Keskin, A.U.

Note | 2009 | ISA Transactions48 ( 2 ) , pp.143 - 144

A critical comment by Ali Umit Keskin on the paper authored by Khan S. A., Shahani D. T., and Agarwala A. K., titled 'Sensor calibration and compensation using artificial neural network', is presented. One section of the paper by Khan and Agarwala presents artificial neural network (ANN) based solutions to linearize negative temperature coefficient (NTC) thermistor based temperature measurement system. Ali comments that a same paper reporting another approach to the same subject has been published by Chatterjee and Munshi relatively. The authors have used data of an NTC thermistor, with different selected temperature modeling span i . . .n their modeling process. Ali emphasizes that in fact, the beta value is also temperature dependent and it decreases with increasing temperature. He says that the inverse model can be evolved so that combined transfer function of a sensor and its inverse model become unity Daha fazlası Daha az

Tutsoy, O. | Barkana, D.E. | Tugal, H.

Article | 2018 | ISA Transactions76 , pp.67 - 77

In this paper, an adaptive controller is developed for discrete time linear systems that takes into account parametric uncertainty, internal-external non-parametric random uncertainties, and time varying control signal delay. Additionally, the proposed adaptive control is designed in such a way that it is utterly model free. Even though these properties are studied separately in the literature, they are not taken into account all together in adaptive control literature. The Q-function is used to estimate long-term performance of the proposed adaptive controller. Control policy is generated based on the long-term predicted value, and . . . this policy searches an optimal stabilizing control signal for uncertain and unstable systems. The derived control law does not require an initial stabilizing control assumption as in the ones in the recent literature. Learning error, control signal convergence, minimized Q-function, and instantaneous reward are analyzed to demonstrate the stability and effectiveness of the proposed adaptive controller in a simulation environment. Finally, key insights on parameters convergence of the learning and control signals are provided. © 2018 IS Daha fazlası Daha az