Innovative Method to Select Optimal Plugging Materials for Preventing Loss Circulation in Deep Fractured Reservoirs Using Machine Learning

Summary Lost circulation, a critical issue in drilling operations caused by drilling fluid loss into formation fractures, is a significant barrier in the exploration and production of oil, natural gas, and geothermal reservoirs. Effective design of the plugging formula to mitigate such losses is vital for the successful extraction of these resources. To efficiently design the plugging formula, in this paper we determine the key performance parameters of plugging materials based on the formation mechanism of the plugging zone, using them as feature input variables. We then use multitask learning (MTL) to establish a high-precision prediction model for the plugging formula, followed by the development of a mathematical optimization model for selecting performance parameters of the plugging formula, with displacement pressure and cumulative loss volume as the objective functions. An improved particle swarm optimization (PSO) algorithm is used to solve this mathematical model and determine the characteristic parameters of the plugging formula. Based on these parameters, the appropriate types of plugging materials, including bridging materials, fillers, and deformable reinforcement materials, are identified for the formula. The results show that the improved PSO algorithm outperforms the basic PSO algorithm, genetic algorithms, and whale optimization algorithms in solving the mathematical optimization model, with a performance improvement of about 10%. Additionally, sensitivity analysis confirms the model’s robustness, revealing that bridging materials play a critical role in the effectiveness of the plugging formula. As the variety of bridging, filling, and deformable reinforcement materials increases, their displacement pressure improves. More specifically, the analysis explores how the friction coefficient, D90 particle-size distribution, thermostability, compressive strength, and acid solubility of bridging materials affect displacement pressure and cumulative loss volume. Experimental findings validate that the innovative method to select optimal plugging materials for deep fractured reservoirs, leveraging MTL and intelligent optimization, facilitates the swift and effective development of deep fracture plugging strategies. This method not only assures effective fracture plugging but also minimizes material consumption in the formulations, thereby reducing overall material costs. The proposed method provides new novel perspectives and a theoretical foundation for the design of the deep fractured reservoir plugging formula.