The technique of refracturing is an effective method to solve the rapid decline in oil well production caused by factors such as severe reservoir energy loss and fracture failure after the initial hydraulic fracturing of low-permeability reservoirs. The key to designing refracturing lies in establishing a model for evaluating the potential fracturing layers. Based on the geological characteristics of the low-permeability conglomerate reservoir in the Lower Wuerhe area of the Eig District of the Xinjiang Oilfield, this paper studies the influence of different development approaches on the distribution pattern of remaining oil in the reservoir. A coupled model of remaining oil distribution and the in situ stress field is established and discusses the characteristics of the four-dimensional in situ stress field under different development modes. This paper analyzes the influence of geological factors and well network factors on the distribution of residual oil, and analyzes the influence of various factors, such as reservoir properties and injection and extraction parameters, on ground stress. Based on the residual oil distribution and ground stress changes, an evaluation method for screening potential fractured layers in reservoirs with different development modes (water injection development and depletion development) is developed.
Reservoir simulation is an important technique to characterize subsurface fluid flow and to support reservoir development and production optimization. Conventional reservoir modeling requires engineers to extract model-relevant information from heterogeneous data, organize the information into predefined formats, and generate simulator-specific input files through professional software. Constructing and iteratively updating such models can often take months of effort due to the high modeling complexity. Large language models (LLMs) offer a potential alternative by translating modeling requirements into simulator input instructions through natural language modeling instructions. However, proprietary reservoir simulators are poorly represented in public training corpora, and their keyword systems may differ substantially from those of widely documented commercial simulators. This study addresses these challenges using the Compositional Advanced Simulation System (COMPASS), an in-house reservoir simulator for unconventional resources, as the target simulator. The proposed knowledge-enhanced LLM framework combines retrieval-augmented generation (RAG) with schema-constrained tool calling to support well-control instruction generation. On the 50-task RECURRENT benchmark using DeepSeek-V4.1-Flash, the four generation strategies achieved average accuracies of 0.67%, 74%, 98%, and 100% for Strategy I (zero-shot), Strategy II (RAG), Strategy III (schema-constrained tool calling), and Strategy IV (RAG combined with schema-constrained tool calling), respectively. Additional experiments with different base LLMs showed accuracies ranging from 92.0% to 100.0%. These results demonstrate that combining enterprise-domain knowledge retrieval with schema-constrained output generation can substantially improve the reliability of LLM-based generation for proprietary reservoir simulation software.