Precise Pulse Processing Discrimination between Alpha and Neutron Radiation Using Grey Wolf and Whale Optimization Algorithms

Overcoming the simultaneous detection of alpha and neutron pulses is a challenge in nuclear environments. Consequently, pulse shape discrimination (PSD) between alpha and neutron pulses is the main objective of this manuscript. A robust digital pulse processing approach is proposed for handling and...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement p. 1
Main Author: El Tokhy, Mohamed S.
Format: Journal Article
Language:English
Published: IEEE 2024
Subjects:
Detectors
Neutrons
Optimization
Shape
Signal processing algorithms
Spirals
Whales
ISSN:0018-9456, 1557-9662
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Overcoming the simultaneous detection of alpha and neutron pulses is a challenge in nuclear environments. Consequently, pulse shape discrimination (PSD) between alpha and neutron pulses is the main objective of this manuscript. A robust digital pulse processing approach is proposed for handling and discriminating alpha and neutron pulses. This approach searches for unknown alpha and neutron pulse widths and positions using both Gray Wolf Optimization (GWO) and Whale Optimization (WOA). Additionally, precise PSD between alpha and neutron pulses using GWO and WOA optimization algorithms are investigated. These optimization algorithms are applied to handle the variable pulse widths due to straggling effect of alpha particles. Simulated normalized alpha and neutron pulses are produced using block diagram programming models. The features of these pulses are acquired using principle component analysis (PCA), discrete cosine transform(DCT), discrete sine transform(DST) and discrete wavelet transform(DWT). These features are trained by artificial neural network(ANN) and fuzzy k-nearest neighbor(FKNN) discriminators which have been saved for matching the tested features. Higher identification results are attained using FKNN compared to ANN classifier. The optimization algorithms depend on a proposed cost function that investigated using the estimated pulse width and discrimination accuracy. This objective function is proposed for precise localization of alpha and neutron pulses. The accuracy is accomplished using pulse shape classification. Besides, precise pulse width and position is attained using GWO optimizer. The GWO demonstrates an improved consumed time compared to WOA. Subsequently, the result due to GWO surpasses that of WOA algorithm. A recognition rate of 100% is demonstrated for discrimination between alpha and neutron pulses by GWO with higher accuracy. Accordingly, the GWO optimizer is the most desirable algorithm for precise PSD between alpha and neutron particle pulses.
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2021.3132060