Aiming at the problems of low prediction accuracy, poor stability, and dependence on sample size of backpropagation (BP) artificial neural networks commonly used in current yarn quality prediction research, a prediction method combining grid search (GS) and generalized regression neural network (GRNN) is proposed. Through the hyperparameter optimum finding function of GS to select the best smoothing factor of GRNN, realizing the automatic optimization of model performance, while achieving the effect of reducing complexity and enhancing generalization ability, the prediction behavior of the model for various quality characteristics of yarns is improved. On this basis, in order to mitigate the influence of features that may be redundant or less contributive to the prediction target in the yarn multi-correlation parameters, sequential backward selection (SBS) is introduced as a dimensionality reduction method to determine the optimal feature subset to obtain the main influencing factors in the design input variables. This hybrid method is compared with multiple linear regression (MLR), BP neural network (BPNN), and support vector regression (SVR). The results show that under the condition of a small amount of spinning data, the average prediction error of GS-GRNN is about 29.31% lower than BPNN, and the prediction accuracy of the base model can be effectively improved by applying SBS to optimize the feature dimension (about 37.2% higher on average), moreover, compared with SVR and MLR, this hybrid model also possesses a better comprehensive prediction effect, which verifies the stable and excellent mapping ability of SBS-GS-GRNN under the small sample set.
DaiNJinHWXuKX, et al.
Prediction of cotton yarn quality based on attention-GRU. Appl Sci2023;
13: 10003.
2.
ChengLAdamsDL.Yarn strength prediction using neural networks: part I: fiber properties and yarn strength relationship. Text Res J1995;
65: 495–500.
3.
MwasiagiJIHuangXBWangXH.Performance of neural network algorithms during the prediction of yarn breaking elongation. Fibers Polym2008;
9: 80–86.
4.
ZhuREthridgeMD.The prediction of cotton yarn irregularity based on the ‘AFIS’ measurement. J Text Inst1996;
87: 509–512.
5.
ZhuREthridgeMD.Predicting hairiness for ring and rotor spun yarns and analyzing the impact of fiber properties. Text Res J1997;
67: 694–698.
6.
KhanZLimAEWangLJ, et al.
An artificial neural network-based hairiness prediction model for worsted wool yarns. Text Res J2009;
79: 714–720.
7.
BeltranRWangLWangX.Mill specific prediction of worsted yarn performance. J Text Inst2006;
97: 11–16.
8.
TurhanYToprakciO.Comparison of high-volume instrument and advanced fiber information systems based on prediction performance of yarn properties using a radial basis function neural network. Text Res J2013;
83: 130–147.
9.
ZhangBWSongJXZhaoSN, et al.
Prediction of yarn strength based on an expert weighted neural network optimized by particle swarm optimization. Text Res J2021;
91: 2911–2924.
10.
ÜreyenMEKadogluH.Regressional estimation of ring cotton yarn properties from HVI fiber properties. Text Res J2006;
76: 360–366.
11.
GhoshAChatterjeeP.Prediction of cotton yarn properties using support vector machine. Fibers Polym2010;
11: 84–88.
12.
DoranECSahinC.The prediction of quality characteristics of cotton/elastane core yarn using artificial neural networks and support vector machines. Text Res J2020;
90: 1558–1580.
13.
YinXGYuWD.Selection and evaluation of input parameters of neural networks using grey superior analysis. Text Res J2007;
77: 375–386.
14.
MwasiagiJI.The use of extreme learning machines (ELM) algorithms to prediction strength for cotton ring spun yarn. Fashion Text2016;
3: 1–9.
15.
YangJGXuLLuZJ, et al.
Yarn quality prediction and process parameters optimization based on genetic algorithm and neural network. Appl Mech Mater2015;
742: 377–383.
16.
HadavandiEMostafayiSSoltaniP.A Grey Wolf Optimizer-based neural network coupled with response surface method for modeling the strength of siro-spun yarn in spinning mills. Appl Soft Comput2018;
72: 1–13.
17.
SoltaniPHadavandiE.A monarch butterfly optimization-based neural network simulator for prediction of siro-spun yarn tenacity. Soft Comput2019;
23: 10521–10535.
18.
SongJXFanTT.Yarn hairiness prediction by generalized regression neural network based on Harris hawk optimization. J Inst Eng India Ser E2022;
103: 347–355.
19.
GhanmiHGhithABenameurT.Ring spun yarn quality prediction using hybrid neural networks. J Text Inst2023;
114: 66–74.
20.
LiuZYChenNLWangJ.Yarn quality prediction of small samples based on random forest algorithm. J Donghua University (Nat Sci)2023;
49: 80–86.
21.
LiuZYChenNLWangJ.A two-layer stacking regression model for predicting yarn quality of small samples. Text Res J2024;
94: 1096–1110.
22.
WangMLWangJAGaoWD, et al.
E-YQP: A self-adaptive end-to-end framework for quality prediction in yarn spinning manufacturing. Adv Eng Inf2024;
62: 102623.
23.
HuZLZhaoQWangJ.The prediction model of cotton yarn intensity based on the CNN-BP neural network. Wireless Pers Commun2018;
102: 1905–1916.
24.
HuSZhangGZhaoXH, et al.
A method for yarn quality fluctuation prediction based on multi-correlation parameter feature subspace mechanism in spinning process. J Eng Fibers Fabr2023;
18: 1–12.
25.
LinDY.Application of GRNN neural network in performance prediction of automotive engine. J Jimei University (Nat Sci)2023;
28: 467–472.
26.
XuFQZhengTTFangBQ.Function approximation based on general regression neural network (GRNN). J Chaohu College2010;
12: 11–16.
27.
WangCHChangYZYuanY, et al.
Using the data of earthquake magnitude samples to verify the superiority of PCA-GSM-GRNN model. Earthquake Res Sichuan2024;
48: 35–38.
28.
YaoYChenZCWuLJ, et al.
A health state estimation method for lithium-ion battery based on improved grid search and generalized regression neural network. Electr Eng2021;
22: 32–37.
29.
LiuGYuWD. The BP neural network modeling on worsted spinning with grey superior theory and correlation analysis. In: 2008 Fourth International Conference on Natural Computation, 18–20 October, 2008, Jinan, China, pp. 374–378. New York: IEEE.
30.
LiBLiaoMJZhangJ.Optimizing the generalized regression neural network based on improved fruit fly algorithm for green agricultural products consumer behavior prediction. J China Agric Univ2023;
28: 224–231.
31.
WuDHuS.Quality fluctuation abnormal source identification based on variable weighted reconstruction analysis in spinning process. Text Leather Rev2024;
7: 1178–1196.
32.
DuCShaoJHYangW, et al.
Support vector machine indoor visible light positioning optimized by grid search method. Laser J2021;
42: 104–109.
33.
JiangHSongJXZhangBW, et al.
Yarn unevenness prediction using generalized regression neural network under various optimization algorithms. J Eng Fibers Fabr2022;
17: 1–10.
34.
WeiYT.Prediction of concrete compressive strength and concrete mix design based on SVR-GA. Master’s Thesis, Tsinghua University, Beijing, China, 2022.
35.
WangMSHeMSiWN, et al.
Polarimetric SAR coastal wetland feature classification based on combined optimization features. Geospatial Inf2023;
21: 63–67.
36.
MiaoJHHanXAvoukaT, et al.
Household sleep staging method based on single channel ECG signal. J Tiangong Univ2023;
42: 83–88.
37.
WangMH.Construct models of fiber quality index based on HVI data. J Text Res2014;
35: 40–45.
38.
FangL.The prediction model of cotton yarn based on neural network. Master’s Thesis, Donghua University, Shanghai, China, 2016.
39.
GuoYL.Analysis and prediction of private car ownership based on grey-generalized regression neural network. Master’s Thesis, North China Electric Power University, Beijing, China, 2023.
40.
LinYPChenLLZouJZ.Application of hybrid feature selection algorithm based on particle swarm optimization in fatigue driving. Comput Eng2019;
45: 278–283.
