Monitoring Of Temperature Distribution Research Articles

Estimation of Temperature Distribution in the Brain Using the Temperatures of Blood Inflow and Outflow for Brain Temperature Control

Brain cells can be damaged by higher temperature in the brain, and brain temperature distribution monitoring system is required from the perspective of brain preservation. Brain tissue can be further damaged by direct measurement of temperature using some sensors. Therefore, indirect methods of measuring temperature are required. In this study, we propose a method for estimating the average metabolic rate of the entire brain based on the difference between the observed and estimated blood flow temperatures that can be measured during selective brain hypothermia. Our mathematical simulator can calculate the brain temperature distribution based on the estimated average metabolic rate, taking into account other parameters like heat transfer, metabolic heat of individual tissues, heat‐washout by blood flow, and environmental temperature. The algorithm for estimating the metabolic rate of mathematical master model substituted as a human head is confirmed using the mathematical slave model on the simulator. It is possible to present the temperature distribution by estimating metabolic heat production in the brain, considering the equilibrium between heat wash‐out by the blood flow and heat transfer. In addition, an appropriate initial value of brain temperature enables the accurate temperature management enough for clinical use even in the process of temperature estimation. The development of our proposed method will make it possible to construct a non‐invasive monitoring system that presents the estimated temperature distribution in the brain instead of the conventional invasive method. The new system is expected to be utilized in a various treatments related to some brain disorders. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Optimal relay nodes placement with game theory optimization for Wireless Sensor Networks

Wireless Sensor Networks (WSN) play a major role in the wide variety of applications like underground pipeline and leaks monitoring, temperature distribution monitoring in industrial cyber systems, military, forest life monitoring, and environmental and geographical monitoring. Sensors are widely used in these different applications. The number of sensors and the application concerned mainly decides the energy consumption, network lifetime. In this process relay nodes may help the sensors as backbone to connect with sink node or base stations. In this paper, we introduce a new approach for relay node selection in WSN to minimize the energy consumption of the network. It uses channel aware relay selection technique using game theory optimization and act as a virtual backbone in connecting to the base station. However, the relay nodes are varied to check the optimal number of relays required for the small, medium and large number of nodes deployed in the network. Simulations are carried out using Network Simulator NS-2.35 and network is analyzed in wide variety of scenarios. Results show that the proposed relay node selection algorithm reduces energy consumption, improves lifetime, throughput of the network.

Integrating Fiber Sensing for Spatially Resolved Temperature Measurement in Fuel Cells

Fiber optic sensors integrated into fuel cell stacks have the potential to significantly enhance the temperature control and health monitoring of fuel cells. Inhomogeneous loading, both within individual cells and across different cells in a stack, leads to the formation of local hotspots that accelerate aging and degrade performance. This study investigates the behavior and feasibility of incorporating polyimide-coated optical fiber sensors into bipolar plates for precise and spatially resolved temperature monitoring. The sensor is successfully integrated into a single cell of a fuel cell stack, positioned on the bipolar plate in direct contact with the membrane. Pre-tests are conducted to thoroughly evaluate the technical properties of the fiber in relation to specific cell requirements. Additionally, a physical prototype featuring the sensor is developed and employed to validate its effectiveness under realistic operating conditions. The temperature measurement obtained via the fiber exhibits a continuous profile throughout the entire length, covering both the active area and distributor region of the cell. Throughout the entire 60 min test period, the measuring system provided continuous and uninterrupted temperature measurements, encompassing the start of the stack, the heating phase, the subsequent stable operating point, and the cooling phase. However, some technical challenges are identified, as mechanical pressure exerted on the fiber influences the measured temperature. While this work demonstrates promising results, further advancements are necessary to address inhomogeneous loading within fuel cells and hotspot mitigation. The precise monitoring of temperature distribution enables early detection of potential damage, facilitating timely interventions to improve the service life and overall performance of fuel cells.

A comparison of ultrasonic temperature monitoring using machine learning and physics-based methods for high-cycle thermal fatigue monitoring

Failure of pipe network components in so-called mixing zones due to high-cycle thermal fatigue (HCTF) can occur within nuclear power plants where fluids of different thermal and hydraulic properties interact. Given that the consequences of such failures are potentially deadly, a method to monitor HCTF non-invasively in real-time is expected to be of great use. This method may be realised by a technique to determine the inaccessible temperature distribution of a component since thermal gradients drive HCTF. Previous work showed that a physics-based method called the inverse thermal modelling (ITM) method can obtain the temperature distribution from external temperature and ultrasonic time of flight (TOF) measurements. This study investigated whether the long-short-term memory (LSTM) machine learning architecture could be a faster alternative to the ITM method for data inversion. On experimental data, a 25-member ensemble of LSTM networks achieved an ensemble median root mean square error (RMSE) of 1.04°C and an ensemble median mean error of 0.194°C (both relative to a resistance temperature device measurement). These values are similar to the ITM method which achieved a RMSE of 1.04°C and a mean error of 0.196°C. The single LSTM network and the ITM method achieved a computation-to-real-world time ratio of 0.008% and 14%, respectively demonstrating that both methods can invert data in real-time. Simulation studies revealed that LSTM performance is sensitive to small differences between the training and real-world parameters leading to unacceptable errors. However, these errors can be detected via an ensemble of independent networks and, corrected by simply adding a correction factor to the TOF prior to being input into the networks. The results show that LSTM has the potential to be an alternative to the ITM method; however, the authors favour ITM for temperature distribution monitoring given its interpretability.

Visual ratiometric optical thermometer with high sensitivity and excellent signal discriminability based on LiScSiO4:Ce3+, Tb3+ thermochromic phosphor.

Developing optical thermometer phosphors with high sensitivity, high signal discriminability and strong fluorescence intensity is ongoing. A dual-emitting thermochromic phosphor, LiScSiO4:Ce3+, Tb3+, was successfully synthesized via solid-state reaction method. The crystal structure, electronic structure, luminescent performance and thermal luminescence behaviors as well as the luminescence mechanism of LiScSiO4:Ce3+, Tb3+ were systematically investigated. Due to the energy transfer and different thermoluminescence behaviors between Ce3+ and Tb3+, high relative sensitivity (2.2% K-1@473K), excellent signal discriminability (5747cm-1), outstanding temperature resolution (0.067K) and good repeatability, as well as efficient emission at high temperatures were achieved based on the fluorescence intensity ratio of Ce3+ and Tb3+, indicating its potential in ratiometric optical thermometer. Moreover, the excellent visualizing thermochromic enable LiScSiO4:Ce3+, Tb3+ to be used as safety sign in variable temperature environment to monitor temperature distribution.

Data-Driven Real-Time Prediction of Pouch Cell Temperature Field Under Minimal Sensing

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). First, empirical spatial basis functions (SBFs) that represent underlying spatial modes of the thermal system are extracted from data snapshots collected offline. Then, we apply the obtained SBFs to the time/space (T/S) separation framework and perform online nonlinear modeling using the partial-node feedback data. On this basis, a dynamics reconstruction strategy is designed for full-node temperature prediction. Experimental studies indicate that the proposed method owns encouraging accuracy and allows minimal sensing configuration. In addition, the error source of the proposed method is systematically analyzed.

A BIM-Based Algorithm for Quantitative Monitoring of Temperature Distribution During Breast Hyperthermia Treatments

Microwave hyperthermia (MH) treatment for breast cancer is a research interest due to its capability to initiate cell necrosis in malignant tumor or to enhance the effect of other treatment modalities such as chemotherapy. The goal of MH treatment is to increase temperature of malignant tumor up to 45°C based on the treatment plan; however, microwave energy focusing is a challenging problem and may cause unwanted hotspots on healthy tissues; therefore, there is a need to monitor the temperature. In this paper, an iterative differential microwave imaging algorithm for temperature monitoring is presented. The algorithm is based on Born iterative method (BIM) and Tikhonov regularization. Feasibility of the algorithm is shown by a large computational study using realistic digital breast phantoms via TM <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">z</sub> polarized 2-D scattered fields. Also, some results are given for calibrated scattering parameters, which are obtained from both a 3-D electromagnetic simulation program and a simple measurement setup. An approach for selection of matching medium in hyperthermia monitoring applications is also presented. The reconstructions are performed with scattered field data collected at 11 discrete frequency points uniformly taken from the 0.5-1.5 GHz range. For a specific heating scenario in 2-D problem, reconstruction error is lower than 0.3% with ±10% noise on reference dielectric property distribution and 40 dB signal to noise ratio (SNR). The results show that the proposed approach provides up to 3°C and 0.1°C resolution in temperature estimation with ±10% noise on reference dielectric property distribution for 30 dB and 60 dB SNR values, respectively.

Implementation of Non-Contact Temperature Distribution Monitoring Solutions for Railway Vehicles in a Sustainability Development System Transport.

The implementation of temperature sensors represented by thermal imaging cameras is becoming increasingly rational. It is playing an important role in the socio-economic environment, in industry, scientific-research work. The main objective of the work is to assess the quality of the railway vehicles in exploitation and their thermal insulation, localise thermal bridges, and the tightness of the body using the FLIR-E6390 thermal inspection camera. An integration of test methods (research methods) was used including a diagnostic method based on a thermographic study integrated with the system approach method and system failure mode effects analysis (SFMEA). The scientific-research work included studies of seven types of railway vehicles in exploitation. A number of conclusions were reached. Specifically providing implementation of innovative and non-contact temperature distribution monitoring solutions for railway vehicles in a sustainability development system transport. Demonstrated the disparities between the different types of vehicles. Next, the identification of critical elements of their thermal insulation, the location of thermal bridges, and the tightness of the body of the rail vehicles, particularly the doors and inter-unit connections. The study covered the state of consumption of stationary electricity (for non-traction needs), implementing innovative indicators for stationary electricity consumption of railway vehicles as a new approach.

VECTOR

Ambient temperature distribution monitoring is desired in a variety of real-life applications including indoors temperature control and building energy management. Traditional temperature sensors have their limitations in the aspects of single point/item based measurements, slow response time and huge cost for distribution estimation. In this paper, we introduce VECTOR, a temperature-field monitoring system that achieves high temperature sensing accuracy and fast response time using commercial sound playing/recording devices. First, our system uses a distributed ranging algorithm to measure the time-of-flight of multiple sound paths with microsecond resolution. We then propose a dRadon transform algorithm that reconstructs the temperature distribution from the measured speed of sound along different paths. Our experimental results show that we can measure the temperature with an error of 0.25°C from single sound path and reconstruct the temperature distribution at a decimeter-level spatial resolution.

Heat loads analysis and creation of a uniform model for commercial refrigeration equipment calculation

The global commercial refrigeration equipment market size was valued at USD 33.53 billion in 2020. It is expected to expand at a compound annual growth rate (CAGR) of 4.2 % from 2021 to 2028. Furthermore, factors such as regulatory pressures, shift to lower Global Warming Potential (GWP) refrigerants, technological breakthroughs, and the ability to cater to the ever-changing consumer behaviors are also anticipated to create promising growth opportunities for the market. Environmental issues related to high GWP refrigerants, including global warming and ozone depletion, are compelling commercial refrigeration equipment manufacturers to seek alternatives. The rising demand for advancements in technologies that can help reduce hazardous gas emissions has led to the market participants increasingly equipping their products with modern and magnetic refrigeration systems. Apart from this, these systems improve the energy efficiency of refrigeration equipment, bringing down the cost of operation.&#x0D; The analysis of the structure and heat loads of the commercial freezer with monitoring of temperature distribution on the body of heat-insulating fences and in the internal volume during operation of the system is carried out. The heat loads on the body depending on the structure of the freezer are substantiated on the example of the M400S commercial freezer model. The obtained results allow to significantly reduce the time of selection and calculation of the dimensions of a given model range of equipment for product storage, by developing a standard calculation taking into account the climatic class in which the equipment will be used, and taking into account experimental data obtained during the experiment

Real-Time Temperature Distribution Monitoring in Chinese Solar Greenhouse Using Virtual LAN

The internal air temperature of Chinese solar greenhouse (CSG) has the problem of uneven spatial and temporal distribution. To determine temperature distribution at different locations, we designed a greenhouse temperature real-time monitoring system based on virtual local area network (VLAN) and estimate, including interpolation estimation module, data acquisition, and transmission module. The temperature data were obtained from 24 sensors, and the Ordinary Kriging algorithm estimated the temperature distribution of the whole plane according to the data. The results showed that the real-time temperature distribution monitoring method established was fast and robust. In addition, data validity rate for VLAN technology deployed for data transmission was 2.64% higher than that of cellular network technology. The following results are obtained by interpolation estimation of temperature data using gaussian model. The average relative error (ARE) of estimate, mean absolute error (MAE), root mean square error (RMSE), and determination coefficient (R2) were −0.12 °C, 0.42 °C, 0.56 °C, and 0.9964, respectively. After simple optimization of the number of sensors, the following conclusions are drawn. When the number of sensors were decreased to 12~16, MAE, RMSE, and R2 were 0.40~0.60 °C, 0.60~0.80 °C, and &gt;0.99, respectively. Furthermore, temperature distribution in the greenhouse varied in the east–west and north–south directions and had strong regularity. The calculation speed of estimate interpolation algorithm was 50~150 ms, and greenhouse Temperature Distribution Real-time Monitoring System (TDRMS) realized simultaneous acquisition, processing, and fast estimate.

Research on the normal emissivity of graphite between 150 and 500 °C by an infrared camera for nuclear fusion devices

• An emissivity measurement equipment by using an infrared camera is constructed and calibrated by a blackbody furnace with a suitable emissivity model. • By using an infrared camera with no filter (band wavelength range of 7.5 μm–13 μm), a 10.2 ± 0.1 μm filter, and a 10.8 ± 0.19 μm filter, the relationship between the temperature and emissivity of graphite and the residual between data and model are obtained respectively and compared. • The emissivity of graphite at different roughness is studied, and uncertainty quantification is used to provide an error estimate for the resulting curves. Due to the advantages of high-temperature resistance, low thermal expansion coefficient, and thermal shock resistance, etc., graphite is regarded as one of the materials for the first wall of nuclear fusion devices. The real-time monitoring of temperature distribution of the first wall based on an infrared camera is widely used to guarantee the stable operation of devices. To accurately measure the temperature of the first wall, it is important to measure the normal emissivity of graphite. However, the emissivity of graphite is affected by many factors. For example, the effect of the surface layers, like carbon-hydro layers-layers, will influence the measurement of the emissivity. The ambition of this work is to study the relationship between graphite emissivity and infrared camera with filters of different wavelengths and the roughness of graphite, and then give the proposed emissivity model to improve the accuracy of graphite surface temperature measurement. The experiment is carried out with a FLIR infrared camera and calibrated by using a blackbody furnace. The emissivity at given temperatures is systematically investigated. By using an infrared camera with no filter (band wavelength range of 7.5–13 μm), a 10.2 ± 0.1 μm filter, and a 10.8 ± 0.19 μm filter, this paper studies the relationship between the temperature and emissivity of graphite from 150 °C to 500 °C and calculates the relative error of temperature measurement respectively. A suitable fitting model which fits emissivity curves is selected. The measurement results show the use of a 10.2 μm filter to measure the graphite surface temperature has the smallest relative error, the range is 0.90%∼1.17%. The emissivity of graphite with different roughness is also studied. At the same temperature, the greater the roughness of the graphite surface, the higher the emissivity value. The uncertainty of the emissivity measurement is analyzed, and its value is 0.0099–0.0211. The graphite surface temperature measurement method based on the emissivity model proposed in this paper provides useful references for the non-contact temperature measurement of the first wall in nuclear fusion devices. The research results can be used as a reference for plasma experiments in some fusion devices and other similar applications.

Co-located dual-wave ultrasonics for component thickness and temperature distribution monitoring

Permanently installed ultrasonic sensors have found increasing applications in the field of structural health monitoring (SHM), in particular with respect to thickness measurement and corrosion monitoring. As ultrasonic velocity is temperature dependent, the state and temperature distribution of a component contribute to much of the measurement uncertainties of an ultrasonic SHM system. On the other hand, the temperature dependency of ultrasonic velocity has also led to various temperature sensing methods for measuring temperature distributions within solid materials. While conventional ultrasound-based techniques can measure either a component’s thickness at a given temperature, or the internal temperature distributions at a given component thickness, measurement fluctuations and drifts can occur if both variables are set to change simultaneously. In this study, we propose a dual-wave approach to overcome the limitations of the existing methods. ‘Co-located’ shear and longitudinal pulse-echo measurements are used to simultaneously track the thickness change and through-thickness temperature variation of a steel plate in complex environmental conditions. Results of the verification experiments showed that, in the given conditions, the proposed dual-wave correction method could reduce thickness measurement uncertainties by approximately a factor of 5 and eliminate 90% of the drift in temperature predictions.

Compressive properties and underlying mechanisms of nickel coated carbon nanotubes modified concrete

Nickel coated multi-walled carbon nanotubes (Ni-MWCNTs) having exceptional mechanical properties, thermal conductivity and dispersibility can effectively overlap in cementitious matrix, thus forming an enhanced and thermal conductive network. They are therefore a promising nanofiller for modifying cement and concrete materials. This paper studies the compressive properties of reactive powder concrete (RPC) filled with different aspect ratios of Ni-MWCNTs, including strength, toughness, Young's modulus and Poisson’s ratio. It is concluded that the incorporation of 0.06 vol.% Ni-MWCNTs with an aspect ratio of 1500 maximally increases the compressive strength and toughness of RPC by 20.24%/20.39 MPa and 43.89%/56.35 (N·m), respectively. However, Young's modulus and Poisson's ratio of Ni-MWCNTs modified composites do not significantly be improved. Besides, a constitutive model of Ni-MWCNTs reinforced RPC under uniaxial compression is established based on the continuum damage mechanics theory, reasonably predicting the relationship between compressive strength and deformation of composites. The modification mechanism of Ni-MWCNTs is also investigated through the temperature distribution monitoring inside composites, Scanning Electron Microscope (SEM) observation and energy dispersive x-ray spectrometry (EDS) analysis of Ni-MWCNTs reinforced RPC. The thermal conductive network formed by Ni-MWCNTs in matrix reduces the temperature difference and improves the temperature uniformity inside composites, thereby decreasing thermal stresses, primary cracks and defects of composites. Furthermore, the incorporation of Ni-MWCNTs makes the RPC microstructures dense, decreases the average CaO to SiO2 ratio, and inhibits the development of cracks inside RPC, thus achieving effective enhancement to RPC.

Dual Separation-Based Spatiotemporal Modeling Methodology for Battery Thermal Process Under Nonhomogeneous Boundary Conditions

The monitoring of temperature distribution is critical to the safety performance and cycle life of lithium-ion batteries (LIBs). This article introduces a systematic solution for real-time modeling of the battery thermal process under nonhomogeneous boundary conditions. The proposed method integrates the nonhomogeneity separation and the time-space (T/S) separation. First, the nonhomogeneity separation is designed to homogenize the boundary conditions. Then, the spatiotemporal dynamics can be decomposed by the T/S separation. With the T/S separation, a set of spatial basis functions (SBFs) are designed to deal with the spatial complexity, and then, a corresponding temporal model is constructed to capture the temporal nonlinearity. According to the Rademacher complexity, the generalization bound of the developed model is deduced, thereby ensuring the modeling performance. Experimental studies demonstrate the validity of the proposed modeling method.

Monitoring of a ceramic surface temperature field induced by pulsed Nd:YAG laser

Temperature distribution induced by laser radiation is a very important parameter for an efficient and safe application of lasers in different ceramic processing techniques. This paper presents the results of an infrared thermography application for monitoring temperature distribution on a ceramic surface during Nd:YAG laser irradiation with different fluences and 8ns pulse duration. The FLIR, E40 and SC7200 infrared cameras were used with the aim of recording the maximum temperature in the irradiated zones. It was expected that infrared thermography could give some information related to the heat affected zone and possible damage to the base material. However, the results have shown that infrared cameras, even those with high performance such as SC7200, cannot record the maximum temperature value at the moment of laser operation, but only the average temperature of the bulk sample material after laser pulses. The results of the numerical simulation have confirmed the value of the thermographic measurements. The micro-structure and micromorphology of the ceramic surface before and after the laser treatment were analysed by optical and SEM as well as by examining the roughness of the irradiated and non-irradiated surfaces, while the micro-mechanical changes were analysed by comparing the micro-hardness of the irradiated and non-exposed surfaces.

Temperature distribution in a permafrost-affected rock ridge from conductivity and induced polarization tomography

SUMMARY Knowledge of the thermal state of steep alpine rock faces is crucial to assess potential geohazards associated with the degradation of permafrost. Temperature measurements at the rock surface or in boreholes are however expensive, invasive, and provide spatially limited information. Electrical conductivity and induced polarization tomography can detect permafrost. We test here a recently developed petrophysical model based on the use of an exponential freezing curve applied to both electrical conductivity and normalized chargeability to infer the distribution of temperature below the freezing temperature. We then apply this approach to obtain the temperature distribution from electrical conductivity and normalized chargeability field data obtained across a profile extending from the SE to NW faces of the lower Cosmiques ridge (Mont Blanc massif, Western European Alps, 3613 m a.s.l., France). The geophysical data sets were acquired both in 2016 and 2019. The results indicate that only the NW face of the rock ridge is frozen. To evaluate our results, we model the bedrock temperature across this rock ridge using CryoGRID2, a 1-D MATLAB diffusive transient thermal model and surface temperature time-series. The modelled temperature profile confirms the presence of permafrost in a way that is consistent with that obtained from the geophysical data. Our study offers a promising low-cost approach to monitor temperature distribution in Alpine rock walls and ridges in response to climate change.

In-situ monitoring of temperature distribution in operating solid oxide fuel cell cathode using proprietary sensory techniques versus commercial thermocouples

Real time surface temperature distribution monitoring of Solid Oxide Fuel Cell (SOFC) systems is important to identify temperature related degradation and understand cell performance. This type of monitoring is limited due to the harsh operating environment of SOFC. Therefore, the temperature variation of an operating SOFC is generally predicted by applying modelling tools which take into account the conventional I-V (current (I)-voltage (V)) curve. However, experimentally obtained temperature data is vital for management of high temperature related degradation and for more reliable modelling of the SOFC. In this study, the temperature distribution of the SOFC is in-situ monitored along the entire cell cathode simultaneously, using commercial TCs on the gas flow channel (the present conventional method) alongside the in-house-developed sensor sensing points (SSPs) directly from the cell cathode surface under both open circuit voltage (OCV) and loading conditions. A considerable difference is observed, especially under the loading condition, between the temperature obtained from the TCs and SSPs even from the same locations. Furthermore, the contribution(s) of different parameters on the temperature variation are investigated, including fuel/air amount under OCV, gas cooling effect, contact area effect and flow direction effect under the loading condition for the given SOFC. There is a fivefold increase in spatial resolution, alongside higher temporal resolution, being observed with the implemented sensor compared to the resolution obtained from the conventional TCs, which yields promise for further development and investigation into test cells and stacks.

Fatigue behaviour evaluation of dissimilar polymer joints: Friction stir welded, single and double-rivets

This article focuses on fatigue life assessment of dissimilar lap-joined polymers. The strength of the friction stir welded polypropylene-to-polyethylene specimens under cyclic loading conditions was analysed. The fatigue life of the strongest welds was compared to both the parent material and blind riveting method with single and double-riveted specimens, in order to compare the welded specimens with available commercial joining techniques. The fatigue lives of the friction stir welded and double-riveted specimens are similar, and they are of the same order of magnitude of the highest performing base material. In order to visualize the temperature variation induced by cyclic loading conditions, a thermographic camera was employed to monitor temperature distribution in the failure region during fatigue testing. For the double-riveted and the parent material specimens, thermal fatigue failure occurred due to temperature increase under cyclic loading. For these two types of specimens, thermal failure occurred when the temperature reached approximately 50 °C in the failure region. Both, the friction stir welded and single-riveted specimens behaved differently from the remaining joints without any significant temperature increase during fatigue testing. The friction stir welded joints presented a brittle failure from the retreating side of the weld nugget, which suffers from defect formation when compared to the advancing side. The single-riveted method produced the weakest joint due to the stress concentration on the drilled hole, while adding a secondary rivet in the same overlapped area created strong joints due to the load transfer among the two rivets.

ISOMAP-Based Spatiotemporal Modeling for Lithium-Ion Battery Thermal Process

The real-time monitoring of temperature distribution in lithium-ion batteries (LIBs) is crucial for their safety and optimal operation in electrical vehicles. An accurate and effective thermal model is needed for online temperature monitoring since limited sensors are available in vehicle application. In this paper, a data-based spatiotemporal modeling method is researched for online estimation of temperature distribution of LIBs. First, Isometric Mapping (ISOMAP) method is used for time/space separation and model reduction. Then, the low-dimensional representation can be obtained in terms of ISOMAP based mapping functions. The unknown temporal dynamics in the low-dimensional space can be approximated using neural network model with parameters trained using extreme learning machine (ELM) algorithm. Finally, the spatiotemporal model of the thermal process can be reconstructed by integrating the neural network model and the mapping functions. The generalization bound of the proposed spatiotemporal model can be analyzed using Rademacher complexity. Simulation results showed that the proposed modeling method can model the LIB thermal process very well.