Abstract
We demonstrate an end-to-end framework to improve the resilience of man-made systems to unforeseen events. The framework is based on a physics-based digital twin model and three modules tasked with real-time fault diagnosis, prognostics and reconfiguration. The fault diagnosis module uses model-based diagnosis algorithms to detect and isolate faults and generates interventions in the system to disambiguate uncertain diagnosis solutions. We scale up the fault diagnosis algorithm to the required real-time performance through the use of parallelization and surrogate models of the physics-based digital twin. The prognostics module tracks fault progression and trains the online degradation models to compute remaining useful life of system components. In addition, we use the degradation models to assess the impact of the fault progression on the operational requirements. The reconfiguration module uses PDDL-based planning endowed with semantic attachments to adjust the system controls to minimize the fault impact on the system operation. We define a resilience metric and use a fuel system example to demonstrate how the metric improves with our framework.
- [1] . 2018. Differentiable MPC for end-to-end planning and control. In Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018 (NeurIPS’18). 8299–8310.Google Scholar
- [2] . 1953. Contact and Rubbing of flat surfaces. Journal of Applied Physics 24, 8 (1953), 981–988.
DOI: Google ScholarCross Ref - [3] . 2005. A Comparison of Planning Based Models for Component Reconfiguration. Technical Report CU-CS-995-05. Colorado University.Google Scholar
- [4] . 2003. Deployment and dynamic reconfiguration planning for distributed software systems. In IEEE ICTAI.Google Scholar
- [5] M. S. Arulampalam, S. Maskell, and N. Gordon. 2002. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Transactions on Signal Processing 50, 2 (2002), 174–188.Google Scholar
- [6] J. Bajada, M. Fox, and D. Long. 2015. Temporal planning with semantic attachment of non-linear monotonic continuous behaviours. In Proceedings of the 24th International Conference on Artificial Intelligence (IJCAI’15). AAAI Press, 1523–1529.Google Scholar
- [7] . 2016. NARX time series model for remaining useful life estimation of gas turbine engines. In PHM Society European Conference, Vol. 3. Issue 1.
DOI: Google ScholarCross Ref - [8] O. Bektas, J. Marshall, and J. Jones. 2020. Comparison of Computational Prognostic Methods for Complex Systems Under Dynamic Regimes: A Review of Perspectives. Archives of Computational Methods in Engineering 27, 4 (2020), 999–1011.Google Scholar
- [9] . 2017. Boosting search guidance in problems with semantic attachments. In International Conference on Automated Planning and Scheduling, Vol. 27. 29–37.Google ScholarCross Ref
- [10] . 2019. Automated planning encodings for the manipulation of articulated objects in 3d with gravity. In AI* IA - International Conference of the Italian Association for Artificial Intelligence. Springer, 135–150.Google ScholarCross Ref
- [11] . 2020. Power system resilience: Current practices, challenges, and future directions. IEEE Access 8 (2020), 18064–18086.Google ScholarCross Ref
- [12] . 2013. Nonlinear System Identification: NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains.
2013016206 Google ScholarCross Ref - [13] T. Blochwitz, M. Otter, J. Akesson, M. Arnold, C. Clauss, H. Elmqvist, M. Friedrich, A. Junghanns, J. Mauss, D. Neumerkel, H. Olsson, and A. Viel. 2011. The functional mockup interface for tool independent exchange of simulation models. In Proceedings of the 8th International Modelica Conference. 105–114.Google Scholar
- [14] . 2014. Planning as model checking in hybrid domains. In AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- [15] . 1971. An algorithm with guaranteed convergence for finding a zero of a function. Comput. J. 14, 4 (
01 1971), 422–425.DOI: Google ScholarCross Ref - [16] J. Cámara, P. Correia, R. de Lemos, and M. Vieira. 2014. Empirical resilience evaluation of an architecture-based self-adaptive software system. In Proceedings of the 10th International ACM Sigsoft Conference on Quality of Software Architectures (QoSA’14). Association for Computing Machinery, 63–72.Google Scholar
- [17] . 2016. A compilation of the full PDDL+ language into SMT. In International Conference on Automated Planning and Scheduling, Vol. 26. 79–87.Google ScholarCross Ref
- [18] . 1997. Planning via model checking: A decision procedure for AR. In Recent Advances in AI Planning. Springer, 130–142.Google ScholarDigital Library
- [19] A. Coles, A. Coles, M. Fox, and D. Long. 2012. COLIN: Planning with continuous linear numeric change. J. Artif. Int. Res. 44, 1 (2012), 1–96.Google Scholar
- [20] . 2006. A higher order estimate of the optimum checkpoint interval for restart dumps. Future Generation Computer Systems 22, 3 (2006), 303–312.
DOI: Google ScholarDigital Library - [21] . 2017. Efficient surrogate model development: Optimum model form based on input function characteristics. In 27th European Symposium on Computer Aided Process Engineering.
Computer Aided Chemical Engineering , Vol. 40. Elsevier, 457–462.Google Scholar - [22] . 1992. Characterizing diagnoses and systems. Journal of Artificial Inteligence 56, 2–3 (1992), 197–222.Google ScholarDigital Library
- [23] . 2012. A universal planning system for hybrid domains. Appl. Intell. 36, 4 (2012), 932–959.Google ScholarDigital Library
- [24] . 2009. Semantic attachments for domain-independent planning systems. In Nineteenth International Conference on Automated Planning and Scheduling.Google ScholarDigital Library
- [25] . 2010. A model-based active testing approach to sequential diagnosis. JAIR 39, 1 (
sep 2010), 301–334.Google ScholarDigital Library - [26] . 2006. Modelling mixed discrete-continuous domains for planning. Journal of Artificial Intelligence Research 27, 1 (2006), 235–297.Google ScholarDigital Library
- [27] . 2011. PDDL2.1: An extension to PDDL for expressing temporal planning domains. (2011). arXiv: https://arxiv.org/abs/arXiv:1106.4561Google ScholarCross Ref
- [28] . 2015. Principles of Object-Oriented Modeling and Simulation with Modelica 3.3: A Cyber-Physical Approach (2 ed.). Wiley, Hoboken, NJ.Google Scholar
- [29] . 1989. Model predictive control: Theory and practice—A survey. Automatica 25, 3 (1989), 335–348.Google ScholarDigital Library
- [30] . 2021. A review on resilience assessment of energy systems. Sustainable and Resilient Infrastructure 6, 5 (2021), 273–299.
DOI: Google ScholarCross Ref - [31] . 2011. Uncoordinated checkpointing without domino effect for send-deterministic MPI applications. In 2011 IEEE International Parallel & Distributed Processing Symposium. 989–1000.
DOI: Google ScholarDigital Library - [32] . 2020. Implementing software resiliency in HPX for extreme scale computing. (2020). Google ScholarCross Ref
- [33] . 2012. Planning with semantic attachments: An object-oriented view. Proc. of ECAI 242.Google Scholar
- [34] . 2005. Model-based fault-detection and diagnosis—status and applications. Annual Reviews in Control 29, 1 (2005), 71–85.Google ScholarCross Ref
- [35] . 1997. New extension of the Kalman filter to nonlinear systems. In Signal Processing, Sensor Fusion, and Target Recognition VI(
Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series , Vol. 3068). 182–193.DOI: Google ScholarCross Ref - [36] . 1960. A new approach to linear filtering and prediction problems. Transactions of the ASME–Journal of Basic Engineering 82, Series D (1960), 35–45.Google ScholarCross Ref
- [37] . 2010. An approach for effective design space exploration. In Monterey Conference on Foundations of Computer Software: Modeling, Development, and Verification of Adaptive Systems (FOCS’10). 33–54.Google ScholarDigital Library
- [38] . 2021. Challenges and opportunities of system-level prognostics. Sensors 21, 22 (2021), 1–25.
DOI: Google ScholarCross Ref - [39] . 2015. Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR’15). Retrieved from http://arxiv.org/abs/1412.6980Google Scholar
- [40] . 2000. Stochastic prognostics for rolling element bearings. Mechanical Systems and Signal Processing 14, 5 (2000), 747–762.
DOI: Google ScholarCross Ref - [41] . 1992. Speed of Convergence of Recursive Least Squares Learning with ARMA Perceptions.
Economics Working Papers . Department of Economics and Business, Universitat Pompeu Fabra.Google Scholar - [42] . 2018. Model-based diagnosis: A frequency domain view. In 2018 IEEE International Conference on Prognostics and Health Management(PHM).Google ScholarCross Ref
- [43] . 2021. Controlling draft interactions between quadcopter unmanned aerial vehicles with physics-aware modeling. Journal of Intelligent and Robotics Systems 101, 21 (2021), 1–21.Google Scholar
- [44] . 2018. Analytic redundancy relations guided parameter estimation for model-based diagnosis. In International Workshop on Principles of Diagnosis (DX’18).Google Scholar
- [45] . 2022. A control approach to fault disambiguation. Annual Conference of the PHM Society 14, 1 (2022), 1–8.Google ScholarCross Ref
- [46] D. McDermott, M. Ghallab, A. Howe, C. Knoblock, A. Ram, M. Veloso, D. Weld, and D. Wilkins. 1998. PDDL - The Planning Domain Definition Language. Technical Report CVC TR-98-003/DCS TR-1165. Yale Center for Computational Vision and Control.Google Scholar
- [47] . 1966. An assessment of the navigation and course corrections for a manned flyby of mars or venus. IEEE Transactions on Aerospace Electronic Systems 2, 4 (
July 1966), 613–623.DOI: Google ScholarCross Ref - [48] . 2014. Using fault augmented modelica models for diagnostics. In International Modelica Conference. 437–445.Google ScholarCross Ref
- [49] . 2019. Design and assessment methodology for system resilience metrics. Risk Analysis 39, 9 (2019), 1885–1898.
DOI: arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1111/risa.13274 Google ScholarCross Ref - [50] . 2017. Metrics and quantification of operational and infrastructure resilience in power systems. IEEE Transactions on Power Systems 32, 6 (2017), 4732–4742.Google ScholarCross Ref
- [51] . 1963. Closure to “Discussions of ‘A Critical Analysis of Crack Propagation Laws”’ (1963, ASME J. Basic Eng., 85, pp. 533–534). Journal of Basic Engineering 85, 4 (
12 1963), 534–534.DOI: Google ScholarCross Ref - [52] A. Paszke, S. Gross, S. Chintala, G. Chanan, E. Yang, Z. DeVito, Z. Lin, A. Desmaison, L. Antiga, and A. Lerer. 2017. Automatic differentiation in PyTorch. In NIPS 2017 Workshop on Autodiff. 1–4.Google Scholar
- [53] . 2000. Issues of Fault Diagnosis for Dynamic Systems. Springer-Verlag London.Google ScholarCross Ref
- [54] . 2016. Solving realistic unit commitment problems using temporal planning: Challenges and solutions. In International Conference on Automated Planning and Scheduling, Vol. 26. 421–430.Google ScholarCross Ref
- [55] . 2016. Heuristic planning for PDDL+ domains. In International Joint Conferences on Artificial Intelligence. 3213–3219.Google Scholar
- [56] . 2023. Learning to operate in open worlds by adapting planning models. In International Conference on Autonomous Agents and Multiagent Systems. ACM, 2610–2612.
DOI: Google ScholarDigital Library - [57] . 2007. A View of Algorithms for Optimization without Derivatives.
Technical Report . University of Cambridge, UK.Google Scholar - [58] . 2002. Survey of Checkpoint/restart Implementations.
Technical Report LBNL-54942. Lawrence Berkeley National Laboratory.Google Scholar - [59] . 2014. Model-based approach for optimal maintenance strategy. In European Conference of the Prognostics and Health Management Society.Google Scholar
- [60] . 2001. Analytical redundancy relations for fault detection and isolation in algebraic dynamic systems. Automatica 37, 5 (2001), 687–699.
DOI: Google ScholarDigital Library - [61] . 2014. Toward local failure local recovery resilience model using MPI-ULFM. In Proceedings of the 21st European MPI Users’ Group Meeting. 51–56.
DOI: Google ScholarDigital Library - [62] . 2002. Fault diagnosis and accommodation of a three-tank system based on analytical redundancy. ISA Transactions 41, 3 (2002), 365–382.
DOI: Google ScholarCross Ref - [63] S. Thiébaux, C. Coffrin, H. Hijazi, and J. Slaney. 2013. Planning with MIP for supply restoration in power distribution systems. In Proceedings of the 23rd International Joint Conference on Artificial Intelligence (Beijing, China) (IJCAI’13). AAAI Press, 2900–2907.Google Scholar
- [64] . 2018. Towards perception-aware task-motion planning. In AAAI Fall Symposium on Reasoning and Learning in Real-World Systems for Long-Term Autonomy. Arlington, VA.Google Scholar
- [65] G. E. P. Box and G. Jenkins. 1990. Time Series Analysis, Forecasting and Control. Holden-Day.Google Scholar
- [66] . 2016. Efficient macroscopic urban traffic models for reducing congestion: A PDDL+ planning approach. In AAAI Conference on Artificial Intelligence, Vol. 30.Google ScholarCross Ref
- [67] . 2020. SciPy 1.0: Fundamental algorithms for scientific computing in Python. Nature Methods 17, 3 (2020), 261–272.
DOI: Google ScholarCross Ref - [68] . 2016. Research on resilience of power systems under natural disasters–a review. IEEE Transactions on Power Systems 31, 2 (2016), 1604–1613.
DOI: Google ScholarCross Ref - [69] . 2003. Model-based programming of fault-aware systems. AI Magazine 24, 4 (2003), 61–61.Google ScholarDigital Library
- [70] . 2001. A new stress-based fatigue life model for ball bearings. Tribology Transactions 44, 1 (2001), 11–18.Google ScholarCross Ref
- [71] . 2011. Fault detection and isolation of the wind turbine benchmark: An estimation-based approach. IFAC Proceedings Volumes 44, 1 (2011), 8295–8300.
DOI: 18th IFAC World Congress .Google ScholarCross Ref - [72] . 2019. A sufficient condition for convergences of adam and RMSProp. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR’19). 11119–11127.
DOI: Google ScholarCross Ref
Index Terms
- System Resilience through Health Monitoring and Reconfiguration
Recommendations
Primary and secondary diagnosis of multi-agent plan execution
Diagnosis of plan failures is an important subject in both single- and multi-agent planning. Plan diagnosis can be used to deal with plan failures in three ways: (i) to provide information necessary for the adjustment of the current plan or for the ...
Information-Theoretic Syndrome Evaluation, Statistical Root-Cause Analysis, and Correlation-Based Feature Selection for Guiding Board-Level Fault Diagnosis
Reasoning-based functional-fault diagnosis has recently been advocated to achieve high diagnosis accuracy, low defect escapes, and reducing manufacturing cost. However, such diagnosis method requires a rich set of test items (syndromes) and a sizable ...
Models and methods for plan diagnosis
We consider a model-based diagnosis approach to the diagnosis of plans. Here, a plan performed by some agent(s) is considered as a system to be diagnosed. We introduce a simple formal model of plans and plan execution where it is assumed that the ...
Comments