当前位置: X-MOL 学术Artif. Intell. Rev. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A deep granular network with adaptive unequal-length granulation strategy for long-term time series forecasting and its industrial applications
Artificial Intelligence Review ( IF 12.0 ) Pub Date : 2020-02-22 , DOI: 10.1007/s10462-020-09822-9
Qiang Wang , Long Chen , Jun Zhao , Wei Wang

An accurate long-term forecasting for some time series in industrial production is substantially significant for improving the economic efficiency of industry enterprise. In this study, a granular computing (GrC)-based deep learning framework is proposed for long-term time series forecasting, which consists of two stages i.e., the adaptive data granulation and the GrC-based deep model construction. In the first stage, for automatically generating the basic information granules with unequal time span adaptively from data, a stacked sparse auto-encoders granulation network is designed, in which the starting and ending points of a granule are adaptively determined by setting a single neuron in the last hidden layer after multi-layer feature extraction. Then, the second stage sees a definition of a partially overlapping sub-block basis (POSB) matrix to extract the features of these granules, based on which a deep sparse coding feature decomposition-based long-term forecasting model is constructed to transform the unequal-length granules into a product of a POSB matrix and a coefficient matrix layer by layer to serve for forecasting. To verify the effectiveness of the proposed method, two synthetic datasets, two real-world datasets and two practical industrial datasets are employed. The experimental results demonstrate that the proposed method outperforms other data-driven ones on long-term time series forecasting, particularly in an industrial case.

中文翻译:

用于长期时间序列预测的自适应不等长粒度策略的深度粒度网络及其工业应用

对工业生产中的某些时间序列进行准确的长期预测,对于提高工业企业的经济效益具有重要意义。在这项研究中,提出了一种基于粒度计算(GrC)的深度学习框架用于长期时间序列预测,它包括两个阶段,即自适应数据粒度和基于 GrC 的深度模型构建。在第一阶段,为了从数据中自适应地自动生成具有不等时间跨度的基本信息颗粒,设计了一个堆叠稀疏自编码器颗粒网络,其中通过设置单个神经元来自适应地确定一个颗粒的起点和终点。多层特征提取后的最后一个隐藏层。然后,第二阶段定义部分重叠子块基(POSB)矩阵来提取这些颗粒的特征,在此基础上构建基于深度稀疏编码特征分解的长期预测模型对不等长将POSB矩阵和系数矩阵的乘积逐层颗粒化,用于预测。为了验证所提出方法的有效性,使用了两个合成数据集、两个真实世界数据集和两个实际工业数据集。实验结果表明,所提出的方法在长期时间序列预测方面优于其他数据驱动的方法,特别是在工业案例中。在此基础上构建基于深度稀疏编码特征分解的长期预测模型,将不等长的颗粒逐层转化为POSB矩阵和系数矩阵的乘积,用于预测。为了验证所提出方法的有效性,使用了两个合成数据集、两个真实世界数据集和两个实际工业数据集。实验结果表明,所提出的方法在长期时间序列预测方面优于其他数据驱动的方法,特别是在工业案例中。在此基础上构建基于深度稀疏编码特征分解的长期预测模型,将不等长的颗粒逐层转化为POSB矩阵和系数矩阵的乘积,用于预测。为了验证所提出方法的有效性,使用了两个合成数据集、两个真实世界数据集和两个实际工业数据集。实验结果表明,所提出的方法在长期时间序列预测方面优于其他数据驱动的方法,特别是在工业案例中。
更新日期:2020-02-22
down
wechat
bug