A Multidimensional Time-series Association Rules Algorithm based on Spark

Fault prediction of industrial systems has been a hot research orientation in recent years, which allows the maintainer to know the operation conditions and the fault to be occurred in advance so as to reduce the risk of fault and the economic loss. In general, association rules learning is one of the most effective methods in fault prediction of industrial systems, however, traditional methods based on association rules are not suitable for sparse time-series data that are common in industrial systems (e.g. transmission line data). Although some methods based on clustering to reduce the dimension of data have been proposed, these methods may lose some of the key rules from the dataset and reduce the effectiveness of the results. In order to solve the problem, we propose a novel algorithm called Multidimensional Time-series Association Rules(MTAR) in this paper, which can fully utilize the information and find out more valuable rules from multidimensional time-series data. Meanwhile, we implement the parallelization of the algorithm based on the parallel computing framework Spark, which can improve the performance of the algorithm greatly. Experiments are conducted on the transmission line dataset in Power Grid System to show the effectiveness and the efficiency of the proposed approach.