Polypropylene is an important product in the chemical industry and also a raw material for packaging bags, masks, and building boards. The melt index (MI) is a key indicator for evaluating the quality and efficiency of the polypropylene production process. Accurate measurement of the MI is beneficial to increase the polypropylene yield and save energy. The polypropylene production process is characterized by strong nonlinearity, obvious dynamic features, and complex structure, so the current soft sensor methods cannot carry out real-time and accurate soft sensor of the MI. In order to fully mine the complex relationship between variables of temporal data and extract the characteristics of time-series space in chemical production processes, this paper proposes a novel dynamic soft sensor method using an improved Pearson correlation coefficient-based graph neural network (GNN) (Pearson-GNN) method. The adjacency matrix is updated through the correlation coefficient of the data, which is integrated into the graph convolution and time sequence convolution modules of GNN to improve the accuracy of the soft sensing. Finally, the performance of the proposed Pearson-GNN is verified in time-series data soft-sensing task on the public air quality data set and actual polypropylene production processes. Compared with the diffusion concurrent recurrent neural networks (DCRNN), the multivariate time-series forecasting with graph neural networks (MTGNN), the spatiotemporal graph convolutional networks (STGCN), and the GNN based on a fully dynamic adjacency matrix without Pearson correlation updates (Fully GNN), the experimental results show that proposed Pearson-GNN is superior to other methods in terms of the mean absolute percentage error, the root-mean-square error, and mean absolute error.

中文翻译：

---

改进的基于 Pearson 相关系数的图神经网络，用于聚丙烯工业动态软传感器


聚丙烯是化工行业的重要产品，也是包装袋、口罩、建筑板的原料。熔融指数 （MI） 是评估聚丙烯生产过程质量和效率的关键指标。准确测量 MI 有利于提高聚丙烯产量和节省能源。聚丙烯生产过程具有非线性强、动态特征明显、结构复杂等特点，因此目前的软传感器方法无法对 MI 进行实时、准确的软传感器。为了充分挖掘时间数据变量之间的复杂关系，提取化工生产过程中时间序列空间的特点，该文提出了一种采用改进的基于皮尔逊相关系数的图神经网络（GNN）方法（Pearson-GNN）的新型动态软传感器方法。邻接矩阵通过数据的相关系数进行更新，并将其集成到 GNN 的图卷积和时序列卷积模块中，以提高软感知的准确率。最后，在公共空气质量数据集和实际聚丙烯生产过程的时间序列数据软传感任务中验证了所提出的 Pearson-GNN 的性能。 与扩散并发递归神经网络 （DCRNN）、使用图神经网络的多元时间序列预测 （MTGNN）、时空图卷积网络 （STGCN） 和基于无 Pearson 相关更新的全动态邻接矩阵的 GNN （Fully GNN） 相比，实验结果表明，所提出的 Pearson-GNN 在平均绝对百分比误差方面优于其他方法， 均方根误差和平均绝对误差。