本文采用加速度变化率评价列车运行的舒适度,应用模糊系统理论提出了3种舒适度评价模型,并实测数据确定了模糊集合的参数。在此基础上,应用集成学习方法将这3种模型的输出集作为列车运行舒适度的综合评价指标。应用北京地铁亦庄线的实测数据对该评价方法进行了验证,结果表明3种模糊模型有较好的一致性,集成学习能增强舒适度评价的精度和鲁棒性。
This paper adopted acceleration rate to evaluate the train ride comfort.By using the Fuzzy System theory,three comfort evaluation models were developed and the parameters of fuzzy sets were determined according to the measured data.Furthermore,the outputs of the three models were integrated by an ensemble learning method to give a comprehensive evaluation index for the ride comfort.The measured data of the Train Operation Control System in Beijing Subway Yizhuang Line were used to validate the models.The results showed that the three fuzzy models had good uniformity and the ensemble learning could enhance accuracy and robustness of the comfort evaluation.