Search

The moisture content in agricultural products is very critical. The presence of moisture also affects the quality of agricultural products like rice, wheat, nuts etc. Moisture content in food grains should be reduced and made optimum value otherwise it would encourage fungi development. The development of fungus makes the grain useless. For measuring the capacitance of paddy grains, designed integrated circuit was interfaced with the PC. The arrangement used is a high precision impedance converter. It is a 12 bit frequency generator and 1 Mega samples / sec analog to digital converter. Frequency sweep can be done using the circuit. This converter is interfaced with PC to measure the capacitance of paddy. Initially ceramic capacitors of different values were used to check the designed circuit. Then using the designed circuit, capacitance of representative amount of samples was measured and calculated the moisture content from the obtained readings. The technique is fast, simple, accurate and non-destructive method. Though the method is accurate, there is a slight variation in decimal points and the error was also corrected using Matlab. [ABSTRACT FROM AUTHOR]

The moisture content in agricultural products will affect the quality. Fungi development happens if the moisture content is not optimum. This paper presents a non - destructive, simple, fast and low cost interface circuit to measure the moisture content of paddy grains heated in different temperature. The arrangement used is a high precision impedance converter. Ceramic capacitors of different values were used to check the measuring circuit. Using this circuit, moisture content of representative standard samples was measured and dielectric constant was calculated. The paper discusses the principle, technique, methodology and experimental set up used and the results obtained. [ABSTRACT FROM AUTHOR]

The objective of the paper is to study the implementation of machine learning based controller to control non-linear systems. A smart controller based on reinforcement learning algorithm is proposed, and its performance is demonstrated by using it to control the level of liquid in a non-linear conical tank system. The system is represented in terms of a Markov Decision Process (MDP), and a reinforcement learning technique based on Q-learning algorithm is used to control the process. The advantage is that a standalone controller is designed on its own without prior knowledge of the environment or the system. The hardware implementation of the designed controller showed that the controller controlled the level of fluid in the conical tank efficiently, and rejected random disturbances introduced in the system. This controller provides an edge over PID, fuzzy, and other neural network based controllers, by eliminating the need for linearizing non-linear characteristics, tuning PID parameters, designing transfer functions, and developing fuzzy membership functions. [ABSTRACT FROM AUTHOR]

Electrical capacitance tomography (ECT) is a non destructive technique for obtaining the distribution of some physical quantity in a closed pipe by measuring the permittivity distribution. Several conducting plates are fixed around the circumference of the pipe so they do not disturb the flow or movement of materials. The imaging quality of an electrical capacitance tomography system depends upon many co-influential parameters such as number of electrodes, length and width of electrodes, axial guard electrodes, radial guard electrodes, and screen guard. Optimum selection of these variables coupled with advancements in sensing electronics and imaging algorithm provides the best inside view of a closed vessel/pipe. This, in turn, provides better process information for control. This article is intended to summarize such design rules for ECT electrodes and sensors. Numerical simulations were performed using commercially available finite element method (FEM) software to help verify the optimality of the design parameters chosen. Experimental verification was conducted using a fabricated capacitance sensing circuit that could measure capacitance in the range of 1 fF to 7999 femtofarads with a root means square noise level of 0.07 fF. Some parameters such as the thickness of the pipe are chosen as demanded by the process. This article will be useful for researchers to design the ECT Sensors with ease. [ABSTRACT FROM AUTHOR]

This project discusses the implementation of pressure control on a real time process using fuzzy logic controller. This project aims to develop a control strategy using a fuzzy based controller as an alternative to the existing PI controller in NI LabVIEW. It consists of controlling a certain process in a much simpler and easy manner by taking the control action. This involves designing and tuning of the membership functions and input/output rules. [ABSTRACT FROM AUTHOR]

This paper presents a Hybrid Adaptive Neurofuzzy Control technique for speed control of BLDC motor drives. The proposed controller is an integration of adaptive neurofuzzy, fuzzy PID and PD controllers. The objective is to utilize the best attribute of fuzzy PID and PD controllers, which exhibits a better response than the neurofuzzy controllers. The error back propagation learning algorithm (EBPA) is used to train the data to minimize learning error. To validate the performance of proposed controller, simulations are done in MATLAB and comparison is made with PI, PD and fuzzy PID controllers. In addition, the performance of proposed controller is benchmarked with other controllers reported in the literature. The results of the proposed controller are promising in terms of quick settling time, zero peak overshoot and zero steady state error. [ABSTRACT FROM AUTHOR]