Rate of penetration (ROP) is the key factor affecting the drilling cycle and cost, and it directly reflects the drilling efficiency. With the increasingly complex field data, the original drilling parameter optimization method can't meet the needs of drilling parameter optimization in the era of big data and artificial intelligence. This paper presents a drilling parameter optimization method based on big data of drilling, which takes machine learning algorithms as a tool. First, field data is pre-processed according to the characteristics of big data of drilling. Then a formation clustering model based on unsupervised learning is established, which takes sonic logging, gamma logging, and density logging data as input. Formation clusters with similar stratum characteristics are decided. Aiming at improving ROP, the formation clusters are input into the ROP model, and the mechanical parameters (weight on bit, revolution per minute) and hydraulic parameters (standpipe pressure, flow rate) are optimized. Taking the Southern Margin block of Xinjiang as an example, the MAPE of prediction of ROP after clustering is decreased from 18.72% to 10.56%. The results of this paper provide a new method to improve drilling efficiency based on big data of drilling.

To address the challenges associated with difficult casing running, limited annular space, and poor cementing quality in the completion of ultra-deep wells, the extreme line casing offers an effective solution over conventional casings. However, due to its smaller size, the joint strength of extreme line casing is reduced, which may cause failure when running in the hole. To address this issue, this study focuses on the CST-ZT Φ139.7 mm × 7.72 mm extreme line casing and employs the elastic-plastic mechanics to establish a comprehensive analysis of the casing joint, taking into account the influence of geometric and material nonlinearities. A finite element model is developed to analyze the forces and deformations of the extreme line casing joint under axial tension and external collapse load. The model investigates the stress distribution of each thread tooth subjected to various tensile forces and external pressures. Additionally, the tensile strength and crushing strength of the extreme line casing joint are determined through both analytical and experimental approaches. The findings reveal that, under axial tensile load, the bearing surface of each thread tooth experiences uneven stress, with relatively high equivalent stress at the root of each thread tooth. The end thread teeth are valuable spots for failure. It is observed that the critical fracture axial load of thread decreases linearly with the increase of thread tooth sequence. Under external pressure, the circumferential stress is highest at the small end of the external thread, leading to yield deformation. The tensile strength of the joint obtained from the finite element model exhibits a relative error of less than 7% compared to the analytical and experimental values, proving the reliability of the finite element model. The tensile strength of the joint is 3091.9 kN. Moreover, in terms of anti-collapse capability, the joints demonstrate higher resistance to collapse compared to the casing body, which is consistent with the test results where the pipe body experiences collapse and failure while the joints remain intact during the experiment. The failure load of the casing body under external collapse pressure is 87.4 MPa. The present study provides a basic understanding of the mechanical strengths of extreme line casing joint.