Application of Smith Predictor Based on Single Neural Network in Cold Rolling Shape Control

Flatness is one of the most important criterion factors to evaluate the quality of the steel strip. To improve the strip＇ s flatness quality, the most frequently used methodology is to employ the closed-loop automatic shape control system. However, in the shape control system, the shape-meter is always installed at the down way of the exit of the cold rolling mill and can not sense the changes of the strip flatness in the rolling gap directly. This kind of installation results in the delay of the feedback in the control system. Therefore, the stability and response performance of the system are strongly affected by the delay. At present, there is still no mature way to design controllers for systems with time delay. Although the conventional PID controller used in most practical applications has the capability to compensate the delay, the effect of the compensation is limited, especially for the systems with long time delay. Smith predictor, as a compensator for solving this problem, is now widely used in industry systems. However, the request of highly precise model of the system and the poor adaptive performance to the changes of related parameters limit the application of the Smith predictor in practice. In order to overcome the drawbacks of the Smith predictor, a new Smith predictor based on single neural network PID （SNN-PID） is proposed. Because the single neural network is employed into the Smith predictor to improve the controller＇s self-adaptability, the adaptive capability to the varying parameters of the system is improved. Meanwhile, for the purpose of solving the problems such as time-consuming and complicated calculation of the neural networks in real time, the learning coefficient of neural network is divided into several stages as usually done in expert control system. Therefore, the control system can obtain fast response due to the improved calculation speed of the neural networks. In order to validate the performance of the proposed controller, the experiment is conducted on the shape control system in a 300 mm four-high reversing cold rolling mill. The experimental results show that the SNN-PID with Smith predictor controller can effectively compensate the delay effects and achieve better control performance than the conventional PID controller.

An Adaptive Single Neural Control for Variable Step-Size P&O MPPT of Marine Current Turbine System

Marine current energy has been increasingly used because of its predictable higher power potential.Owing to the external disturbances of various flow velocity and the high nonlinear effects on the marine current turbine(MCT)system,the nonlinear controllers which rely on precise mathematical models show poor performance under a high level of parameters’uncertainties.This paper proposes an adaptive single neural control(ASNC)strategy for variable step-size perturb and observe(P&O)maximum power point tracking(MPPT)control.Firstly,to automatically update the neuron weights of SNC for the nonlinear systems,an adaptive mechanism is proposed to adaptively adjust the weighting and learning coefficients.Secondly,aiming to generate the exact reference speed for ASNC to extract the maximum power,a variable step-size law based on speed increment is designed to strike a balance between tracking speed and accuracy of P&O MPPT.The robust stability of the MCT control system is guaranteed by the Lyapunov theorem.Comparative simulation results show that this strategy has favorable adaptive performance under variable velocity conditions,and the MCT system operates at maximum power point steadily.

NEW HYDRAULIC ACTUATOR'S POSITION SERVOCONTROL STRATEGY

A new hydraulic actuator-hydraulic muscle （HM） is described, and the actuator＇s features and applications are analyzed, then a position servocontrol system in which HM is main actuator is set up. The mathematical model of the system is built up and several control strategies are discussed. Based on the mathematical model, simulation research and experimental investigation with subsection PID control, neural network self-adaptive PID control and single neuron self-adaptive PID control adopted respectively are carried out, and the results indicate that compared with PID control, neural network self-adaptive PID control and single neuron self-adaptive PID control don＇t need controlled system＇s accurate model and have fast response, high control accuracy and strong robustness, they are very suitable for HM position servo control system.

A Framework for Distributed Semi-supervised Learning Using Single-layer Feedforward Networks

This paper aims to propose a framework for manifold regularization(MR) based distributed semi-supervised learning(DSSL) using single layer feed-forward neural network(SLFNN). The proposed framework, denoted as DSSL-SLFNN is based on the SLFNN, MR framework, and distributed optimization strategy. Then, a series of algorithms are derived to solve DSSL problems. In DSSL problems, data consisting of labeled and unlabeled samples are distributed over a communication network, where each node has only access to its own data and can only communicate with its neighbors. In some scenarios, DSSL problems cannot be solved by centralized algorithms. According to the DSSL-SLFNN framework, each node over the communication network exchanges the initial parameters of the SLFNN with the same basis functions for semi-supervised learning(SSL). All nodes calculate the global optimal coefficients of the SLFNN by using distributed datasets and local updates. During the learning process, each node only exchanges local coefficients with its neighbors rather than raw data. It means that DSSL-SLFNN based algorithms work in a fully distributed fashion and are privacy preserving methods. Finally, several simulations are presented to show the efficiency of the proposed framework and the derived algorithms.

Fuzzy adaptive tracking control within the full envelope for an unmanned aerial vehicle

Motivated by the autopilot of an unmanned aerial vehicle（UAV） with a wide flight envelope span experiencing large parametric variations in the presence of uncertainties, a fuzzy adaptive tracking controller（FATC） is proposed. The controller consists of a fuzzy baseline controller and an adaptive increment, and the main highlight is that the fuzzy baseline controller and adaptation laws are both based on the fuzzy multiple Lyapunov function approach, which helps to reduce the conservatism for the large envelope and guarantees satisfactory tracking performances with strong robustness simultaneously within the whole envelope. The constraint condition of the fuzzy baseline controller is provided in the form of linear matrix inequality（LMI）, and it specifies the satisfactory tracking performances in the absence of uncertainties. The adaptive increment ensures the uniformly ultimately bounded（UUB） predication errors to recover satisfactory responses in the presence of uncertainties. Simulation results show that the proposed controller helps to achieve high-accuracy tracking of airspeed and altitude desirable commands with strong robustness to uncertainties throughout the entire flight envelope.