Image Deep Learning Assisted Prediction of Mechanical and Corrosion Behavior for Al-Zn-Mg Alloys

Ao, Min; Ji, Yucheng; Sun, Xiao‐Guang; GUO, Fengjia; Xiao, Kui; Dong, Chaofang

doi:10.1109/access.2022.3161519

Cited by 7 publications

(5 citation statements)

References 63 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This new research direction aims to deepen our understanding of material properties and their influence. For instance, Ao et al [16] proposed a deep learning strategy to predict the mechanical properties and corrosion behavior of large extruded aluminum profiles by using surface optical microstructure images and determined the precise correlations among metallographic images, hardness, and corrosion potential. Messina et al [17] quantified the segregation ability of aluminum at magnesium grain boundaries by using atomic simulation and revealed the segregation influence of aluminum in the grain boundary structure and local atomic environment by training machine learning models.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning-Assisted Prediction of Corrosion Behavior of 7XXX Aluminum Alloys

Xiong,

Zhang,

Yang

et al. 2024

Metals

View full text Add to dashboard Cite

High-strength and lightweight 7XXX Al alloys are widely applied in aerospace industries. Stress corrosion cracking (SCC) in these alloys has been extensively discussed, and electrochemical corrosion should be brought to the forefront when these materials are used in marine atmospheric environments. This work obtained the corrosion potentials (Ecorr) and corrosion rates of 40 as-cast 7XXX Al alloys by potentiodynamic polarization tests and immersion tests, respectively; then, chemical compositions and physical features were used to build a machine learning model to predict these parameters. RFR was used for the prediction model of Ecorr with the features Cu, Ti, Al, and Zn, and GPR for that of the corrosion rate with the features of specific heat, latent heat of fusion, and proportion of p electrons. The physical meaning and reasonability were discussed based on the analysis of corrosion morphology and precipitated composition. This work provides a reference for the design of corrosion-resistant 7XXX Al alloys and shows a method of conducting corrosion mechanism evaluation by using machine learning.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning-Assisted Prediction of Corrosion Behavior of 7XXX Aluminum Alloys

Xiong,

Zhang,

Yang

et al. 2024

Metals

View full text Add to dashboard Cite

show abstract

“…One of the essential outcomes that is expected from the data analysis of ultrasound NDE is to elucidate the significance of each contributing parameter in the technique, for which Artificial Intelligence (AI) agents have been shown as effective. AI has already been utilized in the field of material behavior monitoring and prediction, helping with various issues ranging from alloy design to damage prognosis/detection [1][2][3] . Machine Learning (ML) has been utilized for content optimization of aluminum alloy to obtain best sensitization behavior 3 .…”

Section: Introductionmentioning

confidence: 99%

“…A novel NDE technique has been developed using a Convolutional Neural Network (CNN) to predict the location and orientation of a crack based on ultrasound measurement 1 . Deep Learning (DP) has been used to predict mechanical and corrosion behavior of the aluminum alloy based metallographic images of the specimen surfaces 2 . In most of the studies, the use of AI is limited to delivering accurate and reliable predictions rather than understanding the significance level of contributing parameters, which can lead to broader understanding of physics underlying the NDE technique.…”

Section: Introductionmentioning

confidence: 99%

Sensitivity analysis of the ultrasound features for the sensitization prediction of Al-Mg alloys via Adaptive Neuro-Fuzzy Inference System (ANFIS)

Dizadji

Abusoua

Huang

2023

Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2023

View full text Add to dashboard Cite

This research analyzes the sensitivity of the ultrasound features to sensitization, a microstructural damage developed in Al-Mg alloys when subjected to extended period of heat treatment. For rule extraction, an Adaptive Neuro-Fuzzy Inference System (ANFIS) was first developed and customized to house the ultrasound features from the Electromechanical Impedance (EMI) of Piezoelectric Wafer Active Sensor (PWAS) attached on aluminum plates with progressive sensitization development. The features are rooted in the rise time and the amplitude of the time domain signal that was obtained at two different resonance phases. The extracted fuzzy rules were analyzed to determine the sensitivity of each feature at both the model and rule level. The analysis revealed that the rise time changes at higher resonance frequency and the amplitude change at lower resonance frequency has a stronger correlation to sensitization. The results of rule significance evaluation demonstrated that the data measured at low resonance frequency exhibits more correlation to sensitization.

show abstract

“…Ao et al developed a prediction model for the corrosion and mechanical properties behaviour of aluminum parts using a deep learning approximation in their research. This model was created by combining mechanical properties and metallographic data, which can support intelligent and non-destructive testing methods to avoid unexpected results (Ao et al, 2022). Ma et al trained a deep convolutional neural network based on DeepLab.…”

Section: Introductionmentioning

confidence: 99%

Optimization with artificial intelligence of the machinability of Hardox steel, which is exposed to different processes

Altuğ

Söyler

2023

Preprint

View full text Add to dashboard Cite

In this study, different process types were processed on Hardox 400 steel. These processes were carried out with five different samples as heat treatment, cold forging, plasma welding, mig-mag welding and commercial sample. The aim here is to determine the changes in properties such as microstructure, microhardness and conductivity that occur in the structure of hardox 400 steel when exposed to different processes. Then, the samples affected by these changes were processed in WEDM with the box-behnken experimental design. Ra, Kerf, MRR and WWR results were analyzed in Minitab 21 program. In the continuation of the study, using these data, a prediction models were created for Ra, Kerf, MRR and WWR with DL and ELM. Anaconda program Python 3.9 version was used as a program in the optimization study. In addition, a linear regression models are presented to comparison the results. According to the results the lowest Ra values were obtained in heat-treated, cold forged, master sample, plasma welded and mig-mag welded processes, respectively. Model F value in ANOVA analysis for Ra is 86,04. Model for Ra r2 value was obtained as 0.9534. The lowest kerf values were obtained in heat-treated, cold forged, master sample, plasma welded and mig-mag welded processes, respectively. Model F value in ANOVA analysis for Kerf is 90,21. Model for Kerf r2 value was obtained as 0.9555. Contrary to Ra and Kerf, it is desirable to have high MRR values. On average, the highest MRR values were obtained in mig-mag welded, plasma welded, cold forged, master sample and heat-treated processes, respectively. Model for MRR r2 value was obtained as 0.9563. The lowest WWR values were obtained in heat-treated, cold forged, master sample, plasma welded and mig-mag welded processes, respectively. Model F value in ANOVA analysis for WWR is 92.12. Model for Kerf wwr r2 value was obtained as 0.09561. In the analysis made with artificial intelligence systems; the best test MSE value for Ra was obtained as 0.0093 in DL and the r squared value 0.9439. The best test MSE value for Kerf was obtained as 248.28 in ELM and r squared value 0.8676. The best MSE value for MRR was obtained as 0.000144 in DL and the r squared value 0.9209. The best MSE value for WWR was obtained as 0.000073 in DL and the r squared value 0.8382. As a result, it was concluded that different optimization methods can be applied according to different outputs (Ra, Kerf, MRR, WWR). It also shows that artificial intelligence-based optimization methods give successful estimation results about Ra, Kerf, MRR, WWR values. According to these results, ideal DL and ELM models have been presented for future studies.

show abstract

Image Deep Learning Assisted Prediction of Mechanical and Corrosion Behavior for Al-Zn-Mg Alloys

Cited by 7 publications

References 63 publications

Machine Learning-Assisted Prediction of Corrosion Behavior of 7XXX Aluminum Alloys

Machine Learning-Assisted Prediction of Corrosion Behavior of 7XXX Aluminum Alloys

Sensitivity analysis of the ultrasound features for the sensitization prediction of Al-Mg alloys via Adaptive Neuro-Fuzzy Inference System (ANFIS)

Optimization with artificial intelligence of the machinability of Hardox steel, which is exposed to different processes

Contact Info

Product

Resources

About