Ensemble learning with a genetic algorithm for surface roughness prediction in multi-jet polishing

Ruoxin Wang, Mei Na Cheng, Yee Man Loh, Chunjin Wang (Corresponding Author), Chi Fai Cheung (Corresponding Author)

Research output: Journal article publicationJournal articleAcademic researchpeer-review

10 Citations (Scopus)


Surface roughness prediction is important for polishing with high production efficiency and low cost since it can reduce the time required for trials and testing. Although many prediction methods have been proposed, there are no studies focusing on the surface roughness prediction in multi-jet polishing (MJP) process. This paper presents the development of a robust surface roughness prediction model based on ensemble learning with a genetic algorithm (ELGA), that can be used for the prediction of surface roughness in the MJP of 3D-printed 316L stainless steel. This paper firstly provides a brief review of the current status of the surface roughness prediction method. Then the development of the ELGA surface roughness prediction model is introduced in detail, which consists of four modules, namely pre-processing module, multi-algorithm regression module, GA module and ensemble module. After that, a series of MJP experiments on 316L stainless steel are conducted to test the effectiveness of the proposed ELGA method. Moreover, the ELGA is compared with six other machine learning-based surface roughness prediction models based on the experiment results. Comparison results show that ELGA model yields the lowest average MAE for the surface roughness prediction in MJP.
Original languageEnglish
Article number118024
JournalExpert Systems with Applications
Publication statusPublished - 30 Nov 2022


  • Surface roughness prediction
  • Fluid jet polishing
  • Genetic algorithm
  • Ensemble learning
  • Ultra-precision machining


Dive into the research topics of 'Ensemble learning with a genetic algorithm for surface roughness prediction in multi-jet polishing'. Together they form a unique fingerprint.

Cite this