Leaf transmittance measurements can improve predictions of the nitrogen status for winter wheat crop

Dynamic crop models can be used to predict the occurrence of nitrogen deficiency during crop growth and optimize nitrogen fertilisation. However, prediction errors can be large and may lead to wrong recommendations. The objective of our work is to study the value of correcting the dynamic model Azodyn using transmittance measurements made with the N-Tester^® (Yara) to predict the nitrogen status of a winter wheat crop. Our approach is to use a Bayesian method called the “interacting particle filter” to fit the model's state variables to measurements obtained over the course of the season. This approach was assessed on 44 experimental plots. Predictions of crop biomass, nitrogen uptake and nitrogen nutrition index were first performed for each plot by using the model without any correction. A second series of predictions was then performed for the same variables by correcting the model with N-Tester measurements at GS 7 on Feekes’ scale. The results showed that the second series of predictions were more accurate. Depending on the prediction dates, model corrections reduced the root mean squared error by 18.1–53.2% for nitrogen nutrition index, by 9.1–10.1% for biomass, and by 17.1–45.0% for nitrogen uptake. The predictions were improved up to 52 days after the measurement but the degree of improvement was higher when the prediction date was close to the measurement date. The results also showed that, when corrected, model predictions were very sensitive to values of N-Tester measurements. It is therefore necessary to use N-Tester measurements which are as precise as possible.     

Seasonal dynamics of Microcystis spp. and their toxigenicity as assessed by qPCR in a temperate reservoir

Blooms of toxic cyanobacteria are becoming increasingly frequent, mainly due to water quality degradation. This work applied qPCR as a tool for early warning of microcystin(MC)-producer cyanobacteria and risk assessment of water supplies. Specific marker genes for cyanobacteria, Microcystis and MC-producing Microcystis, were quantified to determine the genotypic composition of the natural Microcystis population. Correlations between limnological parameters, pH, water temperature, dissolved oxygen and conductivity and MC concentrations as well as Microcystis abundance were assessed. A negative significant correlation was observed between toxic (with mcy genes) to non-toxic (without mcy genes) genotypes ratio and the overall Microcystis density. The highest proportions of toxic Microcystis genotypes were found 4-6 weeks before and 8-10 weeks after the peak of the bloom, with the lowest being observed at its peak. These results suggest positive selection of non-toxic genotypes under favorable environmental growth conditions. Significant positive correlations could be found between quantity of toxic genotypes and MC concentration, suggesting that the method applied can be useful to predict potential MC toxicity risk. No significant correlation was found between the limnological parameters measured and MC concentrations or toxic genotypes proportions indicating that other abiotic and biotic factors should be governing MC production and toxic genotypes dynamics. The qPCR method here applied is useful to rapidly estimate the potential toxicity of environmental samples and so, it may contribute to the more efficient management of water use in eutrophic systems.     

The mechanism and/or prediction of the breaking elongation of polyester/viscose blended open-end rotor spun yarns

In this study, an analysis on the breaking elongation mechanism of the polyester/viscose blended open-end rotor spun yarns has been carried out. In addition, a back propagation multi layer perceptron (MLP) network and a mixture process crossed regression model with two mixture components (polyester and viscose blend ratios) and two process variables (yarn count and rotor speed) are developed to predict the breaking elongation of polyester/viscose blended open-end rotor spun yarns. Seven different blend ratios of polyester/viscose slivers are produced and these slivers are manufactured with four different rotor speed and four different yarn counts in rotor spinning machine. In conclusion, ANN and statistical model both have given satisfactory predictions; however, the predictions of ANN gave relatively more reliable results than those of statistical models. Since the prediction capacity of statistical models is also obtained as satisfactory, it can also be used for breaking elongation (%) prediction of yarns because of its simplicity and non-complex structure. In addition, it is also found in this study that yarn count, rotor speed and breaking elongation of polyester-viscose fibers and the blend ratios of these fibers in the yarn have major effects on yarn breaking elongation.     

Modelling of ring yarn unevenness by soft computing approach

This paper demonstrates the application of two soft computing approaches namely artificial neural network (ANN) and neural-fuzzy system to forecast the unevenness of ring spun yarns. The cotton fiber properties measured by advanced fiber information system (AFIS) and yarn count have been used as inputs. The prediction accuracy of the ANN and neural-fuzzy models was compared with that of linear regression model. It was found that the prediction performance was very good for all the three models although ANN and neural-fuzzy models seem to have some edge over the linear regression model. The linguistic rules developed by the neural-fuzzy system unearth the role of input variables on the yarn unevenness.     

Comparison of regression and adaptive neuro-fuzzy models for predicting the compressed air consumption in air-jet weaving

The aim of this study was to compare the response surface regression and adaptive neuro-fuzzy models for predicting the compressed air consumption in air jet weaving. The prediction models are based on the experimental data of 100 samples comprising weft yarn count, fabric width, loom speed and reed count as input variables and compressed air consumption as output/response variable. The models quantitatively characterize the linear and quadratic relationships as well as interactions between the input and output variables exhibiting very good prediction ability and accuracy, with ANFIS model being slightly better in performance than the regression model. The models could be used for estimating the compressed air consumption, identifying air leakages and production planning in a weaving mill.     

Prediction system of open-end rotor spinning process based on LM-neural network for bamboo charcoal fibers

In line with the environmental protection trends of the 21st century, bamboo charcoal fiber is invented to meet the requirements of the fields of science and technology. Its special functionalities, namely, antistatic, moisture adsorptive, perspiring, antibacterial, deodorizing, anti-radiation, and far infrared properties make it extremely suitable for applications in medicine, sports, and recreational fields, as well as an important breakthrough for environmentally-friendly textile materials. To achieve rapid manufacturing, this study processes bamboo charcoal fibers by open-end (OE) rotor spinning. The Taguchi orthogonal array is applied to the design of this experiment, and the significant factors of fibers quality are obtained through ANOVA in order to facilitate the follow-up processes of quality control. The process prediction system is built based on the test data, and is combined with the back-propagation neural network and the Levenberg-Marquardt (LM) algorithm in order to establish an OE rotor spinning process prediction system. The rotor speed, feed speed, and winding speed are set as the network input parameters, while the yarn strength, the hairiness, the unevenness, and the imperfections indicator (I.P.I.) are the output parameters. Through network learning and training, this system reports a prediction error below 5 %, proving that this prediction system has excellent predictability.     

Predicting bending rigidity of woven fabrics by neuro-genetic hybrid modeling

The possibility of prediction of bending rigidity of cotton woven fabrics with the application of Neuro-genetic model has been explored. For this purpose, number of cotton grey fabrics meant for apparel end-use was desized, scoured, and relaxed. The fabrics were then conditioned and tested for bending properties. A feed-forward neural network model was first formed and trained with adaptive learning rate back-propagation with momentum. In the second model, a hybrid learning strategy was adopted. A genetic algorithm was first used as a learning algorithm to optimize the number of neurons and connection weights of the neural network. Later, a back-propagation was applied as a local search algorithm to achieve global optima. Results of hybrid neural network model were compared with that of back-propagation neural network model in terms of their prediction performance. Results show that the prediction by Neuro-genetic model is better in comparison with that of back-propagation neural model.     

A comparative study on the estimation of evapotranspiration using backpropagation neural network: Penman�CMonteith method versus pan evaporation method

The study compares the prediction performances of evapotranspiration by the FAO56 Penman–Monteith method and the pan evaporation method using the artificial neural network. A backpropagation neural network was adopted to determine the relationship between meteorological factors and evapotranspiration or evaporation. The evapotranspiration in the ChiaNan irrigated area of Tainan was considered. Weather data compiled by Irrigation Experiment Station of ChiaNan Irrigation Association were the input layer variables, including (1) the highest temperature, (2) the lowest temperature, (3) the average temperature, (4) the relative humidity, (5) the wind speed, (6) hours of sunlight, (7) amount of solar radiation, (8) the dew point, (9) morning ground temperature and (10) afternoon ground temperature. The importance of the ten weather factors was ranked by the general influence (GI) factor. Results show that the correlation coefficient between the evapotranspiration in 2004 calculated by FAO56 Penman–Monteith method and the one predicted by the neural network model with a hidden layer of ten nodes is 0.993. The actual evapotranspiration is 911.6 cm, and value prediction by the neural network is 896.4 cm, between which two values the error is 1.67%. The results reveal that the backpropagation neural network based on the FAO56 Penman–Monteith method can accurately predict evapotranspiration. However, the correlation coefficient between the actual evaporation in 2004 and the value prediction by the neural network with a hidden layer of ten nodes and an output layer with the pan evaporation as its target output is 0.708. The pan evaporation is 1,673.1 cm, while the value predicted by the backpropagation neural network is 1,451.7 cm, between which values the error is 13.23%. The backpropagation neural networks with pan evaporation as target outputs predict the evaporation with large errors. Moreover, the use of four agricultural weather factors (determined by the GI) including wind speed, average temperature, dew point and maximum temperature as input variables, and a hidden layer of three nodes in the backpropagation neural network model can successfully predict evapotranspiration based on the FAO56 Penman–Monteith method (R = 0.98, error = 1.35%).     

Analysis and construction of a quality prediction system for needle-punched non-woven fabrics

In this study, polyester and polypropylene staple fibers were selected as the raw material, and then processed through roller-carder, cross-lapper and needle-punching machine to produce needle-punched non-woven fabrics. First, the experiment was planned using the Taguchi method to select processing parameters that affect the quality of the needle-punched non-woven fabric to act as the control factors for this experiment. The quality characteristics were the longitudinal and transverse tensile strength of the non-woven fabric as well as longitudinal and transverse tear strength. The L₁₈ (2¹×3⁷) orthogonal array was selected for the experiment as it offered an improvement on the traditional method that wastes a lot of time, effort and cost. By using the analysis of variance (ANOVA) technique at the same time, the effect of significant factors on the production process of needle-punched non-woven fabrics could be determined. Finally, the processing parameters were set as the input parameters of a back-propagation neural network (BPNN). The BPNN consists of an input layer, a hidden layer and an output layer where the longitudinal/transverse tensile and tear strength of the non-woven fabric were set as the output parameters. This was used to construct a quality prediction system for needle-punched non-woven fabrics. The experimental results indicated that the prediction system implemented in this study provided accurate predictions.     

基于无人机多光谱遥感的冬小麦叶片含水量反演

为了快速监测小麦叶片水分含量,以敏感波段组和植被指数组2种变量分别作为输入变量,以地面同步观测的冬小麦叶片含水量作为输出变量,分别采用偏最小二乘(partial least squares, PLS)、极限学习机(extreme learning machine, ELM)和粒子群算法(particle swarm optimization, PSO)优化极限学习机,建立冬小麦叶片含水量预测模型,并对其反演效果进行比较。结果表明,光谱反射率和植被指数与叶片含水量之间存在较为密切的相关性,依此确定的敏感光谱波段为红光、蓝光和近红外波段,敏感植被指数为绿度指数、过红指数、归一化绿红差值指数、三角形植被指数和过绿指数。从2种变量的建模效果看,基于植被指数组构建的模型的精度和稳定性均优于敏感波段组,其中基于植被指数组的PSO-ELM模型在6个叶片水分含量反演模型中表现最佳,其r²和RMSE分别为0.98和0.26%。利用最优模型反演得到研究区冬小麦叶片含水量的分布范围为45%～75%,平均为64.57%,反演结果与地面实测较相符,说明基于无人机光谱数据通过建立以植被指数为...     

Evaluation of effective electrospinning parameters controlling gelatin nanofibers diameter via modelling artificial neural networks

The aim of this work was to evaluate the effective parameters for prediction of the electrospun gelatin nanofibers diameter using artificial neural network (ANN) technique. The various sets of electrospinning process including temperature, applied voltage and polymer and solvent concentrations were designed to produce pure gelatin nanofibers. The obtained results by analyzing Scanning Electron Microscopy (SEM) images indicated that the produced nanofibers diameter was in the range of 85 to 750 nm. Due to the volume of the data, k fold cross-validation method was used for data setting. Data were divided into the five categories and trained and tested using ANN technique. The results indicated that the network including 4 input variables, 3 hidden layers with 10, 18 and 9 nodes in each layers, respectively, and one output layer had the best performance in the testing sets. The mean squared error (MSE) and linear regression (R) between observed and predicted nanofibers diameter were 0.1531 and 0.9424, respectively. The obtained results demonstrated that the selected neural network model had acceptable performance for evaluating involved parameters and prediction of nanofibers diameter.     

Performance of neural network algorithms during the prediction of yarn breaking elongation

Yarn breaking elongation is one of the most important yarn quality characteristics, since it affects the manufacture and usability of woven and knitted fabrics. One of the methods used to predict the breaking elongation of ring spun yarn is artificial neural network (NN). The design of an NN involves the choice of several parameters which include the network architecture, number of hidden layers, number of neurons in the hidden layers, training, learning and transfer functions. This paper endeavors to study the performance of NN as the design factors are varied during the prediction of cotton ring spun yarn breaking elongation. A study of the relative importance of the input parameters was also undertaken. The results indicated that there is a significant difference in the types of transfer and training functions used. Of the two transfer functions used, purelin performed far much better than logsig function. Among the five training functions, the best training functions in terms of performance was Levenberg-Marquardt. The study of the relative importance of input factors revealed that yarn twist, yarn count, fiber elongation, length, length uniformity and spindle speed, were the six most influential factors.     

Artificial neural network approach for predicting colour properties of laser-treated denim fabrics

In this study, artificial neural network (ANN) and linear regression (LR) approaches are proposed for predicting colour properties of laser-treated denim fabrics. Denim fabrics were treated under different combinations of laser processing parameters, including pixel time (μs), resolution (dot per inch) and grayscale (lightness percentage) as inputs. Colour properties, including colour yield (K/S sum value), CIE L*, a* and b* values and yellowness index were predicted as outputs in these approaches. Later, the prediction performances of two approaches were compared and the statistical findings revealed that ANN approach was able to provide more accurate prediction than LR approach, especially for L value. Moreover, among the three input variables, grayscale (lightness percentage) was found to be the most important factor affecting colour properties of laser-treated denim fabrics.     

Comparison of regression and adaptive neuro-fuzzy models for predicting the bursting strength of plain knitted fabrics

The aim of this study was to compare the response surface regression and adaptive neuro-fuzzy models for predicting the bursting strength of plain knitted fabrics. The prediction models are based on the experimental data comprising yarn tenacity, knitting stitch length and fabric GSM as input variables and fabric bursting strength as output/response variable. The models quantitatively characterize the non-linear relationship and interactions between the input and output variables exhibiting very good prediction ability and accuracy, with ANFIS model being slightly better in performance than the regression model.     

苎麻纤维性能与成纱质量的人工神经网络分析

本文分别采用三种方法-BP神经网络、灰色关联分析结合BP神经网络、主成分结合BP神经网络根据苎麻纤维的性能建立了成纱性能的预测模型。采用灰色关联分析和主成分分析可以减少BP神经网络的输入节点数,提高预测结果的精度和稳定性。与单纯的BP神经网络的预测结果相比,灰色分析结合BP神经网络和主成分分析结合BP神经网络的预测结果更准确,在对成纱性能进行预测时,预测值与实测值之间的平均相对误差均明显下降。     

Predicting the air permeability of polyester/cotton blended woven fabrics

The aim of this study was to model the air permeability of polyester cotton blended woven fabrics. Fabrics of varying construction parameters i.e. yarn linear densities and thread densities were selected and tested for air permeability, fabric areal density and fabric thickness. A total of 135 different fabric constructions were tested among which 117 were allocated for development of prediction model while the remaining were utilized for its validation. Four variables were selected as input parameters on basis of statistical analysis i.e. warp yarn linear density, weft yarn linear density, ends per 25 mm and picks per 25 mm. Response surface regression was applied on the collected data set in order to develop the prediction model of the selected variables. The model showed satisfactory predictability when applied on unseen data and yielded an absolute average error of 5.1 %. The developed model can be effectively used for prediction of air permeability of the woven fabrics.     

VARIATION IN HEADING DATES OF PERENNIAL RYEGRASS CULTIVARS AS INFLUENCED BY SPRING AND EARLY SUMMER TEMPERATURES

Ear emergence data for 9 cultivars of perennial ryegrass have been recorded in Northern Ireland at the Plant Testing Station, Crossnacreevy, each year since 1967. These data show that while early spring (March-April) temperatures have a marked effect on the heading of early cultivars such as Gremie and Aberystwyth S24, the behaviour of later cultivars is more directly affected by temperatures at the time of their stem internode elongation. Ear emergence dates of late cultivars bear no fixed relationship to those of early cultivars. It is concluded that while records of early spring temperatures can be used to predict, with reasonable accuracy, the heading dates of early cultivars, such records do not provide a reliable basis for the prediction of heading dates of later cultivars. In Northern Ireland, reliable prediction of cutting dates for later cultivars to obtain herbage of a required level of digestibility is only possible on a short-term (one-two week) basis. Such predictions must take account of growing conditions in each individual year.     

Glass transition behavior of corn distillers dried grains with solubles (DDGS)

Distillers dried grains with solubles (DDGS), a major co-product from the corn ethanol industry, has high feed value for its chemical composition. The ratio of wet distillers grains (WDG) and condensed distillers solubles (CDS) added during the production process determines the chemical composition of DDGS. Effect of changing this ratio and the influence of moisture content on glass transition behavior of DDGS was studied. Five prediction models were evaluated to explain the glass transition of DDGS. The mixed trends in the result indicated the complex behavior of DDGS particles and revealed that both moisture content and chemical composition impact the glass transition behavior of DDGS. Onset glass transition temperature ranged from 20 to 30 °C depending on the chemical composition. Kwei equation predictions were better than the predictions by Gordon-Taylor equation. The glass transition temperature of DDGS can be mathematically explained by combining the moisture content and chemical components protein, fiber, glycerol, and sugar percent. The artificial neural network (ANN) model gave a better prediction of onset and midpoint glass transition temperature of DDGS and this might be due to the accurate mapping of the interaction between chemical components.     

Predicting the unevenness of polyester/viscose blended open-end rotor spun yarns using artificial neural network and statistical models

In this study, an artificial neural network (ANN) and a statistical model are developed to predict the unevenness of polyester/viscose blended open-end rotor spun yarns. Seven different blend ratios of polyester/viscose slivers are produced and these slivers are manufactured with four different rotor speed and four different yarn counts in rotor spinning machine. A back propagation multi layer perceptron (MLP) network and a mixture process crossed regression model (simplex lattice design) with two mixture components (polyester and viscose blend ratios) and two process variables (yarn count and rotor speed) are developed to predict the unevenness of polyester/viscose blended open-end rotor spun yarns. Both ANN and simplex lattice design have given satisfactory predictions, however, the predictions of statistical models gave more reliable results than ANN.