Search

In recent years, there has been a significant increase in the number of control system techniques that are based on nonlinear concepts. One such method is the nonlinear inverse model based control strategy. This method is dependent on the availability of the inverse of the system model. Since neural networks have the ability to model any nonlinear system including their inverses and their use in this control scheme is promising. In the present paper, direct inverse neural network control strategy for controlling the CSTR with van de vusse reaction is studied. The direct inverse NN control strategy utilizes the process inverse model as controller. For training the neural network, the process input-output data is generated by applying a pseudo random signal on a simulink model of the CSTR process. Then, the input-output data is divided into two parts for training & validation. Training is performed using the Levenberg-Marquardt method. Based on the SSE, the optimum number of hidden nodes is taken as ten. The model obtained after the training is inverse NN model, which is taken as NN based controller. The performance of proposed NN based controller is evaluated for servo and regulatory control problems through simulation studies. Through the closed loop simulation studies, it is found that neural network based direct inverse control strategy gives superior performance to PID controller for setpoint changes. To improve the performance of direct inverse NN controller for regulatory problem, the IMC structured with forward and inverse NN models are included in the closed loop system. [ABSTRACT FROM AUTHOR]

Aglaia bourdillonii is a plant narrowly endemic to the southern portion of the Western Ghats (WG), in peninsular India. To understand its ecological and geographic distribution, we used ecological niche modeling (ENM) based on detailed distributional information recently gathered, in relation to detailed climatic data sets. The ENMs successfully reconstructed key features of the species' geographic distribution, focusing almost entirely on the southern WG. Much of the species' distributional potential is already under protection, but our analysis allows identification of key zones for additional protection, all of which are adjacent to existing protected areas. ENM provides a useful tool for understanding the natural history of such rare and endangered species. [ABSTRACT FROM AUTHOR]

This paper presents a complete asymptotic analysis of a simple model for the evolution of the nocturnal temperature distribution on bare soil in calm clear conditions. The model is based on a simplified flux emissivity scheme that provides a nondiffusive local approximation for estimating longwave radiative cooling near ground. An examination of the various parameters involved shows that the ratio of the characteristic radiative to the diffusive timescale in the problem is of order 10−3, and can therefore be treated as a small parameter (μ). Certain other plausible approximations and linearization lead to a new equation whose asymptotic solution as l μ → 0 can be written in closed form. Four regimes, consisting of a transient at nominal sunset, a radiative-diffusive boundary (‘Ramdas') layer on ground, a boundary layer transient and a radiative outer solution, are identified. The asymptotic solution reproduces all the qualitative features of more exact numerical simulations, including the occurrence of a lifted temperature minimum and its evolution during night, ranging from continuing growth to relatively sudden collapse of the Ramdas layer. [ABSTRACT FROM AUTHOR]