Data-driven subspace predictive control: Stability and horizon tuning

Data-driven Subspace Predictive Control (SPC) is an advanced model-free process control strategy in the presence of system constraints. Efficient implementation of SPC requires appropriate tuning of the controller horizons, which are called Prediction Horizon and Control Horizon. This tuning is a critical step to guarantee the SPC closed-loop stability and to enhance the closed-loop performance and robustness. In this paper we propose an optimal tuning method for unconstrained SPC, which can guarantee stability, computational efficiency and optimality of the unconstrained SPC closed-loop system and is applicable to non-minimum phase open-loop stable or marginally stable systems. Derivation of general form of closed-loop transfer function for unconstrained SPC, and providing a necessary and sufficient condition of the closed-loop stability is the primary contribution of this work. In addition, the stability analysis enabled us to propose an algorithm to determine the shortest-feasible-prediction-horizon and the feasible range of prediction horizon. Consequently, these results are used in proposing a new algorithm to determine the SPC horizons in optimal manner. Simulation results illustrate effectiveness and importance of our proposed stability analysis and horizons tuning algorithm for unconstrained SPC.     

Iterative learning control for linear delay systems with deterministic and random impulses

This paper investigates convergence of iterative learning control for linear delay systems with deterministic and random impulses by virtute of the representation of solutions involving a concept of delayed exponential matrix. We address linear delay systems with deterministic impulses by designing a standard P-type learning law via rigorous mathematical analysis. Next, we extend to consider the tracking problem for delay systems with random impulses under randomly varying length circumstances by designing two modified learning laws. We present sufficient conditions for both deterministic and random impulse cases to guarantee the zero-error convergence of tracking error in the sense of Lebesgue-p norm and the expectation of Lebesgue-p norm of stochastic variable, respectively. Finally, numerical examples are given to verify the theoretical results.     

Adaptive and online network intrusion detection system using clustering and Extreme Learning Machines

Despite the large volume of research conducted in the field of intrusion detection, finding a perfect solution of intrusion detection systems for critical applications is still a major challenge. This is mainly due to the continuous emergence of security threats which can bypass the outdated intrusion detection systems. The main objective of this paper is to propose an adaptive design of intrusion detection systems on the basis of Extreme Learning Machines. The proposed system offers the capability of detecting known and novel attacks and being updated according to new trends of data patterns provided by security experts in a cost-effective manner.     

Composite cooperative synchronization and decentralized learning of multi-robot manipulators with heterogeneous nonlinear uncertain dynamics

This paper studies the problem of composite synchronization and learning of multiple coordinated robot manipulators subject to heterogeneous nonlinear uncertain dynamics under the leader-follower framework. A new two-layer distributed adaptive learning control scheme is proposed, which consists of the first-layer distributed cooperative estimator and the second-layer decentralized deterministic learning controller. The first layer aims to enable each robotic agent to estimate the leader’s information. The second layer is responsible for not only controlling each individual robotic agent to track over desired reference trajectory, but also accurately identifying/learning each robot’s nonlinear uncertain dynamics. Design and implementation of this two-layer distributed controller can be carried out in a fully-distributed manner, which do not require any global information including global connectivity of the communication network. The Lyapunov method is applied to rigorously analyze stability and parameter convergence of the resulting closed-loop system. Numerical simulations on a team of two-degree-of-freedom robot manipulators have been conducted to demonstrate the effectiveness of the proposed results.     

Adaptive iterative learning protocol design for nonlinear multi-agent systems with unknown control direction

This paper investigates a new adaptive iterative learning control protocol design for uncertain nonlinear multi-agent systems with unknown gain signs. Based on Nussbaum gain, adaptive iterative learning control protocols are designed for each follower agent and the adaptive laws depend on the information available from the agents in the neighbourhood. The proper protocols guarantee each follower agent track the leader perfectly on the finite time interval and the Nussbaum-type item can seek control direction adaptively. Furthermore, the formation problem is studied as an extension. Finally, simulation examples are given to demonstrate the effectiveness of the proposed method in this article.     

A clustering algorithm based TS fuzzy model for tracking dynamical system data

This paper presents an optimal fuzzy partition based Takagi Sugeno Fuzzy Model (TSFM) in which a novel clustering algorithm, known as Modified Fuzzy C-Regression Model (MFCRM), has been proposed. The objective function of MFCRM algorithm has been developed by considering of geometrical structure of input data and linear functional relation between input–output data. The MFCRM partitions the data space to create fuzzy subspaces (rules). A new validation criterion has been developed for detecting the right number of rules (subspaces) in a given data set. The obtained fuzzy partition is used to build the fuzzy structure and identify the premise parameters. Once, right number of rules and premise parameters have been identified, then consequent parameters have been identified by orthogonal least square (OLS) approach. The cluster validation index has been tested on synthetic data set. The effectiveness of MFCRM based TSFM has been validated on benchmark examples, such as Boiler Turbine system, Mackey–Glass time series data and Box–Jenkins model. The model performance is also validated through high-dimensional data such as Auto-MPG data and Boston Housing data.     

An adaptive online learning algorithm for distributed convex optimization with coupled constraints over unbalanced directed graphs

This paper investigates a distributed optimization problem over multi-agent networks subject to both local and coupled constraints in a non-stationary environment, where a set of agents aim to cooperatively minimize the sum of locally time-varying cost functions when the communication graphs are time-changing connected and unbalanced. Based on dual decomposition, we propose a distributed online dual push-sum learning algorithm by incorporating the push-sum protocol into dual gradient method. We then show that the regret bound has a sublinear growth of O(T^p) and the constraint violation is also sublinear with order of $O\left(T^{1?p/2}\right),$ where T is the time horizon and 0 < p ≤ 1/2. Finally, simulation experiments on a plug-in electric vehicle charging problem are utilized to verify the performance of the proposed algorithm. The proposed algorithm is adaptive without knowing the total number of iterations T in advance. The convergence results are established on more general unbalanced graphs without the boundedness assumption on dual variables. In addition, more privacy concerns are guaranteed since only dual variables related with coupled constraints are exchanged among agents.     

Iterative learning control for fractional-order multi-agent systems

In this paper, we apply iterative learning control to both linear and nonlinear fractional-order multi-agent systems to solve consensus tacking problem. Both fixed and iteration-varying communicating graphs are addressed in this paper. For linear systems, a PD^α-type update law with initial state learning mechanism is introduced by virtue of the memory property of fractional-order derivative. For nonlinear systems, a D^α-type update law with forgetting factor and initial state learning is designed. Sufficient conditions for both linear and nonlinear systems are established to guarantee all agents achieving the asymptotic output consensus. Simulation examples are provided to verify the proposed schemes.     

Extended dissipative learning of time-delay recurrent neural networks

The paper addresses the issue of extended dissipative learning for a class of delayed recurrent neural networks. Both time-varying delay and time-invariant delay are taken into account. By choosing appropriate Lyapunov–Krasovkii functionals and utilizing some inequalities, several weight learning rules are developed for ensuring the network to be asymptotically stable and extended dissipative. The existence conditions for these learning strategies consist of a few linear matrix inequalities, which are able to be verified readily by Matlab software. Two numerical examples are employed to show the effectiveness and low conservatism of the proposed learning rules.     

Bayesian network based extreme learning machine for subjectivity detection

Subjectivity detection is a task of natural language processing that aims to remove ‘factual’ or ‘neutral’ content, i.e., objective text that does not contain any opinion, from online product reviews. Such a pre-processing step is crucial to increase the accuracy of sentiment analysis systems, as these are usually optimized for the binary classification task of distinguishing between positive and negative content. In this paper, we extend the extreme learning machine (ELM) paradigm to a novel framework that exploits the features of both Bayesian networks and fuzzy recurrent neural networks to perform subjectivity detection. In particular, Bayesian networks are used to build a network of connections among the hidden neurons of the conventional ELM configuration in order to capture dependencies in high-dimensional data. Next, a fuzzy recurrent neural network inherits the overall structure generated by the Bayesian networks to model temporal features in the predictor. Experimental results confirmed the ability of the proposed framework to deal with standard subjectivity detection problems and also proved its capacity to address portability across languages in translation tasks.     

Global dissipativity and quasi-synchronization of asynchronous updating fractional-order memristor-based neural networks via interval matrix method

This paper investigates the global dissipativity and quasi-synchronization of asynchronous updating fractional-order memristor-based neural networks (AUFMNNs) via interval matrix method. First, a new class of FMNNs named AUFMNNs is proposed for the first time, in which the switching jumps are asymmetric. In other words, each memristive connection weight is updated based on its own channel and hence the number of the subsystems increases significantly from 2ⁿ to $2^{2n^2}$. Under the framework of fractional-order differential inclusions, the proposed AUFMNNs can be regarded as a system with interval parameters. Then, the global dissipativity criterion is established by constructing appropriate Lyapunov function in combination with the estimates of 2-norm for interval matrices and some fractional-order differential inequalities. In addition, for drive-response AUFMNNs with mismatched parameters, the problem of quasi-synchronization is explored via linear state feedback control. It has been shown that complete synchronization between two AUFMNNs cannot be achieved via linear feedback control and that the synchronization error bound can be controlled within a relatively small level by selecting suitable control parameters. Finally, three numerical examples are given to demonstrate the effectiveness and the improvement of the obtained results.     

Improved stability criteria for sampled-data systems using modified free weighting matrix

This paper investigates the stability analysis of sampled-data systems in the looped-functional framework. A modified free-weighting matrix inequality with quadratic-type is proposed to reduce conservatism of the integral term. Based on new looped-functional, improved conditions are derived in terms of linear matrix inequalities (LMIs) by utilizing the proposed integral inequality. Numerical examples show the superiority of the proposed condition through comparisons with the most recent results.     

Distributed cooperative learning for a group of uncertain systems via output feedback and neural networks

This paper studies the problem of adaptive neural network (NN) output-feedback control for a group of uncertain nonlinear multi-agent systems (MASs) from the viewpoint of cooperative learning. It is assumed that all MASs have identical unknown nonlinear dynamic models but carry out different periodic control tasks, i.e., each agent system has its own periodic reference trajectory. By establishing a network topology among systems, we propose a new consensus-based distributed cooperative learning (DCL) law for the unknown weights of radial basis function (RBF) neural networks appearing in output-feedback control laws. The main advantage of such a learning scheme is that all estimated weights converge to a small neighborhood of the optimal value over the union of all system estimated state orbits. Thus, the learned NN weights have better generalization ability than those obtained by traditional NN learning laws. Our control approach also guarantees the convergence of tracking errors and the stability of closed-loop system. Under the assumption that the network topology is undirected and connected, we give a strict proof by verifying the cooperative persisting excitation condition of RBF regression vectors. This condition is defined in our recent work and plays a key role in analyzing the convergence of adaptive parameters. Finally, two simulation examples are provided to verify the effectiveness and advantages of the control scheme proposed in this paper.     

Trajectory tracking control for rotary steerable systems using interval type-2 fuzzy logic and reinforcement learning

Rotary steerable system (RSS) is a directional drilling technique which has been applied in oil and gas exploration under complex environment for the requirements of fossil energy and geological prospecting. The nonlinearities and uncertainties which are caused by dynamical device, mechanical structure, extreme downhole environment and requirements of complex trajectory design in the actual drilling work increase the difficulties of accurate trajectory tracking. This paper proposes a model-based dual-loop feedback cooperative control method based on interval type-2 fuzzy logic control (IT2FLC) and actor-critic reinforcement learning (RL) algorithms with one-order digital low-pass filters (LPF) for three-dimensional trajectory tracking of RSS. In the proposed RSS trajectory tracking control architecture, an IT2FLC is utilized to deal with system nonlinearities and uncertainties, and an online iterative actor-critic RL controller structured by radial basis function neural networks (RBFNN) and adaptive dynamic programming (ADP) is exploited to eliminate the stick–slip oscillations relying on its approximate properties both in action function (actor) and value function (critic). The two control effects are fused to constitute cooperative controller to realize accurate trajectory tracking of RSS. The effectiveness of our controller is validated by simulations on designed function tests for angle building hole rate and complete downhole trajectory tracking, and by comparisons with other control methods.     

Terminal iterative learning control for discrete-time nonlinear systems based on neural networks

The terminal iterative learning control is designed for nonlinear systems based on neural networks. A terminal output tracking error model is obtained by using a system input and output algebraic function as well as the differential mean value theorem. The radial basis function neural network is utilized to construct the input for the system. The weights are updated by optimizing an objective function and an auxiliary error is introduced to compensate the approximation error from the neural network. Both time-invariant input case and time-varying input case are discussed in the note. Strict convergence analysis of proposed algorithm is proved by the Lyapunov like method. Simulations based on train station control problem and batch reactor are provided to demonstrate the effectiveness of the proposed algorithms.     

P-type iterative learning control algorithm for a class of linear singular impulsive systems

This paper is focused on the iterative learning control problem for linear singular impulsive systems. For the purpose of tracking the desired output trajectory, a P-type iterative learning control algorithm is investigated for such system. Based on the fundamental property of singular impulsive systems and the restricted equivalent transformation theory of singular systems, the convergence conditions of the tracking errors for the system are obtained in the sense of λ norm. Finally, the validation of the algorithm is confirmed by a numerical example.     

Symmetric least squares solution of a class of Sylvester matrix equations via MINIRES algorithm

The purpose of this paper is deriving the minimal residual (MINIRES) algorithm for finding the symmetric least squares solution on a class of Sylvester matrix equations. We prove that if the system is inconsistent, the symmetric least squares solution can be obtained within finite iterative steps in the absence of round-off errors. Furthermore, we provide a method for choosing the initial matrix to obtain the minimum norm least squares symmetric solution of the problem. Finally, we give some numerical examples to illustrate the performance of MINIRES algorithm.     

The relaxed gradient-based iterative algorithms for a class of generalized coupled Sylvester-conjugate matrix equations

In this paper, two relaxed gradient-based iterative algorithms for solving a class of generalized coupled Sylvester-conjugate matrix equations are proposed. The proposed algorithm is different from the gradient-based iterative algorithm and the modified gradient-based iterative algorithm that are recently available in the literature. With the real representation of a complex matrix as a tool, the sufficient and necessary condition for the convergence factor is determined to guarantee that the iterative solution given by the proposed algorithms converge to the exact solution for any initial matrices. Moreover, some sufficient convergence conditions for the suggested algorithms are presented. Finally, numerical example is provided to illustrate the effectiveness of the proposed algorithms and testify the conclusions suggested in this paper.