A neural-network-based terminal sliding-mode control (SMC) scheme is proposed for robotic manipulators including actuator dynamics. The SMC (TSMC) alleviates some main drawbacks (such as contradiction between efforts in the transient and tracking errors steady state) linear while maintains its robustness to uncertainties. Moreover, an indirect method developed avoid singularity problem initial TSMC. In scheme, a radial basis function neural network (NN) adopted approximate nonlinear dynamics...

In this paper, output feedback adaptive neural network (NN) controls are investigated for two classes of nonlinear discrete-time systems with unknown control directions: 1) pure-feedback and 2) autoregressive moving average exogenous inputs (NARMAX) systems. To overcome the noncausal problem, which has been known to be a major obstacle in design, both transformed predictor design. Implicit function theorem is used difficulty nonaffine appearance input. The problem lacking priori knowledge on...

This paper presents a novel nonlinear control strategy for class of uncertain single-input and single-output discrete-time systems with unstable zero-dynamics. The proposed method combines adaptive-network-based fuzzy inference system (ANFIS) multiple models, where linear robust controller, an ANFIS-based controller switching mechanism are integrated using models technique. It has been shown that the can ensure boundedness input output signals improve dynamic performance closed loop system....

The electronic throttle system (ETS) is one of the important components an automobile engine that adjust air intake to directly affect combustion power engine. In practical scenarios, proportional–integral–derivative (PID) a common and effective method. However, traditional PID difficult satisfy ETS performance requirements, e.g., response overshoot not allowed exist. Moreover, controller gains are also tune manually. To tackle abovementioned issues, we propose signal compensation control...

Taking account of reheating furnaces being multivariable systems with strong coupling and large time delay, the paper applied a decoupling technique Smith compensation to control furnace temperature. Experiments indicate that this proposed strategy can improve performance temperature greatly.

The component concentrations measurement of sodium aluminate solution are critical to the process alumina production, they affect product quality. However, can not be measured online at present, thus control and optimal operation is hardly achieved. This paper presents an on-line fuzzy modeling method predict concentrations. It includes clustering approach which applied in a general class TKS models. Stable learning algorithms for premise consequence parts rules also given. A measuring...

This paper presents the newly developed water level control system for drum boiler using fuzzy strategy. The major dynamics of include nonlinearities, nonminimum phase behavior, instabilities, time delays, and load disturbances. A weighted algorithm logic strategy is applied to steam GPE (Gaussian partition with evenly spaced midpoints) system. controller has been tested in a real plant results obtained are shown.

A fuzzy logic-based, multi-input/multi-output expert controller has been designed for laminar water curtain controlled cooling system at the Anshan Steel Corporation. This can automatically find specified working points under boundary conditions instead of obtaining them from a lot experiments. On basis these points, linearized models be used to determine control variables. The simulation results show that an excellent performance and in practical environment.

A novel technique, using neural networks, is proposed for the adaptive control of a class nonlinear nonminimum phase systems. Using Taylor expansion, system can be regarded as linear with measurable disturbance. Pole-placement used to stabilize system, and network approximate term. Feedforward compensation eliminate steady tracking errors which are caused by

In this paper, a multivariable multiple models direct adaptive decoupling controller is presented to improve the transient response when parameters of system change abruptly. The composed fixed and two models. are derived from corresponding directly guaranteed cover parameter set, without partitioning set again. adopt algorithm reduce design calculation. By choice weighting polynomial matrix, it not only decouples dynamically, but also places poles closed-loop arbitrarily. global convergence...

Aiming at the production technical process of mineral processing and features management considered, this paper takes a thorough research on manufacturing execution system enterprise two layers integrated automation system, proposes framework function to realize optimization indexes design which plan scheduling as main line cost control core indexes. The MES that adopting method is realized integration control. This has been applied minerals plant an iron steel company efficiency increased....