Hidden Markov Model (HMM) based formalism to characterize control room operators' mental models while handling abnormal situations. We show that a suitable HMM representing the operator's mental model – including the states, state transition probabilities, and emission probability distributions – can be identified experimentally using data of the operator's control actions, eye gaze, and process variable values. This HMM can be used for the quantitative assessment of operators' mental models as illustrated using various case studies. We discuss the potential applications of the model in identifying various cognitive errors and human reliability assessment. In Part 2 of this paper, we use the proposed approach to assess operators' learning during training.