首页|基于LSTM神经网络我国印染布产量预测

基于LSTM神经网络我国印染布产量预测

扫码查看
采用性能较优的长短期记忆神经网络模型(LSTM)对我国印染布产量进行预测.结果显示:平均预测误差仅为0.259 1%,比极限学习机的1.018 1%减小76.094 2%,比循环神经网的0.602 0%减小56.960 1%.运用LSTM模型预测2023-2025年我国印染布产量,通过分析,表明这一预测结果有较高的可信度.
Prediction of China's printing and dyeing fabric production based on LSTM
The LSTM model was adopted to predict the production of printed and dyed fabrics in China.The results showed that the average prediction error was only 0.259 1%,a decrease of 76.094 2%compared to the extreme learning machine's 1.018 1%,and a decrease of 56.960 1%compared to the recurrent neural network's 0.602 0%.The LSTM model was used to predict the production of printed and dyed fabrics in China from 2023 to 2025.The analysis shows that this prediction result has high credibility.

long-short term memory(LSTM)printed and dyed fabricproductionprediction

舒服华

展开 >

武汉理工大学继续教育学院(中国)

长短期记忆神经网络模型 印染布 产量 预测

2024

国际纺织导报
东华大学

国际纺织导报

影响因子:0.095
ISSN:1007-6867
年,卷(期):2024.52(4)