Capacity Analysis Method Research Articles

Enhancing State of Health Prediction Accuracy in Lithium-Ion Batteries through a Simplified Health Indicator Method

Accurately predicting the state of health (SOH) of lithium-ion batteries is crucial for optimizing battery performance and achieving efficient energy management, especially in electric vehicle applications. However, the existing incremental capacity analysis methods, which are mostly based on curve multi-parameter analysis, still have limitations in terms of computation, prediction accuracy, and adaptability to actual operating conditions. This paper conducts an in-depth analysis of the incremental capacity (IC) curve and proposes a feature parameter based on the area under the IC curve. By incorporating charge and discharge data, a weighted health indicator sequence is constructed and three mathematical models are proposed to link health indicators with cycle number, capacity, and SOH. The feasibility of using impedance as an additional input is also explored, despite the challenges of measurement, revealing its potential applications. Validation of the models with different datasets shows that the proposed method achieves both average relative error and root mean square error within 5%, outperforming other methods in terms of minimizing error and ensuring stability. The results demonstrate that the area-weighted incremental capacity method significantly enhances battery health monitoring accuracy, contributing to the development of sustainable and efficient energy storage systems.

Degradation analysis of lithium-ion batteries under ultrahigh-rate discharge profile

Lithium-ion batteries (LIBs) demonstrate significant potential in military applications. While, in application scenarios such as electromagnetic emission, directional energy, LIBs need to be discharged under ultrahigh rates for a long time, which can lead to accelerated performance degradation. To conduct an in-depth study on the degradation behaviour of LIBs under these conditions, this study proposes a peak decomposition method for incremental capacity analysis. This method permits a nuanced quantification of distinct degradation modes within LIBs. The effects of ultrahigh-rate constant-current discharge, ultrahigh-rate pulse discharge, and standard-rate discharge on battery degradation mode are compared. Furthermore, we delve into the fundamental processes potentially underpinning the disparities observed among these degradation modes. The results show that the degradation mode of the batteries aged under ultrahigh-rate discharge profile is dominated by the loss of active material compared with that of the batteries aged under standard-rate discharge profile. Upon reaching 80% state of health, the batteries aged under ultrahigh-rate constant-current discharge and ultrahigh-rate pulse discharge retain 87.3% and 88.51% of their initial active material content, respectively. In addition, lithium plating may have occurred in the charging process of the battery aged under ultrahigh-rate pulse discharge.

A Coupled NMR and Differential Capacity Study of the Consumption of Electrolyte and Additive Components during the Formation Cycle of Li-Ion Pouch Cells

Understanding the side reactions occurring inside lithium-ion cells remain a significant challenge, presenting opportunities for innovation. In this context, we developed a coupled 1H NMR (nuclear magnetic resonance) and dQ/dV (differential capacity) analysis method aimed at enhancing our understanding of these reactions during the formation cycle. Using deuterated acetonitrile as an extraction solvent, we measured the relative consumption of electrolyte components inside different electrolyte, including in 1.2M LiPF6 EC:EMC 3:7 2% VC and 1.2M LiPF6 EC:EMC 3:7 2% VC + 1% DTD electrolytes at different voltage. Our NMR observations were subsequently compared with electrochemical data to better understand and validate the results. These findings offer valuable insights into lithium-ion cell dynamics and mark a significant step towards the advancement of diagnostic techniques.

Shear resistance test analysis and calculation method of shear capacity of UHPC-NC beam without web reinforcement

In order to study the failure phenomenon and shear resistance performance of UHPC-NC beams without web reinforcement, shear resistance tests were carried out on 15 UHPC-NC beams without web reinforcement. The variation parameters were shear span ratio, web thickness, steel fiber content, and compressive stress level. The load-deflection curve, failure phenomenon and crack development of the test beam are analyzed. The test results show that the joint between the top plate and the bottom plate of UHPC-NC I-beam without web reinforcement is the weakest, and the cracked web is easy to be “cut off” at the joint; The “banding crack area” of web is closely related to the shear span ratio, and the width of ribbon area increases with the increase of shear span ratio. The shear capacity of UHPC-NC I-beam without web reinforcement decreases with the increase of shear-span ratio. The shear capacity increases with the increase of web thickness and compressive stress level. The shear capacity has little relationship with steel fiber content, and the initial stiffness of the structure can be improved by applying prestress. Finally, considering the influence of the top slab compression-shear zone and the bottom slab tension-shear zone on the shear capacity of UHPC-NC prestressed composite beams without web reinforcement, the corresponding calculation method of shear capacity is given based on the modified compression field theory and the idea of sub-item superposition, and the applicability of the calculation method is verified by the test results.

Online two-dimensional filter for anti-interference aging features extraction to accurately predict the battery health

Reliable and precise extraction of features plays a critical role in predicting the State of Health (SOH) of lithium batteries. Nevertheless, noise-tainted measurement signal can cause the distortion of differential curves, consequently compromising the accuracy of feature extraction. This paper develops an online two-dimensional filtering framework by fusing the Adaptive Taylor Kalman filter (ATKF) and the Improved Gaussian filter (IGF), applying it to both incremental capacity analysis and differential thermal voltammetry methods. Firstly, the Taylor series is harnessed to construct a state model for the noise-affected measurement signal. Then, an adaptive algorithm is introduced to diminish the dependence on human judgment when configuring variances. Finally, the IGF filters the curve from the two-dimensions of time and period. Experimental results demonstrate that the two-dimensional filtering method exhibits robust noise mitigation capabilities, enhancing the stability of feature extraction while maintaining system causality. Furthermore, this method has strong robustness to battery inconsistency and temperature uncertainty. When applying the proposed filter to extract aging features from battery data provided by CALCE and Oxford datasets, the correlation coefficient between the extracted aging features and SOH increases by 34.75% and 10.71%, respectively. Additionally, the RMSE of the SOH prediction results decreases by 60.57% and 59.46%, respectively.

An implicit stabilized node-based smoothed finite element method for ultimate bearing capacity analysis of strip footing

The node-based smoothed finite element method (NS-FEM) has gained significant attention over the past decade. Nodal integration in NS-FEM, however, may lead to spurious oscillation of deformations of soil mass. To address the spurious oscillation of deformations associated with nodal integration, some stabilization techniques have been developed, but most of the stabilized NS-FEM have been implemented in the explicit finite element framework. The implicit framework, nonetheless, may offer some advantages including the high efficiency, good numerical accuracy, and suitability for handling large load increments and static problems. In this study, a novel stabilized NS-FEM by referring to the Taylor series expansion and incorporating the secant shear modulus, named sNS-FEM-KF(Gs), is developed in the implicit finite element framework. Based on the ultimate bearing capacity analysis of some strip footings, it is found that sNS-FEM-KF(Gs) may effectively eliminate the spurious oscillations observed in NS-FEM, and may resolve the overly-stiff behaviors of soil mass predicted by sNS-FEM-KF which is a reduced version of sNS-FEM-KF(Gs). Even compared to the standard finite element method with the 6-node triangular (T6) elements (i.e. FEM(T6)), sNS-FEM-KF(Gs) with linear 3-node triangular (T3) elements may outperform FEM(T6) in the investigated strip footing problems, indicating its good applicability in geotechnical analysis.

Research on energy storage capacity analysis and short-term load prediction method for new energy high penetration system

The uncertainty of high penetration new energy is strong. After the proportion of electric units is reduced, the flexible resources are suppressed, and the system-level energy storage can effectively relieve the frequency modulation pressure. In this paper, an energy storage capacity analysis method is proposed for new energy high permeability system. The short-term load is predicted by quantile regression analysis, so as to obtain the optimal peak regulation and frequency modulation frequency in operation, so as to further analyze the relationship between new energy permeability, capacity and energy storage power. The results show that the analytical method proposed in this paper can determine the demand capacity of the new energy high permeability system.

Calculation method of deep-water surface conductor bearing capacity based on jetting operation parameters

The surface conductor bears the weight of the Christmas tree, a blowout preventer (BOP), and casings from various layers, and is subject to immense force. It is also affected by the coupling effect of the drilling platform and wellhead load for a long time. The accurate characterization of its bearing capacity is an important guarantee for the safety of deepwater drilling operations. Through the analysis of the installation process, mechanical characteristics, and the theoretical bearing capacity model of the surface conductor, three important stages of jet drilling, lifting up jet string, and running jet string are selected. Carry out the jet operation parameters and vertical force analysis for each stage, reveal the relationship between jet operation parameters and vertical friction of the surface conductor, and establish the real-time bearing capacity calculation model of the surface conductor of each stage. From the operation efficiency and economy, an analysis method of bearing capacity based on an actively pressing downward experiment is established when the well is located in a new block or a shallow block with complex geology. The coefficient of each model is corrected by the known well data, and the adaptability of the bearing capacity checking methods in different stages is evaluated. The results show that the calculation accuracy of the surface conductor bearing capacity model based on jetting operation parameters is more than 85%, and the error is reduced by 20% compared with the conventional model. The calculation accuracy is higher when the calculation is based on the upper friction parameter or lower friction parameter. The calculation method of deep-water surface conductor bearing capacity based on jetting operation parameters has been successfully applied in most deep wells in the South China Sea in recent two years and has become an important method for deep-water surface conductor design, which ensures the stability of the wellhead of deep-water oil and gas wells.

ANALISIS PENGGUNAAN ALAT BERAT TERHADAP WAKTU DAN BIAYA (STUDI KASUS : PROYEK JALAN RAYA BABATBOJONEGORO KM 72-73)

Roads are infrastructure built by the government to facilitate regional development so that they become assets that must be managed and function optimally. The transportation infrastructure and facilities system as a basic infrastructure is a prerequisite for the economic movement of the region, where the supporting system and transportation infrastructure drivers play a major role in the efficiency and effectiveness of regional economic activities. The purpose of this study is to determine the time and cost of using heavy equipment used in Babat-Bojonegoro Highway Project KM 72-73 completion on paving work. 
 This research uses the work capacity analysis method, namely by calculating data to find the working capacity of the heavy equipment used, as a basis for calculating the time and cost required for heavy equipment in the implementation of paving work. 
 From the analysis of the time required by heavy equipment in paving work with a volume of 3612 tons / m3 is 167,5 hours or 24 days. For the total cost of heavy equipment analyzed in paving work amounting to Rp. 405.486.106.

Coupling Dual Nonlinearity of Arch Bridge Bearing Capacity Analysis Method

In order to realistically restore the mechanical properties of the arch bridge under load and damage processes, a coupled dual nonlinear analysis method is established for the arch-bridge load–carrying capacity by considering the effects of bidirectional force transfer and adaptive section stiffness. First, based on the geometric nonlinear theoretical method of bidirectional force transfer, the macroscopic structural deformation of arch ribs under different loading conditions and load levels is preliminarily calculated, including the bending and axial deformation of each section of the arch, which is used to characterize the development of plasticity. According to deformation or strain, the fiber model analysis method is used to determine the true moment–curvature and axial force–curvature development paths of key sections, and then the elastic–plastic flexural and compressive stiffnesses of each section under different deformation states are derived. The elastic–plastic stiffness is substituted back to the geometric nonlinear equations to obtain the deformation and internal force along the arch ribs considering the cross-sectional plasticity. Finally, the above process is cycled until the equivalence condition is satisfied between the structural internal force/deformation and cross-sectional ones. In order to verify the rationality and accuracy of such a coupling method, a model test is carried out on a stiff skeletal concrete suspension chain line arch with a span of 12[Formula: see text]m, whose results match satisfactorily with that of calculated by the coupling dual nonlinearity method. Compared with the method suggested in the code JTG3362-2018, the proposed method can better predict the development of deflection of different arch rib sections, as well as the actual internal force state. The bending moment calculated as per the code is 7–16% larger than the test result at the ultimate capacity state, while the method of this paper is within 5%.

Experimental study on heat transfer performance of high temperature heat pipe under axial non-uniform heat flux

Non-uniform high-temperature large heat flux is commonly encountered in engineering applications, posing challenges to heat transfer processes and affecting system performance. High temperature heat pipes offer an effective solution to mitigate the adverse effects of non-uniform heat flux by leveraging the unique characteristics of their inner alkali metal (or alloy) working fluid, such as high latent heat of vaporization, strong heat flux density, and ability to operate at elevated temperatures. These features enable high temperature heat pipes to achieve excellent isothermal and uniform heat transfer performance, thereby improving overall thermal management in heat transfer systems. Building upon the investigation of the original high temperature heat pipe, this study designed and fabricated a specially shaped high temperature heat pipe with a spherical crown surface as the evaporator. Experimental research was conducted to assess its frozen start-up performance and heat transfer characteristics under the influence of axial non-uniform heat flux. The results were also analyzed theoretically, providing valuable insights into the frozen start-up performance and heat transfer performance of the high temperature heat pipe in the presence of non-uniform heat flux conditions. The analysis results reveal several important findings: (1)The high temperature heat pipe demonstrates its capability to convert axial non-uniform high-temperature large heat flux into a uniform heat flux, thus achieving excellent uniform heat transfer performance. (2)The theoretical solution obtained through the lumped heat capacity analysis method shows satisfactory agreement with the actual frozen start-up process of the high temperature heat pipe. This theoretical reference can aid in the transient analysis of the frozen start-up process under the influence of axial non-uniform high-temperature large heat flux. (3)The experiment investigated the influence of heating power on heat transfer performance and temperature uniformity. The results indicate that the temperature uniformity of the high temperature heat pipe exhibits a trend of initially increasing and then decreasing. Specifically, the best temperature uniformity is achieved when the heating power is 1084.7 W. Moreover, when the heating power is 1197.9 W, the high temperature heat pipe exhibits the lowest equivalent thermal resistance of 0.0265 K/W, indicating the best heat transfer performance. (4) The variable power heating approach demonstrates that increasing the heating power leads to an extension of the effective length of the heat pipe. The most favorable heat transfer performance and temperature uniformity are observed when the heating power is set to 1133.7 W, allowing the full length of the condenser of the high temperature heat pipe to participate actively in the heat transfer process. These results can provide quantitative experimental data and theoretical references for improving the thermal shock of non-uniform high-temperature large heat flux.

Comparative Analysis of Bearing Capacity of Pile Foundation Using Van Der Ween, Philipponnat, and Meyerhof Methods

Soil has different characteristics so that it becomes a lot of problems in Civil Engineering construction, especially in foundation planning, it must be done carefully and use several methods as a comparison. This research is to compare the three methods of calculating the bearing capacity of bored pile foundations: Van Der Ween, Phillipponnat, and Meyerhof. The selection of an apposite method in bearing capacity analysis is important to confirm the safety of the building structure. The Van Der Ween Method is a more modern and detailed approach compared to the Meyerhof Method, it takes into account the negative impact of the lateral deformation of the pile, which improves the accuracy of its calculation. The Philipponnat Method is a method that combines aspects of both the Meyerhof Method and the Van der Ween Method, it considers load characteristics and soil properties like Meyerhof, while also accounting for lateral deflection of the piles like Van der Ween. The results show that each method has advantages and disadvantages in determining the bearing capacity of bored pile foundations. Analysis revealed factors such as pile diameter, soil depth, and maximum applied load affect the accuracy of the three methods. This research provides important insights for construction planners in selecting a suitable method for bored pile foundation bearing capacity analysis. It is recommended that soil characteristics and pile geometry be considered before selecting the most appropriate calculation method. This research can be extended by considering other methods and conducting validation through experimental analysis.

Analysis Method for Photovoltaic Absorption Capacity of Distribution Network Based on Risk Quantification and Network Reconstruction

The random characteristics of photovoltaic (PV) power will cause changes in node voltage and line power, which is an important factor affecting the photovoltaic absorption capacity of the distribution network (DN). So as to accurately evaluate the impact of photovoltaic randomness on the absorption capacity of DN, an analysis method of photovoltaic absorption capacity of DN is proposed based on risk quantification. Firstly, a photovoltaic absorption capacity evaluation model is proposed based on risk quantification, which considers the randomness of load and PV power and can improve the accuracy of photovoltaic absorption capacity assessment. Secondly, the photovoltaic absorption capacity DN is calculated with the network topology and photovoltaic access capacity of the DN as the optimization variables. The probabilistic power flow is performed by linear power flow, which effectively improves the calculation speed. Finally, the proposed PV absorption capacity analysis method is simulated and analyzed. The simulation results show that the proposed method can effectively take into account the impact of load and photovoltaic randomness and improve the photovoltaic absorption capacity of DN.

A Battery Capacity Estimation Framework Combining Hybrid Deep Neural Network and Regional Capacity Calculation Based on Real-World Operating Data

Efficient battery capacity estimation is of utmost importance for safe and reliable operations of electric vehicles (EVs). This paper proposes a battery capacity estimation framework based on real-world EV operating data collected from forty electric buses of the same model operating in two cities. First, a reference capacity calculation method is presented by combining the Coulomb counting method with the incremental capacity analysis method. Then the impacts of temperature, current, and State-of-Charge on battery degradation are quantitatively analyzed. Using the historical probability distributions as battery health features, a hybrid deep neural network model that combines a convolutional neural network with a fully-connected neural network is proposed for battery capacity estimation. The validation results show that the proposed model outperforms the state-of-the-art methods and reaches a mean absolute percentage error of 2.79 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> , while maintaining low computational cost.

Deterministic and Probabilistic Analyses of the Bearing Capacity of Screw Cast in Situ Displacement Piles in Silty Soils as Measured by CPT and SDT

The bearing capacity of screw cast in situ displacement piles is mostly unexplored. There is also insufficient research on piles in silty soils. Therefore, five cone penetration tests (CPT) and one piezocone penetration test (CPTu) using direct methods were utilised to determine the load-bearing capacity of four displacement piles in Estonia. In addition to the CPT sounding data, static-dynamic test (SDT) results were used to analyse the load-beating capacity of the piles. Both deterministic and probabilistic methods were used in the analysis. Characteristic values as a 95% reliable mean and 5% fractile values for sounding parameters, according to the Eurocode 7, were included. Additionally, Monte Carlo simulation was included in the reliability-based design (RBD). The bearing capacities of screw cast in situ displacement piles in silty soils, here based on the CPT and SDT sounding data, were similar. The adaptation of SDT results for the CPT direct methods for pile load-bearing capacity analysis certainly deserves attention and further investigation. For both sounding types, the Eurocode 7 method provided the best results for all piles. The results of pile-bearing capacities in the absolute difference varied within ±11% between the average, RBD and characteristic values.

The future capacity prediction using a hybrid data-driven approach and aging analysis of liquid metal batteries

Liquid metal batteries (LMBs) are wildly considered for large-scale energy storage due to the advantages of simple construction, low cost, and long life. It is of great importance to find a reliable and accurate approach to predict the future capacity for battery management and failure evaluation. A hybrid data-driven framework is presented to predict not only the long-term capacity degradation but also the local regeneration. Firstly, the Empirical mode decomposition (EMD) method is employed to decompose original battery capacity data into a residual and some intrinsic mode functions (IMFs). Then based on the data characteristics, Gaussian Process Regression (GPR) and Relevance Vector Machine (RVM) with combined kernel function is utilized to predict the local fluctuations caused by regeneration phenomena and the capacity degradation, respectively. Furtherly, we can obtain accurate capacity prediction by adding individual predicted results. Finally, the aging process and the mechanism of capacity plunge are analyzed by the incremental capacity analysis (ICA) method. The Root Mean Square Error (RMSE) of prediction is 0.117 Ah for a 20 Ah battery and 0.141 Ah for a 50 Ah battery by using the proposed framework. Compared with existing mainstream methods, the proposed framework has a more accurate prediction performance to capture the degradation tendency before the capacity plunge, which indicates the positive promise for practical applications of this framework.

Kinematic horizontal slice method for uplift capacity analysis of plate anchors in nonhomogeneous soils with a nonlinear failure criterion

The reliable estimation of uplift capacity of plate anchors becomes necessary for the safe and cost-effective design of various structures against uplift loads. Uplift capacity studies have traditionally been conducted using semi-analytical methods based on plasticity theories, and the previous research has primarily focused on homogeneous soils and a linear failure criterion. Soils, in general, are nonhomogeneous and exhibit nonlinear shear strength behavior. The present study proposes a novel kinematic horizontal slice method within the context of plasticity theory to determine the vertical uplift capacity of various shapes of plate anchors in nonhomogeneous soils using the nonlinear power-law failure criterion. A linear variation of parameters such as initial cohesion, tensile strength, nonlinear coefficient, and unit weight with depth below the ground surface was considered. The effect of nonassociativity for a general nonlinear material has been examined. A detailed parametric study was conducted to explore the effects of various parameters on the uplift capacity of anchors. The results revealed that increasing initial cohesion while decreasing tensile strength, nonlinear coefficient, and unit weight with depth below the ground surface increases anchor uplift capacity, especially for three-dimensional cases. Anchor failure patterns were also investigated for a few parameter combinations. The results of this study were found to be more consistent with those developed in the literature for some specific cases.

Electric vehicle battery state of health estimation using Incremental Capacity Analysis

The state of health (SOH) is an essential indicator for electric vehicle (EV) batteries. It is important to ensure a proper and safe operation of the battery and of great interest for the increasing second-hand market. As the battery is the most expensive EV component the value of the entire vehicle depends on the SOH. The purpose of this work is to develop and verify a non-invasive method to determine the SOH and study the capability of the incremental capacity analysis (ICA) method to estimate SOH of real EVs. The ICA technique is a common method for battery state estimation through the analysis of the voltage changes produced by the electrochemical reactions that occur during charging and discharging. In this work aging tests have been carried out on cells to determine the ICA features with the best performance to estimate the SOH. LMO/NMC-based batteries used in the BMW i3 have been aged and analyzed using ICA. The position of some of the features extracted from the incremental capacity (IC) curve was used to estimate the SOH of the batteries. Subsequently, in order to verify the method, two vehicles with different mileage were tested using similar conditions, obtaining an accurate SOH estimation with an overall root mean square error (RMSE) of 2%. The proposed method has shown to be effective both in cells and in commercial available vehicles, allowing the estimation of SOH during charging and without the need to interfere in the process.

State of health and remaining useful life prediction of lithium-ion batteries based on a disturbance-free incremental capacity and differential voltage analysis method

State of health (SOH) and remaining useful life (RUL) prediction are crucial for battery management systems (BMS). However, accurate SOH and RUL prediction still need to be improved due to the complicated battery aging mechanism. This work combines incremental capacity analysis (ICA) and differential voltage analysis (DVA) based on the second-order RC model with an improved Bidirectional Gated Recurrent Unit (BiGRU) to develop SOH and RUL prediction framework. Firstly, the voltage is reconstructed through the second-order RC model to obtain the incremental capacity (IC) and differential voltage (DV) curves to avoid the influence of measurement noise and the complex parameter adjustment process in the filtering method on the IC and DV curves. Then, a new set of battery aging features are extracted from the reshaped IC and DV curves to improve SOH and RUL prediction accuracy and robustness. Next, the BiGRU method with attention mechanism (BiGRU-AM) is used to build the prediction models for battery aging features, SOH, and RUL. To reduce the impact of the capacity regeneration phenomenon, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) method is used to decompose the SOH prediction results, and the decomposed residual is used as the input to improve the prediction accuracy of RUL. The uncertainty of RUL prediction results is analyzed by Monte Carlo (MC) simulation. Finally, the proposed method is verified by experimental battery data from Center for Advanced Life Cycle Engineering (CALCE) and Sandia National Laboratory. Experimental results show that the voltage reconstruction results based on the second-order RC model are applied to ICA and DVA analysis, effectively avoiding the influence of noise. The RMSE of voltage reconstruction is within 0.0006, and the Pearson correlation coefficient between the four aging features extracted from the reconstructed IC/DV curve and SOH is above 0.9. Moreover, this method has good robustness to the cell inconsistency, temperature uncertainty, and a satisfied generalization ability to different battery chemistries, which the maximum RUL predicted AE of CALCE and Sandia battery is within 10 and 5, respectively.

Digital twin-long short-term memory (LSTM) neural network based real-time temperature prediction and degradation model analysis for lithium-ion battery

Real-time temperature prediction is essential to circumvent thermal safety issues for lithium-ion batteries (LIB). However, its industrial applications are challenging due to operating temperature, voltage range, capacity degradation, and current rate (C-rate) variations. This study proposes a digital twin (DT) technology and long short-term memory (LSTM) neural network-based method for real-time temperature prediction and degradation pattern analysis. The DT model is established based on lumped thermal equivalent circuits to describe the dynamic thermal behavior of LIB and identify the parameters by calculations. Furthermore, the real-time temperature prediction framework considering voltage, current, and operating temperature is further designed following identifying results, which consists of indicators extraction, correlation analysis, LSTM neural network, and DT model four parts. In addition, the incremental capacity analysis (ICA) method is used to analyze LIB degradation patterns. The experimental results indicate that the primary degradation pattern of the experimental sample is loss of lithium inventory (LLI), and the loss of active material (LAM) appears after 600 cycles. Moreover, the maximum error and root mean square error (RMSE) of the temperature prediction framework is 0.31 °C and 0.17 °C under the constant current (CC) discharging condition, 0.85 °C and 0.47 °C under the dynamic discharging condition, respectively. The results demonstrate that the proposed real-time temperature prediction framework delivers acceptable accuracy for CC discharging and dynamic discharging conditions, which can complete the requirements of practical applications. This study dramatically reduces the response time of temperature prediction and guides optimizing battery thermal management systems (BTMS).