Implementation of System Operation Modes for Health Management and Failure Prognosis in Cyber-Physical Systems

Abstract

Cyber-physical systems (CPSs) have sophisticated control mechanisms that help achieve optimal system operations and services. These mechanisms, imply considering multiple signal inputs in parallel, to timely respond to varying working conditions. Despite the advantages that control mechanisms convey, they bring new challenges in terms of failure prevention. The compensatory action the control exerts cause a fault masking effect, hampering fault diagnosis. Likewise, the multiple information inputs CPSs have to process can affect the timely system response to faults. This article proposes a failure prognosis method, which combines time series-based forecasting methods with statistically based classification techniques in order to investigate system degradation and failure forming on system levels. This method utilizes a new approach based on the concept of the system operation mode (SOM) that offers a novel perspective for health management that allows monitoring the system behavior, through the frequency and duration of SOMs. Validation of this method was conducted by systematically injecting faults in a cyber-physical greenhouse testbed. The obtained results demonstrate that the degradation and fault forming process can be monitored by analyzing the changes of the frequency and duration of SOMs. These indicators made possible to estimate the time to failure caused by various failures in the conducted experiments.

An IOHMM-Based Framework to Investigate Drift in Effectiveness of IoT-Based Systems

“…This modeling framework brings numerous advantages [ 13 ]; (1) it is an explainable graphical model, there is a 1:1 correspondence between observations and states; (2) it formalizes conditional dependencies between the effects (outputs) and their context (inputs), making them suitable to model dynamical systems; (3) it incorporates tolerances on expectations related to uncertainties inherent in the natural variability of physical processes and disturbances possibly resulting from adaptation mechanisms [ 34 ] (randomness [ 35 ]) and/or uncertainties related to prior knowledge on the system and/or users’ expectations (epistemic uncertainties [ 5 , 36 ]).…”

Deep Auto-Encoder and Deep Forest-Assisted Failure Prognosis for Dynamic Predictive Maintenance Scheduling

“…A new hybrid fault prognosis method for multi-functional spoiler systems was proposed in [19], where distributed neural networks were used to estimate the failure parameters, and the recursive Bayesian algorithm was employed to anticipate the system RUL with the estimated failure parameters. Also, some time series-based forecasting methods have been combined with statistically based classification techniques to forecast the failures in cyber-physical systems [20].…”