Abstract:Electric shovels are widely used in the mining industry to dig ore, and the teeth in shovels’ bucket can be lost due to the tremendous pressure exerted by ore materials during operation. When the teeth fall off and enter the crusher with other ore materials, serious damages to crusher gears and other equipment happen, which causes millions of economic loss, because it is made of high-manganese steel. Thus, it is urgent to develop an efficient and automatic algorithm for detecting broken teeth. However, existin… Show more
Deep learning is a sub-field of artificial intelligence that combines feature engineering and classification in one method. It is a data-driven technique that optimises a predictive model via learning from a large dataset. Digitisation in industry has included acquisition and storage of a variety of large datasets for interpretation and decision making. This has led to the adoption of deep learning in different industries, such as transportation, manufacturing, medicine and agriculture. However, in the mining industry, the adoption and development of new technologies, including deep learning methods, has not progressed at the same rate as in other industries. Nevertheless, in the past 5 years, applications of deep learning have been increasing in the mining research space. Deep learning has been implemented to solve a variety of problems related to mine exploration, ore and metal extraction and reclamation processes. The increased automation adoption in mining provides an avenue for wider application of deep learning as an element within a mine automation framework. This work provides a compact, comprehensive review of deep learning implementations in mining-related applications. The trends of these implementations in terms of years, venues, deep learning network types, tasks and general implementation, categorised by the value chain operations of exploration, extraction and reclamation are outlined. The review enables shortcomings regarding progress within the research context to be highlighted such as the proprietary nature of data, small datasets (tens to thousands of data points) limited to single operations with unique geology, mine design and equipment, lack of large scale publicly available mining related datasets and limited sensor types leading to the majority of applications being image-based analysis. Gaps identified for future research and application includes the usage of a wider range of sensor data, improved understanding of the outputs by mining practitioners, adversarial testing of the deep learning models, development of public datasets covering the extensive range of conditions experienced in mines.
Deep learning is a sub-field of artificial intelligence that combines feature engineering and classification in one method. It is a data-driven technique that optimises a predictive model via learning from a large dataset. Digitisation in industry has included acquisition and storage of a variety of large datasets for interpretation and decision making. This has led to the adoption of deep learning in different industries, such as transportation, manufacturing, medicine and agriculture. However, in the mining industry, the adoption and development of new technologies, including deep learning methods, has not progressed at the same rate as in other industries. Nevertheless, in the past 5 years, applications of deep learning have been increasing in the mining research space. Deep learning has been implemented to solve a variety of problems related to mine exploration, ore and metal extraction and reclamation processes. The increased automation adoption in mining provides an avenue for wider application of deep learning as an element within a mine automation framework. This work provides a compact, comprehensive review of deep learning implementations in mining-related applications. The trends of these implementations in terms of years, venues, deep learning network types, tasks and general implementation, categorised by the value chain operations of exploration, extraction and reclamation are outlined. The review enables shortcomings regarding progress within the research context to be highlighted such as the proprietary nature of data, small datasets (tens to thousands of data points) limited to single operations with unique geology, mine design and equipment, lack of large scale publicly available mining related datasets and limited sensor types leading to the majority of applications being image-based analysis. Gaps identified for future research and application includes the usage of a wider range of sensor data, improved understanding of the outputs by mining practitioners, adversarial testing of the deep learning models, development of public datasets covering the extensive range of conditions experienced in mines.
Abstract. An electric shovel is a bucket-equipped mining excavator widely used in open-pit mining today. The prolonged direct impact between the
bucket teeth and the ore during the mining process will cause the teeth to
loosen prematurely or even break, resulting in unplanned downtime and
productivity losses. To solve this problem, we propose a real-time and
accurate detection algorithm of bucket teeth falling off based on improved
YOLOX. Firstly, to solve the problem of poor detection effect caused by uneven illumination, the dilated convolution attention mechanism is added to
enhance the feature expression ability of the target in complex backgrounds
so as to improve the detection accuracy of the target. Secondly, considering
the high computing cost and large delay of the embedded device, the deep
separable convolution is used to replace the traditional convolution in the
feature pyramid network, and the model compression strategy is used to prune
the redundant channels in the network, reduce the model volume, and improve
the detection speed. The performance test is carried out on the
self-constructed dataset of WK-10 electric shovel. The experimental results show that, compared with the YOLOX model, the mean average precision of the
algorithm in this paper reaches 95.26 %, only 0.33 % lower, while the
detection speed is 50.8 fps, 11.9 fps higher, and the model volume is 28.42 MB,
which is reduced to 29.46 % of the original. Compared with many other
existing methods, the target detection algorithm proposed in this paper has
the advantages of higher precision, smaller model volume, and faster speed.
It can meet the requirements of real-time and accurate detection of the
bucket teeth falling off.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.