Effective thermal management is crucial for the performance and longevity of devices such as computer chips and batteries. A fundamental challenge in this field is
Based on spatial methods such as standard deviation ellipse and Moran index, this paper visually analyses the spatial patterns that influence the technological innovation of LiB in China, and
With the rapid development of data acquisition and storage technology, spatio-temporal (ST) data in various fields are growing explosively, so many ST prediction methods
This study focuses on the internal temperature field of lithium-ion batteries, aiming to address the temperature variation issues arising from complex operating conditions in new energy batteries. To
Spatial power density evaluation is a topic of relevance to the field of life cycle assessment (LCA). In power generation LCA, not only is the power plant itself considered but
To address this issue, we propose a field spatiotemporal prediction approach based on transfer learning techniques by studying the dynamics of a 3 D thermal field from
Artificial Intelligence (AI) is leading the charge in revolutionizing research methodologies within the field of latent heat storage (LHS) by using phase change materials
These findings establish key spatial scale threshold parameters for thermal safety strategies in transportation and storage scenarios. And the innovative application of FDS
Accurate real-time temperature prediction in electrochemical energy storage systems plays a critical role in enhancing battery performance, extending lifespan, and preventing thermal
The proposed method transcends the limitations of conventional models and not only achieves a fast solution in the thermal full-field, but also the fusion with deep learning in
This paper presents the efficient process of thermal energy storage (TES) operation for heat load balancing in the domestic hot water (DHW) systems of district heating
To address this, the article introduces a spatial energy storage perception model (SESP) for thermal fault detection and localization, utilizing the Transformer architecture for
Spatial analysis isn''t just some buzzword—it''s becoming the difference between profit and loss in thermal storage. Facilities using these methods report 25% faster ROI on average compared to
A highly accurate temperature field prediction model of battery pack characterized by low computational demands and a distinctive ability to capture temporal and
The SGCN is able to realize accurate spatial relationship modeling, while the GRU-TCN is used to fuse spatial and temporal features, enhancing predictive accuracy and
storage, cavern thermal energy storage, and molten-salt thermal energy sto rage. Sensible Sensible solid storage, on the other hand, comprises borehole thermal energy storage and
The variable selection network identifies important variables for temperature prediction, excludes data that have less impact on the prediction results, and weights the
To address this issue, we propose a field spatiotemporal prediction approach based on transfer learning techniques by studying the dynamics of a 3 D thermal field from multiple
The monitoring of temperature distribution is crucial for advanced battery thermal management. This study proposes a data-driven temperature field prediction method
What drives spatial differentiation of carbon storage in Shanxi province? According to the results of geographical detector factors,the dominant driving factors for spatial differentiation of carbon
The battery thermal process, as a typical distributed parameter system (DPS), is critical to battery management. In practice, the process information is often partially known.
To predict the spatial distribution of thermal discharge from a nuclear power plant under construction, we followed the method in "Numerical simulation" and used the MIKE 3 numerical model to simulate
By summarizing the development and characteristics of wind–thermal bundled power system in China and different countries, current research in this field can be clearly
The calculation formula is as follows: (2-5) f e = ∑ E H i f i / ∑ H + R where f e is electricity carbon emission factor; E H i is consumption of various types of fossil energy in
Finally, the results are analyzed on the basis of the predicted temporal scale, spatial scale and input data. It has been observed that most recent papers highlight the importance of short-term
The temperature field prediction of lithium-ion batteries (LIBs) plays a crucial role in the safety of electric vehicles and their lifetime. However, it is essentially a nonlinear
View a PDF of the paper titled Physics-informed Convolutional Neural Networks for Temperature Field Prediction of Heat Source Layout without Labeled Data, by Xiaoyu Zhao
In temperature field prediction, SegNet''s encoder-decoder architecture is particularly adept at extracting spatial features and reconstructing the local distribution of the
The stability of superheated steam temperature (SST) is severely challenged by the adjustment of thermal power plants under a wide-load range. Accurate and efficient
Then the CFD simulation results were trained by BP neural network algorithm, and the "entrance-atrium" three-dimensional temperature field prediction model was
Regarding that data-driven approaches seem promising for temperature prediction, this research offers a unique efficient temperature prediction model. The model
To address this issue, we propose a field spatiotemporal prediction approach based on transfer learning techniques by studying the dynamics of a 3 D thermal field from multiple homogeneous fields.
Therefore, the results underline that a differential and time-accurate model, like the TES-PD, even if one-dimensional, allows a fast and effective prediction of the performance
Accurately predicting the remaining useful life (RUL) of lithium-ion batteries is crucial to ensure the safe and reliable operation of the energy storage and power supply systems. However, RUL
Abstract: The monitoring of temperature distribution is crucial for advanced battery thermal management. This study proposes a data-driven temperature field prediction method for the pouch cell thermal process, a typical distributed parameter system (DPS).
Extensive experiments showed that the physics-reserved spatiotemporal modeling method outperforms a widely used data-driven spatiotemporal modeling method for battery temperature prediction.
As shown in Fig. 1, the physics-reserved spatiotemporal modeling method constructs a composite network to model the battery thermal process. Except for the spatial coordinate (i.e., x) and time variable (i.e., t), the composite network adopts the battery current (i.e., I) and terminal voltage (i.e., V) as two extra control inputs.
This study proposes a data-driven temperature field prediction method for the pouch cell thermal process, a typical distributed parameter system (DPS). First, empirical spatial basis functions (SBFs) that represent underlying spatial modes of the thermal system are extracted from data snapshots collected offline.
Without using physics, the DL method performs worse than the proposed method for battery temperature prediction. That is to say, the physics can improve the performance of spatiotemporal modeling significantly. 4.4.2. Effectiveness of the branch network for parameter identification
The proposed physics-reserved spatiotemporal modeling method constructed a composite network to model the battery thermal process. The settings of the composite network were as follows. The backbone network and the two branch networks had 8 layers. For the first seven layers, each layer contained 80 neurons. There were 60 neurons in the last layer.
