Refine
Document Type
- Article (peer reviewed) (3) (remove)
Language
- English (3)
Has Fulltext
- no (3)
Is part of the Bibliography
- no (3)
Keywords
- Building Simulation (1)
- Computational cost (1)
- Cross comparison (1)
- HVAC (1)
- LASSO (1)
- Modelling approaches (1)
- Occupancy detection (1)
- Random Forest (1)
- Simulated learning data (1)
- Statistical indices (1)
Institute
- Fakultät für Angewandte Natur- und Geisteswissenschaften (3) (remove)
Faults in Heating, Ventilation and Air Conditioning (HVAC) systems affect the energy efficiency of buildings. To date, there rarely exist methods to detect and diagnose faults during the operation of buildings that are both cost-effective and sufficient accurate. This study presents a method that uses artificial intelligence to automate the detection of faults in HVAC systems. The automated fault detection is based on a residual analysis of the predicted total heating power and the actual total heating power using an algorithm that aims to find an optimal decision rule for the determination of faults. The data for this study was provided by a detailed simulation of a residential case study house. A machine learning model and an ARX model predict the building operation. The model for fault detection is trained on a fault-free data set and then tested with a faulty operation. The algorithm for an optimal decision rule uses various statistical tests of residual properties such as the Sign Test, the Turning Point Test, the Box-Pierce Test and the Bartels-Rank Test. The results show that it is possible to predict faults for both known faults and unknown faults. The challenge is to find the optimal algorithm to determine the best decision rules. In the outlook of this study, further methods are presented that aim to solve this challenge.
The applications for occupancy detection range from controlling building automation and systems, determining heat transfer coefficients and even assessing the risk of infection in rooms. Studies in the literature use various statistical models, physical models and machine learning techniques to detect occupancy. All these methods require data for training the occupancy detection models. However, data generation is time-consuming and expensive. This study demonstrates the feasibility of using simulated learning data. Using three different data sources, we tested the suitability of different methods for generating learning data. We conducted two experiments in two office spaces with a real user and an artificial user, and we generated a third data set using a building simulation model. In addition, this study compares two different machine learning approaches (Random Forest and LASSO) using environmental parameters. Both machine learning approaches could develop models with a sensitivity of at least 83 % and a specificity of at least 97 % with both training data sets. This work shows that it is possible to determine the presence in rooms using simulated data. The results compared to measured data were just slightly less accurate, and the added value due to the lower effort was considerable
Building Energy Simulation (BES) tools play a key role in the optimization of the building system during the different phases, from pre-design through commissioning to operation. BES tools are increasingly used in research as well as in companies. New BES tools and updated versions are continuously being released. Each tool follows an independent validation process but rarely all the tools are compared against each other using a common case study. In this work, the modelling approaches of widespread dynamic simulation tools (i.e. EnergyPlus, TRNSYS, Simulink libraries CarnotUIBK and ALMABuild, IDA ICE, Modelica/Dymola and DALEC), as well as PHPP (a well-known quasi-steady-state tool), are described and the results of all the tools modelling the same characteristic office cell, defined within the IEA SHC Task 56, are compared on a monthly and hourly basis for the climates of Stockholm, Stuttgart and Rome. Unfortunately, different tools require different levels of input detail, which are often not matching with available data, hence the parametrization process highly influences the quality of the simulation results. In the current study to evaluate the deviation between the tools, frequently used statistical indices and normalization methods are analysed and the problems related to their application, in a cross-comparison of different tools, are investigated. In this regard, the deviation thresholds indicated by ASHRAE Guideline 14-2014 are used as a basis to identify results that suggest an acceptable level of disagreement between the predictions of a particular model and the outcomes of all models. The process of reaching a good agreement between all tools required several iterations and great effort on behalf of the modellers. To aid the definition of building component descriptions and future references for inter-model comparison a short history of the executed steps is presented in this work. Together with the comparison of the results of the tools, their computational cost is evaluated and an overview of the modelling approaches supported by the different tools for this case study is provided aiming to support the users in choosing a fit-for-purpose simulation tool.