Validation of virtual sensor-assisted Bayesian inference-based in-situ sensor calibration strategy for building HVAC systems

Li, Guannan; Xiong, Jiahao; Sun, Shaobo; Chen, Jian

doi:10.1007/s12273-022-0935-7

Cited by 16 publications

(7 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the update of the training parameters in preceding layers can alter the distribution of input data in subsequent layers. To mitigate the influence of numerical disparities on model efficacy and improve computational speed, this study applies Max min normalization [ 18 ]. The normalization equation is as follows:

…”

Section: Experimental Setup and Data Preparationmentioning

confidence: 99%

“…Specifically, an AMD Ryzen 7 4800H processor with Radeon Graphics and 16 GB (3200 MHz) of memory was utilized (Computer equipment from Lenovo Group, China). Prior to experimental evaluation, hyperparameter search was conducted based on the literature [ 18 , 41 ]. The Grid search range for hyperparameter tuning is presented in Table 4 .…”

Section: Experimental Setup and Data Preparationmentioning

confidence: 99%

“…Methods used for building energy predictions are typically categorized into two main approaches: physical methods [ 15 ] and data-driven methods [ 16 , 17 , 18 ]. Physical methods require detailed information about the building energy system for modelling purposes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Study on the Impact of Building Energy Predictions Considering Weather Errors of Neighboring Weather Stations

Li,

Wang,

Zhang

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

Weather data errors affect energy management by influencing the accuracy of building energy predictions. This study presents a long short-term memory (LSTM) prediction model based on the “Energy Detective” dataset (Shanghai, China) and neighboring weather station data. The study analyzes the errors of different weather data sources (Detective and A) at the same latitude and longitude. Subsequently, it discusses the effects of weather errors from neighboring weather stations (Detective, A, B, C, and D) on energy forecasts for the next hour and day including the selection process for neighboring weather stations. Furthermore, it compares the forecast results for summer and autumn. The findings indicate a correlation between weather errors from neighboring weather stations and energy consumption. The median R-Square for predicting the next hour reached 0.95. The model’s predictions for the next day exhibit a higher Prediction Interval Mean Width (139.0 in summer and 146.1 in autumn), indicating a greater uncertainty.

show abstract

…”

Section: Experimental Setup and Data Preparationmentioning

confidence: 99%

Section: Experimental Setup and Data Preparationmentioning

confidence: 99%

See 1 more Smart Citation

Study on the Impact of Building Energy Predictions Considering Weather Errors of Neighboring Weather Stations

Li,

Wang,

Zhang

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…(2) When the building HVAC system practical operational data are used, sensor inherent mearured errors and noise may cause unexpected deviations of EC equations [38], which may affect the model reliability of the in-situ EC-BI based calibration method.…”

Section: Challengesmentioning

confidence: 99%

In-situ sensor calibration for building HVAC systems with limited information using general regression improved Bayesian inference

Xiong

Tang

et al. 2023

Building and Environment

View full text Add to dashboard Cite

“…By learning from recent data, the adaptability and calibration accuracy of the FTC model can be improved. Many data-driven sensor calibration methods have been investigated for different amounts of training data [ 43 ]. Ng et al [ 40 ] proposed an enhanced self-organizing incremental neural network for evaluating the potential of incremental learning.…”

Section: Introductionmentioning

confidence: 99%

Study on Sensor Fault-Tolerant Control for Central Air-Conditioning Systems Using Bayesian Inference with Data Increments

Li,

Wang,

Liu

et al. 2024

Sensors

Self Cite

View full text Add to dashboard Cite

A lack of available information on heating, ventilation, and air-conditioning (HVAC) systems can affect the performance of data-driven fault-tolerant control (FTC) models. This study proposed an in situ selective incremental calibration (ISIC) strategy. Faults were introduced into the indoor air (Ttz1) thermostat and supply air temperature (Tsa) and chilled water supply air temperature (Tchws) sensors of a central air-conditioning system. The changes in the system performance after FTC were evaluated. Then, we considered the effects of the data quality, data volume, and variable number on the FTC results. For the Ttz1 thermostat and Tsa sensor, the system energy consumption was reduced by 2.98% and 3.72% with ISIC, respectively, and the predicted percentage dissatisfaction was reduced by 0.67% and 0.63%, respectively. Better FTC results were obtained using ISIC when the Ttz1 thermostat had low noise, a 7-day data volume, or sufficient variables and when the Tsa and Tchws sensors had low noise, a 14-day data volume, or limited variables.

show abstract

Validation of virtual sensor-assisted Bayesian inference-based in-situ sensor calibration strategy for building HVAC systems

Cited by 16 publications

References 62 publications

Study on the Impact of Building Energy Predictions Considering Weather Errors of Neighboring Weather Stations

Study on the Impact of Building Energy Predictions Considering Weather Errors of Neighboring Weather Stations

In-situ sensor calibration for building HVAC systems with limited information using general regression improved Bayesian inference

Study on Sensor Fault-Tolerant Control for Central Air-Conditioning Systems Using Bayesian Inference with Data Increments

Contact Info

Product

Resources

About