The power grid is undergoing significant restructuring driven by the incorporation of renewable power and new flexible technologies that enable space–time load shifting, which is essential to mitigating space–time fluctuations associated with wind/solar power and other disruptions (e.g., extreme weather). The impact of load shifting is typically quantified via sensitivity analysis, which does not quantify operational flexibility (e.g., range or probability of feasible operation). In this work, we present a computational framework to quantify operational flexibility by assessing how much uncertainty in net loads can be tolerated by a power grid under varying levels of load shifting capacity. Our framework combines optimization formulations that quantify operational flexibility with power grid models that capture load shifting in the form of virtual links (pathways that transfer loads across space–time). Our case studies reveal that adding a single virtual link can lead to dramatic improvements in system-wide flexibility; this is because shifting helps relieve space–time congestion from transmission and generator ramping constraints.

Machine learning models are promising as surrogates in optimization when replacing difficult to solve equations or black-box type models. This work demonstrates the viability of linear model decision trees as piecewise-linear surrogates in decision-making problems. Linear model decision trees can be represented exactly in mixed-integer linear programming (MILP) and mixed-integer quadratic constrained programming (MIQCP) formulations. Furthermore, they can represent discontinuous functions, bringing advantages over neural networks in some cases. We present several formulations using transformations from Generalized Disjunctive Programming (GDP) formulations and modifications of MILP formulations for gradient boosted decision trees (GBDT). We then compare the computational performance of these different MILP and MIQCP representations in an optimization problem and illustrate their use on engineering applications. We observe faster solution times for optimization problems with linear model decision tree surrogates when compared with GBDT surrogates using the Optimization and Machine Learning Toolkit (OMLT).

Process industries are fascinated by cyber-physical systems because of the potential to integrate physical systems and the cyber realm, resulting in efficient remote monitoring and control. The conveyor belt system has many critical parameters that require continuous attention, necessitating cyber-physical remote monitoring. Due to cloud-based monitoring of parameters, the system is vulnerable to cyber threats. The proposed technique combines a sparse autoencoder and support vector machine (SVM) to detect false data injection attacks (FDIAs) in the presence of sensor bias fault. The sparse autoencoder extracts sparse features and learns anomaly-free dynamics from the input sensor readings. Then, the trained SVM distinguishes attacks and fault by analysing reconstruction residuals of each measurement reading. The residuals also give an idea about the magnitude of abnormality. The proposed method's efficacy is evaluated in terms of accuracy, precision and false-alarm rate with the help of fault and FDIAs models.

This paper develops a novel model-free Q-learning based approach to estimate linear, unconstrained feedback controllers from noisy process data. The proposed method is based on an extension of an available approach developed to estimate the linear quadratic regulator (LQR) for linear systems with full state measurements driven by Gaussian process noise of known covariance. First, we modify the approach to treat the case of an unknown noise covariance. Then, we use the modified approach to estimate a feedback controller for linear systems with both process and measurement noise and only output measurements. We also present a model-based maximum likelihood estimation (MLE) approach to determine a linear dynamic model and noise covariances from data, which is used to construct a regulator and state estimator for comparisons in simulation studies. The performances of the model-free and model-based controller estimation approaches are compared with an example heating, ventilation, and air-conditioning (HVAC) system. We show that the proposed Q-learning approach estimates a reasonably accurate feedback controller from 24 h of noisy data. The controllers estimated using both the model-free and model-based approaches provide similar closed-loop performances with 3.5 and 2.7% losses respectively, compared to a perfect controller that uses the true dynamic model and noise covariances of the HVAC system. Finally, we give future work directions for the model-free controller design approaches by discussing some remaining advantages of the model-based approaches.

Waste mismanagement has caused environmental pollution, while there is an opportunity to reduce this environmental degradation by converting waste into value-added products. These value-added products from waste have mutual effects from the perspective of water-energy-waste-carbon nexus and a cooperation approach could lead to better management. We develop a Stackelberg game model, where the municipality as a leader intervenes in the waste supply chain with penalties and subsidies to control environmental pollution, water consumption, and energy consumption. The collector collects waste from two channels municipal waste bins and waste purchasing. Buyable waste and recyclable waste from bins are sold to applicants. The collector sells the rest of the bins' waste to electricity and biofuel production (EB) plant and compost plant. A risk-aversion model has been considered for the EB due to the uncertainty of the amount of recyclable waste, and the model has been verified based on Tehran City.

This work proposes a mathematical programming approach for strategic planning in power system operations with the aim of promoting a sustainable energy transition. The approach identifies optimal operating policies that integrate conventional generation plants and renewable energies to meet user demand while considering energy generation, transmission, and distribution. Additionally, the formulation determines the optimal storage units required in the energy transmission network to improve system stability and reduce operating costs by balancing energy supply and demand. However, the operation of the power system is limited by several factors, such as economic and environmental factors as well as energy losses. Therefore, the purpose is to operate the electricity system with the lowest operating cost while minimizing CO2 emissions generated by electricity production. Since there is a conflict between these objectives, a multi-objective approach is necessary to propose a compromise solution. The compromise solution represents a balance between technical, economic, and environmental factors; the results demonstrate that it is possible to achieve a balance between these factors. Finally, we present a case study of the Mexican Electricity System (SEN) to apply the developed model. The case study includes a maximum load operation analysis to determine the system’s limits and ranges. This analysis will enable system expansion or improvement planning to meet future energy demands.

The design of control systems for modular chemical systems typically requires the identification of nonlinear dynamic models. Mechanistic models for modular chemical systems are typically of high order, which results in high online computational cost when the models are incorporated into the nonlinear model predictive control (NMPC) formulations developed for explicitly taking constraints into account. This article proposes the use of a particular class of nonlinear input–output models, polynomial nonlinear-autoregressive-with-exogenous-inputs (NARX) models, in the NMPC formulations. A machine learning algorithm, elastic net, is used to select which terms to include within the NARX polynomial series representation. The approach for constructing sparse predictive models and their use in real-time implementable NMPC are demonstrated in a two-input two-output chemical reactor case study. The Julia programming language is used to solve the NMPC optimization problem, resulting in low online computational cost.

Within the framework of Chemical Engineering, many exponential M-estimators have been proposed and tested. As usual, extensive simulation procedures are run to compare their performances. This work presents a deterministic methodology that reduces the computational endeavor of the comparative analysis. It becomes an effective technique for proposing and selecting high-performance M-estimators. The strategy uses the weight functions’ standardization to provide a common basis for the posterior application of Equivalent M-estimators and Tails Discrepancy definitions. In this way, identical M-estimators are figured out and those that behave likewise are identified. Whichever robust estimation procedure applied to estimate process variables and parameters can take advantage of the methodology results. For validation purposes, its conclusions are contrasted to the traditional performance measures obtained solving robust data reconciliation problems for two chemical processes.

This paper provides a perspective on the major challenges and directions in academic process control research over the next 5–10 years, and its industrial implementation. Large-scale systems control and identification, nonlinear model-based and model-free control, and controller performance monitoring and diagnosis are discussed as major directions for future research, along with control technology and industry workforce challenges and opportunities.

Numerical simulations of chromatography are conventionally performed using reduced-order models that homogenize aspects of flow and transport in the radial and angular dimensions. This enables much faster simulations at the expense of lumping the effects of inhomogeneities into a column dispersion coefficient, which requires calibration via empirical correlations or experimental results. We present a high-definition model with spatially resolved geometry. A stabilized space–time finite element method is used to solve the model on massively parallel high-performance computers. We simulate packings with up to 10,000 particles. The impact of particle size distribution on velocity and concentration profiles as well as breakthrough curves is studied. Our high-definition simulations provide unique insight into the process. The high-definition data can also be used as a source of ground truth to identify and calibrate appropriate reduced-order models that can then be applied for process design and optimization.

In chemical and pharmaceutical industries, process control optimization is a crucial step to improve economical efficiency and the environmental impact. The current state-of-practice heavily relies on expert knowledge and extensive lab experiments. This not only increases the development time but also limits the discovery of new strategies. In this study, we propose Reinforcement Learning-based optimization approach for solvent-switch processes. We utilize a digital twin as the environment for a process designed to switch the THF to 1-propanol. A reward function is created for minimizing the process time and constraints are implemented using logarithmic barrier functions. A PPO agent is trained on the environment. The agent proposed a novel strategy that combines two conventionally separate phases, evaporation and constant volume distillation. This strategy resulted in an overall cost decrease of 24.9% compared to the baseline strategy. Moreover, results were verified experimentally on a pilot plant of Johnson & Johnson (J&J).

Ensuring resilience in process systems is essential for safe and sustainable operations. Resilience is a property of the system which is characterized by the absorption, adaptation, and recovery performances of the system. Fault prognosis predicts the system's behavior after the occurrence of a fault and the time to failure which in-turn helps in determining the intervention strategies for restoring the system to its normal operating conditions. In the proposed framework, an adaptive modeling technique called operable adaptive sparse identification of system is implemented for fault prognosis. The time to failure of the system is determined based on the predicted system behavior. The system's absorption, adaptation, and recovery performances are modeled for different available intervention strategies, and they are evaluated based on a resilience metric. A case study is conducted on a batch reactor in thermal runaway condition and various intervention strategies are employed to demonstrate the applicability of the framework.

In this work, multi-criteria decision-making (MCDM) framework is proposed for selection of surfactant-free microemulsion fuel. Based on performance and emission characteristics, different beneficial and non-beneficial criteria were measured for 16 fuel samples across different engine loads. AHP method was implemented to obtain criteria weights, which were incorporated into three different MCDM methods i.e., AHP-VIKOR, AHP-TOPSIS, and AHP-PROMETHEE to rank all fuels. Results obtained from the proposed framework showed that microemulsion fuels with 20-40% diesel replacement were better alternatives to diesel. The Spearman rank correlation method was used to obtain correlation coefficients across rankings from different MCDM methods. These coefficients were used to combine the rankings to select a better fuel alternate. Microemulsion fuel with 20% diesel replacement was found to perform better compared to other alternatives owing to their lower BSFC and higher BTE at all loading conditions. Diesel was ranked last indicating microemulsions to be a sustainable fuel alternative.

Food security is a fundamental prerequisite of human survival. This study focuses on providing a novel bi-objective model for the design of a green closed-loop pomegranate supply chain based on the value chain. To maximize the benefits of circular economy, we propose a thermochemical conversion process and develop a novel hybrid risk-neutral and risk-averse multi-stage stochastic programming (RNRAMSSP) approach to cope with supply uncertainty. We employ the expected value of perfect information (EVPI) and value of stochastic solution (VSS) to validate the proposed approach. For the VSS metric, we define a novel measure to compare the worst-case cost of the stochastic and deterministic model solutions. To demonstrate the applicability of the proposed model, we provide a real case study in Iran. Based on the VSS metric, the risk-neutral and risk-averse stochastic model solutions save up to 1% and 1.76% in the worst-case cost, respectively, compared to the deterministic model.

This paper proposes a methodology for incipient fault diagnosis and the corresponding trend prediction in nonlinear closed-loop systems considering stochastic Gaussian and non-Gaussian uncertainties. The proposed approach is based on the use of the particle filtering technique for estimating the system states and outputs. From these estimations, the residual signals would be generated through a mathematical filtering and augmentation technique, allowing the incipient fault estimation that is evaluated using the designed fixed and adaptive thresholds that consider system uncertainties. In this way, the fault detection performance is improved but also the false detection and false alarm problems are comprehensively addressed. Moreover, the augmented Gauss–Newton identification method is used for the incipient fault trend prediction. Finally, to evaluate the effectiveness of the proposed approach, the incipient fault diagnosis in the heat transfer unit built in the nonlinear closed-loop continuous stirred-tank reactor (CSTR) system is used. Besides, the confusion matrix is employed to assess the results from a quantitative point of view.

Mechanistic modeling has shown to contribute greatly to the process understanding of chromatography and filtration processes. However, these are mostly considered individually and not connected for an entire downstream process. In this study, mechanistic models were connected to describe an entire downstream process of a Fab fragment. For the capture step, a transport-dispersion model (TDM) combined with an extended Langmuir isotherm was applied. Depth filtration was modeled with a combined pore blocking model. The polishing ion exchange chromatography steps were described by a TDM combined with the colloidal particle adsorption model. The tangential flow filtration model accounts for both the Donnan effects and flow limitations. The presented downstream process model could predict online and offline data recorded at 12,000 L manufacturing scale. Process variations of 23 manufacturing batches were adequately reproduced by the model based on the consideration of input process parameter variations.

The management of trade-off between experimental design space exploration and information maximization is still an open question in the field of optimal experimental design. In classical optimal experimental design methods, the uncertainty of model prediction throughout the design space is not always assessed after parameter identification and parameters precision maximization do not guarantee that the model prediction variance is minimized in the whole domain of model utilization. To tackle these issues, we propose a novel model-based design of experiments (MBDoE) method that enhances space exploration and reduces model prediction uncertainty by using a mapping of model prediction variance (G-optimality mapping). This explorative MBDoE (eMBDoE) named G-map eMBDoE is tested on two models of increasing complexity and compared against conventional factorial design of experiments, Latin Hypercube (LH) sampling and MBDoE methods. The results show that G-map eMBDoE is more efficient in exploring the experimental design space when compared to a standard MBDoE and outperforms classical design of experiments methods in terms of model prediction uncertainty reduction and parameters precision maximization.

In the actual soft sensor project, the complex industrial process leads to a large number of monitoring variables that lead to obvious problems of high dimension and data redundancy. To solve these problems, an adaptive cascade enhancement broad learning system combined with stacked correlation information autoencoder, referred to as SCIAE-ACEBLS, is proposed in this study. The latter is based on the broad learning system (BLS) and it includes two parts: feature node and enhancement node. In the feature node part, the correlation coefficient and the dominant variable are introduced into the stacked autoencoder (SAE), and all the hidden nodes are used as feature nodes. Both the correlation coefficient and the dominant variable are introduced to ensure that the information of feature nodes not only include the relevant information of the dominant variable in the auxiliary variables, but also in the dominant variable, and thus all the information related to dominant variables can be effectively used. In the enhancement node part, an adaptive cascade enhancement node algorithm is used to reduce the redundancy of effective information and solve the problems of node information redundancy and node number uncertainty caused by the randomness of the node parameters in BLS. Finally, two industrial examples show that the proposed model is effective and outperforms existing methods.

Modifier adaptation (MA) is commonly used for economic optimization of systems under model uncertainty. In MA, gradient correction terms require estimation through perturbations, thus delaying the optimization procedure. A directional modifier adaptation method is proposed whereby a subset of available gradient corrections are made. An algorithm that evaluates possible adaptation strategies and chooses those with the largest economic effect is proposed, thereby allowing economical operation with less delay. The proposed scheme, named dMAIS, is deployed on the Williams-Otto process where it is found to outperform MA if not inhibited by filtering. Systems can also suffer from constraint violation if uncertainty is present, hampering safety and profitability. An adjustment step is proposed as part of dMAIS, whereby gradients are used to drive the plant to constraint satisfaction. The adjustments are studied in an evaporator case with a product quality constraint whereby dMAIS is shown to result in infrequent violations leading to higher throughput. The proposed approach was also compared to standard directional MA in the evaporator case study, where it was found to be economically beneficial. The benefits of dMAIS are observed most saliently for systems with increasing disturbance frequency.

Computer-aided molecular design (CAMD) methods can be used to generate promising solvents with enhanced reaction kinetics, given a reliable model of solvent effects on reaction rates. Herein, we use a surrogate model parameterised from computer experiments, more specifically, quantum-mechanical (QM) data on rate constants. The choice of solvents in which these computer experiments are performed is critical, considering the cost and difficulty of these QM calculations. We investigate the use of model-based design of experiments (MBDoE) to identify an information-rich solvent set and integrate this within a QM-CAMD framework. We find it beneficial to consider a wide range of solvents in designing the solvent set, using group contribution techniques to predict missing solvent properties. We demonstrate, via three case studies, that the use of MBDoE yields surrogate models with good statistics and leads to the identification of solvents with enhanced predicted performance with few iterations and at low computational cost.