Capacity Prediction Model Research Articles

Temporal Attention Mechanism Based Indirect Battery Capacity Prediction Combined with Health Feature Extraction

The burgeoning utilization of lithium-ion batteries within electric vehicles and renewable energy storage systems has catapulted the capacity prediction of such batteries to a pivotal research frontier in the energy storage domain. Precise capacity prognostication is instrumental not merely in safeguarding battery operation but also in prolonging its operational lifespan. The indirect battery capacity prediction model presented in this study is based on a time-attention mechanism and aims to reveal hidden patterns in battery data and improve the accuracy of battery capacity prediction, thereby facilitating the development of a robust time series prediction model. Initially, pivotal health indicators are distilled from an extensive corpus of battery data. Subsequently, this study proposes an indirect battery capacity prediction model intertwined with health feature extraction, hinged on the time-attention mechanism. The efficacy of the proposed model is assayed through a spectrum of assessment metrics and juxtaposed against other well-entrenched deep learning models. The model’s efficacy is validated across various battery datasets, with the Test Mean Absolute Error (MAE) and Test Root Mean Squared Error (RMSE) values consistently falling below 0.74% and 1.63%, respectively, showcasing the model’s commendable predictive prowess and reliability in the lithium-ion battery capacity prediction arena.

Effects of structure size on post-earthquake fire resistance of CCBCC joints at non-uniform elevated temperatures

The probability of secondary fires caused by earthquakes is very high. Due to the residual stress and deformation caused by earthquakes, the mechanical behavior of cruciform combined beam-CFST column (CCBCC) joints is extremely complex. In view of this, the goal of this study is to investigate the effects of structure size on the post-earthquake fire failure mechanism of CCBCC joints under gradient temperatures. The calculation model in this article was validated using existing experimental results, subsequently 20 computational models were established to conduct parameter analysis, including the width-to-thickness ratio (γ) of the CFST column, the slenderness ratio (λ) of the CFST column, the width-to-thickness ratio (α) of beam flange, the height-to-thickness ratio (β) of beam web and the damage variable (D̃). The results have demonstrated that the post-earthquake fire resistance of CCBCC joints is mostly affected by damage variable. Parameters β, α, λ and γ also have a significant impact on the failure of these joints. An empirical bearing capacity prediction model of CCBCC joints is obtained. The research results can provide reference and data support for the design, maintenance, and reinforcement of CCBCC joints under post-earthquake fire.

Recycling to alleviate the gap between supply and demand of raw materials in China's photovoltaic industry

The photovoltaic (PV) market's expansion has increased PV waste exponentially. It is essential to conduct scientific research to determine the economics of recycling for the industry to grow sustainably. In this research, we proposes a multi-factor installed capacity prediction model based on bidirectional long short-term memory-grey relation analysis, which accurately predicts China's cumulative PV installed capacity in three growth scenarios from 2022 to 2050. With the Weibull distribution applied to predict the recovery potential of c-Si panels, the importance of recycling in balancing the supply and demand of raw materials is quantified. The results show that in the high-growth scenario, China's cumulative PV installed capacity will reach 2125 GW by 2050 while $400 to $700 million will be generated from the recycling. The study results demonstrate how crucial recycling is to close the loop of supply and demand for key raw materials in the PV industry.

Reliability evaluation of flexural capacity design provision for UHPC beams reinforced with steel rebars/prestressing tendons

This study investigated the reliability of the flexural capacity prediction models for ultra-high performance concrete (UHPC) beams in various standards, including the Chinese UHPC Code (draft), Chinese standards JGJ/T 465–2019 and JTG 3362–2018, Swiss standard SIA 2052–2016, and French standard NF P18–710–2016. The research was based on two comprehensive databases of 110 reinforced and 47 prestressed UHPC beams. Correlation analysis of the model errors of the flexural capacity formulae was conducted at first. Then, the reliability of the prediction models was analyzed through Monte Carlo simulation (MCS) and first-order second-moment (FOSM) method, considering the design parameters such as material strength, live-to-dead load ratio, longitudinal reinforcement ratio, and prestressing tendon ratio. The results indicated that the prediction model in Chinese UHPC Code (draft) could accurately predict the flexural capacity of reinforced and prestressed UHPC beams among the five specifications, with the mean model errors of 1.06 and 1.02, respectively. The reliability indexes of Chinese UHPC Code (draft), Swiss standard SIA 2052–2016, and French standard NF P18–710–2016 for both the reinforced and prestressed UHPC beams were significantly higher than the specified value of 4.2 in the Chinese standard. The sensitivity analysis showed that the reliability index increased with the increase of live-to-dead load ratio, but it was not significantly influenced by UHPC compressive strength. In addition, the reliability index decreased as the longitudinal reinforcement ratio and prestressing tendon ratio increased. Material partial factor of flexural resistance of the formula in Chinese UHPC Code (draft) was calibrated, and γc= 1.30 was recommended for UHPC beams for safety.

Machine learning–assisted drift capacity prediction models for reinforced concrete columns with shape memory alloy bars

AbstractDespite notable progress made in predicting the drift capacity of reinforced columns with steel bars, these techniques and methods are proven inapplicable for accurately predicting the drift capacity of RC columns reinforced with shape memory alloy (SMA) bars. This study employed machine learning (ML) to predict and design the drift limit state of concrete columns using SMA bars. To this end, a total of 292,000 synthetic data points were generated through numerical simulations given the limited amount of experimental data for SMA bars. The data analysis results suggest that the light gradient boosting (LGB) algorithm achieves the best performance in terms of computational efficiency and prediction accuracy among nine candidate ML algorithms considered in this study. Further refinements for the LGB algorithm is introduced to yield better prediction results: (1) Hyperparameters are tuned using particle swarm optimization with an improved particle updating strategy and (2) the dimensions of the input data are reduced using a modified recursive feature elimination algorithm with memorizing capability. In addition, this study demonstrated the application of the proposed ML‐assisted drift capacity prediction model to the design of SMA‐reinforced concrete columns using modified particle swarm optimization that can help structural designers worldwide.

A novel cooling capacity prediction model for open-type cooling radiant ceiling

Open-type cooling radiant ceiling panel systems (O-CRCP) have a higher cooling capacity, but their cooling capacity can only be calculated roughly according to the model of the closed-type cooling radiant ceiling panel systems (C-CRCP), which may cause economic and energy waste. This study aims to develop a novel cooling capacity prediction model for O-CRCP considering the impact of panel size, layout, and installation position. The experimental results revealed that the heat flux of the O-CRCP was 49%–64% greater than that of the C-CRCP. A detailed analysis of the simulation results shows that the natural convective heat transfer is the main factor for the cooling capacity enhancement which basically determines the trend of the total heat flux varying with various factors. Based on the simulation results, a novel cooling capacity prediction model for O-CRCP was developed using a multi-regression method. It was evaluated in an actual room with O-CRCP, and the predicted cooling capacity curve showed good agreement with the measured values, the relative error ranged from 5.78% to 9.72% with an average of 7.47%, which is acceptable for engineering applications. The proposed model can provide support and guidance for designers and engineers in selecting and arranging O-CRCP in real applications.

Tensile performance of cast-in headed studs in thin concrete panels with void formers

In recent times, voided concrete slab or wall system has been increasingly popular due to material and cost savings benefits offered by such system. Fastenings are required to be attached to such systems either to connect to other concrete elements or fixtures. There has been limited published literature on the performance of fastenings in thin concrete shell elements due to presence of voids. The Concrete Capacity (CC) method is the state-of the-art prediction model for capacity of anchors in concrete widely adopted in design standards worldwide. The CC-method has been proven to be a robust model for predicting concrete cone capacity of cast-in and post-installed anchors with effective embedment depths, hef between 4 and 20 times diameter of anchors with a minimum hef of 40 mm in mature age concrete. In this study, over 200 headed studs are investigated experimentally in early age concrete whereby the hef for over half of the specimens is lesser than 40 mm. Further, the failure mode for the headed studs in the presence of plastic void former is expected to be a plug failure which prohibits the development of the full concrete cone. The purpose of this study is to examine the applicability of the CC-method for pull out performance of headed studs in the presence of void formers. A total of 228 headed anchors with varying effective embedment depths ranging from 19 mm to 61 mm were tested in thin concrete panels with varying thicknesses. Based on structural reliability analysis, a modification factor was proposed to the CC-method to safely predict the pull-out design capacity of headed studs in thin concrete panels with plastic void formers to maintain the same degree of safety as for typical headed stud applications within the scope of the CC-method.

Damage evolution mechanism and early warning using long short-term memory networks for battery slight overcharge cycles

Slight faults can damage battery electrodes and electrolytes, leading to cumulative irreversible capacity loss and decreased performance, even a critical state of failure. In this study, the overcharge cycling of lithium-ion battery (Lithium, 2600 mAh, 3.7 V) is studied to reveal the damage evolution mechanism and establish a novel early warning method for slight faults. With the increase of cycles, the aggregation of the loss of active materials leads to the acceleration of capacity fading rate and the acceleration factor increases from 1 to 3.6 when the cut-off voltage attends 4.4 V. But these cells follow a similar damage evolution path to the normal cells during cycling. Based on the accelerating fading feature of fault cells, a capacity prediction model for early warning was developed. The batteries’ capacity data are firstly smoothed by the Savitzky-Golay filter and then transferred to long short-term memory (LSTM) networks for training. The model can predict the capacity of overcharged cells well within a 2% error by optimizing the sizes of input and output data. And the slight overcharge fault can be early warned through a specific threshold of the root-mean-square deviation between the prediction and the norminal capacity degradation curve.

Application of BPNN Optimized by Fireworks Algorithm on Structural Bearing Capacity Analysis of Transmission Tower under Icing Conditions

With the increasing power demand in city development, the construction and application of transmission towers need to meet higher requirements. Icing is an extreme meteorological condition in the world, and icing disasters cause various accidents such as tower collapse and line disconnection of large-area lines every year. Therefore, it is of great significance to study the ultimate bearing capacity of transmission towers under icing conditions. The structural bearing capacity under icing is greatly affected by meteorological conditions and environmental factors, which has strong randomness and complexity, and brings a series of urgent problems to the structural stability of transmission towers. In the paper, the ultimate bearing capacity analysis and failure path research are conducted on the 500 kV linear cathead tower structure, and a structural bearing capacity prediction model based on the fireworks algorithm (FWA) is established. In order to accurately predict the structural bearing capacity, reduce the adverse effects of line icing, and ensure the structural stability of the transmission tower, the FWA is introduced into the neural network model. The self-adjusting mechanism of the local search ability and global search ability of the FWA is used to optimize the optimization process of weights and thresholds in the neural network, and a structural bearing capacity prediction model based on the FWA improved backpropagation neural network (BPNN) is proposed. Through the analysis and calculation of the measured data of the transmission tower in a certain area, and the comparative study with the traditional BPNN and the BPNN optimized by other common algorithms, the analysis and calculation results of the FWA-BPNN model used in this paper are closer to the actual value, the multiple indicators are more superior, and the model is more stable, which can realize the rapid and accurate analysis of the axial stress of tower members and maximum displacement between member nodes of the transmission tower under the icing condition.

Axial compressive behavior of a novel assembled joint connecting FCSRC columns and RC beams with pre-damage

To promote the application of Fiber-reinforced polymer-confined steel-reinforced concrete (FCSRC) in new structures, a novel assembled joint connecting FCSRC columns and RC beams was proposed. The novel joint contained a concrete-filled-steel-tube stub column and a pair of ring plates with steel connecting beams. The joint was connected to FCSRC columns and reinforced concrete (RC) beams by end plates and high-strength bolts. Previous studies have revealed that the assembled joint could effectively connect FCSRC columns and RC beams with good seismic performance. However, research on this novel joint was not sufficient. Axial compressive performance and post-seismic residual resistance are also important structural issues that need to be addressed. This paper thus investigates the effect of pre-damage level and steel tube thickness for the joint on its axial compressive behavior. Results showed that with thinner steel tube thickness, more severe bulging was observed and the axial load and initial stiffness of the specimen was reduced. Besides, based on the test results and the finite element analyses, it is clear that the effect of pre-damage was negligible on the axial load–displacement behavior of the proposed joint. Lastly, a prediction model for the axial load-carrying capacity of the joint was proposed.

Behavior of large diameter carbon fiber anchors

The use of fiber anchors is becoming more commonplace as part of an FRP retrofit of concrete or masonry structures. Such anchors are typically small diameter (sometimes referred to as spike anchors) and are mainly used to delay, or possibly prevent, debonding of externally-bonded FRP laminates. However, capacity prediction models developed for small diameter fiber anchors may not be extended to large carbon fiber (CF) anchors, herein defined as an anchor with a diameter greater than 19 mm. In this study, commercially available 19, 25, and 32 mm diameter CF anchors were tested. First, the behavior of straight CF anchors embedded in concrete under direct tensile loading was examined to obtain the benchmark rupture capacity of the anchors. Embedment depths varied between 10 and 13 times the anchor hole diameter. Then, the behavior of fanned CF anchors under direct tensile load was investigated, considering fan angles of 37° and 57°. Finally, the effect of column bending on the behavior of CF anchors was studied by installing anchors on previously tested large-scale reinforced concrete column-footing subassemblies. It was found that the anchor diameter, anchor fan angle, anchor hole diameter, and embedment depth of the anchor dowel impact the behavior of large diameter CF anchors. Further, confinement of the anchor fan in column applications with hoop direction carbon fiber laminates was found to have a substantial impact on the failure mode of large diameter CF anchors. It was found that for 25 mm diameter CF anchors with a well confined anchor fan, approximately 50% of the straight anchor rupture capacity is possible with a 559 mm long anchor fan with fan angle of 37° and an embedment depth of the anchor dowel 10 times the anchor hole diameter.

Experimental research on shear performance of frontal fillet weld with beading defects

Weld beading is one of the typical welding defects commonly found in steel connections. Severe defects of weld beadings may significantly decrease the welding quality between the steel components; therefore, improving the safety risk in steel connection joints. To obtain a prediction model for shear resistance of frontal fillet weld (FFW) with weld beading defects, the influence laws of the weld beading on the shear properties of (FFW) was investigated in terms of the uniaxial shear loading test on 90 FFW specimens. The test results show that FFW specimens with a higher number of weld beads as well as greater toe height tend to suffer shear failure on one side of the weld. The contribution of the extended weld length to the strengthening of the ultimate shear load capacity of FFW specimens with weld defects is limited, while the amplification of the ductility ratio and initial shear stiffness is more pronounced. When the weld length exceeds 200 mm, the difference in weld toe height should be fully considered for the influence on the shear properties of the frontal fillet weld. Moreover, if the ratio of weld diameter to weld toe height is greater than 2, the impact of weld defects on FFW shear properties rises sharply as the weld diameter increases. A prediction model for the shear load capacity of FFWs with weld beading defects is proposed, which matches well with the test results and can serve as guidance for assessing the shear performance of FFWs with weld beading defects.

Shear Capacity Prediction Model of Deep Beam Based on New Hybrid Intelligent Algorithm

Accurate shear load capacity predictions are crucial to achieving the load-bearing requirements of concrete deep beams in a variety of construction structures. Conventional BP neural networks have the drawbacks of being prone to local optimums and having a sluggish rate of convergence for predicting the shear load capacity of reinforced concrete deep beams. To overcome this problem, this study incorporated the black widow optimization algorithm (BWO) and principal component analysis (PCA) into a BP neural network to create a unique Hybrid Intelligent Optimization Algorithm (PCA-BWO-BP). Firstly, PCA was used to reduce the dimensionality of the input variables of the shear load capacity prediction model of reinforced concrete deep beams. Secondly, BWO was introduced to optimize the weights and thresholds of the BP neural network. Finally, the four algorithms were compared and validated through the use of five model evaluators. The results showed that the PCA-BWO-BP model can explore the intrinsic relationship between member size, bottom longitudinal reinforcement, hoop reinforcement, concrete strength and the shear load capacity of reinforced concrete deep beams and generate reasonable prediction values, and the complexity of the prediction model can be effectively reduced by introducing the PCA algorithm, whereas the BWO algorithm can optimize the weights and thresholds of the BP neural network to improve the convergence and global search ability of the model. The mean absolute percentage error (MAPE) of the PCA-BWO-BP algorithm is 5.126, and the Nash efficiency coefficient (NS) is 0.989. The generalization ability and prediction accuracy are significantly better than those of the BP neural network, which can solve the problem relating to the fact that BP neural networks are prone to falling into the local optimum. The PCA-BWO-BP model has strong prediction ability, stability, generalization ability and robustness, which can predict the shear load capacity of reinforced concrete deep beams more accurately. It provides a new method and case support for further research on the shear bearing capacity of reinforced concrete deep beams.

A novel lithium-ion battery capacity prediction framework based on SVMD-AO-DELM

Accurate and efficient lithium-ion battery capacity prediction plays an important role in improving performance and ensuring safe operation. In this study, a novel lithium-ion battery capacity prediction model combining successive variational mode decomposition (SVMD) and aquila optimized deep extreme learning machine (AO-DELM) is proposed. Firstly, SVMD is used to divide capacity signal and it improves short-term trend prediction, especially for capacity growth that occurs during the degradation process. Secondly, the DELM network outperforms other networks in efficiently extracting time-dependent features, and it is more accurate than other standard ELM-based methods. The AO algorithm is used to find the parameters of the DELM training process for the problem of sensitivity to initial weights. Finally, experiments are conducted to validate the predictive performance of the proposed model based on NASA and CALCE lithium-ion batteries sequences. The MAE (0.0066Ah, 0.0044Ah), RMSE (0.0113Ah, 0.0078Ah), MAPE (0.44%, 0.82%) are effectively reduced, and the R2 (98.94%, 99.87%) is better than the prediction performance of other hybrid models.

Capacity Consistency Prediction and Process Parameter Optimization of Lithium‐Ion Battery based on Neural Network and Particle Swarm Optimization Algorithm

AbstractThe grading capacity of lithium‐ion battery is an important basis for evaluating battery quality. Aiming at the difficulty of determining the critical control factors and the threshold of the control parameters in the lithium‐ion battery manufacturing process, a capacity prediction and process parameter optimization model of lithium‐ion battery is proposed by combining the back propagation (BP) and particle swarm optimization (PSO) algorithms. First, the BP method is applied to establish the nonlinear mapping relationship between process data and grading capacity, which is regarded as the capacity consistency prediction model. Second, using the prediction model as fitness function and combining with PSO algorithm, the optimization model of process parameters is established. Finally, under the given initial process parameters from the lithium‐ion battery pilot line, it is carried out to obtain the best process parameter formula. The results show that the BP method has an accurate capacity consistency prediction effect. Combined with PSO algorithm, the optimized process parameters are obtained, which significantly improves the capacity consistency of lithium‐ion batteries. The results serve as an engineering application method to guide the selection and confirmation of process parameters at the battery design stage.

Behavior of embedded steel profile ultra-high performance concrete-filled stainless steel tubular short columns under axial compression

This study investigated the behavior of ultra-high performance concrete-filled stainless steel tubular columns with embedded steel profiles (ESUHPCFSST) under axial compression. Six short columns were designed with the parameters of diameter-to-thickness ratio and embedded steel profile ratio. Axial compression tests were conducted to investigate the failure modes, failure mechanisms, and the impact of relevant parameters on the mechanical properties of the specimens. A finite element model was developed and validated against the experimental results to enable a more comprehensive parameter analysis. The results indicate that the failure of the specimens always initiates from the steel profile flange and gradually extends to the external stainless steel tube. The initial stiffness, ultimate bearing capacity, and ductility of the specimens increase with decreasing diameter-to-thickness ratio and increasing embedded steel profile ratio. The strength of the embedded steel profile positively correlates with ultimate bearing capacity and ductility. Higher concrete strength improves ultimate bearing capacity but reduces ductility. Finally, a bearing capacity prediction model for ESUHPCFSST columns is proposed based on the experimental and finite element results, which guides the engineering application of such structures.

An Improved Equation for the Bearing Capacity of Concrete-Filled Steel Tube Concrete Short Columns Based on GPR

The determination of the bearing capacity prediction model of concrete-filled steel tubular columns is a key issue in the structural design of prefabricated buildings, which directly relates to the stability and safety of prefabricated buildings. The purpose of this paper is to study the bearing capacity model of concrete-filled steel tubular columns, and propose an explicit formula based on the Gaussian process regression algorithm to calculate the bearing capacity. In order to solve the problem of low accuracy of the traditional empirical bearing capacity model, this paper first proposes a more accurate bearing capacity prediction model based on Gaussian process regression algorithm to automatically learn and capture the characteristics of 122 groups of test data; the paper then determines the function of high sensitivity parameters and section influence parameters through the established bearing capacity prediction model, and this process gives the display formula. Compared with the implicit formula given by a machine learning model, the explicit formula proposed in this paper is more suitable for practical engineering design. In order to verify the validity of the formula, we generated the bearing capacity data through the proposed formula based on the test data and used the descriptive statistical method to verify. The results show that the proposed formula is superior to other existing methods, the error between the data generated by the proposed formula and the test data is smaller, and its accuracy reaches 93.73%, which is more suitable for calculating the bearing capacity of concrete-filled steel tubes with different cross sections.

Surface Mounted Production Line Capacity Prediction Based on Data Driven

Capacity prediction of surface mount production lines is important for improving productivity, dynamic production scheduling, and optimizing production structure. An integrated mutual information-cuckoo search-extreme learning machine (MI-CS-ELM) prediction model is proposed for the impact of nonlinear and high-dimensional features of surface-mounted production lines on capacity. Firstly, the features affecting the production capacity are ranked based on the mutual information method, and the predictive input data set is reconstructed. Secondly, the input parameters of the prediction model are adjusted by the cuckoo search algorithm and the capacity prediction model is built based on an extreme limit learning machine. Finally, the rationality of the proposed method is verified by an example to guide capacity planning and production scheduling optimization.

RESEARCH ON NODE NETWORK TRANSMISSION CAPACITY PREDICTION MODEL FOR LARGE SCALE REMOTE SENSING DATA COLLECTION

Abstract. In recent years, the use of remote sensing technology has grown exponentially in various industries such as agriculture, forestry, and urban planning. Remote sensing data collection systems rely on a network of nodes to collect and transmit data. The transmission capacity of these node networks is a critical factor in the performance and efficiency of the entire system. However, accurately predicting the transmission capacity of a node network can be a challenging task. To carry out large scale open remote sensing data collection, it is necessary to predict the network transmission capacity of nodes in the face of the difference in the execution speed of each node for various tasks. It is necessary to predict the network transmission capacity of nodes. In this research, we propose a node network transmission capacity prediction model for large scale remote sensing data collection using a combination of Particle Swarm Optimization (PSO) and Backpropagation (BP) algorithms. The proposed PSO-BP model aims to accurately predict the transmission capacity of a node network in a remote sensing data collection system. The model is tested and evaluated using a large-scale dataset and the results show that the proposed model outperforms existing models in terms of prediction accuracy. This work contributes to the field of remote sensing data collection by providing a reliable and efficient method for predicting the transmission capacity of node networks.

Experimental study of a composite beam externally bonded with a carbon fiber-reinforced plastic plate

According to the characteristics of steel fiber reinforced concrete (SFRC) with high tensile strength and carbon fiber reinforced plastic (CFRP) with high strength and light weight, a composite beam composed of CFRP plate, SFRC and ordinary concrete (OC) is developed in the paper. Eight specimens, including four CSOCBs with different heights of the SFRC and four SFRC–OC composited beams with varying heights of the SFRC, were tested to analyze the flexural behavior. The results show that the composite beam composed of OC, SFRC and CFRP improves the ultimate load capacity of the beam under unidirectional load, enhances the cracking and deformation resistance of the beam, and solves the defects of the weak tensile capacity of ordinary concrete beams. Applying them to the building structure can improve the stability of the structure and prolong the service life of the building. A prediction model for the bending capacity of the CSOCB was proposed and validated. Based on the limit state design method, the design formula for the bending capacity of the composite beam is described in detail herein.