This paper presents a hardware implementation of multilayer feedforward neural networks (NN) using reconfigurable field-programmable gate arrays (FPGAs). Despite improvements in FPGA densities, the numerous multipliers in an NN limit the size of the network that can be implemented using a single FPGA, thus making NN applications not viable commercially. The proposed implementation is aimed at reducing resource requirement, without much compromise on the speed, so that a larger NN can be realized on a single chip at a lower cost. The sequential processing of the layers in an NN has been exploited in this paper to implement large NNs using a method of layer multiplexing. Instead of realizing a complete network, only the single largest layer is implemented. The same layer behaves as different layers with the help of a control block. The control block ensures proper functioning by assigning the appropriate inputs, weights, biases, and excitation function of the layer that is currently being computed. Multilayer networks have been implemented using Xilinx FPGA "XCV400hq240". The concept used is shown to be very effective in reducing resource requirements at the cost of a moderate overhead on speed. This implementation is proposed to make NN applications viable in terms of cost and speed for online applications. An NN-based flux estimator is implemented in FPGA and the results obtained are presented.

No abstract

Printed Circuit Boards (PCB) plays the important role in the development of electronic devices. PCB provides mechanical support and electrically connects electronic components using conductive tracks. Faults in the PCB may cause the entire system failure. It is necessary to identify the faults in the PCB's before installing to the system. Fault detection of wrong component in the assembled PCB is very important. This is one of the important stages which give the results of PCB processing. There are many techniques are used in fault detection and for missing components in the assembled PCB. In this paper we present the Automated Inspection System for assembled Printed Circuit Board. Automated inspection system implemented using template matching technique to inspect the assembled PCB and to find the missing components. It is very fast and accurate. It detects of any missing components, verify the physical dimension of the component and detailed check sheet extracted. This current work LabVIEW NI vision software has been used to implement PCB inspection.

No abstract

No abstract