Using Artificial Neural Networks for the Prediction and Optimization of Electrochemical Capacity in Aluminum-Based Sacrificial Anodes

Rifqi Aulia Tanjung; Muhammad Alwi Foury; Fikan Mubarok Rohimsyah

doi:10.4028/p-AsDq6h

Paper Titles

Using Artificial Neural Networks for the Prediction and Optimization of Electrochemical Capacity in Aluminum-Based Sacrificial Anodes
p.3

Effect of Electropolishing Time and Distance on Roughness and Corrosion Resistance of AISI 316L Elbow Pipe for Pharmaceutical Industry Using H₂SO₄-H₃PO₄ Solution
p.13

The Influence of Concentration and Surface Roughness on the Corrosion Rate of 316L Stainless Steel Material in Sulfuric Acid Environment
p.23

The Influence of Temperature and Time in Electropolishing on Surface Roughness of Inner Surface of Stainless Steel 316l Cylinder for Pharmaceutical Industry Components
p.35

Dry Reciprocating Wear and Friction Behavior of HVOF Sprayed NiCrBSi-TiB₂ Coating
p.47

A Short Review of Environmentally Friendly Spacer Coatings to Minimize Membrane Fouling
p.55

Synergistic Improvement of Photoactivity in Rare Earth-Doped Hierarchical ZnO Microspheres for Palm Oil Mill Effluent Treatment and Synchronously Biogas Generation
p.67

Characterizing Hydrogen Evolution Reaction of NiCoFe-LDH@NiCo₂O₄ Heterostructured Electrocatalyst for Hydrogen Generation
p.73

HomeSolid State PhenomenaSolid State Phenomena Vol. 377Using Artificial Neural Networks for the...

Using Artificial Neural Networks for the Prediction and Optimization of Electrochemical Capacity in Aluminum-Based Sacrificial Anodes

Abstract:

Corrosion is a pervasive degradation mechanism that arises when materials interact with their surrounding environment, especially in aggressive conditions like seawater. One effective corrosion countermeasure is the use of sacrificial anodes for cathodic protection, with aluminum anodes becoming increasingly popular for seawater applications. The electrochemical capacity of these sacrificial anodes is pivotal for efficient corrosion prevention. However, optimizing their composition and design to adhere to standards and prolong protection is challenging. This study introduces an Artificial Neural Network (ANN) as a tool to refine the elemental composition of sacrificial anode materials. We devised an ANN model that predicts the electrochemical capacity of aluminum-based sacrificial anodes with impressive accuracy. We also examined the impact of several elements (indium, cadmium, silicon, iron, and copper) on anode capacity using the ANN simulations. The designed ANN models (Al-10) showcased accuracy rates of 92%, endorsing the potential of the ANN approach. Notably, iron was observed to augment anode capacity, while silicon exhibited a negative influence. This research showcases a novel computational approach with ANN to predict and optimize the electrochemical capacity of aluminum-based sacrificial anodes, paving the way for enhanced corrosion prevention in harsh seawater conditions.