A method for evaluation and early warning for train axle properties based on mathematical models

Abstract

The invention provides a method for evaluation and early warning for train axle properties based on mathematical models and belongs to the field of methods for evaluation and early warning of high speed train axle properties. The method comprises the steps of establishing an axle temperature variation mathematical model for axle operation in each of the latest 30 days, and obtaining a group of parameters for evaluating the axle properties with respect to each model; performing smoothing processing on each group of parameters, and performing abrupt change detection and trend detection for the axle properties based on the smoothed property parameters. The qualitative method can assist train maintainers in accurately and reliably judging whether axle temperature alarm signals belong to short-period false alarms capable of self-recovery, and further provide important reference bases for maintenance decisions thereof.

Description

technical field [0001] The invention belongs to the field of evaluation and early warning methods for the axle performance of high-speed train sets, and in particular relates to a method for evaluating and early warning the performance of train axles based on a mathematical model. Background technique [0002] The TCMS (Train Control and Management System) train control and management system of high-speed EMUs has functions such as intelligent distributed information collection, storage, logic judgment, alarm indication and human-computer interaction. In addition to the axle temperature sensor data, other sensors are also used to collect and store the train running speed data and the vehicle external environment temperature data respectively. The axle temperature characteristics of the axle can reflect the performance of the axle to a certain extent, which is very important for judging the nature of the axle fault, but the existing TCMS system does not have the intelligent a...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the lack of quantitative indicators to reflect the overall performance of the axle, and the train axle temperature has many influencing factors, complex causes, and very difficult laws, it is difficult to rely on the maintenance of whether the attribute of the axle temperature alarm signal is a short-term false alarm. Rapid identification and judgment based on the experience of personnel; some axle temperature alarm phenomena that have no obvious fault symptoms temporarily but indicate potential hidden dangers cannot be identified, paid attention to, checked or followed up in a timely and effective manner; The method of summarizing the three data mapping rules of ambient temperature prevents the maintenance personnel from investigating the performance change trend of the axle itself and the sensor components related to the axle temperature, so it is impossible to grasp the change rule of component performance in a timely manner or strictly formulate the technical problem of component replacement plan , the present invention provides a method for evaluating and warning the performance of train axles based on a mathematical model

Images