Exploring the role of system operation modes in failure analysis in the context of first generation cyber-physical systems

Typically, emerging system failures have a strong impact on the performance of industrial systems as well as on the efficiency of their operational and servicing processes. Being aware of these, maintenance and repair researchers have developed multiple failure detection and diagnosis techniques that allow early recognition of system or component failures and maintaining continuous system operation in a cost-effective way. However, these techniques have many deficiencies in the case of self-tuning first generation cyber-physical systems (1G-CPSs). The reason is that these systems compensate for the effects of emerging system failures until their resources are exhausted, and the compensatory actions not only mask the failures, but also make their recognition difficult. Late recognition of failures is however in contrast with the principles of preventive maintenance. Therefore, the promotion research concentrated on the issue of recognizing and forecasting failures under dynamic and adaptive behavior of 1G-CPSs. CPSs are enabled to compensate for failure symptoms by changing their system operation modes (SOMs). It was also observed that transitions of SOMs reduce the reliability of a signal-based failure diagnosis. It was hypothesized that the frequency and the duration of the changes of the operational states of the 1G-CPS may be strong indicators of the failure emergence phenomenon and that investigation of SOMs facilitates early detection of failures. Therefore, the completed exploratory studies were aimed at exploring how the frequency and duration of transitions of SOMs can be brought into correlation with specific types of failures, and how they can be computed as measures of failure occurrence. The obtained results revealed that system failures tend to induce unusual system operation modes that can be used as basis for failure characterization, and even for failure forecasting. The empirical research made use of a cyber-physical greenhouse testbed to get experimental data and was completed by the development of computational model. A failure injection strategy was implemented in order to induce failure occurrence in a controlled manner. The proposed approach can be applied as a basis of forecasting system failures of 1G-CPSs, but additional research seems to be necessary