Neural Observer-Based Iterative Learning Leader-Following Control for Multi-Agent Systems Subject to Unknown Dynamics and Multiple Faults

Fault-compensation-based boundary control for hyperbolic PDEs: An adaptive iterative learning scheme

This article studies the fault-tolerant consensus problem with the guaranteed transient performance of multiagent systems (MASs) subject to unknown time-varying actuator faults and disturbances. The general actuator faults, including both multiplicative and additive time-varying faults, are considered in such a problem for the first time. Both single-integrator modeled agents and double-integrator modeled agents are investigated. The transient performance is ensured in the sense that position errors between each pair of neighboring agents are guaranteed within certain user-defined time-varying performance bounds. Adaptive laws are designed to estimate information about faults and disturbances. For MASs with additive faults, the proposed controllers ensure errors asymptotically converge to zero with guaranteed transient performance. For MASs with both multiplicative faults and additive faults, the proposed controllers ensure errors converge to a residual set without asymptotic convergence but still with guaranteed transient performance. Two simulation examples are provided to evaluate the proposed schemes.

In this paper, we formulate a coupled factorial hidden Markov model-based (CFHMM) framework to diagnose dependent faults occurring over time (dynamic case). In our previous research, the problem of diagnosing multiple faults over time (dynamic multiple fault diagnosis (DMFD)) is solved based on a sequence of test outcomes by assuming that the faults and their time evolution are independent. This problem is NP-hard, and, consequently, we developed a polynomial approximation algorithm using Lagrangian relaxation within a FHMM framework. Here, we extend this formulation to a mixed memory Markov coupling model, termed dynamic coupled fault diagnosis (DCFD) problem, to determine the most likely sequence of (dependent) fault states, the one that best explains the observed test outcomes over time. An iterative Gauss-Seidel coordinate ascent optimization method is proposed for solving the DCFD problem. A soft Viterbi algorithm is also implemented within the framework for decoding-dependent fault states over time. We demonstrate the algorithm on simulated systems with coupled faults and the results show that this approach improves the correct isolation rate (CI) as compared to the formulation where independent fault states (DMFD) are assumed. As a by-product, we show empirically that, while diagnosing for independent faults, the DMFD algorithm based on block coordinate ascent method, although it does not provide a measure of suboptimality, provides better primal cost and higher CI than the Lagrangian relaxation method for independent fault case. Two real-world examples (a hybrid electric vehicle, and a mobile autonomous robot) with coupled faults are also used to evaluate the proposed framework.

Synergistic frameworks for sensor fault isolation and accommodation in grid-side converters

For the discrete linear multi-agent systems with random actuator faults and system disturbances, an iterative learning control strategy with the forgetting factor is proposed. Firstly, the random variation of actuator faults with the number of iterations is considered. A multiplicative stochastic fault model obeying a normal distribution is designed, and the correction mechanism is given. Secondly, an iterative learning consistency control algorithm with a forgetting factor is provided under the consideration of random disturbances in the system. The system stability is analyzed by using the mean square stability theory. A sufficient condition for the consistency in the multi-agent system is given through the relevant mathematical derivation, which makes it possible to realize the state consistency for the discrete multi-agent system under the occurrence of random faults in the actuator. Finally, the feasibility of the algorithm is verified by numerical simulation in a multi-agent system.

Learning‐based robust control methodologies under information constraints

This paper proposes an observer-based adaptive control for unknown nonlinear systems using an adaptive dynamic programming (ADP) algorithm. First, a diagonal recurrent neural network (DRNN) observer is proposed to estimate the unknown dynamics of the nonlinear system states. The proposed neural network offers a simpler structure with deeper memory and guarantees the faster convergence. Second, a neural controller is constructed via ADP method using the observed states to get the optimal control. The optimal control law is determined based on the new structure of the critic network, which is performed using the DRNN. The learning algorithm for the proposed DRNN observer-based adaptive control is developed based on the Lyapunov stability theory. Simulation results and hardware-in-the-loop results indicate the robustness of the proposed ADP to respond the system uncertainties and external disturbances compared with other existing schemes.

A new encounter between leader–follower tracking and observer-based control: Towards enhancing robustness against disturbances

This study is concerned with the design of dynamic observer-based robust controller that also facilitates the acquisition of information used for fault detection (FD) purpose in feedback control systems. Through introducing a weighting matrix, the combination of observer states is utilised to generate a residual signal to detect faults. The first technical contribution is to construct a new linearising change-of-variables that is able to convert the dynamic observer-based controller design problem into linear matrix inequality-based optimisation problem. The second one is to show that the proposed dynamic observer-based controller can achieve a better H∞ performance compared with the existing static (Luenberger) observer-based controller design approaches. Finally, via the simple residual structure, a convex fault detector design condition with some parameter matrices fixed is developed for guaranteeing the H− performance used to measure the fault sensitivity. An F-18 aircraft model is given to show the satisfactory FD performance and control performance.

This paper proposes a robust adaptive strategy for longitudinal dynamics of generic hypersonic flight vehicles with uncertainties and faults. Flight vehicles are generally subjected to disturbances and multiple faults, which should be compensated for to preclude performance degradation. To solve this problem, considering fast abrupt faults such as actuator stuck faults, an adaptive fault observer is added into the nominal dynamic inversion controller to accommodate the effects of faults with discrete function patterns. In addition, since the above observer is designed only for fast abrupt faults, an online support vector machine compensator is proposed to learn the state error caused by other faults. As the error contains both dynamic uncertainties and slow variation faults, additional controllers are not required to get rid of the unwanted faults. Stability of the overall closed-loop system is analyzed with the Lyapunov stability theory, and output tracks the expected trajectory. The simulation is presented with multiple faults to verify the effectiveness and feasibility of the proposed scheme.

This paper presents a factorial hidden Markov model (FHMM)-based diagnostic reasoner to handle multiple intermittent faults. The dynamic multiple fault diagnosis (DMFD) problem is to determine the most likely evolution of fault states, the one that best explains the observed test outcomes over time. In our previous research work, we have shown that the problem of diagnosing dynamic multiple faults in the presence of imperfect test outcomes, is an NP-hard problem. Here, we combine a Gauss-Seidel coordinate ascent optimization method with a Soft Viterbi decoding algorithm for solving the DMFD problem. We demonstrated the algorithm on small-scale and medium-scale systems and the simulation results shows that this approach improves primal function value (1.4%~8.3%) and correct isolation rate (1.7%~11.4%) as compared to a Lagrangian relaxation method discussed in our previous work.

In this article, a distributed output-feedback consensus maneuvering problem is investigated for a class of uncertain multiagent systems with multi-input and multi-output (MIMO) strict-feedback dynamics. The followers are subject to immeasurable states and external disturbances. A distributed neural observer-based adaptive control method is designed for consensus maneuvering of uncertain MIMO multiagent systems. The method is based on a modular structure, resulting in the separation of three modules: 1) a variable update law for the parameterized path; 2) a high-order neural observer; and 3) an output-feedback consensus maneuvering control law. The proposed distributed neural observer-based adaptive control method ensures that all followers agree on a common motion guided by a desired parameterized path, and the proposed method evades adopting the adaptive backstepping or dynamic surface control design by reformulating the dynamics of agents, thereby reducing the complexity of the control structure. Combined with the cascade system analysis and interconnection system analysis, the input-to-state stability of the consensus maneuvering closed loop is established in the Lyapunov sense. A simulation example is presented to demonstrate the performance of the proposed distributed neural observer-based adaptive control method for output-feedback consensus maneuvering.

With the development of science and technology, practical systems such as the power systems, traffic systems, robot manipulator systems, etc., have become more complex. Therefore, it is difficult to build practical systems by accurate models. Under the lack of accurate process models, using system data to improve system performance and learn optimal decisions becomes very important. Through the recent years, data-based learning control theories and technologies have widely been investigated, including adaptive dynamic programming, reinforcement learning, iterative learning control, and so on. Data-based methods require the system data instead of the accurate knowledge of system dynamics that can be considered as model-free learning control methods. The data-based methods are effective solutions for the optimal control of nonlinear systems, which motivate this special issue. This special issue aims to collect and present original research dealing with data-based learning and their applications for optimization and control problems. The first group of papers1-7 focuses on data-based control theory, approaches, and applications. A fuzzy model predictive control approach is proposed for stick-slip type piezoelectric actuator to realize the precise control of the end effector.1 A systematic online adaptive dynamic programming control framework is proposed for smart buildings control to ensure hard constraints to be satisfied.2 A multi-verse optimizer tuned PI-type active disturbance rejection generalized predictive control method is described for the motion control problems of ships.3 The sufficient optimality conditions for the optimal controls are established under some convexity assumptions.4 A receding-horizon reinforcement learning algorithm is proposed for near-optimal control of continuous-time systems under control constraints.5 In order to solve the interference compensation control problem of a class of nonlinear systems, a method based on memory data is introduced to suppress interference greatly.6 A new controller design method is proposed for the trajectory tracking problem of robots with imprecise dynamic properties and interference.7 The second group of papers8-12 considers iterative learning identification and iterative learning control. An iterative learning control approach is proposed for linear parabolic distributed parameter systems with multiple actuators and multiple sensors.8 The quantized data-based iterative learning tracking control problem is studied for nonlinear networked control systems with signals quantization and denial-of-service attacks.9 The output tracking problem is considered for a class of nonlinear parabolic distributed parameter systems with moving boundaries.10 A just-in-time learning based dual heuristic programming algorithm is proposed to optimize the control performance of autonomous wheeled mobile robots under faults or disturbances.11 A novel optimal constraint-following controller is proposed for uncertain mechanical systems.12 The third group of papers13-19 focuses on robustness on data-based optimal learning control. A novel Nash game-theoretical optimal adaptive robust control design approach is proposed to address the constraint-following control problem for the uncertain underactuated mechanical systems with fuzzy evidence theory.13 A partial model-free sliding mode control strategy is proposed for a class of disturbed systems.14 A new data-based adaptive dynamic programming algorithm is proposed to solve the optimal control policy for discrete-time systems with uncertainties.15 A method that applies event-triggered mechanism H ∞ $$ {\mathrm{H}}_{\infty } $$ control to continuous-time nonlinear systems with asymmetric constraints based on dual heuristic dynamic programming structure is proposed.16 A novel anti-disturbance inverse optimal controller design method is proposed for a class of high-dimensional chain structure systems with any disturbances, matched, or mismatched.17 A data-driven H ∞ $$ {\mathrm{H}}_{\infty } $$ controller design method is studied for continuous-time linear periodic systems.18 The problem of the post-stall pitching maneuver of an aircraft with lower deflection frequency of control actuator is studied by considering the unsteady aerodynamic disturbances.19 The fourth group of papers20-23 focuses on neural networks and deep neural networks learning methods for optimal control. An optimal tracking control problem for the injection flow front position arising in the filling process in the injection molding machine is considered, and an intelligent real-time optimal control method based on deep neural networks is developed for the online tracking of the flow front position to improve the efficient production process of the plastics.20 An efficient and systematic method is proposed for model-based predictive control synthesis.21 The decentralized control issues of nonlinear large-scale systems are investigated via critic-only adaptive dynamic programming learning methods.22 A singularity-free online neural network-based sliding mode control method is proposed to realize the fixed-wing perch maneuver.23 The fifth group of papers24-27 discusses data-based control for distributed control systems. A mission-driven control scheme, including a consensus-based near-optimal formation controller and a finite-time precise formation controller, is proposed aiming at different requirements of unmanned aerial vehicle swarm.24 The neural network adaptive formation control of a class of second-order nonlinear systems with unmodeled dynamics is investigated, where the control law merely depends on the relative bearings between neighboring agents.25 The neighbor Q-learning based consensus control algorithm is developed for discrete-time multiagent systems.26 The fault-tolerate containment control problem is considered for stochastic nonlinear multiagent systems in the presence of input saturation and sensor faults.27 The sixth group of papers28-30 considers applications of data-based learning methods to industrial processes. A stochastic gradient algorithm based on the minimum Shannon entropy is proposed to identify a type of Hammerstein system with random noise.28 A predictive control strategy based on Hammerstein–Wiener inverse model compensation is proposed aiming at the nonlinearity and large lag of the pH change in wet flue gas desulfurization process.29 An algorithm called the kernel entropy regression is proposed to enhance the interpretability between the fault and the key performance indicator.30 The seventh group of papers31-36 focuses on machine learning, data mining, and practical applications in automation. The performance of a Takagi–Sugeno fuzzy-model-based observer is enhanced by proposing a featured multi-instant united switch-type observer.31 The reinforcement learning theory with deep Q-network is applied for the mobile robot to achieve a collision-free path in an unknown dynamic environment.32 An energy-saving velocity planning algorithm is proposed for rail transit train with running and computation delays.33 A novel COVID-19 transmission model is established by introducing traditional susceptible–exposed–infected–removed disease transmission models into complex network.34 A novel collaborative diagnosis method is presented by combining variational modal decomposition and stochastic configuration network for incipient faults of rolling bearing.35 The linear dependence graph associated with a finite-dimensional vector space is studied.36 In summary, this special issue provides an opportunity to review the most recent developments in data-based learning control for optimization of nonlinear systems, by considering theory, algorithms, and applications.

Advances in Fault Diagnostics and Post‐Fault Operation of Electrical Drives

By applying a linear neural network, an iterative learning control is described for noisy CARMA (Controlled Autoregressive Moving Average) systems. The developed controller has a form of direct controller in a stochastic environment, while the usual iterative controller has a form of discrete observer in a determine-istic environment. Thus, the present iterative controller can treat with the case of noisy measurements. First, we describe the system considered here and state some assumptions to solve the problem. Next, the model of inverse dynamics is derived and the off-line iterative learning rule is explained by using the delta rule. Then, we show a neural controller, under the situation where the measurement noise is assumed to be known. Furthermore, we describe the method to estimate the noise process on-line by using the associated regular dynamics. Finally, we show some simulation examples to illustrate the features of the present controller. In particular, we shall discuss the results from the view points of the initial connec-tions weights and the generalizability of linear neural networks to some different or untrained reference signals.