APPLICATION OF NEURAL NETWORK ALGORITHMS FOR BPM LINEARIZATION
- JLAB
Stripline BPM sensors contain inherent non-linearities, as a result of field distortions from the pickup elements. Many methods have been devised to facilitate corrections, often employing polynomial fitting. The cost of computation makes real-time correction difficult, particulalry when integer math is utilized. The application of neural-network technology, particularly the multi-layer perceptron algorithm, is proposed as an efficient alternative for electrode linearization. A process of supervised learning is initially used to determine the weighting coefficients, which are subsequently applied to the incoming electrode data. A non-linear layer, known as an activation layer, is responsible for the removal of saturation effects. Implementation of a perceptron in an FPGA-based software-defined radio (SDR) is presented, along with performance comparisons. In addition, efficient calculation of the sigmoidal activation function via the CORDIC algorithm is presented.
- Research Organization:
- Thomas Jefferson National Accelerator Facility (TJNAF), Newport News, VA (United States)
- Sponsoring Organization:
- USDOE Office of Science (SC)
- DOE Contract Number:
- AC05-06OR23177
- OSTI ID:
- 1089853
- Report Number(s):
- JLAB-ACE-12-1566; DOE/OR/23177-2683
- Resource Relation:
- Conference: BIW2012, 15-19 April 2012, Newport News, VA
- Country of Publication:
- United States
- Language:
- English
Similar Records
Fast readout algorithm for cylindrical beam position monitors providing good accuracy for particle bunches with large offsets
Convolutional neural network based non-iterative reconstruction for accelerating neutron tomography *