High cycle fatigue life prediction of laser additive manufactured stainless steel: A machine learning approach

Zhang, Meng; Sun, Chen-Nan; Zhang, Xiang; Goh, Phoi Chin; Wei, Jun; Hardacre, David; Li, Hua

doi:10.1016/j.ijfatigue.2019.105194

Cited by 165 publications

(54 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The majority of previous efforts applying ML to predict the properties of high-temperature alloys have used alloy compositions and simple processing conditions as features [6][7][8][9][10][11][12][13] . While these approaches can leverage experimental data accumulated over decades, extrapolating (and even interpolating) these models outside the range of the input data is risky due to the absence of physical constraints.…”

Section: Introductionmentioning

confidence: 99%

Coupling physics in machine learning to predict properties of high-temperatures alloys

et al. 2020

View full text Add to dashboard Cite

High-temperature alloy design requires a concurrent consideration of multiple mechanisms at different length scales. We propose a workflow that couples highly relevant physics into machine learning (ML) to predict properties of complex high-temperature alloys with an example of the 9–12 wt% Cr steels yield strength. We have incorporated synthetic alloy features that capture microstructure and phase transformations into the dataset. Identified high impact features that affect yield strength of 9Cr from correlation analysis agree well with the generally accepted strengthening mechanism. As a part of the verification process, the consistency of sub-datasets has been extensively evaluated with respect to temperature and then refined for the boundary conditions of trained ML models. The predicted yield strength of 9Cr steels using the ML models is in excellent agreement with experiments. The current approach introduces physically meaningful constraints in interrogating the trained ML models to predict properties of hypothetical alloys when applied to data-driven materials.

show abstract

Section: Introductionmentioning

confidence: 99%

Coupling physics in machine learning to predict properties of high-temperatures alloys

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In recent years, with the rapid development of machine learning technology, a few researchers have begun to examine fatigue strength [19] based on ML models. For example, adaptive neuro-fuzzy-based machine learning techniques were studied for potential applications in the modelling of the highcycle fatigue life of L-PBF stainless steel 316L [20,21]. Subsequently, a potential roadmap for a data-driven evaluation platform based on large amounts of experimental data, theoretical calculations, and data analyse was designed for the purpose of shortening the required research time and the development cycles of new materials [22,23].…”

Section: Introductionmentioning

confidence: 99%

Predictions and mechanism analyses of the fatigue strength of steel based on machine learning

et al. 2020

View full text Add to dashboard Cite

It is not completely understood fatigue strength at this time due to its complex formation mechanism. Therefore, in order to address this issue, machine learning has been used to examine the important factors involved in predicting fatigue strength. In this study, a hybrid model was proposed based on the modified bagging method by combining XGBoost and LightGBM, in which the hyperparameters of the models were optimized by a grey wolf algorithm. Moreover, an interpretable method, referred to as Shapley additive explanations (SHAP), was introduced to explain the fatigue strength predictions made by ML models. The SHAP values were calculated, and feature importance of fatigue strength by XGBoost, LightGBM and the hybrid model was discussed. The final results demonstrated that the SHAP method had major potential for interpreting fatigue strength predictions, which would provide constructive guidance for the development of antifatigue steel material in the future.

show abstract

“…Nguyen et al [33] presented an optimization tool that worked based on ML to predict the density of Ti-6Al-4V parts manufactured with any variation in the L-PBF process parameters, including laser power (80-180 W), scanning speed (800-2500 mm/s), layer thickness (20-80 µM), and hatch spacing (30-100 µM). Zhang et al [44] developed a prediction model for the high-cycle fatigue life of L-PBF-manufactured stainless steel parts using ML approaches. Li and Anand [45] trained a feed-forward back-propagation ANN to predict inherent strain obtained by thermo-mechanical simulation for different given hatch patterns that are adopted during the L-PBF process.…”

Section: Introductionmentioning

confidence: 99%

Modeling and Optimization Approaches of Laser-Based Powder-Bed Fusion Process for Ti-6Al-4V Alloy

2020

View full text Add to dashboard Cite

Laser-based powder-bed fusion (L-PBF) is a widely used additive manufacturing technology that contains several variables (processing parameters), which makes it challenging to correlate them with the desired properties (responses) when optimizing the responses. In this study, the influence of the five most influential L-PBF processing parameters of Ti-6Al-4V alloy—laser power, scanning speed, hatch spacing, layer thickness, and stripe width—on the relative density, microhardness, and various line and surface roughness parameters for the top, upskin, and downskin surfaces are thoroughly investigated. Two design of experiment (DoE) methods, including Taguchi L25 orthogonal arrays and fractional factorial DoE for the response surface method (RSM), are employed to account for the five L-PBF processing parameters at five levels each. The significance and contribution of the individual processing parameters on each response are analyzed using the Taguchi method. Then, the simultaneous contribution of two processing parameters on various responses is presented using RSM quadratic modeling. A multi-objective RSM model is developed to optimize the L-PBF processing parameters considering all the responses with equal weights. Furthermore, an artificial neural network (ANN) model is designed and trained based on the samples used for the Taguchi method and validated based on the samples used for the RSM. The Taguchi, RSM, and ANN models are used to predict the responses of unseen data. The results show that with the same amount of available experimental data, the proposed ANN model can most accurately predict the response of various properties of L-PBF components.

show abstract

High cycle fatigue life prediction of laser additive manufactured stainless steel: A machine learning approach

Cited by 165 publications

References 66 publications

Coupling physics in machine learning to predict properties of high-temperatures alloys

Coupling physics in machine learning to predict properties of high-temperatures alloys

Predictions and mechanism analyses of the fatigue strength of steel based on machine learning

Modeling and Optimization Approaches of Laser-Based Powder-Bed Fusion Process for Ti-6Al-4V Alloy

Contact Info

Product

Resources

About