Deep metric learning framework combined with Gramian angular difference field image generation for Raman spectra classification based on a handheld Raman spectrometer.

Rapid identification of unknown material samples using portable or handheld Raman spectroscopy detection equipment is becoming a common analytical tool. However, the design and implementation of a set of Raman spectroscopy-based devices for substance identification must include spectral sampling of standard reference substance samples, resolution matching between different devices, and the training process of the corresponding classification models. The process of selecting a suitable classification model is frequently time-consuming, and when the number of classes of substances to be recognised increases dramatically, recognition accuracy decreases dramatically. In this paper, we propose a fast classification method for Raman spectra based on deep metric learning networks combined with the Gramian angular difference field (GADF) image generation approach. First, we uniformly convert Raman spectra acquired at different resolutions into GADF images of the same resolution, addressing spectral dimension disparities induced by resolution differences in different Raman spectroscopy detection devices. Second, a network capable of implementing nonlinear distance measurements between GADF images of different classes of substances is designed based on a deep metric learning approach. The Raman spectra of 450 different mineral classes obtained from the RRUFF database were converted into GADF images and used to train this deep metric learning network. Finally, the trained network can be installed on an embedded computing platform and used in conjunction with portable or handheld Raman spectroscopic detection sensors to perform material identification tasks at various scales. A series of experiments demonstrate that our trained deep metric learning network outperforms existing mainstream machine learning models on classification tasks of different sizes. For the two tasks of Raman spectral classification of natural minerals of 260 classes and Raman spectral classification of pathogenic bacteria of 8 classes with significant noise, our suggested model achieved 98.05% and 90.13% classification accuracy, respectively. Finally, we also deployed the model in a handheld Raman spectrometer and conducted identification experiments on 350 samples of chemical substances attributed to 32 classes, achieving a classification accuracy of 99.14%. These results demonstrate that our method can greatly improve the efficiency of developing Raman spectroscopy-based substance detection devices and can be widely used in tasks of unknown substance identification.

Online detection of concentrate grade in the antimony flotation process based on in situ Raman spectroscopy combined with a CNN-GRU hybrid model.

Froth flotation is the most critical process for separating stibnite from raw ore. Concentrate grade is a vital production indicator in the antimony flotation process. It is a direct reflection of the product quality of the flotation process and an essential basis for the dynamic adjustment of its operating parameters. Existing methods of measuring concentrate grades suffer from expensive measurement equipment, difficult maintenance of complex sampling systems, and extended testing times. This paper presents a nondestructive and fast methodology to quantify the concentrate grade in the antimony flotation process based on in situ Raman spectroscopy. A particular Raman spectroscopic measuring system is designed for on-line measurement of the Raman spectra of the mixed minerals from the froth layer during the antimony flotation process. To obtain representative Raman spectra that better characterize the concentrate grades, a traditional Raman spectroscopic system has been redesigned to account for the different interferences during actual flotation field acquisition. A one-dimensional convolutional neural network (1D-CNN) is combined with a gated recurrent unit (GRU) and applied to construct a model for online prediction of concentrate grades based on continuously collected Raman spectra of mixed minerals in the froth layer. With an average prediction error of 4.37% and a maximum prediction deviation of 10.56%, the quantitative analysis of concentrate grade by the model demonstrates that our method is distinguished by high accuracy, low deviation, and in situ analysis, and it essentially satisfies the requirements for online quantitative determination of concentrate grade in the antimony flotation site.

On-line multi-gas component measurement in the mud logging process based on Raman spectroscopy combined with a CNN-LSTM-AM hybrid model.

The qualitative and quantitative analysis of gas components extracted from drilling fluids during mud logging is essential for identifying drilling anomalies, reservoir characteristics, and hydrocarbon properties during oilfield recovery. Gas chromatography (GC) and gas mass spectrometers (GMS) are currently used for the online analysis of gases throughout the mud logging process. Nevertheless, these methods have limitations, including expensive equipment, high maintenance costs, and lengthy detection periods. Raman spectroscopy can be applied to the online quantification of gases at mud logging sites due to its in-situ analysis, high resolution, and rapid detection. However, laser power fluctuations, field vibrations, and the overlapping of characteristic peaks of different gases in the existing online detection system of Raman spectroscopy can affect the quantitative accuracy of the model. For these reasons, a gas Raman spectroscopy system with a high reliability, low detection limits, and increased sensitivity has been designed and applied to the online quantification of gases in the mud logging process. The near-concentric cavity structure is used to improve the signal acquisition module in the gas Raman spectroscopic system, thus enhancing the Raman spectral signal of the gases. One-dimensional convolutional neural networks (1D-CNN) combined with long- and short-term memory networks (LSTM) are applied to construct quantitative models based on the continuous acquisition of Raman spectra of gas mixtures. In addition, the attention mechanism is used to futher improve the quantitative model performance. The results indicated that our proposed method has the capability to continuously on-line detect 10 hydrocarbon and non-hydrocarbon gases in the mud logging process. The limitation of detection (LOD) for different gas components based on the proposed method are in the range of 0.0035%-0.0223%. Based on the proposed CNN-LSTM-AM model, the average detection errors of different gas components range from 0.899% to 3.521%, and their maximum detection errors range from 2.532% to 11.922%. These results demonstrate that our proposed method has a high accuracy, low deviation, and good stability and can be applied to the on-line gas analysis process in the mud logging field.

Rapid identification of ore minerals using multi-scale dilated convolutional attention network associated with portable Raman spectroscopy.

Electron portable Raman spectroscopy tools for ore mineral identification are widely used in raw ore analysis and mineral process engineering. This paper demonstrates an extremely fast and accurate method for identifying unknown ore mineral samples by portable Raman spectroscopy from the RRUFF database. Resampling and background subtraction procedures are used to eliminate the influence of the Raman spectrometer and fluorescence scattering. For the complex mineral spectral classification task, a multi-scale dilated convolutional attention network is designed. In addition, to investigate the identification performance of our method, several machine learning and two basic deep learning models, including k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), cosine similarity, extreme gradient boosting machine (XGBoost), Alexnet and ResNet 18, are also developed on the mineral spectra database and applied for mineral identification. Comparative studies show that our CNN network outperforms other models with state-of-the-art results, achieving a top-1 accuracy of 89.51% and a top-3 accuracy of 96.54%. The function of each module and the explanations of the feature extraction in our CNN network were analyzed by ablation experiments and the Grad-CAM algorithm. The identification of ore mineral samples also proves the outstanding performance of our method. In conclusion, the proposed novel approach that exploits the advantages of portable Raman spectroscopy and a deep learning method is promising for rapidly identifying ore mineral samples.

Baseline correction method based on doubly reweighted penalized least squares.

The spectrum acquired on the optical instrument usually contains the pure spectrum and undesirable components such as baseline and random noise. However, the intensity of the baseline, which seriously submerges the spectrum, is the primary limitation of spectral applications. Thus, baseline correction has become one of the most significant challenges for spectral applications. In this paper, we propose a doubly reweighted penalized least squares method to estimate the baseline. This method utilizes the first-order derivative of the original spectrum and established spectrum as a constraint of similarity. Meanwhile, the doubly reweighted strategy achieves a better effort. Considering the drawbacks of the weighting rules for the adaptive iteratively reweighted penalized least squares method, we adapt a boosted weighting rule based on the softsign function, which performs well when the spectrum contains high noise. The simulated results confirm that the proposed method yields better outcomes. The proposed method can be applied to Raman and near-infrared spectra as well, and the result shows that it can estimate various kinds of baselines effectively.

[Fast Classification of Complex Sulphide Ore Based on Raman Spectroscopy].

The regional features, metallogenitic regularities and mineral composition of the hydrothermal sulphide ore have been preliminarily studied. According to the different mineralization period, the patterns of valuable minerals disseminated in ore are complicated, which causes the large changes in the properties of the sulphide ore. The different properties of the sulphide ore may increase the difficulty of the mineral processing and reduce the recovery rate of valuable minerals. Therefore a simple method for rapidly classification of sulphide ore is required to optimize mineral processing flowsheet. Laser Raman spectrometry, as an effective method to analyze the structure of the material is used to identify the component and structure of minerals. The research on the Laser Raman spectra of the large number of sulphide ore samples can reveal the reasons for the difference of the Raman spectra. A new method for classifying the complex sulphide ore using Raman spectroscopy is proposed. The experiment results demonstrate that the properties of the sulphide ore in different mineralization period vary greatly and the fluorescent scattering is mainly produced by gangue minerals. The measured Raman spectral after quenching the fluorescence scattering show the peaks of Raman spectra at 201.62, 242.54, 288.38 and 309.77 cm-1 can be used to identify this kind of complex sulphide ore. The raw ore can be divided into three categories based on the difference of the intensity of fluorescence scattering and the ratio of fluorescence and Raman intensity. The accuracy of the classification method is further validated by the industrial tests. The findings demonstrate the close relationship between Raman spectra and the properties of sulphide ore. The proposed method, which can fast classify the sulphide ore, don't need complex chemical pretreatment before spectra collection. Therefore, this method will have important application value for improving the efficiency of mineral processing.