Big Data architecture for intelligent maintenance: a focus on query processing and machine learning algorithms

Exploiting available condition monitoring data of industrial machines for intelligent maintenance purposes has been attracting attention in various application fields. Machine learning algorithms for fault detection, diagnosis and prognosis are popular and easily accessible. However, our experience in working at the intersection of academia and industry showed that the major challenges of building an end-to-end system in a real-world industrial setting go beyond the design of machine learning algorithms. One of the major challenges is the design of an end-to-end data management solution that is able to efficiently store and process large amounts of heterogeneous data streams resulting from a variety of physical machines. In this paper we present the design of an end-to-end Big Data architecture that enables intelligent maintenance in a real-world industrial setting. In particular, we will discuss various physical design choices for optimizing high-dimensional queries, such as partitioning and Z-ordering, that serve as the basis for health analytics. Finally, we describe a concrete fault detection use case with two different health monitoring algorithms based on machine learning and classical statistics and discuss their advantages and disadvantages. The paper covers some of the most important aspects of the practical implementation of such an end-to-end solution and demonstrates the challenges and their mitigation for the specific application of laser cutting machines.