Deep Learning Approach at the Edge to Detect Iron Ore Type
There is a constant risk of iron ore collapsing during its transfer between processing stages in beneficiation plants. Existing instrumentation is not only expensive but also complex and challenging to maintain. In this research, we propose using edge artificial intelligence for early detection of l...
| Published in: | Sensors |
|---|---|
| Main Authors: | , , , , , , |
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/1/169 |
| _version_ | 1850398346870521856 |
|---|---|
| author | Emerson Klippel Andrea Gomes Campos Bianchi Saul Delabrida Mateus Coelho Silva Charles Tim Batista Garrocho Vinicius da Silva Moreira Ricardo Augusto Rabelo Oliveira |
| author_facet | Emerson Klippel Andrea Gomes Campos Bianchi Saul Delabrida Mateus Coelho Silva Charles Tim Batista Garrocho Vinicius da Silva Moreira Ricardo Augusto Rabelo Oliveira |
| author_sort | Emerson Klippel |
| collection | DOAJ |
| container_title | Sensors |
| description | There is a constant risk of iron ore collapsing during its transfer between processing stages in beneficiation plants. Existing instrumentation is not only expensive but also complex and challenging to maintain. In this research, we propose using edge artificial intelligence for early detection of landslide risk based on images of iron ore transported on conveyor belts. During this work, we defined the device edge and the deep neural network model. Then, we built a prototype will to collect images that will be used for training the model. This model will be compressed for use in the device edge. This same prototype will be used for field tests of the model under operational conditions. In building the prototype, a real-time clock was used to ensure the synchronization of image records with the plant’s process information, ensuring the correct classification of images by the process specialist. The results obtained in the field tests of the prototype with an accuracy of 91% and a recall of 96% indicate the feasibility of using deep learning at the edge to detect the type of iron ore and prevent its risk of avalanche. |
| format | Article |
| id | doaj-art-ec92dec8564a4f428e05b1b28ce1f193 |
| institution | Directory of Open Access Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| spelling | doaj-art-ec92dec8564a4f428e05b1b28ce1f1932025-08-19T22:51:25ZengMDPI AGSensors1424-82202021-12-0122116910.3390/s22010169Deep Learning Approach at the Edge to Detect Iron Ore TypeEmerson Klippel0Andrea Gomes Campos Bianchi1Saul Delabrida2Mateus Coelho Silva3Charles Tim Batista Garrocho4Vinicius da Silva Moreira5Ricardo Augusto Rabelo Oliveira6Graduate Program in Instrumentation, Control and Automation of Mining Processes, Instituto Tecnológico Vale, Federal University of Ouro Preto, Ouro Preto 35400-000, BrazilComputing Department, Federal University of Ouro Preto, Ouro Preto 35400-000, BrazilComputing Department, Federal University of Ouro Preto, Ouro Preto 35400-000, BrazilComputing Department, Federal University of Ouro Preto, Ouro Preto 35400-000, BrazilComputing Department, Federal University of Ouro Preto, Ouro Preto 35400-000, BrazilVALE S.A., Parauapebas, Para 68516-000, BrazilComputing Department, Federal University of Ouro Preto, Ouro Preto 35400-000, BrazilThere is a constant risk of iron ore collapsing during its transfer between processing stages in beneficiation plants. Existing instrumentation is not only expensive but also complex and challenging to maintain. In this research, we propose using edge artificial intelligence for early detection of landslide risk based on images of iron ore transported on conveyor belts. During this work, we defined the device edge and the deep neural network model. Then, we built a prototype will to collect images that will be used for training the model. This model will be compressed for use in the device edge. This same prototype will be used for field tests of the model under operational conditions. In building the prototype, a real-time clock was used to ensure the synchronization of image records with the plant’s process information, ensuring the correct classification of images by the process specialist. The results obtained in the field tests of the prototype with an accuracy of 91% and a recall of 96% indicate the feasibility of using deep learning at the edge to detect the type of iron ore and prevent its risk of avalanche.https://www.mdpi.com/1424-8220/22/1/169edge AIDNNiron ore qualityAIoT |
| spellingShingle | Emerson Klippel Andrea Gomes Campos Bianchi Saul Delabrida Mateus Coelho Silva Charles Tim Batista Garrocho Vinicius da Silva Moreira Ricardo Augusto Rabelo Oliveira Deep Learning Approach at the Edge to Detect Iron Ore Type edge AI DNN iron ore quality AIoT |
| title | Deep Learning Approach at the Edge to Detect Iron Ore Type |
| title_full | Deep Learning Approach at the Edge to Detect Iron Ore Type |
| title_fullStr | Deep Learning Approach at the Edge to Detect Iron Ore Type |
| title_full_unstemmed | Deep Learning Approach at the Edge to Detect Iron Ore Type |
| title_short | Deep Learning Approach at the Edge to Detect Iron Ore Type |
| title_sort | deep learning approach at the edge to detect iron ore type |
| topic | edge AI DNN iron ore quality AIoT |
| url | https://www.mdpi.com/1424-8220/22/1/169 |
| work_keys_str_mv | AT emersonklippel deeplearningapproachattheedgetodetectironoretype AT andreagomescamposbianchi deeplearningapproachattheedgetodetectironoretype AT sauldelabrida deeplearningapproachattheedgetodetectironoretype AT mateuscoelhosilva deeplearningapproachattheedgetodetectironoretype AT charlestimbatistagarrocho deeplearningapproachattheedgetodetectironoretype AT viniciusdasilvamoreira deeplearningapproachattheedgetodetectironoretype AT ricardoaugustorabelooliveira deeplearningapproachattheedgetodetectironoretype |