Tribological properties study and prediction of QBe2 beryllium bronze and 7075-T6 aluminum alloys based on machine learning under mixed lubrication DOI
Z.Y. Li,

Lijie Qiao,

Jiaqi Li

и другие.

Proceedings of the Institution of Mechanical Engineers Part J Journal of Engineering Tribology, Год журнала: 2025, Номер unknown

Опубликована: Янв. 15, 2025

Tribological properties of materials exhibit complex and non-linear correlation with working conditions under mixed lubrication. Selecting an appropriate data-driven method to predict tribological is important for accelerating material design preparation. This paper investigates the performance wear mechanisms QBe2 beryllium bronze 7075-T6 aluminum alloy pairs grease lubrication by using pin-on-disk friction tests. The different further predicted four machine learning algorithms: K-nearest Neighbors (KNN), Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF). experimental results both show that reciprocating frequency has most significant influence. dominant include ploughing adhesive wear. Furthermore, among models, SVM model performs best in predicting

Язык: Английский

Exploring the Benefits and Limitations of Digital Twin Technology in Building Energy DOI Creative Commons
Faham Tahmasebinia, Lin Lin,

Shuo Wu

и другие.

Applied Sciences, Год журнала: 2023, Номер 13(15), С. 8814 - 8814

Опубликована: Июль 30, 2023

Buildings consume a significant amount of energy throughout their lifecycle; Thus, sustainable management is crucial for all buildings, and controlling consumption has become increasingly important achieving construction. Digital twin (DT) technology, which lies at the core Industry 4.0, gained widespread adoption in various fields, including building analysis. With ability to monitor, optimize, predict real time. DT technology enabled cost reduction. This paper provides comprehensive review development application energy. Specifically, it discusses background information modeling (BIM) optimization buildings. Additionally, this article reviews management, indoor environmental monitoring, efficiency evaluation. It also examines benefits challenges implementing analysis highlights recent case studies. Furthermore, emphasizes emerging trends opportunities future research, integrating machine learning techniques with technology. The use sector gaining momentum as efforts optimize reduce carbon emissions continue. advancement technologies expected enhance prediction accuracy, efficiency, improve processes. These advancements have focal point current literature potential facilitate transition clean energy, ultimately goals.

Язык: Английский

Процитировано

44
Predicting Daily Heating Energy Consumption in Residential Buildings through Integration of Random Forest Model and Meta-Heuristic Algorithms DOI

Weiyan Xu,

Jielei Tu,

Ning Xu

и другие.

Energy, Год журнала: 2024, Номер 301, С. 131726 - 131726

Опубликована: Май 20, 2024

Язык: Английский

Процитировано

20
Building energy consumption prediction and optimization using different neural network-assisted models; comparison of different networks and optimization algorithms DOI
Sadegh Afzal, Afshar Shokri,

Behrooz M. Ziapour

и другие.

Engineering Applications of Artificial Intelligence, Год журнала: 2023, Номер 127, С. 107356 - 107356

Опубликована: Ноя. 9, 2023

Язык: Английский

Процитировано

40
Existing industrial buildings – A review on multidisciplinary research trends and retrofit solutions DOI Creative Commons
Neri Banti

Journal of Building Engineering, Год журнала: 2024, Номер 84, С. 108615 - 108615

Опубликована: Янв. 26, 2024

In order to meet the international goals for a sustainable development, it is mandatory implement energy saving solutions on existing buildings and industrial ones should be also addressed since industry related consumption covers approximately one third of global demand. Industrial facilities are usually characterized by low overall quality standards performance levels, largely influenced their old age architectural/technological, energy, structural issues. The paper aims at outlining current state research manufacturing facilities, focusing efficiency redevelopment solutions. PRISMA methodology was adopted in initial stages, coupled with computer-aided bibliometric review tool: globally, 203 scientific papers retrieved Web Of Science ScienceDirect databases were analysed. Three main areas interest pointed out referring seismic behaviour, building envelope systems performance, energy-related analysis conducted revealed significant gap literature concerning integrated retrofit serves as robust knowledge base development comprehensive guidelines this peculiar stock.

Язык: Английский

Процитировано

13
Machine learning-based energy monitoring method applied to the HVAC systems electricity demand of an Italian healthcare facility DOI Creative Commons
Marco Zini, Carlo Carcasci

Smart Energy, Год журнала: 2024, Номер 14, С. 100137 - 100137

Опубликована: Март 21, 2024

The buildings energy consumption is a great part of Europe's overall demand. development diagnostic methods capable promptly alerting users in case issues (e.g. mild and progressive decrease systems components performance) crucial for the smart management buildings. Machine learning-based building monitoring reliable approach identifying subtle anomalies demand behaviour. This study presents application systematic procedure to develop method based on machine learning predictive models, ensuring minimal user knowledge requirements. proposed applied electricity various heating, ventilation air conditioning system real Italian healthcare facility. obtained models are exploited apply method, assessing its capability highlight changes Considering that specific implies an increased technical economic effort carry out data collection, present work aimed at benefits such applications. Because high reproducibility relatively simple integration into centralized systems, offers practical solution enhance systems.

Язык: Английский

Процитировано

10
Machine Learning Algorithms for Predicting Energy Consumption in Educational Buildings DOI Creative Commons
Elhabyb Khaoula,

Amine Baïna,

Mostafa Bellafkih

и другие.

International Journal of Energy Research, Год журнала: 2024, Номер 2024, С. 1 - 19

Опубликована: Май 13, 2024

In the past few years, there has been a notable interest in application of machine learning methods to enhance energy efficiency smart building industry. The paper discusses use buildings improve by analyzing data on usage, occupancy patterns, and environmental conditions. study focuses implementing evaluating consumption prediction models using algorithms like long short-term memory (LSTM), random forest, gradient boosting regressor. Real-life case studies educational are conducted assess practical applicability these models. is rigorously analyzed preprocessed, performance metrics such as root mean square error (RMSE), absolute (MAE), percentage (MAPE) used compare effectiveness algorithms. results highlight importance tailoring predictive specific characteristics each building’s consumption.

Язык: Английский

Процитировано

10
A Review on Machine/Deep Learning Techniques Applied to Building Energy Simulation, Optimization and Management DOI Creative Commons

Francesca Villano,

Gerardo Maria Mauro,

Alessia Pedace

и другие.

Thermo, Год журнала: 2024, Номер 4(1), С. 100 - 139

Опубликована: Март 6, 2024

Given the climate change in recent decades and ever-increasing energy consumption building sector, research is widely focused on green revolution ecological transition of buildings. In this regard, artificial intelligence can be a precious tool to simulate optimize performance, as shown by plethora studies. Accordingly, paper provides review more than 70 articles from years, i.e., mostly 2018 2023, about applications machine/deep learning (ML/DL) forecasting performance buildings their simulation/control/optimization. This was conducted using SCOPUS database with keywords “buildings”, “energy”, “machine learning” “deep selecting papers addressing following applications: design/retrofit optimization, prediction, control/management heating/cooling systems renewable source systems, and/or fault detection. Notably, discusses main differences between ML DL techniques, showing examples use The aim group most frequent ML/DL techniques used field highlighting potentiality limitations each one, both fundamental aspects for future approaches considered are decision trees/random forest, naive Bayes, support vector machines, Kriging method neural networks. investigated convolutional recursive networks, long short-term memory gated recurrent units. Firstly, various explained divided based methodology. Secondly, grouping aforementioned occurs. It emerges that efficiency issues while management systems.

Язык: Английский

Процитировано

9
Enhancing office building energy efficiency: neural network-based prediction of energy consumption DOI

Saeed Momeni,

Ayda Eghbalian,

Mohammad Talebzadeh

и другие.

Journal of Building Pathology and Rehabilitation, Год журнала: 2024, Номер 9(1)

Опубликована: Апрель 16, 2024

Язык: Английский

Процитировано

8
Deep learning-enabled integration of renewable energy sources through photovoltaics in buildings DOI Creative Commons

M. Arun,

Thanh Tuan Le, Debabrata Barik

и другие.

Case Studies in Thermal Engineering, Год журнала: 2024, Номер unknown, С. 105115 - 105115

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

8
Future-Proofing EU-27 Energy Policies with AI: Analyzing and Forecasting Fossil Fuel Trends DOI Open Access
Cristiana Tudor, Robert Şova, Pavlos Stamatiou

и другие.

Electronics, Год журнала: 2025, Номер 14(3), С. 631 - 631

Опубликована: Фев. 6, 2025

The energy sector plays a pivotal role in economic development, societal progress, and environmental sustainability, yet heavy reliance on fossil fuels remains major challenge for achieving climate neutrality. Within this context, the European Union (EU-27) has committed to ambitious goals, including carbon neutrality by 2050, making it critical region studying transition. This study analyzes determinants of fuels’ share (SFF) final consumption at aggregate EU-27 level over 19-year period (2004–2022) forecasts trends region’s transition through 2030. Using random forest (RF) regressor, complex nonlinear relationships between SFF six key predictors—GDP, population, industrial production, CO2 emissions, renewable (SRE), intensity—were modeled. Model interpretability was enhanced Shapley additive explanations (SHAP) partial dependence plots (PDPs), revealing emissions SRE as dominant predictors with opposing effects SFF. Interaction highlighted synergistic emission reduction adoption minimizing fuel reliance. GDP, while less influential overall, exhibited significant negative relationship during early growth stages. Forecasts indicate steady decline reliance, from 1.8% 2022 1.33% 2030, supporting EU’s objectives emphasizing importance control. demonstrates transformative potential machine learning explainable AI (XAI) techniques providing actionable insights advance EU-27’s sustainability journey.

Язык: Английский

Процитировано

1