Stand-Alone Hardware-Based Learning System
نویسندگان
چکیده
The probabilistic Random Access Memory (pRAM) is a biologically-inspired model of a neuron. The pRAM behaviour is described in this paper in relation to binary and real-valued input vectors. The pRAM is hardware-realisable, as is its reinforcement training algorithm. The pRAM model may be applied to a wide range of artificial neural network applications, many of which are classification tasks. The application presented here is a control problem where an inverted pendulum, mounted on a cart, is to be balanced. The solution to this problem using the pRAM-256, a VLSI pRAM controller, is shown.
منابع مشابه
Nonlinear Control for Positive Output Super Lift Luo Converter in Stand Alone Photovoltaic System
This paper proposes a stand-alone photovoltaic (PV) system based on a DC-DC positive output super lift Luo (POSLL) converter. A conventional sliding mode control, a sliding mode controller using a simple sign function and a linear controller using proportional integrator (PI) are used for the control of the PV panel voltage and POSLL converter inductor current and these methods are compared tog...
متن کاملOptimal Torque Control of PMSG-based Stand-Alone Wind Turbine with Energy Storage System
In this paper optimal torque control (OTC) of stand-alone variable-speed small-scale wind turbine equipped with a permanent magnet synchronous generator and a switch- mode rectifier is presented. It is shown that with OTC method in standalone configuration, power coefficient could be reached to its maximum possible value, i.e. 0.48. An appropriate control algorithm based on turbine characterist...
متن کاملOptimal Sizing of a Reliable Hydrogen-based Stand-alone Wind-Fuel Cell System
A hybrid wind/ fuel cell generation system is designed to supply power demand. The aim of this design is to minimize the total cost of the hybrid system over an expected 20 years of operation. The optimization problem is solved aimed at providing a reliable supply for the consumer’s demand. The system consists of fuel cells, some wind units, some electrolyzers, a reformer, an anaerobic reactor ...
متن کاملAn application of vector based swarm optimization for designing MPPT controller of a stand-alone PV System
In this paper, the Vector Based Swarm Optimization method is used for designing an optimal controller for the maximum power point tracker of a stand-alone PV System. The proposed algorithm is executed on vectors in a multi-dimension vector space. These vectors by appropriated orientation converge to a global optimum while the algorithm runs. The Remarkable point of the VBSO algorithm is how us...
متن کاملEnergy Management Strategy of Stand-alone Photovoltaic System in Cathodic Protection Pipeline
In this paper, the stand-alone photovoltaic system for cathodic protection of underground pipelines is presented. The proposed system offers continuous and automatic adjustment of the applied voltage so that the buried pipelines receive the exact current. A modified perturb and observe (P&O) algorithm for maximum power point tracking (MPPT) is used to improve dynamic and steady state performa...
متن کاملOptimizing Design of Stand-alone Hybrid Solar Micro-CHP Systems Using LUS Based Particle Swarm Optimization Algorithm
Utilizing the combined cooling, heating and power generation (CHP) systems to produce cooling, heat and electricity is growing rapidly due to their high efficiency and low emissions in commercial and industrial applications. In conventional CHP systems the deficit of the system power can be purchased from the grid. However, this system cannot be used as the standalone application. The hybrid so...
متن کامل