Product delivery via logistic systems is becoming more efficient, rapidly and continuously bringing products to the customer. The continuous operation of logistic equipment, however, can lead to mechanical stoppages due to excessive use. To avoid system failures, fatigue in each part of the system should be monitored, enabling the accurate prediction of potential stoppages and thus promoting overall system efficiency. To date, various kinds of anomaly-detection methodologies have been proposed. Among them, the Mahalanobis–Taguchi method, which simply describes the extent of a failure using the Mahalanobis distance, has been utilized to detect changes in the mechanical condition of facilities. However, the technique has not yet been applied to anomaly detection in a logistic operating system. In this paper, anomaly detection using the Mahalanobis–Taguchi method targeting the operational characteristics of a large-scale vertical transfer system is proposed and the validity of the method is discussed. The calculation used to produce proper values of the Mahalanobis distance is first developed based on simple excitation using a shaker. Mahalanobis distances under conditions of continuous operation of the target vertical transfer system are then obtained; distances for the system in an artificially damaged condition are compared to values produced under normal conditions, and any significant increase is used as an indicator of a problem. The applicability of the approach to a case involving continuous long-term operation is discussed using a simulation in which the target vertical transfer system is in continuous operation over a two-year period.
Middleware Fault Tolerance Support for the BOSS Embedded Operating System
