Department of Art, Anhui Jianzhu University, Hefei, AnHui 230041, China.
Comput Intell Neurosci. 2022 Apr 22;2022:3667187. doi: 10.1155/2022/3667187. eCollection 2022.
With the continuous development of the field of building optimization, more and more optimization methods have sprung up, among which there are many kinds of intelligent optimization algorithms. This kind of intelligent optimization algorithm usually relies on the traditional building performance simulation method to obtain the building performance index for optimization. However, intelligent optimization algorithms generally require large-scale calculations. At the same time, the time required for building performance simulation is often limited by the complexity of building models and the configuration of computers, which leads to a long time for performance optimization, which cannot give efficient and accurate feedback to designers in engineering. Building performance optimization methods based on intelligent optimization algorithms are mainly used in scientific research and are difficult to put into practical projects. Therefore, this paper builds an accurate and efficient platform for building performance prediction and optimization to help designers make decisions combined with BP neural network and the SPEA-II multiobjective optimization algorithm. Besides, the optimization results of the case are quantitatively and qualitatively analyzed and presented in visual form based on the BP neural network prediction model. Quantitative analysis includes the evolution process of solution set, convergence process, and comprehensive quality evaluation of solution set. Qualitative analysis includes Pareto frontier and optimal architectural scheme analysis. Finally, the conclusion shows that the platform prediction and optimization can give accurate and reliable optimal solution, and the optimal building scheme is reasonable and has high engineering application value.
随着建筑优化领域的不断发展，涌现出越来越多的优化方法，其中包括许多种智能优化算法。这种智能优化算法通常依赖于传统的建筑性能模拟方法来获取建筑性能指标以进行优化。然而，智能优化算法通常需要大规模的计算，同时，建筑性能模拟所需的时间通常受到建筑模型的复杂性和计算机配置的限制，这导致性能优化的时间很长，无法在工程中为设计师提供高效和准确的反馈。基于智能优化算法的建筑性能优化方法主要用于科学研究，难以应用于实际项目。因此，本文结合 BP 神经网络和 SPEA-II 多目标优化算法，构建了一个准确高效的建筑性能预测和优化平台，以帮助设计师做出决策。此外，基于 BP 神经网络预测模型，以可视化的形式对案例的优化结果进行定量和定性分析。定量分析包括解集的演化过程、收敛过程和解集的综合质量评价。定性分析包括 Pareto 前沿和最优建筑方案分析。最后，结论表明，该平台的预测和优化可以提供准确可靠的最优解，最优建筑方案合理，具有很高的工程应用价值。
