Search

Energy saving and environmental protection have become the core development concept of China construction industry. There are still a large number of old urban buildings in Beijing, whose energy consumption far exceeds the current building energy efficiency standards. The energy-saving renovation of these old buildings has been becoming the focus and difficulty of urban building energy-saving. In this paper, a calculation model based on the TNM Decree is proposed to calculate and analyze the energy consumption of heating and domestic hot water supply in winter before and after the renovation of old urban buildings in Beijing. The calculation results show that the thermal insulation performance of building envelope is a key factor affecting the energy consumption of old urban buildings. After the renovation, the energy-saving rate of the old urban buildings completed between 1978 and 1985 can reach 65.53%. The energy-saving rate of the buildings completed between 1986 and 1995 and that between 1996 and 2005 can reach 55.04% and 32.79%, respectively.

As a powerful tool to solve nonlinear problems, artificial neural network method (ANN) gets a wide range of applications in data regression. However, the overfitting often occurs during the ANN training process, which results in high accuracy of correlating the training data but poor prediction performance. At the same time, the principle of k-Nearest Neighbor method (kNN) makes it impossible to make an accurate prediction exceeding the range of the training data, but it can confine the overfitting of ANN. In this work, combining ANN and kNN, a new machine learning method called ANN-kNN combination method (AKC) for thermophysical property prediction of material is proposed. To evaluate the performance of AKC, we take the thermophysical properties of natural gas as an example. The inputs of AKC are temperature, pressure and the components of natural gas, the outputs are the compressibility factor, speed of sound and viscosity. AKC not only overcomes the overfitting problem but also needs less training data than ANN. The average absolute relative deviation of AKC for prediction are 2.5%, which are better than ANN (5.9%) and kNN (19.2%).

Bus rides have become a routine choice for the large population to travel in Beijing. By the end of November 2020, 82.84% of all buses in Beijing had switched to electric vehicles. A solution to the problem of charging a huge number of battery electric buses (BEBs) in urban areas, especially in crowded cities with large populations, has to be found. In the present paper, a calculation model based on the levelized cost of electricity (LCOE) is established for comparison and analysis of the BEB charging. The calculation results show that the hybrid charging mode is economically feasible. Moreover, from the perspectives of optimizing operation shifts and responding to emergency situations, hybrid charging mode is applicable to the current electric bus system. The calculation results also show that the use of BEBs as the main ground public transportation in Beijing can substantially reduce CO2 emissions and save huge fuel costs. Its application is a very wise choice. The analogy calculation on Tongzhou District, the sub center of Beijing which is under construction, shows that the use of BEBs in Tongzhou can reduce CO2 emissions by about 34.6% on average compared with fuel buses. The population is the main influencing factor of analogy calculation.