A technique of cotton bale laydown using clustering algorithm

A new technique of cotton bale management using clustering algorithm has been proposed. The method is based on the grouping cotton bales of similar kind into respective categories using k-mean square clustering algorithm. A set of 500 cotton bales were clustered into 5 categories by minimizing the total within-group squared Euclidean distance around the 5 centroids. In order to cluster bales of different categories, 8 fibre properties, viz., strength, elongation, upper half mean length, length uniformity, short fibre content, micronaire, reflectance and yellowness of each bale have been considered. Once the bales are clustered into different categories, it is possible to prepare consistent bale mix for consecutive laydowns on the basis of frequency relative picking method.     

The use of k-means and artificial neural network to classify cotton lint

The use of High Volume Instrument (HVI) to measure cotton lint characteristics produces high dimensional data. A model which utilized Kohonen Self Organizing Maps (SOM) to visualize cotton lint HVI data, k-means clustering technique to cluster the data and Probabilistic Neural Network (PNN) for data classification was designed and tested using Kenyan cotton lint. According to the model the Kenyan cotton lint can be grouped into four clusters, which were successfully classified by using PNN with a correlation coefficient (R-value) of 1.     

Study on the effects of single fiber tensile properties on bundle tensile properties through estimation of HVI bundle modulus and toughness

The HVI properties and Mantis® single fiber tensile properties were analyzed to evaluate the relationship between fiber and bundle tensile properties. For this study, a new method has been developed for estimating the modulus and toughness of cotton fiber bundles directly from the HVI tenacity-elongation curves. The single fiber tensile properties were shown to be translated well into the bundle tensile properties. The single fiber breaking elongation was found to be the most significant contributing factor to bundle tensile properties. The bundle breaking elongation and toughness were shown to increase as the single fiber breaking elongation increased. The bundle modulus increased as the single fiber breaking elongation and/or standard deviation of single fiber breaking elongation decreased.     

Effects of spinning processes on HVI fiber characteristics and spun yarn properties

The effects of opening, carding, and repeated drawings on single fiber and bundle cotton characteristics were studied by employing Mantis®, AFIS® and HVI Testers. Some of the significant changes in single fiber properties were found to be due to process parameters as well as the changes in the fiber crimps, parallelness of fibers within HVI beards, and the actual changes in the tensile properties of the fibers. The study showed that the HVI test data taken just prior to spinning had the highest correlation with the yarn tensile properties. Based on the study results, we point out the potential of HVI for future quality and process control in spinning by recommending a set of expanded HVI output that is more scientific and comprehensive for the future control needs.     

Prediction of rotor spun yarn strength from cotton fiber properties using adaptive neuro-fuzzy inference system method

In this study, we present the application of a hybrid neuro-fuzzy system for the prediction of cotton rotor spun yarn strength from cotton fiber properties. The proposed system possesses the advantages of both artificial neural networks and fuzzy logic, and is thus more intelligent. HVI (high volume instrument) and Uster AFIS (advanced fiber information system) fiber test results are used to train the neuro-fuzzy inference system. We also study the degree of impact of each fiber property on the rotor spun yarn strength. Fiber strength, upper half mean length, length uniformity and yarn count have a positive impact whereas micronaire, yellowness and short fiber content have a negative impact on rotor spun yarn strength.     

Prediction of cotton yarn properties using support vector machine

This paper presents a support vector machine (SVM) regression approach to forecast the properties of cotton yarns produced on ring and rotor spinning technologies from the fibre properties measured by HVI and AFIS. Prediction performance of SVM models have been compared against those of the artificial neural network (ANN) models. A k-fold cross validation technique is applied to assess the expected generalization accuracies of both SVM and ANN models. The investigation indicates that the yarn properties can be predicted with a very high degree of accuracy using SVM models and the prediction performance of SVM models are better than that of ANN models.     

Cotton yarn engineering via fuzzy least squares regression

Modeling of yarn and fiber properties has been a popular topic in the field of textile engineering in recent decades. The common method for fitting models has been to use classical regression analysis, based on the assumptions of data crispness and deterministic relations among variables. However, in modeling practical systems such as cotton spinning, the above assumptions may not hold true. Prediction is influential and we should therefore attempt to analyze the behavior and structure of such systems more realistically. In the present research, we investigate a procedure to provide a soft regression method for modeling the relationships between fiber properties, roving properties, and yarn count as independent variables and yarn properties as dependent (response) variable. We first selected the effective variables by multivariate test (mtest) and then considered fuzzy least squares regression for evaluating relationship between cotton yarn properties such as tensile, hairiness, unevenness and fiber properties that were measured by HVI system. We also used mean of capability index (MCI) to evaluate the goodness of fit of the fuzzy regression models. The results showed that the equations were significant at very good MCI levels.     

基于HVI测试的标准化操作规范

为了规范大容量棉花测试仪的使用、校准及维护,提高检测结果准确性.作者根据HVI应用手册和实际操作经验,总结了大容量棉花测试仪的标准化工作各项要求.主要包括样品管理、气电及空间要求、恒温室、标准化仪器、校准与核查、比对试验、测试人员、健康安全、消防安全等.供业内同仁参考.     

Cotton yarn engineering using robust regression and criteria of Mallow’s Cp

The main purpose of the present study was to predict yarn’s important properties i.e., tensile, unevenness, hairiness, and imperfections of cotton yarn with minimum random errors and maximum accuracy. In this work, cotton fiber properties were measured from rovings carefully untwisted. HVI system and evenness tester of Premier were used to measure the various properties. All yarns (108 samples) were spun at yarn counts of 16, 20, 24, 28, and 32 Ne with optimum twist factor. The robust regression and criteria of Mallow’s Cp were used to evaluate the data. Optimal equations with appropriate variables and relative importance of various variables were also investigated. After the goodness of fit, desirable Cp and very large adjusted R² values were observed. Furthermore, the analysis of variance tables showed that the obtained equations were significant at usual significance levels.     

Comparison of artificial neural network and linear regression models for prediction of ring spun yarn properties. I. Prediction of yarn tensile properties

In this study artificial neural network (ANN) models have been designed to predict the ring cotton yarn properties from the fiber properties measured on HVI (high volume instrument) system and the performance of ANN models have been compared with our previous statistical models based on regression analysis. Yarn count, twist and roving properties were selected as input variables as they give significant influence on yarn properties. In experimental part, a total of 180 cotton ring spun yarns were produced using 15 different blends. The four yarn counts and three twist multipliers were chosen within the range of Ne 20–35 and α _e 3.8–4.6 respectively. After measuring yarn tenacity and breaking elongation, evaluations of data were performed by using ANN. Afterwards, sensitivity analysis results and coefficient of multiple determination (R²) values of ANN and regression models were compared. Our results show that ANN is more powerful tool than the regression models.     

Prediction of rotor spun yarn strength using support vector machines method

A new method for rotor spun yarn prediction from fiber properties based on the theory of support vector machines (SVM) was introduced. The SVM represents a new approach to supervised pattern classification and has been successfully applied to a wide range of pattern recognition problems. In this study, high volume instrument (HVI) and advanced fiber information system (Uster AFIS) fiber test results consisting of different fiber properties are used to predict the rotor spun yarn strength. The results obtained through this study indicated that the SVM method would become a powerful tool for predicting rotor spun yarn strength. The relative importance of each fiber property on the rotor spun yarn strength is also expected. The study shows also that the combination of SVM parameters and optimal search method chosen in the model development played an important role in better performance of the model. The predictive performances are estimated and compared to those provided by ANFIS model.     

基于光特征的新疆机采棉高产创建全程塑形调控技术

通过新疆机采棉高产创建的实践,在向"温"要产量的基础上挖掘从光要产量,因而总结了新疆机采棉全程塑形调控技术。本文从棉花种植21个关键环节阐述了塑形调控技术的目标与措施,打破了新疆以往只注重棉花群体优势,忽视个体优势不足问题,实现棉花促早发、生殖前移、生殖量增加、多结铃、结优质铃,从而达到高产稳产、提质增效的目的。塑形调控技术能塑造合理的群体、个体结构,提高肥水利用效率,实现棉农增产增收,提高新疆棉花综合生产能力和水平。     

机采与手采鲜叶加工平水日铸茶工艺、品质及成本比较研究

在相同生产时间,对机采与手采鲜叶按连续化颗粒型加工工艺技术生产平水日铸茶,对生产的茶叶品质进行感官审评、成本进行比较分析,比较两种采摘模式下的加工方法、茶叶品质和经济效益。结果表明,机采鲜叶在嫩度与匀整度上明显低于手采鲜叶;可采用相同的初加工工艺与技术参数进行加工;机采毛茶品质由于含梗量与嫩度的原因在外形与叶底上感官审评得分略低于手采毛茶,但在香气与滋味上接近、有的甚至还稍优于手采毛茶,综合品质两者接近;精加工后两者品质更趋一致。在生产成本与得率上,每公斤机采茶的成本比手采茶低36.22%,得率低25.48%,经济效益高约21.30%。     

Effect of various bale treatments on physical quality and chemical composition of rhodes grass (Chloris gayana) hay

The effect of harvest season (winter vs. summer), moisture content at baling and bale mass on hay physical quality and chemical composition of two varieties of Rhodes grass ( Chloris gayana ) was studied during bale storage. Three moisture levels (15–20%, 20–25%, 25–30%) and three bale masses (13 kg, 18 kg, 24 kg, at an equal volume) were tested in varieties Pioneer and Alimba - the most common cultivars in the Arabian Gulf region. Variety Alimba has a rougher texture with more stems and fewer leaves. This caused significantly higher water retention and consequently higher bale temperatures. In summer, bale temperatures of Alimba stored at 25–30% moisture content and 24 kg bale mass averaged 37.7°C compared with 28·2°C in variety Pioneer. Lowest dry-matter (DM) content was 793 g kg⁻¹ and was recorded in the winter cut of variety Alimba baled at the upper moisture level (25–30%), whereas the highest was that of variety Pioneer. Lowest crude protein content was that of variety Pioneer (61 g kg DM⁻¹). Prolonged heat build-up of some bales caused dark-brown discoloration, and, although colour variations were significant, they were not large. There was no contribution of bale mass to changes in DM content, indicating that the selected levels of bale mass in the experiment were lower than those expected to cause significant effects on hay chemical composition and nutritive value. In general, it is recommended to store Rhodes grass hay at moistures up to 30% and even higher in the summer season in the case of variety Alimba. Higher moisture contents at baling could preserve hay quality by minimizing shattering of leaves excessively dried under the prevailing hay-making conditions, especially in the variety Pioneer.     

分布控制的乘坐式仿形采茶原型机研制与试验

为提高茶鲜叶采摘机械的自动化水平以及采摘完整率,降低采茶机系统开发成本,缩短开发周期,本研究提出了机采茶蓬面割刀自动仿形方法和分布式快速控制原型机低成本开发方法,研制了仿形采茶样机,并开展室内和田间试验.仿形采茶机采用超声波传感器,感知往复式割刀与茶树蓬面间的距离信息,通过丝杆实现仿形传动;利用Hampel滤波和低通滤...     

The relationship between spoilage and Listeria monocytogenes contamination in bagged and wrapped big bale silage

A farm-scale trial to compare the effectiveness of polythene bags and wrapping of big bale silage was monitored for Listeria monocytogenes contamination. There was no significant difference between the level of L. monocytogenes found in wrapped and bagged big bale silage, but the work confirmed that big bale silage is prone to contamination by Listeria organisms, and that the degree of Listeria contamination could be significantly reduced by the removal of obviously spoiled material prior to feeding.     

Growth of naturally occurring Listeria spp. in silage: a comparative study of laboratory and farm ensiled grass

A laboratory method for ensiling grass in bags, which simulates the aerobic deterioration found in big bale silage, is described. These conditions selectively encouraged the multiplication of naturally occurring listeria. All grasses ensiled in this way gave detectable numbers of listeria, usually L. monocytogenes , indicating that these bacteria are a normal part of the microflora of grass. The results from the laboratory silage were comparable to those found in the same grass ensiled in big bales on the farm.     

Rebaling of silage and haylage and its effects on forage microbial and chemical composition—A pilot study

Use of big bale silage and haylage can be difficult on farms where daily forage consumption is comparatively low as speed of deterioration of forage after bale opening may be faster than feed-out rate. Production of smaller bales at harvest is possible, but expensive and work-intensive. Therefore, a pilot study of rebaling forage stored in big bales to smaller bales was conducted. Three separate experiments were included, where microbial and chemical composition of silage and haylage was studied before and after rebaling. In Experiment III, residual big bale forage stored and opened together with rebaled forage was included. Results showed that rebaled haylage and silage had higher yeast counts compared to initial forage; however, residual bales in Experiment III had yeast counts similar to rebaled forage, indicating an effect of storage time rather than of rebaling. In Experiment II, mould counts were higher in rebaled compared to initial silage, but not in haylage. Chemical composition was similar in initial and rebaled forage except for ammonia-N. In Experiment III, ammonia-N was higher in rebaled compared to initial and residual forage and was the only chemical variable affected by rebaling. Bale temperature during aerobic storage followed ambient temperature until day 6–8 in Experiment I and until day 14 in Experiment III where ambient temperature was lower. In conclusion, rebaling can be done without large changes in chemical composition of the forage, but yeast and mould counts may be higher in rebaled forage, and this risk should be considered when using this procedure.     

Predicting properties of single jersey fabrics using regression and artificial neural network models

In our previous works, we had predicted cotton ring yarn properties from the fiber properties successfully by regression and ANN models. In this study both regression and artificial neural network has been applied for the prediction of the bursting strength and air permeability of single jersey knitted fabrics. Fiber properties measured by HVI instrument and yarn properties were selected as independent variables together with wales’ and courses’ number per square centimeter. Firstly conventional ring yarns were produced from six different types of cotton in four different yarn counts (Ne 20, Ne 25, Ne 30, and Ne 35) and three different twist multipliers (α _e 3.8, α _e 4.2, and α _e 4.6). All the yarns were knitted by laboratory circular knitting machine. Regression and ANN models were developed to predict the fabric properties. It was found that all models can be used to predict the single jersey fabric properties successfully. However, ANN models exhibit higher predictive power than the regression models.