BEAM: technology for autonomous self-analysis

Mackey, Ryan; James, Mark; Park, Han; Zak, Michail

doi:10.1109/aero.2001.931319

Cited by 16 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ignoring the possibility of coupled effects between different subsystems, state of the art systems can reconfigure themselves after diagnosing faults using reasoners that adapt through learning processes. Such systems have been developed and proven within testbeds at various centres, e.g., the Jet Propulsion Laboratory's (JPL) Beacon-based Exception Analysis for Multi-mission (BEAM) that uses an integrated, on-board or off-board data analysis for fault detection, anomaly detection, and prognostics [68]. Another JPL testbed is the Spacecraft Health Inference Engine (SHINE), a high-speed expert system (stateless rule-based system) and inference engine for the diagnosis of spacecraft predict future failures.…”

Section: Requirements For System Health Managementmentioning

confidence: 99%

On the requirements of digital twin-driven autonomous maintenance

Khan

Farnsworth

McWilliam

et al. 2020

Annual Reviews in Control

View full text Add to dashboard Cite

Autonomy has become a focal point for research and development in many industries. Whilst this was traditionally achieved by modelling self-engineering behaviours at the component-level, efforts are now being focused on the sub-system and system-level through advancements in artificial intelligence.Exploiting its benefits requires some innovative thinking to integrate overarching concepts from big data analysis, digitisation, sensing, optimisation, information technology, and systems engineering.With recent developments in Industry 4.0, machine learning and digital twin , there has been a growing interest in adapting these concepts to achieve autonomous maintenance; the automation of predictive maintenance scheduling directly from operational data and for in-built repair at the systems-level.However, there is still ambiguity whether state-of-the-art developments are truly autonomous or they simply automate a process.In light of this, it is important to present the current perspectives about where the technology stands today and indicate possible routes for the future. As a result, this effort focuses on recent trends in autonomous maintenance before moving on to discuss digital twin as a vehicle for decision making from the viewpoint of requirements, whilst the role of AI in assisting with this process is also explored.A suggested framework for integrating digital twin strategies within maintenance models is also discussed. Finally, the article looks towards future directions on the likely evolution and implications for its development as a sustainable technology.Click here to view linked References

show abstract

Section: Requirements For System Health Managementmentioning

confidence: 99%

On the requirements of digital twin-driven autonomous maintenance

Khan

Farnsworth

McWilliam

et al. 2020

Annual Reviews in Control

View full text Add to dashboard Cite

show abstract

“…The designers of systems found in [ 2 ] , [31, [5], the planner for [15], and [IS] would be far more successful with accurate information about how robots fail. Mackey's [7] system is already designed to use whatever failure information its developers can provide while only slight modifications to [4] would allow it to use frequency information to optimize the diagnosis process.…”

Section: Review Of the Literaturementioning

confidence: 99%

“…Such methods use explicit models of the normal behavior of the robot to detect and diagnose fault conditions. Examples of these can he found in [6], [7], [17], and [18]. Other methods are based on rules at the planning level or partial casual models of the system.…”

Section: Review Of the Literaturementioning

confidence: 99%

See 1 more Smart Citation

Reliability analysis of mobile robots

Carlson

Murphy

2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422)

View full text Add to dashboard Cite

Abslmef-Failure data on mobile robots is critical for three reasons: to support the theory of autonomous fault detection, identilication, and recovery necessary for success in new domains; provide design and manufacturing feedhack to the robotics community; and permit project managers to accurately create development schedules. The failures considered in this paper occurred over a period of 2 years, in a variety of environments. Failure type and frequency data were collected from thirteen robots representing three manufacturers and seven models. The data was analyzed using standard manufacturing measures for the reliability of a product. The mean time between failures represents the average time to the next failnre.Avuifabilify was used to gauge the impact of a failure on a project. The results show that the reliability for mobile robots is low, with an average MTBF of 8 hours and availability of less than 50%. The platform itself was the source of most failures (42%) for field robots, while the control system was responsible for 29% of the failures.

show abstract

“…IBM's eLiza [2] is an autonomic computing [1] project dealing mainly with connectivity problems in self-managing servers. BEAM [20] is an end-to-end method for real-time fault detection and characterization for deep space probes. It separates the two major forces of sensor data: deterministic and stochastic.…”

Section: Related Workmentioning

confidence: 99%

Enabling automatic adaptation in systems with under-specified elements

Raz

Koopman

Shaw

2002

Proceedings of the First Workshop on Self-Healing Systems

View full text Add to dashboard Cite

Software that people use for everyday purposes is usually not mission critical-some failures can be tolerated. However, this software should be dependable enough for its intended use, even when users change expectations. Software systems that could adapt to accommodate both failures and changing user expectations could significantly improve the dependability of such everyday software. Many adaptation techniques require specifications of proper behavior (for detecting improper behavior) and problem severity, alternatives and their selection (for mitigation and for repair).However, the specifications of everyday software are usually incomplete and imprecise. This makes it difficult to determine the dependability of the software and even more difficult to adapt.We address the problem of detecting anomalies-deviations from expected behavior-when specifications of expected behavior are missing. Setting up anomaly detection depends on human participation, yielding predicates that can serve as proxies for missing specifications.We propose a template mechanism to lower the demands on human attention when setting up detection. We show how this mechanism may be used in our framework for enhancing dynamic data feeds with automatic adaptation. We discuss how the same mechanism may be used in repair. Our emphasis is on detecting semantic anomalies: cases in which the data feed is responsive and delivers well-formed results, but these results are unreasonable.

show abstract

BEAM: technology for autonomous self-analysis

Cited by 16 publications

References 4 publications

On the requirements of digital twin-driven autonomous maintenance

On the requirements of digital twin-driven autonomous maintenance

Reliability analysis of mobile robots

Enabling automatic adaptation in systems with under-specified elements

Contact Info

Product

Resources

About