Intelligent oilfield edge computing gateway

Abstract

The invention discloses an intelligent oil field edge computing gateway which comprises a power supply module, a main control module, a data acquisition module, a wireless communication module and a fault identification module. The power supply module is used for supplying power to each sub-module; the main control module is used for receiving, processing and analyzing data of the data acquisitionmodule and the fault identification module, and setting algorithm parameters and control information of the fault identification module; the data acquisition module is used for acquiring data acquired by a plurality of field sensing devices; the fault identification module is used for automatically identifying the fault condition of the oil well based on a deep learning technology; the wireless communication module is used for wirelessly transmitting the fault information to a cloud server. Via the gateway disclosed in the invention, the working state and the working process of the oil well are monitored in real time through the Internet of Things technology, the edge computing technology and the deep learning technology.

Description

technical field [0001] The invention relates to the technical field of edge computing of the Internet of Things, in particular to a data collection and image processing gateway device for smart oil fields. Background technique [0002] In smart oilfields, most of the existing oil extraction machine fault detection is based on the artificial intelligence diagnosis system of the dynamometer diagram based on computer technology and wireless communication technology. According to engineering principles and expert knowledge, it is generally believed that the dynamometer diagrams of pumping wells under typical working conditions have fixed characteristics, such as image 3 shown. At present, the ground dynamometer diagram diagnosis and analysis method is most widely used in my country's oilfields. Most oilfields collect real-time data of suspension point load and suspension point displacement at the work site, so as to draw the ground dynamometer diagram, and further use the artif...

AI Technical Summary

Problems solved by technology

[0004] In the traditional situation, training the artificial intelligence diagnosis system model on the cloud will cause the problem of weak generalization ability of the model

In the smart oilfield, the data sent to the cloud server comes from different oil wells distributed in different regions, and due to the differences in production parameters and working environments of oil wells in different regions, the difference between the dynamometer data of the same fault in wells in different regions There may be a large difference between them, which will eventually lead to an increase in the difficulty of training the neural network model on the cloud server, and will also cause certain model generalization problems.

Images