High-quality as-is 3D thermal modeling in MEP systems using a deep convolutional network

With the growing need for automated condition monitoring and analysis in existing buildings, significant effort has been spent on the development of three-dimensional (3D) thermal models. However, little attention has been paid to ensuring the quality of these 3D thermal models, which can directly impact the accuracy of condition monitoring and analysis results. This study aims to propose a method to generate a high-quality 3D thermal model for mechanical, electrical, and plumbing (MEP) systems by bridging the quality discrepancy between high-resolution laser scan data and low-resolution thermal images using a deep convolutional neural network. The proposed method consists of two main parts: (1) improving the resolution of thermal images based on a deep convolutional network and (2) generating a high-quality 3D thermal model by mapping improved thermal images. The performance of the thermal image resolution improvement was validated using a dataset consisting of 312 thermal images. The results demonstrated that the quality of the improved thermal images based on a deep convolutional network was higher than conventional bicubic interpolation in terms of root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM). Qualitative analysis of a 3D thermal model utilizing the resolution-improved thermal images was also conducted. This was further qualitatively analyzed to have resulted in improved overall quality of the 3D thermal model. The ability to generate a high-quality 3D thermal model can help auditors to perform automated condition monitoring and analysis in buildings based on objective and accurate data.