Data augmentation using conditional generative adversarial network (cGAN): Application for prediction of corrosion pit depth and testing using neural network

Woldesellasse, Haile; Tesfamariam, Solomon

doi:10.1016/j.jpse.2022.100091

Cited by 7 publications

(3 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…He and Zhou [ 19 ] used tabular generative adversarial networks to generate synthetic full-scale blasting test data for corroded pipelines. Woldesellasse and Tesfamariam [ 20 ] used a CGAN to handle the class imbalance in soil data by generating synthetic samples. Habibi et al [ 21 ] used a CTGAN and machine learning for imbalanced tabular data modeling to improve IoT botnet attack detection.…”

Section: Introductionmentioning

confidence: 99%

Data Augmentation of a Corrosion Dataset for Defect Growth Prediction of Pipelines Using Conditional Tabular Generative Adversarial Networks

Ma,

Geng,

Wang

et al. 2024

Materials

View full text Add to dashboard Cite

Due to corrosion characteristics, there are data scarcity and uneven distribution in corrosion datasets, and collecting high-quality data is time-consuming and sometimes difficult. Therefore, this work introduces a novel data augmentation strategy using a conditional tabular generative adversarial network (CTGAN) for enhancing corrosion datasets of pipelines. Firstly, the corrosion dataset is subjected to data cleaning and variable correlation analysis. The CTGAN is then used to generate external environmental factors as input variables for corrosion growth prediction, and a hybrid model based on machine learning is employed to generate corrosion depth as an output variable. The fake data are merged with the original data to form the synthetic dataset. Finally, the proposed data augmentation strategy is verified by analyzing the synthetic dataset using different visualization methods and evaluation indicators. The results show that the synthetic and original datasets have similar distributions, and the data augmentation strategy can learn the distribution of real corrosion data and sample fake data that are highly similar to the real data. Predictive models trained on the synthetic dataset perform better than predictive models trained using only the original dataset. In comparative tests, the proposed strategy outperformed other data generation methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Data Augmentation of a Corrosion Dataset for Defect Growth Prediction of Pipelines Using Conditional Tabular Generative Adversarial Networks

Ma,

Geng,

Wang

et al. 2024

Materials

View full text Add to dashboard Cite

show abstract

“…In recent years, the adoption of machine learning in modelling real engineering problems was built on its ability to understand the interrelationships between real input and output data. The potential of these techniques to predict material properties has been reported in scientific literature [14][15][16][17][18][19]. Among the different techniques proposed in the literature, Artificial Neural Networks (ANNs) have become a promising tool that offers great computational power even when a small experimental dataset is considered [20].…”

Section: Introductionmentioning

confidence: 99%

Corrosion Behaviour Modelling Using Artificial Neural Networks: A Case Study in Biogas Environment

Jiménez-Come,

González Gallero,

Álvarez Gómez

et al. 2023

Metals

View full text Add to dashboard Cite

The main objective established in this work was to develop a model based on artificial neural networks (ANNs) to predict the corrosion status of stainless steel involved in biogas production, analyzing the influence of the material composition and the breakdown potential value. To achieve this objective, an ANN model capable of predicting the corrosion status of the material without the need to perform microscopic analysis on the material surface was proposed. The applicability of the corrosion models was verified via the experimental data considering different factors such as stainless steel composition, biogas environments simulated by artificial solution, temperature, surface finish, and the breakdown potential of the passive layer of stainless steel obtained from electrochemical tests. The optimal prediction performance shown by the model in terms of specificity and sensitivity values were 0.969 and 0.971, respectively, obtaining an accuracy of 0.966. Furthermore, analyzing the influence of the breakdown potential on corrosion modelling, an alternative model was presented capable of predicting the corrosion status automatically, without the need to resort to electrochemical tests for new conditions. The results demonstrated the utility of this technique to be considered in design and maintenance planning tasks for stainless steel structures subjected to localized corrosion in biogas production.

show abstract

“…They have been based on the identifiability assumption of intelligence and aimed to make the simulation a machine. Thus, it seeks to enable people to solve problems specific to humans and learn from data [1][2][3][4]. The primary purpose is to solve the issues that people can learn or solve with their cognitive intelligence with the help of machines or applications.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Factors Affecting Common Use of Generative Artificial Intelligence-Based Tools by Machine Learning Methods

KIRELLİ

2023

IJCESEN

View full text Add to dashboard Cite

Artificial Intelligence is a sub-branch of artificial intelligence used to produce new data or content. These methods can create recent examples in different categorical fields such as natural language processing, image processing, music, and video creation by using models from learning clusters with artificial intelligence (AI) tools in this field. AI tools that can solve real-world problems are also created using different methods apart from generative AI methods. With generative-based artificial intelligence tools, it can facilitate people's work in jobs that require creativity. However, they can offer the opportunity to build advanced models that learn from data with other artificial intelligence methods. In the study, the public dataset has been used. This dataset includes trending artificial intelligence tools, AI methods, and user scores. In this study the working area and user trend of the ai tools in the dataset and the effect of generative AI methods on the development of the tool are discussed. Random Forest and Naive Bayes algorithms from classification methods have been used to measure the impact and estimation. Several AI tools help solve real-life problems. Identifying what type of category is needed for AI tools and method selection are interlinked, and the research provides an overview of this connection.

show abstract

Data augmentation using conditional generative adversarial network (cGAN): Application for prediction of corrosion pit depth and testing using neural network

Cited by 7 publications

References 55 publications

Data Augmentation of a Corrosion Dataset for Defect Growth Prediction of Pipelines Using Conditional Tabular Generative Adversarial Networks

Data Augmentation of a Corrosion Dataset for Defect Growth Prediction of Pipelines Using Conditional Tabular Generative Adversarial Networks

Corrosion Behaviour Modelling Using Artificial Neural Networks: A Case Study in Biogas Environment

Analysis of Factors Affecting Common Use of Generative Artificial Intelligence-Based Tools by Machine Learning Methods

Contact Info

Product

Resources

About