ANN Applications in Automatic Fire Sprinkler Head Calculation for Car Parking Basements: A Comprehensive Review

manually often involves repetitive tasks, high workloads, and the risk of human error. To address this, the present study proposes an intelligent framework that automates the sprinkler layout design process. A dataset of 60 existing sprinkler drawings was used to train a ANN (Artificial Neural Network). Once trained, the model was able to automatically generate sprinkler layouts for new or irregular floorplans, achieving 99.5% coverage of the required protection area. Notably, the ANN-designed layouts used about 13% fewer sprinkler heads compared Fire sprinkler systems are a standard safety feature in modern buildings, but preparing their layouts to those planned by professional engineers, while still complying with relevant codes. This approach not only ensures safety compliance but also improves efficiency—reducing drawing preparation time by nearly 76% and lowering costs by optimizing the number of sprinklers required [1]. This study explores the use of artificial neural networks (ANN) to automatically generate sprinkler system layouts for complex and irregular floorplans. By learning from a dataset of existing designs, the ANN framework demonstrates the ability to produce code-compliant layouts with improved efficiency and optimized resource usage compared to traditional methods. The findings highlight the potential of intelligent design tools to enhance accuracy, reduce workload, and support cost-effective fire protection solutions in modern buildings.