Cycle Life Prediction Research Articles

RUL Prognostics

With the rising complexity of manufacturing processes, resulting from rapid industrial development, the utilization of remaining useful lifecycle (RUL) prediction, based on failure physics and traditional reliability, has remained limited. Although data-driven approaches of RUL prediction were developed using machine learning algorithms, uncertainty-induced challenges have emerged, such as sensor noise and modeling error. To address these uncertainty-induced problems, this study proposes a stochastic ensemble-modeling concept for improving the RUL prediction result. The proposed ensemble model combines artificial degradation patterns and fitness weights, which incorporate formulas reflecting failure patterns and various reliability function data with the observed degradation factor. Furthermore, a recursive Bayesian updating technique, reflecting the difference between expected and observed remaining life sequentially, was leveraged to reduce the prediction uncertainty. Moreover, we comparatively studied the predictive performance of the proposed model (recursive Bayesian ensemble model) against an existing baseline method (exponentially weighted linear regression model). Through simulation and case datasets, this experiment demonstrated the robustness and utility of the proposed algorithm.

Long Short-Term Memory Network with Transfer Learning for Lithium-ion Battery Capacity Fade and Cycle Life Prediction

Machine Learning (ML) is a promising technique for battery health estimation and prediction. However, with more and more types of batteries entering the market, building an ML model from scratch for each new battery requires collecting a large amount of data, which is very expensive and time-consuming. This paper proposes a transfer learning approach to reduce the amount of data that needs to be recollected for a new battery. The key idea is to train an ML model for a new battery of interest (i.e., target battery) with a limited amount of data by transferring the knowledge contained in a well-studied battery (i.e., source battery) with sufficient data. We illustrate this approach using two types of batteries, i.e., the battery with Li0.86Ni0.86Co0.11Al0.03O2-based positive electrode (NCA battery, source battery) and the battery with Li0.84Ni0.83Co0.11Mn0.07O2-based positive electrode (NCM battery, target battery), which have similar degradation patterns but dramatically different cycle life. Specifically, we first pre-train a long short-term memory (LSTM) network, using cycling data of 20 NCA cells at 25 °C and at 45 °C, to predict the following capacity fade based on the previous capacity sequence. Then, to make the model applicable to NCM cells, we employ the transfer learning method to retrain the model, using cycling data of only 2 NCM cells at 25 °C, and propose a two-stage approach to further improve the model performance. The proposed two-stage model can predict the cycle life of NCM cells at 45 °C using the capacities of the first 13 cycles and obtain a cycle life root-mean-squared-error (RMSE) of 25.23 cycles and a capacity trajectory RMSE of 17.80 mAh (0.51 %).

Feature construction for on-board early prediction of electric vehicle battery cycle life

Feature construction for on-board early prediction of electric vehicle battery cycle life

Interpretable Battery Cycle Life Range Prediction Using Early Cell Degradation Data

Battery cycle life prediction using early degradation data has many potential applications throughout the battery product life cycle. For that reason, various data-driven methods have been proposed for point prediction of battery cycle life with minimum knowledge of the battery degradation mechanisms. However, managing the rapidly increasing amounts of batteries at end-of-life with lower economic and technical risk requires prediction of cycle life with quantified uncertainty, which is still lacking. The interpretability (i.e., the reason for high prediction accuracy) of these advanced data-driven methods is also worthy of investigation. Here, a physics-informed Quantile Regression Forest (QRF) model, having the advantage of not assuming any specific distribution of cycle life, is introduced to make cycle life range prediction with uncertainty quantified as the width of the prediction interval, in addition to point predictions with high accuracy. The hyperparameters of the QRF model are optimized with a proposed alpha-logistic-weighted criterion so that the coverage probabilities associated with the prediction intervals are calibrated. The interpretability of the final QRF model is explored with two global model-agnostic methods, namely permutation importance and partial dependence plot.

Early prediction of lithium-ion battery cycle life based on voltage-capacity discharge curves

Accurately predicting the lifetime of lithium-ion batteries is critical for accelerating technological advancements and applications. Nevertheless, the complex aging mechanisms and dynamic operating conditions of lithium-ion batteries have remained major challenges. This paper proposes a method for early predicting lithium-ion batteries cycle life based on weighted least squares support vector machine (WLS-SVM) with health indicators (HIs) as input. The HIs are extracted from lithium-ion batteries voltage-capacity discharge curves, since these curves are easy to measure and strongly correlate to battery cycle life. Taking into account the nonlinearity of batteries cycle life, a support vector machine (SVM) that is capable of strong generalization is used to predict cycle life. As a solution to the problem of misleading results from outlier data in SVM, error square term combined with weight functions is used in this study to improve robustness and prediction accuracy. The datasets of 41 cells are used to verify the proposed early prediction method. The results show that the root mean square error (RMSE) and mean absolute error (MAE) of cycle life prediction results by the proposed method are much lower, and the cycle life early prediction errors of the test cells are all <9 %, which notes that the proposed method is accurate and valid for cycle life early prediction.

A dynamic life cycle assessment model for long-term carbon emissions prediction of buildings: A passive building as case study

Carbon emissions of buildings in the life cycle are huge due to the high resource-intensive and energy consumption of the buildings industry and its upstream industries. And for carbon emissions prediction of the buildings, the life cycle assessment (LCA) with the static parameters input was used to obtain long-term carbon emissions for the buildings in the existed studies. The study presented a dynamic LCA model to predict life cycle carbon emissions of the buildings and optimize the insulation parameter with the improved temporal validation of upstream parameters. A case passive building was selected to perform the dynamic method based on the basic and operational information of this building. The key temporal parameters were collected and predicted via grey prediction. And the electric mix structure was predicted via scenario analysis method. The dynamic life cycle carbon emissions of energy systems were evaluated in different scenarios by the combination of predicting results and historical data. The life cycle carbon emissions of the case building in temporal scenarios reduced approximately 23.4% of that in static scenario. Also, optimal insulation layer thickness in temporal scenarios of and that in static scenario were 130 mm, 120 mm and 250 mm, respectively.

An internet of things enabled framework to monitor the lifecycle of Cordyceps sinensis mushrooms

&lt;em&gt;Cordyceps sinensis&lt;/em&gt; is an edible mushroom found in high quantities in the regions of the Himalayas and widely considered in traditional systems of medicine. It is a non-toxic remedy mushroom and has a high measure of clinical medical benefits including cancer restraint, high blood pressure, diabetes, asthma, depression, fatigue, immune disorder, and many infections of the upper respiratory tract. The cultivation of this kind of mushroom is limited to the region of the Sikkim and to cultivate in the other regions of the country, they are need of investigation and prediction of cordyceps sinensis mushroom lifecycle. From the studies, it is concluded that the precision-based agriculture techniques are limitedly explored for the prediction and growth of &lt;em&gt;Cordyceps sinensis&lt;/em&gt; mushrooms. In this study, an internet of things (IoT) inspired framework is proposed to predict the lifecycle of &lt;em&gt;Cordyceps sinensis&lt;/em&gt; mushrooms and also provide alternate substrate to cultivate &lt;em&gt;Cordyceps sinensis&lt;/em&gt; mushrooms in other parts of the country. As a part of lifecycle prediction, a framework is proposed in this study. According to the findings, an IoT sensor-based system with the ideal moisture level of the mushroom rack is required for the growth of &lt;em&gt;Cordyceps sinensis&lt;/em&gt; mushrooms.

Wafer-level packaging solder joint reliability lifecycle prediction using SVR-based machine learning algorithm

Abstract The development of new electronic packaging structures often involves a design-on-simulation approach. However, simulation results can be subjective, and there can be variances in outcomes depending on who is conducting the simulation. To address this issue, packaging designers are now turning to machine learning to increase the accuracy and efficiency of the design process. This research study focuses on using support vector regression (SVR) techniques, such as single kernel, multiple kernels and a new SVR technique, to predict the reliability of the wafer-level packaging (WLP). By doing so, the study aims to provide designers with a reliable way to assess the reliability life cycle of their packaging designs. This research includes three steps: validating the WLP's reliability using finite element analysis (FEA) and experiment results, using the validated FEA result as input to obtain a predictive model through the SVR technique and the evaluating predictive model's performance. The results show that the predictive models developed using the SVR technique have stable performance on different testing data, which is consistent with the FEA results.

Comparative Analysis of Battery Cycle Life Early Prediction Using Machine Learning Pipeline

Lithium-Ion battery system is one of the most critical but expensive components for both electric vehicles and stationary energy storage applications. In this regard, accurate and reliable early prediction of battery lifetime is important for optimizing life cycle management of batteries from cradle to grave. In particular, accurate aging diagnostics and prognostics is crucial for ensuring longevity, performance, safety, uptime, productivity, and profitability over a battery's lifetime. However, current state-of-art methods do not provide satisfactory prediction performance (lack of uncertainty quantification) using early degradation data. In the present work, to produce the best model for both battery cycle life point prediction and range prediction (i.e., confidence intervals or prediction intervals), a pipeline-based approach is proposed, in which a full 33-feature set is generated manually based on battery degradation knowledge, and then used to learn the best model among five machine learning (ML) models that have been reported in the battery lifetime prediction literature, and two quantile regression models for battery cycle life prediction. The calibration and sharpness property of battery cycle life range prediction is properly evaluated by their coverage probability and width respectively. The experimental results show that the gradient boosting regression tree model provides the best point prediction performance, while the quantile regression forest model provides the best range prediction performance with both full 33-feature set and the MIT 6-feature set.

Assessing the Sustainability of Liquid Hydrogen for Future Hypersonic Aerospace Flight

This study explored the applications of liquid hydrogen (LH2) in aerospace projects, followed by an investigation into the efficiency of ramjets, scramjets, and turbojets for hypersonic flight and the impact of grey, blue, and green hydrogen as an alternative to JP-7 and JP-8 (kerosene fuel). The advantage of LH2 as a propellant in the space sector has emerged from the relatively high energy density of hydrogen per unit volume, enabling it to store more energy compared to conventional fuels. Hydrogen also has the potential to decarbonise space flight as combustion of LH2 fuel produces zero carbon emissions. However, hydrogen is commonly found in hydrocarbons and water and thus it needs to be extracted from these molecular compounds before use. Only by considering the entire lifecycle of LH2 including the production phase can its sustainability be understood. The results of this study compared the predicted Life Cycle Assessment (LCA) emissions of the production of LH2 using grey, blue, and green hydrogen for 2030 with conventional fuel (JP-7 and JP-8) and revealed that the total carbon emissions over the lifecycle of LH2 were greater than kerosene-derived fuels.

Data driven discovery of an analytic formula for the life prediction of Lithium-ion batteries

Predicting the cycle life of Lithium-Ion Batteries (LIBs) remains a great challenge due to their complicated degradation mechanisms. The present work employs an interpretative machine learning of symbolic regression (SR) to discover an analytic formula for LIB life prediction with newly defined features. The novel features are based on the discharging energies under the constant-current (CC) and constant-voltage (CV) modes at every five cycles alternately. The cycle life is affected by the CC-discharging energy at the 15th cycle (E15−CCD) and the difference between the CC-discharging energies at the 45th cycle and 95th cycle (Δ45−95). The cycle life highly correlates with a simple indicator (E15−CCD−3)/Δ45−95 with a Pearson correlation coefficient of 0.957. The machine learning tools provide a rapid and accurate prediction of cycle life at the early stage.

Life prediction model for lithium-ion battery considering fast-charging protocol

With the development of fast-charging technology, fast-charging protocols have been widely used in electric vehicles. However, charging the same type of lithium-ion batteries with different fast-charging protocols has an impact on the cycle life of the battery. Considering the impact of fast-charging protocols on battery life, this paper proposes a life prediction model for lithium-ion batteries that charge with fast-charging protocols. First, the charging-based features are extracted from charge data using dilated convolutional network. Second, the discharging-based features extracted from the discharge curve are enhanced using deep neural network. Finally, the charging-based features and the discharging-based features are merged and fed into random forest regression to predict the cycle life of lithium-ion batteries. Considering that hyperparameters of the model have great influence on the prediction performance, the Bayesian optimization algorithm is used to optimize the hyperparameters of random forest regression. Two public datasets are used for validation. The experimental results show that the proposed method is significantly superior to other existing algorithms for battery cycle life prediction. The relative importance of the charging-based features and the discharging-based features for predicting battery life is also explored.

Ageing Rate of Li-Ion Battery Cells As a Function of Temperature, C-Rate, and State of Health

The ageing rate and consequentially service life of mass-produced lithium-ion batteries depends on many external and internal factors. Some of the more important ones are the charge-discharge rate, ambient temperature, electrode thickness and state of health (SoH). This makes the estimation of the lifetime of battery cells very challenging and time-consuming. This motivates the development of models capable of determining the ageing behavior of a battery cell with relatively little experimental data.In this study1 we build on our previous work2,3 and use Arrhenius plots of the ageing rate to analyze the service life of battery cells in a relatively simple and straightforward way. We cycle aged two types of cells – commercial 5 Ah high-energy 21700 cells with Si/graphite anode (≈3 % Si) and LixNi0.90Co0.05Al0.05O2 + LiyNiO2 (NCA + LNO) cathode and lab-made 0.1 Ah pouch cells with LixNi0.33Mn0.33Co0.33O2 (NMC111) cathode and graphite anode. The ageing is ensured by systematically cycling the cells in a temperature range of -15 °C to 60 °C at various C-rates (0.2 C – 1 C).The capacity fade data is analyzed to obtain the ageing rate (% of SoH per cycle) as a function of temperature, which forms the V-shaped Arrhenius plots shown in Figure 1. Each set of data clearly shows two slopes that cross at intermediate temperatures. As shown previously experimentally2,3 and theoretically,4 the slopes correspond to two ageing mechanisms – lithium plating in the low temperature region and growth of solid-electrolyte interface (SEI) at high temperature region. The intersection of the two Arrhenius slopes denotes a transition between the dominating ageing mechanism and also denotes the optimum temperature at which the battery cell has the highest service life.By analyzing the data, we show that the crossover temperature shifts towards higher temperature values with increasing C-rate and increasing thickness of the anode, as both increase the electrode area-normalized current. The crossover temperature depends on the SoH of the battery. The precise trend depends on the cell chemistry, as we observe increase of the crossover temperature for one type of cells and decrease of crossover temperature for the other type of cells. The shift of the crossover temperature to lower temperatures observed in pouch cells could be explained by a more rapid loss of cyclable lithium, whereas the shift towards higher C-rates observed in commercial 21700 cells can be observed due to increasing practical C-rates as the electrodes degrade and loose some of their initial capacity. By using relatively little input data, we are able to predict the temperature- and C-rate-dependent end of life of a battery cell with good precision.Evaluating the Arrhenius-type dependences of the ageing rate of the battery cells provides valuable insights for use in battery management systems and extending the service life of battery cells. Acknowledgements Gints Kucinskis acknowledges Latvian Council of Science project “Cycle life prediction of lithium-ion battery electrodes and cells, utilizing current-voltage response measurements”, (no. LZP-2020/1-0425). The part of the research performed at ZSW was carried out in the framework of the industrial collective research program (IGF no. 20884 N/2). It was supported by the Federal Ministry for Economic Affairs and Energy (BMWi) through the AiF (German Federation of Industrial Research Associations eV) based on a decision taken by the German Bundestag. References G. Kucinskis, M. Bozorgchenani, M. Feinauer, M. Kasper, M. Wohlfahrt-Mehrens, T. Waldmann, submited to J. Power Sources.T. Waldmann, M. Wilka, M. Kasper, M. Fleischhammer, and M. Wohlfahrt-Mehrens, J. Power Sources, 262, 129–135 (2014) https://linkinghub.elsevier.com/retrieve/pii/S0378775314004352.M. Bozorgchenani, G. Kucinskis, M. Wohlfahrt-Mehrens, and T. Waldmann, J. Electrochem. Soc., 169, 030509 (2022) https://iopscience.iop.org/article/10.1149/1945-7111/ac580d.X.-G. Yang and C.-Y. Wang, J. Power Sources, 402, 489–498 (2018) https://linkinghub.elsevier.com/retrieve/pii/S0378775318310462. Figure 1. Arrhenius plots based on ageing rate for (a-e) commercial 21700 cells at 100 %, 95 %, 90 %, 85 % and 80 % of SoH and (f,g) lab-made pouch cells at 100 % and 95 % SoH. Figure 1

Обоснование системы технического обслуживания и ремонтов перспективных конструкций пути высокоскоростных магистралей

Objective: To create proposals on the system of maintenance for track facilities on the sections with ballastless constructions because the experience in maintaining of such structures is absent. Methods: During the study, the analysis of being predicted life cycle cost of track structure was made. This analysis is based on the study of indicators such as defectiveness of track superstructure elements (rails, fasteners, sleepers), the analysis of being estimated costs on repairing the track using expert evaluation methods. The expert assessment provides for the application of special correction factor. This factor for each maintenance job shows the ratio of job volumes on ballastless track to job volumes on ballast railway track. Results: On the basis of cost calculations and technologies for maintenance, an analysis was pursued of overhaul schemes for sections with ballast railway and for ones with ballastless construction and conclusions were made on required overhaul scheme for a ballastless track structure. Practical importance: The study results are intended to develop a system for planning technical maintenance and repairs of a ballastless superstructure track.

A multi-objective optimization strategy for building carbon emission from the whole life cycle perspective

This research proposed an integrated strategy for building performance optimization from the whole life cycle perspective to explore the optimal building scheme. After the feature elimination, the ensemble learning model (ELM) was trained to obtain a high-precision model for predicting life cycle carbon emissions (LCCE), life cycle costs (LCC), and indoor discomfort hours (IDH). Then, the optimal optimization algorithm was selected among three different optimization algorithms. Finally, the best building scheme was chosen according to the newly proposed solution. The results showed that the ELM could achieve high prediction efficiency by combining input feature evaluation and screening, multi-sampling methods, and hyperparameter optimization. The R2 value of ELM can reach 0.980, while the Two-Archive Evolutionary Algorithm for Constrained multi-objective optimization (C-TAEA) was the optimal optimization algorithm. The best equilibrium solution proposed in this study solved the problem of different optimization ranges of different objectives and maximized the optimization value. Finally, the best equilibrium scheme reduced the LCCE by 34.7%, the LCC by 13.9%, and the IDH by 26.6%. Therefore, this strategy can efficiently optimize building objectives and produce a more balanced and optimal building scheme, thus making it widely applicable in building performance optimization.

Behavior analysis of span structures with cracks during vibrations

Introduction: An important engineering task is to assess the state of span structures during their operation in various conditions and develop a methodology not only for determining the current state of the structure and its individual elements but also for predicting life cycle stages. This work is dedicated to the study of the influence of the location and crack size located in the tension region of the beam cross-section on the value of the natural oscillations frequency of the main beam of the superstructure. The article proposes a method for determining the location and parameters of crack opening in the tension region of a pin-ended beam, which is the span structure base, by analyzing several vibration frequencies. Methods: The bridge crossing beam is modeled using the Euler-Bernoulli-type flexural theory. Crack modeling was carried out using the flexibility function, with the account of the location and length of the crack. A mathematical expression is formulated to determine the location and length of an open crack in the tension region of a pin-ended beam. The MATLAB program was used for numerical studies and simulation modeling of the problem of determining the crack parameters. Results: Values of the bridge girder’s natural resonance frequency with a crack in different places along the span and different lengths of the crack in the tension region of the cross-section were obtained. The relationship between the relative crack length and the relative fundamental beam frequency with a crack for different coordinates of its location and also the relationship between the relative location and the relative fundamental beam frequency with a crack for different crack length values are constructed. These given values are proposed to be used as criterion parameters for assessing the state and possible scenarios for the further operation of the beam span. Discussion: The results obtained show that with an increase in the relative length and relative coordinate of the crack initiation site, the natural frequency decreases. Based on the study results, the conclusion was formulated that cracks in the hinged beam tension region with a relative crack length and a relative location of less than 0.1 deserve the least attention. On the other hand, it is necessary to conduct a study to assess the state of a damaged bridge beam with a relative crack location of more than 0.1 and a relative crack length of less than 0.3, and after the analysis, a decision should be made on the possible modes of further operation of the engineering structures. For span structures whose beams have cracks with a relative crack location of more than 0.1 and a relative crack length of more than 0.3, a detailed study and examination of a structure are required, with the development of recommendations for the required repair work.

Remaining useful cycle life prediction of lithium-ion battery based on TS fuzzy model

Accurately predicting the remaining useful cycle life of a lithium-ion battery is essential for health management of battery systems. Aiming at the time-varying and nonlinear problems of lithium-ion batteries, a remaining useful cycle life estimation method based on Takagi-Sugeno fuzzy model is proposed, which not only reduces the amount of data calculation, but also reduces massive data and has high accuracy. First, collect the rate of change of working voltage in the charging process, and analyze the relationship between the position of voltage rate curve and the number of cycles. Second, in order to reduce the amount of historical data, the interval with obvious mapping relationship is selected, and the recursive least square method is used to fit the curve off-line, which reduces the amount of data calculation and is easy to achieve in battery management system engineering. And then, the Takagi-Sugeno fuzzy model is applied to establish the remaining useful cycle life method based on Takagi-Sugeno fuzzy model. Finally, battery management system application shows that the proposed method can achieve high prediction accuracy and also provides a new perspective for remaining useful cycle life prediction.

Environmental model using life cycle assessment and artificial intelligence techniques to predict impacts on industrial water treatment.

With the advancement of globalization, the growing demand for environmental resources in industrial processes and the increasing availability of data and information, the need to align data modeling concepts with Artificial Intelligence (AI) techniques and existing environmental tools has emerged. From a sustainability perspective, life cycle assessment (LCA) is an extremely important tool in ensuring adequate practices in environmental thinking. It is through the life cycle assessment (LCA) that it is possible to measure the environmental impacts from products and processes, as well as to make projections that minimize these impacts. This research employed an artificial intelligence (AI) methods, namely adaptive neurofuzzy inference system (ANFIS) model, to predict life cycle environmental impacts in industrial water treatment using aluminum sulfate and Tannin-Base biocoagulant. The results show that different AI algorithms are used to build LCA models. The AI algorithms in the studies work from problem identification to the solution stage, so the integration between AI and LCA makes it possible to build predictive machine learning models to enable assertiveness in decision making.

Two-stage aging trajectory prediction of LFP lithium-ion battery based on transfer learning with the cycle life prediction

With the wide application of the LFP lithium-ion batteries, more attention is paid to the battery life and future aging behaviors as the safety and performance of the battery are guaranteed by accurate battery aging monitoring. In recent years, long-term aging trajectory prediction of the lithium-ion battery is always a challenge due to its complex nonlinear aging behaviors especially the aging behaviors in the two aging stages are quite different when the battery experiences the two-stage aging process under fast-charging conditions. Thus, it is harder to achieve accurate long-term aging trajectory prediction of the LFP lithium-ion batteries on the condition of the two-stage aging process. To address it, a novel transfer learning strategy combined with the cycle life prediction technology is presented in this paper. Specifically, a new cycle life prediction method is proposed based on feature extraction and deep learning technology and achieves accurate cycle life prediction. The transfer learning is started by developing a base aging model offline to learn the information of the two-stage aging process. Then, taking the predicted cycle life as its prior information, the Bayesian model migration technology is employed to predict the aging trajectory accurately, and the uncertainty of the aging trajectory is quantified. Two batches of the battery datasets are used for performance evaluation and comparison with two benchmarks. It is novel to combine the cycle life prediction and transfer learning technique to achieve accurate two-stage aging trajectory prediction with only a few data available (first 30%).

A Digital Twin-Driven Life Prediction Method of Lithium-Ion Batteries Based on Adaptive Model Evolution.

Accurate life prediction and reliability evaluation of lithium-ion batteries are of great significance for predictive maintenance. In the whole life cycle of a battery, the accurate description of the dynamic and stochastic characteristics of life has always been a key problem. In this paper, the concept of the digital twin is introduced, and a digital twin for reliability based on remaining useful cycle life prediction is proposed for lithium-ion batteries. The capacity degradation model, stochastic degradation model, life prediction, and reliability evaluation model are established to describe the randomness of battery degradation and the dispersion of the life of multiple cells. Based on the Bayesian algorithm, an adaptive evolution method for the model of the digital twin is proposed to improve prediction accuracy, followed by experimental verification. Finally, the life prediction, reliability evaluation, and predictive maintenance of the battery based on the digital twin are implemented. The results show the digital twin for reliability has good accuracy in the whole life cycle. The error can be controlled at about 5% with the adaptive evolution algorithm. For battery L1 and L6 in this case, predictive maintenance costs are expected to decrease by 62.0% and 52.5%, respectively.