Análise de Perdas da Linha de Montagem em uma Indústria Automotiva

Abstract

This work presents an innovative approach to analyzing losses in the assembly line of an automotive industry, aiming to optimize the efficiency of the production process. The proposed methodology uses the XGBoost machine learning algorithm in conjunction with feature engineering techniques. Loss analysis is crucial to identify and mitigate problems that impact productivity and quality in automotive production. XGBoost, a decision tree-based machine learning algorithm, is chosen because of its ability to efficiently deal with complex data sets and large volumes of information. The feature engineering phase plays a crucial role in selecting relevant features to better capture the nuances of the assembly process. The experimental results demonstrate the effectiveness of the proposed approach in detecting and preventing losses on the assembly line. The XGBoost model, trained with historically relevant data, is capable of anticipating potential failures, allowing proactive interventions to avoid interruptions in the production process.