Fakultät für Angewandte Natur- und Geisteswissenschaften
Refine
Document Type
Language
- English (8) (remove)
Has Fulltext
- no (8)
Is part of the Bibliography
- no (8)
Keywords
- HVAC (2)
- fault detection (2)
- Asymptotic distribution (1)
- Asymptotic theory (1)
- Building Simulation (1)
- CLT building (1)
- Estimating equations (1)
- LASSO (1)
- Linear segmentet regression models (1)
- Occupancy detection (1)
Institute
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
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.
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.
We are concerned with the asymptotic theory of semiparametric estimation equations. We are dealing with estimation equations which have a parametric component of interest and a functional (nonparametric) nuisance component.
We give sufficient conditions for the existence and the asymptotic normality of a consistent estimation equation estimator for the parameter of interest.
These conditions concern the asymptotic distribution of the estimation function and of its derivative as well as the effect of the functional nuisance part in the estimation equation. In order to treat the nonparametric component we introduce a general differential calculus and a general mean value theorem. For the nonparametric part in the estimation equation we distinguish two cases: the situation of a (classical) nuisance parameter and the case of a so called working parameter.
As a special case we get regularity conditions for estimation equations with finite dimensional nuisance or working parameter. As an example we present the semiparametric linear regression model.
We consider asymptotic theory for the maximum likelihood estimator in the generalized linear model with an unknown breakpoint. A proof for the asymptotic normality is given.
The methods are based on the work of Huber (1967). The main problem is the non--differentiability of the likelihood and the score function, which requires non--standard methods.
An example from epidemiology is presented, where confidence intervals for the parameters are calculated with the asymptotic results.
The method is based on a simplified Statistical Energy Analysis(SEA) approach. The energy ratios of various subsystems are the main quantities to predict sound transmission. The method has proven to work sufficiently accurate for masonry and concrete buildings, where the building components like walls, floors etc. can be regarded as rather homogeneous structures. To adapt this method for solid timber constructions it is necessary to prove that basic SEA requirements are fullfilled by orthotropic materials and heterogeneous structures that occur in these building types. In a case study, an isolated T-junction formed by Cross Laminated Timber(CLT) elements is experimentally investigated. The buildings elements are subdivided in segments with typical screwed connections.
In the experiments the diffusivity of the vibration field is investigated, using point excitation with a shaker at several positions and many, randomly chosen response positions. MONTE-CARLO simulations are conducted for random but fix-sized subsets of the measured response positions to find the necessary number of response positions for an accurate determination of the vibrational energy.
As a result the distribution of the mean velocity levels can be approximated.
In a second approach a multiple linear regression model based on the least absolute shrinkage and selection operator(LASSO)is applied, because for lower frequency bands multicollinearity is expected.
In the context of linear regression modelling, data-driven methods are used to select optimal subsets of response positions, to get an estimating equation.