Evaluation of Artificial Intelligence Methods for Lead Time Prediction in Non-Cycled Areas of Automotive Production

TL;DR

This study evaluates AI techniques for predicting lead times in automotive production, demonstrating that ensemble learning methods like LightGBM can achieve up to 90% accuracy and are valuable for process control.

Contribution

It introduces a tailored AI approach using ensemble classifiers for lead time prediction in non-cycled automotive production areas, emphasizing hyperparameter tuning and model retraining.

Findings

LightGBM achieves up to 90% prediction accuracy.

Ensemble learning methods outperform traditional approaches.

Periodic retraining improves model accuracy over time.

Abstract

The present study examines the effectiveness of applying Artificial Intelligence methods in an automotive production environment to predict unknown lead times in a non-cycle-controlled production area. Data structures are analyzed to identify contextual features and then preprocessed using one-hot encoding. Methods selection focuses on supervised machine learning techniques. In supervised learning methods, regression and classification methods are evaluated. Continuous regression based on target size distribution is not feasible. Classification methods analysis shows that Ensemble Learning and Support Vector Machines are the most suitable. Preliminary study results indicate that gradient boosting algorithms LightGBM, XGBoost, and CatBoost yield the best results. After further testing and extensive hyperparameter optimization, the final method choice is the LightGBM algorithm. Depending on feature availability and prediction interval granularity, relative prediction accuracies of up to 90% can be achieved. Further tests highlight the importance of periodic retraining of AI models to accurately represent complex production processes using the database. The research demonstrates that AI methods can be effectively applied to highly variable production data, adding business value by providing an additional metric for various control tasks while outperforming current non AI-based systems.