Improving building occupant comfort through a digital twin approach: A Bayesian network model and predictive maintenance method

Energy and Buildings, Journal Year: 2023, Volume and Issue: 288, P. 112992 - 112992

Published: March 23, 2023

This study introduces a Bayesian network model to evaluate the comfort levels of occupants two non-residential Norwegian buildings based on data collected from satisfaction surveys and building performance parameters. A Digital Twin approach is proposed integrate information modeling (BIM) with real-time sensor data, occupant feedback, probabilistic detect predict HVAC issues that may impact comfort. The also uses 200000 points as historical various sensors understand previous systems' behavior. presents new methods for using BIM visualization platform predictive maintenance identify address problems in system. For maintenance, nine machine learning algorithms were evaluated metrics such ROC, accuracy, F1-score, precision, recall, where Extreme Gradient Boosting (XGB) was best algorithm prediction. XGB average 2.5% more accurate than Multi-Layer Perceptron (MLP), up 5% other models. Random Forest around 96% faster XGBoost while being relatively easier implement. paper novel method utilizes several standards determine remaining useful life HVAC, leading potential increase its lifetime by at least 10% resulting significant cost savings. result shows most important factors affect are poor air quality, lack natural light, uncomfortable temperature. To challenge applying these wide range buildings, proposes framework ontology graphs different systems, including FM, CMMS, BMS, BIM. study's results provide insight into influence comfort, help expedite identifying equipment malfunctions point towards solutions, sustainable energy-efficient buildings.

Language: Английский

---

Deep reinforcement learning for multi-objective optimization in BIM-based green building design

Automation in Construction, Journal Year: 2024, Volume and Issue: 166, P. 105598 - 105598

Published: July 4, 2024

Language: Английский

---

Digital Twin framework for automated fault source detection and prediction for comfort performance evaluation of existing non-residential Norwegian buildings

Energy and Buildings, Journal Year: 2022, Volume and Issue: 281, P. 112732 - 112732

Published: Dec. 28, 2022

Numerous buildings fall short of expectations regarding occupant satisfaction, sustainability, or energy efficiency. In this paper, the performance in terms comfort is evaluated using a probabilistic model based on Bayesian networks (BNs). The BN founded an in-depth analysis satisfaction survey responses and thorough study building parameters. This also presents user-friendly visualization compatible with BIM to simplify data collecting two case studies from Norway 2019 2022. paper proposes novel Digital Twin approach for incorporating information modeling (BIM) real-time sensor data, occupants' feedback, comfort, HVAC faults detection prediction that may affect comfort. New methods as platform, well predictive maintenance method detect anticipate problems system, are presented. These will help decision-makers improve conditions buildings. However, due intricate interaction between numerous equipment absence integration among FM systems, CMMS, BMS, integrated into framework utilizing ontology graphs generalize so it can be applied many results aid facility management sector by offering insight aspects influence speeding up process identifying malfunctions, pointing toward possible solutions.

Language: Английский

---

An AI-driven model for predicting and optimizing energy-efficient building envelopes

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 79, P. 480 - 501

Published: Aug. 19, 2023

Unlike many previous studies that often focus on optimizing energy efficiency for buildings when detailed design drawings are available, this paper introduces a newly integrated model energy-efficient building envelope in the early stages (when not yet available). The developed includes three main components: simulation model, predictive and an optimization model. simulates building's performance, considering different values various parameters. employs machine learning algorithms, including RF, ANN, DNN, SVM, GENLIN, GB (in which has been identified as most suitable algorithm), boasting very high R2(0.994) to assess consumption. uses AI algorithms (such NSGA II, DSE, MOPSO) integrates into evaluation function during evolutionary process, efficiently searching Pareto-optimal solutions. Results show simultaneous savings cost energy, with of 7.52 % 8.48 or 21.17 0.4 case study Vietnam. This establishes foundation by providing solutions stakeholders assess, can incorporate additional objectives at later stages.

Language: Английский

---

Planning shared energy storage systems for the spatio-temporal coordination of multi-site renewable energy sources on the power generation side

Energy, Journal Year: 2023, Volume and Issue: 282, P. 128976 - 128976

Published: Sept. 2, 2023

Language: Английский

---

Multi-objective optimization of the solar orientation of two residential multifamily buildings in south Brazil

Energy and Buildings, Journal Year: 2023, Volume and Issue: 285, P. 112838 - 112838

Published: Feb. 8, 2023

The shape and orientation of a building influence the energy demand, therefore optimal decisions should only be made rigorously supported by evaluation programs, which allow for measuring demand more precisely. main purpose this research is to evaluate massive residential social housing multifamily buildings find best solar positioning minimize cooling heating demands simultaneously in bioclimatic zone 2 (Cfa) southern region Brazil. To do this, study utilizes multi-objective optimization with genetic algorithm (NSGA-II) simulating thermal behavior EnergyPlus performing Python language programming code, totalizing 80,000 simulations. results showed that could reduce total 4% "H" 22% linear isolated scenario. For condominium condition, reduction 2% typology 8% shape. presented can help engineers architects design energy-efficient address energetic vulnerability same building. Moreover, future work carried out improve constructive pattern replicated all over country, improving surroundings.

Language: Английский

---

Multi-objective optimization of shading devices using ensemble machine learning and orthogonal design of experiments

Energy and Buildings, Journal Year: 2023, Volume and Issue: 283, P. 112840 - 112840

Published: Jan. 31, 2023

Language: Английский

---

Regression-based sensitivity analysis and multi-objective optimisation of energy performance and thermal comfort: Building envelope design in hot arid urban context

Building and Environment, Journal Year: 2023, Volume and Issue: 248, P. 111099 - 111099

Published: Dec. 9, 2023

Language: Английский

---

Building energy consumption optimization method based on convolutional neural network and BIM

Alexandria Engineering Journal, Journal Year: 2023, Volume and Issue: 77, P. 407 - 417

Published: July 7, 2023

The increasing tension of energy supply and demand makes the optimization building consumption more concerned by researchers. Based on theory convolutional neural network BIM (Building Information Modeling), a model is constructed. parameter solving problem solved. In simulation process, calculation same size as Revit's three-dimensional established in eQUEST software, basic analysis parameters model, such geographical location, meteorological data other information, component materials, running time table are set unified standards. was carried out for self-built automatically generated improved DOE-2 file software. body coefficient 0.370, window-wall ratios east, west, south north directions 0.07, 0.21, 0.30 0.16, respectively, which all meet requirements relevant specifications. Compared with scheme before optimization, it found that reduced 24.53%, natural lighting increased 18.98%, pressure par hours 10.57%.

Language: Английский

---

Modeling and optimization method for building energy performance in the design stage

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 87, P. 109019 - 109019

Published: March 8, 2024

Language: Английский

---