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.

With the continuous growth in global energy demand, the exploration and development of hydrates has been the focus of increasing attention, and the accurate evaluation of the mechanical properties of hydrate layers has become particularly important. In this study, using a self-developed hydrate sample preparation device and hydrate triaxial seepage test platform, triaxial shear tests were carried out using the in situ synthesis method for hydrate sediment in the laboratory, and the stress–strain curves of hydrate sediment with different levels of saturation were obtained. By analyzing the stress–strain curve, the mechanical parameters of hydrate sediment were calculated and simulated using ABAQUS (2021, Dassault systemes, Vélizy Villacoublay France) finite element software. Several p-y curves were calculated and compared with the simulation results, and the p-y curve correction method of the hydrate layer in a shallow seabed was obtained. It was found that the strength of the hydrate sediment increased with an increase in saturation. At the same time, an increase in confining pressure and a decrease in temperature also increased the strength of hydrate deposits. Through comparison with the existing API (American Petroleum Institute) standard p-y curve, it was found that its strength is low because the existence of the hydrate improves the formation strength.