Abstract Optimal control of heating, ventilation and air conditioning systems (HVACs) aims to minimize the energy consumption of equipment while maintaining the thermal comfort of occupants. Traditional rule-based control methods are not optimized for HVAC systems with continuous sensor readings and actuator controls. Recent developments in deep reinforcement learning (DRL) enabled control of HVACs with continuous sensor inputs and actions, while eliminating the need of building complex thermodynamic models. DRL control includes an environment, which approximates real-world HVAC operations; and an agent, that aims to achieve optimal control over the HVAC. Existing DRL control frameworks use simulation tools (e.g., EnergyPlus) to build DRL training environments with HVAC systems information, but oversimplify building geometrics. This study proposes a framework aiming to achieve optimal control over Air Handling Units (AHUs) by implementing long-short-term-memory (LSTM) networks to approximate real-world HVAC operations to build DRL training environments. The framework also implements state-of-the-art DRL algorithms (e.g., deep deterministic policy gradient) for optimal control over the AHUs. Three AHUs, each with two-years of building automation system (BAS) data, were used as testbeds for evaluation. Our LSTM-based DRL training environments, built using the first year's BAS data, achieved an average mean square error of 0.0015 across 16 normalized AHU parameters. When deployed in the testing environments, which were built using the second year's BAS data of the same AHUs, the DRL agents achieved 27%–30% energy saving comparing to the actual energy consumption, while maintaining the predicted percentage of discomfort (PPD) at 10%.
David J. Albers, Tell D. Bennett, Jana de Wiljes
et al.
Identifying the effects of mechanical ventilation strategies and protocols in critical care requires analyzing data from heterogeneous patient-ventilator systems within the context of the clinical decision-making environment. This research develops a framework to help understand the consequences of mechanical ventilation (MV) and adjunct care decisions on patient outcome from observations of critical care patients receiving MV. Developing an understanding of and improving critical care respiratory management requires the analysis of existing secondary-use clinical data to generate hypotheses about advantageous variations and adaptations of current care. This work introduces a perspective of the joint patient-ventilator-care systems (so-called J6) to develop a scalable method for analyzing data and trajectories of these complex systems. To that end, breath behaviors are analyzed using evolutionary game theory (EGT), which generates the necessary quantitative precursors for deeper analysis through probabilistic and stochastic machinery such as reinforcement learning. This result is one step along the pathway toward MV optimization and personalization. The EGT-based process is analytically validated on synthetic data to reveal potential caveats before proceeding to real-world ICU data applications that expose complexities of the data-generating process J6. The discussion includes potential developments toward a state transition model for the simulating effects of MV decision using empirical and game-theoretic elements.
This study examines the dynamics of the urban heat island (UHI) effect by conducting a comparative analysis of air temperature hysteresis patterns in Paris and Madrid, two major European cities with distinct climatic and urban characteristics. Utilizing high-resolution modelled air temperature data aggregated at a fine temporal resolution of three-hour intervals from 2008 to 2017, we investigate how diurnal and seasonal hysteresis loops reveal both unique and universal aspects of UHI variability. Paris, located in a temperate oceanic climate, and Madrid, situated in a cold semi-arid zone, display pronounced differences in UHI intensity, seasonal distribution, and diurnal patterns. Despite these contrasts, both cities exhibit remarkably similar hysteresis loop directions and slopes, suggesting that time-dependent mechanisms such as solar radiation and heat storage fundamentally govern air temperature UHI across diverse urban contexts. Our findings underscore the importance of considering both local climate and universal physical processes in developing targeted, climate-resilient urban strategies. The results pave the way for group-based interventions and classification of cities by hysteresis patterns to inform urban planning and heat mitigation efforts.
Ventilator dyssynchrony (VD) is often described as a mismatch between a patient breathing effort and the ventilator support during mechanical ventilation. This mismatch is often associated with an increased risk of lung injury and longer hospital stays. The manual VD detection method is unreliable and requires considerable effort from medical professionals. Automating this process requires a computational pipeline that can identify VD breaths from continuous waveform signals. For that, while various machine learning (ML) models have been proposed, their accuracy is often limited due to the unavailability of a large, well-annotated VD waveform dataset. This paper presents a new approach combining mathematical and deep generative models to generate synthetic, clinically relevant VD waveforms. The mathematical model, which we call the VD lung ventilator model (VDLV), can accurately replicate clinically observable deformation in the pressure and volume waveforms. These temporal deformations are hypothesized to be related to specific VD breaths. We leverage the VDLV model to produce training waveform datasets covering normal and various VD breaths. These datasets are further diversified using deep learning models such as Generative Adversarial Network (GAN) and Conditional GAN (cGAN). The performance of both GAN and cGAN models is assessed through quantitative metrics, demonstrating that this hybrid approach effectively creates realistic and diverse VD waveforms. Notably, the pressure and volume cGAN models enable the generation of more precise and targeted VD signals. These improved synthetic waveform datasets have the potential to significantly enhance the accuracy and robustness of VD detection algorithms.
Abstract Supervised learning techniques have witnessed significant successes in fault detection and diagnosis (FDD) for heating ventilation and air-conditioning (HVAC) systems. Despite the good performance, these techniques heavily rely on balanced datasets that contain a large amount of both faulty and normal data points. In real-world scenarios, however, it is often very challenging to collect a sufficient amount of faulty training samples that are necessary for building a balanced training dataset. In this paper, we introduce a framework that utilizes the generative adversarial network (GAN) to address the imbalanced data problem in FDD for air handling units (AHUs). To this end, we first show the necessary procedures of applying GAN to increase the number of faulty training samples in the training pool and re-balance the training dataset. The proposed framework then uses supervised classifiers to train the re-balanced datasets. Finally, we present a comparative study that illustrates the advantages of the proposed method for FDD of AHU with various evaluation metrics. Our work demonstrates the promising prospects of performing robust FDD of AHU with a limited number of faulty training samples.
Francois D. Boshoff, Sybrand J. van der Spuy, Johannes P. Pretorius
An axial flow cooling fan has been designed for use in a concentrated solar power plant. The plant is based on a supercritical carbon dioxide (sCO2) Brayton cycle, and uses a forced draft air-cooled heat exchanger (ACHE) for cooling. The fan performance has been investigated using both computational fluid dynamics (CFD) and scaled fan tests. This paper presents a CFD model that integrates the fan with the heat exchanger. The objective is to establish a foundation for similar models and to contribute to the development of efficient ACHE units designed for sCO2 power cycles. The finned-tube bundle is simplified, with a Porous Media Model representing the pressure drop through the bundle. Pressure inlet and -outlet boundary conditions are used, meaning the air flow rate is solved based on the fan and tube bundle interaction. The flow rate predicted by the CFD model is 0.5% higher than the analytical prediction, and 3.6% lower than the design value, demonstrating that the assumptions used in the design procedure are reasonable. The plenum height is also found to affect the flow rate, with shorter plenums resulting in higher flow rates and fan efficiencies, and longer plenums resulting in more uniform cooling air flow.
In this paper, we introduce a novel framework for building learning and control, focusing on ventilation and thermal management to enhance energy efficiency. We validate the performance of the proposed framework in system model learning via two case studies: a synthetic study focusing on the joint learning of temperature and CO2 fields, and an application to a real-world dataset for CO2 field learning. For building control, we demonstrate that the proposed framework can optimize the control actions and significantly reduce the energy cost while maintaining a comfort and healthy indoor environment. When compared to existing traditional methods, an optimization-based method with ODE models and reinforcement learning, our approach can significantly reduce the energy consumption while guarantees all the safety-critical air quality and control constraints. Promising future research directions involve validating and improving the proposed PDE models through accurate estimation of airflow fields within indoor environments. Additionally, incorporating uncertainty modeling into the PDE framework for HVAC control presents an opportunity to enhance the efficiency and reliability of building HVAC system management.
Mist/air two-phase flow is a promising cooling technique for many applications such as internal cooling of gas turbine blades. A significant enhancement of heat transfer can be achieved with a low mass fraction of droplets by utilizing the latent heat of the droplets. Using newly designed atomizers to accurately control the mist droplets, this study experimentally explores the heat transfer performance of mist/air flow in a high-temperature channel with a maximum temperature of 880 K. The effects of the mist/air mass ratio, droplet size, Reynolds number, and wall heat flux are studied. The results show that the cooling performance of the test section can be significantly improved by even adding a small amount of droplets. Considering mist droplets of different sizes, larger droplets can cause more remarkable temperature reduction, while smaller droplets can improve the uniformity of temperature distribution. For large droplets, the cooling effect in the upstream is more obvious than that in the downstream due to the interaction between the wall and the droplets, and with the increase of mist/air mass ratio, the area with obvious cooling extends downstream. The performance of mist/air cooling is tested by increasing the heat flux until the maximum temperature at the outlet reaches a predetermined value. Compared with air-only cooling, the increment in the wall heat flux by the mist/air cooling with a mass ratio of 3% can be up to 18.4%.
Widespread air source heat pump (ASHP) adoption faces several challenges that on-site thermal energy storage (TES), particularly thermochemical salt hydrate TES, can mitigate. No techno-economic analyses for salt-hydrate-based TES in residential applications exist. We quantify the residential space heating value of four salt hydrate TES materials - MgSO4, MgCl2, K2CO3, and SrBr2 - coupled with ASHPs across 4,800 representative households in 12 U.S. cities by embedding salt-hydrate-specific Ragone plots into a techno-economic model of coupled ASHP-TES operations. In Detroit, salt hydrate TES is projected to reduce household annual electricity costs by up to $\$$241 (8$\%$). Cost savings from TES can differ by over an order of magnitude between households and salt hydrates. We identify the most promising salt in this study, SrBr2, due to its high energy density and low humidification parasitic load. Break-even capital costs of SrBr2-based TES range from $\$$13/kWh to $\$$17/kWh, making it the only salt hydrate studied to reach and exceed the U.S. Department of Energy's $\$$15/kWh TES cost target. Sensitivities highlight the importance of variable TES sizing and efficiency losses in the value of TES.
Niloufar Eghbali, Tuka Alhanai, Mohammad M. Ghassemi
Mechanical Ventilation (MV) is a critical life-support intervention in intensive care units (ICUs). However, optimal ventilator settings are challenging to determine because of the complexity of balancing patient-specific physiological needs with the risks of adverse outcomes that impact morbidity, mortality, and healthcare costs. This study introduces ConformalDQN, a novel distribution-free conformal deep Q-learning approach for optimizing mechanical ventilation in intensive care units. By integrating conformal prediction with deep reinforcement learning, our method provides reliable uncertainty quantification, addressing the challenges of Q-value overestimation and out-of-distribution actions in offline settings. We trained and evaluated our model using ICU patient records from the MIMIC-IV database. ConformalDQN extends the Double DQN architecture with a conformal predictor and employs a composite loss function that balances Q-learning with well-calibrated probability estimation. This enables uncertainty-aware action selection, allowing the model to avoid potentially harmful actions in unfamiliar states and handle distribution shifts by being more conservative in out-of-distribution scenarios. Evaluation against baseline models, including physician policies, policy constraint methods, and behavior cloning, demonstrates that ConformalDQN consistently makes recommendations within clinically safe and relevant ranges, outperforming other methods by increasing the 90-day survival rate. Notably, our approach provides an interpretable measure of confidence in its decisions, which is crucial for clinical adoption and potential human-in-the-loop implementations.
We performed numerical simulations to study mechanisms of solar prominence formation triggered by a single heating event. In the widely accepted ``chromospheric-evaporation condensation" model, localized heating at footpoints of a coronal loop drives plasma evaporation and eventually triggers condensation. The occurrence of condensation is strongly influenced by the characteristics of the heating.Various theoretical studies have been conducted along one-dimensional field lines with quasi-steady localized heating. The quasi-steady heating is regarded as the collection of multiple heating events among multiple strands constituting a coronal loop. However, it is reasonable to consider a single heating event along a single field line as an elemental unit.We investigated the condensation phenomenon triggered by a single heating event using 1.5-dimensional magnetohydrodynamic simulations. By varying the magnitude of the localized heating rate, we explored the conditions necessary for condensation. We found that when a heating rate approximately $\sim 10^{4}$ times greater than that of steady heating was applied, condensation occurred. Condensation was observed when the thermal conduction efficiency in the loop became lower than the cooling efficiency, with the cooling rate significantly exceeding the heating rate. Using the loop length $L$ and the Field length $λ_{\mathrm{F}}$, the condition for condensation is expressed as $λ_{\mathrm{F}} \lesssim L/2$ under conditions where cooling exceeds heating. We extended the analytically derived condition for thermal non-equilibrium to a formulation based on heating amount.
Abstract Fault detection in heating, ventilation, and air conditioning (HVAC) systems is essential because faults lead to energy wastage, shortened lifespan of equipment, and uncomfortable indoor environments. In this study, we proposed a data-driven fault detection and diagnosis (FDD) scheme for air handling units (AHUs) in building HVAC systems to enable reliable maintenance by considering undefined states. We aimed to determine whether a neural-network-based FDD model can provide significant inferences for input variables using the supervised auto-encoder (SAE). We evaluated the fitness of the proposed FDD model based on the reconstruction error of the SAE. In addition, fault diagnosis is only performed by the FDD model if it can provide significant inferences for input variables; otherwise, feedback regarding the FDD model is provided. The experimental data of ASHRAE RP-1312 were used to evaluate the performance of the proposed scheme. Furthermore, we compared the performance of the proposed model with those of well-known data-driven approaches for fault diagnosis. Our results showed that the scheme can distinguish between undefined and defined data with high performance. Furthermore, the proposed scheme has a higher FDD performance for the defined states than that of the control models. Therefore, the proposed scheme can facilitate the maintenance of the AHU systems in building HVAC systems.
Liu Chengning, Liang Xingyu, Shao Liangliang
et al.
Reasonable optimization of the operation strategy is essential for saving energy in the long-term operation of heat pump systems. However, the strategy optimization process is susceptible to load uncertainty, which causes the optimized strategy to save less energy than expected. To address this issue, a method of operation strategy optimization using stochastic load prediction was developed in this study. The method adopts multiple stochastic process samplings to simulate the uncertainty of the load prediction, thereby improving the robustness and energy savings of the operation strategy. The energy-saving properties of the optimization method were verified and analyzed using an air-source heat pump hot-water system. The results show that the novel optimization strategy can reduce the chance of using peak electricity and increase the utilization of off-peak electricity. In the long-term operation simulation, the novel optimization strategy was found to save 6.4% of energy costs compared with the traditional optimization method.
Heating and ventilation. Air conditioning, Low temperature engineering. Cryogenic engineering. Refrigeration
In the context of the "3060 carbon peaking and carbon neutrality goals", promoting energy-efficient transportation and rational utilization is one of the important paths to achieve carbon neutrality, where heat exchangers are known to play a crucial role. Compared with traditional heat exchangers, microchannel heat exchangers significantly reduce the volume while maintaining the same heat exchange capacity. They also significantly improve the heat exchange efficiency and have applications in many important fields. For example, supercritical CO2 (S-CO2) power generation systems, transcritical heat pumps, and refrigeration systems have important application prospects as they are environmentally friendly and offer high-efficiency advantages in the context of the "dual carbon target." Drastic changes in the properties of S-CO2 and the high-temperature and high-pressure requirements of the system pose significant challenges to heat exchanger design, high-temperature and high-pressure resistance, compactness, and efficiency. Therefore, S-CO2 heat exchangers have become a hot topic in scientific and industrial research. In recent decades, significant progress has been made in related research. This paper comprehensively reviews the research progress of microchannel heat exchangers in S-CO2 systems. The paper focuses on different structural forms and design optimization methods of printed circuit heat exchangers (PCHE) and discusses the impact of PCHE optimization on the performance improvement of the entire S-CO2 system. This review provides a comprehensive discussion of S-CO2 microchannel heat exchangers and provides an important reference for the selection, design, and optimization of heat exchangers in systems using CO2 or other supercritical working fluids as the working media for power generation, heat pumps, and refrigeration.
Heating and ventilation. Air conditioning, Low temperature engineering. Cryogenic engineering. Refrigeration
Indoor air pollution, a significant driver of respiratory and cardiovascular diseases, claims 3.2 million lives yearly, according to the World Health Organization, highlighting the pressing need to address this global crisis. In contrast to unconstrained outdoor environments, room structures, floor plans, ventilation systems, and occupant activities all impact the accumulation and spread of pollutants. Yet, comprehensive in-the-wild empirical studies exploring these unique indoor air pollution patterns and scope are lacking. To address this, we conducted a three-month-long field study involving over 28 indoor spaces to delve into the complexities of indoor air pollution. Our study was conducted using our custom-built DALTON air quality sensor and monitoring system, an innovative IoT air quality monitoring solution that considers cost, sensor type, accuracy, network connectivity, power, and usability. Our study also revealed that conventional measures, such as the Indoor Air Quality Index (IAQI), don't fully capture complex indoor air quality dynamics. Hence, we proposed the Healthy Home Index (HHI), a new metric considering the context and household activities, offering a more comprehensive understanding of indoor air quality. Our findings suggest that HHI provides a more accurate air quality assessment, underscoring the potential for wide-scale deployment of our indoor air quality monitoring platform.
To explore the effect of the open structure on the boiling heat transfer of a micro-ribbed rectangular channel, a visual experimental study was conducted on the flow boiling heat transfer performance of open drop-shaped micro-rib channels and compared with the flow boiling heat transfer performance of a water droplet microchannel. At the same time, the flow and growth processes of bubbles under different flow rates in the channel were recorded and analyzed using a high-speed camera. Using deionized water as the working fluid, the inlet temperature was set at 30 °C, with a flow rate of 0.2–7.2 kg/h, heating voltage of 60 V, and shooting frequency of 500 fps. The experimental results show that the opening structure of the micro-fin array affects the flow characteristics. The open structure increases the heat transfer area, which is beneficial for the formation of the vaporization core and heat transfer. At lower and higher Re, the convection heat transfer of the unclosed droplet-shaped micro-fin array is better than that of the water-droplet-shaped micro-fin array. The waiting time and growth time of bubbles in microchannels II and III increase with an increase in Re, and the bubble growth time is greater than the waiting time. In addition, the waiting and growth times of region II were shorter than those of region III.
Heating and ventilation. Air conditioning, Low temperature engineering. Cryogenic engineering. Refrigeration
Air pollution is a pernicious but increasingly rampant health problem in human populations across the globe. Varying duration of exposure to airborne pollutants can result in a plethora of health conditions, ranging from short-term bronchitis to prolonged cardiovascular diseases and lung cancers. Under chronic exposure to pollution, medical treatment for pollutant-caused health conditions can be quite costly. The most immediate and effective way to combat the health detriments of pollution is air purifiers, which take in ambient air and filter out the harmful pollutants before releasing it back into the surroundings. Filters are highly effective at decreasing air pollution, and by association, hospitalizations from exposure. An analysis of 52 common air purifiers was undertaken to compare acquisition and maintenance costs during severe air pollution levels across four counties in California. This approach enables the "cost" of clean air to be put into perspective i.e., the price compared to the cost of healthcare and other expenses, population age, and pre-existing conditions.