scholarly journals Implementation of Fpga-based Pseudo-random Words Generator

2020 ◽  
Vol 5 (2) ◽  
pp. 85-90
Author(s):  
Volodymyr Opanasenko ◽  
◽  
Stanislaw Zavyalov ◽  
Olexander Sofiyuk
Keyword(s):  
Internal Structure ◽  
Hardware Implementation ◽  
Timing Diagrams ◽  
Random Bit Generator ◽  
On Line ◽  
Random Bit Generators

A hardware implementation of pseudo-random bit generator based on FPGA chips, which use the principle of reconfigurability that allows the modernization of their algorithms and on-line replacement of the internal structure (reconfiguration) in the process of functioning have been considered in the paper. Available DSP blocks embedded into the structure of FPGA chips allow efficient hardware implementation of the pseudorandom bit generator through the implementation of the basic operations of multiplication with accumulation on the gate level. Using CAD ISE 14.02 Foundation and VHDL language three types of pseudo-random bit generators have been implemented on Spartan series chip 6SLX4CSG225-3, for which time and hardware expenses are represented. Using the simulating system ModelSim SE 10.1c, timing diagrams of simulation for these structures have been obtained.

scholarly journals Photonic Reinforcement Learning Based on Optoelectronic Reservoir Computing

2021 ◽  
Author(s):  
Kazutaka Kanno ◽  
Atsushi Uchida
Keyword(s):  
Artificial Intelligence ◽  
Reinforcement Learning ◽  
Robot Control ◽  
Deep Neural Networks ◽  
Hardware Implementation ◽  
Computational Cost ◽  
Autonomous Driving ◽  
Training Data ◽  
Reservoir Computing ◽  
On Line

Abstract Reinforcement learning has been intensively investigated and developed in artificial intelligence in the absence of training data, such as autonomous driving vehicles, robot control, and internet advertising. However, the computational cost of reinforcement learning with deep neural networks is extremely high, and reducing the learning cost is a challenging issue. We propose a photonic on-line implementation of reinforcement learning using optoelectronic delay-based reservoir computing, both experimentally and numerically. In the proposed scheme, we accelerate reinforcement learning at a rate of several megahertz because there is no required learning process for the internal connection weights in reservoir computing. We perform two benchmark tasks, CartPole-v0 and MountanCar-v0 tasks, to evaluate the proposed scheme. Our results represent the first hardware implementation of reinforcement learning based on photonic reservoir computing and paves the way for fast and efficient reinforcement learning as a novel photonic accelerator.

Neural Network Designs for Partially Known Dynamic Systems

1994 ◽  
Vol 116 (3) ◽  
pp. 407-409 ◽  
Author(s):  
S. I. Mistry ◽  
S. S. Nair
Keyword(s):  
Dynamic Systems ◽  
Machine Tools ◽  
Hardware Implementation ◽  
Back Propagation ◽  
Neural Dynamic ◽  
Modeling And Control ◽  
Training Scheme ◽  
Network Training ◽  
On Line ◽  
And Control

Algorithms are investigated for system identification and control using neural networks and validated using on-line hardware implementation. Such algorithms require very little knowledge about the system which, together with their capability of learning, make them attractive for the modeling and control of nonlinear partially known dynamic systems. An implementation architecture for neural dynamic back propagation suitable for application to other machine tools and manufacturing processes, and a network training scheme with more general features are proposed.

Design of On-Line Measurement System of Film Thickness Based on Infrared Technology

2017 ◽  
Vol 865 ◽  
pp. 619-623
Author(s):  
Ping He ◽  
Ji Kai Yu ◽  
Long Hua Hong
Keyword(s):  
Film Thickness ◽  
Economic Benefit ◽  
Hardware Implementation ◽  
Detection System ◽  
Digital Signal ◽  
Analog Filter ◽  
Line Measurement ◽  
Infrared Technology ◽  
On Line ◽  
Physical Index

The thickness of the plastic film is an important physical index to the production of plastic. The measurement reslut relates directly to the companies’ economic benefit. This paper mainly introduces the digital signal processing in the detection system of film thickness. Through a perfect processing, the system can improve its SNR and finally get a high precision. Firstly, the principle and scheme was presented. After that, this paper mainly introduces the hardware implementation of the system. It includes analog filter circuit, AD sampling and digital filter. With the experimental verification, the system realizes the measurement of the film thickness on-line which can get the precision of micrometer. At present, the equipment has aready put into use by some companies.

Enhancement of Ev On-Board Diagnostics System into Preliminary Operation Using Estimation Theory

2013 ◽  
Vol 391 ◽  
pp. 592-595 ◽  
Author(s):  
Chun Liang Chen ◽  
Chan Wei Hsu
Keyword(s):  
Mobile Communication ◽  
Hardware Implementation ◽  
Estimation Theory ◽  
Data Logging ◽  
Information Display ◽  
Research Platform ◽  
On Line ◽  
Remote Surveillance ◽  
Diagnostics System ◽  
Remote Health

This paper presents a recent study to construct an EV preliminary research platform using hybrid communications. Vehicular network, which integrated battery and powertrain information, is applied for performance display and on-line diagnostics. Mobile communication offers one-way data collection for remote surveillance when data transmission is continuously linked with server through mobile communication. Data acquisition is handled by on-board unit via EV CAN network. However, on-line data size, e.g. state of health, is so huge that it isnt easily transmitted when hundreds of vehicles are simultaneously connected for data logging into server. Taking SOH as example, the continuity of curve variation is a challenge in order to be effectively provided for remote health estimation. Hence, estimation theory is applied and embedded into hardware implementation before data reporting. Cubic spine and linear Kalman filter are applied to curve fitting and estimation for data size reduction. The proposed system provides not only information display but also on-board diagnosis; furthermore, the processed data can be devoted to EV preliminary operation in Taiwan.

Sign in / Sign up

Export Citation Format

Share Document