Automatic Inspection System of Welding Radiographic Images Based on ANN Under a Regularisation Process

Zapata, Juan; Vilar, Rafael; Ruíz, Ramón Eduardo

doi:10.1007/s10921-011-0118-4

Cited by 40 publications

(15 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Naárea de pesquisa relacionada ao suporte eà automação da inspeção radiográfica de juntas soldadas, a maior parte da literatura emprega técnicas rasas de aprendizado de máquina (como Sistemas Fuzzy [Baniukiewicz 2014, Liao 2003], redes Multilayer Perceptron [Zapata et al 2012, Nacereddine e Tridi 2005 e Support Vector Machine [Duan et al 2019]). Tais técnicas necessitam do design manual dos atributos relevantes ao problema, resultando em abordagens, geralmente, com alta dependência de parâmetros manuais.…”

Section: Trabalhos Relacionadosunclassified

Filtragem de Dados de Treinamento para Aprendizagem Profunda Aplicada à Inspeção de Juntas Soldadas em Tubulações de Petróleo

Silva¹,

Suyama²,

Silva³

et al. 2020

Anais Do Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2020)

View full text Add to dashboard Cite

A inspeção de radiografias de soldas é uma tarefa essencial para a prevenção de vazamentos em tubulações da indústria petrolífera. A inspeção automática é importante para auxiliar os especialistas em uma tarefa que pode ser influenciada pela fadiga, acuidade visual e experiência. Uma dificuldade da inspeção automática é a disponibilidade de imagens laudadas que possam ser utilizadas para o treinamento de classificadores. O uso de aumento de dados auxilia nesta tarefa mas pode produzir imagens com pouco impacto ou mesmo impacto negativo no treinamento de um classificador. Neste artigo apresenta-se uma método para filtragem de imagens, de forma a favorecer o reaprendizado do classificador, processo este que se dá pela eliminação de imagens com baixo desempenho na base de treino e posterior retreinamento, com impacto positivo para a generalização do modelo de classificação. Os resultados experimentais do método mostram que a filtragem dos dados acelera o processo de aprendizado e produz uma melhora no desempenho da classificação.

show abstract

Section: Trabalhos Relacionadosunclassified

Filtragem de Dados de Treinamento para Aprendizagem Profunda Aplicada à Inspeção de Juntas Soldadas em Tubulações de Petróleo

Silva¹,

Suyama²,

Silva³

et al. 2020

Anais Do Encontro Nacional De Inteligência Artificial E Computacional (ENIAC 2020)

View full text Add to dashboard Cite

show abstract

“…Abderrazak et al [10] established a welding quality evaluation method of ANN by simulating welding parameters (welding time, current, voltage, thickness, etc.). Zapata et al [11] modified the ANN to improve the detection accuracy of individual and overall defect characteristics. Yuan et al [12] studied adaptive organization and adaptive feed-forward neural network to figure out the essential features of defects and effectively reduce identification errors.…”

Section: Introductionmentioning

confidence: 99%

A New Image Recognition and Classification Method Combining Transfer Learning Algorithm and MobileNet Model for Welding Defects

et al. 2020

View full text Add to dashboard Cite

Welding quality directly affects the welding structure's service performance and life. Hence, the effective monitoring welding defects is essential to ensure the quality of the weld structure. Owing to the non-uniformity of the shape, position and size of welding defects, it is a complicated task to analyze and evaluate the acquired welding defects images manually. Fortunately, deep learning has been successfully applied to image analysis and target recognition. However, the use of deep learning to identify welding defects is time-consuming and less accurate due to the lack of adequate training data samples, which easily cause redundancy into the classifier. In this situation, we proposed a new transfer learning model based on MobileNet as a welding defect feature extractor. By using the ImageNet dataset (non-welding defect data) to pre-train a MobileNet model, migrate the MobileNet model to the welding defects classification field. This article suggested a new TL-MobileNet structure by adding a new Full Connection layer (FC-128) and a Softmax classifier into a traditional model called MobileNet. The entire training process of TL-MobileNet model has been successfully optimized by the DropBlock technology and Global average pooling (GAP) method. They can effectively accelerate the convergence rate and improve the classification network generalization. By testing the proposed TL-MobileNet on the welding defects dataset, it turned out our model prediction accuracy has arrived at 97.69%. The experimental results show that in several aspects, TL-MobileNet have better performance than other transfer learning models and traditional neural network methods.

show abstract

“…In the literature related to classification of welding defects, the researchers have used different feature extraction techniques such as Principal Component Analysis (PCA) [3], self organizing map [4], ant colony optimization technique [5] to classify the weld defects. But these techniques produce good results when they are applied on weld defects having less similarity in geometric and texture information.…”

Section: Introductionmentioning

confidence: 99%

Localization and classification of welding defects using genetic algorithm based optimal feature set

Kamran

Awan

Jalil

et al. 2015

2015 International Conference on Information and Communication Technologies (ICICT)

View full text Add to dashboard Cite

Radiography is being widely used as a nondestructive testing technique to investigate the safety and reliability of welded process. In this paper an automated weld defect recognition framework is presented, which employs image processing and pattern recognition methods on weld radiographs. Initially, a pre-processing step is performed on radiographs that suppresses undesired distortions and enhances image features important for further processing. After image pre-processing, a set of features including the geometric and texture features are extracted from each object in a segmented image. Genetic algorithm is applied for selecting the optimal feature sets. The optimal and reduced feature vector is then given as input to SVM and ANN for classification. The last step of the recognition system includes the evaluation of the detected/classified defects in the weld on the basis of acceptance criterion. Experimental results show that an overall improvement in performance and accuracy is achieved using GA based optimal features with SVM as classifier.

show abstract

Automatic Inspection System of Welding Radiographic Images Based on ANN Under a Regularisation Process

Cited by 40 publications

References 13 publications

Filtragem de Dados de Treinamento para Aprendizagem Profunda Aplicada à Inspeção de Juntas Soldadas em Tubulações de Petróleo

Filtragem de Dados de Treinamento para Aprendizagem Profunda Aplicada à Inspeção de Juntas Soldadas em Tubulações de Petróleo

A New Image Recognition and Classification Method Combining Transfer Learning Algorithm and MobileNet Model for Welding Defects

Localization and classification of welding defects using genetic algorithm based optimal feature set

Contact Info

Product

Resources

About