Article
Engineering, Chemical
Jun Qi, Jiru Chu, Zhao Xu, Cong Huang, Minglei Zhu
Summary: In this article, a novel neural network-based parallel model predictive control (PMPC) method is proposed to deal with the tracking problem of quadrotor unmanned aerial vehicles (Q-UAVs) system in specific environments. The PMPC algorithm introduces parallel control structure and experience pool replay technology to reconstruct the dynamics model of the UAV system using an NN-based artificial system running in parallel. The accuracy of the reconstructed model is maintained using experience replay technology to ensure the effectiveness of the model prediction algorithm. Numerical results and analysis are provided to demonstrate the effectiveness of the PMPC algorithm.
Article
Automation & Control Systems
Giacomo Galuppini, Enrico F. Creaco, Lalo Magni
Summary: Pressure real-time control is an effective way to address the issue of leakage in water distribution networks. However, current closed-loop control methods only focus on a single node, resulting in poor overall performance. This study proposes a novel multinode RTC approach that considers pressure control at multiple nodes using a Kalman filter, steady-state auxiliary target calculator, and model predictive controller. Simulation results demonstrate satisfactory performance and low computational complexity, making this approach suitable for practical implementation.
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
(2023)
Article
Automation & Control Systems
Christian Kloeppelt, Julian Berberich, Frank Allgoewer, Matthias A. Mueller
Summary: This paper presents a data-driven model predictive control (MPC) scheme that can stabilize unknown linear time-invariant systems by predicting the future system behavior using Willems' lemma. The scheme includes a state-feedback MPC based on input-state data and constraint tightening, and extensions for output feedback control.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2022)
Article
Engineering, Chemical
Ngiam Li Jian, Haslinda Zabiri, Marappagounder Ramasamy
Summary: This study proposes an alternative approach to solve the problem of implementing model predictive controllers in conditions where the timescale multiplicity of the process model is not considered. The proposed method, based on multiple timescale recurrent neural network (MTRNN)-based neural network predictive controllers, effectively handles setpoint tracking scenarios. The optimized MTRNN-based controller exhibits stable response, minimal error, and improved setpoint tracking ability compared to a nonlinear autoregressive exogeneous-based NNPC.
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH
(2023)
Article
Automation & Control Systems
Fei Li, Huiping Li, Shaoyuan Li, Yuyao He
Summary: This article presents an online learning stochastic model predictive control method for linear uncertain systems. The proposed method utilizes probabilistic reachable sets as time-varying tubes to embody the chance constraints by forecasting the variance propagation of uncertainty via Gaussian process regression. The algorithm trains the Gaussian process model of uncertainty online by refining the active data dictionary and selects data points from the raw data around the predicted optimal nominal trajectories to reduce computational load and preserve control performance.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2022)
Article
Automation & Control Systems
Keke Huang, Ke Wei, Fanbiao Li, Chunhua Yang, Weihua Gui
Summary: This article proposes a deep learning based MPC method that uses the LSTM network to predict the behavior of the controlled system. It combines the MPC framework with an adaptive gradient descent method to handle optimization problems and constraints. The proposed method reduces reliance on switching strategies by automatically matching different operating modes, and ensures practical application through stability and feasibility analysis.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Automation & Control Systems
J. M. Manzano, D. Munoz de la Pena, J. Calliess, D. Limon
Summary: The study introduces a data-based predictive controller that offers both robust stability guarantees and online learning capabilities by employing a double-prediction approach. The combination of safe prediction and online learning prediction ensures the safety of the controlled system and allows for incremental learning over time. Sufficient conditions for robust stability and constraint satisfaction are provided, with illustrations given in a simulated case study.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2021)
Article
Automation & Control Systems
Sergio Lucia, Denis Navarro, Benjamin Karg, Hector Sarnago, Oscar Lucia
Summary: This article proposes learning the optimal control policy defined by a complex model predictive formulation using deep neural networks offline, so that the online use of the learned controller only requires evaluating a neural network, improving control efficiency. The research demonstrates the potential of the presented approach in a hardware-in-the-loop setup of a resonant power converter, showing that it can be executed rapidly on embedded hardware.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Construction & Building Technology
Syed Ahsan Raza Naqvi, Koushik Kar, Sandipan Mishra
Summary: This paper investigates the temperature control in shared workspaces with different heating and cooling sources for energy saving and personalized environment. It proposes multiple time-bound control strategies for preparing the workspace before scheduled activities and a separate control strategy for enhancing occupant comfort during occupied intervals. Experimental results show that the proposed strategies significantly save energy and achieve the desired indoor temperature.
ENERGY AND BUILDINGS
(2023)
Article
Engineering, Electrical & Electronic
Gannamraju Siva Kumar, Ravikumar Bhimasingu
Summary: In this study, a new fixed switching frequency-based MPC algorithm for current source rectifier (CSR) is proposed, which can simultaneously control the load and source current, improving the quality of the supply current and the steady state and transient switching performance.
IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS
(2022)
Article
Automation & Control Systems
Fei Li, Huiping Li, Yuyao He
Summary: This paper presents two stochastic model predictive control methods for linear time-invariant systems subject to unbounded additive uncertainties. The methods convert chance constraints into deterministic form and propose soft constraints to enhance feasibility. Numerical simulations demonstrate the effectiveness of these methods.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2022)
Article
Thermodynamics
Zhichen Wei, John Calautit
Summary: With the increasing energy prices and growing concerns over energy security, an accelerated transition to net zero carbon built environment has become more important. Advanced control strategies such as model predictive control (MPC) have been shown to achieve energy efficiency, demand flexibility, and maximize renewable energy production in buildings. This study investigates the potential of integrating price-responsive MPC with a low-temperature heating system and passive structural thermal energy storage (STES), and explores integration with a photovoltaic (PV) system. The results show that this integrated system can achieve higher load shifting ability and lower energy usage under future climate conditions.
Article
Computer Science, Interdisciplinary Applications
Angelo D. Bonzanini, Joel A. Paulson, Georgios Makrygiorgos, Ali Mesbah
Summary: Learning-based multistage MPC (msMPC) introduces Gaussian Processes to adapt scenario trees online for systems with hard-to-model dynamics and time-varying plant-model mismatch, showing promise for control of hard-to-model systems with fast dynamics on millisecond timescales.
COMPUTERS & CHEMICAL ENGINEERING
(2021)
Article
Construction & Building Technology
Qiong Chen, Nan Li
Summary: The research developed a physics-based model for radiant ceiling cooling systems and applied model predictive control to improve zone air temperature control, achieving better thermal comfort and energy efficiency. By simplifying the system model and utilizing advanced control strategies, the proposed approach demonstrated significant potential for enhanced performance compared to traditional control methods.
BUILDING AND ENVIRONMENT
(2021)
Article
Automation & Control Systems
Marvin Jung, Paulo Renato da Costa Mendes, Magnus oennheim, Emil Gustavsson
Summary: The prediction model plays a vital role in MPC strategies as its accuracy directly impacts the quality of predictions and control performance. In cases where a model based on physical equations is not available or difficult to obtain all parameters, using black-box models within the MPC framework is an attractive alternative, as they only require input and output data. This paper discusses questions such as the feasibility of using LSTM as predictors, implementation methods, computation of derivatives, recommended solvers and tools, and ensuring real-time capability.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Construction & Building Technology
Parth Bansal, Steven Jige Quan
Summary: This study investigates the relationship between urban form and canopy layer urban heat island (CUHI) using a relatively large sample of microclimate sensors in Seoul, Korea. The study compares different statistical models and finds that the spatially explicit gradient boosting decision tree (GBDT) model has the highest accuracy. The study also shows that the effect of urban form on CUHI varies at different time instances during the day. These findings provide valuable insights for planners to understand the complexity of urban climate and reduce CUHI magnitude.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Miaomiao Liu, Salah Almazmumi, Pinlu Cao, Carlos Jimenez-bescos, John Kaiser Calautit
Summary: Windcatchers provide effective low-energy ventilation and summer passive cooling in temperate climates. However, their use in winter is limited due to significant ventilation heat loss and potential discomfort. This study evaluates the applicability of windcatchers in low-temperature conditions, highlighting the need for control strategies to reduce over-ventilation and the integration of heat recovery or thermal storage to enhance winter thermal conditions.
BUILDING AND ENVIRONMENT
(2024)
Review
Construction & Building Technology
Behrouz Nourozi, Aneta Wierzbicka, Runming Yao, Sasan Sadrizadeh
Summary: This article presents a systematic review of ventilation solutions in hospital wards, aiming to enhance pathogen removal performance while maintaining patient and healthcare staff comfort using air-cleaning techniques. The study reveals the importance of proper ventilation systems in reducing infection risk and adverse effects of cross-contamination.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Zhen Yang, Weirong Zhang, Hongkai Liu, Weijia Zhang, Mingyuan Qin
Summary: The study examines the influence of personalized local heating on the thermal comfort of occupants in old residential buildings. The findings reveal that personalized local heating can increase the overall thermal sensation of occupants, but only a few methods are effective in enhancing thermal comfort. The chosen heating methods and background temperature affect the participants' selection of heating parts.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Hong Cheng, Dan Norback, Huilin Zhang, Liu Yang, Baizhan Li, Yinping Zhang, Zhuohui Zhao, Qihong Deng, Chen Huang, Xu Yang, Chan Lu, Hua Qian, Tingting Wang, Ling Zhang, Wei Yu, Juan Wang, Xin Zhang
Summary: The home environment and sick building syndrome (SBS) symptoms in five southern Chinese cities have been studied over time. The study found a decrease in asthma prevalence and an increase in allergic rhinitis. Cockroaches, rats, mice, mosquitoes or flies were identified as consistent biological risk factors for SBS symptoms, while redecoration, buying new furniture, and traffic air pollution were identified as other risk factors.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Chaojie Xing, Zhengtao Ai, Zhiwei Liu, Cheuk Ming Mak, Hai Ming Wong
Summary: This study experimentally investigated the emission characteristics of droplets around the mouth during dental treatments. The results showed that the peak mass fraction of droplets occurs within the size range of 20 μm to 100 μm, and droplets with a diameter less than 200 μm account for over 80% of the mass fraction. The dominant emission direction of droplets is towards the dummy's head and chest, forming an approximately cone shape.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Zhijian Liu, Zhe Han, Lina Hu, Chenxing Hu, Rui Rong
Summary: This study compared the effects of different respiratory behaviors on the distribution of aerosols in a ward and the risk of infection for healthcare workers using numerical simulation. It was found that talking in the ward significantly increased aerosol concentrations, particularly short periods of talking. Wards designed with side-supply ventilation had lower overall infection risk. Talking alternately between healthcare workers and patients slightly extended the impact time of aerosols.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Yan Yan, Mengyuan Kang, Haodong Zhang, Zhiwei Lian, Xiaojun Fan, Chandra Sekhar, Pawel Wargocki, Li Lan
Summary: In a high-density city, opening windows for sleep may lead to increased indoor temperature, higher PM2.5 concentration, and noise disturbance, which can negatively impact sleep quality.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Yan Bai, Liang Liu, Kai Liu, Shuai Yu, Yifan Shen, Di Sun
Summary: This study developed a non-intrusive personal thermal comfort model using machine learning techniques combined with infrared facial recognition. The results showed that the ensemble learning models perform better than traditional models, and the broad learning model has a higher prediction precision with lower computational complexity and faster training speed compared to deep neural networks. The findings provide a reference for optimizing building thermal environments.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Yue Lei, Zeynep Duygu Tekler, Sicheng Zhan, Clayton Miller, Adrian Chong
Summary: Mixed-mode ventilation is a promising solution for achieving energy-efficient and comfortable indoor environments. This study found that occupants can thermally adapt when switching between natural ventilation (NV) and air-conditioning (AC) modes within the same day, with the adaptation process stabilizing between 35 to 45 minutes after the mode switch. These findings are important for optimizing thermal comfort in mixed-mode controls, considering the dynamic nature of thermal adaptation.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Nan Mo, Jie Han, Yingde Yin, Yelin Zhang
Summary: This study develops a method based on the LCZ framework for a comprehensive evaluation of urban-scale heat island effects, considering the impact of geographic factors on LST. The results show that Guilin's geomorphological conditions lead to abnormal heat island effects during winter, and the cooling effects of mountains and water bodies vary seasonally in different built areas, with LCZ 2 exhibiting the strongest cooling effect.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Tunga Salthammer
Summary: Monitoring the potential formaldehyde emission of wood-based materials through test chamber investigations has significantly contributed to reducing indoor formaldehyde concentrations. However, the different methodologies used in these procedures prevent direct result comparison. Empirical models for converting formaldehyde steady-state concentrations based on temperature, humidity, air change rate, and loading were developed in the 1970s and have been modified to accommodate the development of lower-emitting materials. Formaldehyde emissions from wood-based materials are complex and require nonlinear regression tools for mathematical analysis.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Katarina Stebelova, Katarina Kovacova, Zuzana Dzirbikova, Peter Hanuliak, Tomas Bacigal, Peter Hartman, Andrea Vargova, Jozef Hraska
Summary: This study investigated the impact of reduced short-wavelength light on the hormone melatonin metabolite 6-sulfatoxymelatonin (u-sMEL) and examined the association between previous day's light exposure and u-sMEL. It was found that reducing short-wavelength light during the day did not change the concentration of u-sMEL. Personal photopic illuminance was positively correlated with u-sMEL in the reference week. The illuminance had a significant impact on u-sMEL, as shown by the evaluation of the mean of all three urine samples. However, this correlation was not found in the experimental week.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Ruoxin Xiong, Ying Shi, Haoming Jing, Wei Liang, Yorie Nakahira, Pingbo Tang
Summary: This study proposes a data-model integration method to identify and calibrate uncertainties in machine learning models, leading to improved thermal perception predictions. The method utilizes the Multidimensional Association Rule Mining algorithm to identify biased human responses and enhances prediction accuracy and reliability. The study also evaluates different calibration techniques and discovers their potential in enhancing prediction reliability.
BUILDING AND ENVIRONMENT
(2024)
Article
Construction & Building Technology
Beichao Hu, Zeda Yin, Abderrachid Hamrani, Arturo Leon, Dwayne McDaniel
Summary: This paper introduces an innovative super-resolution approach to model the air flow and temperature field in the cold aisle of a data center. The proposed method reconstructs a high-fidelity flow field by using a low-fidelity flow field, significantly reducing the computational time and enabling real-time prediction.
BUILDING AND ENVIRONMENT
(2024)