Adaptive Neural Control of MIMO Nonstrict-Feedback Nonlinear Systems With Time Delay

In this paper, an adaptive neural output-feedback tracking controller is designed for a class of multiple-input and multiple-output nonstrict-feedback nonlinear systems with time delay. The system coefficient and uncertain functions of our considered systems are both unknown. By employing neural networks to approximate the unknown function entries, and constructing a new input-driven filter, a backstepping design method of tracking controller is developed for the systems under consideration. The proposed controller can guarantee that all the signals in the closed-loop systems are ultimately bounded, and the time-varying target signal can be tracked within a small error as well. The main contributions of this paper lie in that the systems under consideration are more general, and an effective design procedure of output-feedback controller is developed for the considered systems, which is more applicable in practice. Simulation results demonstrate the efficiency of the proposed algorithm.

LogDet divergence-based metric learning with triplet constraints and its applications

How to select and weigh features has always been a difficult problem in many image processing and pattern recognition applications. A data-dependent distance measure can address this problem to a certain extent, and therefore an accurate and efficient metric learning becomes necessary. In this paper, we propose a LogDet divergence-based metric learning with triplet constraints (LDMLT) approach, which can learn Mahalanobis distance metric accurately and efficiently. First of all, we demonstrate the good properties of triplet constraints and apply it in LogDet divergence-based metric learning model. Then, to deal with high-dimensional data, we apply a compressed representation method to learn, store, and evaluate Mahalanobis matrix efficiently. Besides, a dynamic triplets building strategy is proposed to build a feedback from the obtained Mahalanobis matrix to the triplet constraints, which can further improve the LDMLT algorithm. Furthermore, the proposed method is applied to various applications, including pattern recognition, facial expression recognition, and image retrieval. The results demonstrate the improved performance of the proposed approach.

Observer-based adaptive neural tracking control for a class of nonlinear systems with prescribed performance and input dead-zone constraints

This paper investigates the problem of output feedback neural network (NN) learning tracking control for nonlinear strict feedback systems subject to prescribed performance and input dead-zone constraints. First, an NN is utilized to approximate the unknown nonlinear functions, then a state observer is developed to estimate the unmeasurable states. Second, based on the command filter method, an output feedback NN learning backstepping control algorithm is established. Third, a prescribed performance function is employed to ensure the transient performance of the closed-loop systems and forces the tracking error to fall within the prescribed performance boundary. It is rigorously proved mathematically that all the signals in the closed-loop systems are semi-globally uniformly ultimately bounded and the tracking error can converge to an arbitrarily small neighborhood of the origin. Finally, a numerical example and an application example of the electromechanical system are given to show effectiveness of the acquired control algorithm.

Filtering of Discrete-Time Switched Neural Networks Ensuring Exponential Dissipative and $l_{2}$ - $l_{\infty }$ Performances

This paper studies delay-dependent exponential dissipative and l₂ - l_∞ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and l₂ - l_∞ senses. The design of the desired exponential dissipative and l₂ - l_∞ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.

Finite-Time L2-Gain Asynchronous Control for Continuous-Time Positive Hidden Markov Jump Systems via T-S Fuzzy Model Approach

This article investigates the finite-time asynchronous control problem for continuous-time positive hidden Markov jump systems (HMJSs) by using the Takagi-Sugeno fuzzy model method. Different from the existing methods, the Markov jump systems under consideration are considered with the hidden Markov model in the continuous-time case, that is, the Markov model consists of the hidden state and the observed state. We aim to derive a suitable controller that depends on the observation mode which makes the closed-loop fuzzy HMJSs be stochastically finite-time bounded and positive, and fulfill the given L₂ performance index. Applying the stochastic Lyapunov-Krasovskii functional (SLKF) methods, we establish sufficient conditions to obtain the finite-time state-feedback controller. Finally, a Lotka-Volterra population model is used to show the feasibility and validity of the main results.

Adaptive-Critic Design for Decentralized Event-Triggered Control of Constrained Nonlinear Interconnected Systems Within an Identifier-Critic Framework

This article studies the decentralized event-triggered control problem for a class of constrained nonlinear interconnected systems. By assigning a specific cost function for each constrained auxiliary subsystem, the original control problem is equivalently transformed into finding a series of optimal control policies updating in an aperiodic manner, and these optimal event-triggered control laws together constitute the desired decentralized controller. It is strictly proven that the system under consideration is stable in the sense of uniformly ultimate boundedness provided by the solutions of event-triggered Hamilton-Jacobi-Bellman equations. Different from the traditional adaptive critic design methods, we present an identifier-critic network architecture to relax the restrictions posed on the system dynamics, and the actor network commonly used to approximate the optimal control law is circumvented. The weights in the critic network are tuned on the basis of the gradient descent approach as well as the historical data, such that the persistence of excitation condition is no longer needed. The validity of our control scheme is demonstrated through a simulation example.

A data-driven ground fault detection and isolation method for main circuit in railway electrical traction system

Due to the complex and harsh operation conditions, like corrosion, aging cable and static electricity, of electrical traction drive system, ground fault will generate large short circuit current to harm the key components. Effective fault diagnosis is important, but also challenging. The conventional method used for ground fault detection only takes advantage of voltage measurements of DC-link. Other measurements onboard are also available, which are correlated with the voltage measurements. Taking the correlation into account will improve the detection performance. To this end, this paper presents a data-driven solution, which makes full use of the correlation between the voltage measurements with other measurements onboard. The proposed method consists of two components: (1) a canonical correlation analysis-based fault detection method, which takes into account the correlation within measurements; (2) a fault isolation method by means of the fault direction, which can be obtained with the available faulty data stored in the long-term operation. The developed method is applied to a traction drive system. It is shown that the proposed approach is able to improve the fault detection and isolation performance significantly with respect to three performance indicators, namely fault detection rate, detection delay and correct isolation rate, in comparison with the conventional method, which only uses the voltage measurements of DC-link.

An adaptive reinforcement learning-based multimodal data fusion framework for human-robot confrontation gaming

Playing games between humans and robots have become a widespread human-robot confrontation (HRC) application. Although many approaches were proposed to enhance the tracking accuracy by combining different information, the problems of the intelligence degree of the robot and the anti-interference ability of the motion capture system still need to be solved. In this paper, we present an adaptive reinforcement learning (RL) based multimodal data fusion (AdaRL-MDF) framework teaching the robot hand to play Rock-Paper-Scissors (RPS) game with humans. It includes an adaptive learning mechanism to update the ensemble classifier, an RL model providing intellectual wisdom to the robot, and a multimodal data fusion structure offering resistance to interference. The corresponding experiments prove the mentioned functions of the AdaRL-MDF model. The comparison accuracy and computational time show the high performance of the ensemble model by combining k-nearest neighbor (k-NN) and deep convolutional neural network (DCNN). In addition, the depth vision-based k-NN classifier obtains a 100% identification accuracy so that the predicted gestures can be regarded as the real value. The demonstration illustrates the real possibility of HRC application. The theory involved in this model provides the possibility of developing HRC intelligence.

Finite- and Fixed-Time Cluster Synchronization of Nonlinearly Coupled Delayed Neural Networks via Pinning Control

In this article, the cluster synchronization problem for a class of the nonlinearly coupled delayed neural networks (NNs) in both finite- and fixed-time cases are investigated. Based on the Lyapunov stability theory and pinning control strategy, some criteria are provided to ensure the cluster synchronization of the nonlinearly coupled delayed NNs in both finite-and fixed-time aspects. Then, the settling time for stabilization that is dependent on the initial value and independent of the initial value is estimated, respectively. Finally, we illustrate the feasibility and practicality of the results via a numerical example.

Fuzzy-Model-Based Sliding Mode Control of Nonlinear Descriptor Systems

This paper addresses the problem of sliding mode control (SMC) for a type of uncertain time-delay nonlinear descriptor systems represented by T-S fuzzy models. One crucial contributing factor is to put forward a novel integral fuzzy switching manifold involved with time delay. Compared with previous results, the key benefit of the new manifold is that the input matrices via different subsystems are permitted to be diverse, and thus much more applicability will be achieved. By resorting to Frobenius' theorem and double orthogonal complement, the existence condition of the fuzzy manifold is presented. The admissibility conditions of sliding motion with a strictly dissipative performance are further provided. Then, the desired fuzzy SMC controller is synthesized by analyzing the reachability of the manifold. Moreover, an adaptive fuzzy SMC controller is also proposed to adapt the input saturation and the matched uncertainty with unknown upper bounds. The feasibility and virtue of our theoretical findings are demonstrated by a fuzzy SMC controller implementation for a practical system about the pendulum.

Mutual-Collision-Avoidance Scheme Synthesized by Neural Networks for Dual Redundant Robot Manipulators Executing Cooperative Tasks

Collision between dual robot manipulators during working process will lead to task failure and even robot damage. To avoid mutual collision of dual robot manipulators while doing collaboration tasks, a novel recurrent neural network (RNN)-based mutual-collision-avoidance (MCA) scheme for solving the motion planning problem of dual manipulators is proposed and exploited. Because of the high accuracy and low computation complexity, the linear variational inequality-based primal-dual neural network is used to solve the proposed scheme. The proposed scheme is applied to the collaboration trajectory tracking and cup-stacking tasks, and shows its effectiveness for avoiding collision between the dual robot manipulators. Through network iteration and online learning, the dual robot manipulators will learn the ability of MCA. Moreover, a line-segment-based distance measure algorithm is proposed to calculate the minimum distance between the dual manipulators. If the computed minimum distance is less than the first safe-related distance threshold, a speed brake operation is executed and guarantees that the robot cannot exceed the second safe-related distance threshold. Furthermore, the proposed MCA strategy is formulated as a standard quadratic programming problem, which is further solved by an RNN. Computer simulations and a real dual robot experiment further verify the effectiveness, accuracy, and physical realizability of the RNN-based MCA scheme when manipulators cooperatively execute the end-effector tasks.

H∞ consensus and synchronization of nonlinear systems based on a novel fuzzy model

This paper investigates the H∞ consensus control problem of nonlinear multiagent systems under an arbitrary topological structure. A novel Takagi-Sukeno (T-S) fuzzy modeling method is proposed to describe the problem of nonlinear follower agents approaching a time-varying leader, i.e., the error dynamics between the follower agents and the leader, whose dynamics is evolving according to an isolated unforced nonlinear agent model, is described as a set of T-S fuzzy models. Based on the model, a leader-following consensus algorithm is designed so that, under an arbitrary network topology, all the follower agents reach consensus with the leader subject to external disturbances, preserving a guaranteed H(∞) performance level. In addition, we obtain a sufficient condition for choosing the pinned nodes to make the entire multiagent network reach consensus. Moreover, the fuzzy modeling method is extended to solve the synchronization problem of nonlinear systems, and a fuzzy H(∞) controller is designed so that two nonlinear systems reach synchronization with a prescribed H(∞) performance level. The controller design procedure is greatly simplified by utilization of the proposed fuzzy modeling method. Finally, numerical simulations on chaotic systems and arbitrary nonlinear functions are provided to illustrate the effectiveness of the obtained theoretical results.

Adaptive Control of Nonlinear Semi-Markovian Jump T-S Fuzzy Systems With Immeasurable Premise Variables via Sliding Mode Observer

The issue of observer-based adaptive sliding mode control of nonlinear Takagi-Sugeno fuzzy systems with semi-Markov switching and immeasurable premise variables is investigated. More general nonlinear systems are described in the model since the selections of premise variables are the states of the system. First, a novel integral sliding surface function is proposed on the observer space, then the sliding mode dynamics and error dynamics are obtained in accordance with estimated premise variables. Second, sufficient conditions for stochastic stability with an H_∞ performance disturbance attenuation level γ of the sliding mode dynamics with different input matrices are obtained based on generally uncertain transition rates. Third, an observer-based adaptive controller is synthesized to ensure the finite time reachability of a predefined sliding surface. Finally, the single-link robot arm model is provided to verify the control scheme numerically.

Deep learning-based open set multi-source domain adaptation with complementary transferability metric for mechanical fault diagnosis

Intelligent fault diagnosis aims to build robust mechanical condition recognition models with limited dataset. At this stage, fault diagnosis faces two practical challenges: (1) the variability of mechanical working conditions makes the collected data distribution inconsistent, which brings about the domain shift; (2) some unpredictable unknown fault modes that do not observe in the training dataset may occur in the testing scenario, leading to a category gap. In order to cope with these two entangled challenges, an open set multi-source domain adaptation approach is developed in this study. Specifically, a complementary transferability metric defined on multiple classifiers is introduced to quantify the similarity of each target sample to known classes to weight the adversarial mechanism. By applying an unknown mode detector, unknown faults can be automatically identified. Moreover, a multi-source mutual-supervised strategy is further adopted to mine relevant information between different sources to enhance the model performance. Extensive experiments are conducted on three rotating machinery datasets, and the results show that the proposed method is superior to traditional domain adaptation approaches in the mechanical diagnosis issues that new fault modes occur.

Robot path planning based on artificial potential field with deterministic annealing

In the context of motion planning in robotics, the problem of path planning based on artificial potential fields has been examined using different algorithms to avoid trapping in local minima. With this objective, this paper proposes a novel method based on a deterministic annealing strategy to improve the potential field function by introducing a temperature parameter to increase the robot's obstacle avoidance efficiency. The annealing and tempering strategies prevent the robot from being trapped at the local minima and allow it to continue towards its destination. The initial path is optimised using an annealing algorithm to enhance the overall performance. The time, length and success rate of the planned path measures the quality of the solution. Simulation results and comparative experiments demonstrate that the proposed algorithm can solve path planning in different environments. The proposed algorithm is suitable for complex environments with convex or non-convex polygon obstacles.

Fuzzy Output Tracking Control and Filtering for Nonlinear Discrete-Time Descriptor Systems Under Unreliable Communication Links

In this paper, the problems of output tracking control and filtering are investigated for Takagi-Sugeno fuzzy-approximation-based nonlinear descriptor systems in the discrete-time domain. Especially, the unreliability of the communication links between the sensor and actuator/filter is taken into account, and the phenomenon of packet dropouts is characterized by a binary Markov chain with uncertain transition probabilities, which may reflect the reality more accurately than the existing description processes. A novel bounded real lemma (BRL), which ensures the stochastic admissibility with H_∞ performance for fuzzy discrete-time descriptor systems despite the uncertain Markov packet dropouts, is presented based on a fuzzy basis-dependent Lyapunov function. By resorting to the dual conditions of the obtained BRL, a solution for the designed fuzzy output tracking controller is given. A design method for the full-order fuzzy filter is also provided. Finally, two examples are finally adopted to show the applicability of the achieved design strategies.

Mixed H2/Hinfinity output-feedback control of second-order neutral systems with time-varying state and input delays

A mixed H2/Hinfinity output-feedback control design methodology is presented in this paper for second-order neutral linear systems with time-varying state and input delays. Delay-dependent sufficient conditions for the design of a desired control are given in terms of linear matrix inequalities (LMIs). A controller, which guarantees asymptotic stability and a mixed H2/Hinfinity performance for the closed-loop system of the second-order neutral linear system, is then developed directly instead of coupling the model to a first-order neutral system. A Lyapunov-Krasovskii method underlies the LMI-based mixed H2/Hinfinity output-feedback control design using some free weighting matrices. The simulation results illustrate the effectiveness of the proposed methodology.

Robust Stabilization of Delayed Neural Networks: Dissipativity-Learning Approach

This paper examines the robust stabilization problem of continuous-time delayed neural networks via the dissipativity-learning approach. A new learning algorithm is established to guarantee the asymptotic stability as well as the (Q,S,R) - α -dissipativity of the considered neural networks. The developed result encompasses some existing results, such as H_∞ and passivity performances, in a unified framework. With the introduction of a Lyapunov-Krasovskii functional together with the Legendre polynomial, a novel delay-dependent linear matrix inequality (LMI) condition and a learning algorithm for robust stabilization are presented. Demonstrative examples are given to show the usefulness of the established learning algorithm.

Effects of Passive- and Active-Modified Atmosphere Packaging on Physio-Chemical and Quality Attributes of Fresh In-Hull Pistachios (Pistacia vera L. cv. Badami)

The effects of passive- and active-modified atmosphere packaging (passive- and active-MAP) were investigated on the physio-chemical and quality attributes of fresh in-hull pistachios stored at 4 ± 1 °C and 90 ± 5% R.H. Fresh pistachios were packaged under each of the following gas combinations: active-MAP1 (AMA1) (5% O2 + 5% CO2), AMA2 (5% O2 + 25% CO2), AMA3 (5% O2 + 45% CO2), AMA4 (2.5% O2 + 5% CO2), AMA5 (2.5% O2 + 25% CO2), and AMA6 (2.5% O2 + 45% CO2), all balanced with N2, as well as passive-MAP (PMA) with ambient air (21% O2 + 0.03% CO2 + 78% N2). Changes in quality parameters were evaluated after 0, 15, 30 and 45 days of storage. Results demonstrated that AMA6 and PMA had significantly lower (7.96 Log CFU g-1) and higher (9.81 Log CFU g-1) aerobic mesophilic bacteria counts than the other treatments. However, the AMA6 treatment decreased, kernel chlorophyll and carotenoid content, hull antioxidant capacity, and anthocyanin content. The PMA treatment produced a significant weight loss, 0.18%, relative to the other treatments. The active-MAP treatments were more effective than the passive-MAP in decreasing weight loss, microbial counts, kernel total chlorophyll (Kernel TCL), and kernel carotenoid content (Kernel CAC). The postharvest quality of fresh in-hull pistachios was maintained best by the AMA3 (5% O2 + 45% CO2 + 50% N2) treatment.

Region Stabilization of Switched Neural Networks With Multiple Modes and Multiple Equilibria: A Pole Assignment Method

This article investigates region stabilization issue of switched neural networks (SNNs) with multiple modes (MMs) and multiple equilibria (ME) via a pole assignment method. In such an SNN, every neuron is observed with more than one mode and unstable equilibrium point. First, SNNs with MMs and ME are modeled in terms of switched systems with unstable subsystems and ME. Second, a necessary and sufficient condition and a sufficient condition are, respectively, proposed for arbitrary switching paths pole assignment and arbitrary periodic/quasi-periodic switching paths (PSPs/QSPs) asymptotically region stabilizing pole assignment of switched linear time-invariant (LTI) systems with ME. It is shown that to stabilize a switched LTI system, some/all poles of all/some linear subsystems can be assigned to suitable locations of the right-half side of the complex plane. Third, based on the obtained pole assignment results, an asymptotical-region-stabilizing-control law observed as distributed state feedback controllers of MMs, asymptotical-region-stabilizing PSPs/QSPs, and a corresponding algorithm are all designed for asymptotical region stabilization of switched linear/nonlinear neural networks with MMs and ME. Finally, a numeral example is given to illustrate the effectiveness and practicality of the new results.