Multi-objective constrained optimization for energy applications via tree ensembles

Thebelt, Alexander; Tsay, Calvin; Lee, Robert M.; Sudermann‐Merx, Nathan; Walz, D.; Tranter, Thomas G.; Misener, Ruth

doi:10.1016/j.apenergy.2021.118061

Cited by 15 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a multi-objective genetic algorithm to find the Pareto Frontier of multi-objective performance in the prediction results can solve the problem of searching for elements of material composition ( Bao et al, 2022 ). Combined with adaptive iterative methods for model uncertainty-based material screening, optimized material compositions or processes can be identified, guiding materials research ( Chen H. et al, 2022 ; Thebelt et al, 2022 ). In the context of multi-objective performance requirements, the application of machine learning to the field of high-entropy alloys is particularly critical, such as the co-optimization of strength and corrosion resistance of high-strength and corrosion-resistant high-entropy alloys, the co-optimization of density and strong toughness properties of lightweight high-entropy alloys, the co-optimization of high-temperature strength and oxidation resistance properties needed for refractory high-entropy alloys, and the co-optimization of biocompatibility, mechanical properties matching those of living organisms, and excellent corrosion resistance required for biological high-entropy alloys.…”

Section: Component Design Theory and Simulation Studiesmentioning

confidence: 99%

Bio-high entropy alloys: Progress, challenges, and opportunities

Feng

Tang

Liu

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

With the continuous progress and development in biomedicine, metallic biomedical materials have attracted significant attention from researchers. Due to the low compatibility of traditional metal implant materials with the human body, it is urgent to develop new biomaterials with excellent mechanical properties and appropriate biocompatibility to solve the adverse reactions caused by long-term implantation. High entropy alloys (HEAs) are nearly equimolar alloys of five or more elements, with huge compositional design space and excellent mechanical properties. In contrast, biological high-entropy alloys (Bio-HEAs) are expected to be a new bio-alloy for biomedicine due to their excellent biocompatibility and tunable mechanical properties. This review summarizes the composition system of Bio-HEAs in recent years, introduces their biocompatibility and mechanical properties of human bone adaptation, and finally puts forward the following suggestions for the development direction of Bio-HEAs: to improve the theory and simulation studies of Bio-HEAs composition design, to quantify the influence of composition, process, post-treatment on the performance of Bio-HEAs, to focus on the loss of Bio-HEAs under actual service conditions, and it is hoped that the clinical application of the new medical alloy Bio-HEAs can be realized as soon as possible.

show abstract

Section: Component Design Theory and Simulation Studiesmentioning

confidence: 99%

Bio-high entropy alloys: Progress, challenges, and opportunities

Feng

Tang

Liu

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…A recent overview of methods to identify the feasible regions in optimization problems via trained machine learning classifiers can be found in Maragno et al (2021), who present it as a more general framework for data-driven optimization. The works (Mistry et al 2021;Thebelt et al 2021Thebelt et al , 2020Ceccon et al 2022;Thebelt et al 2022) deal with the integration of trained gradient-boosted regression trees into optimization models stemming from different applications. There the distribution of the training data, that influences the prediction accuracy is integrated as a penalty term into the objective function to minimise risk.…”

Section: Literature Reviewmentioning

confidence: 99%

Optimization over decision trees: a case study for the design of stable direct-current electricity networks

et al. 2023

View full text Add to dashboard Cite

In many real-world mixed-integer optimization problems from engineering, the side constraints can be subdivided into two categories: constraints which describe a certain logic to model a feasible allocation of resources (such as a maximal number of available assets, working time requirements, maintenance requirements, contractual obligations, etc.), and constraints which model physical processes and the related quantities (such as current, pressure, temperature, etc.). While the first type of constraints can often easily be stated in terms of a mixed-integer program (MIP), the second part may involve the incorporation of complex non-linearities, partial differential equations or even a black-box simulation of the involved physical process. In this work, we propose the integration of a trained tree-based classifier—a decision-tree or a random forest, into a mixed-integer optimization model as a possible remedy. We assume that the classifier has been trained on data points produced by a detailed simulation of a given complex process to represent the functional relationship between the involved physical quantities. We then derive MIP-representable reformulations of the trained classifier such that the resulting model can be solved using state-of-the-art solvers. At the hand of several use cases in terms of possible optimization goals, we show the broad applicability of our framework that is easily extendable to other tasks beyond engineering. In a detailed real-world computational study for the design of stable direct-current power networks, we demonstrate that our approach yields high-quality solutions in reasonable computation times.

show abstract

“…Other GP-based approaches were applied for tissue engineering (Olofsson et al, 2018), solar cell material optimization (Herbol et al, 2018), and optimization of sustainable algal production (Bradford et al, 2018b). Other data-driven model-based design of experiment approaches use tree ensembles (Mistry et al, 2020;Thebelt et al, 2021Thebelt et al, , 2022 and algebraic basis functions (Wilson and Sahinidis, 2017) to predict new promising points for evaluation.…”

Section: How This Type Of Data Is Addressed In the Literaturementioning

confidence: 99%

Maximizing information from chemical engineering data sets: Applications to machine learning

Thebelt,

Wiebe,

Kronqvist

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

It is well-documented how artificial intelligence can have (and already is having) a big impact on chemical engineering. But classical machine learning approaches may be weak for many chemical engineering applications. This review discusses how challenging data characteristics arise in chemical engineering applications. We identify four characteristics of data arising in chemical engineering applications that make applying classical artificial intelligence approaches difficult: (1) high variance, low volume data, (2) low variance, high volume data, (3) noisy/corrupt/missing data, and (4) restricted data with physics-based limitations. For each of these four data characteristics, we discuss applications where these data characteristics arise and show how current chemical engineering research is extending the fields of data science and machine learning to incorporate these challenges. Finally, we identify several challenges for future research.

show abstract

Multi-objective constrained optimization for energy applications via tree ensembles

Cited by 15 publications

References 47 publications

Bio-high entropy alloys: Progress, challenges, and opportunities

Bio-high entropy alloys: Progress, challenges, and opportunities

Optimization over decision trees: a case study for the design of stable direct-current electricity networks

Maximizing information from chemical engineering data sets: Applications to machine learning

Contact Info

Product

Resources

About