1. Accurate ion type and concentration detection using two bare electrodes by machine learning of non-faradaic electrochemical impedance measurements of an automated fluidic system.
- Author
-
Zahid Sagiroglu, M., Deniz Demirel, Eda, and Mutlu, Senol
- Subjects
- *
ARTIFICIAL neural networks , *MACHINE learning , *IMPEDANCE spectroscopy , *ELECTRODES , *ELECTROCHEMICAL electrodes - Abstract
[Display omitted] • Two bare electrodes are used for non-faradaic electrochemical impedance spectroscopy (EIS) data and machine learning. • Automated electro-mechanical fluidic system is built to prepare 148 solutions of LiCl, NaCl, and KCl and measure EIS data. • A data-augmentation model is proposed for non-faradaic voltage sweep EIS datafor deep neural network (DNN) training. • Ion types and their concentrations are detected successfully with machine learning. • Trained DNN models was successful with 4.51 mM average deviation from the 200 mM total solution concentration. Detecting ion types and their concentrations in multi-ion aqueous solutions poses a complex challenge with significant implications for sensing applications. This paper introduces an automated fluidic system using two bare electrodes to measure electrochemical impedance spectroscopy (EIS) data and evaluates deep neural network (DNN) for ion type and concentration detection. Additionally, a data-augmentation model is proposed for non-faradaic voltage sweep EIS data, intended for neural network training. To validate the effectiveness of our approach, prepared solutions featuring varying concentrations of LiCl, NaCl, and KCl are experimented. Impedance (Z) vs DC bias voltage (V) data, i.e., ZV-EIS are measured from −400 mV to + 400 mV at 9 different frequencies up to ∼ 200 kHz, for 148 automatically prepared solutions, having total salt concentrations up to 200 mM. DNN models are trained with augmented samples and successfully identified individual ions in test set solutions and their concentrations with 4.51 mM average deviation. The study delves into the nuanced impacts of factors such as sampling voltage window, and measurement frequency on the performance of the machine learning models, 8 mV and 20 Hz giving the most significant results. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF