Unifying System Health Management and Automated Decision Making

Abstract

Health management of complex dynamic systems has evolved from simple automated alarms into a subfield of artificial intelligence with techniques for analyzing off-nominal conditions and generating responses. This evolution took place largely apart from the development of automated system control, planning, and scheduling (generally referred to in this work as decision making). While there have been efforts to establish an information exchange between system health management and decision making, successful practical implementations of integrated architectures remain limited. This article proposes that rather than being treated as connected yet distinct entities, system health management and decision making should be unified in their formulations. Enabled by advances in modeling and algorithms, we believe that a unified approach will increase systems' resilience to faults and improve their effectiveness. We overview the prevalent system health management methodology, illustrate its limitations through numerical examples, and describe a proposed unified approach. We then show how typical system health management concepts are accommodated in the proposed approach without loss of functionality or generality. A computational complexity analysis of the unified approach is also provided.

Predictive System Reconfiguration for Fulfillment of Future Mission Requirements

“…The methodology developed and employed here is in line with the analysis presented by Balaban et al (2019) which suggests that prognostics itself is not meaningful for controllable degradation processes and therefore health monitoring (and not prognostics) should be integrated with decision-making to achieve more efficient and effective solutions. The referred paper presents a detailed analysis on the topic.…”

“…The focus of this work is on the predictive reconfiguration of an autonomous vehicle during mission execution to avoid that equipment failures jeopardize the accomplishment of his mission. One important requirement in this case is that degradation associated to relevant failure modes is controllable (Balaban, Johnson and Kochenderfer, 2019), i.e. it is possible to alter the rate at which equipment degrades based on changes in system configuration/operation.…”

“…However, there are also important differences between the work presented here and that from Balaban et al (2019). In the referred work, partially observable Markov decision process (POMDP) is presented as the mathematical framework to be employed for decision making under state estimation uncertainty.…”

Partially Observable Markov Decision Processes in Robotics: A Survey

“…Robots are systems where knowing which sensors and actuators are fully operational is crucial for safety and robustness. Such questions are tackled by system health monitoring, which is becoming increasingly unified with decision-making, see [15] and references therein. This implies further possibilities for leveraging POMDP planning for objectives such as greater fault resiliency in robotics.…”