Refine
Document Type
Language
- English (5) (remove)
Is part of the Bibliography
- no (5)
Keywords
- HVAC (2)
- fault detection (2)
- occupancy (2)
- random forest (2)
- LASSO (1)
- Occupancy detection (1)
- Random Forest (1)
- Simulated learning data (1)
- maschine learning (1)
- model prediction (1)
The energy efficiency of the building HVAC systems can be improved when faults in the running system are known. To this day, there are no cost-efficient, automatic methods that detect faults of the building HVAC systems to a satisfactory degree. This study induces a new method for fault detection that can replace a graphical, user-subjective evaluation of a building data measured on site with an automatic, data-based approach. This method can be a step towards cost-effective monitoring. For this research, the data from a detailed simulation of a residential case study house was used to compare a faultless operation of a building with a faulty operation. We argue that one can detect faults by analysing the properties of residuals of the prediction to the actual data. A machine learning model and an ARX model predict the building operation, and the method employs various statistical tests such as the Sign Test, the Turning Point Test, the Box-Pierce Test and the Bartels-Rank Test. The results show that the amount of data, the type and density of system faults significantly affect the accuracy of the prediction of faults. It became apparent that the challenge is to find a decision rule for the best combination of statistical tests on residuals to predict a fault.
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
When monitoring the energy performance of buildings, it may be of interest to identify the occupation periods of people in the room due to their possible impact on the energy balance. In order to be able to carry out a comprehensive energy assessment of the system and building, it is necessary to be able to classify user influence during the evaluation. This thesis investigates how the presence of people in a room can be determined cost-effectively and with little additional effort. The aim is to determine which sensors of a room control system provide sufficiently reliable data. The presence of 1-2 persons was examined on a test facility of the Technical University Rosenheim. The air-, mean radiation- and surface-temperatures, the air humidity as well as the CO2 and VOC concentrations were measured. For the analysis, a method of supervised machine and statistical learning, random forest, is used. The smallest model error detected in predicting the presence of 1 or 2 persons from CO2 sensor data is 1.43%. The error rates are low for all tested models if time-dynamic effects are used as predictors and the data is processed in a so-called time period form. Additionally, the ways in which this data should ideally be made available for future measurements and processed to facilitate analysis with machine and statistical learning techniques have been investigated. A further goal is to apply the models developed on measurement series in laboratory environments to real rooms and to assess the transferability of these models.
Knowing about the presence and number of people in a room can be of interest for precise control of heating, ventilation and air conditioning. To determine the number and presence of occupants cost-effectively, it is of interest to use already existing air condition sensors (temperature, humidity, CO2) of the building automation system. Different approaches and methods for determining presence have attracted attention in recent years. We propose an occupancy detection method based on a method of supervised machine learning. In an experiment, measurement data were recorded in a research apartment with controllable boundary conditions. The presence of people was simulated by artificial injection of water vapour, CO2 and heat dissipation. The variation of the number of artificial users, the duration of presence and the supply air volume flow of the ventilation resulted in a total of 720 combinations. By using artificial users, the boundary conditions were accurately defined, and different presence situations could be measured time-effectively. The data is evaluated with a method of supervised machine learning called random forest. The statistical model can determine precisely the number of people in over 93% of the cases in a disjoint test sample. The experiments took part in the Rosenheim Technical University of Applied Sciences laboratory.