Search

Wind energy is highly volatile, and large-scale wind power grid integration significantly impacts grid stability. Accurate forecasting of wind turbine power can improve wind power consumption and ensure the economy of the power grid. This paper proposes a multistep forecasting method for offshore wind turbine power based on a multi-timescale input and an improved transformer. First, the wind speed sequence is decomposed by the VMD method to extract adequate timing information and remove the noise, after which the decomposition signals are merged with the rest of the timing features, and the dataset is split according to different timescales. A GRU receives the short-timescale inputs, and the Improved Transformer captures the timing relationship of the long-timescale inputs. Finally, a CNN is used to extract the information of each time point at the output of each branch, and the fully connected layer outputs multistep forecasting results. Experiments were conducted on operation data from four wind turbines located within the offshore wind farm but not near the edge. The results show that the proposed method achieved average errors of 0.0522 in MAE, 0.0084 in MSE, and 0.0907 in RMSE on a four-step forecast. This outperformed comparison methods LSTM, CNN-LSTM, LSTM-Attention, and Informer. The proposed method demonstrates superior forecasting performance and accuracy for multistep offshore wind turbine power forecasting. [ABSTRACT FROM AUTHOR]

To improve the power generation efficiency of offshore wind turbines and address the problem of high fire monitoring and warning costs, we propose a data-driven fire warning method based on transfer learning for wind turbines in this paper. This paper processes wind turbine operation data in a SCADA system. It uses an extreme gradient-boosting tree (XGBoost) algorithm to build an offshore wind turbine unit fire warning model with a multiparameter prediction function. This paper selects some parameters from the dataset as input variables for the model, with average cabin temperature, average outdoor temperature, average cabin humidity, and average atmospheric humidity as output variables. This paper analyzes the distribution information of input and output variables and their correlation, analyzes the predicted difference, and then provides an early warning for wind turbine fires. This paper uses this fire warning model to transfer learning to different models of offshore wind turbines in the same wind farm to achieve fire warning. The experimental results show that the prediction performance of the multiparameter is accurate, with an average MAPE of 0.016 and an average RMSE of 0.795. It is better than the average MAPE (0.051) and the average RMSE (2.020) of the prediction performance of a backpropagation (BP) neural network, as well as the average MAPE (0.030) and the average RMSE (1.301) of the prediction performance of random forest. The transfer learning model has good prediction performance, with an average MAPE of 0.022 and an average RMSE of 1.469. [ABSTRACT FROM AUTHOR]

Calculating impact forces in asymmetrical lateral structures has been a complex challenge that spans decades in engineering. Traditional models often fall short due to the inherent complexity of asymmetrical members and the need for significant computational resources or a vast pool of training data. This paper develops an approximate formula for accurately calculating the impact force of asymmetrical lateral-impact members under lateral impact. Existing methods for assessing impact forces have been limited in their application due to the inherent complexity of asymmetrical members and the significant computational resources or extensive training data they often require. Our approach employs the residuals margin method, and Laplace transforms to derive an efficient and accurate formula for impact force calculation. The paper rigorously validates this Formula through experimental testing, demonstrating high precision with an error margin of less than 5%. Further validation against diverse impact data from multiple studies on different materials and loadings under static and dynamic conditions confirmed the Formula's consistency. Despite simplifying assumptions, this research contributes a novel and computationally efficient approach for calculating impact forces. The formula offers engineers a practical tool while advancing a fundamental understanding of asymmetric impact dynamics. Rigid experimentation verified its significant accuracy, establishing the formula as a valuable structural impact analysis and design resource. This research presents an analytical formula for calculating impact forces on structures like buildings, bridges, and vehicles experiencing asymmetrical lateral impacts. Such impacts commonly occur due to falling debris, vehicle collisions, seismic pounding, and derailed train strikes. However, existing design formulas often oversimplify impact mechanics or require complex simulations. The proposed method provides engineers with a simple spreadsheet-compatible equation relating impact force directly to tangible mechanical quantities like momentum. This enables rapid impact load assessments essential for performance-based design against accidental hazards. The formula was validated through laboratory impact tests on reinforced concrete slabs, demonstrating precision within 5% of measured forces. Additional validations against published experimental and simulation data on different construction materials confirmed accuracy. The proposed formula equips structural engineers and safety analysts with a practical impact analysis tool by offering a computationally efficient approach with proven reliability. It facilitates assessing design performance for asymmetrical impact load scenarios, helping improve resilience for critical facilities subjected to hazardous lateral impacts. [ABSTRACT FROM AUTHOR]

The interface bond strength between carbon fiber-reinforced polymer (CFRP) layers and concrete is a crucial metric for determining the mechanical properties of CFRP-reinforced concrete. This bond strength is essential for evaluating CFRP-reinforced concrete's performance and ensuring the materials' structural integrity. A database was established using the experimental data in the literature to evaluate the interface bond strength. This database comprised 360 groups of different conditions test results of CFRP-reinforced concrete, which were used to create a prediction model using an artificial neural network. The database was randomly divided into two data sets: 310 groups were used for training the neural network model and 50 for simulated prediction. A three-layer artificial neural network model was trained using the backpropagation algorithm, which is widely used in artificial neural networks. The model's input layer considered seven parameters, including the type of CFRP layer, surface form, CFRP layer thickness, anchorage length, failure mode, concrete compressive strength, and normalized concrete cover thickness. These parameters were selected based on their known influence on the interface bond strength between the CFRP layers and concrete. The output layer of the model represented the interface bond strength between the CFRP layers and concrete. The model's results indicated that the backpropagation (BP) neural network model had strong capability of prediction and generalization. The predicting error was minimal, a crucial aspect of the model's accuracy. Further, this approach allows for integrating many factors that influence the interface bond strength between the CFRP layers and concrete, providing accurate predictions of the bond strength. It can be used as a valuable tool for evaluating the performance of CFRP-reinforced concrete. This research develops an accurate method to predict the bond strength between CFRP layers and concrete using artificial neural networks. A strong bond is crucial for the structural integrity of concrete reinforced with CFRP. The neural network model considers factors like the type and thickness of CFRP used, how the concrete surface is prepared, and the concrete's strength. Engineers can use this neural network tool to evaluate how well CFRP will reinforce specific concrete mixtures and structures before construction. This allows structures to be designed and built with optimal, cost-effective use of CFRP to reinforce concrete in applications like bridges and buildings. The neural network approach integrates many technological and material factors into one predictive model, providing a useful evaluation method for the construction industry. [ABSTRACT FROM AUTHOR]

This study investigated the impact of axial load on the dynamic response of reinforced concrete (RC) members to asymmetrical lateral impact loads. A series of asymmetrical-span impact tests were conducted on circular and square RC members with and without Carbon Fiber Reinforced Polymers (CFRP) while varying the axial compression ratios. The impact process was simulated using ABAQUS software, and the time history curves of deflection and impact were measured. The study found that specific impact loads caused bending and shearing failures. The axial compression ratio ranged from 0.05 to 0.13 when the impact curve reached its maximum deflection before the component's impact resistance decreased. Analysis of the impact point and inclined crack location revealed that axial load affects the maximum local concrete. The speed of inclined crack penetration and inclined cracks take longer to form, with weaker resistance to damage to local concrete when the axial compression ratio is between 0.05 and 0.13. When the axial compression ratio is greater than 0.13, inclined cracks form sooner with more brittle and severe damage to the impact point's concrete. The study also identified key parameters affecting the dynamic response of RC members, including impact height, CFRP layer thickness, axial force, and impact location. Thicker CFRP layers in RC can improve impact resistance, especially when the impact location is farther from the center. However, there is a limit to the impact of axial force on this resistance. [ABSTRACT FROM AUTHOR]

With the plethora of data on how CFRP layers enhance RCs under static loads, research on how the reinforced structural components react to unequal lateral impact loads from a derailed train striking metro station columns or a car accident is lacking. A similar motivation inspired the current study, which sought to create a numerical technique backed by actual testing to evaluate RC members with CFRP in a range of unequal lateral impact scenarios. This paper uses explicit nonlinear finite element techniques to numerically analyze the response of unequal lateral impact‐loaded RC members wrapped in (CFRP) layers. Diverse variables related to CFRP, concrete, steel reinforcement, and impact energy are investigated. This kind of thorough analysis provides unique insights to strengthen RC members against unequal lateral impact loads. The effects of internal forces and deflections, as well as absorbed energy on the impact response of CFRP‐RC components, were investigated and verified by prior experimental results. A parametric sensitivity analysis was conducted after the strain characteristics of steel bars confirmed the finite element model, reinforcement ratio, impact velocity, CFRP properties, and ductility index all influence the member's impact response. This study's results will help advance the field's understanding of CFRP‐RC components analysis and design under unequal lateral impact. [ABSTRACT FROM AUTHOR]

Reinforced concrete members under impact loading stress may be destroyed in a split period. Because of the need to investigate the impact resistance of reinforced concrete members, this issue remains a much-debated topic. This study investigates the response of reinforced concrete (RC) square members under an unequal lateral impact force. The performance of RC members under the effect of impact load is examined using a drop hammer impact test system. The importance of unequal lateral impact load is highlighted and addressed by examining RC members' failure mode and dynamic response characteristics. Four types of RC members are experimentally investigated in detail. A finite element method (FEM) modeling is proposed to predict the impact responses of the RC members. Moreover, the effects of the impact position, height, and hammer mass on the dynamic response characteristics under an impact force are evaluated. The predictions of the proposed numerical model are validated against experimental results, emphasizing impact force history, deflection time history, and failure modes. Results indicate the viability of the FEM model. The findings from the experimental and numerical studies can improve the impact-resistant performance of reinforced concrete members. [ABSTRACT FROM AUTHOR]

Strengthening with externally bonded CFRP reinforcement is widely used in structural reinforcement and attractive to stakeholders and engineers because of ease and speed of construction, corrosion resistance, lightweight, high strength, and versatility stiffness which can be oriented according to the need. Numerous research studies were carried out to explore RC beams' flexural and shear performance when subjected to dynamic impact loading. The results were auspicious in using such a technique of strengthening. Regular square section reinforced concrete frame members strengthened by CFRP material is taken as the research object. However, little attention to the impact behavior of CFRP-shear-strengthened square reinforced concrete (RC) specimens has been paid. The dynamic response of CFRP to reinforced concrete members under unequal cross-impact is discussed. This paper investigates the effectiveness of CFRP strengthening on the square RC specimen in preventing shear failure and evaluation of the flexural performance of the strengthened specimen under the impact load. The drop hammer impact test is firstly conducted on RC specimens with and without CFRP strengthening. The results show that using CFRP to strengthen the RC specimen in shear is very effective at preventing shear failure and leading the specimen's response to flexural domination. This result is also the motivation for developing a numerical model supported by experimental tests to study the flexural performance of strengthened RC specimens. It is found that the strengthened specimen is prone to exhibit pure bending deformation under the impact load in terms of dynamic amplification factor (DAF) for section moment. Then, an extensive parameter study is carried out to evaluate further the influence of impact velocity, reinforcement ratio, and concrete strength on the flexural performance of the strengthened specimen and CFRP layers. Such a holistic study may provide preliminary research regarding the use of CFRP to strengthen RC specimens in shear under impact loads and will enhance the current state of knowledge in this area; also, the optimal value of the CFRP reinforcement layer was proposed. [ABSTRACT FROM AUTHOR]

Building structure regularly needs reinforcement due to damage, specification requirements, and functional changes; carbon fiber reinforced polymer (CFRP) is widely used in structural reinforcement due to its high strength, lightweight, good corrosion resistance and easy construction. The regular square section reinforced concrete frame elements strengthened by CFRP material are taken as the research object. The dynamic response of CFRP to reinforced concrete elements under unequal lateral impact was discussed. This technical paper demonstrates that the test elements are subject to the bending failure mode, and the impact point and the near impact point support are severely damaged areas; the transversely wrapped elements are more abruptly broken, and the longitudinal wrapping elements and the number of wrapping layers can effectively reduce the level of damage. Analysis of the impact, deflection, and strain time history curves obtained in the test show that the wrapping mode and the number of layers have less influence on the impact force peak; the longitudinally wrapped elements and the plateau segment take longer. Dynamic equilibrium principle equation was proposed based on the experimental results. The horizontal partition plateau segment fluctuates greatly; the number of vertical wrap layers increases the plateau value. The larger the number of layers, the smaller the deflection caused by the impact. The longitudinal wrapping can effectively transmit the force. [ABSTRACT FROM AUTHOR]