Service robot movement system cloud end fault diagnosis system and method

Abstract

The invention discloses a service robot movement system cloud end fault diagnosis system and method. The service robot movement system cloud end fault diagnosis system comprises a sensor module, a robot controller and a robot fault diagnosis cloud end; the sensor module collects the movement data of a robot in real time; the robot controller is configured to receive the data collected by the sensor module, gather the data and transmit the data to the robot fault diagnosis cloud end through the network; and the robot fault diagnosis cloud end is configured to diagnose the faults of the robot according to the received data and feed the diagnosis result back to the robot controller. A speed encoder and an inertial measurement unit are adopted for data fusion, fault modeling is conducted through a deep studying model, the model is deployed on a cloud end server with high operational capability, and the advantages of high diagnosis real-time performance, high model robustness and high practicability are achieved.

Description

technical field [0001] The invention belongs to the application field of fault diagnosis of mobile robots, and in particular relates to a cloud fault diagnosis system and method for a motion system of a service robot. Background technique [0002] The service robot motion system refers to the whole body composed of motion-related devices, control units and mechanical structures in the service robot, including wheels, motors, encoders, drives, motion controllers, etc. The reliability and safety of the service robot's motion system is the lifeline of the robot, and the fault diagnosis system is of great significance to the robot. The fault diagnosis system can diagnose or predict the fault in advance when the fault occurs or before it occurs, so as to avoid further deterioration of the fault and cause major safety accidents. The traditional service robot motion system fault diagnosis methods have the following methods and disadvantages: [0003] (1) The fault diagnosis metho...

AI Technical Summary

Problems solved by technology

[0003] (1) The fault diagnosis method of fault tree exists. For complex robot systems, it is difficult to establish an intricate fault tree. At the same time, the fault tree can only detect faults with relatively simple logic and obvious phenomena.

[0004] (2) The fault diagnosis method of the expert system needs long-term experience accumulation, and has the disadvantage of low universality

[0005] (3) The fault diagnosis method based on the mathematical model has the disadvantage that it is difficult to model complex high-order nonlinear systems, and the robustness to noise is low

[0006] (4) Traditional fault diagnosis is deployed on the robot itself. Therefore, for data-driven fault diagnosis, the robot itself has the disadvantages of low computing power, complex algorithm models are difficult to deploy, and the calculation speed is slow, resulting in high time lag.

At the same time, if the fault diagnosis controller hardware of the robot itself is damaged, the fault diagnosis system will fail completely.

Images