An Evaluation of Iron Ore Characteristics Through Machine Learning and 2-D LiDAR Technology

Matos, Saulo N.; Pinto, Thomas V. B.; Domingues, Jacó D.; Ranieri, Caetano M.; Albuquerque, Kaike S.; Moreira, Vinicius S.; Souza, Ernandes S.; Ueyama, Jó; Euzébio, Thiago A. M.; Pessin, Gustavo

doi:10.1109/tim.2023.3342220

Cited by 1 publication

(1 citation statement)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These AI-related applications are mainly based on convolutional neural networks (CNNs) and transfer learning, for which GoogleNet and MobileNet are highlighted architectures. Concerning flotation processes, Matos et al [112] developed an intelligent online instrument to recognize ore type and degree of fragmentation on conveyor belts. They did so by utilizing a 2D LiDAR sensor combined with machine learning (ML) techniques.…”

Section: Gapsmentioning

confidence: 99%

Sensor Technologies for Safety Monitoring in Mine Tailings Storage Facilities: Solutions in the Industry 4.0 Era

Cacciuttolo,

Guzmán,

Catriñir

et al. 2024

Minerals

View full text Add to dashboard Cite

The recent tailings storage facility (TSF) dam failures recorded around the world have concerned society in general, forcing the mining industry to improve its operating standards, invest greater economic resources, and implement the best available technologies (BATs) to control TSFs for safety purposes and avoid spills, accidents, and collapses. In this context, and as the era of digitalization and Industry 4.0 continues, monitoring technologies based on sensors have become increasingly common in the mining industry. This article studies the state of the art of implementing sensor technologies to monitor structural health and safety management issues in TSFs, highlighting advances and experiences through a review of the scientific literature on the topic. The methodology applied in this article adheres to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and utilizes scientific maps for data visualization. To do so, three steps were implemented: (i) a quantitative bibliometric analysis, (ii) a qualitative systematic review of the literature, and (iii) a mixed review to integrate the findings from (i) and (ii). As a result, this article presents the main advances, gaps, and future trends regarding the main characteristics of the sensor technologies applied to monitor TSF structural health and safety management in the era of digitalization. According to the results, the existing research predominantly investigates certain TSF sensor technologies, such as wireless real-time monitoring, remote sensors (RS), unmanned aerial vehicles (UAVs), unmanned survey vessels (USVs), artificial intelligence (AI), cloud computing (CC), and Internet of Things (IoT) approaches, among others. These technologies stand out for their potential to improve the safety management monitoring of mine tailings, which is particularly significant in the context of climate change-related hazards, and to reduce the risk of TSF failures. They are recognized as emerging smart mining solutions with reliable, simple, scalable, secure, and competitive characteristics.

show abstract

Section: Gapsmentioning

confidence: 99%