Robust design using multiobjective optimisation and artificial neural networks with application to a heat pump radial compressor

Although robustness is an important consideration to guarantee the performance of designs under deviation, systems are often engineered by evaluating their performance exclusively at nominal conditions. Robustness is sometimes evaluated a posteriori through a sensitivity analysis, which does not guarantee optimality in terms of robustness. This article introduces an automated design framework based on multiobjective optimisation to evaluate robustness as an additional competing objective. Robustness is computed as a sampled hypervolume of imposed geometrical and operational deviations from the nominal point. In order to address the high number of additional evaluations needed to compute robustness, artificial neutral networks are used to generate fast and accurate surrogates of high-fidelity models. The identification of their hyperparameters is formulated as an optimisation problem. In the frame of a case study, the developed methodology was applied to the design of a small-scale turbocompressor. Robustness was included as an objective to be maximised alongside nominal efficiency and mass-flow range between surge and choke. An experimentally validated 1D radial turbocompressor meanline model was used to generate the training data. The optimisation results suggest a clear competition between efficiency, range and robustness, while the use of neural networks led to a speed-up by four orders of magnitude compared to the 1D code.

Is Our Archiving Reliable? Multiobjective Archiving Methods on “Simple” Artificial Input Sequences

In evolutionary multiobjective optimisation ( EMO ), archiving is a common component that maintains an (external or internal) set during the search process, typically with a fixed size, in order to provide a good representation of high-quality solutions produced. Such an archive set can be used solely to store the final results shown to the decision maker, but in many cases may participate in the process of producing solutions (e.g., as a solution pool where the parental solutions are selected). Over the last three decades, archiving stands as an important issue in EMO, leading to the emergence of various methods such as those based on Pareto, indicator, or decomposition criteria. Such methods have demonstrated their effectiveness in literature and have been believed to be good options to many problems, particularly those having a regular Pareto front shape, e.g., a simplex shape. In this article, we challenge this belief. We do this through artificially constructing several sequences with extremely simple shapes, i.e., 1D/2D simplex Pareto front. We show the struggle of predominantly used archiving methods which have been deemed to well handle such shapes. This reveals that the order of solutions entering the archive matters, and that current EMO algorithms may not be fully capable of maintaining a representative population on problems with linear Pareto fronts even in the case that all of their optimal solutions can be found.

Multiobjective optimisation and cluster analysis in placement of best management practices in an urban flooding scenario

Urban floods cause massive damage to infrastructure and loss of life. This research is being carried out to study how Best Management Practices (BMPs) can mitigate the negative effects of urban floods during extreme rainfall events. Strategically placing BMPs throughout open areas and rooftops in urban areas serves multiple purposes of storage of rainwater, removal of pollutants from surface runoff and sustainable utilisation of land. This situation is framed as a multiobjective optimisation problem to analyse the trade-offs between multiple goals of runoff reduction, construction cost and pollutant load reduction. Output includes a wide range of choices to choose from for decision makers. Proposed methodology is demonstrated with a case study of Greater Hyderabad Municipal Corporation (GHMC), India. Historical extreme rainfall event of 237.5 mm which occurred in year 2016 and extreme rainfall event of 1,740.62 mm corresponding to Representative Concentration Pathway (RCP) 2.6 were considered for analysis. Two multiobjective optimisation algorithms, namely, Non-dominated Sorting Genetic Algorithm – III (NSGA-III) and Constrained Two-Archive Evolutionary Algorithm (C-TAEA) are employed to solve the BMP placement problem, following which the resulting pareto-fronts are ensembled. K-Medoids-based cluster analysis is performed on the resulting ensembled pareto-front. The proposed ensembled approach identified ten possible BMP configurations with costs ranging from Rs. to surface runoff reduction ranging from to and pollutant load removal ranging from tonnes. Use of BMPs in future event has the potential to reduce surface runoff from , while simultaneously removing tonnes of pollutants for cost ranging from The proposed framework forms an effective and novel way to characterise and solve BMP optimisation problems in context of climate change, presenting a view of the urban flooding scenario today, and the likely course of events in the future.