【摘要】 用麻雀搜索算法优化的深度极限学习机(SSA-DELM)构建柴油车NO_x排放预测模型，对柴油车低速、中速和高速状态下的NO_x排放进行预测，并将此模型性能与深度极限学习机(DELM)模型性能进行对比分析。结果表明：SSA-DELM模型的预测效果较好，在低速、中速、高速状态下该模型平均绝对百分比误差MAPE分别为0.061 0、0.044 9、0.039 1;在低速、中速、高速状态下SSA-DELM模型的性能评价指标比DELM模型性能评价指标分别优约23%、44%、11%。更多还原

【Abstract】 A deep extreme learning machine(SSA-DELM)optimized by Sparrow search algorithm was used to construct a NO_x emission prediction model for diesel vehicles to predict NO_x emission of diesel vehicles at low, medium and high speeds. The performance of this model was compared with that of deep extreme learning machine(DELM) model. The results showed that SSA-DELM model had good prediction effect, with a mean absolute percentage error MAPE of 0.061 0, 0.044 9 and 0.039 1 at low, medium and high speeds, respectively. The performance evaluation indexes of SSA-DELM model were about 23%, 44% and 11% better than those of DELM model at low, medium and high speeds, respectively.更多还原