Self-attention variational autoencoder-based method for incomplete model parameter imputation of digital twin building energy systems DOI

Jie Lu,

Chaobo Zhang, Bozheng Li

и другие.

Energy and Buildings, Год журнала: 2024, Номер unknown, С. 115162 - 115162

Опубликована: Дек. 1, 2024

Язык: Английский

Improved robust model predictive control for residential building air conditioning and photovoltaic power generation with battery energy storage system under weather forecast uncertainty DOI Creative Commons
Zehuan Hu, Yuan Gao, Luning Sun

и другие.

Applied Energy, Год журнала: 2024, Номер 371, С. 123652 - 123652

Опубликована: Июнь 12, 2024

Язык: Английский

Процитировано

10
Using machine learning techniques to identify major determinants of electricity usage in residential buildings of Pakistan DOI

Muhammad Sohaib Jarral,

Khuram Pervez Amber, Taqi Ahmad Cheema

и другие.

Journal of Building Engineering, Год журнала: 2025, Номер 100, С. 111800 - 111800

Опубликована: Янв. 7, 2025

Язык: Английский

Процитировано

1
Hybrid Transformer Model with Liquid Neural Networks and Learnable Encodings for Buildings’ Energy Forecasting DOI Creative Commons

Antonesi Gabriel,

Tudor Cioara, Ionuț Anghel

и другие.

Energy and AI, Год журнала: 2025, Номер unknown, С. 100489 - 100489

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

1
A Spatial–Temporal Adaptive Graph Convolutional Network with Multi-Sensor Signals for Tool Wear Prediction DOI Creative Commons
Yu Xia,

Guangji Zheng,

Ye Li

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(4), С. 2058 - 2058

Опубликована: Фев. 16, 2025

Tool wear monitoring is crucial for optimizing cutting performance, reducing costs, and improving production efficiency. Existing tool prediction models usually design integrated based on a convolutional neural network (CNN) recurrent (RNN) to extract spatial temporal features separately. However, the topological structures between multi-sensor networks are ignored, ability limited. To overcome these limitations, novel spatial–temporal adaptive graph (STAGCN) proposed capture dependencies with signals. First, simple linear model used patterns in individual time-series data. Second, layer composed of bidirectional Mamba an convolution established degradation reflect dynamic trend using graph. Third, multi-scale triple attention (MTLA) fuse extracted across spatial, temporal, channel dimensions, which can assign different weights adaptively retain important information weaken influence redundant features. Finally, fused fed into regression estimate wear. Experimental results conducted PHM2010 dataset demonstrate effectiveness STAGCN model, achieving mean absolute error (MAE) 3.40 μm root square (RMSE) 4.32 average three datasets.

Язык: Английский

Процитировано

0
Decoupling prediction of cooling load and optimizing control for dedicated outdoor air systems by using a hybrid artificial neural network method DOI Creative Commons
Yang Cui, Chengliang Fan, Wenhao Zhang

и другие.

Case Studies in Thermal Engineering, Год журнала: 2025, Номер unknown, С. 106046 - 106046

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Estimating air conditioning energy consumption of residential buildings using hourly smart meter data DOI
Jin Xu, Shunjiang Wang, Qinran Hu

и другие.

Journal of Building Engineering, Год журнала: 2024, Номер unknown, С. 110729 - 110729

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

1
Self-attention variational autoencoder-based method for incomplete model parameter imputation of digital twin building energy systems DOI

Jie Lu,

Chaobo Zhang, Bozheng Li

и другие.

Energy and Buildings, Год журнала: 2024, Номер unknown, С. 115162 - 115162

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

0