AGV online fault prediction system and method based on Kalman filtering

Abstract

The invention discloses an AGV online fault prediction system based on Kalman filtering, and the system comprises a current sensor which is used for reading the current real-time data of an AGV, adding a corresponding timestamp and a device ID to the current data, and uploading the current data to a local server; and uploading the data to an industrial Internet of Things big data analysis center through the industrial Internet of Things gateway to predict the running current of the AGV and predict the fault state of the AGV according to the predicted current data. The method has the advantages that the current data of the AGV is collected in real time, the current data of the AGV at the future moment is predicted according to the current data, the future fault state of the AGV is judged according to the predicted current result, fault prediction is given more reasonably and reliably, and the prediction result is more accurate and reasonable.

Description

technical field [0001] The present invention relates to the field of AGV trolley fault management, in particular to an AGV online fault prediction system and method based on Kalman filtering Background technique [0002] In the prior art, the online fault prediction of AGV cars needs to conduct offline inspections of the entire fleet in turn according to the specified maintenance plan. Since the service life of the AGV car’s own bearings and other components fluctuates greatly, regular inspections not only need to consume a lot of time and money, but also affect AGV operating efficiency. There is also no way to realize real-time prediction of failures, prepare maintenance parts inventory in advance and on demand, and improve production efficiency. [0003] At present, there are many fault prediction methods based on the vibration signal of the trolley on the market, but most of them are applicable to fixed working conditions. In some complex and variable working conditions,...

AI Technical Summary

Problems solved by technology

[0003] At present, there are many fault prediction methods based on the vibration signal of the trolley on the market, but most of them are applicable to fixed working conditions. In some complex and variable working conditions, the fault prediction effect is often not very ideal.

AGV is often used as a handling tool in complex situations. Its vibration signal is often doped with a lot of background noise, which brings great interference to signal analysis.

Images