When air is entrained into the engine lubricating oil system to form an oil and gas two-phase flow, it will seriously affect the normal operation of the lubrication system. Therefore, it is very important to realize the accurate and rapid measurement of the void fraction of the oil-gas two-phase flow in the engine lubricating oil system. This paper determines the void fraction in the engine lubrication system at the elbow based on the spectral matching method, Firstly, the absorption data of oil-gas two-phase flow were obtained at two flow rates and five temperature conditions, covering a gas content range of 0. 10% to 1.00% (with an interval of 0.06%). This was accomplished by utilizing near-infrared, visible, and ultraviolet spectrophotometers, followed by rigorous analysis, It was ascertained that the oil-gas two-phase flow demonstrates absorption across all three wavelengths, with the intensity of absorption being correlated to the gas content. Secondly, the data preprocessing method combined with spectral similarity measure is proposed and applied to the gas content spectral analysis of bent pipe, significantly reducing the maximum relative error of gas content prediction based on the original spectrum, Using data enhancement methods such as center and autoscaling combined with Spectral Angle Cosine methods in the near-infrared spectrum, the maximum relative error of the gas content of the new lubricating oil was reduced from 48% to 36% relative to the original spectrum, The method predicts the void fraction of gas-oil two-phase flow in three bands respectively. The experimental conditions include two flow rates and five temperatures, and the influence of the temperature and flow rate of the two-phase flow on the void fraction prediction is analyzed. At the temperature of 30.0 C and the flow rate of 5.1 m min, the gas content information in the ultraviolet band (193.5 similar to 413.8 nm) is more closely related to the spectral feature of the direction or shape difference of the spectral vector and the maximum relative error of the gas content prediction is only 6%. In the near-infrared and visible bands, the maximum relative error decreases with the increase of temperature or velocity when the flow rate or temperature is constant. There is no specific effect of temperature on the prediction of gas content in the ultraviolet band, With the increase of the two-phase flow rate, the maximum relative crror of gas content prediction tends to increase. The results show that for new lubricating oil with good light transmittance, the gas content data is collected by the ultraviolet spectrometer, and the maximum relative error of gas content prediction is minimum by using standardized pretreatment combined with spectral Angle cosine method.

The accurate and rapid measurement of the gas void fraction in the oil-gas two-phase flow of the engine lubrication system holds significant importance for ensuring the safe operation of industrial processes. The precise determination of the void fraction is particularly crucial for monitoring the operational status of the engine. In light of the limitations associated with traditional gas void fraction detection methods, a method is proposed that combines ultraviolet spectroscopy with a modeling algorithm for predicting the void fraction. Initially, within the range of 185 to 430 nm, 31 sets of absorption spectra data were collected at five different two-phase flow temperatures and three different two-phase flow velocities, encompassing 15 operational conditions. The spectra were obtained for gas void fractions ranging from 0.9% to 3%. A total of 1799 spectral wavelength variables were considered for analysis. The spectral-physicochemical value coexistence distance algorithm (SPXY) was employed to partition the spectral data set into 21 calibration and 10 test sets. Partial least squares (PLS) modeling was conducted for various gas void fraction conditions, resulting in a test set determination coefficient R-2) range of 0.63 to 0.91. To address the significant variations in prediction performance across different operating conditions, various data preprocessing methods, including centering, autoscaling, Savitzky-Golay convolution smoothing, multiplicative scatter correction (MSC), standard normal variate (SNV) transformation, detrending, and orthogonal partial least squares (OPLS) orthogonal signal correction, were applied to optimize the model. The Detrend-center-PLS model exhibited the best predictive performance, with the R-2 increasing from 0.903 2 to 0.955 7. To address the issue of excessive spectral wavelength variables, three methods, Competitive Adaptive Reweighted Sampling (CARS), Monte Carlo Uninformative Variable Elimination (MCUVE), and Genetic Algorithm (GA), were employed for band dimension reduction. The reduced spectral data were then modeled using Multiple Linear Regression (MLR), Partial Least Squares, and Least Squares Support Vector Machine (LS-SVM). The optimal predictive model was determined to be the Detrend-center-CARS-PLS model, which exhibited an improved R-2 from 0.955 7 to 0.959 8 compared to the full-wavelength model. Due to the limited improvement in optimization, the intersection of the three-dimensionality-reduction methods was taken, and the modeling was re-conducted. The R-2 increased from 0.959 8 to 0.967 1, indicating a noticeable enhancement in optimization. Considering the influence of temperature and flow rate on the predictive model, a multi-condition gas void fraction prediction model was established using the same mprocess as the single-condition model-Autoscaling was identified as the optimal preprocessing method, and the R-2 for the autoscaling-PLS model was 0.948 8. The wavelength dimensionality reduction method reduced the 1799 wavelength variables to 400 similar to 500 demonstrating a significant dimensionality reduction. For different modeling methods, the autoscaling-MCUVE-LS-SVM model was identified as the best multi-condition predictive model, achieving an R-2 of 0.992 6. Finally, by comparing the single-condition predictive model with the multi-condition predictive model, it was found that the gas void fraction prediction performance of the multi-condition model was superior, improving overall predictive accuracy. The results indicate that using spectral analysis combined with modeling algorithms for predicting gas void fraction in oil-gas two-phase flow is feasible and provides an effective monitoring method for the safe operation of engines.

针对中国试车台供气压缩机组并网主要采用人工操作的现状,提出一种基于规则的专家系统,开展了供气压缩机组的并网仿真及相关验证实验.基于某型试车台供气压缩机组的结构,构建机组中压缩机、管网、换热器以及各个不同口径蝶阀的动态仿真模型;基于蝶阀连续动作阀位信号构建蝶阀执行机构动态模型;分析历史运行数据,构建基于规则的专家系统.在MATLAB/Simulink平台上搭建试车台供气压缩机组的并网仿真模型,进行并网控制仿真,并进行实验验证.实验结果表明,压缩机入口压力平均相对误差为3.12%,压缩机出口压力平均相对误差为0.44%,压比平均相对误差为3.23%.并网过程中实际机组最大压比为3.69,最小压比为2.27,满足机组安全要求,证明该控制策略具备可靠性.

Motivated by recent research on two-phase flow void fraction measurement, this paper presents a study on void fraction measurements of a lubricant air-oil two-phase flow using a near infrared (NIR) optical-fiber spectrometer associated with partial least squares (PLS) regression models. To overcome the measurement inaccuracy due to interface scattering, this study used PLS regression models to analyse the spectrum of air-oil two-phase flow. First, an NIR optical-fiber spectrometer experimental system was developed. Second, a flow regime analysis was conducted for the bubble flow transition inside the experimental system. Finally, the PLS regression model validations, the void fraction measurement accuracies, and the uncertainties of the experimental system were evaluated and discussed, and the different PLS regression models were compared in detail. The results indicate that the NIR optical-fiber spectrometer combined with the PLS regression model can achieve void fraction measurements of lubricants in air-oil two-phase flow, with a maximum squared correlation coefficient (R (2)) of 0.981, a minimum Type A uncertainty of 0.039% and a minimum expanded uncertainty of 0.077%.

Atherosclerotic plaque with a thin fibrous cap can be ruptured by shear force. Exploiting the mechanical properties of plaques within different histological regions can help to better understand the physical mechanisms of the plaque. The association between the plaque components and viscoelasticity was studied when mapping the viscoelasticity to histological features. Eleven in-vitro carotid plaques were tested with ramp-hold relaxation nanoindentation tests. Viscoelasticity (elastic modulus E-0, fluidity alpha, and viscosity tau) was characterized by Kelvin-Voigt fractional derivative (KVFD) modeling. There is a significant difference (p < 0.001) on E-0, alpha, and tau between the collagen-rich (CR) group and the non-collagen-rich (NCR) group. In the CR group, the elastic modulus E0 was higher but the fluidity alpha and viscosity tau were lower than those of the NCR group. Receiver operating characteristic (ROC) analysis revealed that combinations of E-0 and alpha can be used as a CR indicator with an area under the curve (AUC) of 0.770. There was a negative correlation between E-0 and the percentages of myxoid degeneration (r = -0.160, p < 0.001), necrosis (r = -0.229, p < 0.001) and inflammatory cells (r = -0.130, p < 0.001), and a positive correlation between elasticity E0 and the percentage of foam cells (r = 0.121, p < 0.001). There was a positive correlation between fluidity alpha and the percentage of necrosis (r = 0.308, p < 0.001). The results confirmed the clinical evidence that the CR group with higher elasticity and lower fluidity has higher resisting ability, whereas the NCR group with lower elasticity and higher fluidity has accompanied with more myxoid degeneration, extracellular lipids and necrosis.

In order to improve the accuracy of the whole blood hemoglobin (Hb) concentration prediction model, the original whole blood transmission spectrum signals were first preprocessed by using centering, auto scaling, standard normal variate (SNV), multiplicative scatter correction (MSC), and Savitzky-Golay (SG) smoothing combined with MSC. And the best preprocessing effect was obtained with a R2 value of 0. 9441 by using SG smoothing combined with MSC. The width of the SG smoothing window was discussed, and the optimal width is 27. The baseline shift of the whole blood absorbance signals was eliminated, and the signal-to-noise ratio was improved after data preprocessing. The 190 samples were divided into a calibration set (corresponding Hb concentrations from 10. 6 to 17. 3 g.dL(-1)) of 143 samples and a validation set (corresponding Hb concentrations from 10. 3 to 17. 3 g.dL(-1)) of 47 samples. The model's applicability was ensured when two sets have a similar distribution and range of Hb concentrations. And then, the Monte Carlo uninformative variable elimination (MC-UVE) was used to select the informative wavelength, which simplified the model structure and increased the proportion of useful wavelengths. When the Monte Carlo iteration number was 1000, 191 wavelength points were selected from the 700 wavelengths of the whole blood absorbance spectrum to build the whole blood Hb concentration partial least squares (PLS) model. Finally, a comparison was performed among the model based on the original whole blood transmission spectrum, the model based on the whole blood absorbance spectrum, the SG-MSC-PLS model, the SG-MSC-MC-UVE-PLS model and an existing model. In addition to this, the number of selected wavelengths based on MC-UVE was much smaller than the total number, but the predictive effect was much better, which was beneficial to improve the calculation efficiency of the model. The results indicate that the SG-MSC-MC-UVE-PLS method effectively increases the signal-to-noise ratio of the whole blood absorption spectrum signal and simplifies the model. Besides, our procedure's prediction accuracy and calculation efficiency of the model was improved by our procedure, which has reference significance for the development of hemoglobin concentration detection technology.

In this paper, a data reconstruction method was proposed to reconstruct the missing current data of a panel string of a PV power system. Two training sets and one evaluation set from a practical PV power system were used to build and evaluate the original PLS data reconstruction model. To increase the accuracy of data reconstruction model, a subset PLS model was built and evaluated using the evaluation set. Results indicates the proposed method can increase the accuracy of data reconstruction effectively.

Cancer progression involves biomechanical changes within transformed cells and the surrounding extracellular matrix (ECM). The viscoelastic features of fluidity and elasticity that are based on a novel Kelvin–Voigt fractional derivative (KVFD) model were found capable of discriminating normal, benign and malignant breast biopsy tissues on the cellular scale. The improved specificity of KVFD model parameters derives from greater accuracy of fitting the entire approaching force-indentation measurement curve ($$R^{2}$$ > 0.99) compared with traditional elastic models ($$R^{2}$$ < 0.86). Moreover, model parameters can be interpreted in terms of histopathological features. First, statistical comparisons reveal there are significant differences (p < 0.001) in elasticity E0, fluidity $$\alpha$$, and viscosity $$\tau$$ among healthy, benign, and malignant groups. Malignant breast tissues show low-value, broad-distributions in E0 and with high fluidity $$\alpha$$ as compared with healthy and benign tissues. Second, histograms of E0 and $$\alpha$$ provide distinctive features by fitting to Gaussian mixture (GM) models. The histograms of E0 and $$\alpha$$ are best fit by two kernels GM for malignant tissues, indicating that the cells are soft but with high fluidity and the ECM is stiff but with low fluidity. However, the data suggest one-kernel GM model for benign tissue and a patched uniform distribution for healthy tissue. Third, using fluidity $$\alpha$$ as the test statistic, the area under the receiver operator characteristic curve (AUC) is 0.701 ± 0.012 (p < 0.0001) for control versus malignant and 0.706 ± 0.013 (p < 0.0001) for benign versus malignant group. Variations in tissue fluidity and elasticity offer a concise set of viscoelastic biomarkers that correlate well with histopathological features.

This paper proposed an improved linear-in-parameters based genetic programming method for the chemical kinetics system modelling. To make the search space suitable for chemical kinetics modelling a functional library with basic chemical kinetics items is built. The proposed method was then applied into several simulated nonlinear chemical kinetics procedures. Results indicated that by designing its function library, the identified model can be behavioural and phenomenological for the chemical kinetics models and the identified model can produce convincing reaction rates.

Accurate and fast determination of blood component concentration is very essential for the efficient diagnosis of patients. This paper proposes a nonlinear regression method with high-dimensional space mapping for blood component spectral quantitative analysis. Kernels are introduced to map the input data into high-dimensional space for nonlinear regression. As the most famous kernel, Gaussian kernel is usually adopted by researchers. More kernels need to be studied for each kernel describes its own high-dimensional feature space mapping which affects regression performance. In this paper, eight kernels are used to discuss the influence of different space mapping to the blood component spectral quantitative analysis. Each kernel and corresponding parameters are assessed to build the optimal regression model. The proposed method is conducted on a real blood spectral data obtained from the uric acid determination. Results verify that the prediction errors of proposed models are more precise than the ones obtained by linear models. Support vector regression (SVR) provides better performance than partial least square (PLS) when combined with kernels. The local kernels are recommended according to the blood spectral data features. SVR with inverse multiquadric kernel has the best predictive performance that can be used for blood component spectral quantitative analysis.

In this paper,a Fuzzy-PID model was established for a 600 MW supercritical lignite-fired boiler through GSE software,of which the control effect was tested and compared with conventional PID control.The research result showed that when hot flue gas extracting percent stepped from 100％ to 50％,the minimum of live steam temperature of Fuzzy-PID strategy was higher by 0.21℃ than conventional PID strategy,while the maximum of which was lower by 0.15℃,and the time of dynamic response reduced by 477 s;Under the same condition,the minimum of reheat outlet steam temperature of Fuzzy-PID strategy was higher by 0.32℃ than conventional PID strategy,while the maximum of which was lower by 0.49℃,and the time of dynamic response reduced by 387 s.It turned out that rapidity and stability of steam temperature adjustnent under Fuzzy-PID control was better than conventional PID control,proving that this Fuzzy-PID strategy could improve the quality of common-used control system.The consequence had certain significance on power plant steam temperature control system optimization.

In this study, outliers in the spectral calibration set were analyzed and categorized based on their error introducing patterns. A double outlyingness analysis (DOA) method for outlier detection and categorization was proposed as a tool to detail the error structures of outliers. Two outlyingness values were calculated based on a proposed procedure. The outlier diagnosis diagram based on the inlier model was drawn to distinguish four types of samples: type I (outlier), incorrect concentration(s) with contaminated spectral signals; type II (outlier), incorrect concentration(s) with uncontaminated spectral signals; type III (outlier), correct concentration(s) with contaminated spectral signals; type IV (inlier), correct concentration(s) with uncontaminated spectral signals. Four data sets for quantitative spectral calibrations were used to compare DOA and five existing methods. Results show that DOA is able to detect all types of outliers and provide a tool to analyze outlier structures.

Motivated by environmental protection concerns, monitoring the flue gas of thermal power plant is now often mandatory due to the need to ensure that emission levels stay within safe limits. Optical based gas sensing systems are increasingly employed for this purpose, with regression techniques used to relate gas optical absorption spectra to the concentrations of specific gas components of interest (NOx, SO2 etc.). Accurately predicting gas concentrations from absorption spectra remains a challenging problem due to the presence of nonlinearities in the relationships and the high-dimensional and correlated nature of the spectral data. This article proposes a generalized fuzzy linguistic model (GFLM) to address this challenge. The GFLM is made up of a series of “If-Then” fuzzy rules. The absorption spectra are input variables in the rule antecedent. The rule consequent is a general nonlinear polynomial function of the absorption spectra. Model parameters are estimated using least squares and gradient descent optimization algorithms. The performance of GFLM is compared with other traditional prediction models, such as partial least squares, support vector machines, multilayer perceptron neural networks and radial basis function networks, for two real flue gas spectral datasets: one from a coal-fired power plant and one from a gas-fired power plant. The experimental results show that the generalized fuzzy linguistic model has good predictive ability, and is competitive with alternative approaches, while having the added advantage of providing an interpretable model.

In this paper, we proposed a wavelength selection method based on random decision particle swarm optimization with attractor for near‐infrared (NIR) spectra quantitative analysis. The proposed method was incorporated with partial least square (PLS) to construct a prediction model. The proposed method chooses the current own optimal or the current global optimal to calculate the attractor. Then the particle updates its flight velocity by the attractor, and the particle state is updated by the random decision with the new velocity. Moreover, the root‐mean‐square error of cross‐validation is adopted as the fitness function for the proposed method. In order to demonstrate the usefulness of the proposed method, PLS with all wavelengths, uninformative variable elimination by PLS, elastic net, genetic algorithm combined with PLS, the discrete particle swarm optimization combined with PLS, the modified particle swarm optimization combined with PLS, the neighboring particle swarm optimization combined with PLS, and the proposed method are used for building the components quantitative analysis models of NIR spectral datasets, and the effectiveness of these models is compared. Two application studies are presented, which involve NIR data obtained from an experiment of meat content determination using NIR and a combustion procedure. Results verify that the proposed method has higher predictive ability for NIR spectral data and the number of selected wavelengths is less. The proposed method has faster convergence speed and could overcome the premature convergence problem. Furthermore, although improving the prediction precision may sacrifice the model complexity under a certain extent, the proposed method is overfitted slightly. Copyright © 2015 John Wiley & Sons, Ltd.

As a traditional linear regression model, the partial least squares (PLS) could not handle the nonlinearities in spectral quantitative analysis. This paper focuses on four types of nonlinear partial least square (NPLS) models: the internal NPLS model, the external NPLS model, the nonlinear components extracted NPLS model and the kernel NPLS model. The internal NPLS model adopts the neural network as the nonlinear function to describe the inner relation. For the external NPLS model, the PLS regression is performed on the extended input matrix which contains the nonlinear terms of the independent variables. The nonlinear components extracted NPLS model extracts the nonlinear principal components by selecting the weight vectors with PLS, and then the nonlinear relationship between the nonlinear principal components and the dependent variables is established. For the kernel NPLS model, the original input is transformed into a high-dimensional space by the nonlinear kernel functions and the PLS regression model is built in the new feature space. The 10-fold root–mean–squares error of cross validation is the criterion to decide the optimal parameters of these models. The performance of the different regressions is demonstrated by three real spectral datasets: the meat dataset, the flue gas dataset of gas-fired plant and the flue gas dataset of coal-fired plant. The results suggest that the internal NPLS model with the radial basis function neural network, the external NPLS model with the radial basis function neural network and the kernel NPLS model with polynomial kernel function have a higher predictive ability for spectral quantitative analysis in most cases.

This paper proposed a near-infrared (NIR) spectra quantitative analysis method for flue gas of thermal power plant based on wavelength selection. For the proposed method, the self-adaptive accelerated particle swarm optimization is presented for determining the most representative wavelengths of NIR spectral signals and is combined with partial least square for predicting the various contents of the real flue gas dataset. The proposed method chooses the current own optimal or the current global optimal as the reference state randomly and accelerated updates of the flight velocity by the reference state, then the particle state is updated based on the new velocity self-adaptively. The experimental results of a real flue gas dataset verified that the proposed method has higher predictive ability and could overcome the premature convergence. Key words: Thermal power plant, fuel gas, near-infrared spectrum, wavelength selection, self-adaptive accelerated discrete particle swarm optimization.

This paper proposes an near infrared spectroscopy quantitative analysis model based on incremental neural network with partial least squares .The proposed model adopts the typical three-layer back-propagation neural network (BPNN) ,and the absorbance of different wavelengths and the component concentration are the inputs and the outputs ,respectively .Partial least square (PLS) regression is performed on the history training samples firstly ,and the obtained history loading matrices of the in-dependent variables and the dependent variables are used for determining the initial weights of the input layer and the output lay-er ,respectively .The number of the hidden layer nodes is set as the number of the principal components of the independent varia-bles .After a set of new training samples is collected ,PLS regression is performed on the combination dataset consisting of the new samples and the history loading matrices to calculate the new loading matrices .The history loading matrices and the new loading matrices are fused to obtain the new initial weights of the input layer and the output layer of the proposed model .Then the new samples are used for training the proposed mode to realize the incremental update .The proposed model is compared with PLS ,BPNN ,the BPNN based on PLS (PLS-BPNN) and the recursive PLS (RPLS) by using the spectra data of flue gas of nat-ural gas combustion .For the concentration prediction of the carbon dioxide in the flue gas ,the root mean square error of predic-tion (RMSEP) of the proposed model are reduced by 27.27% ,58.12% ,19.24% and 14.26% than those of PLS ,BPNN ,PLS-BPNN and RPLS ,respectively .For the concentration prediction of the carbon monoxide in the flue gas ,the RMSEP of the pro-posed model are reduced by 20.65% ,24.69% ,18.54% and 19.42% than those of PLS ,BPNN ,PLS-BPNN and RPLS ,re-spectively .For the concentration prediction of the methane in the flue gas ,the RMSEP of the proposed model are reduced by 27.56% ,37.76% ,8.63% and 3.20% than those of PLS ,BPNN ,PLS-BPNN and RPLS ,respectively .Experiments results show that the proposed model could optimize the construction and the initial weights of BPNN by PLS and has higher prediction effectiveness .Moreover ,based on the information of the built model ,the proposed model uses the new samples for incremental update without accessing the history samples .Hence ,the proposed model has better robustness and generalization .

To deal with nonlinear characteristics of spectra data for the thermal power plant flue, a nonlinear partial least square (PLS) analysis method with internal model based on neural network is adopted in the paper. The latent variables of the independent variables and the dependent variables are extracted by PLS regression firstly, and then they are used as the inputs and outputs of neural network respectively to build the nonlinear internal model by train process. For spectra data of flue gases of the thermal power plant, PLS, the nonlinear PLS with the internal model of back propagation neural network (BP-NPLS), the nonlinear PLS with the internal model of radial basis function neural network (RBF-NPLS) and the nonlinear PLS with the internal model of adaptive fuzzy inference system (ANFIS-NPLS) are compared. The root mean square error of prediction (RMSEP) of sulfur dioxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 16. 96%, 16. 60% and 19. 55% than that of PLS, respectively. The RMSEP of nitric oxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 8. 60%, 8. 47% and 10. 09% than that of PLS, respectively. The RMSEP of nitrogen dioxide of BP-NPLS, RBF-NPLS and ANFIS-NPLS are reduced by 2. 11%, 3. 91% and 3. 97% than that of PLS, respectively. Experimental results show that the nonlinear PLS is more suitable for the quantitative analysis of glue gas than PLS. Moreover, by using neural network function which can realize high approximation of nonlinear characteristics, the nonlinear partial least squares method with internal model mentioned in this paper have well predictive capabilities and robustness, and could deal with the limitations of nonlinear partial least squares method with other internal model such as polynomial and spline functions themselves under a certain extent. ANFIS-NPLS has the best performance with the internal model of adaptive fuzzy inference system having ability to learn more and reduce the residuals effectively. Hence, ANFIS-NPLS is an accurate and useful quantitative thermal power plant flue gas analysis method.

Quantitative analysis of flue gas of thermal power plant is of great significance for environmental protection. This article reports the characterization of the flue gas of a coal-fired power plant by ultraviolet-visible spectroscopy and a Tagaki-Sugeno model consisting of a series of fuzzy rules. The wavelength signals are expressed by linguistic terms in the rule antecedent. The component concentration is a linear combination of the wavelength signals. Real spectral data obtained from the flue gas is adopted in the model. Prediction models for sulfur dioxide, nitric oxide, and nitrogen dioxide were built with the Tagaki-Sugeno model, back-propagation neural network, least squares support vector machine, and partial least squares. The effectiveness of the models was primarily evaluated by root-mean-squared error of prediction. The experimental results verified that the predictive capability of the Tagaki-Sugeno model was the highest.

Quantitative analysis for the flue gas of natural gas-fired generator is significant for energy conservation and emission reduction. The traditional partial least squares method may not deal with the nonlinear problems effectively. In the paper, a nonlinear partial least squares method with extended input based on radial basis function neural network (RBFNN) is used for components prediction of flue gas. For the proposed method, the original independent input matrix is the input of RBFNN and the outputs of hidden layer nodes of RBFNN are the extension term of the original independent input matrix. Then, the partial least squares regression is performed on the extended input matrix and the output matrix to establish the components prediction model of flue gas. A near-infrared spectral dataset of flue gas of natural gas combustion is used for estimating the effectiveness of the proposed method compared with PLS. The experiments results show that the root-mean-square errors of prediction values of the proposed method for methane, carbon monoxide, and carbon dioxide are, respectively, reduced by 4.74%, 21.76%, and 5.32% compared to those of PLS. Hence, the proposed method has higher predictive capabilities and better robustness.