Multivariate time series prediction of complex systems based on graph neural networks with location embedding graph structure learning

Graph convolutional neural networks (GNNs) have an excellent expression ability for complex systems. However, the smoothing hypothesis based GNNs have certain limitations for complex process industrial systems with high dynamics and noisy environment. In addition, it is difficult to obtain an accurate information about the in-terconnections of sensor networks in manufacturing systems, which brings challenges to the application of GNNs. This paper introduces a graph convolution filter with a serial alternating structure of low-pass filter and high-pass filter to alleviate the problem of node feature loss. Furthermore, we propose a simple and effective method to learn graph structure information during training. This method combines the advantages of graph structure learning based on metric method and direct optimization method. Finally, a spatiotemporal parallel feature extraction framework for multivariate time series prediction is constructed. Experiments are carried out on real industrial datasets, and the results demonstrate the effectiveness of the model.

Automated summary

The paper introduces an improved graph convolution filter and a simple yet effective method for learning graph structure information, constructing a framework for multivariate time series prediction, with experimental results demonstrating the effectiveness of the model.