Drill bit performance evaluation and model selection method

Abstract

The invention provides a drill bit performance evaluation and model selection method, and the method comprises the following steps: acquiring performance parameters of various drill bits, and constructing a training set; calculating a correlation coefficient between data in the performance parameters of each drill bit through the training set; based on the correlation coefficient, determining the contribution rate of each data in the performance parameters; determining principal component data in the data of the performance parameters based on the contribution rate; and obtaining drill bit performance parameters based on the principal component data. According to the drill bit performance evaluation and model selection method, the principal component data used for analyzing the drill bit performance is determined based on the correlation coefficient and the contribution rate, the collected performance parameter data can be screened and processed, the serious correlation between the original data is eliminated, and the drill bit performance analysis is more accurate.

Description

technical field [0001] The invention relates to the field of drilling, in particular to a method for evaluating and selecting the performance of a drill bit. Background technique [0002] Reasonable selection of drill bits is of great significance to both safe drilling and reducing the total cost of drilling. Drill bit performance evaluation is an important part of drill bit selection, and the quality of the evaluation method directly affects the rationality of the drill bit selection results. Predecessors have done a lot of research on the performance evaluation of drill bits, and put forward a variety of evaluation methods, such as: per-meter drilling cost method, specific energy method, fuzzy comprehensive evaluation method, gray correlation analysis method, attribute hierarchy analysis method, neural network method, Stratigraphic comprehensive coefficient method, etc. These methods mostly use several indicators such as drill footage, drill life, ROP, and drill cost as ...

AI Technical Summary

Problems solved by technology

However, each bit performance evaluation index does not exist independently, but there are intricate correlations

In the evaluation process, the correlation between the indicators will cause the evaluation information to overlap and interfere with each other, resulting in inaccurate evaluation and selection methods of drill bit performance in the current technology, and low referenceability

Images