Development of a Smart Signal Detection Method for Cyclic Voltammetry via Artificial Neural Intelligence
- Department of Mechanical and Nuclear Engineering, Virginia Commonwealth University, Richmond, VA (United States)
- Department of Computer Science and Engineering, Virginia Commonwealth University, Richmond, VA (United States)
The electrorefiner (ER) is the heart of pyroprocessing technology which is a high-temperature method for separating uranium from Used Nuclear Fuel (UNF). It is important to improve this technology with respect to nuclear materials detection and accountability. Artificial Neural Intelligence (ANI) is a novel data analysis and simulation method that can be applied to electrochemical data sets. This computational code, which has been performed using the commercial software MATLAB, can be trained to generalize adequate electrical current and potential simulated data sets for the unseen data with a high accuracy of prediction. For this purpose, a massive collection of cyclic voltammetry (CV) data sets by Hoover (2014), for 0.5, 1, 2.5, and 5 wt% of zirconium chloride in LiCl-KCl molten salt with different scan rates at 773 K has been considered. The computer is trained via ANI to predict the unseen data after providing suitable hidden layers and validation numbers. In addition, this work can trace the CV plot for a blind condition by interpolating between two simulated data set. The different hidden layers with various neurons (from 5 to 30) at several validation numbers (from 5 to 30) has been studied and the average percent error between experimental and theoretical data for 0.5 wt% with 200 and 450 mV/s has been calculated. Preliminary results demonstrate that if the number of hidden layers increases from one to three, the average error falls down from 44% to around 8%. The best condition which gives a minimum average percent error has been discovered and the simulated CV graph has been compared with the experimental data. (authors)
- OSTI ID:
- 23042598
- Journal Information:
- Transactions of the American Nuclear Society, Vol. 115; Conference: 2016 ANS Winter Meeting and Nuclear Technology Expo, Las Vegas, NV (United States), 6-10 Nov 2016; Other Information: Country of input: France; 13 refs.; available from American Nuclear Society - ANS, 555 North Kensington Avenue, La Grange Park, IL 60526 (US); ISSN 0003-018X
- Country of Publication:
- United States
- Language:
- English
Similar Records
MABAL: a Novel Deep-Learning Architecture for Machine-Assisted Bone Age Labeling
Report on Concepts & Approaches for SSBD for eCHEM
Related Subjects
11 NUCLEAR FUEL CYCLE AND FUEL MATERIALS
COMPUTERIZED SIMULATION
DATA ANALYSIS
ELECTRIC CURRENTS
ELECTROCHEMISTRY
ERRORS
LITHIUM CHLORIDES
MOLTEN SALTS
NUCLEAR FUELS
NUCLEAR MATERIALS MANAGEMENT
POTASSIUM CHLORIDES
URANIUM
VALIDATION
VOLTAMETRY
ZIRCONIUM CHLORIDES