The automotive industry is rapidly transitioning towards Industry 4.0, transforming vehicle manufacturing. To achieve a lower carbon footprint, it is crucial to minimize raw material wastage and energy consumption. Reducing component wastage, lead time, and automating gear manufacturing are key areas. Gear micro-geometry inspection is vital, as variations affect service life and NVH (Noise, Vibration, Harshness). Despite standards for permissible errors, manual evaluation is often needed.This subjective evaluation approach will have a possibility that a gear with undesired variations gets assembled into the product. These issues can be detected during NVH testing, leading to replacement of part and re-assembly thus increasing lead time.
This generates a need for an automated system which could reduce the human intervention and perform the activity. This paper discusses methodologies to meet these requirements and achieve desired results. The research aims to develop a deep learning-based model to eliminate the ambiguity of manual evaluation of microgeometry errors and qualify gears using trained data.
In this research we have identified three best possible models used in image classification tasks – Random Forest algorithm, XGBoost algorithm, and Convolutional Neural Network. The dataset is used to train these models, perform hyperparameter tuning, and obtain optimal results based on the confusion matrix, precision, recall, F1 score, and validation accuracy.
Conclusion :
This paper explores the use of deep learning techniques to predict gear quality, aiming to minimize human intervention, reduce rework, and enhance productivity. By comparing various machine learning methods, the study identifies the most effective approach for gear manufacturing and measurement. The findings highlight the transformative potential of deep learning in gear production, promising economic savings and improved efficiency.