US 12,092,269 B2
Method for troubleshooting potential safety hazards of compressor in smart gas pipeline network and internet of things system thereof
Zehua Shao, Chengdu (CN); Yong Li, Chengdu (CN); Yuefei Wu, Chengdu (CN); Bin Liu, Chengdu (CN); and Guanghua Huang, Chengdu (CN)
Assigned to CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Chengdu (CN)
Filed by CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Sichuan (CN)
Filed on Jan. 5, 2024, as Appl. No. 18/406,072.
Application 18/406,072 is a continuation of application No. 18/154,016, filed on Jan. 12, 2023, granted, now 11,906,112.
Claims priority of application No. 202211629717.3 (CN), filed on Dec. 19, 2022.
Prior Publication US 2024/0142063 A1, May 2, 2024
Int. Cl. F17D 3/01 (2006.01); F17D 5/00 (2006.01)
CPC F17D 3/01 (2013.01) [F17D 5/005 (2013.01); Y02P 90/02 (2015.11)] 16 Claims
OG exemplary drawing
 
1. A method for troubleshooting potential safety hazards of a compressor in a smart gas pipeline network, wherein the method is implemented based on a smart gas safety management platform of an Internet of Things system for troubleshooting potential safety hazards of a compressor in a smart gas pipeline network, comprising:
performing a purification process on sound data of a gas compressor, and determining a target sound feature, the purification process used to remove background noise in the sound data;
establishing a feature data vector library based on networked data and reference device data, wherein the feature data vector library includes a reference gas data vector, a reference device data vector, a reference sound feature and a reference vibration feature corresponding to the reference gas data vector, and a reference sound feature and a reference vibration feature corresponding to the reference device data vector;
determining a current gas data vector and a current device data vector based on gas data and device data, respectively;
searching the feature data vector library based on the current gas data vector and the current device data vector, and determining a reference sound feature and a reference vibration feature that meet a preset condition as a standard sound feature and a standard vibration feature; and
predicting whether there is a safety hazard in the gas compressor using a hazard model based on the target vibration feature and the standard vibration feature, or based on the target sound feature and the standard sound feature, the hazard model being a machine learning model.