Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning
The present work investigates the relationship between fatigue crack growth rate (d<i>a</i>/d<i>N</i>) and stress intensity factor range (∆<i>K</i>) using machine learning models with the experimental fatigue crack growth rate (FCGR) data of cryo-rolled Al 2014 al...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-10-01
|
| Series: | Metals |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4701/10/10/1349 |
| _version_ | 1797551525028954112 |
|---|---|
| author | Allavikutty Raja Sai Teja Chukka Rengaswamy Jayaganthan |
| author_facet | Allavikutty Raja Sai Teja Chukka Rengaswamy Jayaganthan |
| author_sort | Allavikutty Raja |
| collection | DOAJ |
| description | The present work investigates the relationship between fatigue crack growth rate (d<i>a</i>/d<i>N</i>) and stress intensity factor range (∆<i>K</i>) using machine learning models with the experimental fatigue crack growth rate (FCGR) data of cryo-rolled Al 2014 alloy. Various machine learning techniques developed recently provide a flexible and adaptable approach to explain the complex mathematical relations especially, non-linear functions. In the present work, three machine algorithms such as extreme learning machine (ELM), back propagation neural networks (BPNN) and curve fitting model are implemented to analyse FCGR of Al alloys. After tuning of networks with varying hidden layers and number of neurons, the trained models found to fit well to the tested data. The three tested models are compared with each other over the training as well as testing phase. The mean square error for predicting the FCG of cryo-rolled Al 2014 alloy by BPNN, ELM and curve fitting methods are 1.89, 1.84 and 0.09 respectively. While the ELM models outperform the rest of models in terms of training time, curve fitting model showed best performance in terms of accuracy over testing data with least mean square error (MSE). In terms of local optimisation, back propagation neural networks excel the other two models. |
| first_indexed | 2024-03-10T15:46:18Z |
| format | Article |
| id | doaj.art-f43b99aebb85455096e38aa9c4b8f8b0 |
| institution | Directory Open Access Journal |
| issn | 2075-4701 |
| language | English |
| last_indexed | 2024-03-10T15:46:18Z |
| publishDate | 2020-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Metals |
| spelling | doaj.art-f43b99aebb85455096e38aa9c4b8f8b02023-11-20T16:28:41ZengMDPI AGMetals2075-47012020-10-011010134910.3390/met10101349Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine LearningAllavikutty Raja0Sai Teja Chukka1Rengaswamy Jayaganthan2Department of Engineering Design, Indian Institute of Technology Madras, Chennai 600036, IndiaDepartment of Engineering Design, Indian Institute of Technology Madras, Chennai 600036, IndiaDepartment of Engineering Design, Indian Institute of Technology Madras, Chennai 600036, IndiaThe present work investigates the relationship between fatigue crack growth rate (d<i>a</i>/d<i>N</i>) and stress intensity factor range (∆<i>K</i>) using machine learning models with the experimental fatigue crack growth rate (FCGR) data of cryo-rolled Al 2014 alloy. Various machine learning techniques developed recently provide a flexible and adaptable approach to explain the complex mathematical relations especially, non-linear functions. In the present work, three machine algorithms such as extreme learning machine (ELM), back propagation neural networks (BPNN) and curve fitting model are implemented to analyse FCGR of Al alloys. After tuning of networks with varying hidden layers and number of neurons, the trained models found to fit well to the tested data. The three tested models are compared with each other over the training as well as testing phase. The mean square error for predicting the FCG of cryo-rolled Al 2014 alloy by BPNN, ELM and curve fitting methods are 1.89, 1.84 and 0.09 respectively. While the ELM models outperform the rest of models in terms of training time, curve fitting model showed best performance in terms of accuracy over testing data with least mean square error (MSE). In terms of local optimisation, back propagation neural networks excel the other two models.https://www.mdpi.com/2075-4701/10/10/1349machine learningfatigue crack growthback propagation neural networkextreme learning machinecryo-rollingAl alloy |
| spellingShingle | Allavikutty Raja Sai Teja Chukka Rengaswamy Jayaganthan Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning Metals machine learning fatigue crack growth back propagation neural network extreme learning machine cryo-rolling Al alloy |
| title | Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning |
| title_full | Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning |
| title_fullStr | Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning |
| title_full_unstemmed | Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning |
| title_short | Prediction of Fatigue Crack Growth Behaviour in Ultrafine Grained Al 2014 Alloy Using Machine Learning |
| title_sort | prediction of fatigue crack growth behaviour in ultrafine grained al 2014 alloy using machine learning |
| topic | machine learning fatigue crack growth back propagation neural network extreme learning machine cryo-rolling Al alloy |
| url | https://www.mdpi.com/2075-4701/10/10/1349 |
| work_keys_str_mv | AT allavikuttyraja predictionoffatiguecrackgrowthbehaviourinultrafinegrainedal2014alloyusingmachinelearning AT saitejachukka predictionoffatiguecrackgrowthbehaviourinultrafinegrainedal2014alloyusingmachinelearning AT rengaswamyjayaganthan predictionoffatiguecrackgrowthbehaviourinultrafinegrainedal2014alloyusingmachinelearning |