Iron ore identification method using reflectance spectrometer and a deep neural network framework

Xiao, Dong; Le, Ba Tuan; Ha, Thai Thuy Lam

doi:10.1016/j.saa.2020.119168

Cited by 23 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The R7544 plot against R6744 (Figure 3b) shows that most of the reflectance is relatively smooth in the region 670−750 nm. The black dotted circles demonstrate the similarities between the pegmatite (5) and siliceous sandstone (9) samples.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

MarSCoDe Passive Reflectance Spectroscopy Analysis for Martian Minerals

Fang,

Wang,

et al. 2024

ACS Earth Space Chem.

View full text Add to dashboard Cite

Mineral analysis is one of the most vital missions in Mars exploration. Laser-induced breakdown spectroscopy (LIBS) is suitable for in situ analysis of minerals on Mars because of its ability to substantially remove dust and analyze most major elements. However, the longevity of active LIBS technology is susceptible to the Martian atmosphere and environmental temperature. Assuming that the LIBS laser had a malfunction, reflectance spectra of surface materials could be acquired in passive mode to analyze minerals and rocks, as is done on the ChemCam and SuperCam instruments on the Mars Science Laboratory and Mars 2020 rover missions, respectively. In addition, passive reflectance can provide constraints on the mineral structure and depositional environment of the rocks encountered by the rover. In this work, we present a passive reflectance spectra method based on the MarSCoDe ground simulator using the spectrometer module of the prototype system to test its ability to acquire visible reflectance spectra. The work presents the reflectance spectra of 24 National Reference Materials from which we computed the spectral parameters of minerals and rocks. Chemometrics based on particle swarm optimizationsupport vector classification (PSO-SVC) are used to accomplish the recognition of various materials. The results show that the passive spectral method could acquire targeted visible reflectance information and identify materials effectively.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Passive spectra in the visible/near-infrared are commonly utilized in soil analysis and mineral classification. , In addition, passive spectra can be used in conjunction with other active spectral methods such as laser-induced breakdown spectroscopy (LIBS). The NASA Curiosity rover included the first LIBS payload, ChemCam.…”

Section: Introductionmentioning

confidence: 99%

MarSCoDe Passive Reflectance Spectroscopy Analysis for Martian Minerals

Fang,

Wang,

et al. 2024

ACS Earth Space Chem.

View full text Add to dashboard Cite

show abstract

“…The final model accuracy reached 89%. Xiao et al (2021) first used the visible infrared reflectance spectrometer to obtain the spectral image of the ore, and then input it into the custom dilated convolutional neural network for training, and realized the classification of five kinds of ore such as hematite and magnetite.…”

Section: Introductionmentioning

confidence: 99%

Rock image classification using deep residual neural network with transfer learning

Chen

Su²,

Chen³

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Rock image classification is a significant part of geological research. Compared with traditional image classification methods, rock image classification methods based on deep learning models have the great advantage in terms of automatic image features extraction. However, the rock classification accuracies of existing deep learning models are unsatisfied due to the weak feature extraction ability of the network model. In this study, a deep residual neural network (ResNet) model with the transfer learning method is proposed to establish the corresponding rock automatic classification model for seven kinds of rock images. ResNet34 introduces the residual structure to make it have an excellent effect in the field of image classification, which extracts high-quality rock image features and avoids information loss. The transfer learning method abstracts the deep features from the shallow features, and better express the rock texture features for classification in the case of fewer rock images. To improve the generalization of the model, a total of 3,82,536 rock images were generated for training via image slicing and data augmentation. The network parameters trained on the Texture Library dataset which contains 47 types of texture images and reflect the characteristics of rocks are used for transfer learning. This pre-trained weight is loaded when training the ResNet34 model with the rock dataset. Then the model parameters are fine-tuned to transfer the model to the rock classification problem. The experimental results show that the accuracy of the model without transfer learning reached 88.1%, while the model using transfer learning achieved an accuracy of 99.1%. Aiming at geological engineering field investigation, this paper studies the embedded deployment application of the rock classification network. The proposed rock classification network model is transplanted to an embedded platform. By designing a rock classification system, the off-line rock classification is realized, which provides a new solution for the rock classification problem in the geological survey. The deep residual neural network and transfer learning method used in this paper can automatically classify rock features without manually extracting. These methods reduce the influence of subjective factors and make the rock classification process more automatic and intelligent.

show abstract

“…However, deep learning (DL) brought new research methods to the study of strip shape. Surface defect detection [10] was also an important research direction, involving a convolutional neural network (CNN) [11][12][13][14][15][16], deep belief network (DBN) [17], visual geometry group network (VGG) [18], and the combination of DL and an extreme learning machine [19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function

Liu

Song

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

With the improvement of industrial requirements for the quality of cold rolled strips, flatness has become one of the most important indicators for measuring the quality of cold rolled strips. In this paper, the strip production data of a 1250 mm tandem cold mill in a steel plant is modeled by an improved deep neural network (the improved DNN) to improve the accuracy of strip shape prediction. Firstly, the type of activation function is analyzed, and the monotonicity of the activation function is deemed independent of the convexity of the loss function in the deep network. Regardless of whether the activation function is monotonic, the loss function is not strictly convex. Secondly, the non-convex optimization of the loss functionextended from the deep linear network to the deep nonlinear network, is discussed, and the critical point of the deep nonlinear network is identified as the global minimum point. Finally, an improved Swish activation function based on batch normalization is proposed, and its performance is evaluated on the MNIST dataset. The experimental results show that the loss of an improved Swish function is lower than that of other activation functions. The prediction accuracy of a deep neural network (DNN) with an improved Swish function is 0.38% more than that of a deep neural network (DNN) with a regular Swish function. For the DNN with the improved Swish function, the mean square error of the prediction for the flatness of cold rolled strip is reduced to 65% of the regular DNN. The accuracy of the improved DNN is up to and higher than the industrial requirements. The shape prediction of the improved DNN will assist and guide the industrial production process, reducing the scrap yield and industrial cost.

show abstract

Iron ore identification method using reflectance spectrometer and a deep neural network framework

Cited by 23 publications

References 37 publications

MarSCoDe Passive Reflectance Spectroscopy Analysis for Martian Minerals

MarSCoDe Passive Reflectance Spectroscopy Analysis for Martian Minerals

Rock image classification using deep residual neural network with transfer learning

Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function

Contact Info

Product

Resources

About