Analysis and optimization of assembly accuracy for a specific bolted joint mechanism based on catboost and bayesian algorithm

TY - GEN

T1 - Analysis and optimization of assembly accuracy for a specific bolted joint mechanism based on catboost and bayesian algorithm

AU - Wang, Ruixiang

AU - Gong, Hao

AU - Liu, Jianhua

AU - Wang, Xiao

N1 - Publisher Copyright: © 2026 SPIE.

PY - 2026/2/15

Y1 - 2026/2/15

N2 - This study proposes an integrated approach, including rough surface morphology reconstruction, finite element method modeling of threaded connections, proxy model training and assembly parameters optimization, to investigate the alignment precision of the HexaLock Positioning Assembly in precision inertial platforms as affected by bolt preloads and rough contact surface topography. Firstly, the microscopic morphology of cylindrical contact surfaces was reconstructed based on measured roughness parameters by using conjugate gradient method. Then, a finite element model considering both threaded interfaces and rough contact surface was established. A dataset of center deviation was generated based on 50 sets of Latin hypercube sampling. The CatBoost model was trained to build a surrogate model, which exhibited higher prediction accuracy than other six popular algorithms, RF, SVR, GBM, XGBoost, and AdaBoost. The Bayesian optimization was employed to globally optimize the tightening angles of the six bolts with the objective of minimizing the center offset. The optimized tightening scheme achieved center offset of 0.62 μm, which was better than experimental measurements and within-group simulation results, and consequently improved the assembly accuracy of HexaLock Positioning Assembly significantly. This study provides a new data-driven approach for error prediction and preload control in precision assembly of inertial platforms.

AB - This study proposes an integrated approach, including rough surface morphology reconstruction, finite element method modeling of threaded connections, proxy model training and assembly parameters optimization, to investigate the alignment precision of the HexaLock Positioning Assembly in precision inertial platforms as affected by bolt preloads and rough contact surface topography. Firstly, the microscopic morphology of cylindrical contact surfaces was reconstructed based on measured roughness parameters by using conjugate gradient method. Then, a finite element model considering both threaded interfaces and rough contact surface was established. A dataset of center deviation was generated based on 50 sets of Latin hypercube sampling. The CatBoost model was trained to build a surrogate model, which exhibited higher prediction accuracy than other six popular algorithms, RF, SVR, GBM, XGBoost, and AdaBoost. The Bayesian optimization was employed to globally optimize the tightening angles of the six bolts with the objective of minimizing the center offset. The optimized tightening scheme achieved center offset of 0.62 μm, which was better than experimental measurements and within-group simulation results, and consequently improved the assembly accuracy of HexaLock Positioning Assembly significantly. This study provides a new data-driven approach for error prediction and preload control in precision assembly of inertial platforms.

KW - Assembly Accuracy analysis

KW - Machine learning

KW - Surface topography

KW - Threaded connection

UR - https://www.scopus.com/pages/publications/105032520392

U2 - 10.1117/12.3106392

DO - 10.1117/12.3106392

M3 - Conference contribution

AN - SCOPUS:105032520392

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Sixth International Conference on Mechanical Engineering and Materials, ICMEM 2025

A2 - Manoj, Gupta

A2 - Xu, Jinyang

PB - SPIE

T2 - 6th International Conference on Mechanical Engineering and Materials, ICMEM 2025

Y2 - 21 November 2025 through 22 November 2025

ER -