Search

The real-time quantitative analysis of the calorific value of pulverized coal particle flow is important for the efficient and clean combustion of coal. Herein, a piezoelectric vibratory feeder produced a continuous flow of pulverized coal particles, which were detected by laser-induced breakdown spectroscopy (LIBS), and the corresponding spectral information was obtained. The obtained data matrices, after removing abnormal data, were subjected to normalization in a row-wise manner to improve the signal repeatability. Then, the second convolution derivative was conducted on the LIBS spectra to correct the spectral interference. To acquire appropriate number and type of variables for the PLS quantitative model, the variable selection methods of genetic algorithm (GA) and synergy interval partial least squares (siPLS) in the quantitative model were analyzed and compared. The results showed that spectral correction could be used to improve the predictive precision and accuracy of the quantitative model based on the full spectrum. The predictive accuracy of the model with variables selected by siPLS was further improved. The minimum average relative error (RE) of the predictive values for the validation samples was 1.53%, and the average error of the proposed model for the calorific value quantitative analysis was 0.22 MJ kg−1. The measurement indicated that LIBS could realize an accurate and precise real-time quantitative analysis of the pulverized coal particle flow.

The aim of this study was to analyze the carbon contents in coal samples by laser-induced breakdown spectroscopy (LIBS). The 266 nm laser radiation was utilized for laser ablation and plasma generation under atmospheric conditions. The correlated carbon atomic and molecular emission lines were determined for the variables of the multiple linear regression (MLR) model. Then, the plasma temperatures of different coal samples were compared to characterize the necessity of residue correction from the MLR model. Finally, the partial least squares regression (PLSR) and support vector regression (SVR) were proposed to correct the residue errors of the MLR model. R2, RMSECV, and RMSEP for the MLR model were 0.86%, 3.20%, and 3.41%, whereas these values for the MLR model coupled with the PLSR correction model were 0.99%, 0.13%, and 2.46%, respectively; moreover, these values for the MLR model coupled with the SVR correction model were 0.99%, 0.00039%, and 1.43%. The results showed that the combination of carbon atomic and molecular emissions with both PLSR and SVR correction could improve the measurement accuracy, and the SVR correction helped in achieving better measurement accuracy.

T91 and 12Cr1MoV are two representative heat-resistant steel widely used in industrial pressure-bearing equipment. During long-term operation, the safety and service life of the equipment will be affected by the change of metallographic structure and mechanical properties of the steel components (i.e. material aging). In this study, the spectral data of eight T91 steel specimens with different aging grades, and seven 12Cr1MoV steel specimens with different grain size grades were obtained by laser induced breakdown spectroscopy (LIBS). In order to construct steel aging estimation models, two classification models including logistic regression (LGR) and support vector machine (SVM) were used, and two representative feature selection methods including analysis of variance (ANOVA) and LGR filter were utilized to reduce the high dimensional LIBS data (12,281 initial variables) into fewer features for improving the performance of estimation models. Furthermore, a new layered interval wrapper (LIW) feature selection method was proposed for being more targeted toward LIBS data. The effects of different feature selection methods on model performance were compared and discussed. The characteristics of the variables selected by different feature selection methods were observed and analyzed. The results showed that the model performance of LGR and SVM can be improved to a certain degree by all three feature selections methods, and LIW showed a greatest improvement for classification prediction. For T91, the prediction accuracy of LGR/SVM coupled with LIW was improved to 0.92/0.94, while the prediction accuracy with full spectral input was 0.76/0.81; for 12Cr1MoV, the prediction accuracy using LIW was improved to 0.87/0.90, while the prediction accuracy with full spectral input was 0.69/0.69. This study demonstrates that LIW is a new effective feature selection method for high dimensional LIBS data.

T91 steel is a representative martensitic heat-resistant steel widely used in high temperature compression components of industrial equipment. During the service period, the operation safety and the service life of the equipment will be affected by the change of structure and mechanical properties of the steel components, which is called material aging. In order to develop a rapid in-situ aging estimation technology of high temperature compression components surface, laser-induced breakdown spectroscopy (LIBS) coupled with support vector machine (SVM) was employed in this paper. The spectral characteristics of 10 T91 steel specimens with different aging grades were analyzed. Line intensities and the line intensity ratios (ionic/atomic and alloying element/matrix element) that indicate the change of metallographic structure were used to establish SVM models, and the results using different variable sets were compared. The model was optimized by comparing different pulse number for practical effectiveness, and the robustness of the model was investigated in dealing with the inhomogeneity of steel composition. The study results show that the estimation model obtained the best performance using line intensities and line intensity ratios averaged from 31st–60th laser pulses as input variables. The estimation accuracy of validation set was greatly improved from 75.8% to 95.3%. In addition, the model showed the outstanding capacity for handling the fluctuations of spectral signals between measuring-points (spots), which indicated that the aging estimation based on a few measuring-points is feasible. The studies presented here demonstrate that the LIBS coupled with SVM is a new useful technique for the aging estimation of steel, and would be well-suited for fast safety assessment in industrial field.

Calorific value is an essential fuel parameter during the process of energy utilization. Forty-four coal samples with different calorific values were quantitatively analyzed by laser-induced breakdown spectroscopy (LIBS) in this paper. The influences of different spectral preprocessing methods such as smoothing, standard normal variate transformation (SNV), multiplicative scatter correction (MSC), mean centering (MC), and derivation by convolution (Savitzky–Golay) on the quantitative model have been analyzed and compared. The results showed that the quantitative model obtained the best comprehensive performance with the application of the 11 points smoothing combined with the second-order derivation. The correlation coefficient of calibration set, correlation coefficient of validation set, RMSECV, and RMSEP were 0.9909, 0.9972, 0.467, and 0.276 MJ/kg, respectively, which were optimized compared with the traditional partial least-squares (PLS) model by 15.9%, 37.7%, 75.1%, and 88.3%, respectively. It indic...

Heat-resistant steel is widely used in various industries, and the running state is of great importance for equipment function and safety. In this work, laser-induced breakdown spectroscopy (LIBS) is applied to evaluate the running state of steel using indicators of micro and macro properties. The hybrid model based on wavelet threshold denoising (WTD) and K-fold-support vector machine-recursive feature elimination (K-SVM-RFE) is proposed to estimate the different indictors of various service conditions of steel. Fourteen T91 specimens, including 4 industrial specimens obtained from different service conditions in the power plant boiler, were used as the analytes. Firstly, the noise signal of the LIBS spectra of each specimen was analyzed and removed with WTD. Secondly, an improved approach K-SVM-RFE was applied to select the optimal feature subset and build the classification models of aging grade and hardness grade. The influence of denoising pretreatment on model performance was compared and discussed. Finally, the assessment matrix, established using the indicators from the aging grade and hardness grade, was used to evaluate the running state of steel. The results show that the test assessment matrix obtained with the hybrid model based on WTD and K-SVM-RFE is consistent with the reference matrix on the running state of steel.