Research On Disease Monitoring Technology Of CRTS? Slab Ballastless Track

CRTS? slab ballastless track is widely used in China's high-speed railway.When CRTS? slab ballastless track is in service for a long time,its track slab structure is prone to such typical diseases as CA mortar void and slab end camber deformation,which seriously affects the stability of the track structure.Therefore,it is necessary to monitor the void length and camber deformation degree of CRTS? slab ballastless track slab,to guide the timely maintenance of track slab after the occurrence of diseases,and to send out real-time alarm information when endangering the traffic safety.At present,the detection of ballastless track disease mainly depends on the method of field manual visual inspection,which is time-consuming and laborious and has poor effect.When the track plate end is arched to make the track irregularity change,the comprehensive inspection train can be found indirectly in the daily maintenance.However,because the track plate initial disease has little change in the track irregularity amplitude,which is far from the daily maintenance standard,it is easy to be ignored by the inspection personnel.Therefore,this paper studies an on-line monitoring technology of track slab diseases in key sections,using angle sensor to obtain the vibration displacement data of track slab,and realizes the recognition of void length and the monitoring of camber degree of track slab based on distributed angle detection.In order to solve the problem of void detection of track slab,a void length recognition algorithm based on depth neural network is proposed.In order to generate the training data of different void length of CA mortar,based on the traditional vehicle rail coupling model,an improved CA mortar layer structure is proposed,and the vibration displacement data of track plate under different void degree are obtained.Then,taking the displacement data of track slab as the index,the CA mortar classification feature database is constructed,and the algorithm of CA mortar void length classification based on LSTM depth neural network is trained.The simulation results show that the algorithm proposed in this paper can identify five levels of void disease,and the recognition accuracy is more than 90%.In order to solve the problem of track slab camber monitoring,this paper proposes a distributed monitoring system based on inclination sensor for ballastless track slab end camber.The system uses Zig Bee technology to build a wireless sensor network,and optimizes the network structure and communication protocol considering the environment along the railway,so that the system has the characteristics of energy saving,accuracy and strong anti-interference ability.In order to verify the effectiveness of the monitoring system,a verification experiment based on the real size track board test-bed was carried out.The experimental results show that the system can give an alarm to the damage of the arch on the end of the track slab and meet the accuracy required by the field use.The system designed in this paper can realize the real-time monitoring of the defects of the track slab CA mortar void and the track slab arch.It can provide technical support for the detection and prevention of the defects of the track slab of CRTS? slab ballastless track,and has high practical value.