基于Blending-Clustering集成学习的大坝变形预测模型

【目的】变形是反映大坝结构性态最直观的效应量,构建科学合理的变形预测模型是保障大坝安全健康运行的重要手段。针对传统大坝变形预测模型预测精度低、误报率高等问题导致的错误报警现象,【方法】选取不同预测模型和聚类算法集成,构建了一种Blending-Clustering集成学习的大坝变形预测模型,该模型以Blending对单一预测模型集成提升预测精度为核心,并通过Clustering聚类优选预测值改善模型稳定性。以新疆某面板堆石坝变形监测数据为实例分析,通过多模型预测性能比较,对所提出模型的预测精度和稳定性进行全面评估。【结果】结果显示:Blending-Clustering模型将预测模型和聚类算法集成,均方根误差(RMSE)和归一化平均百分比误差(nMAPE)明显降低,模型的预测精度得到显著提高;回归相关系数(R~2)得到提升,模型具备更强的拟合能力;在面板堆石坝上22个测点变形数据集上的预测评价指标波动范围更小,模型的泛化性和稳定性得到有效增强。【结论】结果表明:Blending-Clustering集成预测模型对于预测精度、泛化性和稳定性均有明显提升,在实际工程具有一定的应用价值。

Microstructure and thermal properties of dissimilar M300–CuCr1Zr alloys by multi-material laser-based powder bed fusion

Multi-material laser-based powder bed fusion (PBF-LB) allows manufacturing of parts with 3-dimensional gradient and additional functionality in a single step. This research focuses on the combination of thermally-conductive CuCr1Zr with hard M300 tool steel.Two interface configurations of M300 on CuCr1Zr and CuCr1Zr on M300 were investigated. Ultra-fine grains form at the interface due to the low mutual solubility of Cu and steel. The material mixing zone size is dependent on the configurations and tunable in the range of0.1–0.3 mm by introducing a separate set of parameters for the interface layers. Microcracks and pores mainly occur in the transition zone.Regardless of these defects, the thermal diffusivity of bimetallic parts with 50vol% of CuCr1Zr significantly increases by 70%–150%compared to pure M300. The thermal diffusivity of CuCr1Zr and the hardness of M300 steel can be enhanced simultaneously by applying the aging heat treatment.

基于Prophet算法和Blending集成学习的实时负荷中期预测

目前的中期负荷预测一般未考虑负荷实时状态,而负荷数据的非线性、季节性、随机性、时序性特征将影响实时负荷的中期预测。构建一个实时负荷中期预测的框架,采用Prophet算法提取负荷数据的季节性部分,采用Blending集成学习对负荷数据的非季节部分进行滚动预测,将季节性部分和非季节性部分合成中期负荷实时数据。爱尔兰电力系统的算例结果验证了模型的有效性和稳定性。

Probabilistic-Ellipsoid Hybrid Reliability Multi-Material Topology Optimization Method Based on Stress Constraint

This paper proposes a multi-material topology optimization method based on the hybrid reliability of the probability-ellipsoid model with stress constraint for the stochastic uncertainty and epistemic uncertainty of mechanical loads in optimization design.The probabilistic model is combined with the ellipsoidal model to describe the uncertainty of mechanical loads.The topology optimization formula is combined with the ordered solid isotropic material with penalization(ordered-SIMP)multi-material interpolation model.The stresses of all elements are integrated into a global stress measurement that approximates the maximum stress using the normalized p-norm function.Furthermore,the sequential optimization and reliability assessment(SORA)is applied to transform the original uncertainty optimization problem into an equivalent deterministic topology optimization(DTO)problem.Stochastic response surface and sparse grid technique are combined with SORA to get accurate information on the most probable failure point(MPP).In each cycle,the equivalent topology optimization formula is updated according to the MPP information obtained in the previous cycle.The adjoint variable method is used for deriving the sensitivity of the stress constraint and the moving asymptote method(MMA)is used to update design variables.Finally,the validity and feasibility of the method are verified by the numerical example of L-shape beam design,T-shape structure design,steering knuckle,and 3D T-shaped beam.

Multi-Material Topology Optimization of 2D Structures Using Convolutional Neural Networks

In recent years,there has been significant research on the application of deep learning(DL)in topology optimization(TO)to accelerate structural design.However,these methods have primarily focused on solving binary TO problems,and effective solutions for multi-material topology optimization(MMTO)which requires a lot of computing resources are still lacking.Therefore,this paper proposes the framework of multiphase topology optimization using deep learning to accelerate MMTO design.The framework employs convolutional neural network(CNN)to construct a surrogate model for solving MMTO,and the obtained surrogate model can rapidly generate multi-material structure topologies in negligible time without any iterations.The performance evaluation results show that the proposed method not only outputs multi-material topologies with clear material boundary but also reduces the calculation cost with high prediction accuracy.Additionally,in order to find a more reasonable modeling method for MMTO,this paper studies the characteristics of surrogate modeling as regression task and classification task.Through the training of 297 models,our findings show that the regression task yields slightly better results than the classification task in most cases.Furthermore,The results indicate that the prediction accuracy is primarily influenced by factors such as the TO problem,material category,and data scale.Conversely,factors such as the domain size and the material property have minimal impact on the accuracy.

基于Blending集成学习的多源信息液压系统多类故障诊断研究

针对传统故障诊断方法准确性不高、耗时长问题,研究通过多个EfficientNet模型对传感器数据进行预训练,并使用XGBoost作为元学习器,提出了一种基于Blending集成学习的多源信息液压系统多类故障诊断方法。实验结果表明,各个子分类器在训练次数达到300次后趋于收敛,准确率均达到95%左右。该方法具有较高的准确性和鲁棒性,为液压系统故障诊断提供了一种有效的解决方案。

基于Blending集成学习模型的电力市场日前出清电价预测

精准的掌握未来电价信息对把握市场的运行状态、支撑市场参与各方进行有效决策、推动市场主体合理优化资源配置具有重要意义。因此基于Blending集成学习机制构建了一种面向于日前电价预测的综合模型。该模型充分考虑电价的高波动性特点,采用Ashin变换,减小了输入数据波动性对预测模型的影响;选取SVM、LightGBM、EWNN、SARIMAX 4种较为成熟的单一电价预测模型作为初级学习器,进而保证了基于Blending集成学习模型的预测精度。选用美国PJM电力市场实际运行数据对上述构建的电价预测模型进行验证,通过对预测结果的对比分析,表明构建的基于Blending集成学习机制的电价综合预测模型集成了多种传统预测模型的优点,具有较好的准确性与稳定性。

基于FPFF-Blending模型融合的个体工商户信用评价研究

个体工商户信用评价研究往往通过单一机器学习模型建立,其预测精确率较低,抗干扰能力较弱。基于特征金字塔的FPFF特征融合算法,应用于Blending模型融合框架,建立个体工商户信用评价异质融合模型,并赋予模型可解释性,综合解决单一模型稳定性较差、原有Blending框架融合模型过拟合、融合模型缺乏可解释性的问题。通过对个体工商户数据集进行实证实验,结果表明:融合模型较单一机器学习模型在个体工商户信用评价场景下具有更优的预测性能和泛化能力。

Simultaneous multi-material embedded printing for 3D heterogeneous structures

In order to mimic the natural heterogeneity of native tissue and provide a better microenvironment for cell culturing,multi-material bioprinting has become a common solution to construct tissue models in vitro.With the embedded printing method,complex 3D structure can be printed using soft biomaterials with reasonable shape fidelity.However,the current sequential multi-material embedded printing method faces a major challenge,which is the inevitable trade-off between the printed structural integrity and printing precision.Here,we propose a simultaneous multi-material embedded printing method.With this method,we can easily print firmly attached and high-precision multilayer structures.With multiple individually controlled nozzles,different biomaterials can be precisely deposited into a single crevasse,minimizing uncontrolled squeezing and guarantees no contamination of embedding medium within the structure.We analyse the dynamics of the extruded bioink in the embedding medium both analytically and experimentally,and quantitatively evaluate the effects of printing parameters including printing speed and rheology of embedding medium,on the 3D morphology of the printed filament.We demonstrate the printing of double-layer thin-walled structures,each layer less than 200μm,as well as intestine and liver models with 5%gelatin methacryloyl that are crosslinked and extracted from the embedding medium without significant impairment or delamination.The peeling test further proves that the proposed method offers better structural integrity than conventional sequential printing methods.The proposed simultaneous multi-material embedded printing method can serve as a powerful tool to support the complex heterogeneous structure fabrication and open unique prospects for personalized medicine.

Evaluation of different crosslinking methods in altering the properties of extrusion-printed chitosan-basedmulti-material hydrogel composites

Three-dimensional printing technologies exhibit tremendous potential in the advancing fields of tissue engineering and regenerative medicine due to the precise spatial control over depositing the biomaterial.Despite their widespread utilization and numerous advantages,the development of suitable novel biomaterials for extrusion-based 3D printing of scaffolds that support cell attachment,proliferation,and vascularization remains a challenge.Multi-material composite hydrogels present incredible potential in this field.Thus,in this work,a multi-material composite hydrogel with a promising formulation of chitosan/gelatin functionalized with egg white was developed,which provides good printability and shape fidelity.In addition,a series of comparative analyses of different crosslinking agents and processes based on tripolyphosphate(TPP),genipin(GP),and glutaraldehyde(GTA)were investigated and compared to select the ideal crosslinking strategy to enhance the physicochemical and biological properties of the fabricated scaffolds.All of the results indicate that the composite hydrogel and the resulting scaffolds utilizing TPP crosslinking have great potential in tissue engineering,especially for supporting neo-vessel growth into the scaffold and promoting angiogenesis within engineered tissues.

Closed-loop scheduling optimization strategy based on particle swarm optimization with niche technology and soft sensor method of attributes-applied to gasoline blending process

Gasoline blending scheduling optimization can bring significant economic and efficient benefits to refineries.However,the optimization model is complex and difficult to build,which is a typical mixed integer nonlinear programming(MINLP)problem.Considering the large scale of the MINLP model,in order to improve the efficiency of the solution,the mixed integer linear programming-nonlinear programming(MILP-NLP)strategy is used to solve the problem.This paper uses the linear blending rules plus the blending effect correction to build the gasoline blending model,and a relaxed MILP model is constructed on this basis.The particle swarm optimization algorithm with niche technology(NPSO)is proposed to optimize the solution,and the high-precision soft-sensor method is used to calculate the deviation of gasoline attributes,the blending effect is dynamically corrected to ensure the accuracy of the blending effect and optimization results,thus forming a prediction-verification-reprediction closed-loop scheduling optimization strategy suitable for engineering applications.The optimization result of the MILP model provides a good initial point.By fixing the integer variables to the MILPoptimal value,the approximate MINLP optimal solution can be obtained through a NLP solution.The above solution strategy has been successfully applied to the actual gasoline production case of a refinery(3.5 million tons per year),and the results show that the strategy is effective and feasible.The optimization results based on the closed-loop scheduling optimization strategy have higher reliability.Compared with the standard particle swarm optimization algorithm,NPSO algorithm improves the optimization ability and efficiency to a certain extent,effectively reduces the blending cost while ensuring the convergence speed.

Feasibility Investigation of Bitumen Properties by Blending of Coal Tar Pitch

There are numerous methods and additives available to improve the durability and quality of road bitumen. A coal tar obtained by coal coking was distilled in a laboratory into fractions of initial boiling point IBP-180℃ (gasoline-like fuel), 180℃ - 360℃ (diesel-like fuel), and >360℃ (residue or coal tar pitch). The coal tar pitch was added into road bitumen by up to 1 - 5 wt% and investigated the alteration of physical and chemical properties. The physico-mechanical properties of coal tar pitch and bitumen blends, as well as the chemical group composition, were determined using standard techniques (MNS) and the SARA method, respectively. Results of 3% coal tar pitch addition into bitumen enhanced ductility by 12.4% and softening point by 1.6℃. We found that blending with bitumen coal tar pitch as a modifier could improve bitumen properties.

Conceptual Blending and Meme Humor on the Internet:The Example of COVID-19 Publicity Posters in Chinese Microblogging

Internet memes,as multimodal cultural products disseminated through the Internet,usually take the form of short videos or images that express humor or satire.The creation and dissemination of humor in memes are both creative and complex,and the successful perception of meme humor reflects humans’universal thinking capacity.Based on the theoretical framework of conceptual blending,this paper selects a set of COVID-19 publicity posters from the official Weibo account of China Guangzhou Fabu(Guangzhou Internet Information Office),analyses the multi-level structure of Internet memes,and explores the dynamic cognitive process in the interpretation of humorous memes to reveal people’s ability to make simultaneous analogies and integration between elements in different mental spaces.

The application study of dual-energy CT nonlinearblending technique in pulmonary angiography

Objective This study aimed to explore the feasibility of enhancing image quality in computed tomography(CT) pulmonary angiography (CTPA) and reducing radiation dose using the nonlinear blending (NLB)technique of dual-energy CT.Methods A total of 61 patients scheduled for CTPA were enrolled, and 30 patients underwent dual-energyscanning. Nonlinear blending images (NLB group) and three groups of linear blending images (LB group,80 kV group, and 140 kV group) were reconstructed after scanning;31 patients underwent single-energyscanning (120 kV group). The CT values and standard deviations of the pulmonary trunk, left and rightpulmonary arteries, and ipsilateral back muscle at the bifurcation level of the left and right pulmonaryarteries were measured. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of the fivegroups were calculated. The subjective image quality of the five groups was assessed. The radiation dosesof the dual- and single-energy groups were recorded and calculated.Results The CNR and SNR values of blood vessels in the NLB group were significantly higher than thosein the LB, 140 kV, and 80 kV groups (CNR of pulmonary artery trunk: t = 3.50, 4.06, 7.17, all P < 0.05;SNRof pulmonary trunk: t = 3.76, 4.71, 6.92, all P < 0.05). There were no statistical differences in the CNR andSNR values between the NLB group and 120 kV group (P > 0.05). The effective radiation dose of the dualenergygroup was lower than that of the single-energy group (t = –4.52, P < 0.05). The subjective scores ofimages in the NLB group were the highest (4.28 ± 0.74).Conclusion The NLB technique of dual-energy CT can improve the image quality of CTPA and reducethe radiation dose, providing more reliable imaging data for the clinical diagnosis of pulmonary embolism.

A review:Health benefits and physicochemical characteristics of blended vegetable oils

Oil blending is the method of choice used worldwide to improve oxidative stability and nutritional value.There is no such edible oil/fat that meets all the recommendations from the health point of view.The fatty acid composition of vegetable oils decides the fate of the oil.Pure single oil is unable to provide a balanced amount of fatty acids(FAs)required/recommended on a daily intake basis.Blending oils/fats is an appropriate procedure of physically mixing multiple oils in suitable proportions which may provide functional lipids with improved antioxidant potential and desirable physical and chemical properties.This review piled up the accessible data on the blending of diverse oils/fats in the combination of binary,ternary,quaternary,or other types of oils into a single blended oil.Blending can be found very convincing towards appropriate FA profile,enhancement in physicochemical characteristics,and augmented stability for the period of storage or when used as cooking/frying processes which could ultimately serve as an effectual dietary intervention towards the health protectiveness.

Umami taste components in chicken-spices blends and potential effect of aroma on umami taste intensity

In this study,umami taste intensity(UTI)and umami taste components in chicken breast(CB)and chickenspices blends were characterized using sensory and instrumental analysis.Our main objective was to assess the aroma-umami taste interactions in different food matrices and reconcile the aroma-taste perception to assist future product development.The impact of key aroma,including vegetable-note"2-pentylfuran",meaty"methional",green"hexanal",and spicy-note-estragole and caryophyllene"on UTI was evaluated in monosodium glutamate and chicken extract.We found that spices significantly decreased UTI and umami taste components in CB.Interestingly,the perceptually similar odorants and tastants exhibited the potential to enhance UTI in food matrices.Methional was able to increase the UTI,whereas spicy and green-note components could reduce the UTI significantly.This information would be valuable to food engineers and formulators in aroma selection to control the UTI perceived by consumers,thus,improving the quality and acceptability of the chicken products.

Research on Blended Teaching Mode:A Case Study of Floristry

In order to better carry out research on education and teaching,the author consulted relevant literature on blended teaching mode from 2011-2021 through CNKI,Web of Science and other websites,summarized and analyzed the research status of blended teaching mode,in order to lay a good foundation for studying blended teaching mode in course teaching.

The Effectiveness of the Havriliak-Negami Model in Predicting the Master Curves of the Asphalt Blends with SBS Triblock Copolymer and Organic-Montmorillonite at Different Temperatures and Frequencies

The dynamic viscoelastic properties of asphalt AC-20 and its composites with Organic-Montmorillonite clay (OMMt) and SBS were modeled using the empirical Havriliak-Negami (HN) model, based on linear viscoelastic theory (LVE). The HN parameters, α, β, G0, G∞and τHN were determined by solving the HN equation across various temperatures and frequencies. The HN model successfully predicted the rheological behavior of the asphalt and its blends within the temperature range of 25˚C - 40˚C. However, deviations occurred between 40˚C - 75˚C, where the glass transition temperature Tg of the asphalt components and the SBS polymer are located, rendering the HN model ineffective for predicting the dynamic viscoelastic properties of composites containing OMMt under these conditions. Yet, the prediction error of the HN model dropped to 2.28% - 2.81% for asphalt and its mixtures at 100˚C, a temperature exceeding the Tg values of both polymer and asphalt, where the mixtures exhibited a liquid-like behavior. The exponent α and the relaxation time increased with temperature across all systems. Incorporating OMMt clay into the asphalt blends significantly enhanced the relaxation dynamics of the resulting composites.

An Analysis on the Blended Teaching Mode of College English

This paper explores blended teaching in college English from five aspects:the connotation,theoretical basis,design principles,advantages,and challenges of blended teaching and blended teaching models.The purpose is to attract more foreign language practitioners and learners to pay attention to this model and put it into practice.

A Study on the Application of Peer Feedback among EFL Students in Blended Teaching

Recent years have witnessed the rise and popularity of blended teaching for EFL students,yet the lack of face-to-face communication and insufficient interaction lead researchers and educators to explore methods of improving the effectiveness of teaching.Peer feedback,a teaching strategy used to raise the bars by exposing instructions to a new teaching perspective to enhance students’online and offline collaboration,has received the lion’s share of attention in recent studies.On the basis of literature review,class records,and interviews,this paper,in hope of supporting advances in teachers’practice and field researches,examines the possible approaches to effectively implementing the application of peer feedback in blended teaching mode with a special focus on teachers’roles.