《计算机应用》唯一官方网站 ›› 0, Vol. ›› Issue (): 79-83.DOI: 10.11772/j.issn.1001-9081.2024030374

• 数据科学与技术 • 上一篇    下一篇

CNN增强型Informer模型在工业时间序列预测中的应用及性能优化

李嘉源1, 王晓东1(), 何启学2   

  1. 1.中国科学院 成都计算机应用研究所,成都 610213
    2.中国科学院大学,北京 100049
  • 收稿日期:2024-04-02 修回日期:2024-06-10 接受日期:2024-06-11 发布日期:2025-01-24 出版日期:2024-12-31
  • 通讯作者: 王晓东
  • 作者简介:李嘉源(1996—),男,安徽阜阳人,硕士研究生,主要研究方向:时间序列预测、深度学习
    王晓东(1973—),男,四川乐山人,高级工程师,硕士,主要研究方向:工业建模、物联网、机器学习
    何启学(1978—),男,四川自贡人,高级工程师,硕士,主要研究方向:工业大数据、智能制造、机器学习。
  • 基金资助:
    四川省重点研发计划项目(2023YFG0113);四川省科技成果转化示范项目(2023ZHCG0005)

Application and performance optimization of CNN enhanced Informer model in industrial time series prediction

Jiayuan LI1, Xiaodong WANG1(), Qixue HE2   

  1. 1.Chengdu Institute of Computer Application,Chinese Academy of Sciences,Chengdu Sichuan 610213,China
    2.University of Chinese Academy of Sciences,Beijing 100049,China
  • Received:2024-04-02 Revised:2024-06-10 Accepted:2024-06-11 Online:2025-01-24 Published:2024-12-31
  • Contact: Xiaodong WANG

摘要:

在实际的工业生产中,Informer模型自身的概率稀疏机制会导致在特征提取时大量时序特性的丢失。为了克服Informer模型的这种缺陷,同时兼顾工业生产中对预测速度和效率的要求,提出一种使用卷积神经网络(CNN)增强的Informer模型。该模型引入短时傅里叶变换(STFT)处理序列获取数据在频域的特征,以进一步减少概率稀疏注意力机制带来的特征丢失,并提高预测准确度。在ETT(Electricity Transformer Temperature)、ECL(Electricity Consumption Load)公开数据集和一个私有数据集上,所提模型与工业领域应用最广泛使用的长短期记忆网络(LSTM)、自回归积分滑动平均(ARIMA)模型等4种模型进行对比实验的结果表明,所提模型的均方误差(MSE)和平均绝对误差(MAE)两项指标均有下降,性能有所提升。

关键词: 时序预测, 工业数据, 卷积神经网络, Informer模型, 短时傅里叶变换

Abstract:

In actual industrial production, Informer model will lose a large number of temporal characteristics during feature extraction due to its probabilistic sparsity mechanism. To address this shortcoming of Informer model and meet the demands for prediction speed and efficiency in industrial production, a Convolutional Neural Network (CNN)-enhanced Informer model was proposed. Short-Time Fourier Transform (STFT) was introduced to process sequence to obtain frequency-domain features of the data, thereby further reducing feature loss caused by probabilistic sparse attention mechanism and improving prediction accuracy. On public datasets, ETT (Electricity Transformer Temperature), ECL (Electricity Consumption Load), as well as one private dataset, comparative experiments were conducted between the proposed model and four models widely used in the industrial field, including Long Short-Term Memory (LSTM) and AutoRegressive Integrated Moving Average (ARIMA) model. Experimental results show that both Mean Squared Error (MSE) and Mean Absolute Error (MAE) of the proposed model are decreased.

Key words: time series prediction, industrial data, Convolutional Neural Network (CNN), Informer model, Short-Term Fourier Transform (STFT)

中图分类号: