Ivan Castillo

• Doctor of Engineering
• Senior technology manager at Dow Chemical Company

Fouling in heat exchangers leads to increased pressure drop, associated with higher energy consumption, utility costs, and CO$_2$ emissions. However, other effects can also take place, threatening process operations and safety. This is the case of ethylene oxide operations, where unplanned outages and decomposition events pose significant safety ri...

We explore the use of tools from Riemannian geometry for the analysis of symmetric positive definite matrices (SPD). An SPD matrix is a versatile data representation that is commonly used in chemical engineering (e.g., covariance/correlation/Hessian matrices and images) and powerful techniques are available for its analysis (e.g., principal compone...

We explore the use of tools from Riemannian geometry for the analysis of symmetric positive definite matrices (SPD). An SPD matrix is a versatile data representation that is commonly used in chemical engineering (e.g., covariance/correlation/Hessian matrices and images) and powerful techniques are available for its analysis (e.g., principal compone...

In this article, multiple reinforcement learning (RL) methods such as value‐based, policy‐based, and actor‐critic algorithms are investigated for typical control tasks found in the chemical industries. Through a critical assessment of these novel techniques, their main advantages are highlighted, but also the challenges that still need to be resolv...

In the Industry 4.0 era, the chemical industry is embracing broad adoption of artificial intelligence (AI) and machine learning (ML) methods. This article provides a holistic view of how the industry is transforming digitally towards AI at scale. First, a historical perspective on how the industry used AI to aid humans in better decision‐making is...

In this work, we present a hybrid fundamental-empirical model to monitor and predict the catalyst lifetime of an operating industrial reactor. The hybrid model combines a fundamental adiabatic reactor model to calculate the activity of the catalyst bed with an empirical partial least-squares model to predict the catalyst activity at different opera...

In this paper, we propose a statistical learning procedure that integrates process knowledge for the Dow data challenge problem presented in Braun et al. (2020). The task is to build an accurate inferential sensor model to predict the impurity in the product stream with apparent drifts. The proposed method consists of i) process data exploratory an...

The chemical processing industry has relied on modeling techniques for process monitoring, control, diagnosis, optimization, and design, especially since the third industrial revolution and the emergence of Process Systems Engineering. The fourth industrial revolution, connected to massive digitization, made it possible to collect and process large...

The operational management of wastewater treatment plants (WWTP) is a complex activity due to the biological phenomena’ intricate nature. This complexity hinders the adoption of first principles approaches, which lack the necessary accuracy to be adopted in practice. Data-driven methodologies also face significant challenges in processing the diffe...

Reinforcement learning is a branch of machine learning, where an agent gradually learns a control policy via a combination of exploration and interactions with a system. Recent successes of model-free reinforcement learning (RL) has attracted tremendous attention from the process control community. For instance, RL has been successfully applied in...

This article addresses the plant‐model mismatch estimation problem for linear multiple‐input and multiple‐output systems operating under the dynamic matrix control (DMC) implementation of model predictive control. An autocovariance‐based method is proposed, aiming to identify parameter values that minimize the discrepancy between the theoretical au...

The optimization of batch processes usually relies on the availability of a detailed knowledge-driven model. However, because of the great varieties of industrial batch processes and their small production rates, a knowledge-driven model might not always be available. In such a case, a data-driven model, developed after a limited number of experime...

This paper explores dimensionality reduction (DR) approaches for visualizing high dimensional data in chemical processes. Visualization provides powerful insight and process understanding in the industrial context, and accelerates process troubleshooting. A diverse array of existing, easy-to-use DR methods are evaluated in three case studies on lar...

Developing predictive models from industrial datasets implies the consideration of many possible predictor variables (features). Using all available features for data-driven modelling is not recommended, as most of them are expected to be irrelevant and their inclusion in the model may compromise robustness and accuracy. In this work, we present, t...

Manufacturing analytics is of paramount importance in many plants today, and its relevance increases in the current big data context of Industry 4.0. The fields of statistics, chemometrics, and machine learning are expected to provide tools that effectively handle many of the characteristics of industrial data. In this paper, the task of image-base...

The area of controller performance monitoring, assessment and diagnosis for model predictive control (MPC) has seen an increase in interest in recent years. A frequently identified cause of degraded performance is mismatch between the plant model used in the controller and the true dynamics of the plant. Most recent research focuses on locating pla...

We present a data analytics framework for offline analysis of batch processes. The framework provides a unified setting for implementing several variants of feature oriented analysis proposed in the literature, including a new methodology based on the process variables’ profiles presented in this article. It also integrates feature generation and f...

In this paper, we propose a novel autocovariance-based plant-model mismatch estimation approach for linear MPC MIMO control loops with changing setpoints and measurable disturbances. Assuming a noise model is available and that there are of periods of operating data where the active set of the controller is fixed and the plant-model mismatch is inv...

In this paper, we present autocovariance-based estimation as a novel methodology for determining plant-model mismatch for multiple-input, multiple-output systems operating under model predictive control. Considering discrete-time, linear time invariant systems under reasonable assumptions, we derive explicit expressions of the autocovariances of th...

Big data analytics is the journey to turn data into insights for more informed business and operational decisions. As the chemical engineering community is collecting more data (volume) from different sources (variety), this journey becomes more challenging in terms of using the right data and the right tools (analytics) to make the right decisions...

The present paper addresses the task of quality prediction in batch processes, where measurements from process variables are used to predict one or more quality variables of interest. The majority of current methods for batch quality prediction are based on complete time profiles for all variables, requiring synchronization before batch-wise unfold...

In this paper, we present a novel data-driven approach for estimating plant-model mismatch for linear MIMO systems operating under constrained MPC. We begin with analyzing the closed-loop plant data; under the assumption that changes in the active set of constraints of the controller are due to (low frequency) setpoint changes, we separate the data...

One of the challenges of utilizing soft sensors is that their prediction accuracy deteriorates with time due to multiple factors, including changes in operating conditions. Once soft sensors are designed, a mechanism to maintain or update these models is highly desirable in industry. This paper proposes an index that can monitor the prediction perf...

Abstracts: * Soft sensor model update AIChE.pdf (13.5KB) - Uploading Abstracts

Soft sensors (or inferential sensors) have been demonstrated to be an effective solution for monitoring quality performance and control applications in the chemical industry. One of the key issues during the development of soft sensor models is the selection of relevant variables from a large array of measurements. A subset of variables that are se...

This paper proposes a model-based detection and isolation (FDI) system based on nonlinear state estimation that can be applied to nonlinear systems. The proposed FDI system uses an extended Kalman filter (EKF), in which conditions based on high filtering are defined to best serve the FDI objectives. A better understanding of the residual trends, ca...

For multimode processes, the conventional multivariate statistical processes monitoring (MSPM) techniques such as multiple principal component analysis (MPCA), multiple partial least squares (MPLS) and Gaussian mixture model (GMM) methods require fault-free data from all different operating conditions in order to train the data-driven models of nor...

Missing data is a common issue due to sensor failure, multi-rate sampling frequency and device unreliability in industrial processes. Despite considerable literature research in the fields of multivariate statistics process monitoring and soft sensor estimation, appropriate way of handling random missing measurements in industrial process data rema...

This paper proposes a robust fault detection and isolation system for nonlinear processes that can be formulated as differential algebraic equations. For open-loop stable or closed-loop stabilized systems that operate under strict nonlinear detectability conditions, a methodology to design a nonlinear state estimator based on sliding mode theory wa...

This paper presents a nonlinear fault detection and isolation system that is able to distinguish single faults that have the same fault signatures. The detection mechanism is based on nonlinear state estimation. Fuzzy set theory followed by parameter estimation of certain parameters of the fault-free model are applied for fault isolation. This para...

This paper proposes a robust fault detection system that can be applied to nonlinear chemical processes. A nonlinear state estimator which is able to handle both parameter estimation and parameters with uncertainties is designed. The detection process is created by examining changes in the controlled outputs with respect to set point, followed by p...

This paper presents the main advantages of using an industrial distributed control system (DCS) in the operation of a distillation column which is used in an undergraduate unit operations laboratory course at the University of Texas at Austin. Taking advantage of the resources of an industrial DCS (friendly display options, an alarm management syst...

Fault detection and identification applications are mostly based on empirical models that quickly degenerate in time due to slow changes in what operators consider normal process conditions. The extensive use of such algorithms is always rare due to the variations that a traditional industrial facility undergoes in time. This work illustrates the u...

Process control classes and laboratories have adopted affordable control systems from industry with easy to use software/hardware configurations and interactive design tools in order to make process control more practical and accessible to students. Consequently, the implementation of control algorithms in real time systems has become an important...

RESUMEN En este artículo se presenta un método para la identificación y control de sistemas no lineales usando modelos difusos tipo Takagi-Sugeno. La identificación se basa en técnicas de clustering y el control se realiza mediante técnicas predictivas. En primer lugar se hace una descripción global de la técnica de clustering haciendo referencia a...