Management of the Integration of aRtificial Intelligence Systems in the Optimization of Noise, Vibration, and Harshness (NVH) Performance for ABS Braking Units

The growing need to improve noise, vibration, and harshness (NVH) performance in anti-lock braking systems (ABS) has intensified researchers’ interest in identifying new methods capable of complementing and surpassing the limitations of traditional analytical and experimental approaches. The acoustic and vibrational phenomena generated during braking significantly influence vehicle comfort, perceived quality, and system validation processes, while the complexity of modern braking architectures amplifies the limitations of deterministic NVH models. In this context, artificial intelligence (AI) appears to be one of the most effective and cost-efficient methods for improving NVH prediction, analysis, and optimization. The overall objective of this study is to establish a framework that outlines how AI-based techniques integrate into NVH evaluation workflows. To achieve this, the research analyzes current NVH challenges, synthesizes theoretical and operational definitions relevant to intelligent modeling, and examines the contributions of supervised, unsupervised, and hybrid algorithmic strategies. The methodology combines qualitative evaluation of the literature with quantitative analysis of experimental braking datasets, together with data preprocessing, feature extraction, and interpretable, robust predictive models. The study highlights the strategic potential of AI for improving NVH assessment, enhancing prediction accuracy, supporting adaptive decision-making, and reducing testing efforts. Although AI is not implemented at this stage, the resulting framework lays the groundwork for future development and validates the relevance, feasibility, and expected benefits of intelligent approaches to optimizing NVH performance in anti-lock braking systems.