Browsing by Author "Jayawardane, TSS"

Now showing 1 - 9 of 9

item: Article-Abstract
Analysis, modeling and simulation of a poly-bag manufacturing system
(2016-09-22) Gopura, RARC; Jayawardane, TSS
The cost of raw material of poly-bags increases and fluctuates with an unpredictable trend. Further, legal restrictions imposed on some types of polythene products adversely affects for the demand. In this context, entrepreneurs engaging in poly-bag anufacturing face major challenges. With the purview of optimizing the poly-bag manufacturing process, authors attempted to analyze, model and simulate the poly-bag manufacturing process in the light of posed challenges. This paper presents preliminary analysis, modeling and simulation strategies of a poly-bag manufacturing system. In addition, a risk prioritization method is proposed in the preliminary analysis and also a simulation tool is developed.
item: Conference-Abstract
Control methodologies for upper limb exoskeleton robots
(2016-09-22) Gunasekara, JMP; Gopura, RARC; Jayawardane, TSS; Lalitharathne, SWHMTD
An exoskeleton robot is kind of a man-machine system which mostly uses combination of human intelligence and machine power. These robotic systems are used for different applications such as rehabilitation, human power amplification, motion assistance, virtual reality etc. Successful operation of an exoskeleton robot depends on correct selection of design and control methodologies. This paper reviews control methodologies used in upper limb exoskeleton robots. In the review, the control methods used in the exoskeleton robots are classified into three categories: control system based on human biological signal, non-biological signal and platform independent control system. Different types of control methods under each category are compared and reviewed.
item: Conference-Abstract
Influence of varying supply yarn package diameter on the pirn winding tension
(2011) Fernando, ESK; Jayawardane, TSS; Fernando, WSP
Pirn winding is an operation of winding yarn from supply yarn package onto pirns which are used for shuttle weft insertion. As the package size varies when winding pirns, the varying balloon effect caused to change the thread tension at the winding point of the pirn. As a number of pirns can be wound from a single supply yarn package, pirns are wound from different yarn package diameters. A significant change in take off tension takes place from pirn to pirn. Placing dead weights on the disc tension controller which adds a tension to take off tension may help to compensate the yarn tension variation to some extent. However, incorrect timing of compensation and stepwise compensation may create significant tension variations in pirn windings. The authors attempted to design a tension control device by applying an automatically continuously varying electromagnetic force on the dead weight, so that the variation of take off tension due to change of package diameter is compensated and investigate influence of varying supply yarn package diameter on the fmal winding tens ion of pirn.
item: Article-Abstract
Kernel-based clustering approach in developing apparel size charts
Vithanage, CP; Jayawardane, TSS; Thilakaratne, CD; Niles, SN
With the industry revolution, apparel products also become more sophisticated moving from the basic purpose of clothing to aesthetic appeal of the garment embracing the concepts garment fitting and fashion. Garment fitting is a key technical essential for comfortable wearing. In garment fitting, size refers to a set of specified values of body measurements, such that it will provide a means for garments perfectly fit to a person. With the advent of computer software and improved data mining techniques, researchers attempted new advances in formulation of size charts with a better fit. This article suggests a kernel-based clustering approach in developing an effective size chart for the pants of Sri Lankan females. A new kernel based approach “Global Kernel K- means clustering” was successfully deployed to cluster lower body anthropometric data of Sri Lankan females within the age range of 20-40 years. Through the proposed Kernel- based clustering method can effectively handle highly non-linear data in input space which is a key property of lower body anthropometric data and make it linearly separable in feature space without reduction in dimensions and also mathematically justified. Through this method promising results could be obtained and further clustering method was internally validated with kernel based Dunn’s index. The level of fitness of the developed size chart was also evaluated with the aggregate loss of fit factor. The proposed method has strong implications to utilize globally in developing size charts.
item: Conference-Full-text
Machine learning-based approach for modelling elastic modulus of woven fabrics
(IEEE, 2020-07) Kularatne, SDMW; Ranawaka, RAHS; Fernando, EASK; Niles, SN; Jayawardane, TSS; Ranaweera, RKPS; Edussooriya, C; Weeraddana, CUS; Abeysooriya, RP
There has been a shift of focus from aesthetic properties to mechanical and functional properties of textiles with the recent developments in technical textiles and wearable technology. Therefore, understanding how various fabric parameters influence the mechanical properties of fabrics is paramount. In applications where compression and stretching of fabrics are important, the elastic modulus is a key fabric property that needed to be controlled precisely. Woven fabrics are capable of providing superior elastic properties, but how various fabric parameters affect elastic modulus is not well understood. In this study, two machine learning techniques were implemented to model the elastic modulus of woven fabrics and were compared with multivariable regressions. The two machine learning techniques used are Artificial Neural Network (ANN) and Random Forest Regression. As input variables; weave factor (numerical representation of weave structure), warp yarn count and pick density were used. Both ANN and Random Forest Regression were able to generate reasonably accurate results with Random Forest Regression been the better of the two methods. Using Random Forest Regression, feature importance of the input variables was obtained, and it proved that the weave structure has a notable impact on the elastic modulus of woven fabrics.
item: Conference-Full-text
Mathematical Analysis of Startup Mark in Elastic Tape on a Narrow Fabric Loom
(2015-08-03) Dayaratne, HDCT; Premakumara, R; Perera, T; Prince, S; Fernando, EASK; Jayawardane, TSS
Start-up marks are considered as one of the major defect in woven fabric, it occurs when the loom is restarted after loom stoppage due to various reasons. This defect is more prominent in high speed weaving looms especially with elastic warp yarns and is caused to deteriorate the fabric quality. This research paper deals with the mathematical analysis of the startup mark generation in elastic tape on narrow fabric loom. Mathematical analysis was carried out for both continuous operation condition and under stopping condition of the narrow fabric loom. A system simulation was carried out using the model developed and compared with the experimental results to show the accuracy of the model.
item: Conference-Abstract
Mathematical analysis of startup mark in elastic tape on a narrow fabric loom
Dayaratne, HDCT; Premakumara, R; Perera, T; Prince, S; Fernando, EASK; Jayawardane, TSS
Start-up marks are considered as one of the major defect in woven fabric, it occurs when the loom is restarted after loom stoppage due to various reasons. This defect is more prominent in high speed weaving looms especially with elastic warp yarns and is caused to deteriorate the fabric quality. This research paper deals with the mathematical analysis of the startup mark generation in elastic tape on narrow fabric loom. Mathematical analysis was carried out for both continuous operation condition and under stopping condition of the narrow fabric loom. A system simulation was carried out using the model developed and compared with the experimental results to show the accuracy of the model.
item: Article-Abstract
Mathematical modeling of weft yarn tension in pirn winding
(2015-08-24) Fernando, EASK; Jayawardane, TSS
Pirn winding is an operation of winding yarn from supply yarn package onto pirns which are used for shuttle weft insertion. Firm and coherent winding tension is required to maintain in the pirn winding process to withstand the high forces produced by the deceleration of the shuttle at the end of each pick and to avoid permanent strains in yarns which will appears as fabric defects in weaving. The package size and its diameter vary due to subsequent winding of pirns. Hence the balloon effect varies and caused to change the thread tension at the winding point of the pirn. The thread tension variation is considerably significant from the first pirn wound from a package to the last pirn wound from the same if no tension controlling mechanism is devised. Placing dead weights on the disc tension controller which adds a tension to take off tension may help to compensate the yarn tension variation to some extent to combat with this problem. However, this is a stepwise manual compensation technique which needs the correct timing of compensation to avoid significant tension variations in pirn windings. The author attempted to theoretically analyze the tension variation in the yarn path of the pirn winding machine and theoretically model the tension variation with and without deadweight placement on the tensioners. Author also verified the accuracy and the validity of the model developed through the experimental results obtained at different locations along the yarn path..
item: Thesis-Full-text
A Novel approach in formulating a size chart for female pants
Vithanage, CP; Jayawardane, TSS; Niles, N; Tilakaratne, CD
Each country understands that they need their own size charts representing their population because researchers have found that human body shapes, proportions and measurements change significantly due to the geographical and demographical differences. Even though, many countries have developed their own size charts, ready-to-wear apparel industry still faces the problem of poor fit of apparels. Reasons for this fit problems may be due to several factors such as limitations of existing size chart development approaches, lack of up-to-date anthropometric data of the relevant population, vast body shape differences among the population, and restrictions in mass production systems. In this research, one of the above problems; issues in existing size chart development approaches, was studied comprehensively in order to identify drawbacks of the size chart development approaches. Statistical approach which uses descriptive statistics, k-means clustering combined with factor analysis and classification and regression decision tree method were widely used popular size chart development approaches. With the current lower body anthropometric data of Sri Lankan females of age 20-40 years, limitations of the above approaches were investigated. Through this explorative analysis, limitations of current approaches and potential improvements for a better approach were discerned. Thereby a novel approach for development of size charts was formulated. The proposed approach is capable of handling linearly inseparable data with high dimensionality without variable reduction. Further, number of clusters can be objectively determined and the transformation function could be optimized by tuning the parameters of it. Kernel based learning is one of the latest data mining approaches in pattern recognition. A kernel based clustering technique called “global kernel k-means clustering technique”, was adopted to cluster lower body anthropometric data in the proposed method. Selection of proper kernel function and tuning of kernel parameters are crucial in successful data clustering. For determining the number of clusters objectively, kernel based Dunn’s index, which is one of the cluster validation technique, was successfully instrumented in the said novel approach. Thereby the lower body anthropometric dataset of females was successfully clustered through the proposed novel approach taking all variables into account. It was also proved that the developed size chart could successfully eliminate the fitting problems of Sri Lankan female pants. The size chart was validated through a well accepted index called Aggregate Loss of Fit index on theoretical ground and the live model fitting of fabricated pants according to the size chart through a standard feedback questionnaire. The complete approach in developing size charts could be of interest to other clustering applications in many fields also