Predicting Remaining Fatigue Life of Topside Piping Using Deep Learning

2021 ◽  
Author(s):  
Supratik Chatterjee ◽  
Arvind Keprate
Keyword(s):  
Deep Learning ◽  
Fatigue Life ◽  
Remaining Fatigue Life

scholarly journals S-N Curve Characterisation for Composite Materials and Prediction of Remaining Fatigue Life Using Damage Function

2021 ◽  
Vol 5 (3) ◽  
pp. 76
Author(s):  
Ho Sung Kim ◽  
Saijie Huang
Keyword(s):  
Fatigue Life ◽  
Composite Materials ◽  
Loading Rate ◽  
Theoretical Method ◽  
Damage Function ◽  
Simple Method ◽  
Arbitrary Choice ◽  
Number Of Cycles ◽  
First Time ◽  
Remaining Fatigue Life

S-N curve characterisation and prediction of remaining fatigue life are studied using polyethylene terephthalate glycol-modified (PETG). A new simple method for finding a data point at the lowest number of cycles for the Kim and Zhang S-N curve model is proposed to avoid the arbitrary choice of loading rate for tensile testing. It was demonstrated that the arbitrary choice of loading rate may likely lead to an erroneous characterisation for the prediction of the remaining fatigue life. The previously proposed theoretical method for predicting the remaining fatigue life of composite materials involving the damage function was verified at a stress ratio of 0.4 for the first time. Both high to low and low to high loadings were conducted for predicting the remaining fatigue lives and a good agreement between predictions and experimental results was found. Fatigue damage consisting of cracks and whitening is described.

A Hybrid Supervised Deep Learning and Nonlinear Finite Element Framework for Efficient Fatigue Life Predictions of Rotary Shouldered Threaded Connections

2020 ◽  
Author(s):  
Fei Song ◽  
Ke Li
Keyword(s):  
Finite Element ◽  
Deep Learning ◽  
Fatigue Life ◽  
Learning Algorithm ◽  
Fatigue Tests ◽  
Full Scale ◽  
Remaining Useful Life ◽  
Nonlinear Finite Element ◽  
Threaded Connections ◽  
Life Predictions

Abstract In this paper, a hybrid computational framework that combines the state-of-the art machine learning algorithm (i.e., deep neural network) and nonlinear finite element analysis for efficient and accurate fatigue life prediction of rotary shouldered threaded connections is presented. Specifically, a large set of simulation data from nonlinear FEA, along with a small set of experimental data from full-scale fatigue tests, constitutes the dataset required for training and testing of a fast-loop predictive model that could cover most commonly used rotary shouldered connections. Feature engineering was first performed to explore the compressed feature space to be used to represent the data. An ensemble deep learning algorithm was then developed to learn the underlying pattern, and hyperparameter tuning techniques were employed to select the learning model that provides the best mapping, between the features and the fatigue strength of the connections. The resulting fatigue life predictions were found to agree favorably well with the experimental results from full-scale bending fatigue tests and field operational data. This newly developed hybrid modeling framework paves a new way to realtime predicting the remaining useful life of rotary shouldered threaded connections for prognostic health management of the drilling equipment.

Structural integrity assessment for a component of the bucket-wheel excavator

2014 ◽  
Vol 5 (2) ◽  
pp. 129-140 ◽  
Author(s):  
Anghel Cernescu ◽  
Liviu Marsavina ◽  
Ion Dumitru
Keyword(s):  
Risk Factor ◽  
Fatigue Life ◽  
Crack Length ◽  
Structural Integrity ◽  
Evaluation Procedure ◽  
Content Type ◽  
Integrity Assessment ◽  
Material Component ◽  
High Level ◽  
Remaining Fatigue Life

Purpose – The purpose of this paper is to present a methodology for assessing the structural integrity of a tie member from a bucket-wheel excavator, ESRC 470 model, which was in operation for about 20 years. The tie member is made of S355J2N structural steel. Following the period of operation, the occurrence of microcracks which can propagate by fatigue is almost inevitable. It is therefore necessary to analyze the structural integrity and the remaining life of the component analyzed. Design/methodology/approach – In principle, the assessment methodology is based on three steps: first, the evaluation of mechanical properties of the material component; second, a BEM analysis using FRANC 3D software package to estimate the evolution of the stress intensity factor based on crack length and applied stress; third, risk factor estimation and remaining fatigue life predictions based on failure assessment diagram and fatigue damage tolerance concept. Findings – Following the evaluation procedure were made predictions of failure risk factor and remaining fatigue life function of crack length and variable stress range, for a high level of confidence. Originality/value – As results of this analysis was implemented a program for verification and inspection of the tie member for the loading state and development of small cracks during operation.

Sign in / Sign up

Export Citation Format

Share Document