Parameterization techniques to support human learning curves forecasting & optimization: Review, method & proposed framework

Abstract

A state-of-the-art literature review was conducted to explore the latest advancements in parameterization techniques to facilitate the effective and efficient modelling of human learning curve models. Findings helped to select the best techniques for parameterizing workers’ learning curves. Understanding and analyzing the learning curve of human-based manufacturing operations is highly important for production managers aiming to optimize workforce performance and enhance the productivity of manual and semi-automated manufacturing systems. Effective forecasting of workers’ performance rates based on accurate learning curves is crucial for achieving optimal workforce capacity utilization as it evolves to efficiently meet production objectives. However, most existing learning curve evaluation methods rely on standard values for the learning rate of different operations, which may not accurately capture the actual improvement pace of workers. The learning rates in human-based manufacturing operations can vary based on factors such as previous worker experience, operation complexity, and working conditions. To address this challenge, this research paper introduces a Human Learning Curve Forecasting & Optimization (HLCF&O) framework that combines advanced parameterization techniques with data simplification methods to streamline the calculation and updating processes of a worker learning curve.