Using near-infrared process analysis to study gas–solid adsorption process as well as its data treatment based on artificial neural network and partial least squares

Cai, Chen-Bo; Yang, Hong-Wei; Wang, Bo; Tao, Yong-Yuan; Wen, Mei-Qiong; Xu, Lu

doi:10.1016/j.vibspec.2011.02.009

Cited by 15 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to ameliorate the difficulty, a chemometrics strategy composed of selecting NIR band, pretreating NIR spectra with partial least squares (PLS) and afterward constructing nonlinear calibration model based on back propagation-artificial neural network (BP-ANN) has been developed and demonstrated its validity. [20] Finally, it is worth noting that in our methodology the kinetics data and the information about interaction between adsorbate molecule and adsorbent surface are synchronous, or in other words, obtained at the same time. Therefore, it is possible to incorporate them together for understanding the adsorption process more thoroughly as well as clearly-a major purpose of the paper that is less concerned in our previous papers or other authors.…”

Section: Introductionmentioning

confidence: 99%

Investigating the Adsorption Process of Isoamyl Alcohol Vapor Onto Silica Gel with Near-infrared Process Analytical Technology

Cai

Tao

Wang

et al. 2014

Spectroscopy Letters

Self Cite

View full text Add to dashboard Cite

This paper demonstrates the application of near-infrared process analytical technology to investigate the kinetics as well as the interaction between adsorbate molecule and adsorbent surface during a gas-solid (isoamyl alcohol vapor-silica gel) adsorption process. The adsorption process took place in a differential adsorption bed, which was temperature-and mass-homogeneous, and was in-line monitored by a near-infrared spectrometer via an optical fiber probe. After pretreating near-infrared data with band selection and partial least squares, a calibration model of back propagation-artificial neural network has been constructed to quantitatively determine the amount of adsorbate onto the adsorbent surface at any time within the entire adsorption process, the prerequisite for studying adsorption kinetics. The interaction between adsorbate and adsorbent could be acquired from the near-infrared spectra of the adsorbent adsorbing the adsorbate continuously. What is perhaps more important, since the kinetics data and the information about interaction are synchronous, it is feasible to incorporate them together for understanding the adsorption process more thoroughly than any current method.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigating the Adsorption Process of Isoamyl Alcohol Vapor Onto Silica Gel with Near-infrared Process Analytical Technology

Cai

Tao

Wang

et al. 2014

Spectroscopy Letters

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, BP models have two main flaws, that is, tendency to overfitting and difficulty to determine the optimal number of the hidden-layer nodes. Recently, a lot of improved BP models based on partial least square (PLS) have been presented and applied to various fields in solving nonlinear issues from natural to man-made systems [8][9][10][11][12][13][14][15]. Medhat presented two methodologies, namely, partial mutual information and self-organizing map, integrated with a genetic algorithm and general regression neural network [12].…”

Section: Introductionmentioning

confidence: 99%

“…In [10], PLS is used to decrease the abundance of input variables; that is, PLS plays a preprocessing role in a three-layered BP network. In [11], in order to study gas-solid adsorption process, PLS serves for data compression and noise reduction before a normal threelayered BP network is performed.…”

Section: Introductionmentioning

confidence: 99%

A PLS‐Based Weighted Artificial Neural Network Approach for Alpha Radioactivity Prediction inside Contaminated Pipes

Tuo

Liu

Wang

et al. 2014

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Long-range alpha detection (LRAD) has been used to measure alpha particles emitting contamination inside decommissioned steel pipes. There exists a complex nonlinear relationship between input parameters and measuring results. The input parameters, for example, pipe diameter, pipe length, distance to radioactive source, radioactive source strength, wind speed, and flux, exhibit different contributions to the measuring results. To reflect these characteristics and estimate alpha radioactivity as exactly as possible, a hybrid partial least square back propagation (PLSBP) neural network approach is presented in this paper. In this model, each node in the input layer is weighted, which indicates that different input nodes have different contributions on the system and this finding has been little reported. The weights are determined by the PLS. After this modification, a variety of normal three-layered BP networks are developed. The comparison of computational results of the proposed approach with traditional BP model and experiments confirms its clear advantage for dealing with this complex nonlinear estimation. Thus, an integrated picture of alpha particle activity inside contaminated pipes can be obtained.

show abstract

Terahertz-dependent PM2.5 monitoring and grading in the atmosphere

Miao

Zhan

Zhang

et al. 2018

Sci. China Phys. Mech. Astron.

View full text Add to dashboard Cite

Using near-infrared process analysis to study gas–solid adsorption process as well as its data treatment based on artificial neural network and partial least squares

Cited by 15 publications

References 26 publications

Investigating the Adsorption Process of Isoamyl Alcohol Vapor Onto Silica Gel with Near-infrared Process Analytical Technology

Investigating the Adsorption Process of Isoamyl Alcohol Vapor Onto Silica Gel with Near-infrared Process Analytical Technology

A PLS‐Based Weighted Artificial Neural Network Approach for Alpha Radioactivity Prediction inside Contaminated Pipes

Terahertz-dependent PM2.5 monitoring and grading in the atmosphere

Contact Info

Product

Resources

About