The thermal characterisation of a building envelope is usually best performed from on site measurements with controlled heating power set points. Occupant-friendly measurement conditions provide on the contrary less informative data. Notwithstanding occupancy, the boundary conditions alone contribute to a greater extent to the energy balance. Non intrusive conditions question therefore the repeatability and relevance of such experiment.This paper proposes an original numerical methodology to assess the repeatability and accuracy of the estimation of an envelope's overall thermalresistance under variable weather conditions. A comprehensive building energy model serves as reference model to produce multiple synthetic datasets. Each is run with a different weather dataset from a single location and serves for the calibration of an appropriate model, which provides a thermal resistance estimate. The estimate's accuracy is then assessed in the light of the particular weather conditions that served for data generation. The originality also lies in the use of stochastically generated weather datasets to perform an uncertaintyand global sensitivity analysis of all estimates with respect to 6 weather variables.The methodology is applied on simulated data from a one-storey house case study serving as reference model. The thermal resistance estimations are inferred from calibrated stochastic RC models. It is found that 11 days are necessary to achieve robust estimations. The large air change rate in the case study explains why the outdoor temperature and the wind speed are found highly influential.

翻译：建筑物封套的热特性通常最好通过有控加热电源设置点的现场测量进行,每个建筑能源综合模型都是制作多个合成数据集的参考模型。每个模型都使用不同的天气数据集运行,用于校准适当的模型,该模型提供热抗药性估计。然后根据为数据生成工作提供的特定天气条件评估估算的准确性。原始数字方法也在于使用随机生成的天气数据集,对6种天气变量的所有估计数进行不确定性和全球敏感性分析。该方法用于模拟一个仓库的案例研究产生的数据,作为参考模型。从测算高温到测温速度模型,从测温到高温度模型。