scholarly journals A Noise-Resilient Neuromorphic Digit Classifier Based on NOR Flash Memories with Pulse-Width Modulation Scheme

Electronics ◽  
2021 ◽  
Vol 10 (22) ◽  
pp. 2784
Author(s):  
Gerardo Malavena ◽  
Alessandro Sottocornola Sottocornola Spinelli ◽  
Christian Monzio Monzio Compagnoni

In this work, we investigate the implementation of a neuromorphic digit classifier based on NOR Flash memory arrays as artificial synaptic arrays and exploiting a pulse-width modulation (PWM) scheme. Its performance is compared in presence of various noise sources against what achieved when a classical pulse-amplitude modulation (PAM) scheme is employed. First, by modeling the cell threshold voltage (VT) placement affected by program noise during a program-and-verify scheme based on incremental step pulse programming (ISPP), we show that the classifier truthfulness degradation due to the limited program accuracy achieved in the PWM case is considerably lower than that obtained with the PAM approach. Then, a similar analysis is carried out to investigate the classifier behavior after program in presence of cell VT instabilities due to random telegraph noise (RTN) and to temperature variations, leading again to results in favor of the PWM approach. In light of these results, the present work suggests a viable solution to overcome some of the more serious reliability issues of NOR Flash-based artificial neural networks, paving the way to the implementation of highly-reliable, noise-resilient neuromorphic systems.

2014 ◽  
Vol 8 (23) ◽  
pp. 2356-2362 ◽  
Author(s):  
P. Muthukumar ◽  
P. Melba Mary ◽  
V. Deepaprincy ◽  
F. Monica

Electronics ◽  
2022 ◽  
Vol 11 (2) ◽  
pp. 187
Author(s):  
Intissar Moussa ◽  
Adel Khedher

An appropriate modulation scheme selection ensures inverter performance. Thus, space vector modulation (SVM) is more efficient and has its own distinct advantages compared to other pulse width modulation (PWM) techniques. This work deals with the development of an advanced space vector pulse width modulation (SVM) technique for two-phase inverter control using an XSG library to ensure rapid prototyping of the controller FPGA implementation. The proposed architecture is applied digitally and in real time to drive a two-phase induction motor (TPIM) for small-scale wind turbine emulation (WTE) profiles in laboratories with minimum current ripple and torque oscillation. Four space voltage vectors generated for the used SVM technique do not contain a zero vector. Hence, for an adequate adjustment of these four vectors, a reference voltage vector located in the square locus is determined. Considering the asymmetry between the main and auxiliary windings, the TPIM behavior, which is fed through the advanced SVM controlled-two-phase inverter (2ϕ-inverter), is studied, allowing us to control the speed and the torque under different conditions for wind turbine emulation. Several quantities, such as electromagnetic torque, rotor fluxes, stator currents and speed, are analyzed. To validate the obtained results using both Simulink and XSG interfaces, the static and dynamic characteristics of the WTE are satisfactorily reproduced. The collected speed and torque errors between the reference and actual waveforms show low rates, proving emulator controller effectiveness.


2015 ◽  
Vol 8 (7) ◽  
pp. 1083-1094 ◽  
Author(s):  
Pradabane Srinivasan ◽  
Beeramangalla Lakshminarasaiah Narasimharaju ◽  
Nandiraju Venkata Srikanth

Sign in / Sign up

Export Citation Format

Share Document