The aim of this paper is to review the state-of-the-art of Field Programmable Gate Array (FPGA) technologies and their contribution to industrial control applications. Authors start by addressing various research fields which can exploit the advantages of FPGAs. The features of these devices are then presented, followed by their corresponding design tools. To illustrate the benefits of using FPGAs in the case of complex control applications, a sensorless motor controller has been treated. This controller is based on the Extended Kalman Filter. Its development has been made according to a dedicated design methodology, which is also discussed. The use of FPGAs to implement artificial intelligence-based industrial controllers is then briefly reviewed. The final section presents two short case studies of Neural Network control systems designs targeting FPGAs.
1 June 2016 in IEEE Transactions on Industrial Informatics
Gesture recognition is a domain of grate interest of our days due to the multiple application possibilities, from the spatial or subaquatic robots manipulation, to the sign language used for communication by the peoples with hearing or speech disabilities. This paper shows an application of the artificial neural networks (ANN) implemented in field programmable gate arrays (FPGA) for the hand static gestures (postures) recognition. The adopted recognition method uses an ANN structured on two levels. The first level, a feedforward ANN trained using supervised Hebbian algorithm, is used for input data preprocessing. The second one, used for data classification is a competitive ANN. Using an ANN for input data preprocessing offers flexibility regarding the implementation of a preprocessing method. This combination of two ANN leads to 100% recognition rate for the training set and two other sets of test.
The PI algorithm has proven to be a popular and widely used control method, due to its relative simplicity and robustness. Despite this, the linear nature of the algorithm means it doesn't provide optimal control to non-linear systems. This paper presents a novel method of improving the performance of the PI controller using an ANFIS network to provide gain scheduling. This control scheme is applied to a Boost Converter circuit and simulated within the PSIM modelling environment. The simulation results indicate that using the ANFIS controller provides a fast system response with minimal errors even under dynamic operating conditions. The ANFIS controller is also shown to simplify the design flow in comparison to the popular Fuzzy-PI gain scheduling method.
This paper presents a hardware implementation of a multilayer feed-forward neural network based on back-propagation. The implementation is assumed to design and implement modules that emulate FF-BP functions with computing blocks of the predefined System Generator library and user defined blocks integrated in the System Generator library. The main application of the developed structure is an artificial olfactory system used to recognize the type of coffee presented in a test chamber. Data acquisition was achieved through the PC-MIO-16E-1 acquisition card and a virtual instrument, developed in Labview, for signal pre-processing and data logging into text files. The patterns presented (the type of coffee) have been recognized through neural networks. In order to select the RNA with the highest accuracy in recognising the coffee type, several different RNAs were simulated.