This article introduces a method for realizing the Gaussian activation function of radial-basis (RBF) neural networks with their hardware implementation on field-programmable gaits area (FPGAs). The results of modeling of the Gaussian function on FPGA chips of different families have been presented. RBF neural networks of various topologies have been synthesized and investigated. The hardware component implemented by this algorithm is an RBF neural network with four neurons of the latent layer and one neuron with a sigmoid activation function on an FPGA using 16-bit numbers with a fixed point, which took 1193 logic matrix gate (LUTs—LookUpTable). Each hidden layer neuron of the RBF network is designed on an FPGA as a separate computing unit. The speed as a total delay of the combination scheme of the block RBF network was 101.579 ns. The implementation of the Gaussian activation functions of the hidden layer of the RBF network occupies 106 LUTs, and the speed of the Gaussian activation functions is 29.33 ns. The absolute error is ± 0.005. The Spartan 3 family of chips for modeling has been used to get these results. Modeling on chips of other series has been also introduced in the article. RBF neural networks of various topologies have been synthesized and investigated. Hardware implementation of RBF neural networks with such speed allows them to be used in real-time control systems for high-speed objects.
The module of stabilization of an inclination of the plane with three degrees of freedom, the software for data acquisition from MPU-6050 using the I2C protocol, and the program of realization of the digital proportional-integral-diff erential regulator with algorithm of subtomatic factor is developed. A model of a gyroscopic device for testing the created solution was built. Considering time and resource constraints, the following solutions were chosen: PID controller for motor voltage control, PWM as a way to create a control signal, Kalman fi lter for processing output of the IMU, device and relay method in pairs with the Ziegler-Nichols method for the selection of the coeffi cients of the regulator. Test results or the following characteristics of the transition process: the time of the transition process - 0.44s, overregulation - 6.2%. Further improvement of the quality of the transient process is possible through the use of high-quality inertial measuring devices, high-precision electric motors withhigh torque.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.