Drilling process working condition identification method based on multi-time scale characteristics and neural network

Abstract

The invention provides a drilling process working condition recognition method based on multi-time scale characteristics and a neural network. Drilling process monitoring and drilling process abnormalworking condition recognition are carried out. The method comprises the following steps: dividing logging data into long-time scale section data and short-time scale section data by utilizing a multi-time scale method by analyzing change conditions of the corresponding logging data along with time under abnormal working conditions in a drilling process; a least square method and a self-adaptive threshold method are adopted to extract long-time slow varying characteristics and short-time abrupt change characteristics; a probabilistic neural network method is utilized to establish a drilling process working condition recognition model which is input as well logging data, long-time slowly varying characteristics and short-time abrupt change characteristics at the current moment and output asone of five types of drilling process working condition types of well leakage, drilling tool falling, drill jamming, super-pulling and normal drilling processes. The method has the beneficial effectsthat the drilling cost is reduced, the recognition speed and recognition precision of abnormal working conditions in the drilling process are improved, and a good foundation is laid for safety monitoring and working condition recognition in the geological exploration drilling process.

Description

technical field [0001] The invention relates to the field of intelligent control of the geological exploration drilling process, in particular to a method for identifying working conditions in the drilling process based on multi-time scale features and a neural network. Background technique [0002] my country is rich in deep mineral resources, but deep geological exploration technology is still immature. To ensure national resource and energy security, it is necessary to promote technological innovation in deep geological drilling and establish intelligent decision-making and drilling control methods that meet the needs of complex geological drilling. Safety monitoring and working condition identification in the drilling process are the key to efficient and safe drilling under complex geological conditions. If an abnormality occurs underground and is not dealt with in time, it will easily lead to drilling accidents, which will not only affect the progress of the entire proje...

AI Technical Summary

Problems solved by technology

[0004]Currently, the identification of working conditions in the drilling process is only obtained by analyzing the mud logging data at a single moment, and most of them do not consider the relationship between the changes in the mud logging time series data

Images