Capacity Prediction Model Research Articles

Integrated learning model for water intake capacity of Tyrolean weirs under supercritical flow

ABSTRACT Tyrolean weir can be used as an effective solution to address floatation and sediment deposition in runoff hydropower stations. To improve the efficiency and accuracy of calculating this structure's water intake capacity. The integrated learning algorithm random forest (RF), the firefly algorithm (FA), and the exponential distribution algorithm (EDO) are utilized to develop the algorithm that can be used for the Tyrolean weir Cd and (qw)i/(qw)T prediction models. Sobol's method and SHAP theory are introduced to analyze the above parameters quantitatively and qualitatively. It is shown that EDO-RF is the optimal prediction model for the Tyrolean weir's discharge coefficient and the Froude number Fr has the greatest influence on the Cd prediction results; when Fr < 30, the greater the negative influence of Fr on the model prediction results. When Fr > 30, the greater the positive influence of Fr on the model prediction results. FA-RF is the optimal prediction model for the Tyrolean weir water capture capacity (qw)i/(qw)T, with the ratio of bar length to bar spacing L/e being the largest; When L/e < 20, the greater the negative influence of L/e on the model prediction results. When L/e > 20, the more significant the positive impact of L/e on the model prediction results.

A new prediction model for residual deformation capacity of corroded steel bars

Corrosion of reinforcing steel bars (rebar) is one of the primary factors leading to the performance degradation of reinforced concrete (RC) structures. It is essential to take into consideration the deteriorating effects of corrosion when it comes to assessing the performance of existing RC structures. However, due to the uncertainties and randomness associated with the degree and distribution of corrosion, accurately assessing the residual deformation capacity of corroded rebar is a significant challenge. This paper presents a comprehensive theoretical model for the prediction of the residual deformation capacity of corroded rebar. Taking into account the mechanical characteristics of the steel material, three classes of non-uniform corrosion in rebar are firstly defined on a quantitative basis to characterize the deformation distribution patterns under tension. Based on the concept of deformation accumulation, a simplified theoretical model is proposed for evaluating the residual deformation capacity of corroded rebar, incorporating both the non-uniformity of corrosion and the sample (or gauge) length; thus, a length scale is built into the nominal strain measure to accommodate the use of different sample or gauge lengths. Numerical tensile tests on 500 randomly generated samples of rebar with varying corrosion levels are conducted, and the parameters of the theoretical model for the three corrosion classes are determined based on a regression analysis of the tensile test results. Comparisons with actual experimental results and existing degradation models demonstrate that the proposed theoretical model provides a more accurate estimation for the deformation capacity of corroded rebar. The model offers a reliable reference for accurately assessing the tensile performance of corroded rebar in subsequent engineering applications.

Seismic response of RC short columns strengthened by high-strength stainless steel wire rope meshes reinforced ECC jacket

A novel strengthening scheme of high-strength stainless steel wire rope (HSSSWR) meshes reinforced engineering cementitious composite (ECC) jacket was used to strengthen the reinforced concrete (RC) short columns in this paper. The seismic performance of short columns after being strengthened was investigated, considering the changes in the strengthening scheme, and the spacing of lateral HSSSWRs. The failure mode, hysteresis behavior, envelope curve, ductility, energy dissipation, stiffness degradation, and strength degradation were introduced specifically based on the analysis of six full-scale short columns. The test results show a significant enhancement in the seismic performance of the strengthened short columns, especially in ductility and energy dissipation, which were increased by 49.4–98.4 %, and 149.3–713.2 %, respectively. The placement of HSSSWRs in ECC jacket proved to be effective in enhancing the strengthening effect of the jacket. A prediction model for the shear capacity of the strengthened columns was proposed using the Modified Compression Field Theory (MCFT), and the predicted results were in good agreement with the test results presented in this paper and in relative study.

A hybrid data-driven method based on data preprocessing to predict the remaining useful life of lithium-ion batteries

Abstract The estimation of remaining useful life (RUL) for lithium-ion batteries is an essential part for battery management system (BMS). A hybrid method is presented which is combining principal component analysis (PCA), improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), sparrow search algorithm (SSA), Elman neural network (Elman-NN), and gaussian process regression (GPR) to forecast battery RUL. Firstly, in the data preprocessing stage, the PCA+ICEEMDAN algorithm is creatively proposed to extract features of capacity decay and fluctuation. The PCA method is used to reduce the dimensionality of the extracted indirect health indicators (HIs), and then the ICEEMDAN algorithm is introduced to decompose the fused HI sequence and actual capacity data into residuals and multiple Intrinsic mode functions (IMFs). Secondly, in the prediction stage, feature data is corresponded one to-one with the mixed model. The prediction models of SSA-Elman algorithm and GPR algorithm are established, with the SSA-Elman algorithm predicting the capacity decay trend and the GPR algorithm quantifying the uncertainty caused by the capacity regeneration phenomenon. The final prediction results are obtained by superimposing the two sets of prediction data, and the prediction error and RUL are calculated. The effectiveness of the proposed hybrid approach is validated by RUL prediction experiments on three kinds of batteries. The comparative experimental results indicate that the mean absolute error (MAE) and root mean square error (RMSE) of the presented prediction model for lithium-ion battery capacity are less than 0.7% and 1.0%.

Reliability framework for CLT floors in out-of-plane bending using Monte Carlo simulation

Sustainably sourced engineered wood products (EWP) such as cross-laminated timber (CLT) floor panels are viable alternatives to conventional concrete and steel, however their inherent natural variability increases perceived risks and limits wide-spread adoption. The reliability index (β) is the metric used by design standards to communicate allowable structural risk. Although not included directly in any structural capacity equations, it governs all the partial resistance factors and load amplification factors that inform those design code calculations. CLT floors have significant partial resistance factors due to the natural variability of the material that effectively penalise the calculated design strength of those products. By exploring their reliability there is the potential to allow these products to be designed more efficiently, leading to increased competitiveness among traditional materials and less waste. A novel statistical capacity prediction model that goes beyond a simple averaged-value strength assumption to include consideration of the variability between individual boards within a panel was validated against experimental data. A CLT database of 237 out-of-plane bending test results was collected for the first time to inform an appropriate model error factor. Monte Carlo simulation (MCS) approaches were adopted to predict the reliability levels of CLT panels by defining the material, geometrical and loading parameters as random variables and assigning each a mean, coefficient of variation and appropriate distribution. The target and calculated reliability levels were compared across both Eurocode 5 and the North American codes ANSI/APA PRG 320 and CSA O86 as the preeminent CLT design codes internationally. This study found that the calculated reliability levels met or exceeded both codes in most scenarios. The impacts of width, load ratio, material strength distribution, and CLT layups on the expected failure probabilities were explored with sensitivity analyses. The MCS framework was also applied to the calibration of an appropriate resistance factor for CLT design to inform the potential creation of an Australian CLT design code. A resistance factor of 0.85 was calibrated which falls between the equivalent European and North American code resistance factors.

Experimental study on the punching failure model of soft red rock subgrade by BPT-BVM methods and it’s assessment of the load bearing capacity

The recommended bearing capacity of medium weathering mudstone foundation is less than the capacity of the rock structure to withstand loads in Southwest China. A comprehensive failure characterization of medium weathering mudstone in Chengdu has been performed including bearing plate test (BPT), binocular vision measurement (BVM) test, uniaxial compressive strength test, trial trench test of shallow rock surface and 3D imaging in this paper. Failure behavior of rock has been modeled with 3D imaging algorithm that utilizes Zhang’s calibration method in BVM system combination with trial trench test of shallow rock surface. The bearing capacity of medium weathering mudstone foundation were extracted from uniaxial experiments and BPT-BVM test by fitting relevant material properties to the data. The results revealed that: Bearing capacity of medium weathering mudstone of layered isotropic in Chengdu is undervalued. Specifically, the characteristic load carrying value is in the range 1500–2500 kP, that is 50% higher than in the local standard system. Failure process is different from Hoek–Brown Failure Criterion, presenting a wave peak transfer phenomenon of the increment displacement into the distance. Thus, it can be reduced to that of punching failures for thin bedded structures of Moudstone foundations. Compressive strength of soft rock proves to be main factor limiting the bearing capacity, a clear correlation between the uniaxial compressive strength reduction coefficient and the bearing capacity has been used to establish, leading to the proposal of a load bearing capacity prediction model.

A SVM based demand response capacity prediction model considering internal factors under composite program

Demand response capacity is a key reference for demand-side participation in peak regulation and earning profit in the electricity market, and it is influenced by not only external public factors but demand-side internal individual factors. Demand change caused by internal individual reasons cannot be recognized by public features. Single participating in response industrial and commercial consumers cannot balance this change through large numbers of participants, unlike aggregators. The prediction model only considering the external public factors will cause significant errors. However, the actual industrial and commercial data is difficult to obtain because of the cost and privacy, and the simulation platform cannot accurately describe this situation, resulting in the problem being ignored. Therefore, this paper aims to prove the importance of internal factors and proposes an improved method considering the problem. First, based on an actual dataset, the optimal responsive behavior of consumers is modeled to quantify response capacity. Second, a support vector machine (SVM) method is applied to predict response capacity. Finally, combined with raw data, this paper proves that significant errors are caused by internal factors and provides different improvement methods for internal and external operators. The case study indicates that the improved model can provide better performance.

Effects of Freeze-Thaw Cycles on Axial Compression Behaviors of UHPC-RC Composite Columns.

Ultra-high performance concrete (UHPC) with excellent durability has broad application prospects in improving the durability of reinforced concrete (RC) structures. To clarify the influence of freeze-thaw cycles on the axial compression performance of UHPC-RC composite columns, axial compression tests were carried out on composite columns with different cycles (0, 100, 200, 300 cycles) and stirrup spacing (35, 70, 105 mm). The results showed that the UHPC shell did not fall off when the composite column was destroyed, even in the freeze-thaw environment. Under the action of freeze-thaw cycles, the peak load Nu,t and initial elastic modulus E of the composite column decreased, but the ductility coefficient μ increased. Increasing the stirrup spacing could significantly improve the ductility of the composite column. After 100 freeze-thaw cycles, the ductility coefficient μ of the 35 mm stirrup spacing specimen was 112.6% higher than that of the 105 mm specimen. A prediction model for the bearing capacity of UHPC-RC composite columns under freeze-thaw cycles was established, and the predicted results were in good agreement with the experimental results. This study lays a theoretical and experimental foundation for the application and design of UHPC-RC composite columns in the freeze-thaw environment.

A Lithium-Ion Battery Degradation Prediction Model With Uncertainty Quantification for Its Predictive Maintenance

Battery degradation modeling in the presence of uncertainty is a key but challenging issue in the applications of battery predictive maintenance. This paper develops a capacity prediction model with uncertainty quantification for lithium-ion batteries and proposes a dynamic maintenance strategy which can help to make an optimized decision at each battery cycle stage. To be specific, after using the one-dimensional convolution neural network (1dCNN), deep representative features hidden in original measured signals are extracted. Then, the bi-directional long short-term memory (Bi-LSTM) is applied to estimate the battery capacities, while the quantile regression (QR) layer is embedded into the construction of the Bi-LSTM network to obtain the capacities for different quantiles. Next, the kernel density estimation (KDE) is utilized to derive the probability density of the predicted points at each battery cycle stage. Thus, the combination of 1dCNN, Bi-LSTM, QR and KDE, named 1dCNN-BiLSTMQR-KDE, forms an efficacious capacity prediction model with reliable uncertainty management. Finally, the costs of different decisions at each battery cycle stage are evaluated, and the decision with the lower cost will be chosen. The whole proposition is verified on battery degradation datasets from NASA, and the comparison with other methods show that the proposed method is competitive.

Analytical model for prestressed glulam beams reinforced with unbonded steel bars

Glulam beams reinforced with bonded steel bars are a common form. The study describes theoretical models of unbonded reinforced and prestressed reinforced glulam beams for assessing the reinforcement ratio and prestress level range, and for predicting the effect of unbonded steel bars on the flexural capacity of the beam. Considering the stress changes of beam cracking and cross-sectional stress, the minimum and maximum reinforcement ratios were determined. On this basis, the influence of the service load on the beam in the actual engineering was explored, and the force equilibrium equation was established to derive a reasonable prestress range related to the reinforcement ratio. Combined with the glulam constitutive model, and analyzed the strain distribution of unbonded steel bars was to establish the flexural capacity prediction model. The accuracy of the model was verified by the relative error between the prediction and test values ranging from-11.78% to 8.84%.

Experimental and numerical research on the uniaxial behavior of the stiffened circular concrete-filled steel tube stub columns

In large-span bridges or high-rise buildings, CFST columns with large width-to-thickness ratio are often adopted, which require proper stiffening measures to improve the mechanical behaviors. This paper presents a comparative study of circular CFST stub columns with different stiffening methods, including longitudinal stiffeners (cross-shaped, T-shaped and ordinary type), additional reinforcement and headed studs. Axial compression tests have been conducted to investigate the effects of different stiffening methods on the failure mode, ultimate strength and ductility of the circular CFST stub columns. Finite element models are established to simulate the columns’ behaviors and conduct parametric studies. Based on test and simulation results, an axial bearing capacity prediction model for circular CFST stub columns stiffened by longitudinal stiffeners is proposed. It is demonstrated that the failure modes of the steel tube and core concrete are changed by the longitudinal stiffeners. The longitudinal steel stiffeners as well as reinforcing cage can effectively improve the axial bearing capacity and ductility of the columns. The latter is more efficient in promoting the bearing capacity while the former is more efficient in improving the ductility and residual strength. A combination of the additional stirrups and the ordinary stiffeners will be a more economical choice. In addition, the proposed formula gives better prediction accuracy compared to the equations in various design codes.

A collapse capacity prediction model based on ground motion duration

A prediction model for the seismic collapse capacity, which explicitly considers the influence of strong motion duration, in addition to key structural properties, is presented in this study. The model is developed based on incremental dynamic analyses of single-degree-of-freedom systems, employing a set of 67 earthquake records. The selected ground motions are matched by scaling to a target Eurocode 8 response spectrum, to avoid spectral shape bias in the results, and have varying 5–75% significant duration from about 5 s up to nearly 70 s. The structural models exhibit vibration periods in the range of 0.2 s to 3.0 s, varying negative slope in their post-capping branch from 0.02 to 0.30, and ductility between 1.0 and 6.0. Each oscillator is assigned bilinear and pinching hysteresis. Correlation coefficients are computed between the collapse capacity and the structural properties examined, as well as three ground motion parameters, which include the duration, Arias Intensity, and Husid plot slope. The period, post-capping slope, and ductility are all shown to be strongly correlated to collapse resistance while, among the ground motion variables, the duration exhibits the highest correlation. Based on iteratively reweighted least squares, predictive models are fitted to the collapse capacity data, providing estimates for the median collapse capacity and the variance. The predicted collapse capacity associated with the maximum duration considered is found to be up to 67% lower than that corresponding to the minimum duration. The rate of collapse capacity reduction with duration is shown to depend on the period, P-Δ level, hysteresis type, and the duration value itself. The proposed model is compared to those from previous studies and is shown to provide a simple and computationally efficient method to obtain collapse capacity estimates for specific target levels of strong motion duration.

Multi-expression programming based prediction of the seismic capacity of reinforced concrete rectangular columns

This article presents an innovative artificial intelligence based multi-expression programming approach to predict the seismic capacity of reinforced concrete rectangular columns. For the evolution of these multi-expression programming based computational models, an investigational test database created by pacific earthquake engineering research centre was employed. This database consisted of the experimental record of 250 specimens of reinforced concrete rectangular columns exposed to seismic loading. The overall seismic capacity of the aforementioned columns was considered to be the function of their flexural and shear capacities, for the prediction of which five input variables were used. Once these models were evolved utilizing MEPX version 2022.3.19.0-beta, their performance was determined on the basis of ten most frequently used performance indicators, one of which is the coefficient of determination i.e., R2. Based on the findings of this research, a strong correlation (i.e., an R2 of 0.9747 and 0.9664 for the flexural and shear capacity prediction models respectively) was found to exist between the predicted and tested seismic capacities of reinforced concrete rectangular columns. Moreover, the proposed seismic capacity prediction models were found to outperform that of ACI 318-19 in terms of precision and prediction accuracy. The proposed seismic capacity prediction models were also found to be well trained on the correlation between input and output variables which verifies their ability to capture the underlying physical processes involved in the seismic action on reinforced concrete rectangular columns. Therefore, the proposed multi-expression programming based computational models can be confidently recommended for predicting the seismic capacity of reinforced concrete rectangular columns for practical design applications.

Probabilistic assessment of anchor foundation for transmission tower using multivariate adaptive regression splines

ABSTRACT This paper pertains to the reliability analysis of transmission tower foundations under variable wind loads. The reliability analysis of the anchor foundation, frequently employed for transmission towers due to their huge uplift capacity at shallow depth, is presented using a systematic probabilistic approach. The paper presents the design of an anchor foundation for a typical transmission tower based on loads obtained by applying lateral wind velocity on the tower. The Multivariate Adaptive Regression Splines (MARS) surrogate model is first developed to construct a deterministic prediction model for the anchor uplift capacity. The developed model is further used in the reliability analysis of the anchor foundation considering variabilities in the soil properties and the uplift load, and the results of the probabilistic analysis are reported in the paper. The results indicate the importance of incorporating variability in design variables for the proper safety of the structure. Soil cohesion is found to be the most sensitive parameter in the uplift capacity of the tower foundation. The comparison of the deterministic factor of safety and failure probability of the foundation brings out the importance of the reliability-based design methodology.

Simulation of population size and economic scale supportable by the Yellow River’s available freshwater in 2030 under multiple scenarios

The Yellow River plays a crucial role in China’s socioeconomic development and ecological security. The amount of freshwater available for allocation to the nine provinces of the Yellow River basin (YRB) is expected to be 39.485 billion m3 in 2030, for a projected population of 0.13094 billion people. This study aimed to simulate the sustainable population size and economic scale attainable with the Yellow River’s restricted freshwater supply. We forecasted population size and economic scale under various scenarios using a water resource carrying capacity (WRCC) prediction model. Further, the most likely scenarios—high, moderate, and low development—were analyzed based on historical trends. The results showed that by 2030, the available freshwater could support population sizes of 0.16, 0.152, and 0.147 billion under the high-, moderate-, and low-development scenarios, respectively, all of which are greater than 0.13094 billion. Moreover, economic scales of CNY17.5 trillion ($2.52 trillion), CNY15.01 trillion ($2.18 trillion), and CNY13.2 trillion ($1.91 trillion) could be supported under the high-, moderate-, and low-development scenarios, respectively. This study’s contributions are that (1) using population size and economic scale to characterize WRCC overcomes the limitation of measuring WRCC with a dimensionless index; (2) quantifying WRCC overcomes the flaws of single-trend measurement; and (3) the scenarios paint a clear picture of the YRB’s future water security and socioeconomic development. Our findings could help steer the direction of future water-, population-, and economy-related policymaking.

Full-cycle prediction of gas production variations in gas wells using different production methods

Gas production from gas wells is affected by formation pressure and wellbore outflow during gas production. To increase the daily gas production and obtain smooth and efficient gas production gas wells, methods such as wellbore shut-in pressure recovery and foam injection and drainage for gas production are usually adopted. In this paper, the gas-carrying liquid model, capacity prediction model, and pressure recovery model are utilized to establish a full-cycle production prediction method for newly developed gas wells. Combining the initial development pressure, gas production, and water production parameters of the gas well, the gas production prediction is obtained for the next few years. Meanwhile, the implementation time of the forced drainage method is calculated and obtained.

Axial compression performance of circular UHPC-filled stainless-steel tubular columns

Whether the high ductility of stainless-steel tubes can impede the brittle failure of ultrahigh-performance concrete (UHPC) and improve their cooperative load-carrying efficiency is a research direction worth exploring. Twenty-seven circular UHPC-filled stainless-steel tubular (UHPCFSST) columns were designed and tested under axial compression. The variables were the outside diameter and wall thickness of the stainless-steel tube. The axial compression performance and cooperative load-carrying efficiency of the UHPCFSST columns, such as the failure mode, stress–strain relationship, and ductility, were quantitatively evaluated. The experimental results show that the stress–axial strain curves can be divided into two forms based on hoop confinement coefficient (ξs). The ductility of the UHPCFSST columns is considerably better than that of UHPC-filled steel tubular (UHPCFST) columns, and there is an obvious strain-hardening phenomenon after the peak. A database of UHPCFST columns containing 272 specimens was constructed. The relationships between parameters and enhancement coefficients such as the strength index were quantitatively investigated. Through regression analysis, a prediction model for the axial compression load-carrying capacity of UHPCFSST and UHPCFST columns was established. Using the database, the rationality and accuracy of the proposed model were verified.

Application of Gray Expansion Model in Energy Economic Analysis and Load Forecasting

Objective and effective prediction of energy consumption can not only optimize the energy consumption structure, but also provide important information for the government to formulate energy conservation and emission reduction measures. With the development of new energy sources and changes in the global energy consumption structure, historical energy data that are too old may no longer be reliable for forecasting, which leads to a decrease in the amount of information on energy, and the gray theory, which is applicable to “poor information”, has gained attention. Firstly, the optimization of energy economic objectives and transformation path methods at this stage is clarified; then, the DEA-Malmqusit model is used to improve the shortcomings of the traditional model that can only compare different cross-sections at the same time node, and to evaluate and analyze the full-factor multi-indicators of energy enterprises in terms of technological empowerment, environmental dynamics, and economic output efficiency; finally, the LEAPS-based energy system consumption and load capacity prediction model. The results show that the traditional algorithm is not accurate enough and has some deviation when the energy raw data fluctuates a lot. The algorithm proposed in this paper still gives a better prediction, predicting a city’s carbon emission to be 65,240,100 tons in 2024, with a 3.6% increase in energy output year by year.

Capacity Prediction Method of Lithium‐Ion Battery in Production Process Based on Improved Random Forest

Measuring capacity in the grading process is an important step in battery production. The traditional capacity acquisition method requires considerable time and energy consumption; therefore, an accurate capacity estimation is crucial in reducing production costs. Herein, a capacity prediction method for lithium‐ion batteries based on improved random forest (RF) is proposed. This method extracts features from the voltage data of the entire formation process and the first 25% of the grading process, saving 56.7% of the energy consumption and 74.6% of the time in the grading process. The importance of these features is ranked by RF, the best feature subset is selected, and the RF algorithm with parameters optimized by the genetic algorithm is applied to establish a capacity prediction model. The results show that the proposed model can accurately predict the capacity, with root mean square error (RMSE) and mean absolute percentage error (MAPE) values of only 191.89 mAh and 0.13%, respectively. Compared with other regression algorithms, the model shows a lower RMSE and MAPE and a higher capacity prediction accuracy for low‐capacity cells.

Machine learning based prediction model for the pile bearing capacity of saline soils in cold regions

The difficulty in determining the bearing capacity of pile foundations in saline soil environments in cold regions can pose a challenge when developing a bearing capacity prediction model. To address this, the study uses data from the construction of the De Xiang Expressway project in Qinghai Province, China, and considers pile length, pile diameter, corrosion depth, and spalling thickness as influential parameters. We combine Python with ABAQUS to build a finite element model of a single pile in a salt marsh environment with random parameters and develop a database for machine learning. We use the kernel ridge regression (KRR) and multilayer perceptron (MLP) algorithms to establish load-bearing capacity prediction models for vertical and horizontal loads, respectively. The SHAP (SHapley Additive exPlanations) method is employed to perform explanatory analysis on the prediction models, providing insight into influential parameter effects on prediction accuracy. The results demonstrate that the database established through the random parameter finite element method is suitable for machine learning. While the KRR model exhibits good performance in predicting vertical load-bearing capacity, the MLP model performs well in predicting horizontal load-bearing capacity. Moreover, the SHAP method effectively explains the importance of influential parameters on the prediction results and enhances the reliability of the prediction models. The vertical bearing capacity of a saline soil pile foundation is more affected by the depth of salt erosion than the thickness of spalling, while the horizontal bearing capacity is more affected by the thickness of spalling than the depth of salt erosion.