Trend term removal is a key step in Fourier transform infrared spectroscopy(FTIR)data pre-processing.The most commonly used least squares(LS)method,although satisfying the real-time requirement,has many problems such ...Trend term removal is a key step in Fourier transform infrared spectroscopy(FTIR)data pre-processing.The most commonly used least squares(LS)method,although satisfying the real-time requirement,has many problems such as highly correlated initial values of the expression parameters,the need to pre-estimate the trend term shape,and poor fitting accuracy at low signal-to-noise ratios.In order to achieve real-time and robust trend term removal,a new trend term removal method using genetic programming(GP)in symbolic regression is constructed in this paper,and the FTIR simulation interference results and experimental measurement data for common volatile organic compounds(VOCs)gases are analyzed.The results show that the genetic programming algorithm can both reduce the initial value requirement and greatly improve the trend term accuracy by 20%-30% in three evaluation indicators,which is suitable for gas FTIR detection in complex scenarios.展开更多
A method for extracting optical parameters of plastics materials based on terahertz time domain spectroscopy is presented. The transmission-type Terahertz Time-Domain Spectroscopy(THz TDS) system is adopted to detect ...A method for extracting optical parameters of plastics materials based on terahertz time domain spectroscopy is presented. The transmission-type Terahertz Time-Domain Spectroscopy(THz TDS) system is adopted to detect the refractive index and extinction coefficient on different plastic materials. Then the corresponding spectral information is obtained by Fourier transform of the terahertz time domain waveform of the sampling points, including the corresponding amplitude and phase information of the waveform. The optical parameter extraction model is built. By using the simplex optimization method, the curves of the refractive index and extinction coefficient for the plastic material are obtained. The experimental samples are made of different plastic parallel plate materials. The experimental results show that the optimization of optical parameters can improve their extraction accuracy, and the error of refractive index is ±0.005. Extraction technology with the simplex optimization method of optical parameter based on THz TDS can help to extract the optical parameters of engineering plastics. It is of great significance for the research of terahertz nondestructive testing.展开更多
To address the problem of identifying multiple types of additives in lubricating oil,a method based on midinfrared spectral band selection using the eXtreme Gradient Boosting(XGBoost)algorithm combined with the ant co...To address the problem of identifying multiple types of additives in lubricating oil,a method based on midinfrared spectral band selection using the eXtreme Gradient Boosting(XGBoost)algorithm combined with the ant colony optimization(ACO)algorithm is proposed.The XGBoost algorithm was used to train and test three additives,T534(alkyl diphenylamine),T308(isooctyl acid thiophospholipid octadecylamine),and T306(trimethylphenol phosphate),separately,in order to screen for the optimal combination of spectral bands for each additive.The ACO algorithm was used to optimize the parameters of the XGBoost algorithm to improve the identification accuracy.During this process,the support vector machine(SVM)and hybrid bat algorithms(HBA)were included as a comparison,generating four models:ACO-XGBoost,ACO-SVM,HBA-XGboost,and HBA-SVM.The results showed that all four models could identify the three additives efficiently,with the ACO-XGBoost model achieving 100%recognition of all three additives.In addition,the generalizability of the ACO-XGBoost model was further demonstrated by predicting a lubricating oil containing the three additives prepared in our laboratory and a collected sample of commercial oil currently in use。展开更多
基金supported by JKW Program(No.M102-03)National Program(No.E0F80246).
文摘Trend term removal is a key step in Fourier transform infrared spectroscopy(FTIR)data pre-processing.The most commonly used least squares(LS)method,although satisfying the real-time requirement,has many problems such as highly correlated initial values of the expression parameters,the need to pre-estimate the trend term shape,and poor fitting accuracy at low signal-to-noise ratios.In order to achieve real-time and robust trend term removal,a new trend term removal method using genetic programming(GP)in symbolic regression is constructed in this paper,and the FTIR simulation interference results and experimental measurement data for common volatile organic compounds(VOCs)gases are analyzed.The results show that the genetic programming algorithm can both reduce the initial value requirement and greatly improve the trend term accuracy by 20%-30% in three evaluation indicators,which is suitable for gas FTIR detection in complex scenarios.
基金National defense technical basic research project,Terahertz detection technology and application research on ceramic matrix composites(JSZL2015411C002)
文摘A method for extracting optical parameters of plastics materials based on terahertz time domain spectroscopy is presented. The transmission-type Terahertz Time-Domain Spectroscopy(THz TDS) system is adopted to detect the refractive index and extinction coefficient on different plastic materials. Then the corresponding spectral information is obtained by Fourier transform of the terahertz time domain waveform of the sampling points, including the corresponding amplitude and phase information of the waveform. The optical parameter extraction model is built. By using the simplex optimization method, the curves of the refractive index and extinction coefficient for the plastic material are obtained. The experimental samples are made of different plastic parallel plate materials. The experimental results show that the optimization of optical parameters can improve their extraction accuracy, and the error of refractive index is ±0.005. Extraction technology with the simplex optimization method of optical parameter based on THz TDS can help to extract the optical parameters of engineering plastics. It is of great significance for the research of terahertz nondestructive testing.
文摘本文以76份青稞为研究对象,利用近红外光谱仪采集青稞4000~10000 cm-1波段光谱,并联合其水分、β-葡聚糖、直链淀粉、蛋白质实测含量数值,构建了基于近红外光谱技术的青稞特征营养成分含量快速检测模型。结果显示,SG卷积平滑(Savitzky Golay,SG)是水分、直链淀粉、β-葡聚糖含量的偏最小二乘法(Partial Least Squares,PLS)预测模型的最优光谱预处理方法,而SG卷积平滑+多元散射校正(Multiplicative Scatter Correction,MSC)是蛋白质含量的偏最小二乘法(PLS)预测模型的最优光谱预处理方法。为进一步提高青稞各成分含量预测模型的准确性,考察了竞争性自适应重加权法(Competitive Adaptive Reweighted Sampling,CARS)、连续投影算法(Successive Projections Algorithm,SPA)和变量组合集群分析混合迭代保留信息变量法(Variables Combination Population Analysis and Iterative Retained Information Variable,VCPA-IRIV)特征波长选择算法对模型预测结果的影响。结果表明,VCPA-IRIV处理可有效提高水分、直链淀粉、蛋白质含量预测模型的预测决定系数,降低预测均方根误差;CARS对β-葡聚糖含量预测模型优化效果显著。基于上述最优方法建立的青稞水分、β-葡聚糖、直链淀粉、蛋白质实测含量预测模型,其预测相关系数分别为0.9868、0.9808、0.9701、0.9879;预测均方根误差分别为0.2042、0.1846、0.8135、0.2095。综上,本研究建立的基于近红外光谱的青稞特征营养成分含量快速检测模型具有较高的准确性,对加工企业快速了解原料品质及高效筛选合格原料有一定指导意义。
基金the Beijing Natural Science Foundation(Grant No.2232066)the Open Project Foundation of State Key Laboratory of Solid Lubrication(Grant LSL-2212).
文摘To address the problem of identifying multiple types of additives in lubricating oil,a method based on midinfrared spectral band selection using the eXtreme Gradient Boosting(XGBoost)algorithm combined with the ant colony optimization(ACO)algorithm is proposed.The XGBoost algorithm was used to train and test three additives,T534(alkyl diphenylamine),T308(isooctyl acid thiophospholipid octadecylamine),and T306(trimethylphenol phosphate),separately,in order to screen for the optimal combination of spectral bands for each additive.The ACO algorithm was used to optimize the parameters of the XGBoost algorithm to improve the identification accuracy.During this process,the support vector machine(SVM)and hybrid bat algorithms(HBA)were included as a comparison,generating four models:ACO-XGBoost,ACO-SVM,HBA-XGboost,and HBA-SVM.The results showed that all four models could identify the three additives efficiently,with the ACO-XGBoost model achieving 100%recognition of all three additives.In addition,the generalizability of the ACO-XGBoost model was further demonstrated by predicting a lubricating oil containing the three additives prepared in our laboratory and a collected sample of commercial oil currently in use。
