Abstract

Near infrared (NIR) spectroscopy in combination with partial least-squares regression (PLS) is widely applied in process control for non-destructive measurement of quality parameters during production. PLS assumes an approximate linear relationship between the parameter to be estimated and the intensity of its absorption bands. Spectra, however, may contain non-linearities for various reasons such as differences in viscosity, temperature, pH, particle size and chemical composition of the sample matrix. In such cases, PLS might not predict the parameter of interest sufficiently well, and one must find other methods for the calibration task. Support vector machine regression (SVR) has been gaining interest within chemometrics in recent years. SVR is capable of modelling highly non-linear data, also when data are of very high dimensions. The aim of this study was to develop calibration models of NIR spectra from four different process steps in a raw-sugar factory. The models were intended for monitoring two quality parameters at the individual process steps. Our goal was to obtain global calibration models covering all four process steps in order to obtain simple calibration maintenance. SVR was used for the calibration task, since all of the above-mentioned sources of non-linearities were present. SVR results were benchmarked against PLS. SVR had a better prediction performance than PLS (1) for models built on individual process steps, (2) for global models covering all four process steps and (3) when the global models were evaluated on the individual process steps. Moreover, the majority of SVR models had prediction errors close to reference uncertainty and hence were close to being optimal. Finally, the global SVR models predicted the individual process steps better than the corresponding local PLS models. We conclude that the nonlinear modelling method SVR was able to model non-linearities caused by pooling NIR spectra from multiple different process steps. Implementation of the global SVR models would have several advantages over the local PLS models. First, they would allow simple calibration maintenance because only one model per quality parameter would have to be maintained. Second, they would allow more precise estimation of the quality parameters and therefore better process monitoring.

© 2015 The Author(s)

Application of ultraviolet–visible spectroscopy coupled with support vector regression for the quantitative detection of thiamethoxam in tea

Delong Meng, Gu Ciyong, Lin Li, Zhimin Zhao, Weichun Zhang, and Chaoling Du
Appl. Opt. 61(21) 6186-6192 (2022)

Spectral reflectance estimation from camera responses by support vector regression and a composite model

Wei-Feng Zhang and Dao-Qing Dai
J. Opt. Soc. Am. A 25(9) 2286-2296 (2008)

Combination of near-infrared spectroscopy with Wasserstein generative adversarial networks for rapidly detecting raw material quality for formula products

Xiaowei Xin, Junhua Jia, Shunpeng Pang, Ruotong Hu, Huili Gong, Xiaoyan Gao, and Xiangqian Ding
Opt. Express 32(4) 5529-5549 (2024)

System nonlinearity correction based on a multi-output support vector regression machine

Ji Cui, Si Ao Cai, and Guoying Feng
Opt. Continuum 2(4) 877-893 (2023)

Optimization of the phase generated carrier demodulation algorithm based on support vector regression

Huyong Ma, Binai Li, Min Xue, Wenbin Zhao, Shuangjiao Wei, Zhenglan Bian, and Fenghong Chu
Appl. Opt. 60(31) 9818-9827 (2021)