Finding faults: A scoping study of fault diagnostics for Industrial Cyber-Physical Systems

Barry Dowdeswell, Roopak Sinha, Stephen MacDonell
2020 Journal of Systems and Software  
Context: As Industrial Cyber-Physical Systems (ICPS) become more connected and widely-distributed, often operating in safety-critical environments, we require innovative approaches to detect and diagnose the faults that occur in them. Objective: We profile fault identification and diagnosis techniques employed in the aerospace, automotive, and industrial control domains. Each of these sectors has adopted particular methods to meet their differing diagnostic needs. By examining both theoretical
more » ... resentations as well as case studies from production environments, we present a profile of the current approaches being employed and identify gaps. Methodology: A scoping study was used to identify and compare fault detection and diagnosis methodologies that are presented in the current literature. We created categories for the different diagnostic approaches via a pilot study and present an analysis of the trends that emerged. We then compared the maturity of these approaches by adapting and using the NASA Technology Readiness Level (TRL) scale. Results: Fault identification and analysis studies from 127 papers published from 2004 to 2019 reveal a wide diversity of promising techniques, both emerging and in-use. These range from traditional Physics-based Models to Data-Driven Artificial Intelligence (AI) and Knowledge-Based approaches. Hybrid techniques that blend aspects of these three broad categories were also encountered. Predictive diagnostics or prognostics featured prominently across all sectors, along with discussions of techniques including Fault trees, Petri nets and Markov approaches. We also profile some of the techniques that have reached the highest Technology Readiness Levels, showing how those methods are being applied in real-world environments beyond the laboratory. Conclusions: Our results suggest that the continuing wide use of both Model-Based and Data-Driven AI techniques across all domains, especially when they are used together in hybrid configuration, reflects the complexity of the current ICPS application space. While creating sufficiently-complete models is labour intensive, Model-free AI techniques were evidenced as a viable way of addressing aspects of this challenge, demonstrating the increasing sophistication of current machine learning systems. Connecting ICPS together to share sufficient telemetry to diagnose and manage faults is difficult when the physical environment places demands on ICPS. Despite these challenges, the most mature papers present robust fault diagnosis and analysis techniques which have moved beyond the laboratory and are proving valuable in real-world environments. J o u r n a l P r e -p r o o f Journal Pre-proof 65 100 elements and the sensors that provide the information that all operational decisions are made on. For 2 J o u r n a l P r e -p r o o f Journal Pre-proof 195 Normal behavior for an ICPS such as this warehouse robot is to pick up packages, navigate reliably and efficiently to another location, and then unload its cargo. The robot's activities rely on receiving inputs from its sensors and being able to co-ordinate 200 the movements of its actuators to complete tasks that achieve previously-defined goals. Our example 3 J o u r n a l P r e -p r o o f Journal Pre-proof 270 ing the location of the fault and its nature [34]. This can be difficult to determine reliably in large systems that contain many interconnected subsystems. Hence, fault isolation includes the anal-4 J o u r n a l P r e -p r o o f Journal Pre-proof J o u r n a l P r e -p r o o f Journal Pre-proof 730 on AI approaches. They suggest that given the complexity of some fault scenarios, the conclusions 9 J o u r n a l P r e -p r o o f Journal Pre-proof 1050 tional luxury item into something that required 14 J o u r n a l P r e -p r o o f Journal Pre-proof 1130 demand. This requires a degree of self-awareness from plant equipment, which must be able to signal if it is available when changes are requested. 15 J o u r n a l P r e -p r o o f Journal Pre-proof J o u r n a l P r e -p r o o f Journal Pre-proof J o u r n a l P r e -p r o o f Journal Pre-proof 1710 methodologies for distributed fault detection and isolation, Applied Sciences 9 (7) (2019) 1286. doi: 10.3390/app9071286. 20 J o u r n a l P r e -p r o o f Journal Pre-proof J o u r n a l P r e -p r o o f Journal Pre-proof 1970 [162] G. Rizzoni, S. Onori, M. Rubagotti, Diagnosis and prognosis of automotive systems: motivations, history and some results, IFAC Proceedings Volumes 42 (8) 22 J o u r n a l P r e -p r o o f Journal Pre-proof Professor Stephen MacDonell, Auckland University of Technology • Conceptualization of the paper. • Supervision of the lead author. • Methodology -design and advice on the application of the survey protocols and review of how they were applied. J o u r n a l P r e -p r o o f Journal Pre-proof
doi:10.1016/j.jss.2020.110638 fatcat:5gdzvwpzcbaxhi3cocty2pafza