Complex shape aerodynamic optimization frequently encounters the problem of dimensionality curse. Extracting geometric features from the original design space proves effective in this issue by ...reconstructing shapes with lower-dimension. While deep learning methods possess strong capabilities in dimensionality reduction, they suffer from longer training times and higher computational resource requirements. However, Proper Orthogonal Decomposition (POD) presents a more practical algorithm that can be effectively utilized for complex high-dimensional shapes. In this study, we propose a combination of the POD-based method and Gaussian Process Regression with an automatic kernel construction algorithm (AKC-GPR) to optimize complex shapes in a lower-dimensional reparameterization space using small training sets. This approach aims to explore the potential for reducing optimization cost. By reducing the design parameters from 56 to 18 with an error rate of 1.28 %, we establish surrogate models for optimization using AKC-GPR with progressively decreasing training sets. For samples below 100, the Mean Absolute Percentage Errors (MAPEs) remain below 2 %, while the Mean Relative Percentage Errors (MRPEs) approach 10 %. It emphasizes the proficiency of POD in geometric dimensionality reduction. The optimized shapes exhibit smoother contour, resulting in a 10 % improvement in lift and a relatively modest reduction in drag of less than 3 %. The lift-to-drag ratio experiences an increase of over 14 %. The shapes optimized by various training sets possess minimal differences in geometric shapes and aerodynamic characteristics. This confirms the AKC-GPR algorithm's high-precision fitting capability in effectively handling complex aerodynamic coefficients of multi-parameter shapes during small-sample shape optimization.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
To facilitate isogeometric analysis, this paper presents a new type of T-spline named the weighted T-spline, which introduces a new weighting idea to T-spline basis functions. Weighted T-spline basis ...functions satisfy partition of unity and are linearly independent. In addition, we apply the bicubic weighted T-splines to reparameterize trimmed NURBS surface patches. Edge interval extension is performed to reconstruct the trimming curve on the T-spline surface, and the trimming curve can be exactly preserved. Comparisons with standard T-splines show that the weighted T-splines can decrease the required number of control points and T-mesh elements. The surface error introduced by weighted T-spline basis functions is bounded (within 0.5%), and the error introduced by the trimming curve is constrained within its three-ring neighboring elements. Weighted T-spline models are also applied to solve the linear elasticity problems and Poisson’s equation, demonstrating that they can be used in isogeometric analysis.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Selain produksi biodiesel, bioetanol, biometana dan biohidrogen dari sumber terbarukan, gamma-valerolactone (GVL) muncul sebagai bahan bakar terbarukan potensial lainnya yang dapat diproduksi dari ...biomassa. GVL menunjukkan karakteristik yang sesuai sebagai sumber energi cair berkelanjutan yang menjanjikan. Dlaam kegiatan produksi GVL murni jumlah besar pastinya melibatkan proses pemisahan/ pemurnian, salah satunya adalah distilasi. Dalam perancangan proses distilasi diperlukan data kesetimbangan Uap – Cair (VLE), dan untuk akurasi perancangan biasanya digunakakan software simulasi proses seperti ChemCAD. Dalam penelitian ini, data VLE yang tersedia akan direparamterisasi sehingga bisa digunakan sebagai parameter model thermodinamika di Software ChemCAD. Pada penelitian ini dilakukan reparemeterisasi parameter interaksi biner (BIP) model NRTL untuk data VLE komponen yang terlibat dalam produksi GVL dari literature yang tersedia. Kemudian BIP hasil reparemterisasi digunakan untuk analisis sensitivitas pada shortcut kolom distilasi. Hasil analisis sensitivitas menunjukan bahwa perubahan suhu umpan berpengaruh terhadap konvigurasi kolom, tetapi tidak pada kualitas GVL yang dihasilkan
In addition to producing biodiesel, bioethanol, biomethane, and biohydrogen from renewable sources, gamma- valerolactone (GVL) is emerging as a potential renewable fuel from biomass. As a promising long-term liquid energy source, GVL possesses the necessary characteristics. The production of pure GVL in large quantities involves a separation/purification process, one of which is distillation. In designing the distillation process, Vapor- Liquid equilibrium(VLE) data is needed, and process simulation software such as ChemCAD is usually used for design accuracy. In this study, the available VLE data will be reparameterized to be used as a thermodynamic model parameter in ChemCAD Software. The binary interaction parameter (BIP) NRTL model reparameterization for the VLE data of the components involved in the creation of GVL was carried out in this work using data from the literature. The reparameterized BIP was then applied to the distillation column shortcut for sensitivity analysis. The findings of the sensitivity study reveal that changing the feed temperature changes the column arrangement but not the quality of the GVL produced
Due to the complex background, small and dense targets, and large scale continuous changes in remote sensing images, universal object detectors are difficult to adapt well, resulting in poor ...detection performance. To address the above issues, a multi-branch feature mapping based remote sensing image object detection algorithm is proposed based on the YOLOv5s model. Firstly, a RepVGG module combined with gated channel transformation is designed using structural reparameterization technology. Its series structure is used to replace the C3 module of the original backbone network, aggregating global contextual information and enhancing feature expression and extraction capabilities. Secondly, the adaptive exponential weighted pooling method and the sampling method of inverse process reconstruction feature fusion network are used to maximize the retention of feature information and improve the detection performance of smaller targets. Finally, the combination of EIoU and Focal Loss is introduced as the loss functi
With the development of technology, using radar for gesture recognition is feasible and valuable. However, ensuring that gesture recognition can be applied to a wide range of scenarios with ...sufficient accuracy is still challenging. Due to the lack of accuracy and efficiency of traditional methods, we propose a gesture recognition scheme based on deep learning. We converted radar signals into pictures and designed a lightweight network called a self-reparameterization network based on distance and velocity awareness and binary coding (SR-DVBNet) to match them. We use the Self-reparameterization Encoder of the signal as the baseline of the network and add distance- and velocity-aware embedding (DVAE) between different blocks to do weighting for different dimensions. Since gesture recognition by radar signals often uses 2-D data, such as RDM or chirp-arranged matrices, we designed the DVAE module, which can weigh the different dimensions of the data separately to enhance the interpretability and gesture recognition accuracy of the model. At the same time, we use binary descriptors as the final representation of feature vectors for classification, which can well reflect the features of images and improve classification accuracy. Finally, we verify the algorithm's effectiveness on two publicly available datasets and achieve an accuracy rate of more than 98%, surpassing other known gesture recognition algorithms.
The longitudinal pattern of root aerenchyma formation of its relationship with the function of adventitious roots in rice remains unclear. In this study, the percentage of the aerenchyma area to the ...cross-sectional area (i.e., aerenchyma percentage) was fit with four non-linear models, namely, W
-Gompertz, Ti-Gompertz, logistic, and von Bertalanffy. Goodness-of-fit criteria such as the
, the Akaike information criterion (AIC), and the Bayesian information criterion (BIC) were used to select the model. The bias of the parameters was evaluated using the difference between the ordinary least squares-based parameter estimates and the mean of 1,000 bootstrap-based parameter estimates and the symmetry of the distributions of these parameters. The results showed that the Ti-Gompertz model, which had a high goodness-of-fit with an
close to 1, lower AIC and BIC values, parameter estimates close to being unbiased, and good linear approximation, provided the best fit for the longitude pattern of rice aerenchyma formation with different root lengths among the competing models. Using the second- and third-order derivatives according to the distance from the root apex, the critical points of Ti-Gompertz were calculated. The rapid stage for aerenchyma formation was from the maximum acceleration point (1.38-1.76 cm from the root apex) to the maximum deceleration point (3.13-4.19 cm from the root apex). In this stage, the aerenchyma percentage increased by 5.3-15.7% per cm, suggesting that the cortical cells tended to die rapidly for the aerenchyma formation rather than for the respiration cost during this stage. Meanwhile, the volume of the aerenchyma of the entire roots could be computed using the integral function of the Ti-Gompertz model. We proposed that the longitudinal pattern of root aerenchyma formation modeled by the Ti-Gompertz model helped to deeply understand the relationship between the anatomical traits and physiological function in rice adventitious roots.
The data-consistency item is a necessary condition for a reliable solution to the inverse problem. However, the current supervised-based deep-learning reconstruction approaches generally lack the ...data-consistency item, which directly leads to unreliable subsurface images for field data. To resolve this problem, we have developed a consistent least-squares reverse time migration (CLSRTM) approach using convolutional neural networks (CNNs), which is referred to as CNN-CLSRTM. The key point is that we have enforced that the predicted recording via the inverted image from the CNN model is consistent with the observed recording in the least-squares sense. We utilize the standard reverse time migration (RTM) image of single-shot recording as the input of the constructed CNN model. As a result, the optimal reflection image can be obtained by iteratively updating the parameters of CNN by minimizing the data residuals. Benefiting from the similarity of RTM images of adjacent recordings and the representation ability of the well-trained CNN model, we can directly predict the optimal reflection image for the testing datasets in a very fast way, which can greatly improve computational efficiency. Through synthetic and field data sets, we have determined that the proposed CNN-CLSRTM approach can retrieve high-resolution images with balanced amplitudes and continuous events. At the same time, our approach has better antinoise ability inherited from the benefit of CNN model compared to the standard LSRTM approach. In addition, we analyze the generalization ability of the CNN model for synthetic and field datasets.
This work presents a machine learning approach to optimize the energy efficiency (EE) in a multi-cell wireless network. This optimization problem is non-convex and its global optimum is difficult to ...find. In the literature, either simple but suboptimal approaches or optimal methods with high complexity are proposed. In contrast, we propose an unsupervised machine learning framework to approach the global optimum. While the neural network (NN) training takes moderate time, application with the trained model requires very low computational complexity. In particular, we introduce a novel objective function based on stochastic actions to solve the non-convex optimization problem. Besides, we design a dedicated NN architecture SINRnet for the power allocation problems in the interference channel that is permutation-equivariant. We encode our domain knowledge into the NN design and shed light into the black box of machine learning. Training and testing results show that the proposed method without supervision and with reasonable computational effort achieves an EE close to the global optimum found by the branch-and-bound algorithm and outperform the successive convex approximation (SCA) algorithm. Hence, the proposed approach balances between computational complexity and performance.