Collection method for fault analysis data of harbor machine

Abstract

The invention reveals a collection method for fault analysis data of a harbor machine, and the method comprises the following steps: setting a collection time duration t0 before an abnormality and a collection time duration t1 after the abnormality, wherein the abnormality is a time point t when a fault code is detected; setting the sampling period; carrying out the sampling of the operation dataof the harbor machine according to the sampling period; detecting the fault code, and recording the time point t when the fault code is detected; extracting the data from the sampled data from a moment t-t0 to a moment t+t1, and enabling the data to serve as fault collection data; transmitting the fault collection data to a fault analysis server; enabling the fault analysis server to input the fault collection data into the fault analysis model for learning and training, so as to update the fault analysis model; adjusting the collection time duration t0 before the abnormality and the collection time duration t1 after the abnormality according to the updated fault analysis model, and repeatedly carrying out the above process according to the adjusted collection time duration t0 before the abnormality and the adjusted collection time duration t1 after the abnormality.

Description

technical field [0001] The invention relates to the field of port machinery, more specifically, to the technical field of failure analysis of port machinery. Background technique [0002] The operation time of port machinery is very strict, and the loading and unloading operations must be completed within the specified time. If it is overtime, it will affect the shipping schedule and the normal operation of the terminal, causing economic losses to the port operator. Due to the harsh environment of the port and the different working conditions of the machinery in each port, failures are inevitable. Therefore, how to collect the failure data of port machinery becomes particularly important. If enough failure data can be collected, combined with the failure analysis model, with the assistance of artificial intelligence and big data technology, it will be possible to transform from failure-time maintenance to predictive maintenance or maintenance based on equipment status, the...

AI Technical Summary

Problems solved by technology

However, the setting of these early warning values ​​is generally based on experience, lacking certain calculation and theoretical basis, and it is easy to cause omissions. If the important data directly related to the fault is lost, it will not be able to meet the needs of fault diagnosis.

Images