Ensemble of convolutional neural networks based on an evolutionary algorithm applied to an industrial welding process

This paper presents an approach for image classification based on an ensemble of convolutional neural networks and the application to a real case study of an industrial welding process. The ensemble consists of five convolutional neural networks, whose outputs are combined through a voting policy. I...

Descripción completa

Detalles Bibliográficos
Autores: Cruz, Yarens J., Rivas, Marcelino, Quiza, Ramón, Villalonga, Alberto, Haber Guerra, Rodolfo E., Beruvides, Gerardo
Tipo de recurso: artículo
Estado:Versión aceptada para publicación
Fecha de publicación:2021
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/251367
Acceso en línea:http://hdl.handle.net/10261/251367
Access Level:acceso abierto
Palabra clave:Image classification
Ensemble of models
Convolutional neural networks
Evolutionary parameters
Descripción
Sumario:This paper presents an approach for image classification based on an ensemble of convolutional neural networks and the application to a real case study of an industrial welding process. The ensemble consists of five convolutional neural networks, whose outputs are combined through a voting policy. In order to select appropriate network parameters (i.e., the number of convolutional layers and layers hyperparameters) and voting policy, an efficient search process was carried out by using an evolutionary algorithm. The proposed method is applied and validated in a case study focused on detecting misalignment of metal sheets to be joined through submerged arc welding process. After selecting the most convenient setup, the ensemble outperforms other seven strategies considered in a comparison in several metrics, while maintaining an adequate computational cost.