Development of stress concentration factors for geared shafts

No Thumbnail Available

URL

Journal Title

Journal ISSN

Volume Title

Insinööritieteiden korkeakoulu | Master's thesis

Date

2024-01-22

Department

Major/Subject

Solid Mechanics

Mcode

Degree programme

Master's Programme in Mechanical Engineering (MEC)

Language

en

Pages

85

Series

Abstract

The presence of geometrical irregularities in shafts, such as shaft shoulders, grooves, and keyways, disrupts the homogeneity of stress distribution, creating areas with stress concentrations. This intricate connection between geometric complexities and stress gradients is crucial as it significantly impacts both the initiation and propagation of cracks in shafts. Consequently, the development of a precise and comprehensive calculation method for stress concentration is always imperative to ensure the integrity of mechanical design. By comprehending and unifying these interconnected factors, engineers can make well-informed design decisions that contribute to the enhanced reliability and durability of shaft-integrated systems. This thesis investigated modern techniques for assessing stress concentrations in shafts and introduced an Artificial Intelligence (AI) based approach to compute the Stress Concentration Factor (SCF) in geared shafts subjected to the combination of bending, axial, torsional, and shear stresses. The proposed calculation method employs Artificial Neural Network (ANN) models trained on stress datasets obtained from Finite Element Analysis (FEA) of industrial gearbox shafts. These models can predict SCFs for both familiar and unfamiliar geometric irregularities within the confines of the training dataset’s limits. Comparative analyses with results from conventional analytical approaches demonstrated that the stress concentration factors obtained through the proposed AI-based method are both valid and reliable. Notably, this method proves its validity for handling combined stresses and exhibits applicability to complex geometric conditions, including keyways with shaft shoulders, setting it apart from the underlined analytical methods.

Description

Supervisor

Remes, Heikki

Thesis advisor

Musharraf, Mashrura

Keywords

stress concentration factor (SCF), artificial neural network (ANN), finite element method (FEM), geared shaft, stress analysis, notch effect

Other note

Citation