Optimal Parameter Design for Power Electronic Converters Using a Probabilistic Learning-Based Stochastic Surrogate Model

TL;DR

This paper presents a probabilistic learning framework using neural networks and heuristic optimization to efficiently design power electronic converters, balancing efficiency and thermal safety with improved accuracy and reduced design time.

Contribution

It introduces a novel stochastic surrogate modeling approach that combines classification, probabilistic prediction, and heuristic optimization for power converter design.

Findings

Enhanced predictive accuracy over traditional methods

Effective multi-objective optimization balancing efficiency and thermal constraints

Comparison shows superior performance of the proposed heuristic optimization approach

Abstract

The selection of optimal design for power electronic converter parameters involves balancing efficiency and thermal constraints to ensure high performance without compromising safety. This paper introduces a probabilistic-learning-based stochastic surrogate modeling framework to address this challenge and significantly reduce the time required during the design phase. The approach begins with a neural network classifier that evaluates the feasibility of parameter configurations, effectively filtering out unsafe and/or impractical inputs. Subsequently, a probabilistic prediction model estimates the converter's efficiency and temperature while quantifying prediction uncertainty, providing both performance insights and reliability metrics. Finally, a heuristic optimization-based model is employed to optimize a multi-objective function that maximizes efficiency while adhering to thermal constraints. The optimization process incorporates penalty terms to discourage solutions that violate practical thresholds, ensuring actionable and realistic recommendations. An advanced heuristic optimization method is used to find the optimal solution and is compared with several well-known search algorithms, including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Simulated Annealing (SA), Tabu-Search (TS), and Stochastic Hill Climbing (SHC). The results demonstrate significant improvements in predictive accuracy and optimization outcomes, offering a robust solution for advancing power electronics design.