Multi-objective optimization algorithms are becoming ever more popular in the field of electrical machine design as they provide engineers with an automated way efficiently exploring huge spaces when searching for machines that simultaneously highly competitive regarding several objectives, such efficiency, material costs, torque ripple, and others. Apart from exhibiting these good target characteristics, a should also be robust, i.e., it not very sensitive to slight changes its parameters...

This paper deals with accelerating typical optimization scenarios for electrical machine designs. Besides the advantage of a reduced computation time, this leads to reduction in computational power and thus lower consumption when running optimization. If machines high density are required, usually highly utilized assemblies that feature nonlinear characteristics obtained. Optimization considered where evaluation potential design requires computationally expensive finite element (FE)...

The past five years have seen rapid development of plans and test pilots aimed at introducing connected autonomous vehicles (CAVs) in public transport systems around the world. While self-driving technology is still being perfected, authorities are increasingly interested ability to model optimize benefits adding CAVs existing multi-modal systems. Using a real-world scenario from Leeds Metropolitan Area as case study, we demonstrate an effective way combining macro-level mobility simulations...

In this paper, we demonstrate the application of features from landscape analysis, initially proposed for multi-objective combinatorial optimisation, to a benchmark set 1 200 randomly-generated multiobjective interpolated continuous optimisation problems (MO-ICOPs). We also explore benefits evaluating considered on basis fixed-size sampling search space. This allows fine control over cost when aiming an efficient feature-based automated performance prediction and algorithm selection. While...

The task of designing electrical drives is a multi-objective optimization problem (MOOP) that remains very slow even when using state-of-the-art approaches like particle swarm and evolutionary algorithms because the fitness function used to assess quality proposed design based on time-intensive finite element (FE) simulations. One straightforward solution replace original FE-based with much faster-to-evaluate surrogate. In our particular case each scenario poses rather unique challenges...

This article deals with accelerating typical optimization scenarios for electrical machine designs. Besides the advantage of a reduced computation time, this leads to reduction in computational power and thus lower consumption when running optimization. If high density is required, usually highly-utilized machines which feature nonlinear characteristics are applied. As consequence, typically considered where evaluation potential design requires computationally expensive finite element (FE)...

By employing state-of-the-art automated design and optimization techniques from the field of evolutionary computation, engineers are able to discover electrical machine designs that highly competitive with respect several objectives like efficiency, material costs, torque ripple others. Apart being Pareto-optimal, a good must also be quite robust, i.e., it not sensitive regard its parameters as this would severely increase manufacturing costs or make physical exhibit characteristics very...

We present an effective optimization strategy for industrial batch processes that is centered around two computational intelligence methods: linear and non-linear predictive mappings (surrogate models) quality control (QC) indicators state-of-the-art multi-objective evolutionary algorithms (MOEAs). The proposed construction methodology of the neural network-based integrates implicit expert-based knowledge with a new data-driven sample selection hybridizes several design experiments...

Purpose The paper aims to raise awareness in the industry of design automation tools, especially early phases, by demonstrating along a case study seamless integration prototypically implemented optimization, supporting space exploration phase and an operational use product configurator, drafting detailing solution predominantly later phase. Design/methodology/approach Based on comparison modeled as-is to-be processes ascent assembly designs with without roadmap is developed. Using...

In this paper, a central step in predictive maintenance within chip production systems is addressed, that is, to predict the quality of items (microfluidics chips) at an early stage. The criteria (flatness six nest positions) only measured from time due semi-manual inspection, which leads high-dimensional batch process forecast modeling problem, based on trends continuously data. Therefore time-series transformation for dimension reduction applied with usage partial least squares (PLS),...

We address the problem of predicting product quality for a latter stage in production process already at an early stage. Thereby, idea is to use time-series values, recorded during on-line and containing possible system dynamics variations according parameter settings or different environmental conditions, as input predict final criteria apply non-linear partial least squares (PLS) variant reducing high dimensionality batch-process problems, by combining PLS with generalized Takagi-Sugeno...

We present an effective optimization strategy that is capable of discovering high-quality cost-optimal solution for two-dimensional (2D) path network layouts (i.e., groups obstacle-avoiding Euclidean Steiner trees) that, among other applications, can serve as templates complete ascent assembly structures (CAA-structures). The main innovative aspect our approach aim not restricted to simply synthesizing optimal designs with regard a given goal, but we also strive discover the best tradeoffs...

We describe two enhancements that significantly improve the rapid convergence behavior of DECM02 - a previously proposed robust coevolutionary algorithm integrates three different multi-objective space exploration paradigms: differential evolution, two-tier Pareto-based selection for survival and decomposition-based evolutionary guidance. The first enhancement is refined active search adaptation mechanism relies on run-time sub-population performance indicators to estimate stage dynamically...