基于神经网络的高速铁路钢轨伸缩调节器形变监测技术及模型研究

Research on Deformation Monitoring Technology and Model of High-speed Railway Rail Expansion Regulator Based on Neural Network

高铁工务检养修是保障高铁运营安全、畅通、舒适的重要技术工作。随着我国高速铁路的蓬勃发展和运营里程的不断延展,传统的人工定期巡检式管理手段已无法满足高速铁路工务管理需求,给高速铁路的安全运营也带来了巨大的挑战,亟需采用信息化、大数据等新技术、新手段进行精细化管理。其中,高速铁路钢轨伸缩缝调节器作为铁路轨道组成的重要构件,具有造价高、运维难等特点。因此选取高速铁路钢轨伸缩缝调节器的工务运维作为研究对象,首先采用柔性电感技术设计了高速铁路钢轨伸缩缝调节器实时监测系统,然后基于神经网络算法构建了钢轨伸缩温度-形变二值预测模型,并以某地区钢轨伸缩形变数据作为样本进行试验。实践效果表明:构建预测模型精度达到97.1%,能够有效提高高速铁路钢轨伸缩缝调节器工务运维管理水平和效率,支撑运维决策。

Maintenance and repair of high-speed railway are important technical works to ensure safe,smooth and comfortable operation of high-speed railway.With the vigorous development of high-speed railway and the continuous extension of operating mileage in China,the traditional manual regular inspection management method can no longer meet the needs of high-speed railway maintenance management,which also brings great challenges to the safe operation of high-speed railway.It is urgent to adopt new technologies and new methods such as informatization and big data for fine management.Among them,the rail expansion regulator of high-speed railway,as an important component of the railway track,has the characteristics of high cost and difficult operation and maintenance.Therefore,the maintenance of high-speed railway rail expansion regulator was selected as the research object.First,a real-time monitoring system of high-speed railway rail expansion regulator was designed by using the flexible inductor technology.Then,a binary prediction model of rail expansion temperature-deformation was constructed based on the neural network algorithm,and the rail expansion deformation data in a certain area was taken as a sample for experiments.The practical results show that the accuracy of the prediction model is 97.1%,which can effectively improve the management level and efficiency of highspeed railway rail expansion regulator and support the operation and maintenance decision.