Event-Triggered Learning-Based Fault Accommodation for a Class of Nonlinear Interconnected Systems.

In this article, a distributed learning-based fault accommodation scheme is proposed for a class of nonlinear interconnected systems under event-triggered communication of control and measurement signals. Process faults occurring in the local dynamics and/or propagated from interconnected neighboring subsystems are considered. An event-triggered nominal control law is used for each subsystem before detecting any fault occurrence in its dynamics. After fault detection, the corresponding event-triggered fault accommodation law is utilized to reconfigure the nominal control law with a neural-network-based adaptive learning scheme employed to estimate an ideal fault-tolerant control function online. Under the asynchronous controller reconfiguration mechanism for each subsystem, the closed-loop stability of the interconnected systems in different operating modes with the proposed event-triggered learning-based fault accommodation scheme is rigorously analyzed with the explicit stabilization condition and state upper bound derived in terms of event-triggering parameters, and the Zeno behavior is shown to be excluded. An interconnected inverted pendulum system is used to illustrate the proposed fault accommodation scheme.

Event-triggered adaptive dynamic programming for decentralized tracking control of input constrained unknown nonlinear interconnected systems.

This paper addresses decentralized tracking control (DTC) problems for input constrained unknown nonlinear interconnected systems via event-triggered adaptive dynamic programming. To reconstruct the system dynamics, a neural-network-based local observer is established by using local input-output data and the desired trajectories of all other subsystems. By employing a nonquadratic value function, the DTC problem of the input constrained nonlinear interconnected system is transformed into an optimal control problem. By using the observer-critic architecture, the DTC policy is obtained by solving the local Hamilton-Jacobi-Bellman equation through the local critic neural network, whose weights are tuned by the experience replay technique to relax the persistence of excitation condition. Under the event-triggering mechanism, the DTC policy is updated at the event-triggering instants only. Then, the computational resource and the communication bandwidth are saved. The stability of the closed-loop system is guaranteed by implementing event-triggered DTC policy via Lyapunov's direct method. Finally, simulation examples are provided to demonstrate the effectiveness of the proposed scheme.

A Data-Driven ILC Framework for a Class of Nonlinear Discrete-Time Systems.

In this article, we propose a data-driven iterative learning control (ILC) framework for unknown nonlinear nonaffine repetitive discrete-time single-input-single-output systems by applying the dynamic linearization (DL) technique. The ILC law is constructed based on the equivalent DL expression of an unknown ideal learning controller in the iteration and time domains. The learning control gain vector is adaptively updated by using a Newton-type optimization method. The monotonic convergence on the tracking errors of the controlled plant is theoretically guaranteed with respect to the 2-norm under some conditions. In the proposed ILC framework, existing proportional, integral, and derivative type ILC, and high-order ILC can be considered as special cases. The proposed ILC framework is a pure data-driven ILC, that is, the ILC law is independent of the physical dynamics of the controlled plant, and the learning control gain updating algorithm is formulated using only the measured input-output data of the nonlinear system. The proposed ILC framework is effectively verified by two illustrative examples on a complicated unknown nonlinear system and on a linear time-varying system.

Online Learning With Adaptive Rebalancing in Nonstationary Environments.

An enormous and ever-growing volume of data is nowadays becoming available in a sequential fashion in various real-world applications. Learning in nonstationary environments constitutes a major challenge, and this problem becomes orders of magnitude more complex in the presence of class imbalance. We provide new insights into learning from nonstationary and imbalanced data in online learning, a largely unexplored area. We propose the novel Adaptive REBAlancing (AREBA) algorithm that selectively includes in the training set a subset of the majority and minority examples that appeared so far, while at its heart lies an adaptive mechanism to continually maintain the class balance between the selected examples. We compare AREBA with strong baselines and other state-of-the-art algorithms and perform extensive experimental work in scenarios with various class imbalance rates and different concept drift types on both synthetic and real-world data. AREBA significantly outperforms the rest with respect to both learning speed and learning quality. Our code is made publicly available to the scientific community.

Data-Driven Iterative Learning Control for Nonlinear Discrete-Time MIMO Systems.

This article considers the tracking control of unknown nonlinear nonaffine repetitive discrete-time multi-input multi-output systems. Two data-driven iterative learning control (ILC) schemes are designed based on two equivalent dynamic linearization data models of an unknown ideal learning controller, which exists theoretically in the iteration domain. The two control schemes provide ways of selecting learning controllers based on the complexity of the controlled nonlinear systems. The learning control gain matrixes of the two learning controllers are optimized through the steepest descent method using only the measured input-output data of the nonlinear systems. The proposed ILC approaches are pure data-driven since no model information of the controlled systems is involved. The stability and convergence of the proposed ILC approaches are rigorously analyzed under reasonable conditions. Numerical simulation and an experiment based on a Gantry-type linear motor drive system are conducted to verify the effectiveness of the proposed data-driven ILC approaches.

Optimal Elevator Group Control via Deep Asynchronous Actor-Critic Learning.

In this article, a new deep reinforcement learning (RL) method, called asynchronous advantage actor-critic (A3C) method, is developed to solve the optimal control problem of elevator group control systems (EGCSs). The main contribution of this article is that the optimal control law of EGCSs is designed via a new deep RL method, such that the elevator system sends passengers to the desired destination floors as soon as possible. Deep convolutional and recurrent neural networks, which can update themselves during applications, are designed to dispatch elevators. Then, the structure of the A3C method is developed, and the training phase for the learning optimal law is discussed. Finally, simulation results illustrate that the developed method effectively reduces the average waiting time in a complex building environment. Comparisons with traditional algorithms further verify the effectiveness of the developed method.

Distributed Fault-Tolerant Control of Multiagent Systems: An Adaptive Learning Approach.

This paper focuses on developing a distributed leader-following fault-tolerant tracking control scheme for a class of high-order nonlinear uncertain multiagent systems. Neural network-based adaptive learning algorithms are developed to learn unknown fault functions, guaranteeing the system stability and cooperative tracking even in the presence of multiple simultaneous process and actuator faults in the distributed agents. The time-varying leader's command is only communicated to a small portion of follower agents through directed links, and each follower agent exchanges local measurement information only with its neighbors through a bidirectional but asymmetric topology. Adaptive fault-tolerant algorithms are developed for two cases, i.e., with full-state measurement and with only limited output measurement, respectively. Under certain assumptions, the closed-loop stability and asymptotic leader-follower tracking properties are rigorously established.

Fault Estimation and Accommodation of Interconnected Systems: A Separation Principle.

This paper addresses the fault estimation (FE) and accommodation issues of interconnected systems by using two new concepts namely interconnected separation principle and constrained interconnected separation principle that allow for the separate design not only between diagnostic observer and fault tolerant controller for each subsystem, but also between observer/controller of each subsystem and those of other ones. Sufficient fault recoverability conditions are established, under which both distributed and decentralized FE and accommodation schemes are provided. The new results help to provide a framework for observer-based fault diagnosis and fault tolerant control of interconnected systems, and are further applied to the meta aircraft configuration that consists of multiple aircraft joined together to illustrate their efficiency.

Semantically Enhanced Online Configuration of Feedback Control Schemes.

Recent progress toward the realization of the "Internet of Things" has improved the ability of physical and soft/cyber entities to operate effectively within large-scale, heterogeneous systems. It is important that such capacity be accompanied by feedback control capabilities sufficient to ensure that the overall systems behave according to their specifications and meet their functional objectives. To achieve this, such systems require new architectures that facilitate the online deployment, composition, interoperability, and scalability of control system components. Most current control systems lack scalability and interoperability because their design is based on a fixed configuration of specific components, with knowledge of their individual characteristics only implicitly passed through the design. This paper addresses the need for flexibility when replacing components or installing new components, which might occur when an existing component is upgraded or when a new application requires a new component, without the need to readjust or redesign the overall system. A semantically enhanced feedback control architecture is introduced for a class of systems, aimed at accommodating new components into a closed-loop control framework by exploiting the semantic inference capabilities of an ontology-based knowledge model. This architecture supports continuous operation of the control system, a crucial property for large-scale systems for which interruptions have negative impact on key performance metrics that may include human comfort and welfare or economy costs. A case-study example from the smart buildings domain is used to illustrate the proposed architecture and semantic inference mechanisms.

An Integrated Learning and Filtering Approach for Fault Diagnosis of a Class of Nonlinear Dynamical Systems.

This paper develops an integrated filtering and adaptive approximation-based approach for fault diagnosis of process and sensor faults in a class of continuous-time nonlinear systems with modeling uncertainties and measurement noise. The proposed approach integrates learning with filtering techniques to derive tight detection thresholds, which is accomplished in two ways: 1) by learning the modeling uncertainty through adaptive approximation methods and 2) by using filtering for dampening measurement noise. Upon the detection of a fault, two estimation models, one for process and the other for sensor faults, are initiated in order to identify the type of fault. Each estimation model utilizes learning to estimate the potential fault that has occurred, and adaptive isolation thresholds for each estimation model are designed. The fault type is deduced based on an exclusion-based logic, and fault detectability and identification conditions are rigorously derived, characterizing quantitatively the class of faults that can be detected and identified by the proposed scheme. Finally, simulation results are used to demonstrate the effectiveness of the proposed approach.

Embedded Hardware-Efficient Real-Time Classification With Cascade Support Vector Machines.

Cascade support vector machines (SVMs) are optimized to efficiently handle problems, where the majority of the data belong to one of the two classes, such as image object classification, and hence can provide speedups over monolithic (single) SVM classifiers. However, SVM classification is a computationally demanding task and existing hardware architectures for SVMs only consider monolithic classifiers. This paper proposes the acceleration of cascade SVMs through a hybrid processing hardware architecture optimized for the cascade SVM classification flow, accompanied by a method to reduce the required hardware resources for its implementation, and a method to improve the classification speed utilizing cascade information to further discard data samples. The proposed SVM cascade architecture is implemented on a Spartan-6 field-programmable gate array (FPGA) platform and evaluated for object detection on 800×600 (Super Video Graphics Array) resolution images. The proposed architecture, boosted by a neural network that processes cascade information, achieves a real-time processing rate of 40 frames/s for the benchmark face detection application. Furthermore, the hardware-reduction method results in the utilization of 25% less FPGA custom-logic resources and 20% peak power reduction compared with a baseline implementation.

Adaptive approximation for multiple sensor fault detection and isolation of nonlinear uncertain systems.

This paper presents an adaptive approximation-based design methodology and analytical results for distributed detection and isolation of multiple sensor faults in a class of nonlinear uncertain systems. During the initial stage of the nonlinear system operation, adaptive approximation is used for online learning of the modeling uncertainty. Then, local sensor fault detection and isolation (SFDI) modules are designed using a dedicated nonlinear observer scheme. The multiple sensor fault isolation process is enhanced by deriving a combinatorial decision logic that integrates information from local SFDI modules. The performance of the proposed diagnostic scheme is analyzed in terms of conditions for ensuring fault detectability and isolability. A simulation example of a single-link robotic arm is used to illustrate the application of the adaptive approximation-based SFDI methodology and its effectiveness in detecting and isolating multiple sensor faults.

Balancing search and target response in cooperative unmanned aerial vehicle (UAV) teams.

This paper considers a heterogeneous team of cooperating unmanned aerial vehicles (UAVs) drawn from several distinct classes and engaged in a search and action mission over a spatially extended battlefield with targets of several types. During the mission, the UAVs seek to confirm and verifiably destroy suspected targets and discover, confirm, and verifiably destroy unknown targets. The locations of some (or all) targets are unknown a priori, requiring them to be located using cooperative search. In addition, the tasks to be performed at each target location by the team of cooperative UAVs need to be coordinated. The tasks must, therefore, be allocated to UAVs in real time as they arise, while ensuring that appropriate vehicles are assigned to each task. Each class of UAVs has its own sensing and attack capabilities, so the need for appropriate assignment is paramount. In this paper, an extensive dynamic model that captures the stochastic nature of the cooperative search and task assignment problems is developed, and algorithms for achieving a high level of performance are designed. The paper focuses on investigating the value of predictive task assignment as a function of the number of unknown targets and number of UAVs. In particular, it is shown that there is a tradeoff between search and task response in the context of prediction. Based on the results, a hybrid algorithm for switching the use of prediction is proposed, which balances the search and task response. The performance of the proposed algorithms is evaluated through Monte Carlo simulations.