On the use of machine learning methods to predict component reliability from data-driven industrial case studies

The reliability estimation of engineered components is fundamental for many optimization policies in a production process. The main goal of this paper is to study how machine learning models can fit this reliability estimation function in comparison with traditional approaches (e.g., Weibull distribution). We use a supervised machine learning approach to predict this reliability in 19 industrial components obtained from real industries. Particularly, four diverse machine learning approaches are implemented: artificial neural networks, support vector machines, random forest, and soft computing methods. We evaluate if there is one approach that outperforms the others when predicting the reliability of all the components, analyze if machine learning models improve their performance in the presence of censored data, and finally, understand the performance impact when the number of available inputs changes. Our experimental results show the high ability of machine learning to predict the component reliability and particularly, random forest, which generally obtains high accuracy and the best results for all the cases. Experimentation confirms that all the models improve their performance when considering censored data. Finally, we show how machine learning models obtain better prediction results with respect to traditional methods when increasing the size of the time-to-failure datasets.