Intelligent monitoring method and device for liquid level of oil and gas well

Abstract

The invention relates to the field of artificial intelligence, in particular to an oil and gas well liquid level intelligent monitoring method and device. Characteristic data in the oil and gas well in the current time period are collected; calculating the abnormal degree of the feature data at each moment; calculating the transmission urgent degree of the feature data; grading the feature data in the current time period, and calculating an adjustment coefficient of the feature data of each grade; constructing an adjustment coefficient sequence of each level of feature data; performing Huffman coding according to the adjustment coefficient sequence of the feature data of each level in the current time period, correcting the duration of the next acquisition time period to obtain a coding result of each time period, and transmitting the coding result; and decoding the coding result to obtain oil and gas well characteristic data, and regulating and controlling oil and gas well parameters according to the abnormal degree of the characteristic data. According to the method, the problem that the abnormal data is not the shortest code value in the traditional Huffman coding is solved by calculating the adjustment coefficient, and the rapid and accurate transmission of the abnormal data can be realized.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a method and device for intelligent monitoring of liquid level in oil and gas wells. Background technique [0002] Oil and gas wells are affected by flow pressure drop during the production process, and the output and flow rate at different positions are quite different; due to the large amount of fluid output in the high-permeability section, the output inrush effect is particularly obvious, and the resulting uneven profile, Once it encounters water or gas, it is easy to cause coning, which leads to the obstruction of fluid outflow in some liquid-producing sections, and the production of oil and gas wells will be greatly reduced. It has also been continuously updated. At this stage, there has been a flow regulating water control screen that can automatically adjust the inflow resistance according to the formation liquid production situation. With the development of flow r...

AI Technical Summary

Problems solved by technology

[0005] The invention provides an intelligent monitoring method and device for oil and gas well liquid level to solve the existing problems, including collecting characteristic data of the current time period in the oil and gas well; calculating the degree of abnormality of the characteristic data at each time; calculating the urgency of transmission of the characteristic data ; Classify the feature data in the current time period, calculate the adjustment coefficient of each level of feature data; construct the adjustment coefficient sequence of each level of feature data; perform Hough according to the adjustment coefficient sequence of each level of feature data in the current time period Mann coding, correct the duration of the next acquisition time period, obtain the coding result of each time period, and transmit the coding result; decode the coding result, get the characteristic data of oil and gas wells, and analyze the oil and gas wells according to the abnormal degree of the characteristic data parameters to regulate

[0006] According to the technical means proposed by the present invention, the data volume of adaptive data transmission is obtained through the abnormality degree of the characteristic data collected in the oil and gas well, and the problem that the abnormal data in the traditional Huffman coding is not the shortest code value is solved by calculating the adjustment coefficient, thereby To achieve the purpose of fast and accurate transmission of abnormal data, and then this purpose can make the control module more efficient when adjusting the parameters of the flow control and water control screen, and prevent the best control time from being missed

Images