Shaft temperature sensor detecting method and device

Abstract

The embodiment of the invention provides a shaft temperature sensor detecting method and device. The method comprises the steps that if the state of a shaft temperature sensor is normal, the difference between the temperature value at the current time and the temperature reference value at the current time is acquired to acquire the temperature change value at the current time, and whether the temperature reference value of the current time is updated is related to whether the temperature change value of the previous time is greater than a preset hop threshold; if the temperature change valueat the current time is greater than the hop threshold, an abnormal hop occurs; the number of consecutive abnormal hops is counted; and if the number of consecutive abnormal hops is greater than a number threshold, the shaft temperature sensor is faulty. According to the embodiment of the invention, the problem of complex and long-time model constructing of state anomaly detection is overcome, andthe shaft temperature sensor is detected in real time.

Description

technical field [0001] The present invention relates to the technical field of sensor abnormality detection, and more specifically, to a detection method and device of an axle temperature sensor. Background technique [0002] At present, the abnormal detection of shaft temperature is mostly offline detection, which requires a large amount of sample data for model building, which takes a long time and cannot meet the needs of real-time detection of EMU operation. There is a problem that the fault cannot be reported in time and is later than the system false alarm output. It is very easy to affect the operation order of the EMU. At the same time, the above scheme involves a large amount of calculation, and requires a high calculation capability of the axle temperature real-time detection system, which is not suitable for the EMU operating environment platform. Contents of the invention [0003] The present invention provides a detection method and device for an axle tempera...

AI Technical Summary

Problems solved by technology

[0002] At present, the abnormal detection of shaft temperature is mostly offline detection, which requires a large amount of sample data for model building, which takes a long time and cannot meet the needs of real-time detection of EMU operation. There is a problem that the fault cannot be reported in time and is later than the system false alarm output. It is very easy to affect the operation order of the EMU

At the same time, the above scheme involves a large amount of calculation, and requires a high calculation capability of the axle temperature real-time detection system, which is not suitable for the EMU operating environment platform

Images