AI-Enabled Design Diagnostics and Optimisation System for Mould Prevention (AI-DOMP)

2020年Awaab Ishak因长期接触霉菌而在Rochdale Boroughwide住房公寓不幸死亡的后果提高了人们对霉菌构成的健康风险的认识水平。当时，健康从业者正在倡导，解决住房中霉菌和潮湿问题的要求应该与气体安全检查具有同等的法律地位(Brown，2022)。直到今天，还没有出现具体的监管规定，尽管有几个反对者强调了租户和房东在遏制这种威胁方面的作用。平整、住房和社区事务大臣迈克尔·戈夫表示，Awaab的死亡是“一个不可接受的悲剧”，对于住房行业来说，这一事件应该是一个决定性的时刻，以增加对潮湿和霉菌问题的认识和加深理解。为此，需要研究如何开发人工智能(AI)驱动的模拟系统，该系统能够分析和优化不同的建筑设计，以预测潜在的霉菌生长，以建立最佳设计，以避免霉菌生长。因此，该项目提出了一项开发人工智能防霉设计诊断和优化系统(AI-DOMP)的可行性研究。这项研究将探讨开发一种人工智能系统的可能性，该系统可以分析现有和新的建筑设计，以识别容易霉菌生长的区域，并优化这些设计，以减缓这些区域和整个建筑中的霉菌生长。该系统将通过分析设计中容易受潮的区域来支持防霉菌的建筑设计，以便对潮湿和霉菌生长做出预防性决策。拟议的人工智能系统将具有以下两(2)项关键功能：1)**设计分析的人工智能诊断平台：**该平台将允许建筑师、设计师和维护人员将带有材料组件的建筑设计上传到系统中。该系统将分析设计，并识别任何容易受潮和霉菌滋生的区域。根据气流、湿度和热性能水平，确定的霉菌或潮湿易发区域将被分为三个主要类别(即重度、中度和轻度)。2)**启用人工智能的设计优化和决策支持平台：**这将执行设计优化，以达到防止建筑物内霉菌生长的性能水平。然后，这将成为新建和/或翻新现有建筑的设计决策过程的一部分。

The aftermath of the tragic death of Awaab Ishak because of prolonged exposure to mould in Rochdale Boroughwide Housing flats in 2020 increases the level of awareness of the health risks posed by mould. At the time, health practitioners were advocating that the requirements to address mould and dampness in housing should be given the same legal standing as gas safety checks (Brown, 2022). Till today, no specific regulation has emerged even though, there are several adversaries highlighting the roles of tenants and landlords in curbing this menace. Michael Gove, the levelling up, housing and communities secretary, said Awaab's death was "an unacceptable tragedy" and that the incident should be a defining moment for the housing sector in increasing knowledge and deepening understanding surrounding the issue of dampness and mould.To this effect, research on how to develop Artificial intelligence (AI)-powered simulation system that is capable of analysing and optimising different building designs to predict potential mould growth is needed to establish the best design to avoid mould growth. As such, this project proposed a feasibility study for the development of an AI-enabled design diagnostics and optimisation system for mould prevention (AI-DOMP). The study will look at the possibility of developing an AI-enabled system that can analyse existing and new building designs to identify areas prone to mould growth and optimise such designs to mitigate the growth of mould in the areas and the whole building. The system will support building design for mould prevention using analysis of moisture-prone areas within the design to make preventive decisions on damp and mould growth. The proposed AI-enabled system will have two (2) key functionalities as follows:1) **AI-enabled diagnostic platform for design analytics:** this platform will allow architects, designers, and maintenance officers to upload architectural designs with material components onto the system. The system will analyse the design and identify any area that is prone to dampness and mould growth. The identified mould or dampness-prone area will be classified into three main categories (i.e., Severe, Moderate and Mild) using air flow, humidity, and thermal performance level.2) **AI-enabled design optimisation and decision support platform:** this will perform design optimisation to achieve a performance level that will prevent mould growth in the building. This will then form part of the design decision-making process for new builds and/or refurbishment of existing buildings.