A Prediction Method of Drilling Loss Probability Based on Naive Bayesian Algorithm
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A Bayesian algorithm and prediction method technology, applied in prediction, computer parts, computing and other directions, can solve the problems of difficult to control leakage, unable to control missing parameters, repeated occurrence and so on.
Active Publication Date: 2021-07-23
SOUTHWEST PETROLEUM UNIV
View PDF0 Cites 0 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
[0005] In order to overcome the insufficiency and limitation of the existing lost circulation prediction methods, which cause the well site technicians to be unable to control the corresponding lost circulation parameters, making the lost circulation difficult to control and occur repeatedly, and enrich the methods of predicting lost circulation by using drilling parameters , the present invention proposes a drilling loss probability prediction method based on naive Bayesian algorithm
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more
Image
Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
example 10
[0056] 1-4) In the embodiment of this description, the drilling loss probability prediction model based on the drilling loss parameters using the Naive Bayesian algorithm is a supervised learning process. In order to avoid the additional error caused by data division and affect the accuracy of the final classification results, attention should be paid to maintaining the consistency of data distribution when dividing data. At the same time, in order to ensure the representativeness of data, the division data is divided into Training set and test set, the above-mentioned preprocessed drilling loss parameter data are randomly stratified and divided into training set and test set according to the preset ratio of 10:1;
[0057] 2) figure 2 It is a flow chart of drilling loss probability prediction based on naive Bayesian algorithm, such as figure 2 As shown, in the specific implementation case of the scheme of the present invention, the drilling data parameters after data collec...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
PUM
Login to view more
Abstract
The invention belongs to the fields of drilling loss prediction and artificial intelligence machine learning, and in particular relates to a drilling loss probability prediction method based on a naive Bayesian algorithm. The method is as follows: extract historical reservoir development data from a reservoir well history database in a certain reservoir development zone and perform preprocessing, create a sample set and a test set, determine characteristic attributes and output category space from the sample data, and according to the sample Collect the data of drilling loss parameters and count the prior probability of each characteristic attribute value, and use the prior probability learning to calculate the conditional probability. The method calculates the corresponding conditional probability to improve the generalization performance of the model, calculates the posterior probability jointly by the prior probability, establishes the naive Bayesian model classifier, uses the verification set for verification, and inputs the real-time drilling parameter data into the model to obtain the corresponding loss probability size.
Description
technical field [0001] The invention belongs to the fields of drilling loss prediction and artificial intelligence machine learning, and in particular relates to a drilling loss probability prediction method based on a naive Bayesian algorithm. Background technique [0002] Lost circulation is a complex and common working condition in the drilling process, which will cause serious harm and economic loss to the drilling industry. During the drilling process, many drilling parameters will affect lost circulation, such as well depth, layer, lithology, weight on bit, torque, speed of penetration, vertical pressure, inlet flow, outlet flow, porosity, permeability, drilling fluid density, drilling Liquid-solid phase content, Young's modulus, bit type, bit size, hook load, etc. The changes of these drilling parameters during the drilling process may make the drilling fluid column pressure greater than the formation rock fracture pressure, thereby forming induced fractures, or reop...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more
Application Information
Patent Timeline
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.