The ALAMO approach to machine learning

Advanced Modeling and Optimization Strategies for Process Synthesis

This article provides a systematic review of recent progress in optimization-based process synthesis. First, we discuss multiscale modeling frameworks featuring targeting approaches, phenomena-based modeling, unit operation-based modeling, and hybrid modeling. Next, we present the expanded scope of process synthesis objectives, highlighting the considerations of sustainability and operability to assure cost-competitive production in an increasingly dynamic market with growing environmental awareness. Then, we review advances in optimization algorithms and tools, including emerging machine learning-and quantum computing-assisted approaches. We conclude by summarizing the advances in and perspectives for process synthesis strategies.

Modeling Framework for Cost Optimization of Process-Scale Desalination Systems with Mineral Scaling and Precipitation

Cost-optimization models are powerful tools for evaluating emerging water treatment processes. However, to date, optimization models do not incorporate detailed chemical reaction phenomena, limiting the assessment of pretreatment and mineral scaling. Moreover, novel approaches for high-salinity and high-recovery desalination are typically proposed without direct quantification of pretreatment needs or mineral scaling. This work addresses a critical gap in the literature by presenting a modeling framework that includes complex water chemistry predictions with process-scale optimization. We use this approach to conduct a technoeconomic assessment on a conceptual high-recovery treatment train that includes chemical pretreatment (i.e., soda ash softening and recarbonation) and membrane-based desalination (i.e., standard and high-pressure reverse osmosis). We demonstrate how to develop and integrate accurate multidimensional surrogate models for predicting precipitation, pH, and mineral scaling tendencies. Our findings show that cost-optimal results balance the costs of pretreatment with reverse osmosis system design. Optimizing across a range of water recoveries (i.e., 50-90%) reveals multiple cost-optimal schemas that vary the chemical dosing in pretreatment and the design and operation of reverse osmosis. Our results reveal that pretreatment costs can be more than double the cost of the primary desalination process at high recoveries due to the extensive pretreatment required to control scaling. This work emphasizes the importance of and provides a framework for including chemistry and mineral scaling predictions in the evaluation of emerging technologies in high-recovery desalination.

Multi-scale techno-economic assessment of nitrogen recovery systems for livestock operations

Intensive livestock farming generates vast amounts of organic materials, which are an important source of nitrogen releases. These anthropogenic nitrogen releases contribute to multiple environmental problems, including eutrophication of water systems, contamination of drinking water sources, and greenhouse gas emissions. Nitrogen recovery and recycling are technically feasible, and there exists a number of processes for nitrogen recovery from livestock material in the form of different products. In this work, a multi-scale techno-economic assessment of techniques for nitrogen recovery and recycling is performed. The assessment includes a material flow analysis of each process, from material collection to final treatment, to determine nitrogen recovery efficiency, losses, and recovery cost, as well as an environmental cost-benefit analysis to compare the nitrogen recovery cost versus the economic losses derived from its uncontrolled release into the environment. The results show that transmembrane chemisorption process results in the lowest recovery cost, 3.4-10.4 USD per kilogram of nitrogen recovered in the range of studied processing scales. The recovery of nitrogen from livestock material through three technologies, i.e., transmembrane chemisorption, MAPHEX, and stripping in packed bed, reveales to be cost-effective. Since the economic losses due to the harmful effects of nitrogen into the environment are estimated at 32-35 USD per kilogram of nitrogen released, nitrogen recycling is an environmentally and economically beneficial approach to reduce nutrient pollution caused by livestock operations.

Bayesian Symbolic Learning to Build Analytical Correlations from Rigorous Process Simulations: Application to CO2 Capture Technologies

Process modeling has become a fundamental tool to guide experimental work. Unfortunately, process models based on first principles can be expensive to develop and evaluate, and hard to use, particularly when convergence issues arise. This work proves that Bayesian symbolic learning can be applied to derive simple closed-form expressions from rigorous process simulations, streamlining the process modeling task and making process models more accessible to experimental groups. Compared to conventional surrogate models, our approach provides analytical expressions that are easier to communicate and manipulate algebraically to get insights into the process. We apply this method to synthetic data obtained from two basic CO₂ capture processes simulated in Aspen HYSYS, identifying accurate simplified interpretable equations for key variables dictating the process economic and environmental performance. We then use these expressions to analyze the process variables' elasticities and benchmark an emerging CO₂ capture process against the business as usual technology.

A Comparative Study of Demand Forecasting Models for a Multi-Channel Retail Company: A Novel Hybrid Machine Learning Approach

Demand forecasting has been a major concern of operational strategy to manage the inventory and optimize the customer satisfaction level. The researchers have proposed many conventional and advanced forecasting techniques, but no one leads to complete accuracy. Forecasting is equally important in manufacturing as well as retail companies. In this study, the performances of five regression techniques of machine learning, viz. random forest (RF), extreme gradient boosting (XGBoost), gradient boosting, adaptive boosting (AdaBoost), and artificial neural network (ANN) algorithms, are compared with a proposed hybrid (RF-XGBoost-LR) model for sales forecasting of a retail chain considering the various parameters of forecasting accuracy. The weekly sales data of a US-based retail company is considered in the analysis of the forecasts undertaking the attributes affecting the sale such as the temperature of the region and the size of the store. It is observed that the hybrid RF-XGBoost-LR outperformed the other models measured against various metrics of performance. This study may help the industry decision-maker to understand and improve the methods of forecasting.

Industrial data science – a review of machine learning applications for chemical and process industries

Understand and optimize industrial processes via machine learning and chemical engineering principles.

Compensating Data Shortages in Manufacturing with Monotonicity Knowledge

Systematic decision making in engineering requires appropriate models. In this article, we introduce a regression method for enhancing the predictive power of a model by exploiting expert knowledge in the form of shape constraints, or more specifically, monotonicity constraints. Incorporating such information is particularly useful when the available datasets are small or do not cover the entire input space, as is often the case in manufacturing applications. We set up the regression subject to the considered monotonicity constraints as a semi-infinite optimization problem, and propose an adaptive solution algorithm. The method is applicable in multiple dimensions and can be extended to more general shape constraints. It was tested and validated on two real-world manufacturing processes, namely, laser glass bending and press hardening of sheet metal. It was found that the resulting models both complied well with the expert’s monotonicity knowledge and predicted the training data accurately. The suggested approach led to lower root-mean-squared errors than comparative methods from the literature for the sparse datasets considered in this work.

Statistical Machine Learning in Model Predictive Control of Nonlinear Processes

Recurrent neural networks (RNNs) have been widely used to model nonlinear dynamic systems using time-series data. While the training error of neural networks can be rendered sufficiently small in many cases, there is a lack of a general framework to guide construction and determine the generalization accuracy of RNN models to be used in model predictive control systems. In this work, we employ statistical machine learning theory to develop a methodological framework of generalization error bounds for RNNs. The RNN models are then utilized to predict state evolution in model predictive controllers (MPC), under which closed-loop stability is established in a probabilistic manner. A nonlinear chemical process example is used to investigate the impact of training sample size, RNN depth, width, and input time length on the generalization error, along with the analyses of probabilistic closed-loop stability through the closed-loop simulations under Lyapunov-based MPC.

Towards the Development of Digital Twins for the Bio-manufacturing Industry

The bio-manufacturing industry, along with other process industries, now has the opportunity to be engaged in the latest industrial revolution, also known as Industry 4.0. To successfully accomplish this, a physical-to-digital-to-physical information loop should be carefully developed. One way to achieve this is, for example, through the implementation of digital twins (DTs), which are virtual copies of the processes. Therefore, in this paper, the focus is on understanding the needs and challenges faced by the bio-manufacturing industry when dealing with this digitalized paradigm. To do so, two major building blocks of a DT, data and models, are highlighted and discussed. Hence, firstly, data and their characteristics and collection strategies are examined as well as new methods and tools for data processing. Secondly, modelling approaches and their potential of being used in DTs are reviewed. Finally, we share our vision with regard to the use of DTs in the bio-manufacturing industry aiming at bringing the DT a step closer to its full potential and realization.

DOMINO: Data-driven Optimization of bi-level Mixed-Integer NOnlinear Problems

The Data-driven Optimization of bi-level Mixed-Integer NOnlinear problems (DOMINO) framework is presented for addressing the optimization of bi-level mixed-integer nonlinear programming problems. In this framework, bi-level optimization problems are approximated as single-level optimization problems by collecting samples of the upper-level objective and solving the lower-level problem to global optimality at those sampling points. This process is done through the integration of the DOMINO framework with a grey-box optimization solver to perform design of experiments on the upper-level objective, and to consecutively approximate and optimize bi-level mixed-integer nonlinear programming problems that are challenging to solve using exact methods. The performance of DOMINO is assessed through solving numerous bi-level benchmark problems, a land allocation problem in Food-Energy-Water Nexus, and through employing different data-driven optimization methodologies, including both local and global methods. Although this data-driven approach cannot provide a theoretical guarantee to global optimality, we present an algorithmic advancement that can guarantee feasibility to large-scale bi-level optimization problems when the lower-level problem is solved to global optimality at convergence.

Knowledge based recursive non-linear partial least squares (RNPLS)

Soft sensors driven by data are very common in industrial plants to perform indirect measurements of difficult to measure critical variables by using other variables that are relatively easier to obtain. The use of soft sensors implies some challenges, such as the colinearity of the predictor variables, the time-varying and possible non-linear nature of the industrial process. To deal with the first challenge, the partial least square (PLS) regression has been employed in many applications to model the linear relations between process variables, with noisy and highly correlated data. However, the PLS model needs to deal with the other two issues: the non-linear and time-varying characteristics of the processes. In this work, a new knowledge-based methodology for a recursive non-linear PLS algorithm (RNPLS) is systematized to deal with these issues. Here, the non-linear PLS algorithm is set up by carrying out the PLS regression over the augmented input matrix, which includes knowledge based non-linear transformations of some of the variables. This transformation depends on the system's nature, and takes into account the available knowledge about the process, which is provided by expert knowledge or emulated using software tools. Then, the recursive exponential weighted PLS is used to modify and adapt the model according to the process changes. This RNPLS algorithm has been tested using two case studies according to the available knowledge, a real industrial evaporation station of the sugar industry, where the expert knowledge about the process permits the formulation of the relationships, and a simulated wastewater treatment plant, where the necessary knowledge about the process is obtained by a software tool. The results show that the methodology involving knowledge regarding the process is able to adjust the process changes, providing highly accurate predictions.

Introduction to Metamodeling for Reducing Computational Burden of Advanced Analyses with Health Economic Models: A Structured Overview of Metamodeling Methods in a 6-Step Application Process

Metamodels can be used to reduce the computational burden associated with computationally demanding analyses of simulation models, although applications within health economics are still scarce. Besides a lack of awareness of their potential within health economics, the absence of guidance on the conceivably complex and time-consuming process of developing and validating metamodels may contribute to their limited uptake. To address these issues, this article introduces metamodeling to the wider health economic audience and presents a process for applying metamodeling in this context, including suitable methods and directions for their selection and use. General (i.e., non-health economic specific) metamodeling literature, clinical prediction modeling literature, and a previously published literature review were exploited to consolidate a process and to identify candidate metamodeling methods. Methods were considered applicable to health economics if they are able to account for mixed (i.e., continuous and discrete) input parameters and continuous outcomes. Six steps were identified as relevant for applying metamodeling methods within health economics: 1) the identification of a suitable metamodeling technique, 2) simulation of data sets according to a design of experiments, 3) fitting of the metamodel, 4) assessment of metamodel performance, 5) conducting the required analysis using the metamodel, and 6) verification of the results. Different methods are discussed to support each step, including their characteristics, directions for use, key references, and relevant R and Python packages. To address challenges regarding metamodeling methods selection, a first guide was developed toward using metamodels to reduce the computational burden of analyses of health economic models. This guidance may increase applications of metamodeling in health economics, enabling increased use of state-of-the-art analyses (e.g., value of information analysis) with computationally burdensome simulation models.