Fault detection and diagnosis in building energy systems: A tool chain for the automated generation of training data

The application of fault detection and diagnosis (FDD) algorithms in building energy management systems (BEMS) has great potential to increase the efficiency of building energy systems (BES). The usage of supervised learning algorithms requires time series depicting both nominal and component faulty behaviour for their training. In this paper, we introduce a method that automates Modelica code extension of BES models in Python with fault models to approximate real component faults. The application shows two orders of magnitude faster implementation compared to manual modelling, while no errors occur in the connections between fault and component models.

Combined Building-Energy Systems with Heat Transfer Control by Building Constructions using RES

Energy systems built into one of the building structures that serve to capture solar energy, geothermic energy, and ambient energy, or which have the function of end elements of heating, cooling, and ventilation system, we generally call combined building-energy systems. Among combined building-energy systems we include solar roofs with built-in pipe absorbers, building structures with active thermal protection (ATP) - active heat transfer control, which have a multifunctional purpose – a thermal barrier, low-temperature heating, high-temperature cooling, recuperation and accumulation of heat, solar and ambient energy collection, large-capacity heat storage (ground heat accumulators built simultaneously in the foundation slab of the building), or heat exchangers used for recuperative ventilation of buildings built into the foundation slabs and wall structures. The research of combined building-energy systems at the Department of Building Services, Faculty of Civil Engineering, Slovak University of Technology in Bratislava has been carried out continuously since 2005. Within five research projects (responsible researcher, Kalús, D.) HZ 04-309-05, HZ 04-310- 05, HZ 04-142-07 (research and experimental measurements took place in the years 2005 to 2007), HZ PG73/2011 (research and experimental measurements took place in the years 2011 to 2013), [13,] and HZ PR10/2015 (research and experimental measurements have been carried out since 2015), two experimental houses IDA I. and EB2020, a mobile laboratory designed for measuring and optimizing a compact heat station using renewable heat sources, were designed and built by the research team at our workplace, and also a research of a fragment of a perimeter wall with built-in active thermal protection was carried out in the climatic chamber of the Faculty of Civil Engineering STU in Bratislava, Slovak Republic. Significant contribution to the research was provided by doctoral students Ing. Martin Cvíčela, Ph.D., (supervisor, Kalús, D.), Ing. Peter Janik, PhD., (supervisor, Kalús, D.) and Ing. Martin Šimko, PhD., (supervisor, Kalús, D.), who described the results of the research in their dissertations. At present experimental measurements in the mobile laboratory are performed by doctoral student Ing. Matej Kubica, (supervisor, Kalús, D.). In the area of combined construction and energy systems, research and optimization of suitable solutions continues, which have been transformed into one European patent and three utility models.

A tool for automated detection of hidden operation modes in building energy systems

The integration of renewable energy sources into building energy systems and the progressive coupling between the thermal and electrical domains makes the analysis of these systems increasingly complex. At the same time, however, more and more building monitoring data is being collected. The manual evaluation of this data is time-consuming and requires expert knowledge. Hence, there is a strong need for tools that enable the automatic knowledge extraction from these huge data sets to support system integrators and favor the development of smart energy services, e.g., predictive maintenance. One crucial step in knowledge extraction is the detection of change points and hidden states in measurements. In this work, we present a tool for automated detection of hidden operation modes based on multivariate time series data deploying motif-aware state assignment (MASA). The tool is evaluated utilizing measurements of a heat pump and compared to two baseline algorithms, namely k-Means and k-Medoids. MASA performs particularly well on noisy data, where it shows only a small deviation in the number of detected change points compared to the ground truth with up to 77% accuracy. Furthermore, it almost always outperforms the baseline algorithms, which in turn require extensive preprocessing.

An energy-economic analysis of real-world hybrid building energy systems

A coordinated operation of decentralised micro-scale hybrid energy systems within a locally managed network such as a district or neighbourhood will play a significant role in the sector-coupled energy grid of the future. A quantitative analysis of the effects of the primary energy factors, energy conversion efficiencies, load profiles, and control strategies on their energy-economic balance can aid in identifying important trends concerning their deployment within such a network. In this contribution, an analysis of the operational data from five energy laboratories in the trinational Upper-Rhine region is evaluated and a comparison to a conventional reference system is presented. Ten exemplary data-sets representing typical operation conditions for the laboratories in different seasons and the latest information on their national energy strategies are used to evaluate the primary energy consumption, CO2 emissions, and demand-related costs. Various conclusions on the ecologic and economic feasibility of hybrid building energy systems are drawn to provide a toe-hold to the engineering community in their planning and development.

Automated modelling of building energy systems with mode-based control algorithms in Modelica

The increasing use of renewable energy in building energy systems has brought considerable challenges for the traditional planning process to develop appropriate control strategies. In previous work, we have introduced the MODI method to support the structured development of mode-based control algorithms, in which operating modes are core elements. However, modeling of energy systems and control algorithms for control tests is time-consuming and error-prone. Identification of permissible operating modes is also unfeasible. The paper introduces a methodology to identify permissible operating modes and model energy systems with mode-based control algorithms in the modeling language Modelica automatically. In the case study, we apply the methodology for an energy supply network and verify the functionality of the methodology. In future work, automated optimization of control algorithms will be integrated into the methodology.