Automated Monitoring of Construction Sites of Electric Power Substations Using Deep Learning

Abstract

With each passing year, the consumption of electric energy in Brazil and the world increases, making it necessary to adopt measures such as the construction of new plants and the installation of power distribution structures. Monitoring for construction management in companies is still done in person and manually, resulting in expenses that could be avoided. That said, there are opportunities to automate such processes using artificial intelligence and, therefore, the main objective of this work is the development of an automated constructions management system, whose goal is to increase the management and monitoring of substation constructions with the remote monitoring. The system incorporates resources of deep learning to classify the components in bays, comparing the data generated in this recognition with the engineering projects to verify the progress of the installation of these components and generating indicators of conformity and evolution of the construction. To achieve the main objective, a comparison was made among four convolutional neural network architectures: DenseNet, Inception, ResNet, and SqueezeNet, in the classification task. The models were trained with thousands of images extracted from photos of different bays captured in the field and, additionally, data augmentation techniques were applied. The models were trained using transfer learning and fine tuning starting from pre-trained weights in the ImageNet data set. All models obtained results close to 100% in the images of the test set, hence it is possible to conclude that, for the proposed problem, there was no significant difference between the assertiveness of the architectures. The chosen model was part of the final application that monitors the construction management of the bays in the electricity substations.

Estação Meteorológica De Baixo Custo Para Cálculo, Armazenamento E Exibição Da Evapotranspiração De Referência

“…Para verificar a confiabilidade da medida ou estimação de uma determinada variável, é necessário fazer a comparação dos dados obtidos a partir do método proposto com valores reais ou então que possam ser considerados como referência (OLIVEIRA et al, 2021). Segundo Meira e Ávila (2010), "a comparação ideal entre os parâmetros atmosféricos estimados e as medidas requer a obtenção de métricas de avaliação dos parâmetros atmosféricos", o que permite verificar a confiabilidade dos dados obtidos pela estimação.…”

Detection and Location of Safety Protective Wear in Power Substation Operation Using Wear-Enhanced YOLOv3 Algorithm

“…The continuous expansion of power systems means the increasing number and scale of substations. The long-term safe and stable operation of substation is necessary for the safe and stable operation of power systems [2].…”

Uma Abordagem de Classificação de Ovos de Parasitos Intestinais Humanos em Imagens Microscópicas usando Redes Neurais Convolucionais

“…Atualmente, um dos principais algoritmos de aprendizado de máquina são as redes neurais convolucionais, também conhecidas como CNNs. Elas pertencem a uma classe de redes neurais profundas e são constantemente aplicadas em tarefas de classificac ¸ão e detecc ¸ão de objetos em imagens [6].…”