Research Ivan Verhaert

Abstract

Buildings contribute to 40% of global energy consumption, with 36% attributed to heating, ventilation, and air-conditioning (HVAC). Therefore, optimizing HVAC control in buildings is crucial in the transition to a more sustainable society. Model predictive control (MPC) and (deep) reinforcement learning (DRL) have been explored for optimal control strategies, producing promising results. However, their performance depends on the underlying simulation model's accuracy, which is why an accurate model throughout the building's lifecycle is important. Physics-based models introduce discrepancies due to necessary simplifications, called the sim-to-real-gap. Closing this gap requires expert knowledge to increase the model's complexity, which is often not feasible. Given the emergence of smart, sensor-equipped buildings, data-driven solutions are possible, enabling a hybrid model that exploits the advantages of data-driven and physics-based models. First, data-driven models, like for example deep neural networks (DNNs), are added to the physics-based model on the level of the components to close the sim-to-real-gap. Second, as components degrade, the sim-to-real-gap will grow again and is closed using the same approach. Third, the hybrid model facilitates automatic fault detection and diagnosis (AFDD) using results from the adjustment process. Finally, an assessment of energy loss due to component degradation guides cost-optimal maintenance strategies.

Researcher(s)

• Promoter: Hellinckx Peter
• Co-promoter: Verhaert Ivan
• Fellow: Houben Pieter Jan

Research team(s)

• Modelling for Sustainability (M4S)

Project type(s)

• Research Project

Abstract

Given the rising quality requirements for comfort and air quality on the one hand, and the challenge of making our building stock energy sustainable on the other, the demands placed on HVAC or air handling systems have only increased. Designing, commissioning and managing a sustainable air treatment system in larger buildings is therefore a highly complex task involving various challenges, and this in a booming market segment.In order to provide an appropriate response to this growing demand and increasing customer requirements taking into account the time constraints prevailing in the sector, no ready-made solutions existed until recently. However, two things have changed recently, making the sector ready for this. For instance, thanks to the digitisation of modern buildings, there is a wealth of additional information available (e.g. via BIM models or real-time measurements) which, if used properly, can contribute to more efficient and sustainable systems. Examples from research show that savings of more than 10% can be achieved through targeted follow-up and monitoring of HVAC alone. Further progress is also possible in terms of design, both in terms of energy and cost savings. The Flux50- cSBO project 'Towards smart ventilation systems in mid-sized buildings' demonstrated the savings potential of a new design method with regard to life-cycle costs (= material, installation and energy costs) with additional benefits in terms of commissioning and acoustic performance. However, there is still a need for a user-friendly tool that enables designers to put the new methods into practice and for guidelines that support the correct use of data and models for control and design. In this project, we will support the HVAC sector in innovating the design and control of sustainable HVAC installations in non-residential buildings through concrete tools and guidelines. We will involve all market players ranging from manufacturers, installers and engineering firms to software agencies, service companies and building managers. In Belgium, there are more than 1,100 companies active in ventilation, air and climate control, most of which are SMEs without their own R&D department . Specific goals: - Develop a user-friendly design tool that supports the design engineer in designing sustainable HVAC systems. - Develop practical guidelines and teaching materials with a view to regulation and data use, as well as for use of digital (BIM) models and communication through the process from design to use. - Increase knowledge among the broad target group through broad communication and the provision of didactic material and its use in workshops and refresher courses. - Social objective: to contribute to the decarbonisation objectives of Flanders (and Europe) by designing more energy-efficient air treatment systems and using sustainable energy

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

Collective heating and cooling in apartment buildings or district heating simplifies the sustainability of heat generation. It facilitates smart electrification and an efficient shift to renewable heat sources. However, faults in the network or more generally suboptimal design, control and behavior of the heat distribution lead to efficiency losses from 10% to more than 50%. The growth of available data and progress in the field of data science opens up the opportunity to research and develop fault detection (FD) and fault detection + diagnosis (FDD) algorithms and techniques. However, the diversity in buildings and heating concepts limits their potential and functionality if they are based solely on measurement data. In FDD-accelerator an emulator will be built that is able to generate high quality labelled data on faults and suboptimal behaviour and able to validate potential FD(D) solutions. In the emulator methodologically structured expert knowledge is translated into a modular framework (digital twin) able to simulate suboptimal behaviour. The framework is combined with a lab set-up in which faults can be mimicked for validation, providing already some insight into the sim-to-real gap, which can be later exploited in further research.

Researcher(s)

• Promoter: Verhaert Ivan
• Co-promoter: Hellinckx Peter

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

As the urgency and importance of energy transition begins to seep into the housing market as well, players in the heating industry are inundated with practical questions from building owners. At the same time, techniques have become much more complex and can no longer be separated from other building aspects. The existing analysis tools and sizing methods to work out and select sustainable installation alternatives require (too) much time and money to implement for each individual home. In addition, the various players in the industry (installers, wholesalers, manufacturers, energy experts...) have a fragmented view of the different aspects of this issue. Moreover, not enough installers are making the move from fossil heat sources to sustainable techniques, and the influx of new installers is also limited. The renovation market faces two challenges in this regard. First, a lack of accessible detailed data to do sizing correctly and second, a lack of standard solutions. For the first problem, some promising techniques are under development in recent research. In this project, we want to generalize these insights and bring them together in a clear way and translate them to the building sector.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

The residential ventilation market has found itself in a constant shift in its performance requirements in the last few years. During the SARS-Cov2 pandemic, the focus was on indoor air quality (IAQ) centered performance and changed during the energy crisis, to minimize the energy use. In addition, the emphasis on renovation solutions has challenged the applicability of the traditional prescriptive ventilation standards and is pushing the market towards performance-based design. Moreover, the limited space available for ventilation ducts in renovation has led to a renewed focus on natural and hybrid decentralized ventilation solutions. Out of this context, we envision the next generation in residential ventilation system that is smart, robust, requires minimal intervention in existing dwellings and guarantees a good IAQ and low energy use. The NudgeFlow system dynamically nudges and tweaks the natural flow pattern through the different spaces in the dwelling to satisfy the instantaneous ventilation needs and flexibly adapt to the prevailing climate conditions. This novel ventilation system consists of interconnected local low pressure drop ventilation components, sensors tracking ventilation demand and climate conditions and a distributed controller adjusting the operation of these components. Thorough scientific basic research is required to enable this next generation ventilation design and to tackle the challenges that come with it. From understanding how and where to 'nudge' the overall airflow pattern in the dwelling, over measuring and benchmarking its performances, creating appropriate control and performance-based design strategies for such a system to integrating all these elements in a technology concept. The overall aim of this project is to formulate the NudgeFlow technology concept by investigating all the relevant methodological elements, determining the system components and proving the feasibility of the NudgeFlow system via simulations. The specific scientific goals to be achieved: • To enhance the physical understanding of the effect of infiltration flows and unsteady pressure differences on indoor airflows in residential buildings with a NudgeFlow system • To establish a modeling approach for airflows, temperatures and concentrations in and around NudgeFlow buildings • To propose a stochastic multi-zone calculation method and associated method to assess the indoor air quality and energy performance of a NudgeFlow system • To define acoustical performance criteria and an evaluation method for NudgeFlow components • To formulate the performance-based design process of the NudgeFlow system • To determine a distributed model-based controller for the NudgeFlow system including treatment of disturbances and inputs • To demonstrate the feasibility of a virtual NudgeFlow system With the aid of the companies and federations involved in the industrial advisory board (IAB) representing the whole economic value chain (design, development, manufacturing, installation and operation), this project will determine the NudgeFlow technology concept. The valorization outlook is broken down into 4 valorization objectives with accompanying utilization objectives reducing capital, development and operational expenditures: • Hardware modules • Generative algorithms for the design phase • Generative algorithms for the operational phase • Machine learning (ML) on multiple NudgeFlow systems

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

District Heating and Cooling (DHC) is a promising technology to shift to a sustainable energy supply, offering flexibility to the electric grid. Thermal storage can provide the necessary flexibility to balance production an demand for both electrical and thermal renewable energy sources (RES). Especially, the integration of decentralised thermal prosumers (e.g. boosters, thermal solar panel) in DHC have great potentials to improve the overall efficiency. Therefore, future DHC will need advanced control strategies facilitating the operation of prosumers-based DHC and providing flexibility to RES-dominated electric grids. Hereby, two main questions arise: (i) how should the temperature be controlled to improve the energetic, ecologic and economic performance of a DHC? And (ii) how to take into account the requirements of every direct stakeholder in the DHC? By simulating the DHC's behaviour, considering hydronics and prosumer behaviour, I will research the potential of a data-based control strategy, including multi-agent reinforcement learning (MARL). Every agent (per consumer, heat storage, etc.) pursues the local as well as the global objectives. The RL-agents are capable of self-learning a control strategy based on feedback (rewards). Besides valorisation throughout implementing such controls, the feedback and/or reward itself can be subject of follow-up research with respect to policy support.

Researcher(s)

• Promoter: Verhaert Ivan
• Co-promoter: Hellinckx Peter
• Fellow: Jacobs Stef

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

The importance of good indoor air quality and consequently high-quality air distribution systems in buildings has never been more topical than today. However, the function of an air distribution system is so much more than just providing and distributing sufficient fresh air in a building. Its main aim is to always satisfy occupants by controlling indoor air quality, temperature, and humidity, considering acoustic comfort, a variable occupancy in the building, and changing outdoor conditions. In addition, this has to be accomplished while minimizing energy use. Energy-efficient air distribution systems are a prerequisite to not just meet but go beyond the current minimum energy performance requirements for buildings. This is a crucial step to achieving a climate-neutral Europe by 2050 and realizing the European green deal. Clearly, designing and operating high-performing air distribution systems is very challenging and complex. Especially when these systems also have to be designed within a limited budget and time as is the case in practice. User-friendly tools are needed that support the design engineer in his or her decision-making to achieve optimal performing air distribution systems. However, no tool exists today to select the most optimal system in a specific building based on a coherent set of indicators for design optimization (i.e. indoor air quality (IAQ), acoustic and thermal comfort, and life cycle costs). Instead, design decisions are based on rules of thumb and the experience of the design engineer in charge, leading to suboptimal performing systems. The overarching aim is to develop a holistic, flexible, and user-friendly design tool for optimal air distribution systems in nonresidential buildings. Starting from a building's floor plan, the tool must be able to automatically calculate the optimal air distribution system's configuration (i.e., ductwork layout and sizing), while minimizing the life cycle costs (i.e., energy, material, installation, and maintenance costs). In addition, performance parameters will be taken into account that are more difficult to translate into a cost, but which are nevertheless crucial to the optimal performance of the system, such as acoustics, indoor air quality, and comfort. The tool must be applicable to both new construction projects and retrofitting projects. In this first project, we aim for a proof of concept optimizing retrofit strategies and parallel distribution systems. In parallel, software integration and complementarity with existing design tools / practice will be further explored in collaboration with industry.

Researcher(s)

• Promoter: Jorens Sandy
• Co-promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

The city of Antwerp has the ambition to be climate neutral by 2050. The role-out of district heating grids can help cities to accelerate the decarbonization and reduction of local emissions, by e.g. connecting waste heat in the vicinity of the city to the buildings in the city. In this project some open research questions with respect to the role-out and planning phase of such networks are addressed. Particular attention is paid to the robustness of the planning as circumstances tend to change along the way, with respect to demand, supply, infrastructural constraints and opportunities. On the short term a high temperature grid linked to a high temperature industrial waste heat plant is expected to have the biggest impact in a historical city like Antwerp, however on the longer term low temperature grids can become more interesting to reach a mature district heating market in which multiple suppliers can participate, reaching also a higher overall efficiency. Besides the research on planning, the ambition of this project is to bridge the gap between practice and academic research, supporting policy and role-out of future-proof district heating networks. The chair is funded by Fluvius and the city of Antwerp.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project
• Education Project

Abstract

To realize efficient and sustainable cooling systems for building applications, the field of construction and installation require a set of tools and guidelines. Cooling 2.0 will fill this gap by developing and offering practical guidelines and user-friendly tools for selection and component sizing of emission, distribution and generation parts of a cooling system. The focus hereby is on hydronic systems with a central generation of cooling and with (ice)water as a cooling medium.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

In a sustainable energy supply, heat networks provide answers to questions of flexibility, energy efficiency and air quality. Heat delivery units (HIUs) play a key role in this respect and are responsible for matching local comfort requirements with a high-performance and efficient heat network. There is therefore a need for a quality protocol and associated test infrastructure to test and evaluate such units for targeted improvements. (Inter)national protocols have been developed, but these are often limited to specific types of delivery units and certainly not foreseen for testing new functionalities. The goal of this project is to scale up and adapt our test infrastructure to a level that we can also smoothly organize contract research, taking into account the dynamics of the business world which is a lot faster than the academic one. An additional condition is that it does not hamper our research into new types of delivery sets and functionalities so that we can stay one step ahead of the market. This will mainly require some targeted investments to de-duplicate test capacity and automate metering devices, as well as the necessary links to test local booster systems and cooling functionality. In addition, targeted training and development in PLC programming is needed to automate some processes and make them more cost-effective with a view to contract research.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

Project type(s)

• Research Project

Abstract

The project translates research results towards industry with respect to sizing and control of domestic hot water appliances. Hereby the specific needs for each product are taken into account. Besides this the method is validated in other domains of applications like hotels and carecenters.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project type(s)

• Research Project

Abstract

Globally we are facing severe water stress and security challenges due to more frequent and serious droughts combined with increasing water demand by society. Industrial activities play a key role in societal water demand, while also frequently being the first to be affected by water shortages. For example, in the region of Flanders (Belgium), nearly a quarter of the gross value added is generated by industrial activities. Flanders is, however, also extremely water stressed with 40-80% of its water resources being utilized and 40% of the water demand being used by Flemish industry. Companies are also the first to lose their 'license to operate' in the event of drought; compromising their ability to generate economic output. The industry itself has voiced concerns about its resilience towards water shortage, yet it also admits to not being prepared to act upon it. Industrial water use is complex in terms of quantities, qualities and dynamics, rendering it difficult to uncover opportunities without the help of holistic computational tools. However, industrial sites offer opportunities for efficient water use and industrial ecology, as individual activities are located in close proximity and show diverse characteristics in terms of demand and supply. Efficient management of water with a focus on using 'alternative water sources' like reclaimed water and rainwater is therefore very important to support a sustainable growth of the Flemish economy. The Blue Deal of the Flemish government puts alternative water sourcing as a key goal, underlining the urgency of the challenge. The objective of the Water Reuse and Exchange Advanced Computational Tool (WaterREACT) is to prototype model code that minimizes water demand within industrial zones from external, 'conventional' sources, i.e. tap water, surface water and groundwater. WaterREACT aims to support planning for circular water and rainwater use at industrial sites. More specifically, the model algorithm will deliver computation-based decision inputs, through calculating scenarios that maximize water exchange based on alternative sources, and thus minimize dependency on conventional sources. Water demand and supply will be matched based on quantity, quality and temporality of the flows. Additionally, the proximity of the supply and demand points is accounted, along with the treatment options to upgrade water quality. Water exchange can be modelled for bilateral and multi-company exchanges. To support decision making, indicators considering water resilience, cost and environmental impacts are calculated for different scenarios. At an early stage of the project, customer demands will be elicited and use to define the minimal viable product and the valorization trajectories.

Researcher(s)

• Promoter: Vlaeminck Siegfried
• Co-promoter: Spiller Marc
• Co-promoter: Verhaert Ivan

Research team(s)

Project type(s)

• Research Project

Abstract

As people spend the majority of their times in indoor spaces, providing them with comfortable & clean environments is crucial for their wellbeing and productivity. This can be achieved through the implementation of Smart Ventilation designs that are able to continually adjust themselves depending on the dynamically changing indoor/outdoor conditions, to provide good IAQ while minimizing energy use, discomfort and noise. Current practices in ventilation design are driven by minimum requirements of IAQ, energy use and investment costs, rendering them conservative and inefficient. At present, no method exists that allows to select the most optimal system & room layout based on a coherent set of indicators (IEQ, energy use, comfort, resilience, LCCs...). ​"Towards Smart Ventilation in Mid-sized buildings" project, financed by VLAIO aims to meet these needs by developing a performance-based method that approaches the design of Smart Ventilation systems as a whole, driven by performance assessment and optimization during the whole life-cycle of the system. The project also aims to improve the energy efficiency of buildings and its systems, to achieve a decarbonised EU building stock, taking a step forward towards a climate neutral Europe by 2050.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

• Energy and Materials in Infrastructure and Buildings

Project website

Project type(s)

• Research Project

Abstract

Energy efficiency in the built environment plays a key role in the transition towards a sustainable zero-carbon future. More specifically, renewables and industrial waste heat should be integrated in today's energy distribution systems. This integration is facilitated by so-called thermal grids, i.e. large systems at building or district level that consist of heat (and/or cold) sources and sinks, which are all connected by distribution pipes. The operation of thermal grids has highly complex dynamics because of two reasons. First, -analogue to the electrical grid- the intermittent loads of the sources and sinks should be aligned to ensure thermal and sanitary comfort of the end-users. Second, each type of thermal load (space heating, cooling and domestic hot water) requires a different temperature level. These temperature levels strictly affect both distribution losses and production efficiency. Currently, thermal grids are operated with static and mostly linear rule-based fuzzy logic control structures. Because of the simplicity and compactness of the linguistic approach of these types of controllers, trajectory following problems (such as heating and cooling reference tracking etc.) can successfully be accomplished. Yet, even though these solutions perfectly fit specific industrial applications, they do not offer any contribution to energy saving for complex thermal grids. Thus, the potential of thermal grids cannot be fully exploited by using conventional approaches. Indeed, primitive rule-based perspectives cannot fully optimize the alignment between production and demand, or the temperature set points along the grids. To sum up, they are designed for reliability, not for optimal efficiency. Optimizing controller dynamics of complex systems has been tackled in numerous areas of industrial applications: automotive, avionics, process industry etc. However, all these subsystems have mostly time-invariant dynamics and considerably less uncertainties that have serious effects on the aimed goal. This means that the data-driven algorithm can stop pre-processing input-output data after proposing an optimal solution under strict assumptions and constraints. On the other hand, environments such as thermal grids, which include high non-linearity, high complexity and time-varying parameters, require novel trends towards data-driven control methodologies. Despite their advantages and maturity, data-driven approaches have not adapted and penetrated into thermal grid applications (or HVAC systems in general). The reason is a lack of existing frameworks for implementation of these approaches and insufficient joint forces of HVAC and AI multi-disciplinary expertise. With this project, ID-Lab and EMIB, aim to set up a strong collaboration and obtain a leading role in the research of data-driven methodologies for optimizing energy efficiency in the building sector.

Researcher(s)

• Promoter: Verhaert Ivan
• Co-promoter: Hellinckx Peter
• Co-promoter: Van Riet Freek

Research team(s)

Project type(s)

• Research Project

Abstract

New guidelines are being developed for for sanitary hot water installations, with regard to dimensioning, on behalf of and in collaboration with BBRI. In this project, the insights obtained from the projects for the residential sector are translated into others, with a view to adapting the existing norms and standards. For this, among other things, we carry out in-situ measurement campaigns in hotels to answer this question.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

Project type(s)

• Research Project

Abstract

Within a sustainable energy supply district heating offers flexibility and scale-advantage with respect to the integration of renewable and pollution-free heat production. Also within collective housing facilities,e.g apartment block, collective heating systems offer these advantages. These have been illustrated in previous projects and elsewhere in Europe. To enable the Flemish industry and policy makers to put this into practice and to support further innovation by validating novel low -temperature heating and cooling concepts, this TETRA-project is initiated. The goal of this project to develop a code of good practice for collective hydronic heating systems with following objectives: * design guides and tools for the installers with respect to the production of heat and cold * a quality framework for manufacturers to evaluate their present and future products, e.g HIU's * initiation further innovation with respect to operational optimization, through quality measurements and smart metering

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

Project type(s)

• Research Project

Abstract

Even though energy demand in buildings is falling sharply and will have to fall even further, a correct calculation of the required installed capacity is becoming increasingly important. Innovative techniques often require a larger investment, which means that correct sizing is required in order to compete with conventional techniques. By introducing all kinds of IT solutions, smart solutions can be introduced which, on the one hand, allow better control of building comfort (correct power and temperature regime at all times, resulting in improved efficiency) and, on the other hand, allow to respond to grid requirements (Smart Grids, both electrical and heat) because there too the variable availability of sufficient power entails a cost.

Researcher(s)

• Promoter: Audenaert Amaryllis
• Co-promoter: Verbeke Stijn
• Co-promoter: Verhaert Ivan

Research team(s)

Project type(s)

• Research Project

Abstract

In the provence of Antwerp a new industrial site is being developed for further exploitation, In this development process sustainability is considered in order to facilitate future energy savings. On site the presence of large wells rises the question whether it is favorable to incorporate this local asset in a thermal heating/cooling network. The research aims to develop some answers providing a better insight in this matter and start a potential analysis. This includes an prediction of the cooling and heating demand of an office building and an indication of the thermal storage capacity.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

Project type(s)

• Research Project

Abstract

Policy supporting research activities in the field of energy performance in buildings. In a large alliance of different universities, scientific institutions and engineering offices EMIB support TMK to execute and manage several research tasks.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

Project type(s)

• Research Project

Abstract

The project aims to facilitate the realization of efficient and innovative installations for sanitary (cold and hot) water and for space heating. A methodology to design and realize these installations will be elaborated, both for newly built as for renovated residential buildings. An optimal design includes conceptual choices and sizing and will need to find a balance between the different design criteria as energy, comfort, hygiene, water quality and total cost.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

Project website

Project type(s)

• Research Project

Abstract

The project supports the market introduction of micro-CHP for building applications by offering sizing tools and guidance for HVAC- installation companies. A number of field tests will be analysed in order to formulate a road map for following successful installations. Next to that some the innovation potential will be elaborated by introducing new materials for thermal storage and new economic drivers within a smart grid context.

Researcher(s)

• Promoter: Verhaert Ivan

Research team(s)

Project website

Project type(s)

• Research Project