Limited Test Data Research Articles

Natural language processing‐based deep transfer learning model across diverse tabular datasets for bond strength prediction of composite bars in concrete

AbstractAs conventional machine learning models often struggle with scarcity and structural variation of training data, this paper proposes a novel regression transfer learning framework called transferable tabular regressor (TransTabRegressor) to address this challenge. The TransTabRegressor integrates natural language processing (NLP) for feature encoding, transformer for enhanced feature representation, and deep learning (DL) for robust modeling, facilitating effective transfer learning across tabular datasets using reducing input parameters. By leveraging the NLP data processor, the framework embeds both parameter names and values, enabling it to recognize and adapt to different expressions of similar parameters. For instance, the bond strength of fiber‐reinforced polymer (FRP) bars embedded in ultra‐high‐performance concrete (UHPC) is critical for ensuring the integrity of FRP‐UHPC structures. While pullout tests are widely adopted for their simplicity to generate substantial data, beam tests provide a closer approximation to actual stress conditions but are more complex thus resulting in limited data size. As a verification, the framework is applied to predict the bond strength of FRP bars embedded in UHPC using limited beam test data. A pre‐trained model is first established using 479 pieces of pullout test data. Subsequently, two transfer learning models are developed by fine‐tuning on 115 pieces of beam test data, where 66 correspond to concrete splitting failure and 49 correspond to pullout failure. For comparative analysis, XGBoost and neural network models are directly trained on the beam test data. Evaluation results demonstrate that the transfer learning models achieve significantly improved prediction accuracy and generalization capability. This study significantly highlights the effectiveness of the proposed TransTabRegressor in handling data scarcity and variability in input parameters across various engineering applications.

Evaluating the Use of Predicted Cushion Curves for Comparing the Performance of Some Sustainable Cushion Systems

ABSTRACTThis paper studies the cushion performance of a range of sustainable cushion systems and applies two methods to estimate cushion curves from limited cushion test data. The methods employed were previously developed to allow for (1) the conversion of cushion curves representing a material's performance for a given drop height and sample thickness to alternative (non‐measured) drop heights and sample thicknesses and (2) generating a complete cushion curve for a given thickness and drop height from a single acceleration (shock) measurement. The results include those generated for medium‐density polyethylene (MDP) closed‐cell foam for benchmarking of the materials and to aid in validating the approach. The results indicate that predicting cushion curves from single shock measurements is generally accurate for polymeric materials (MDP closed‐sell foam and HDPE inflated bag) but much less so for organic materials (sugarcane bagasse and perforated cardboard). Finally, all alternative cushioning materials and systems evaluated are shown to only be effective for very low static stresses. This finding demonstrates that much higher volumes are required when using the alternative materials to achieve the same cushioning effectiveness as MPD foam.

Nondestructive fatigue life prediction for additively manufactured metal parts through a multimodal transfer learning framework

Understanding the fatigue behavior and accurately predicting the fatigue life of laser powder bed fusion (L-PBF) parts remain a pressing challenge due to complex failure mechanisms, time-consuming tests, and limited fatigue data. This study proposes a physics-informed data-driven framework, a multimodal transfer learning (MMTL) framework, to understand process-defect-fatigue relationships in L-PBF by integrating various modalities of fatigue performance, including process parameters, XCT-inspected defects, and fatigue test conditions. It aims to leverage a pre-trained model with abundant process and defect data in the source task to predict fatigue life nondestructively with limited fatigue test data in the target task. MMTL employs a hierarchical graph convolutional network (HGCN) to classify defects in the source task by representing process parameters and defect features in graphs, thereby enhancing its interpretability. The feature embedding learned from HGCN is then transferred to fatigue life modeling in neural network layers, enabling fatigue life prediction for L-PBF parts with limited data. MMTL validation through a numerical simulation and real-case study demonstrates its effectiveness, achieving an F1-score of 0.9593 in defect classification and a mean absolute percentage log error of 0.0425 in fatigue life prediction. MMTL can be extended to other applications with multiple modalities and limited data.

Study on seismic behavior of corroded reinforced concrete walls in flexural-shear failure

In this study, artificial climate-accelerated corrosion tests and pseudostatic loading tests were conducted on six reinforced concrete (RC) shear walls subjected to flexural-shear failure. The effects of the corrosion degree and axial compression ratio parameters on the seismic performance of RC shear walls were investigated. The corrosion conditions (corrosive cracks and corroded steel bars), failure process, bearing ability, deformation capacity and energy consumption capacity were compared. The test results showed that chlorine salt erosion induced severe deterioration of the properties of the RC shear wall. The internal reinforcement of the specimen was severely corroded near the protective layer. The failure mode of the severely corroded specimens changed from the original flexural-shear failure mode to the bending failure mode. Rebar corrosion markedly decreased the bearing ability, deformability and energy dissipation capability of the specimens. Based on the limited test data in this study, the existing equations for calculating the parameters of the characteristic points were modified, and equations for calculating the parameters of the skeleton curve of the corroded RC shear wall were proposed. The cyclic corrosion degradation index was utilized to define the degradation of various mechanical properties of the specimen (yield load, hardening stiffness, reloading stiffness, peak load, unloading stiffness, etc.). With cyclic loading, and considering the pinching characteristics, a restoring force model of a corroded RC shear wall was established based on the Ibarra-Medina-Krawinkler (IMK) model. The comparison illustrated that the built restoring force model was in good agreement with the skeleton curve and hysteresis rules and could accurately reflect the hysteresis performance of corroded RC shear walls to a certain extent.

Performance Analysis of Random Forest Algorithm in Automatic Building Segmentation with Limited Data

Airborne laser technology produces point clouds that can be used to build 3D models of buildings. However, the work is a laborious process that could benefit from automation. Artificial intelligence (AI) has been widely used in automating building segmentation as one of the initial stages in the 3D modeling process. The algorithms with a high success rate using point clouds for automatic semantic segmentation are random forest (RF) and PointNet++, with each algorithm having its own advantages and disadvantages. However, the training and testing data to develop and test the model usually share similar characteristics. Moreover, producing a good automation model requires a lot of training data, which may become an issue for users with a small amount of training data (limited data). The aim of this research is to test the performance of the RF and PointNet++ models in different regions with limited training and testing data. We found that the RF model developed from a small amount data, in different regions between the training and testing data, performs well compared to PointNet++, yielding an OA score of 73.01% for the RF model. Furthermore, several scenarios have been used in this research to explore the capabilities of RF in several cases.

Numerical simulation of steel-concrete composite beams and slabs at elevated temperatures

Steel-concrete composite beams with shear studs providing composite action between the concrete slabs and steel beams are widely used in modern steel-framed building construction. Three-dimensional finite element modelling has been a viable option for investigating the fire behaviour of composite beams. Although many finite element models are available in the open literature, most of them are simplified models verified by limited test data. Meanwhile, early test data often did not have all the required information for finite element simulation, and some assumptions need to be made. But more detailed test data are now available in the open literature for steel-concrete composite beams, which can be used to develop a generalised finite element model. In addition, National Institute of Standards and Technology has proposed new stress-strain models for steels at elevated temperatures, which can be compared with the more widely adopted Eurocode 4 steel material models in simulating composite beams. Accordingly, this paper selected 22 specimens, including two reinforced concrete slabs, 12 composite beams with reinforced concrete slabs, two composite slabs with profiled steel sheeting, two steel-concrete composite push test specimens with profiled steel sheeting, and four composite beams with profiled steel sheeting, from nine references to verify the developed finite element model. The proposed finite element model can capture different failure modes of composite beams, such as steel yielding/local buckling, concrete cracking/crushing, debonding of profiled steel sheeting, and stud fracture, which is crucial to comprehend the composite beam behaviour at elevated temperatures.

Characterizing Freshwater Ecotoxicity of More Than 9000 Chemicals by Combining Different Levels of Available Measured Test Data with In Silico Predictions.

Ecotoxicological impacts of chemicals released into the environment are characterized by combining fate, exposure, and effects. For characterizing effects, species sensitivity distributions (SSDs) estimate toxic pressures of chemicals as the potentially affected fraction of species. Life cycle assessment (LCA) uses SSDs to identify products with lowest ecotoxicological impacts. To reflect ambient concentrations, the Global Life Cycle Impact Assessment Method (GLAM) ecotoxicity task force recently recommended deriving SSDs for LCA based on chronic EC10s (10% effect concentration, for a life-history trait) and using the 20th percentile of an EC10-based SSD as a working point. However, because we lacked measured effect concentrations, impacts of only few chemicals were assessed, underlining data limitations for decision support. The aims of this paper were therefore to derive and validate freshwater SSDs by combining measured effect concentrations with in silico methods. Freshwater effect factors (EFs) and uncertainty estimates for use in GLAM-consistent life cycle impact assessment were then derived by combining three elements: (1) using intraspecies extrapolating effect data to estimate EC10s, (2) using interspecies quantitative structure-activity relationships, or (3) assuming a constant slope of 0.7 to derive SSDs. Species sensitivity distributions, associated EFs, and EF confidence intervals for 9862 chemicals, including data-poor ones, were estimated based on these elements. Intraspecies extrapolations and the fixed slope approach were most often applied. The resulting EFs were consistent with EFs derived from SSD-EC50 models, implying a similar chemical ecotoxicity rank order and method robustness. Our approach is an important step toward considering the potential ecotoxic impacts of chemicals currently neglected in assessment frameworks due to limited test data. Environ Toxicol Chem 2024;43:1914-1927. © 2024 The Author(s). Environmental Toxicology and Chemistry published by Wiley Periodicals LLC on behalf of SETAC.

Kriging-based surrogate data-enriching artificial neural network prediction of strength and permeability of permeable cement-stabilized base

Limited test data hinder the accurate prediction of mechanical strength and permeability of permeable cement-stabilized base materials (PCBM). Here we show a kriging-based surrogate model assisted artificial neural network (KS-ANN) framework that integrates laboratory testing, mathematical modeling, and machine learning. A statistical distribution model was established from limited test data to enrich the dataset through the combination of markov chain monte carlo simulation and kriging-based surrogate modeling. Subsequently, an artificial neural network (ANN) model was trained using the enriched dataset. The results demonstrate that the well-trained KS-ANN model effectively captures the actual data distribution characteristics. The accurate prediction of the mechanical strength and permeability of PCBM under the constraint of limited data validates the effectiveness of the proposed framework. As compared to traditional ANN models, the KS-ANN model improves the prediction accuracy of PCBM’s mechanical strength by 21%. Based on the accurate prediction of PCBM’s mechanical strength and permeability by the KS-ANN model, an optimization function was developed to determine the optimal cement content and compaction force range of PCBM, enabling it to concurrently satisfy the requirements of mechanical strength and permeability. This study provides a cost-effective and rapid solution for evaluating the performance and optimizing the design of PCBM and similar materials.

An efficient machine learning-based model for predicting the stress-strain relationships of thermoplastic polymers with limited testing data

Thermoplastic polymers used in aeronautical structures such as poly-ether-ether-ketone (PEEK) usually exhibit nonlinear stress-strain relationships, which can be usually predicted by the physical and phenomenological models. For different thermoplastic polymers, however, existing models may encounter difficulties in reasonably predicting the stress-strain relationships. By reasonably using experimental data, the machine learning-based model can accurately predict the stress-strain relationships. In this paper, an efficient machine learning-based model is built to predict the stress-strain relationships of thermoplastic polymers by using the Kriging model, where limited testing data are merely used. Experiments of 69 specimens for PEEK are firstly performed under uniaxial tensile, where the temperatures range from 23 °C to 140 °C and the strain rates range from 10−3 s−1 to 10−1 s−1. Genetic algorithm is employed to train the proposed model based on the stress-strain relationships obtained from experiments. Moreover, the results predicted by the proposed Kriging-based model are compared with those obtained from the DSGZ (Duan-Saigal-Greif-Zimmerman) model. The results indicate that the Kriging-based model possesses better accuracy, lower complexity, and better robustness than the selected model, because the prior estimation is introduced by the assumption of Gaussian stochastic processes. In addition, the proposed model is also applied to Poly-Propylene (PP), PEEK at high temperatures, and polycarbonate (PC), it can be found that the Kriging-based model can also predict the stress-strain relationships of other amorphous and semi-crystalline thermoplastic polymers.

Intelligent Detection of Surface Defects in High-Speed Railway Ballastless Track Based on Self-Attention and Transfer Learning

The detection of ballastless track surface (BTS) defects is a prerequisite for ensuring the safe operation of high-speed railways. Traditional convolutional neural networks fail to fully exploit contextual information and lack global pixel representations. The extensive stacking of convolutions leads deep learning models to play a black-box detection role, lacking interpretability. Due to the current lack of sufficient high-quality surface data for ballastless tracks, it is a severe constraint on the accurate identification of the substructure state in high-speed railways. This paper proposes an intelligent detection method for BTS defects named TrackNet based on self-attention and transfer learning. The method enhances the fusion ability of global features of BTS defects using multihead self-attention. The model’s dependence on extensive defect data is reduced by transferring knowledge from large-scale publicly available datasets. Experimental results demonstrate that compared to advanced Swin Transformer model results, the TrackNet model achieves improvements in average accuracy and F1-score by 5.15% and 5.16%, respectively, on limited test data. The TrackNet model visualizes the decision regions of the model in identifying BTS defects, revealing the black-box recognition mechanism of deep learning models. This research performs engineering applications and provides valuable insights for the multiclass recognition of BTS defects in high-speed railways.

Bond strength between recycled aggregate concrete and rebar: Interpretable machine learning modeling approach for performance estimation and engineering design

Recycled aggregate concrete has a large potential for application as a sustainable building material. To assist in guiding the engineering design of this low-carbon material, the complex relationship between its bond strength to the rebar and various design parameters was modeled. Comparative studies of multiple machine learning methods have shown that the extreme random tree model demonstrates outstanding performance with root mean square error of 1.982, mean absolute error of 1.202 and coefficient of determination of 0.954. To determine the role of design parameters in performance prediction, importance analysis and sensitivity analyses for parameters were used to explore the complex relationship in the model. The results indicated that rebar type, water-cement ratio, anchorage length, and compressive strength are crucial factors affecting the bond strength between recycled aggregate concrete and rebar. In addition, to further demonstrate the reliability and accuracy of machine learning models, explicit models in some specifications were used for comparative analysis. Due to variability in influencing factors, limited test data, and variability in material properties, the explicit models have limited accuracy for bond strength between recycled aggregate concrete and rebar. Therefore, the interpretable modeling approach can provide an accurate estimate of the bond strength between recycled concrete aggregates and rebar and guide the engineering design of this structure.

Excavation response and reinforcement practice of large underground caverns within high-stress hard rock masses: The case of Shuangjiangkou hydropower Station, China

The construction of large-scale underground caverns poses numerous challenges due to their massive scale and high complexity. Among them, stability has always been a major concern during the construction process of large underground caverns within high-stress hard rock masses. It is not only influenced by the geological background of the project but also by the engineering activities during construction. This study takes the construction of the Shuangjiangkou (SJK) hydropower station as a case study and combines field investigations to summarize engineering issues and solutions under high geostress in three aspects. Firstly, it focuses on estimating and modifying the in-situ stress field of the underground caverns in the deep-cut valley area using limited geostress testing data and the observed failure phenomena in the pilot tunnel. Secondly, it discusses the typical failure phenomena of caverns under high geostress, including global stress-induced failures and local vein-controlled failures, as well as the corresponding failure mechanisms and treatment measures. Finally, it addresses the special failure phenomena occurring in the protective layer of the rock-anchored beam and optimizes the excavation scheme based on the observed failure patterns. The research results and solutions provided in this study, based on the case of the SJK hydropower station, are expected to serve as a reference for subsequent construction of large underground caverns within high-stress hard rock masses.

Decision region analysis for generalizability of artificial intelligence models: estimating model generalizability in the case of cross-reactivity and population shift.

Understanding an artificial intelligence (AI) model's ability to generalize to its target population is critical to ensuring the safe and effective usage of AI in medical devices. A traditional generalizability assessment relies on the availability of large, diverse datasets, which are difficult to obtain in many medical imaging applications. We present an approach for enhanced generalizability assessment by examining the decision space beyond the available testing data distribution. Vicinal distributions of virtual samples are generated by interpolating between triplets of test images. The generated virtual samples leverage the characteristics already in the test set, increasing the sample diversity while remaining close to the AI model's data manifold. We demonstrate the generalizability assessment approach on the non-clinical tasks of classifying patient sex, race, COVID status, and age group from chest x-rays. Decision region composition analysis for generalizability indicated that a disproportionately large portion of the decision space belonged to a single "preferred" class for each task, despite comparable performance on the evaluation dataset. Evaluation using cross-reactivity and population shift strategies indicated a tendency to overpredict samples as belonging to the preferred class (e.g., COVID negative) for patients whose subgroup was not represented in the model development data. An analysis of an AI model's decision space has the potential to provide insight into model generalizability. Our approach uses the analysis of composition of the decision space to obtain an improved assessment of model generalizability in the case of limited test data.

Characterization of model uncertainty of the p-y method for reliability-based design of offshore wind turbines under the serviceability limit state

Recent studies show that the API p-y method may underestimate the pile-soil initial stiffness of offshore wind turbine (OWT) monopiles in clay while overestimate that in sand. To facilitate the reliability-based design of OWT monopiles with the API p-y design method, a two-stage evaluation method of the model bias factor for the p-y method (εpy) of monopiles under the serviceability limit state (SLS) was presented. The model bias factor εpy is derived by comparing field test data with high-fidelity 3D finite element model (FEM) results, and the p-y method predictions, addressing the issues of limited field test data for OWT monopiles. Results show that the mean of the model bias factor εpy depends on the characteristics of piles, the soil properties, and the composition of the layered ground. The systematic dependency is expressed by a trend function and the residual model bias factor follows a lognormal distribution with a mean of 1.01 and a COV of 0.14. The significance of the model uncertainty is illustrated using a case study. The results of the field example show that the design in clay sites may be considerably conservative and may be less conservative in sand sites if ignoring the model uncertainty. The result of this work can provide a basis for promoting reliability-based design for OWT monopiles.

Procena fundamentalnih faktora koji utiču na karakteristike materijala na bazi micelijuma - pregled

The mycelium-based materials (MBMs) are produced by growing the vegetative part of the mushroom-forming fungi-from Dikarya group: phylum Basidiomycota and Ascomycota, on different organic substrates, mostly due to containing important mycelium characteristics: septa and anastomosis. Moreover, function of these composites can be further tuned by controlling the species of fungus, the growing conditions, and the processing methods to meet a specific mechanical requirement in their further applications. The material formed after full colonization of the substrate, needs to be exposed to dry heating in order to remove the moisture content and to inactivate the mycelium, giving us the lightweight, and biodegradable material with great potential to replace fossil-based and synthetic materials such as polyurethane and polystyrene. Their low carbon footprint, low energy and processing cost, biodegradability, low heat conductivity, high acoustic absorption, and fire safety qualities were some of the main characteristics that encouraged the use of mycelium based composites (MBCs) in the construction and building sector, especially as paneling, insulation, and furniture materials. Since mycelium products are quite new and there is limited industry peer-reviewed testing data available, there is a need for standardized mechanical properties, universal testing requirements and published standards (ISO, ASTM) to ensure that qualification and testing programs can be developed to support the manufacture and use of MBCs.

Bootstrap method for characterizing statistical uncertainty in bivariate shear strength parameters and its application to reliability‐based design of slopes

This study characterizes the statistical uncertainties in the bivariate distribution of friction angle and cohesion of soils using bootstrap method and explores its application to the reliability‐based design of slopes. First, the bivariate distribution of friction angle and cohesion is modelled using the copula approach based on limited test data. Then, the statistical uncertainties in the derived bivariate distribution of friction angle and cohesion are characterized by the bootstrap method. Finally, an infinite slope is employed to investigate the impact of the statistical uncertainties in friction angle and cohesion on slope reliability. The reliability‐based designs of slopes based on the point and interval estimate of reliability index are compared. The results indicate that the bivariate distribution of friction angle and cohesion derived from limited test data exhibits large statistical uncertainties. The reliability index of the infinite slope shows visible variation because of the large statistical uncertainties in friction angle and cohesion. The reliability index of slopes considering the statistical uncertainties in friction angle and cohesion is presented as a confidence interval. The interval estimate of reliability index gives a more comprehensive description of slope reliability than the point estimate of reliability index. Furthermore, the reliability‐based design of slopes based on the interval estimate of reliability index can reflect the effect of the amount of test data on the design and link the site investigation efforts and investments on shear tests to final design savings.

Development of sound field simulation and optimization over large acoustic space by use of novel SEA method

Panasonic is committed to providing customers with optimal PA system. The ability to predict PA system performance from digital mock-up is key to help designing optimal system under various conditions. Sound predictions over large spaces are challenging with FEM/BEM methods due to high computational cost and response sensitivity. Additionally, adding detail in source or boundary is difficult with Ray-tracing methods. Finally, traditional SEA methods don't provide sufficient resolution of response. We have investigated a novel SEA method with ability to predict spatial variations in acoustic response. Sound propagation in large public spaces over the full audio range was predicted, accounting for detailed loudspeaker source characteristics, room geometry and boundaries absorption. Predictions were validated against test in a Panasonic auditorium. Method was then used to predict PA system performance in public space under realistic noise conditions. Inverse method was used to synthesize background noise source from limited test data. STI predictions were then performed and optimization carried out to identify PA system loudness requirements in order to achieve best STI performance over wide area while minimizing signal loudness at any position for various background noise conditions.

Epidemiological Profile of Polycythemia Vera Patients Diagnosed during 2016-2020: An Ethnic Variation in Armenia

Background: Polycythemia Vera (PV), a rare myeloproliferative neoplasm, exhibits variations in disease characteristics across diverse ethnic populations. Epidemiological data on PV patients in low-middle-income countries, such as Armenia, is scarce. This study represents the first comprehensive retrospective analysis of PV patients diagnosed between 2016 and 2020 in Armenia. It aims to provide valuable insights into disease characteristics, including median survival, gender distribution, hemoglobin levels, JAK2V617F mutation status, and treatment patterns. Additionally, it explores gender disparities in PV patients in Armenia which is essential to tailor appropriate therapeutic strategies. While previous studies have reported a consistent male-to-female ratio of 2:1 across all ethnicities, this research highlights a contrasting male-to-female ratio in Armenia. Methods: This study included all patients with a diagnosis of PV in the Republic of Armenia from 2016 to 2020, which were registered through the registry of the Hematology Center after Prof. Yeolyan, which stands as the sole hematology center in Armenia. Medical records were reviewed retrospectively and analyzed. Gender distribution was meticulously examined in the context of ethnicity, allowing for a nuanced understanding of the male-to-female ratio variation. Furthermore, the study explored additional epidemiological data, including median survival, hemoglobin levels, JAK2V617F mutation status, and treatment patterns. Results: This analysis provides the first in-depth epidemiological insights into PV patients in Armenia. Surprisingly, our findings indicate that in Armenia, the male-to-female ratio deviates from the established norm, manifesting as a male-to-female ratio of 1.0/0.8 (55.1% males, 44.9% females). This ethnic variation in gender distribution prompts further investigation into the underlying genetic and environmental factors that may contribute to the occurrence of PV within the Armenian population. Additionally, the study revealed a mean survival of 79.457 months (95% CI: 76.718 - 82.196). The median hemoglobin level was 198 g/l. JAK2V617F mutation analysis was conducted in a portion of the cases, with 81.4% of patients not undergoing testing. Among the cases where JAK2V617F mutation analysis was performed, 81.8% tested positive for the mutation, while 18.2% yielded negative results. The majority (88.1%) of PV patients received Hydroxyurea as a therapeutic intervention. However, limitations such as the absence of JAK2V617F mutation analysis in a substantial portion (81.4%) of cases highlight the challenges faced in resource-limited settings like Armenia. The high cost of Ruxolitinib poses further barriers to access for the patient population. Conclusion: This pioneering epidemiologic study in Armenia offers valuable insights into PV's characteristics within this unique ethnic context. The observed difference in the male-to-female ratio in PV patients in Armenia merits further investigation. Unraveling the factors contributing to this ethnic variation could provide crucial insights into the pathogenesis of PV and may aid in optimizing diagnostic and therapeutic approaches for this rare hematologic disorder in Armenia. Limitations: This nationwide study exploring PV in Armenia encountered limitations due to unavailable data for 26 cases, including 5 deceased patients. The retrospective design, and limited genetic testing data may impact the study's generalizability and disease characterization. Longitudinal follow-up and potential unmeasured confounding factors further warrant consideration.

Data-Driven Semi-Empirical Model Approximation Method for Capacity Degradation of Retired Lithium-Ion Battery Considering SOC Range

The rapid development of the electric vehicle industry produces large amounts of retired power lithium-ion batteries, thus resulting in the echelon utilization technology of such retired batteries becoming a research hotspot in the field of renewable energy. The relationship between the cycle times and capacity decline of retired batteries performs as a fundamental guideline to determine the echelon utilization. The cycle conditions can influence the characteristics of the degradation of battery capacity; especially neglection of the SOC ranges of batteries leads to a large error in estimating the capacity degradation. Practically, the limited cycle test data of the SOC ranges of the retired battery cannot support a model to comprehensively describe the characteristics of the capacity decline. In this background, based on the limited cycle test data of SOC ranges, this paper studies and establishes a capacity degradation model of retired batteries that considers the factors affecting the battery cycle more comprehensively. In detail, based on the data-driven method and combined with the empirical model of retired battery capacity degradation, three semi-empirical modeling methods of retired battery capacity degradation based on limited test data of SOC ranges are proposed. The feasibility and accuracy of these methods are verified through the experimental data of retired battery cycling, and the conclusions are drawn to illustrate their respective scenarios of applicability.

Predicting subsurface classification in 2D from cone penetration test data

Uncertainty is inevitable in the characterisation of a geotechnical site, especially due to the inherently heterogeneous nature of the ground. In this paper, a method for characterising a subsurface with limited cone penetration test (CPT) data is proposed. The method is based on integrating predictions of CPT parameters with a probabilistic approach for subsoil classification at the CPTs. The predicted stratigraphy is able to capture the spatial variability of soil measured via CPTs and takes account of the uncertainties that arise from transforming CPT measurements into soil units as well as errors in the measurements themselves. The applicability of the proposed method is demonstrated for a site in the Netherlands. The results show that the proposed approach can identify the most likely classification in the domain with good accuracy. Furthermore, the significance of considering the uncertainties in predicting the most likely classification is illustrated via finite element stability analyses of a slope cut-out in the domain.