Smart Spare Parts (SSP): Artificial Intelligence and Additive Manufacturing Applied to Predictive Maintenance in Industry 4.0

Smart spare parts (SSPs) emerge as an alternative to strengthen predictive maintenance in Industry 4.0, by incorporating sensors that monitor variables such as temperature, vibration, and force during operation. This chapter focuses on the manufacturing of SSPs using additive manufacturing, analyzing the technology, functional materials, machine learning algorithms, and integration methods such as the Stop-and-Go technique. The goal is to minimize the component’s mechanical strength and improve the interaction between the sensors and the variables of interest, thereby increasing the quality of the collected data for subsequent predictive analysis. The results demonstrate the feasibility of integrating sensors directly during 3D printing, allowing for the generation of complex cavities without the need for external elements and reducing the component’s mechanical strength. Furthermore, it is observed that the use of materials with electrical or magnetic properties allows the variables of interest to be measured without intervening in the part. However, technical challenges related to data processing and transmission remain. It is concluded that the combination of additive manufacturing and artificial intelligence offers opportunities for the manufacture of SSPs, provided that advances are made in the materials used in additive manufacturing, machine learning algorithms, and subsequent processes, thereby improving aspects such as data quality, mechanical performance, and sensor performance.