US 11,860,978 B2
Methods and systems for detecting detection devices located at energy metering points of natural gas
Zehua Shao, Chengdu (CN); Haitang Xiang, Chengdu (CN); Yaqiang Quan, Chengdu (CN); and Bin Liu, Chengdu (CN)
Assigned to CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Chengdu (CN)
Filed by CHENGDU QINCHUAN IOT TECHNOLOGY CO., LTD., Sichuan (CN)
Filed on Dec. 4, 2022, as Appl. No. 18/061,474.
Application 18/061,474 is a continuation of application No. 17/649,343, filed on Jan. 28, 2022, granted, now 11,562,182.
Claims priority of application No. 202110155161.8 (CN), filed on Feb. 4, 2021; and application No. 202210045109.1 (CN), filed on Jan. 14, 2022.
Prior Publication US 2023/0098183 A1, Mar. 30, 2023
Int. Cl. G06F 18/2413 (2023.01); G06F 18/23 (2023.01); G06F 11/30 (2006.01)
CPC G06F 18/2413 (2023.01) [G06F 11/3089 (2013.01); G06F 18/23 (2023.01)] 13 Claims
OG exemplary drawing
 
1. An early warning method for a detection device located at an energy metering point of natural gas, comprising:
obtaining a first detection data set collected by the detection device located at the energy metering point of the natural gas, wherein the first detection data set includes sub detection data respectively collected by at least two data detection units of the detection device;
determining a first cluster center set through clustering a first historical detection data set;
determining a first vector corresponding to the first detection data set based on the first detection data set;
determining a first target cluster center based on the first vector and the first cluster center set; and
determining whether the detection device is abnormal based on a distance between the first vector and the first target cluster center;
in response to determining that the detection device is abnormal, for each of the sub detection data in the first detection data set,
obtaining a second vector through removing an element corresponding to the sub detection data from the first vector;
obtaining a second target clustering center through removing an element corresponding to the sub detection data from the first target clustering center; and
determining whether the data detection unit corresponding to the sub detection data is an abnormal data detection unit based on a second distance between the second vector and the second target clustering center.