Engineering Cotton Yarns with Artificial Neural Networking (ANN) by Tasnim N. Shaikh and Sweety A. Agrawal

5:48 AM
Engineering Cotton Yarns with Artificial Neural Networking (ANN)
By Tasnim N. Shaikh and Sweety A. Agrawal
Engineering Cotton Yarns with Artificial Neural Networking

Contents
Preface xiii
1 Classification of textile yarns 1
1.1 Introduction 2
1.2 Types of textile fibers 3
1.3 Types of textile yarn 5
1.4 Significance of cotton yarn in textile industry 9
1.5 Production pattern in brief for most significant cotton fiber in textile industry 10
1.6 Impact of natural fiber variations on yarn
production process 13
References 14
2 Attributes of cotton mixing 17
2.1 Need for mix formulation 17
2.2 Interrelationship between fiber characteristics
and yarn quality 18
2.3 Contribution of fiber parameters on ring spun
yarn quality & cost 21
2.3.1 Length & length variations 21
2.3.2 Fineness 23
2.3.3 Maturity 25
2.3.4 Strength 26
2.3.5 Trash 27
2.3.6 Moisture 28
2.3.7 Colour 29
2.4 Importance of mix homogeneity 30
2.5 Impact of technological changes on homogeneity of mix 30
Reference 30
3 Testing techniques used in yarn engineering 33
3.1 Introduction 33
3.1.2 Attributes of cotton ring spun yarn engineering 34
3.2 Role of testing in cotton selection 35
3.3 Various fiber testing techniques 35
3.3.1 Fiber length 36
3.3.2 Fiber fineness 44
3.3.3 Fiber maturity 48
3.3.4 Fiber strength 51
3.3.5 Trash 55
3.3.6 Moisture 58
3.3.7 Colour 59
3.4 Stages of developments in testing techniques and its impact
on mix formulation process 61
3.4.1 Classical testing techniques 62
3.4.2 Semi-automatic mode of testing 63
3.4.3 Automatic mode of testing 65
References 69
4 Statistical techniques used in yarn engineering 71
4.2 Analysis of test data 72
4.2.1 Measures of central tendency 73
4.2.2 Measurement of dispersion 74
4.3 Compatibility test methods 78
4.4 Statistical techniques for defining technological value of
cotton 80
4.4.1 Drafting quality index (Q) 81
4.4.2 Fiber quality index (FQI) 82
4.4.3 Modified fiber quality index (MFQI) 84
4.4.4 Spinning consistency index (SCI) 85
4.4.5 Premium discount index (PDI) 86
4.4.6 Multi criteria decision-making (MCDM) 87
4.4.7 Geometric properties index (IG) 88
4.5 Statistical techniques for defining proportion of cotton
constituents in mix 89
4.5.1 Judicious mixing 89
4.5.2 Linear programming 89
4.5.3 Fuzzy linear programming approach 92
References 93
5 Artificial neural networking (ANN) 95
5.1 Introduction 95
5.2 Historical background for the development of ANN 97
5.3 Basic concept of ANN (Artificial Neural Network) 98
5.4 Types of neural network 98
5.4.1 Single layer feed forward network 100
5.4.2 Multilayer feed forward network 100
5.4.3 Recurrent network 100
5.4.4 Learning of a network 101
5.5 Architecture of ANN 101
5.6 Designing the network 102
5.7 Operational mode of ANN 103
5.7.1 Training the network 103
5.7.2 Verification testing 104
5.8 Applications areas of ANN 104
5.9 ANN applications in the field of textile engineering 105
5.9.1 Fibers 106
5.9.2 Yarn 108
5.9.3 Fabric 109
5.9.4 Garment 114
5.9.5 Non-woven 115
5.10 Connotation of ANN offered solutions
over the other methods 116
References 116
6 Changes in mix formulation approach with the
technological developments 127
6.1 Introduction 127
6.2 Basic objectives of mix formulation 128
6.3 Constrains for accurate mixing 129
6.4 Different approaches of mix formulation 129
6.4.1 Classical visual judgment approach 130
6.4.2 Mix formulation with non–automatic instrumental
technology 135
6.4.3 Mix formulation with automatic instrumental
technology 143
References 149
7 Cotton fiber engineering 151
7.1 Introduction 151
7.2 Importance of cotton fiber engineering 152
7.3 Attributes of cotton fiber engineering 153
7.3.1 Cotton purchasing strategy 154
7.3.2 Cotton testing 154
7.3.3 Bale management 155
7.3.4 Cotton fiber selection 156
7.4 Bale inventory analysis system (BIAS) 159
7.5 Engineered fiber selection (EFS) 160
7.5.1 Determination of cotton specifications 160
7.5.2 Opening line configuration and availability 161
7.5.3 In-house inventory management 163
7.5.4 Mix profiles 165
7.5.5 Bale selection 165
7.5.6 Mix evaluation and performance verification 166
7.5.7 Benefits offered by EFS® 166
7.6 Linear programming 167
7.6.1 Assumptions of linear programming 168
7.6.2 Types of linear programming 168
7.6.3 Effect of inventory constraints 169
References 170
8 Yarn engineering by back propagation algorithm concept of
ANN 173
8.1 Introduction 174
8.2 Reverse yarn engineering 175
8.2.1 Importance 175
8.2.2 Basic steps of networking 175
8.3 Procedure for cotton yarn engineering 176
8.3.1 Defining aim of yarn engineering 177
8.3.2 Database creation 178
8.3.3 Construction of desired artificial
neural network 179
8.3.4 Modelling 183
8.3.5 Testing of neural network 190
8.3.6 Computing prediction error 191
References 192
9 Optimisation of yarn quality, cost and process parameters 195
9.1 Introduction 195
9.2 Components for optimisation 196
9.3 Technological value of cotton mix 197
9.3.1 Cotton fiber quality 197
9.3.2 Cotton cost 198
9.4 Optimisation of process parameters 200
9.5 Optimisation of yarn technological value 202
9.5.1 End product added value 204
9.5.2 Optimum fiber quality utilisation for target
yarn by the use of EFS® system 206
9.5.3 Optimum fiber quantity utilisation efficiency for target yarn by the use of EFS® system 211
9.6 Summary 214
References 215
10 Case study 217
10.1 Introduction 217
10.2 Case study I 218
10.2.1 Basic attributes used for ANN reverse yarn engineering model 218
10.2.2 Sample preparation 219
10.2.3 Optimisation of ANN parameters 220
10.2.4 Validation of ANN prediction 221
10.2.5 Linear programming 222
10.2.6 Impact analysis 222
10.3 Case study II 225
10.3.1 Basic attributes of artificial neural network 225
10.3.2 Sample preparation 226
10.3.3 Experimentation 227
10.4 Case study III 229
10.4.1 Artificial neural networking 229
10.4.2 ANN parameters 230
10.4.3 Experimental 231
10.4.4 Prediction performance of ANN 231
10.4.5 Analysis of input parameters influence 232
10.4.6 Trend analysis by ANN model 233
References 234
Appendix 237
Abbrevations 249
Index 251


Read “Engineering Cotton Yarns with Artificial Neural Networking (ANN)” as PDF
How to Get Book? To get any book you can send Email: textileebooks@gmail.com

Share this

Related Posts

Previous
Next Post »