基于ARIMA的腐蚀时序数据趋势预测

Corrosion time series data trend prediction based on ARIMA

腐蚀造成的事故严重影响炼化企业生产安全与经济效益。为防止事故发生,企业通常会采取监测技术对设备运行过程的各项参数进行获取与评估。文中基于在线监测探针采集的腐蚀速率数据,建立ARIMA模型,开展腐蚀时序数据趋势预测。首先对腐蚀速率数据进行预处理并判断其稳定性,接着确定ARIMA模型的建模参数,最后采用ARIMA(2,1,5)和ARIMA(1,1,1)2种参数实现了腐蚀速率趋势的快速预测和提前10 d报警,且平均误差为1.4%,为炼化企业优化腐蚀防控提供1种新方法。

Accidents caused by corrosion seriously affect the production safety and economic benefits of refining and chemical enterprises. In order to prevent accidents, enterprises usually adopt monitoring technology to obtain and evaluate the parameters of equipment operation process. Based on the corrosion rate data collected by the on-line monitoring probe, ARIMA model was established to predict the trend of corrosion time series data. Firstly, the corrosion rate data was preprocessed and its stability was determined, and then the modeling parameters of the ARIMA model were determined. Finally, ARIMA(2,1,5) and ARIMA(1,1,1)were used to quickly predict the corrosion rate trend and alarm 10 d in advance, with an average error of 1.4%, which provided a new method for optimizing corrosion prevention and control in refining and chemical enterprises.