Laser Powder Bed Fusion of Ti-6Al-2Sn-4Zr-6Mo Alloy and Properties Prediction Using Deep Learning Approaches

Hassanin, Hany; Zweiri, Yahya; Finet, Laurane; Essa, Khamis; Qiu, Chunlei; Attallah, Moataz M.

doi:10.3390/ma14082056

Cited by 21 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This, in turn, greatly enhances the model's performance and predictive capabilities. Training DNN models beforehand has been noted to elevate both the overall predictive accuracy and generalization capabilities when compared to traditional ML algorithms [40].…”

Section: Tailored ML Model For Small Datasetsmentioning

confidence: 99%

Integrating machine learning and the finite element method for assessing stiffness degradation in photovoltaic modules

2024

J. Phys.: Condens. Matter

View full text Add to dashboard Cite

This study introduces a novel machine learning (ML) method utilizing a stacked auto-encoder network to predict stiffness degradation in photovoltaic (PV) modules with pre-existing cracks. The input data for the training process was derived from numerical simulations, ensuring a comprehensive representation of module behavior under various conditions. The findings highlight the robust predictive capability of the model, as evidenced by its impressive R2 value of 0.961 and notably low root mean square error (RMSE) of 4.02%. These metrics significantly outperform those of other conventional methods, including the convolutional neural network (CNN) with R2 of 0.905 and RMSE of 9.43%, the space vector machine (SVM) with R2 of 0.827 and RMSE of 17.93%, and the random forest (RF) with R2 of 0.899 and RMSE of 11.02%. Moreover, the findings suggest that the predictive dynamics of degradation are affected by the varying weight functions of different input parameters, such as climate temperature, grain size, material effort, and pre-crack size, as the degradation level changes. Furthermore, a geometric analysis reveals model deficiencies where significant overestimations correlate with thicker glass components, while pronounced underestimations are predominantly associated with thinner layers of polycrystalline silicon wafer and Ethylene Vinyl Acetate in the module. As a case study, it demonstrated that to maintain a constant degradation level between 1.30 and 1.32 in a PV module with components featuring consistent geometric attributes, the input parameters must be kept within specific ranges: climate temperature ranging from 33 to 57°C, grain size ranging from 36 to 81 μm, material effort ranging from 0.74 to 0.81, and pre-crack size ranging from 24 to 32 μm. Therefore, this underscores that the ML model not only predicts degradation but also delineates the parameter space required to achieve a consistent output value.

show abstract

Section: Tailored ML Model For Small Datasetsmentioning

confidence: 99%

Integrating machine learning and the finite element method for assessing stiffness degradation in photovoltaic modules

2024

J. Phys.: Condens. Matter

View full text Add to dashboard Cite

show abstract

“…Many scholars have carried out laser additive experimental research on adding modifying elements to titanium alloys, aluminum alloys and other metal materials [5,6]. Yang [7] improved the grain characteristics of Ti6Al4V alloy by laser direct deposition technology by adding V element, and the tensile strength was improved.…”

Section: Am Alloy Performance Improvementmentioning

confidence: 99%

Effect of Lanthanum Oxide Addition on Microstructure and Wear Performance of Iron-Chromium Alloy Manufactured by Laser Direct Deposition Additive Manufacturing

et al. 2022

View full text Add to dashboard Cite

Additive Manufacturing (AM) has become increasingly common, and its use in various industries is increasing. However, the microstructure, friction and wear performance of metals made by AM, such as the inexpensive and relatively good-performing iron-chromium alloys, require further investigation. Generally, adding rare earth elements can effectively improve the performance of AM alloys, such as tensile strength, wear resistance, corrosion resistance, creep resistance, etc. This work aims to study the variation of microstructure, friction and wear properties of laser additive manufacturing processed iron-chromium alloys after adding different mass fractions of La2O3. The observations obtained by scanning electron microscopy showed that, with the addition of La2O3, the microstructure of AM alloy becomes more uniform and the grains are significantly refined. It is found by friction test that the running-in period is significantly shortened after the addition of La2O3. The coefficient of friction is reduced to a minimum of 0.68. Compared with AM alloys without La2O3, the wear rate of AM alloys with La2O3 is significantly reduced, with a maximum reduction of 38%. Using an optical microscope to observe the surface morphology of the wear scar, it is found that, after adding rare earth oxide, the wear mechanisms changed from adhesive wear and abrasive wear to abrasive wear, with the spalling of hard particles at the same time.

show abstract

“…For AM of metals, it is common to find extensive research on the effect of printing settings on the part dimensions. For instance, in previous literature, it is possible to find examples of studies where laser powder bed fusion [7][8][9] and selective laser melting [10,11] were adopted to create complex metallic structures, and exhaustive research on the effect of the process parameters was conducted. However, on the other hand, the influence of AM processing parameters on the final properties of ceramic components has begun to be investigated only more recently and, even though the conducted studies have been providing progressively more information, further investigations can strengthen the existing knowledge base.…”

Section: Introductionmentioning

confidence: 99%

DLP of Translucent Alumina: In-Depth Investigation on Slurry Development and Debinding Regimes

et al. 2023

Self Cite

View full text Add to dashboard Cite

Exploring the feasibility of producing near-net-shape components with advanced properties and geometrical features via 3D printing has incrementally become the research focus of various studies. Digital light processing (DLP) technology can manufacture complex-structured components for various technical applications. The aims of this research were to investigate Al2O3 ceramic slurry preparation procedures to identify the ideal components to add to an in-house-developed ceramic slurry, to determine the optimal DLP printing parameters and conditions while understanding their effect on the green part properties and to evaluate the appropriate debinding regime to achieve fully dense crack-free fired parts capable of exhibiting translucent behaviours. The slurry obtained from the ball-milled powder at 800 rpm for 1 h, together with 2 wt.% BYK-145 as a dispersant and the highest achievable solid loading of 85 wt.%, showed the desired rheological and photopolymerisation properties. Full-factorial design of experiments (DOE) was employed to study the impact of the printing parameters on the density and the dimensions of the samples. Different debinding regimes were investigated and it was proven that the lowest debinding heat rate (0.2 °C/min) and longer holding times helped to reduce defects and promote densification (>99.0%), providing optimal grounds to obtain translucent fired parts.

show abstract

Laser Powder Bed Fusion of Ti-6Al-2Sn-4Zr-6Mo Alloy and Properties Prediction Using Deep Learning Approaches

Cited by 21 publications

References 45 publications

Integrating machine learning and the finite element method for assessing stiffness degradation in photovoltaic modules

Integrating machine learning and the finite element method for assessing stiffness degradation in photovoltaic modules

Effect of Lanthanum Oxide Addition on Microstructure and Wear Performance of Iron-Chromium Alloy Manufactured by Laser Direct Deposition Additive Manufacturing

DLP of Translucent Alumina: In-Depth Investigation on Slurry Development and Debinding Regimes

Contact Info

Product

Resources

About