The use of extreme learning machines (ELM) algorithms to prediction strength for cotton ring spun yarn

Abstract

The increasing use of artificial neural network in the prediction of yarn quality properties calls for constant improvement of the models. This research work reports the use of a novel training algorithm christened extreme learning machines (ELM) to prediction yarn tensile strength (strength). ELM was compared to the Backpropagation (BP) and a hybrid algorithm composed of differential evolution and ELM and named DE-ELM. The three yarn strength prediction models were trained up to a mean squared error (mse) of 0.001. This is an arbitrary level of mse that was selected to enable a comparative study of the performance of the three algorithms. According to the results obtained in this research work, the BP model needed more time for training, while the ELM model recorded the shortest training time. The DE-ELM model was in between the two models. The correlation coefficient (R2) of the BP model was lower than that of ELM model. In comparison to the other two models the DE-ELM model gave the highest R2 value.

Prediction of yarn unevenness based on BMNN

“…Subsequently, in the period of the rapid development of neural networks, Furferi and Gelli 2 proposed a model based on feedforward back propagation (BP) artificial neural network to predict yarn strength. Mwasiagi 3…”

“…Subsequently, in the period of the rapid development of neural networks, Furferi and Gelli 2 proposed a model based on feedforward back propagation (BP) artificial neural network to predict yarn strength. Mwasiagi 3 proposed a DE-ELM algorithm combining differential evolution (DE) algorithm and Extreme Learning Machine (ELM) to predict the strength of spun yarn; Zhenlong et al 4 combined convolutional neural network (CNN) and BP neural network, and proposed a CNN-BP neural network to predict yarn strength; Hu et al 5 considers the influence of time on yarn quality and strength, and proposes a yarn strength and quality prediction model based on artificial recurrent neural network (RNN).…”

A two-layer stacking regression model for predicting yarn quality of small samples

“…While neural network models outperformed traditional mathematical-statistical models, they grappled with challenges such as subpar generalization, inadequate prediction accuracy, sluggish convergence rates, and a propensity to become ensnared in local optima. 4,5 In addition, the data-intensive nature of neural network algorithms often exceeds the data capacity of regular textile factories.…”

“…The second category centers on the application of diverse evolutionary algorithms, such as genetic algorithms, 15 particle swarm optimization algorithms, 4 emperor butterfly optimization algorithms, 16 fireworks algorithms, 17 differential evolution algorithms and other evolutionary algorithms, 5 to identify the optimal weights and thresholds of the neural networks.…”

Prediction of yarn strength based on an expert weighted neural network optimized by particle swarm optimization

“…Considering that the back propagation (BP) algorithm can optimize the parameters in a neural network, Furferi and Gelli 2 proposed a model based on a feedforward BP ANN to predict the strength of the yarn. Due to the problem of low accuracy of the ANN, Mwasiagi 3 proposed a DE-ELM algorithm combining the differential evolution algorithm (DE) and extreme learning machine (ELM) for the prediction of yarn strength of spun yarn. Considering the role of feature extraction in the convolutional neural network (CNN), for yarn production data with many parameters and a small amount of data, Hu et al.…”