[目的]地铁折返道岔动作频繁且工况复杂,很容易进入超负荷动作从而引发卡阻等机械故障,对此提出一种短时动作负荷预测及超负荷预警评估方法.[方法]围绕地铁道岔短时动作超负荷预警展开研究,阐述道岔短时状态预警评估方法.基于提出的多描述加权预测机以及自适应核密度估计等方法,描述如何实现动作负荷的区间预测以及预警评估指标的计算,并说明了预警评估流程.据此建立动作超负荷预警应用方案,并依托武汉地铁道岔动作数据进行实证测试.[结果及结论]首先,实时连续地采集道岔功率曲线特征点,计算均方根值得到道岔动作负荷特征序列作为预测输入;然后,设计多描述互补预测机制,并采用ELM(极限学习机)作为基预测器,建立多描述互补预测机进行短时动作负荷特征多步范围预测,构成预测特征集;最后,以预测特征集元素为样本,基于自适应核密度估计方法计算预测时段道岔动作负荷特征的概率密度函数和整体取值置信区间,并结合历史负荷特征取值置信区间定义预测时段的动作超负荷度作为预警评估指标.实证测试结果显示:对于故障前负荷特征数据,预测估计的置信区间覆盖率可达94.2%,且置信区间宽度基本契合实际值区间宽度变化;当预警评估门限为0.63时,各测试案例均能在道岔故障前第4~9次动作时成功发出预警.测试结果验证了超负荷预警方法的有效性.
[Objective]Metro turnback turnouts undergo fre-quent movements and complex working conditions,making them prone to overload actions that lead to mechanical failures such as jamming and blockage.A method for predicting short-term action loads and assessing overload early-warnings is pro-posed.[Method]Focusing on metro turnout short-term action overload early-warning,research is carried out expounding the assessment method for turnout short-term state early-warnings.Utilizing the proposed multi-description weighted prediction mechanism and adaptive kernel density estimation,the ap-proach to achieve interval prediction of action loads and the cal-culation of early-warning assessment indicators are described,and the early-warning assessment process is outlined.Based on this,an application plan for action overload early-warning is es-tablished and empirically tested using turnout action data from Wuhan Metro.[Result & Conclusion]First,real-time con-tinuous collection of turnout power curve characteristic points is conducted,and the root mean square value is calculated to ob-tain the characteristic sequence of turnout action loads as the in-put for prediction.Then,a multi-description complementary prediction mechanism is designed,using ELM(extreme learn-ing machine)as the base predictor to establish a multi-descrip-tion complementary prediction machine to carry out multi-step range prediction of short-term action load characteristics,form-ing a prediction feature set.Lastly,taking the elements of the prediction feature set as samples,the probability density func-tion and the overall value confidence interval of the turnout ac-tion load characteristics during the prediction period is calculat-ed using an adaptive kernel density estimation method.Combi-ning this with the confidence interval of historical load charac-teristics,the action overload degree during the prediction peri-od is defined as the early-warning assessment indicator.Empir-ical test results show that for pre-fault load characteristic data,the coverage rate of the estimated confidence interval by predic-tion reaches 94.2%,and the confidence interval width general-ly matches the actual value interval width changes.When the early-warning assessment threshold is set at 0.63,all test cases can successfully issue early-warnings during the 4th to 9th ac-tions before turnout faults occur.The test results validate the effectiveness of the overload early-warning method.