Development of Artificial Intelligence Methods for Dynamic Electrochemical Studies of Complex Reaction Mechanisms

The identification of electrochemical systems is generally a complex process with many difficulties. In this thesis a range of artificial intelligence methods are developed for the analysis of cyclic DC voltammetry and Fourier transformed AC voltammetry, these automated methods are then applied to interesting electrochemical systems. A range of artificial intelligence methods are based on techniques of statistics and machine learning with the specific methods being Optimisation, Bayesian inference, Supervised learning, and Unsupervised learning. In this thesis these methods show promise at extracting and identifying electrochemical information that was previously not possible by manual methods of analysis.