Search results

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

The purpose of this research is to establish a robust numerical framework for the calibration of macroscopic constitutive parameters, based on the analysis of polycrystalline RVEs with computational homogenisation.

This framework is composed of four building-blocks: (1) the multi-scale model, consisting of polycrystalline RVEs, where the grains are modelled with anisotropic crystal plasticity, and computational homogenisation to link the scales, (2) a set of loading cases to generate the reference responses, (3) the von Mises elasto-plastic model to be calibrated, and (4) the optimisation algorithms to solve the inverse identification problem. Several optimisation algorithms are assessed through a reference identification problem. Thereafter, different calibration strategies are tested. The accuracy of the calibrated models is evaluated by comparing their results against an FE2 model and experimental data.

In the initial tests, the LIPO optimiser performs the best. Good results accuracy is obtained with the calibrated constitutive models. The computing time needed by the FE2 simulations is 5 orders of magnitude larger, compared to the standard macroscopic simulations, demonstrating how this framework is suitable to obtain efficient micro-mechanics-informed constitutive models.

This contribution proposes a numerical framework, based on FE2 and macro-scale single element simulations, where the calibration of constitutive laws is informed by multi-scale analysis. The most efficient combination of optimisation algorithm and definition of the objective function is studied, and the robustness of the proposed approach is demonstrated by validation with both numerical and experimental data.

In the field of steel defect detection, the existing detection algorithms struggle to achieve a satisfactory balance between detection accuracy, computational cost and inference speed due to the interference from complex background information, the variety of defect types and significant variations in defect morphology. To solve this problem, this paper aims to propose an efficient detector based on multi-scale information extraction (MSI-YOLO), which uses YOLOv8s as the baseline model.

First, the authors introduce an efficient multi-scale convolution with different-sized convolution kernels, which enables the feature extraction network to accommodate significant variations in defect morphology. Furthermore, the authors introduce the channel prior convolutional attention mechanism, which allows the network to focus on defect areas and ignore complex background interference. Considering the lightweight design and accuracy improvement, the authors introduce a more lightweight feature fusion network (Slim-neck) to improve the fusion effect of feature maps.

MSI-YOLO achieves 79.9% mean average precision on the public data set Northeastern University (NEU)-DET, with a model size of only 19.0 MB and an frames per second of 62.5. Compared with other state-of-the-art detectors, MSI-YOLO greatly improves the recognition accuracy and has significant advantages in computational cost and inference speed. Additionally, the strong generalization ability of MSI-YOLO is verified on the collected industrial site steel data set.

This paper proposes an efficient steel defect detector with high accuracy, low computational cost, excellent detection speed and strong generalization ability, which is more valuable for practical applications in resource-limited industrial production.

This proposal aims to forecast energy consumption in residential buildings based on the effect of opening and closing windows by the deep architecture approach. In this task, the developed model has three stages: (1) collection of data, (2) feature extraction and (3) prediction. Initially, the data for the closing and opening frequency of the window are taken from the manually collected datasets. After that, the weighted feature extraction is performed in the collected data. The attained weighted feature is fed to predict energy consumption. The prediction uses the efficient hybrid multi-scale convolution networks (EHMSCN), where two deep structured architectures like a deep temporal context network and one-dimensional deep convolutional neural network. Here, the parameter optimization takes place with the hybrid algorithm named jumping rate-based grasshopper lemur optimization (JR-GLO). The core aim of this energy consumption model is to predict the consumption of energy accurately based on the effect of opening and closing windows. Therefore, the offered energy consumption prediction approach is analyzed over various measures and attains an accurate performance rate than the conventional techniques.

An EHMSCN-aided energy consumption prediction model is developed to forecast the amount of energy usage during the opening and closing of windows accurately. The emission of CO₂ in indoor spaces is highly reduced.

The MASE measure of the proposed model was 52.55, 43.83, 42.01 and 36.81% higher than ANN, CNN, DTCN and 1DCNN.

The findings of the suggested model in residences were attained high-quality measures with high accuracy, precision and variance.

Based on the strong feature representation ability of the convolutional neural network (CNN), generous object detection methods in remote sensing (RS) have been proposed one after another. However, due to the large variation in scale and the omission of relevant relationships between objects, there are still great challenges for object detection in RS. Most object detection methods fail to take the difficulties of detecting small and medium-sized objects and global context into account. Moreover, inference time and lightness are also major pain points in the field of RS.

To alleviate the aforementioned problems, this study proposes a novel method for object detection in RS, which is called lightweight object detection with a multi-receptive field and long-range dependency in RS images (MFLD). The multi-receptive field extraction (MRFE) and long-range dependency information extraction (LDIE) modules are put forward.

To concentrate on the variability of objects in RS, MRFE effectively expands the receptive field by a combination of atrous separable convolutions with different dilated rates. Considering the shortcomings of CNN in extracting global information, LDIE is designed to capture the relationships between objects. Extensive experiments over public datasets in RS images demonstrate that our MFLD method surpasses the state-of-the-art methods. Most of all, on the NWPU VHR-10 dataset, our MFLD method achieves 94.6% mean average precision with 4.08 M model volume.

This paper proposed a method called lightweight object detection with multi-receptive field and long-range dependency in RS images.

The anomaly detection task for oil and gas pipelines based on acoustic signals faces issues such as background noise coverage, lack of effective features, and small sample sizes, resulting in low fault identification accuracy and slow efficiency. The purpose of this paper is to study an accurate and efficient method of pipeline anomaly detection.

First, to address the impact of background noise on the accuracy of anomaly signals, the adaptive multi-threshold center frequency variational mode decomposition method(AMTCF-VMD) method is used to eliminate strong noise in pipeline signals. Secondly, to address the strong data dependency and loss of local features in the Swin Transformer network, a Hybrid Pyramid ConvNet network with an Agent Attention mechanism is proposed. This compensates for the limitations of CNN’s receptive field and enhances the Swin Transformer’s global contextual feature representation capabilities. Thirdly, to address the sparsity and imbalance of anomaly samples, the SpecAugment and Scaper methods are integrated to enhance the model’s generalization ability.

In the pipeline anomaly audio and environmental datasets such as ESC-50, the AMTCF-VMD method shows more significant denoising effects compared to wavelet packet decomposition and EMD methods. Additionally, the model achieved 98.7% accuracy on the preprocessed anomaly audio dataset and 99.0% on the ESC-50 dataset.

This paper innovatively proposes and combines the AMTCF-VMD preprocessing method with the Agent-SwinPyramidNet model, addressing noise interference and low accuracy issues in pipeline anomaly detection, and providing strong support for oil and gas pipeline anomaly recognition tasks in high-noise environments.

The purpose of this paper is to clarify the influence of low earth orbit space environment on the wear mechanism of TC4 alloy material and crank rocker mechanism.

In this study, friction experiments were carried out on TC4 alloy friction discs and crank rocker mechanisms, both before and after exposure to atomic oxygen and proton irradiation. Nanoindentation, grazing incidence X-ray diffraction (GIXRD), and X-ray photoelectron spectroscopy were employed to systematically characterize alterations in mechanical properties, surface phase, and chemical composition.

The results show that the wear mechanism of TC4 alloy friction disc is mainly adhesive wear in vacuum environment, while the wear mechanism of crank rocker mechanism includes not only adhesive wear but also abrasive wear. Atomic oxygen exposure leads to the formation of more oxides on the surface of TC4 alloy, which form abrasive particles during the friction process. Proton irradiation will lead to a decrease in fatigue performance and an increase in hardness on the surface of TC4 alloy, thus causing fatigue wear on the surface of TC4 alloy, and more furrows appear on the crank rocker mechanism after proton irradiation. In the three environments, the characteristics of abrasive wear of the crank rocker mechanism are more obvious than those of the TC4 alloy friction disc.

These results highlight the importance of understanding the subtle effects of atomic oxygen and proton irradiation on the wear behavior of TC4 alloy and provide some insights for optimizing its performance in space applications.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-02-2024-0051/

Powder bed additive manufacturing has recently seen substantial growth, yet consistently producing high-quality parts remains challenging. Recoating streaking is a common anomaly that impairs print quality. Several data-driven models for automatically detecting this anomaly have been proposed, each with varying effectiveness. However, comprehensive comparisons among them are lacking. Additionally, these models are often tailored to specific data sets. This research addresses this gap by implementing and comparing these anomaly detection models for recoating streaking in a reproducible way. This study aims to offer a clearer, more objective evaluation of their performance, strengths and weaknesses. Furthermore, this study proposes an improvement to the Line Profiles detection model to broaden its applicability, and a novel preprocessing step was introduced to enhance the models’ performances.

All found anomaly detection models have been implemented along with several preprocessing steps. Additionally, a new universal benchmarking data set has been constructed. Finally, all implemented models have been evaluated on this benchmarking data set and the effect of the different preprocessing steps was studied.

This comparison shows that the improved Line Profiles model established it as the most efficient detection approach in this study’s benchmark data set. Furthermore, while most state-of-the-art neural networks perform very well off the shelf, this comparison shows that specialised detection models outperform all others with the correct preprocessing.

This comparison gives new insights into different recoater streaking (RCS) detection models, showcasing each one with its strengths and weaknesses. Furthermore, the improved Line Profiles model delivers compelling performance in detecting RCS.

The premise of this research is that the coupling of reinforcement learning algorithms and computational dynamics can be used to design efficient control strategies and to improve the cooling of hot components by quenching, a process that is classically carried out based on professional experience and trial-error methods. Feasibility and relevance are assessed on various 2-D numerical experiments involving boiling problems simulated by a phase change model. The purpose of this study is then to integrate reinforcement learning with boiling modeling involving phase change to optimize the cooling process during quenching.

The proposed approach couples two state-of-the-art in-house models: a single-step proximal policy optimization (PPO) deep reinforcement learning (DRL) algorithm (for data-driven selection of control parameters) and an in-house stabilized finite elements environment combining variational multi-scale (VMS) modeling of the governing equations, immerse volume method and multi-component anisotropic mesh adaptation (to compute the numerical reward used by the DRL agent to learn), that simulates boiling after a phase change model formulated after pseudo-compressible Navier–Stokes and heat equations.

Relevance of the proposed methodology is illustrated by controlling natural convection in a closed cavity with aspect ratio 4:1, for which DRL alleviates the flow-induced enhancement of heat transfer by approximately 20%. Regarding quenching applications, the DRL algorithm finds optimal insertion angles that adequately homogenize the temperature distribution in both simple and complex 2-D workpiece geometries, and improve over simpler trial-and-error strategies classically used in the quenching industry.

To the best of the authors’ knowledge, this constitutes the first attempt to achieve DRL-based control of complex heat and mass transfer processes involving boiling. The obtained results have important implications for the quenching cooling flows widely used to achieve the desired microstructure and material properties of steel, and for which differential cooling in various zones of the quenched component will yield irregular residual stresses that can affect the serviceability of critical machinery in sensitive industries.

In the dynamic realm of energy storage, lithium-ion batteries stand out as a frontrunner, powering a myriad of devices from smartphones to electric vehicles. However, efficient heat management is crucial for ensuring the longevity and safety of these batteries. This paper aims to delve into the process of lithium-ion battery heat management systems, exploring how cutting-edge technologies are used to regulate temperature and optimize performance. In addition, computational fluid dynamics (CFD) studies take center stage, offering insights into the intricate thermal dynamics within these powerhouses.

In this study, thermal behavior of pouch type lithium-ion battery cell has been investigated by using CFD method. Result of different discharge rates have been evaluated by using multi-scale multi-dimensional (MSMD) battery model. By using MSMD Model 0.5C, 1C, 2C, 3C and 5C discharge rates are compared in equivalent circuit model (ECM) and NTGK empirical models by monitoring averaged surface temperature on battery body wall. In addition, on NTGK model, air cooling effect has been studied with the 0.1 m/s, 0.2 m/s and 0.5 m/s air, velocities.

Results shows that higher discharge rate causes higher temperature on battery zones and air cooling is effective to obtain the lower zone temperatures. Also, ECM model gives higher temperature than NTGK model on battery zone.

When the literature is evaluated, comparison of the models used in battery cooling (ECM and NTGK) has never been done before. Within the scope of this study, model comparison was made. At the same time, the time step has always been ignored in the literature. In this study, both time step and forced convection conditions were considered when comparing the models.