Thermal Prediction Model Research Articles

An indoor thermal comfort model for group thermal comfort prediction based on K-means++ algorithm

Predicting indoor thermal comfort plays an essential role in controlling energy consumption in buildings. Existing studies have used supervised machine learning to predict thermal comfort, which were more accurate than traditional models. However, these models required occupants’ subjective feedback for model training, which reduced the accuracy of the model. In this study, a prediction model that didn’t require feedback was proposed for the first time using the K-means++ algorithm based on the ASHRAE Global Thermal Comfort Database II. Firstly, the data quality was improved through feature selection, dimensional processing, and feature weighting. Then the influence of different outlier judgment methods, feature weight and data set size on model accuracy were compared. Finally, the K-means++ algorithm was applied for thermal comfort clustering analysis. The result showed that the model with an accuracy higher than 90 % could be constructed using only three factors (CLO, TA, RH), and the proposed model could predict indoor group thermal comfort reliably, and provide a foundation for the indoor thermal sensation evaluation.

A multi-scale modeling approach for predicting and mitigating thermal runaway in electric vehicle batteries

This study presents a unique multi-scale modelling technique for electric vehicle (EV) battery thermal runaway prediction models using electrochemical, thermal, and machine learning approaches. This modelling framework has illuminated the thermal runaway’s physical process and the race between heat production and dissipation at the cell, module, and pack levels.Experimental evaluation has demonstrated solid predictive performance for each component. The modified pseudo-two-dimensional (P2D) electrochemical model has achieved high voltage prediction accuracy (mean absolute error: 8.5 mV), and the 3D thermal model has captured battery module temperatures with an average error of ± 1.5 °C.The machine learning model has exhibited 96.8% accuracy, excellent classification precision, and an 18.3-minute early warning time. It was also demonstrated that the integrated multi-scale model outperformed standalone single-scale models with 15% higher prediction accuracy and 32% higher average early warning time.Based on these findings, adaptive cooling techniques, unique charge/discharge procedures, and early isolation methods were created. Simulations showed that these mitigation techniques decreased thermal runaway occurrence by 78% and severity by 93%. Despite its high computing cost, this technique might improve EV battery safety, guide battery pack design, and accelerate EV adoption, which would cut carbon emissions.

Estimation of Canopy Water Content by Integrating Hyperspectral and Thermal Imagery in Winter Wheat Fields

Rapid and accurate estimation of canopy water content (CWC) is important for agricultural water management and food security. Due to the complexity of dynamic changes in water transport during plant growth, estimation of CWC using a single sensor often leads to high uncertainty in the results. Multi-sensor data fusion is one of the solutions to this problem, but suitable spectral preprocessing methods and data fusion methods still need further research. The objectives of this study were to characterize the performance of two varieties at different growth stages under five water stress conditions and screen hyperspectral sensitive spectral bands by using continuous wavelet transform (CWT) and a successive projection algorithm (SPA). Ultimately, the CWC prediction model of winter wheat hyperspectral characteristic bands and thermal imaging information fusion was created using the GRA algorithm. The results showed that canopy temperature parameters and spectral parameters responded significantly to water deficits in winter wheat. Using the CWT-SPA method, a total of 285 hyperspectral feature bands with wavelet decomposition scales ranging from one to eight were selected. The sensitive bands were mainly distributed in the following ranges: 545–561, 746–1348, 1561–1810, and 2122–2430 nm. The GRA algorithm has good multi-source data model fusion capability, and its constructed prediction model based on hyperspectral and thermal image fusion has high accuracy on the canopy water content in winter wheat (R2 = 0.930, RMSE = 5.44%, nRMSE = 7.94%). Compared to the single-feature spectral model (R2 = 0.864, RMSE = 5.92%, nRMSE = 8.63%) and thermal image CWC prediction model (R2 = 0.813, RMSE = 7.22%, nRMSE = 10.49%), the model prediction accuracy based on the GRA algorithm is increased by 7.64% and 13.69%, respectively.

Traditional and contemporary building thermal sensations prediction models in a warm-humid climate

ABSTRACT Passive ways of providing thermal comfort have been intensively researched in many nations. Despite researchers’ strenuous efforts, most studies on thermal comfort concerns are centred on continents such as Asia, America, Europe, and Africa, with a handful of studies comparing building types in the sub-Saharan area. However, none has focused on statistical models to predict the thermal sensations of occupants in traditional and modern structures during the dry season. Hence, this study investigated interior relative humidity, air temperature, and occupants’ thermal feelings in traditional and modern structures in the dry season in Okigwe, Nigeria. The data for this investigation was collected by physically measuring relative humidity and air temperature using data loggers. A longitudinal survey technique was also used to elicit answers from the residents of the selected traditional and modern structures on the thermal feeling of comfort temperature. To predict the inhabitants’ thermal sensations in the building types investigated, two statistical models were developed: ‘TSVt = 0.65 (MITt) – 13.5’ for traditional structures and ‘TSVc = 0.74 (MITc) – 16’ for modern. The comfort range and neutral temperature of ‘3.15 ≤ TSV ≤ 4.85’ 1–7 yielded 26.8°C as the neutral temperature for the occupants of traditional buildings, with the comfort ranging between 25.6°C and 28.2°C. Contemporary building occupants’ neutral temperature and comfort ranges from 25.9°C to 28.2°C. The study therefore recommended the use of the developed models by Architects, Planners, and Designers for predicting the occupants’ sensations of the building types before preliminary investigations and design sketches, as with such information, the designer possesses the necessary tools for providing buildings that are thermally comfortable for maximum comfort and minimal consumption of energy.

Multi-objective cooling control optimization for air-liquid cooled data centers using TCN-BiGRU-Attention-based thermal prediction models

Multi-objective cooling control optimization for air-liquid cooled data centers using TCN-BiGRU-Attention-based thermal prediction models

Experimental study evaluating the performance of thermal conductivity prediction models for air–water saturated weathered sandstone heritage

As a critical parameter, thermal conductivity directly determines the heat transfer and temperature variation within rocks, which can lead to mechanical damage and chemical corrosion. Consequently, understanding the thermal conductivity of stone heritage is vital for assessing their deterioration mechanisms and developing effective conservation strategies. This study obtained sandstone samples from the Yungang Grottoes and subjected them to freeze–thaw cycle experiments to generate weathered sandstone samples. Subsequently, the thermal conductivity of these samples was measured under both dry and water-saturated state using the transient plane source method. To analyze the relationship between air–water saturation, porosity, and thermal conductivity, a saturation influence coefficient was introduced. Thereafter, the effectiveness and applicability of 13 commonly used thermal conductivity mixing law prediction models were evaluated based on experimental data. The results suggested that the influence of water saturation on the thermal conductivity of rocks varies with porosity, and water saturation significantly enhances the thermal conductivity of weathered sandstone. Among the 13 common models, the Geometric mean model was found to be more accurate than other models, with superior performance in both dry (MAE, RMSE, MAPE are 0.148, 0.214, 5.59% respectively) and water-saturated (MAE, RMSE, MAPE are 0.244, 0.170, 8.4% respectively) state. The Albert model demonstrates a good fit in the dry state, whereas the Walsh model (with maximum effect), Ribaud model, and Huang model also exhibit good fitting efficacy in the water-saturated state. This study provides a solid foundation for better predicting the thermal conductivity of weathered stone heritage and developing effective preventive conservation strategies.

The Mechanism of Street Spatial Form on Thermal Comfort from Urban Morphology and Human-Centered Perspectives: A Study Based on Multi-Source Data

The influence of street spatial form on thermal comfort from urban morphology and human-centered perspectives has been underexplored. This study, utilizing multi-source data and focusing on urban central districts, establishes a refined index system for street spatial form and a thermal comfort prediction model based on extreme gradient boosting (XGBoost) and Shapley additive explanations (SHAP). The results reveal the following: (1) Thermal comfort levels display spatial heterogeneity, with areas of thermal discomfort concentrated in commercial zones and plaza spaces. (2) Compared to the human-centered perspective, urban morphology indicators correlate strongly with thermal comfort. (3) The key factors influencing thermal comfort, in descending order of importance, are distance from green and blue infrastructure (GBI), tree visibility factor (TVF), street aspect ratio (H/W), orientation, functional diversity indices, and sky view factor. All but the TVF negatively correlates with thermal comfort. (4) In local analyses, the primary factors affecting thermal comfort vary across streets with different heat-risk levels. In high heat-risk streets, thermal comfort is mainly influenced by distance from GBI, H/W, and orientation, whereas in low heat-risk streets, vegetation-related factors dominate. These findings provide a new methodological approach for optimizing urban thermal environments from both urban and human perspectives, offering theoretical insights for creating more comfortable cities.

Research on The local clothing thermal insulation prediction model with different dress state of indoor occupants

In a dynamic and non-uniform thermal environment, adjusting personal dress states is an effective method for achieving thermal comfort. During this process, clothing thermal insulation, as a key parameter in human thermoregulation models, is not uniformly distributed across the body. However, current thermal comfort standards do not provide a direct method for obtaining local clothing thermal insulation. Based on field surveys, this study summarized typical year-round clothing ensembles and common dress states, and tested the local thermal insulation of 40 clothing ensembles and 60 individual garments using a thermal manikin. Subsequently, a prediction model for the local thermal insulation of clothing ensembles was developed based on the overall thermal insulation of individual garments. Meanwhile, it was found that changes in dress state significantly alter the thermal insulation of body parts such as the arms and chest. Simulations conducted using the JOS-3 and UCB models revealed that the lower the ambient temperature, the greater the impact of changes in local clothing thermal insulation on human skin temperature and thermal sensation. Finally, a correction model for different dress states was developed, and comparison with existing models showed the lower root mean square error (RMSE) between the predicted and measured values. This study provides a more accurate and convenient method for determining local thermal insulation, offering a data foundation for improving indoor environmental control and enhancing energy efficiency.

A temperature-sensitive points selection method for machine tool based on rough set and multi-objective adaptive hybrid evolutionary algorithm

Reasonable deployment of temperature sensors is the key to accurately monitoring the temperature field of machine tools and improving the accuracy of thermal error prediction and compensation models. To determine the optimal deployment location of sensors, this paper proposes a temperature-sensitive points selection method tightly coupled with rough set and multi-objective optimization. Firstly, the importance of each temperature measurement point to the thermal error is calculated based on the rough set, and information entropy is introduced to amplify the importance difference among adjacent measurement points at the same heat source. Then, with the temperature measurement points groups as the variables, the number of temperature measurement points in the group, and the information importance of the group as the objectives, a multi-objective attribute reduction model is established, which transforms the temperature-sensitive points selection problem into a discrete multi-objective optimization problem. Finally, a multi-objective adaptive hybrid evolutionary algorithm is proposed, which designs a population initialization method based on mutual information and interval probability, and dynamic adaptive evolutionary parameters to achieve optimal temperature-sensitive points selection. Experiments on the high-speed dry hobbing machine verify the superiority and effectiveness of the proposed method.

Achieving high thermal conductivity and strong bending strength diamond/aluminum composite via nanoscale multi-interface phase structure engineering

Diamond/aluminum composites, as a new generation of thermal management materials, are caught in the dilemma between inhibiting the formation of Al4C3 and improving the performance. Herein, we proposed a strategy for nanoscale multi-interface phase structure engineering, utilizing a combination of magnetron sputtering and vacuum heat treatment to obtain diamond particles with nanoscale TiC-Ti layers. Prolonging the vacuum heating time increases the content of TiC, but results in significant differences in the morphology and coverage of TiC formed on the diamond(100) and (111) facets. First-principles calculations reveal that the work of adhesion and C-Ti reaction tendency of diamond(100)/Ti are stronger than those of diamond(111)/Ti, clarifying the difference in interfacial properties between diamond/Ti and diamond/TiC. Diamond-TiC-Ti configuration obtained in advance contributes to fabricating the composite with diamond-TiC-Al(Al3Ti) structure, and the multi-interface phase structure is beneficial to improve the interface bonding, adjust the acoustic mismatch, and inhibit the formation of Al4C3. (800 °C 0.5 h)@Ti-coated diamond(100 μm)/aluminum composite with the multi-interface phase exhibits excellent thermal conductivity(646 W m−1 K−1) and outstanding bending strength(358 MPa), exceeding 90 % of the theoretical prediction of the differential effective medium model. The performance of (800 °C 0.5 h)@Ti-coated diamond/aluminum composite is about 30 % higher than that of traditional Ti-coated diamond/aluminum composite. The TiC layer formed by increasing the heat treatment time is thicker and discontinuous, leading to a decrease in the thermal conductivity of the composite and a weakening effect of Al4C3 inhibition. We clarified the formation mechanism of interface structure related to diamond orientation by multi-scale characterization. Based on the thermal conductivity prediction models, the interface structures corresponding to different diamond orientations were considered, and the predicted values showed good consistency with the experimental results. By interface modification engineering, we overcome the dilemma of introducing modified layer to inhibit Al-C reaction while leading to additional interface thermal resistance, providing insights into the interfacial thermal transport mechanism.

Enhancing demand response and heating performance of air source heat pump through optimal water temperature scheduling: Method and application

Air source heat pump (ASHP) is a key technology for the electrification of building heating, and its participation in demand response (DR) has important implications for reducing the grid peak load. However, current DR strategies mainly focus on changing the setpoint of indoor temperature, using the building’s thermal mass as a passive thermal storage, while the impacts of water temperature on the performance of ASHP units are often overlooked. Therefore, this study proposes an optimal water temperature scheduling (OWTS) method to respond time–of–use tariffs. It is developed based on a room thermal dynamic prediction model and an ASHP power consumption prediction model, optimizing supply water temperature schedule with objectives of maintaining indoor thermal comfort and reducing heating operating costs. The effectiveness of the OWTS method was tested on a field ASHP system in Beijing, and compared with two benchmark methods. Results demonstrate that the application of the OWTS method can enhance the DR capability of the ASHP heating system, with the average value of Flexibility Factor increasing from 0.134 to 0.728, and can reduce the heating operating costs by 20.8%–43.0%. This study thereby offers a promising method for ASHP heating systems to effectively participate in DR.

An attention-based architecture for predicting thermal stress on turbine blade film hole surface using partial temperature data

The thermal stress of film holes is crucial for the life of turbine blades with double-wall cooling systems. Finite Element Analysis (FEA) is widely used for thermal stress analysis, which requires the entire temperature field as input. However, only partial temperature data can be measured in engineering experiments, which is insufficient for FEA. This study proposed an attention-based deep learning architecture to map partial temperature data to film hole surface thermal stress. A thermal stress dataset with 300 samples of double-wall cooling units was constructed using conjugate heat transfer and FEA simulations and the thermal stress prediction model was trained using this dataset. Compared with the simulation results, the mean relative error (MRE) of the predicted results on the test dataset is 7.43%, and the MRE of peak thermal stress is 2.16%. The impact of the model input composed of different surface groups and sampling schemes on prediction performance was analyzed, and a reference for temperature measurement arrangement that balances accuracy and cost-effectiveness was proposed. Additionally, The impact of input noise on model performance was explored and the results demonstrate that the model trained with noise demonstrated significantly enhanced resistance to noise, and the MRE was about 8%.

Thermal modeling and Machine learning for optimizing heat transfer in smart city infrastructure balancing energy efficiency and Climate Impact

The paper proposes a framework based on deep learning, transfer learning, and multi-objective optimisation to model and optimise heat transfer in smart city infrastructure to make them energy efficient and thermally comfortable. The framework in the paper contains a building thermal dynamics prediction model developed using hybrid CNN-LSTM on an extensive dataset (12.56 metric tonnes) of Indian buildings covering various characteristics, which is then fine-tuned with data from five major Indian cities. This predictive framework has a high generalisation capability of energy consumption and predicting indoor temperature profiles with the mean absolute errors (MAE) of building energy consumption ranging from 8.7 to 12.3 kWh and indoor temperature as 0.6 to 1.1 °C, respectively. Transfer learning is considerably improving the performance of the proposed model in newly added cities, which improved the MAE in the training cities (New Delhi and Mumbai) by 3.6 % and reduced the R^2 to 10.7 %. The multi-objective optimisation involving decision-making processes resulted in energy savings of 15.7 % to 22.3 % and improved comfort levels by 21.8 % to 28.5 % in the evaluated cities. The paper significantly contributes to developing a data-driven, generalisable, and interpretable framework, which can usher how to optimise heat transfer using deep learning to make smart city infrastructure resilient and comfortable. It also provides a novel solution to addressing the problems posed by energy efficiency and climate change in Indian cities. Policymakers and urban planners can utilise these key policy recommendations suggested in the paper to design new, liveable and self-sustaining urban environments in India.

Forecasting regional in-situ thermal conductivity of soil based on tree-based ensemble learning

Borehole heat exchanger is essential component in ground-source heat pumps (GSHPs) for developing geothermal energy, where device efficiency depends on the thermal conductivity of soil. Although the thermal response test is generally used to measure this parameter, its time-consuming and susceptibility to test conditions can impact the accuracy of the test. To address this issue, the study conducted shallow geothermal surveys to establish a comprehensive dataset, enabling the construction of the in-situ thermal conductivity predictive model. By selecting seven input features, four classic tree-based ensemble learning models and stacking algorithms were used. Among all the post-tuned models examined, XGBoost-RF emerged as the standout performer, boasting an impressive R2 value of 0.9809 along with the lowest RMSE and MAE. Notably, it demonstrated generalization capabilities, with errors consistently staying within 5 % during the validation process. Additionally, the SHapley Additive exPlanations (SHAP) was used to enhance the interpretability of the model. Among these, the weighted thermal conductivity of the geotechnical was the most influential feature, while groundwater conditions such as permeability coefficient and aquifer thickness were also significant factors. This study provides a rapid and precise prediction of regional in-situ thermal conductivity. It leads to effective decision-making in the design stage of GSHPs.

BP neural network multi-module green roof thermal performance prediction model optimized based on sparrow search algorithm

Green roofs, as a passive building energy-saving technology, offer a range of benefits including reduced energy consumption and mitigation of the urban heat island effect. To analyze the thermal performance of green roofs more accurately and efficiently, this study introduces a novel predictive model that utilizes a Sparrow Search Algorithm (SSA) optimized Backpropagation Neural Network (BPNN) for forecasting the thermal performance of green roofs in subtropical regions. Compared to traditional BPNN, the SSA-BPNN model enhances the network's convergence and generalization capabilities by optimizing initial weights and thresholds. The model, established using meteorological data from Guangzhou, China, and simulated green roof temperature data, underwent rigorous training and validation. The results indicate that predictive accuracy has significantly improved across all seasons, with substantial reductions in all 12 evaluation metrics, and the model GR3 (SSA-BP) emerging as the optimal model. Particularly in summer, the SSA-BPNN model exhibits the highest accuracy, underscoring its effectiveness for subtropical climates. The findings suggest that the SSA-BPNN model is a powerful tool for sustainable urban planning and green roof design in subtropical regions, marking a significant advancement in the integration of artificial intelligence in environmental engineering.

Assessment of thermal conductivity prediction models for compacted bentonite-based backfill material

Assessment of thermal conductivity prediction models for compacted bentonite-based backfill material

Multi-objective optimization of buildings in urban scale for early stage planning and parametric design

Passive design of buildings in early design stage is essential for energy efficiency and sustainability. In this study, a streamlined tool for parametric study and passive design of buildings in urban scale considering thermal loads and natural lighting performance is presented, which markedly enhances the efficiency of early-stage urban planning. The tool is comprised of three sub-models, including (1) degree-month based annual building thermal load prediction model, (2) simplified climate modification model that takes into account the effects of building layout on solar heat gain and urban heat island, (3) multi-objective optimization algorithm NSGA-II, which optimizes both energy-saving and natural lighting performance. Model validation results show that this tool has an average error of 11.44% and 15.82% in simulating building thermal load compared with Dragonfly and CitySim, and has an average error of 9.9% in predicting average daylight factor compared with Radiance. Multiple optimization scenarios and sensitivity analysis in 10 typical climatic cities were conducted. It is found that in cold and hot climatic cities, it is more beneficial to set energy target as the optimization objective, meanwhile, establishing natural lighting as a constraint, rather than solely minimizing thermal loads. In contrast, the inherently lower thermal loads of buildings in milder climatic cities help to achieve both energy-saving and natural lighting goals, and it is also found that the increased thermal loss due to a higher window-to-wall ratio can be offset by employing thicker wall and roof insulation or by improving building layouts.

Accelerated computational strategies for multi-scale thermal runaway prediction models in Li-ion battery

Numerical simulation techniques have become an important tool in the study of thermal runaway (TR) in lithium-ion batteries (LIB). With the research progress, the complexity of the TR prediction model increases, extending its application from single battery to battery packs and entire vehicle systems. This expansion has led to a significant increase in the computational demands of TR prediction model. The computational efficiency has become a critical issue that cannot be ignored. Therefore, it is meaningful to research and develop accelerated computational strategies for the TR prediction model while ensuring the computational accuracy and stability. This paper introduces specific accelerated computational strategies to tackle this challenge. The stability and accuracy of these strategies are validated using 2D and 3D models developed with OpenFOAM software, and the speed up effect from coupling of different accelerated schemes is also analysed. The results show that, compared with the traditional prediction model, coupling various accelerated strategies can speed up the 2D model by a factor of 4.91x and 3D model by a factor of 6.07x. The optimized models with accelerated computational strategies substantially improve the ability to handle complex working conditions, large-scale models and TR propagation problems.

System reliability study of geothermal energy walls in subway stations based on rapid thermal performance prediction model

The energy conservation potential of relative systems in subway stations can be improved via the implementation of energy walls. However, current research mainly focuses on analyzing the factors affecting the energy walls' heat transfer performance, neglecting the reliability and performance assessment for ground source heat pump systems based on energy walls. This paper focuses on a subway station in hot-summer and cold-winter climate zone. Initially, both a resistance-capacity model and a 3D finite element model of energy walls are established. The resistance-capacity model is validated to be integrated with heat pump units to propose the rapid system performance prediction. Subsequently, the system thermal performance with the input of dynamic loads and conventional operational strategies is investigated. The results reveal that due to the heating and cooling load imbalance, the system inevitably experiences thermal imbalances and enters an inefficient operational state by the 6th year. Finally, to address this issue, a hybrid heat pump system with cooling towers is proposed, which demonstrates better thermal performance when used during non-cooling seasons. Another hybrid heat pump system for simultaneous cooling and heating is also proposed. These approaches both delay the onset of the system's inefficient operational state by 1–2 years, thereby improving the thermal performance.

High-temperature thermal fatigue of Ni3Al-based single crystal alloy affected by wall thickness and peak temperature

Complex thin-walled structures are commonly employed in turbine components to improve cooling efficiency. However, thin-walled blades are prone to thermal fatigue failure due to the high thermal stress induced by frequent and abrupt temperature fluctuations during duty cycles. The thermal fatigue behavior of Ni3Al-based single crystal alloy with thin-walled structure during 25 °C ↔ 1000 °C/1100 °C was investigated by combining thermal fatigue tests and finite element simulation. The thermal fatigue demonstrated a significant thickness debit effect, with thermal fatigue property dropping as peak temperature and wall thickness increased. Wall thickness had a more pronounced effect than peak temperature. Visible slip traces were found on the wall thickness surface, and their density was positively correlated with wall thickness. Further investigation revealed that thermal fatigue is primarily driven by the octahedral slip system ({111}<110>), with significant contributions from (111)[101‾] and (1‾1‾1)[101]. Simulations of thermal stress distribution and J-integral at the crack tip during crack initiation and propagation stages indicated that wall thickness influences thermal fatigue properties by affecting thermal stress concentration at the notch and crack tip. Higher peak temperatures increased thermal stress and reduced yield strength, thus diminishing thermal fatigue performance. A thermal fatigue crack propagation prediction model was constructed incorporating Paris' law and the J-integral. The model revealed an unfavorable correlation between material Cj/ nj and both peak temperature/wall thickness, indicating that both factors adversely affect thermal fatigue resistance.