Abstract
The electric shovel is a bucket-equipped mining excavator widely used in open-pit mining today. The prolonged direct impact of the bucket teeth with hard and abrasive materials such as ore during the process of the mining excavation can cause the bucket teeth to break and fall off prematurely, resulting in unplanned downtime and productivity losses. In response to this problem, we have developed a vision-based bucket teeth fault detection algorithm with deep learning. Using a dataset based on the images of both real shovel teeth and 3D-printed models, we trained a Faster Region Convolutional Neural Network (Faster R-CNN) to obtain the number of normal bucket teeth and the positions of the bucket teeth from the images, using the additional bucket dataset from 3D-printed models to pre-train the network for improving its detection accuracy on the real bucket data. We compared the resulting Faster R-CNN model with the ZFNet, the ResNet-50, and the VGG16 and found our Faster R-CNN model to perform best in terms of accuracy and speed.
Highlights
Open-pit mining [1] today involves different mining and transportation methods, ranging from discontinuous, semi-continuous to continuous systems
DATASET PREPARATION To be the best of our knowledge, there are no existing standard datasets for bucket teeth detection, and acquiring a large real bucket teeth image dataset for deep learning is challenging. We address this problem by reconstructing bucket teeth datasets that are suitable for training deep learning models
For the MSTOD, we collected 12,500 images from photos of the model bucket, of which 10,000 are used as the training set and 2,500 are used as the test set. With data enhancement, such as image rotation, translation, zoom, and other methods, we have a total of 30,000 MSTOD images for training, while the size of the data-enhanced RSTOD training dataset is 1110, leading to 2220 images after the data is expanded by the mirror flip function that comes with the Faster R-Convolutional Neural Network (CNN)
Summary
Open-pit mining [1] today involves different mining and transportation methods, ranging from discontinuous, semi-continuous to continuous systems. An automatic machine vision-based detection algorithm that can judge whether the bucket teeth of the electric shovel are faulty from the images can provide timely or even early warning information, guide the on-site personnel in a deal with failures, reduce maintenance time, economic loss, and protect personal safety. We design a deep learning algorithm for object detection of bucket teeth based on Faster R-CNN. Based on these two original datasets of 3D printing models and real working conditions, we compared the performance of our Faster R-CNN algorithm with other state-of-the-art computer vision algorithms and found that our model outperformed existing methods in the detection of faulty bucket teeth and positions.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
