基于相空间重构和支持向量机的多相催化剂失活预测

Application of phase space reconstruction and support vector regression for forecasting of catalyst deactivation

针对多相催化剂在非定态下的复杂失活机理及活性受多种因素的影响,获取催化剂失活过程的时间序列数据非常有限,因而降低建模效率和预测精度的情况,提出一种基于相空间重构和支持向量机结合的非线性时间序列预测方法.将该方法应用于甲醇氧化羰基化反应中Cu-Si-Al碳酸二甲酯合成催化剂失活过程建模,仿真结果表明预测误差在满意的范围之内,所给出的碳酸二甲酯时空收率的预测值可以为反应器的正确设计和操作以及反应过程的优化提供有效信息.

The catalytic performance of heterogeneous catalysts is dependent on many factors and the mechanism of catalyst deactivation is very complicated.Moreover,the limitation of getting time series data during the deactivation process of catalysts reduces the modeling efficiency and prediction precision.Therefore,a method for nonlinear time series forecasting of the catalyst deactivation based on phase space reconstruction and support vector regression is presented.The method is applied to predict the deactivation process of the Cu-Si-Al based catalysts for the synthesis of dimethyl carbonate（DMC）.The simulation results show that the prediction error of catalyst deactivation model is in a range of tolerance.The prediction space-time yield value of DMC can provide important information for the design and operation of reactors as well as the optimization of the reaction conditions.