河南科技大学学报（自然科学版）2025，Vol.46Issue(2)：48-58,11.DOI:10.15926/j.cnki.issn1672-6871.2025.02.006
基于LSTM-MHKAN的离散制造业物料需求预测方法研究
Research on Material Demand Forecasting Method for Discrete Manufacturing Industry Based on LSTM-MHKAN
摘要
Abstract
In industrial production,material demand is influenced by a myriad of factors,exhibiting highly complex and dynamic characteristics.These dynamic features include nonlinear relationships,short-term fluctuations,and potential long-term trends,which pose significant challenges to traditional forecasting methods.To address this issue,this study proposes an innovative material demand forecasting method,LSTM-MHKAN,which integrates Long Short-Term Memory networks(LSTM),Kolmogorov-Arnold Networks(KAN),and Multi-Head Attention(MHA)mechanisms.The method optimizes the forecasting process in three key steps.First,LSTM is utilized to capture temporal dependencies within the material demand data,identifying short-term variations and adjusting model parameters to accommodate dynamic fluctuations.Second,MHA is introduced to weight the LSTM outputs,enhancing the model's sensitivity to critical demand fluctuations.Finally,the KAN algorithm is applied to model the weighted attention outputs,capturing nonlinear relationships and adaptively forecasting future demand.Experimental results show that,compared to traditional forecasting algorithms,LSTM-MHKAN effectively reduces mean absolute error and mean absolute error,while improving R-Square.These results validate the effectiveness of LSTM-MHKAN in discrete manufacturing material demand prediction,providing strong decision support for cost reduction in the manufacturing industry.关键词
物料预测/LSTM神经网络/Multi Head Attention/Kolmogorov-Arnold网络/时间序列预测Key words
Kolmogorov-Arnold network/long short-term memory/material demand forecasting/multi-head attention/time series forecasting分类
计算机与自动化引用本文复制引用
吴小芳,成益盈,杨美怡,杨磊..基于LSTM-MHKAN的离散制造业物料需求预测方法研究[J].河南科技大学学报（自然科学版）,2025,46(2):48-58,11.基金项目
国家自然科学基金项目(61976243) （61976243）
河南省重点研发专项项目(231111222600) （231111222600）
