Data-Driven Constraint Handling in Multi-Objective Inductor Design

Abstract

This paper analyses the multi-objective design of an inductor for a DC-DC buck converter. The core volume and total losses are the two competing objectives, which should be minimised while satisfying the design constraints on the required differential inductance profile and the maximum overheating. The multi-objective optimisation problem is solved by means of a population-based metaheuristic algorithm based on Artificial Immune Systems (AIS). Despite its effectiveness in finding the Pareto front, the algorithm requires the evaluation of many candidate solutions before converging. In the case of the inductor design problem, the evaluation of a configuration is time-consuming. In fact, a non-linear iterative technique (fixed point) is needed to obtain the differential inductance profile of the configuration, as it may operate in conditions of partial saturation. However, many configurations evaluated during an optimisation do not comply with the design constraint, resulting in expensive and unnecessary calculations. Therefore, this paper proposes the adoption of a data-driven surrogate model in a pre-selection phase of the optimisation. The adopted model should classify newly generated configurations as compliant or not with the design constraint. Configurations classified as unfeasible are disregarded, thus avoiding the computational burden of their complete evaluation. Interesting results have been obtained, both in terms of avoided configuration evaluations and the quality of the Pareto front found by the optimisation procedure.

A Comprehensive Review of Bio-Inspired Optimization Algorithms Including Applications in Microelectronics and Nanophotonics

“…Improvement of photoelectric performance of thin film solar cells [184] Optimization of nanosecond laser processing [185] VLSI floor planning optimization regarding measures such as area, wire length and dead space between modules [186] Lifetime reliability, performance and power consumption of heterogeneous multiprocessor embedded systems [187] MO Particle Swarm Optimization Review of many applications of MO PSO in diverse areas [188] Floor planning of the VLSI circuit and layout area minimization using MO PSO [189] MO Ant Colony Optimization A 3D printed bandpass frequency-selective surface structure with desired center frequency and bandwidth [190] Analog filter design [191] Multi-criteria optimization for VLSI floor planning [192] Artificial Bee Colony Area and power optimization for logic circuit design [193] Design of digital filters [194] Artificial Immune System Spectrum management and design of 6G networks [195] Multi-objective design of an inductor for a DC-DC buck converter [196] Differential Evolution Geometry optimization of high-index dielectric nanostructures [197] Multi-objective synchronous modeling and optimal solving of an analog IC [198] Firefly Algorithm Reducing heat generation, sizing and interconnect length for VLSI floor planning [199] Secure routing for fog-based wireless sensor networks [200] Cuckoo Search Multi-objective-derived energy-efficient routing in wireless sensor networks [201] Parameter extraction of photovoltaic cell based on a multi-objective approach [202] MO Grey Wolf Optimizer Electrochemical micro-drilling in MEMS [203] Multi-objective task scheduling in cloud-fog computing [204] Besides using metaheuristic algorithms, multi-objective optimization can be implemented using machine learning techniques such as artificial neural networks (multi-layer perceptrons), convolutional neural networks and recurrent neural networks.…”