Under the background of the new power system and the large-scale integration of new energy sources, the short-circuit current level at substations has been continuously rising, and the traditional “numerical calculation + manual table lookup” mode is unable to balance accuracy and efficiency. This paper builds a mixed integer optimization model for key equipment selection based on short-circuit current constraints, introduces a safety margin coefficient to characterize the stability of equipment, and embeds large language models in the aspects of condition analysis, simulation script generation, and candidate equipment pruning, forming a collaborative process of “short-circuit current calculation – equipment selection – result interpretation”. The example results show that when the absolute error of short-circuit current remains within 0.25 to 0.30 kA, the proposed method can increase the overall safety margin of the entire station by approximately 0.02 to 0.04, reduce equipment costs by approximately 3% to 5%, and the design time for a single example is about 40% to 60% of the traditional process. The research provides a feasible path for the deep integration of large language models with power system simulation and optimization, and has certain engineering significance for promoting the intelligence and collaboration of substation design.
Povzetek: This paper addresses the issue of significant short-circuit rise and high design difficulty in the new power system, and constructs a collaborative framework for short-circuit current calculation and equipment selection. A large language model is introduced to complete condition analysis and script generation. The results show that the current error is 0.25 to 0.30 kA, the safety margin is increased by 0.03, the cost is reduced by 3% to 5%, the design time is reduced from 120 seconds to 55 seconds, and the scheme has significant application value.
