View in EDS HTML Full Text PDF Full Text

Study on Abrasive Coal-Slurry Flow and Erosion Wear of NiCrBSiCoFeWC HVOF Coating for Coal-Conveying Slurry Pumps Using Machine Learning Approach.

Saved in:

Bibliographic Details
Title:	Study on Abrasive Coal-Slurry Flow and Erosion Wear of NiCrBSiCoFeWC HVOF Coating for Coal-Conveying Slurry Pumps Using Machine Learning Approach.
Authors:	Singh, Jashanpreet^1,2 (AUTHOR) ijashanpreet@gmail.com, Sharma, Vikas^1,2 (AUTHOR), Singh, Amanpreet³ (AUTHOR)
Source:	International Journal of Coal Preparation & Utilization. 2026, Vol. 46 Issue 6, p1679-1712. 34p.
Subject Terms:	Slurry, Machine learning, Mechanical wear, Metal spraying, *Material erosion
Abstract:	In the present study, the slurry erosion of NiCrBSiCoFeWC coatings under different impact angles, slurry concentrations, and median particle size of coal slurry has been investigated successfully using machine learning approach. Different machine learning techniques were applied to evaluate the erosion wear. Results showed that the wear performance of SS316L steel was improved by the deposition of NiCrBSiFeWC coating. Analysis of the surface morphology shows that impact angle plays a major role in the wear behavior with lower (30°) impact angles leading to micro cutting and plowing while higher (60°) impact angles resulting in extensive cratering, material displacement, and coating delamination. Wear is intensified as slurry concentration is increased from 30 wt.% to 60 wt.% which changes the major wear mechanisms from minor smearing and cutting to deep cratering and plowing. At the same time, the erosion patterns were also affected by the median particle size in which smaller particles (D50) caused lower, more uniform erosion. Results also confirmed that the wear mechanisms are greatly a function of operational variables. It is recommended that the optimum coating compositions and impact conditions must be optimized for enhanced erosion resistance in harsh environments. [ABSTRACT FROM AUTHOR]
Database:	Energy & Power Source
Full text is not displayed to guests. Login for full access.

Description
Abstract:	In the present study, the slurry erosion of NiCrBSiCoFeWC coatings under different impact angles, slurry concentrations, and median particle size of coal slurry has been investigated successfully using machine learning approach. Different machine learning techniques were applied to evaluate the erosion wear. Results showed that the wear performance of SS316L steel was improved by the deposition of NiCrBSiFeWC coating. Analysis of the surface morphology shows that impact angle plays a major role in the wear behavior with lower (30°) impact angles leading to micro cutting and plowing while higher (60°) impact angles resulting in extensive cratering, material displacement, and coating delamination. Wear is intensified as slurry concentration is increased from 30 wt.% to 60 wt.% which changes the major wear mechanisms from minor smearing and cutting to deep cratering and plowing. At the same time, the erosion patterns were also affected by the median particle size in which smaller particles (<D50) of higher kinetic energy gave rise to deep craters, while larger particles (>D50) caused lower, more uniform erosion. Results also confirmed that the wear mechanisms are greatly a function of operational variables. It is recommended that the optimum coating compositions and impact conditions must be optimized for enhanced erosion resistance in harsh environments. [ABSTRACT FROM AUTHOR]
ISSN:	19392699
DOI:	10.1080/19392699.2025.2505456