Application of artificial neural networks in the prediction of slurry erosion performance: a comprehensive review

• Published in: International journal on interactive design and manufacturing Vol. 19; no. 3; pp. 1591 - 1609
• Main Authors: Prashar, Gaurav, Vasudev, Hitesh
• Format: Journal Article
• Language: English
• Published: Paris Springer Paris 01.03.2025; Springer Nature B.V
• Subjects: Artificial intelligence; Artificial neural networks; Big Data; CAE) and Design; Computer-Aided Engineering (CAD; Damage; Data management; Efficiency; Electronics and Microelectronics; Engineering; Engineering Design; Erosion rates; Fuzzy logic; Genetic algorithms; Hydraulic turbines; Hydroelectric power; Industrial Design; Instrumentation; Internet of Things; Machine learning; Materials science; Mechanical Engineering; Mining industry; Natural language processing; Neural networks; R&D; Research & development; Review; Slurry pipelines; Turbine blades; Turbines; Voice recognition; Workplaces; India; AI; ANN; Slurry erosion; ML
• ISSN: 1955-2513; 1955-2505
• DOI: 10.1007/s12008-024-02014-7

The prevalence of artificial intelligence (AI) is driving the acceptance of various machine learning (ML) approaches. With artificial neural networks (ANN), a comprehensive physical model of the system is not necessary, allowing for a "black-box" modeling approach. It makes more sense to only look at the data from the inputs and outputs when trying to understand how the system worked. As AI has recently emerged to predict slurry erosion rates, ANNs have been the subject of substantial research. This study provided an in-depth analysis of the roles of ANN in slurry erosion predictions. Slurry erosion causes significant damage to equipment components in workplaces, such as hydraulic turbines and slurry pipelines. This damage is so severe that the affected machine parts cannot be fixed and must be replaced with new ones promptly. The popularity of AI has increased, as it may be used for other tasks such as site selection, parameter evaluation, and optimization of operation and maintenance. This study presents a comprehensive analysis of the use of AI in slurry erosion predictions within the hydropower (turbine blades) and mining industry using heavy duty pumps or impellers. The utilization of ML and big data management techniques is becoming imperative in order to enhance industry efficiency.