Search

This paper contains an overview of intelligent heating based on the investigation and analysis of campus buildings of Harbin Institute of Technology. Indoor thermal environment and energy consumption of the Cheku building were simulated under six working conditions in the cold region climate conditions. Based on the calculation outcome of the Cheku building, the energy-saving rate of the Campus I, the Campus II, and the Science Park in heating season are calculated. Results show that the low-temperature heating at night during the semester season can reduce the energy consumption by 5.20%. Low-temperature heating in winter vacation reduced energy consumption by 17.01%. During the semester and winter vacation, low-temperature heating at night can reduce energy consumption by 10.21%. The research results provide a reference for the application of energy conservation and intelligent heating in campus buildings.

The present generation of district heating (DH) technologies will have to be further developed into the 4th generation to fulfil the important role in future smart energy systems. At present, automatic meter reading systems have been installed in DH systems. These systems make hourly or even minutely meter readings available at low cost. However, the sheer quantity and complex of the data poses a challenge at various levels for traditional data analysis approaches. Data mining is a promising technology and is used to automatically extract valuable knowledge hidden in large amounts of data. To investigate the potential application of descriptive data mining techniques in DH systems, this study proposes a method based on descriptive data mining to improve the energy performance of DH substations. The proposed method consists of five steps: data cleaning, data transformation, cluster analysis, association analysis, and interpretation/evaluation. Data cleaning and transformation are implemented to improve data quality and transform data into forms that are appropriate for mining. Cluster analysis is performed to identify distinct operating patterns of substations. Based on each pattern, association analysis is then adopted to discover the unsuspected knowledge in the form of rules. Interpretation/evaluation is performed to select and interpret potentially useful rules. To demonstrate its applicability, the proposed method is used to analyze the datasets obtained from an automatic meter reading system at two substations in the DH system in Changchun, China. This application reveals that the method can effectively extract potentially useful knowledge and thereby provide essential guidance for the fault detection and operation optimization of DH substations.

This study proposes a machine learning-based leakage fault detection (LFD) method that locates leakage faults using variation rates of observation data from installed flowmeters and pressure sensors. In the proposed LFD method, a delayed alert triggering algorithm periodically checks the time series of make-up flow rate to identify if the network leaks. When a district heating system is in normal conditions, a hydraulic simulation model built based on the results of impedance identification is used to simulate all possible leakage faults in the network, and the resulting change rates of observation data constitute a leakage data set. An LFD model is then trained using the leakage data set. When the delayed alert triggering algorithm sends a leakage signal, a variation rate vector of observations of this leakage condition is collected. According to the vector, the LFD model can output the name of the leakage pipe. The proposed LFD method is validated in a case study, where the mean values of accuracy and macro-F1 score of the LFD results are 85.85% and 0.99786, respectively. The results show that the proposed LFD method provides a feasible and convenient solution for heat providers to timely and accurately detect leakage faults in networks.

Predicting next-day heat load curves is essential to guarantee sufficient heat supply and optimal operation of district heat systems (DHSs). Existing studies have mainly investigated one-step ahead forecasting methods, which can predict a single value at a future time step. To predict heat load curves, multi-step ahead forecasting methods are needed. This study proposes a machine learning-based framework for multi-step ahead DHS heat load forecasting. Specifically, support vector regression, deep neural network, and extreme gradient boosting (XGBoost) are respectively used as the base learner to develop forecasting models. Two multi-step ahead forecasting methods, i.e. direct strategy and recursive strategy, adopt the learnt models to generate predictions. A DHS in China is used as the case study to comprehensively assess the performance of these two forecasting strategies. Recursive strategy using the XGBoost-based forecasting model can achieve the most accurate and stable predictions with a value of 10.52% for the coefficient of variation of root mean square error. Furthermore, the modeling process of recursive strategy is much more convenient than that of direct strategy. The research shows that the recursive strategy is a better solution to multi-step ahead forecasting than the direct strategy with respect to accuracy, prediction stability, and modeling process.

A series of experiments were carried out in Harbin, a typical city of the severe cold climate zone of China under real transient outdoor conditions to investigate thermal performance, color effect and energy savings of a building-integrated solar air heating system based on unglazed transpired collectors (UTCs). The average efficiency of black UTC was 77.64% and 68.92% under high and low air flow rate respectively, which are higher than most glazed flat-plate collectors. Collector's surface color had an effect on its thermal performance. However, the thermal efficiency of colored UTC was still competitive, and therefore it is feasible to use colored UTC on building facade for esthetic reasons. Design heating load of a reference building in Harbin can be reduced by 6.4% due to reduced wall loss with the application of UTC. For a first cost less than 200 $/m2, it is economically viable to use UTC as an energy efficiency measure in Harbin with net present value of 333 $/m2 and payback time of 10.5 years. With better coordination with architectural design at early stage in a project, this building-integrated solar air heating system can be both esthetically and technically viable in cold climate of China.

As the heat flux sensor calibration`s using conditions and the conditions of demarcate the sensor is inconsistent coefficient C,it would results in large measurement errors when using Heat flow meter to detect the heat transfer coefficient of the wall. This Article is research on the methods that applicate the hot-box to demarcate the heat flux sensor calibration coefficients C. The results show that using flat tests to calibrate the heat flux sensor`s coefficient C is 12.2%∼18.9% smaller than applicating the protective box. Utilization protective box to calibrate heat flow meter is feasible,and the methods is simple, high precision, convenient and quick.

An experimental rig was set up to test the thermal performance of a solar air heating system based on an unglazed transpired collector of 2.5 m2. The experiment was carried out at Harbin Institute of Technology in the city of Harbin, which is located in northeastern China, at latitude 45°41′ N and longitude 126°37′ E. The tests were spread over a number of days, in which the 4-day experimental data within the period were selected as the sample for analysis. Experimental results show that solar collector’s surface temperature and exit air temperature increase with increasing solar irradiation. The influence of ambient temperature on surface temperature and exit temperature is negligible. Temperature rise decreases with increasing air flow rate, while collector efficiency increases with increasing air flow rate. For an air flow rate of 100 m3/h in Test 1, the average air temperature rise and collector efficiency were 28.86°C and 72% respectively; for an air flow rate of 235 m3/h in Test 2, the average air temperature rise and collector efficiency were 11.52°C and 78% respectively. Higher airflow rate tends to operate the collector at lower surface temperature, which results in lower overall heat losses from the collector to the surroundings, therefore increasing airflow rate reduces air temperature rise and enhances the collector efficiency. The average efficiency of the experimental solar air heating system in the 4-day experiment period was 72%, 78%, 61%, and 72% respectively, which are higher than most conventional glazed flat-plate solar air collectors. With better coordination with architectural design at early stage in a project, this building-integrated solar air heating system can be both aesthetically and technically viable.

The ratio of public heating losses to total heating losses is fixed for a given building. The determination of this ratio is the basis for allocating heating charges fairly and reasonably, and is also the basis for determining the ratio of fixed heating charges to total heating charges. The changing rule of the ratio of public heating losses to total heating losses of 15 residential buildings in north China was researched under different conditions, such as different energy conservation performance, different usage and different layout etc, and drew some referable conclusions.Copyright © 2005 by ASME