Hybrid Model of Machine Learning Method and Empirical Method for Rate of Penetration Prediction Based on Data Similarity

Abstract

The rate of penetration (ROP) is an important indicator affecting the drilling cost and drilling performance. Accurate prediction of the ROP has important guiding significance for increasing the drilling speed and reducing costs. Recently, numerous studies have shown that machine learning techniques are an effective means to accurately predict the ROP. However, in petroleum engineering applications, its robustness and generalization cannot be guaranteed. The traditional empirical model has good robustness and generalization ability. Based on the quantification of data similarity, this paper establishes a hybrid model combining a machine learning method and an empirical method, which combines the high prediction accuracy of the machine learning method with the good robustness and generalization of the empirical method, overcoming the shortcomings of any single model. The AE-ED (the Euclidean Distance between the input data and reconstructed data from the autoencoder model) is defined to measure the data similarity, and according to the data similarity of each new piece of input data, the hybrid model chooses the corresponding single model to calculate. The results show that the hybrid model is better than any single model, and all the evaluation indicators perform better, making it more suitable for the ROP prediction in this field.