State evaluation and fault early warning method, device and equipment for train traction system

Abstract

The invention discloses a state evaluation and fault early warning method for a train traction system. The method comprises the following steps: receiving train operation data sent by an evaluated traction system; associating traction system state information of different vehicles and different frames of the same train, and performing deviation analysis on the operation data according to a predetermined rule; performing state evaluation according to the result of the deviation analysis; feeding back the state evaluation result to the traction system; and displaying fault early warning information corresponding to the result through a display device if the state evaluation result belongs to a preset early warning state. The method can comprehensively, simply and conveniently evaluate the state of the train traction system and give an early warning prompt before a fault, thereby providing effective support for the safety guarantee and system maintenance of the train. The invention also discloses a state evaluation and fault early warning device and equipment of the train traction system and a computer readable storage medium, which have the above beneficial effects.

Description

technical field [0001] The invention relates to the field of rail transit, in particular to a method, device, equipment and a computer-readable storage medium for state evaluation and fault early warning of a train traction system. Background technique [0002] The train traction system is the core part of the train, which is responsible for the mutual conversion between the electric energy and the mechanical energy of the train. In the field of rail transit, the traction system under the multi-coupling condition of vehicle / road / network / environment is the main source of high-frequency train failures, and it is used in applications where the fault tolerance of traction systems for electric locomotives, EMUs, and urban rail vehicles is low , it is very important for the status assessment and fault warning of the traction system. [0003] Existing health assessment methods for vehicle real-time data mainly include empirical knowledge assessment methods and data-driven methods....

AI Technical Summary

Problems solved by technology

The method based on empirical knowledge judges the operating status of the equipment and the normal value range of each parameter. When it exceeds the threshold, it is considered unhealthy; due to the intricate coupling relationship inside the train system, the system has many operating parameters and is synergistic. The health assessment and fault warning of empirical knowledge are very difficult and the accuracy is low

The data-driven method does not require prior knowledge of the object system, and uses data analysis and processing methods to mine the hidden information and make predictions; this method has high requirements for data quality. High-quality real-time data cannot meet the requirements of data-driven methods, and the implementation process of collecting high-quality real-time data itself is very complicated

Images