Water absorption thermodynamics in single wood pellets modelled by multivariate near-infrared spectroscopy

Holzforschung ◽  
2008 ◽  
Vol 62 (4) ◽  
Author(s):  
Torbjörn A. Lestander
Keyword(s):  
Water Content ◽  
Near Infrared ◽  
Calorific Value ◽  
Least Squares Regression ◽  
Wood Pellets ◽  
Differential Heat ◽  
On Line ◽  
Explained Variation ◽  
Test Sets ◽  
Content Range

Abstract Samples of wood pellets were adjusted into six water content classes from 0% to 12%. The water content in single pellets varied between 0.1% and 14.2%. Three equations were constructed to estimate the differential heat of sorption (-ΔH) values from (1) fractal-geometry, (2) isosteric, and (3) calorimetric data. The ranges in calculated -ΔH of single pellets were (1) 133–1475, (2) 315–881, and (3) 195–1188 J g-1 water, respectively, across the studied moisture content range. Partial least squares regression was used to model near-infrared (NIR) spectra from single pellets and to predict -ΔH values and water content. The explained variation in test sets for the different models ranged from 97.1% to 99.9%. The shifts in peak absorbance for two water bands indicated that frequency in overtone vibration of O-H stretching and bending decreased, when water content was raised. Simulations of mixes between pellets of differential heat values showed that released heat was up to 0.03% of the gross calorific value of wood pellets. This heat may be a major contributor to initial temperature increases in pellet stacks during storage. The results indicate that on-line NIR based predictions of differential heat in wood pellets is possible to apply in the pellet industry.

Review: The evolution of chemometrics coupled with near infrared spectroscopy for fruit quality evaluation

2022 ◽  
pp. 096703352110572
Author(s):  
Nicholas T Anderson ◽  
Kerry B Walsh
Keyword(s):  
Near Infrared ◽  
Nir Spectroscopy ◽  
Short Wave ◽  
Least Squares Regression ◽  
Machine Learning Methods ◽  
Transmission Geometry ◽  
Modelling Techniques ◽  
Test Sets ◽  
Model Robustness

Short wave near infrared (NIR) spectroscopy operated in a partial or full transmission geometry and a point spectroscopy mode has been increasingly adopted for evaluation of quality of intact fruit, both on-tree and on-packing lines. The evolution in hardware has been paralleled by an evolution in the modelling techniques employed. This review documents the range of spectral pre-treatments and modelling techniques employed for this application. Over the last three decades, there has been a shift from use of multiple linear regression to partial least squares regression. Attention to model robustness across seasons and instruments has driven a shift to machine learning methods such as artificial neural networks and deep learning in recent years, with this shift enabled by the availability of large and diverse training and test sets.

scholarly journals Application of VIS/NIR Spectroscopy and SDAE-NN Algorithm for Predicting the Cold Storage Time of Salmon

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Ting Wu ◽  
Nan Zhong ◽  
Ling Yang
Keyword(s):  
Neural Network ◽  
Cold Storage ◽  
Storage Time ◽  
Near Infrared ◽  
High Efficiency ◽  
Back Propagation ◽  
Nir Spectroscopy ◽  
Back Propagation Neural Network ◽  
Least Squares Regression ◽  
Test Sets

The cold storage time of salmon has a significant impact on its freshness, which is an important factor for consumers to evaluate the quality of salmon. The efficient, accurate, and convenient protocol is urgent to appraise the freshness for quality checking. In this paper, the ability of visible/near-infrared (VIS/NIR) spectroscopy was evaluated to predict the cold storage time of salmon meat and skin, which were stored at low-temperature box for 0~12 days. Meanwhile, a double-layer stacked denoising autoencoder neural network (SDAE-NN) algorithm was introduced to establish the prediction model without spectral pre-preprocessing. The results showed that, compared with the common methods such as partial least squares regression (PLSR) and back propagation neural network (BP-NN), the SDAE-NN method had a better performance due to its high efficiency in decreasing noise and optimizing the initial weights. The determination coefficient of test sets (R2test) and root mean square error of test sets (RMSEP) have been calculated based on SDAE-NN, for the salmon meat (skin), the R2test can reach 0.98 (0.92), and the RMSEP can reach 0.93 (1.75), respectively. It is highlighted that the algorithm is efficient and accurate and that the salmon meat would be more suitable for predicting freshness than the salmon skin. VIS/NIR spectroscopy combined with the SDAE-NN algorithm can be widely used to predict the freshness of various agricultural products.

Qualitative Analysis of Oil Sand Slurries Using On-Line NIR Spectroscopy

1996 ◽  
Vol 50 (12) ◽  
pp. 1535-1540 ◽  
Author(s):  
Waldemar I. Friesen
Keyword(s):  
Steady State ◽  
Water Content ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Fiber Optic Probe ◽  
Oil Sand ◽  
Plant Environment ◽  
On Line ◽  
Optic Probe

The development of a reliable on-line method to monitor process streams is important for improved process control in oil sand extraction plants. The suitability of diffuse reflectance near-infrared (NIR) spectroscopy for this purpose has been tested in a pilot plant environment. Spectra of a feed slurry flowing through a pipe were measured with the use of an on-line fiber-optic probe. Data were collected throughout a nine-hour period during which ore type and slurry water content were varied. The feasibility of monitoring feed stream conditions is demonstrated by principal component analysis of the measured spectra. Clustering of these spectra according to ore type and water content enables the detection of deviations from and transitions between steady-state conditions of the process. Estimates are given of characteristic times for the process to reach a steady state after a change in condition has been initiated. The use of artificial neural networks for classifying spectra on the basis of ore type is also illustrated.

Near-infrared spectroscopy for soil water determination in small soil volumes

2004 ◽  
Vol 84 (3) ◽  
pp. 333-338 ◽  
Author(s):  
P. R. Bullock ◽  
X. Li ◽  
L. Leonardi
Keyword(s):  
Infrared Spectroscopy ◽  
Water Content ◽  
Soil Water ◽  
Soil Water Content ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Water Levels ◽  
Least Squares Regression ◽  
Volumetric Soil Water Content ◽  
Volumetric Soil Water

Critical soil water levels for soil microscale processes are difficult to determine because of variability in large soil volumes and lack of techniques for logging soil water contents in small soil volumes. This study tested nearinfrared (NIR) spectroscopy for soil water content determination. Five soil horizons with a range in soil texture, soil organic carbon, carbonates, pH and horizon depth, were tested at air-dry, field capacity and 0.1 MPa tension water content. Volumetric soil water content, determined using the standard method of oven-drying and soil bulk density, was compared to NIR absorbance in various combinations and wavelengths. The NIR spectra obtained with the probe in direct contact with the soil gave better results than when the probe was separated from the soil with a glass slide. The most reliable validation results were obtained using a multivariate partial least squares regression of the full spectrum with an r2 of 0.95 and RMSE of prediction of 6.4%. Smoothing and derivatives of the spectra did not improve the validation results. The relationships for absorbance at single wavelength segments, ratios, differences and area under the curve around the 1940 nm peak were good (r2 values near 0.85 ) but poorer than the results using the full spectra. The high correlation coefficients obtained with the wide variety of soils utilized in this study suggest that NIR absorbance is a practical method for determining volumetric soil water content for small soil volumes. Key words: Near-infrared spectroscopy, soil water, Near-infrared absorbance

Monitoring Carotenoid and Chlorophyll Pigments in Virgin Olive Oil by Visible-Near Infrared Transmittance Spectroscopy. On-Line Application

2003 ◽  
Vol 11 (3) ◽  
pp. 219-226 ◽  
Author(s):  
A. Jiménez Márquez
Keyword(s):  
Olive Oil ◽  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Virgin Olive Oil ◽  
Reference Laboratory ◽  
Least Squares Regression ◽  
Chlorophyll Pigments ◽  
Infrared Transmittance ◽  
On Line

Visible-near infrared transmittance spectroscopy was used to determine total levels of chlorophyll and carotenoid in virgin olive oil. Calibration models were developed in the laboratory using partial least squares regression. An initial smoothing followed by a first derivative treatment was the best signal correction. The validation set gave a correlation coefficient and standard error of prediction of 0.985 and 0.66 mg kg−1 for carotene totals and 0.993 and 0.96 mg kg−1 for chlorophyll totals. These partial least squares models were used to monitor on-line levels of these compounds during virgin olive oil processing in olive oil mills. The results indicate similarity between both visible-near infrared transmittance spectroscopy and reference laboratory methods.

scholarly journals Near-Infrared Spectroscopy as an Analytical Process Technology for the On-Line Quantification of Water Precipitation Processes during Danhong Injection

2015 ◽  
Vol 2015 ◽  
pp. 1-10 ◽  
Author(s):  
Xuesong Liu ◽  
Chunyan Wu ◽  
Shu Geng ◽  
Ye Jin ◽  
Lianjun Luan ◽  
...  
Keyword(s):  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Least Squares Regression ◽  
Process Technology ◽  
Danhong Injection ◽  
Fiber Optic Probes ◽  
Quantitative Monitoring ◽  
On Line ◽  
Predicted Values

This paper used near-infrared (NIR) spectroscopy for the on-line quantitative monitoring of water precipitation during Danhong injection. For these NIR measurements, two fiber optic probes designed to transmit NIR radiation through a 2 mm flow cell were used to collect spectra in real-time. Partial least squares regression (PLSR) was developed as the preferred chemometrics quantitative analysis of the critical intermediate qualities: the danshensu (DSS, (R)-3, 4-dihydroxyphenyllactic acid), protocatechuic aldehyde (PA), rosmarinic acid (RA), and salvianolic acid B (SAB) concentrations. Optimized PLSR models were successfully built and used for on-line detecting of the concentrations of DSS, PA, RA, and SAB of water precipitation during Danhong injection. Besides, the information of DSS, PA, RA, and SAB concentrations would be instantly fed back to site technical personnel for control and adjustment timely. The verification experiments determined that the predicted values agreed with the actual homologic value.

scholarly journals Low-cost, handheld near-infrared spectroscopy for root dry matter content prediction in cassava

2021 ◽  
Author(s):  
Jenna Hershberger ◽  
Edwige Gaby Nkouaya Mbanjo ◽  
Prasad Peteti ◽  
Andrew Smith Ikpan ◽  
Kayode Ogunpaimo ◽  
...  
Keyword(s):  
Dry Matter ◽  
Near Infrared ◽  
Low Cost ◽  
Model Performance ◽  
Matter Content ◽  
Dry Matter Content ◽  
Least Squares Regression ◽  
Breeding Programs ◽  
Test Sets ◽  
Root Dry Matter Content

Over 800 million people across the tropics rely on cassava as a major source of calories. While the root dry matter content (RDMC) of this starchy root crop is important for both producers and consumers, characterization of RDMC by traditional methods is time-consuming and laborious for breeding programs. Alternate phenotyping methods have been proposed but lack the accuracy, cost, or speed ultimately needed for cassava breeding programs. For this reason, we investigated the use of a low-cost, handheld NIR spectrometer for field-based RDMC prediction in cassava. Oven-dried measurements of RDMC were paired with 21,044 scans of roots of 376 diverse clones from 10 field trials in Nigeria and grouped into training and test sets based on cross-validation schemes relevant to plant breeding programs. Mean partial least squares regression model performance ranged from R2p = 0.62 - 0.89 for within-trial predictions, which is within the range achieved with laboratory-grade spectrometers in previous studies. Relative to other factors, model performance was highly impacted by the inclusion of samples from the same environment in both the training and test sets. Random forest variable importance analysis of root spectra revealed increased importance in a region previously identified as predictive of water content in plants (~950 - 990 nm). With appropriate model calibration, the tested spectrometer will allow for field-based collection of spectral data with a smartphone for accurate RDMC prediction and potentially other quality traits, a step that could be easily integrated into existing harvesting workflows of cassava breeding programs.

scholarly journals A New Two Dimensional Germinative Classification of Malting Barley Quality Based on Separate Estimates of Vigour and Viability

2011 ◽  
Vol 40 (No. 3) ◽  
pp. 102-108
Author(s):  
B. Møller ◽  
L. Munck
Keyword(s):  
Near Infrared ◽  
Two Dimensional ◽  
Least Squares Regression ◽  
Infrared Transmission ◽  
Beta Glucan ◽  
Fully Integrated ◽  
Integration Pattern ◽  
Dimensional Classification ◽  
On Line

It is surprising that not even today do germination data seem fully integrated with malting data in barley quality evaluation. In order to implement such an integration, pattern recognition multivariate data analysis (chemometrics) is essential. Inspired by the results from chemometric analyses of whole germination curves we tested a two-dimensional classification plot of barley samples based on separate estimates for “vigour” (g%1) germination energy (GE) as abscissa with limits at 70% and 30% and “viability” (g%3) as ordinate with limits at 98% and 92%. The seven barley classes obtained visualise the quality differences in a consistent and instructive way clearly differencing and ordering malting barleys with falling extract% and increasing wort β-glucan (mg/l) according to a subsequent validation analysis. “Vigour” g%1 could surprisingly be predicted by Partial Least Squares Regression (PLSR) correlation by Near Infrared Transmission (NIT) and by a separate set of ten physical-chemical analyses. Samples with “viability” g%3 lower than 92% were outliers. It was concluded that germination speed is connected with the structure of the seed, which regulates the availability of substrate for germ growth near connected to the speed of malt modification. It is suggested that a NIT PLSR prediction model for “vigour” can be used directly “on-line” for quality control in the grain industry and by plant breeders. A fast germinative classification plot can be established with NIT spectroscopy for “vigour” and the Tetrazolium germ-staining test for “viability” within two hours.    

Laboratory customized online measurements for the prediction of the key-parameters of biomass quality control

2019 ◽  
Vol 27 (1) ◽  
pp. 15-25 ◽  
Author(s):  
M Mancini ◽  
D Duca ◽  
G Toscano
Keyword(s):  
Near Infrared ◽  
Nir Spectroscopy ◽  
Calorific Value ◽  
Ash Content ◽  
Laboratory Analysis ◽  
Physical Parameters ◽  
Electromagnetic Spectrum ◽  
Least Squares Regression ◽  
Gross Calorific Value ◽  
Technical Problems

The European target of ensuring reliable and sustainable energy has led to the increase in biofuel demand. This growth makes necessary the check of the product quality in order to prevent environmental and technical problems during combustion. Technical standard EN ISO 17225 divided the different biofuels into quality classes on the basis of their chemico-physical characteristics and the origin and source. In addition, they define the laboratory methodologies to be performed. These conventional analyses can determine these quality parameters but they are lengthy and expensive compared to the real need of the market. In this study, Vis-NIR spectroscopy coupled with partial least squares regression was used to predict the most important chemical-physical parameters of woodchip and pellet samples as a possible alternative to the conventional laboratory analysis. The results showed the possibility to use spectroscopy to obtain information about biofuel quality. In detail, moisture content and net calorific value of woodchip samples were predicted with RMSEP of 3.78% (r2(pred) = 0.97) and RMSECV of 0.37 MJ/kg (r2(CV) = 0.92), respectively. Ash content and gross calorific value of pellet samples were predicted with RMSECV of 0.44% (r2(CV) = 0.81) and 0.20 MJ/kg (r2(CV) = 0.78), respectively, while ash content and gross calorific value on ground pellet samples were predicted with RMSECV of 0.47% (r2(CV) = 0.78) and 0.19 MJ/kg (r2(CV) = 0.80), respectively. The best results were obtained considering only the near infrared region of the electromagnetic spectrum, suggesting that the visible part is not influential for the prediction of the parameters of this study. Having such a rapid and economic tool will be fundamental for the biofuel processors in order to check different quality characteristics of the products directly in real time without the time delay of the laboratory analysis and complications of sampling representation.

Sign in / Sign up

Export Citation Format

Share Document