Convolutional Neural Network based Power Crane Defect Analysis

Crane failures cause severe damage both to the crane itself and to the surrounding area. These accidents often cause high losses and also result in serious injury or death to workers. The significant loss of life and property can be reduced by frequent inspection and crane maintenance. Therefore, the detection of fault detection in crane is of great importance to the researchers. In this paper, we have developed a model based on Convolutional Neural Network which can detect the defect in a crane effectively and efficiently. The model takes an image as input and classifies whether the image is normal or has a defect. To verify the effectiveness of the model, a case study was conducted on a crane wire image dataset.