Facilitating autonomous systems with AI-based fault tolerance and computational resource economy

Proposed is the facilitation of fault-tolerant capability in autonomous systems with particular consideration of low computational complexity and system interface devices (sensor/actuator) performance. Traditionally model-based fault-tolerant/detection units for multiple sensor faults in automation require a bank of estimators, normally Kalman-based ones. An AI-based control framework enabling low computational power fault tolerance is presented. Contrary to the bank-of-estimators approach, the proposed framework exhibits a single unit for multiple actuator/sensor fault detection. The efficacy of the proposed scheme is shown via rigorous analysis for several sensor fault scenarios for an electro-magnetic suspension testbed.

[1]  Youmin Zhang,et al.  Bibliographical review on reconfigurable fault-tolerant control systems , 2003, Annu. Rev. Control..

[2]  Radu-Emil Precup,et al.  RESULTS AND CHALLENGES OF ARTIFICIAL NEURAL NETWORKS USED FOR DECISION-MAKING AND CONTROL IN MEDICAL APPLICATIONS , 2019 .

[3]  S. Kate Devitt,et al.  Trustworthiness of Autonomous Systems , 2018, CDC 2018.

[4]  Spyros G. Tzafestas,et al.  Modelling and FDI of Dynamic Discrete Time Systems Using a MLP with a New Sigmoidal Activation Function , 2004, J. Intell. Robotic Syst..

[5]  Ian Postlethwaite,et al.  A comparative study of NN- and EKF-based SFDA schemes with application to a nonlinear UAV model , 2010, Int. J. Control.

[6]  Rolf Isermann,et al.  Supervision, fault-detection and fault-diagnosis methods — An introduction , 1997 .

[7]  Guillermo Heredia,et al.  Sensor and actuator fault detection in small autonomous helicopters , 2008 .

[8]  Marios M. Polycarpou,et al.  Adaptive Approximation for Multiple Sensor Fault Detection and Isolation of Nonlinear Uncertain Systems , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Giampiero Campa,et al.  On‐line learning neural networks for sensor validation for the flight control system of a B777 research scale model , 2002 .

[10]  Spyros G. Tzafestas,et al.  AI-Based Actuator/Sensor Fault Detection With Low Computational Cost for Industrial Applications , 2016, IEEE Transactions on Control Systems Technology.

[11]  C. W. Chan,et al.  Online fault detection and isolation of nonlinear systems based on neurofuzzy networks , 2008, Eng. Appl. Artif. Intell..

[12]  Steven X. Ding,et al.  Design of robust fuzzy fault detection filter for polynomial fuzzy systems with new finite frequency specifications , 2018, Autom..

[13]  Stefano Bruni,et al.  Estimation of lateral and cross alignment in a railway track based on vehicle dynamics measurements , 2019, Mechanical Systems and Signal Processing.

[14]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[15]  Sung Kyung Hong,et al.  Fault Diagnosis and Fault-Tolerant Control Scheme for Quadcopter UAVs with a Total Loss of Actuator , 2019, Energies.

[16]  Zoltán Rusák,et al.  Systematic exploration of signal-based indicators for failure diagnosis in the context of cyber-physical systems , 2019, Frontiers of Information Technology & Electronic Engineering.

[17]  Jan Lunze,et al.  Sensor and actuator fault diagnosis of systems with discrete inputs and outputs , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[18]  Marios M. Polycarpou,et al.  Automated fault detection and accommodation: a learning systems approach , 1995, IEEE Trans. Syst. Man Cybern..

[19]  José A. De Doná,et al.  Sensor fault‐tolerant control of a magnetic levitation system , 2010 .

[20]  Inseok Hwang,et al.  A Survey of Fault Detection, Isolation, and Reconfiguration Methods , 2010, IEEE Transactions on Control Systems Technology.

[21]  Keith Glover,et al.  A loop-shaping design procedure using H/sub infinity / synthesis , 1992 .

[22]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[23]  Brad Seanor,et al.  A fault tolerant flight control system for sensor and actuator failures using neural networks , 2000 .

[24]  Kemin Zhou,et al.  FAULT TOLERANT SAFE FLIGHT CONTROLLER BANK 1 , 2006 .

[25]  Yan Wu,et al.  Design and Analysis for Early Warning of Rotor UAV Based on Data-Driven DBN , 2019, Electronics.

[26]  Christopher Edwards,et al.  Sensor fault tolerant control using sliding mode observers , 2006 .

[27]  Spyros G. Tzafestas,et al.  Fault diagnosis via local neural networks , 2002, Math. Comput. Simul..

[28]  Paul M. Frank,et al.  New developments using AI in fault diagnosis , 1996 .

[29]  Lorenzo Ciani,et al.  Reliability and Maintenance Analysis of Unmanned Aerial Vehicles † , 2018, Sensors.

[30]  Ian Postlethwaite,et al.  Survey and application of sensor fault detection and isolation schemes , 2011 .

[31]  Marios M. Polycarpou,et al.  Learning methodology for failure detection and accommodation , 1995 .

[32]  Mario Innocenti,et al.  Kalman filters and neural-network schemes for sensor validation in flight control systems , 1998, IEEE Trans. Control. Syst. Technol..