Artificial intelligence empowering museum space layout design: Insights from China

Area of Science:

• Architecture
• Artificial Intelligence
• Urban Planning

Background:

• Traditional museum exhibition space design faces limitations in innovation and efficiency.
• Floor plan layout is crucial for museum circulation and spatial form.
• Artificial intelligence offers promising solutions for complex design challenges.

Purpose of the Study:

• To explore the application of artificial intelligence, specifically the conditional generative adversarial network (CGAN) model, in assisting the space design of urban cultural museum exhibition halls.
• To introduce the CGAN model's superiority over traditional methods for exhibition hall design.
• To provide a novel method for generating innovative and practical exhibition hall floor plans.

Main Methods:

• The study details the principles and training process of the CGAN model.
• The CGAN model was trained on 100 floor plans of urban cultural museum exhibition halls.
• The model's ability to generate new floor plan designs was evaluated.

Main Results:

• The CGAN model successfully learned from existing floor plans to generate novel exhibition hall designs.
• The AI-assisted design process demonstrated the potential to significantly shorten design cycles and improve efficiency.
• Generated designs were diverse and personalized, catering to various needs and scenarios.

Conclusions:

• The CGAN model offers an effective approach to enhance the innovation and practicality of urban cultural museum exhibition hall design.
• This AI integration streamlines design processes, offering diverse and personalized spatial solutions.
• The findings provide a valuable reference for AI applications in various design fields, including office, residential, and landscape spaces.