Automated classification of civil structure defects based on convolutional neural network

Today, the most commonly used civil infrastructure inspection method is based on a visual assessment conducted by certified inspectors following prescribed protocols. However, the increase in aggressive environmental and load conditions, coupled with the achievement of many structures of the life-cycle end, has highlighted the need to automate damage identification and satisfy the number of structures that need to be inspected. To overcome this challenge, this paper presents a method for automating concrete damage classification using a deep convolutional neural network. The convolutional neural network was designed after an experimental investigation of a wide number of pretrained networks, applying the transfer-learning technique. Training and validation were conducted using a database built with 1352 images balanced between “undamaged”, “cracked”, and “delaminated” concrete surfaces. To increase the network robustness compared to images in real-world situations, different image configurations have been collected from the Internet and on-field bridge inspections. The GoogLeNet model, with the highest validation accuracy of approximately 94%, was selected as the most suitable network for concrete damage classification. The results confirm that the proposed model can correctly classify images from real concrete surfaces of bridges, tunnels, and pavement, resulting in an effective alternative to the current visual inspection techniques.     

EXACT RELATIONSHIPS BETWEEN PARAMETERS AND TEST DATA FOR MODELS OF SYNCHRONOUS MACHINES

ABSTRACT

In a recent paper the authors have presented a new method expressing the parameters of a synchronous machine model in terms of measurable time constants, without the traditional simplifying assumptions. The considered model is characterized by equal mutual reactances between armature, field and damper windings.

This paper shows the extention of the new method to the models with all three unequal mutuals and with two equal mutuals. The exact relationships between the parameters of the examined models and the test data are provided. Comparisons are made between new and old method results to demonstrate the discrepancies in values of parameters.