Fault-Tolerant Damage Control of Nonlinear Structures Using Artificial Intelligence

A novel simultaneous fault detection and diagnostics (FDD) and fault tolerant control (FTC) strategy for nonlinear stochastic systems in closed loops based on a continuous stirred tank reactor (CSTR) is presented. The purpose of control is to track the reactant concentration setpoint. Instead of output feedback we propose here to use proportional-integral-derivative (PID) state feedback, which is shown essential to achieve FTC against sensor faults. A new concept of "equivalent bias" is proposed to model the sensor faults. Both the states and the equivalent bias are on-line estimated by a pseudo separate-bias estimation algorithm. The estimated equivalent bias is then evaluated via a modified Bayes' classification based algorithm to detect and diagnose the sensor faults. Many kinds of sensor faults are tested by Monte Carlo simulations, which demonstrate that the proposed strategy has definite fault tolerant ability against sensor faults, moreover the sensor faults can be on-line detected, isolated, and estimated simultaneously.

Adaptive fuzzy output feedback FTC for nonstrict-feedback systems with sensor faults and dead zone input

This paper discusses the design of an active fault-tolerant flight control strategy for improvement of the operational control capability of the aircraft system. The research work draws expertise from actions undertaken within the European Flight Mechanics Action Group [FM-AG(16)] on fault-tolerant control, which develops a collaborative effort in Europe to create new fault-tolerant control technologies that significantly advance the goals of the aviation safety. The methodology is applied to a trimmable horizontal stabilizer runaway fault occurring in a large transport aircraft. The goal is to provide a self-repairing capability to enable the pilot to land the aircraft safely. The fault-tolerant control strategy works in such a way that once the fault is detected by the fault detection and isolation unit, a compensation loop is activated for safe recovery. A key feature of the proposed strategy is that the design of the fault-tolerant control loop is done independently of the nominal autopilot and the nominal flight control system in place. Nonlinear simulation results demonstrate the effectiveness of the proposed fault-tolerant control scheme.

Intending to address the issue of sensor fault-tolerant control, a model-free adaptive fault-tolerant constrained control strategy is proposed with virtual sensor technology. The novel introduction of observer-based model-free adaptive control to fault-tolerant control brings benefits to the nonlinear systems with unknown dynamics in the presence of sensor faults. In the design procedures, the dynamic linearization technique is utilized first to establish the equivalent linear model of nonlinear systems. Then, the virtual sensor technology is introduced by designing the novel state-observer-based estimation algorithm to fulfill the data-driven system dynamic and sensor fault modeling. Besides, the broad learning technique is employed with offline training to provide output information for observer-based data-driven modeling under the fault case. Based on the data-driven model, the fault-tolerant constrained control scheme is explored with the anti-windup compensator against input constraints caused by actuator saturation, and the stability analysis is supplied. Finally, the simulations are carried out for both affine and non-affine nonlinear systems to manifest the effectiveness and superiority of the proposed control strategy.

Track switches are essential in order to enable railway vehicles to change routes however they are also the largest single cause of failure on the railway network and remain a single point of failure. This thesis focusses on modelling and fault tolerant control of a new type of electromechanical railway track switch. Unlike conventional track switch machines, this switch needs closed loop feedback control. Firstly, a detailed simulation model of the switch is developed and validated against experimental results. Two model-based control designs are then developed and tested: a classical cascaded P/PI controller and a modern state feedback LQR controller. The two controllers are compared and it is found that, whilst there are some performance differences, both meet the requirements for use in a redundantly actuated track switch. Following this, a fault tolerant control scheme for sensor faults is developed and validated using fault detection, identification and accommodation methods applied to a detailed non-linear simulation model and then validated on the experimental test rig. The results demonstrate that using a reliable fault tolerant control configuration could increase the availability and reliability of the switch in the presence of sensor faults. Finally, a fault tolerant control approach to actuator faults on the switch with triplex redundancy is developed and validated. In order to achieve this, a dynamic model of a railway track is developed in simulation as the basis for load application to the system. Three parallel actuators with their associated controllers are used to actuate the switch showing good performance in meeting the position control requirements. Different actuator faults are applied and their control performance results are shown. A summary of the control performance is also presented highlighting the differences in performance with different permutations of actuator faults. Overall, it is shown that redundancy in actuation with a suitable control scheme provides benefits in achieving post-fault availability of a redundantly actuated electromechanical railway track switch in the presence of actuator faults.

A novel fault tolerant control algorithm is proposed in this paper based on model reference reinforcement learning for autonomous surface vehicles subject to sensor faults and model uncertainties. The proposed control scheme is a combination of a model-based control approach and a data-driven method, so it can leverage the advantages of both sides. The proposed design contains a baseline controller that ensures stable tracking performance at healthy conditions, a fault observer that estimates sensor faults, and a reinforcement learning module that learns to accommodate sensor faults using fault estimation and compensate for model uncertainties. The impact of sensor faults and model uncertainties can be effectively mitigated by this composite design. Stable tracking performance can also be ensured even at both the offline training and online implementation stages for the learning-based fault tolerant control. A numerical simulation with gyro sensor faults is presented to demonstrate the efficiency of the proposed algorithm.

This paper focuses on insufficient perception in blind scenes and the failures of the actuator and sensor of vehicle suspension. The safe speed is designed and the fault-tolerant strategy based on the observer is designed when the actuator and sensor fail simultaneously. A speed planning strategy to ensure that vehicles operate at a safe speed is proposed. The Markov suspension fault jump model considering the suspension sensor and actuator faults is established. Based on the fault estimation obtained by the fault observer, a fault tolerance control strategy of sensor signal reconstruction and actuator fault compensation is adopted. The measurement index for evaluating fault tolerance effectiveness has been established, and an exploration of fault tolerance control is conducted across various fault levels, to identify the preferred fault tolerance strategies corresponding to different levels of fault tolerance. The simulation results show that the designed speed control strategy can improve vehicle safety by decelerating in advance, the fault observer is capable of accurately estimating the true values of actuator and sensor faults. The simulation and vehicle test results demonstrate that similar suspension performance has been obtained by fault-tolerant control strategy and preferred fault tolerance under different fault tolerance levels compared with normal fault tolerance.

Loss of control accounts for over 25% of aircraft accidents worldwide. This study presents a fault tolerant flight control strategy for increasing aircraft safety. The work has been undertaken within the Action Group on fault tolerant control (FTC) of the European GARTEUR programme, which develops collaborative efforts in Europe to create new FTC technologies that could significantly advance the goals of the aviation safety. After the fault detection and confirmation by the in-flight dedicated systems, a compensation loop is activated to ensure safe recovery. The design of the FTC loop is achieved without any changes in the nominal (and certificated) flight control system (FCS). The FTC scheme design is formulated as an H∞ strong stabilisation problem. Fault compensability is subsequently discussed and formulated as a trim-deficiency analysis problem. The proposed technique is implemented on the SIMONA flight simulator and evaluated through a pilot experiment. The tested scenario corresponds to the landing approach of a large transport aircraft (B747-100/200). The faulty situation is related to trimmable horizontal stabiliser (THS) failures. Piloted flight simulator experiments show that fault tolerance can be achieved under the condition that there exists sufficient remaining control authority.

This paper develops a novel fault reconstruction (FR) method and an FR-based fault-tolerant control (FTC) scheme for systems suffering from both sensor and actuator faults based on the combination of a Luenberger-like reduced-order observer and an interval observer. Firstly, by introducing an output transformation, an auxiliary output that is able to decouple the sensor fault is obtained. Secondly, for addressing the external disturbance and actuator fault, a multiple unknown input (MUI) is formed, and a reduced-order observer that is able to decouple the MUI is constructed. Consequently, asymptotic convergence estimations of the state and the sensor fault can be accomplished. Thirdly, in order to obtain the asymptotic convergence actual FR (AFR), an interval observer is designed. After this, an algebraic connection of the MUI and the state error estimation is given, and, based on the algebraic relationship, an algebraic MUI reconstruction (MUIR) method is proposed. Finally, an FTC scheme is developed by using the state estimation and MUIR. Under the FTC, the closed-loop system is asymptotically stable even if it suffers from sensor and actuator faults simultaneously. Theoretical analysis demonstrates that the observer-based FTC mechanism satisfies the separation principle. At last, two simulation examples are given to verify the effectiveness of the proposed methods.

The problem of fault tolerant shape control for particle size distribution (PSD) process subject to simultaneous time‐varying actuator and sensor faults is studied. In this work, sensor and actuator faults are taken into consideration in a unified framework, and estimated by using adaptive observer technique. For the PSD process, the output distribution, rather than the system output signal itself, is adopted for shape control. Square root rational B‐spline approximation is used to fit the distribution shape. An innovative on‐line fault estimation scheme is proposed for simultaneous actuator and sensor faults estimation. Then an augmented controller based on the virtual actuator and virtual sensor techniques is designed to compensate for the faults and realise PSD shape tracking. A simulation example of emulsion polymerisation is used to validate the proposed scheme and satisfactory performance is obtained.

Wind energy is one of the widely applied renewable energies in the world. Wind turbine as the main wind energy converter at present has very complex technical system containing a huge number of components, actuators and sensors. However, despite of the hardware redundancy, sensor faults have often affected the wind turbine normal operation and thus caused energy generation loss. In this paper, aiming at the wind turbine hydraulic pitch system, data-driven design of process monitoring (PM) and diagnosis has been realized in the wind turbine benchmark. Fault tolerant control (FTC) strategies focused on sensor faults have also been presented here, where with the implementation of soft sensor the sensor fault can be handled and the performance of the system is improved. The performance of this method is demonstrated with the wind turbine benchmark provided by MathWorks®.

For the forklift equipped with electrical sensors, a fault tolerant control (FTC) strategy is proposed. First, considering the uncertainty of forklift cargo and the external output disturbance, the equivalent sensor fault model of forklift is constructed. Then, a sliding mode observer (SMO) with adaptive regulation law is proposed to solve the problem that some fault reconstruction methods demand the upper bound of faults. Based on the fault value reconstructed by SMO, a sliding mode fault-tolerant controller is designed. It can realize active FTC of typical sensor faults of forklift in the presence of uncertainties and output disturbance. Finally, experiment is given to verify the effectiveness of the proposed FTC strategy.

Beta Residuals: Improving Fault-Tolerant Control for Sensory Faults via Bayesian Inference and Precision Learning

The unmanned aerial vehicle (UAV) has been developing rapidly recently, and the safety and the reliability of the UAV are significant to the mission execution and the life of UAV. Sensor and actuator failures of a UAV are one of the most common malfunctions, threating the safety and life of the UAV. Fault-tolerant control technology is an effective method to improve the reliability and safety of UAV, which also contributes to vehicle health management (VHM). This paper deals with the sliding mode fault-tolerant control of the UAV, considering the failures of sensor and actuator. Firstly, a terminal sliding surface is designed to ensure the state of the system on the sliding mode surface throughout the control process based on the simplified coupling dynamic model. Then, the sliding mode control (SMC) method combined with the RBF neural network algorithm is used to design the parameters of the sliding mode controller, and with this, the efficiency of the design process is improved and system chattering is minimized. Finally, the Simulink simulations are carried out using a fault tolerance controller under the conditions where accelerometer sensor, gyroscope sensor or actuator failures is assumed. The results show that the proposed control strategy is quite an effective method for the control of UAVs with accelerometer sensor, gyroscope sensor or actuator failures.

The paper deals with the design of an active fault-tolerant control scheme, which is based on the actuator and sensor fault estimator. Thus, the paper starts with the development of such a fault estimation scheme capable of estimating these faults simultaneously. It is assumed that the estimator should have a desired \(H_\infty \) performance. Subsequently, a new fault-tolerant control law is proposed, which is based on a parallel digital twin of the system. Thus, the goal is to control the system in such a way as to follow the states of the references digital twin irrespective of the faults. Finally, the effectiveness of the proposed approach is verified with the laboratory three-tank system. In particular, the performance of the system is tested against a set of simultaneous actuator and sensor faults, respectively.