Profiling industrial vehicle duties using CAN bus signal segmentation and clustering

Industrial vehicles working in construction sites show rather heterogeneous usage patterns. Depending on its type, model, and context of usage, the vehicle workload may vary from light to heavy with variable periodicity. Duties summarize the current state of a vehicle according to its usage level. They are usually set up manually vehicle by vehicle according to the specifications of the manufacturer. To automate the definition of per-vehicle duty levels, this paper explores the use of clustering techniques applied to CAN bus signals. It first performs a segmentation of the CAN bus signals to identify specific working cycles. Then, it clusters the segments to support the definition of vehicle-specific duty levels. The preliminary results, acquired on real vehicle usage data, show the applicability of the proposed approach.