Rail turnout disease detection system based on operating vehicle and rail turnout disease detection method based on operating vehicle

Abstract

The invention discloses a rail turnout disease detection system based on an operating vehicle and a rail turnout disease detection method based on the operating vehicle. The system comprises an acceleration sensor, a signal collection and preprocessing unit and a signal processing unit, wherein the acceleration sensor generates transverse direction and vertical direction acceleration signals of a bogie according to the vibration in the vehicle operation process so as to detect the vibration state of a vehicle body in the vehicle operation state; the signal collection and preprocessing unit collects the transverse direction and vertical direction acceleration signals at the fixed sampling frequency and performs preprocessing to generate signals to be detected at each sampling moment; and the signal processing unit uses an SVM (Support Vector Machine) for recognizing the rail turnout disease according to the signals to be detected. The technical scheme has the advantages that the real-time detection when a train passes through a turnout can be realized; the time limitation is avoided; and the problem that artificial errors easily occur due to manual detection is avoided.

Description

technical field [0001] The invention relates to the field of switch disease detection. More specifically, it relates to a system and method for detecting track turnout defects based on operating vehicles. Background technique [0002] The current research results on vehicle-turnout dynamics at home and abroad are as follows. [0003] Overseas: In the TS7 and MU14 projects of the Swedish government, the research on the relationship between the turnout disease and the low-frequency interaction between the vehicle and the turnout is carried out, see "Wheel / railimpactsatarailwayturnoutcrossing". The Austrian VAE member group headed by Oswald and the German BWG company studied the influence of different curve forms in the turnout area on the wheel-rail system, see "Turnout geometry optimization with dynamics simulation of track and vehicle". Scholars such as Netter in Germany used SIMPACK to simulate the dynamic characteristics of a passenger car passing through a turnout, and ...

AI Technical Summary

Problems solved by technology

The common detection method used by various operating companies is to regularly (nightly) send track maintenance workers to conduct on-site detection of each turnout in the line. This detection method not only takes a long time, but also requires a lot of manpower support. If a disease occurs suddenly, the method of manual detection will lose its effect

For example, using the tip rail close-fitting detector to identify the defect of the tip rail not being close-fitted, and using the manual measurement method to detect the reverse superelevation of the guide curve, this detection method requires a lot of manpower and material resources; it is prone to detection errors caused by human negligence and other reasons ; and because the detection time is fixed and the real-time performance is poor, sudden diseases of the turnout cannot be found in time

Images