scholarly journals Predictive Maintenance of Induction Motors Using Ultra-Low Power Wireless Sensors and Compressed Recurrent Neural Networks

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 178891-178902 ◽  
Author(s):  
Michal Markiewicz ◽  
Maciej Wielgosz ◽  
Mikolaj Bochenski ◽  
Waldemar Tabaczynski ◽  
Tomasz Konieczny ◽  
...  
Keyword(s):  
Neural Networks ◽  
Low Power ◽  
Recurrent Neural Networks ◽  
Wireless Sensors ◽  
Induction Motors ◽  
Predictive Maintenance ◽  
Ultra Low Power

scholarly journals Ultra low power mixer with out-of-band RF energy harvesting for wireless sensor networks applications

2020 ◽  
Vol 40 (1) ◽  
pp. 1-6
Author(s):  
Jie Jin ◽  
Xianming Wu ◽  
Zhijun Li
Keyword(s):  
Energy Harvesting ◽  
Low Power ◽  
Wireless Sensors ◽  
Supply Voltage ◽  
Battery Life ◽  
Ic Design ◽  
Rf Energy Harvesting ◽  
Ultra Low Power ◽  
Rf Energy ◽  
Cmos Rf

An ultra low power mixer with out-of-band radio frequency (RF) energy harvesting suitable for the wireless sensors network (WSN) application is proposed in this paper. The presented mixer is able to harvest the out-of-band RF energy and keep it working in ultra low power condition and extend the battery life of the WSN. The mixer is designed and simulated with Global Foundries ’ 0.18 μ m CMOS RF process, and it operates at 2.4GHz industrial, scientific, and medical (ISM) band. The Cadence IC Design Tools post-layout simulation results demonstrate that the proposed mixer consumes 248 μ W from a 1V supply voltage. Furthermore, the power consumption can be reduced to 120.8 μ W by the out-of-band RF energy harvesting rectifier.

scholarly journals Adiabatic superconducting cells for ultra-low-power artificial neural networks

2016 ◽  
Vol 7 ◽  
pp. 1397-1403 ◽  
Author(s):  
Andrey E Schegolev ◽  
Nikolay V Klenov ◽  
Igor I Soloviev ◽  
Maxim V Tereshonok
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Low Power ◽  
Power Dissipation ◽  
Radial Basis Function Networks ◽  
Activation Functions ◽  
Ultra Low Power ◽  
Network Algorithms ◽  
Low Power Dissipation

We propose the concept of using superconducting quantum interferometers for the implementation of neural network algorithms with extremely low power dissipation. These adiabatic elements are Josephson cells with sigmoid- and Gaussian-like activation functions. We optimize their parameters for application in three-layer perceptron and radial basis function networks.

Recurrent Neural Networks for Predictive Maintenance of Mill Fan Systems

2011 ◽  
Vol 57 (3) ◽  
Author(s):  
Petia Koprinkova-Hristova ◽  
Mincho Hadjiski ◽  
Lyubka Doukovska ◽  
Simeon Beloreshki
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Predictive Maintenance
Sign in / Sign up

Export Citation Format

Share Document