【摘要】 为建立稳定可靠的分解炉温度预测模型,结合与分解炉温度密切相关的几个主要运行参数,提出一种粒子群参数优化的支持向量回归机算法(PSO-SVR),并在粒子群算法中引入自适应惯性权重的思想,构建出分解炉温度预测模型。与未改进的模型进行仿真对比实验,实验结果表明,该IPSO-SVR模型具有较佳的预测能力,预测相关系数达到0.707 5,温度预测误差绝对值不超过7℃,误差率在0.8%以内。更多还原

【Abstract】 In order to establish a stable and reliable temperature prediction model for the decomposing furnace,in combination with several main operating parameters closely related to the decomposing furnace temperature,a particle swarm optimization based support vector regression(PSO-SVR)machine algorithm is proposed. The thought of adaptive inertia weight is introduced into the particle swarm optimization algorithm to construct the decomposing furnace temperature prediction model. The model is compared with the unimproved one by means of simulation experiment. The experimental results show that the IPSOSVR model has better forecasting ability,the correlation coefficient reached to 0.707 5,the temperature prediction error absolute value is less than 7 ℃,and the error rate is within 0.8%.更多还原