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。

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。

Multi-objective Design of Blending Fuel by Intelligent Optimization Algorithms

Fuel design is a complex multi-objective optimization problem in which facile and robust methods are urgently demanded.Herein,a complete workflow for designing a fuel blending scheme is presented,which is theoretically supported,efficient,and reliable.Based on the data distribution of the composition and properties of the blending fuels,a model of polynomial regression with appropriate hypothesis space was established.The parameters of the model were further optimized by different intelligence algorithms to achieve high-precision regression.Then,the design of a blending fuel was described as a multi-objective optimization problem,which was solved using a Nelder–Mead algorithm based on the concept of Pareto domination.Finally,the design of a target fuel was fully validated by experiments.This study provides new avenues for designing various blending fuels to meet the needs of next-generation engines.

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.

A deep reinforcement learning approach to gasoline blending real-time optimization under uncertainty

The gasoline inline blending process has widely used real-time optimization techniques to achieve optimization objectives,such as minimizing the cost of production.However,the effectiveness of real-time optimization in gasoline blending relies on accurate blending models and is challenged by stochastic disturbances.Thus,we propose a real-time optimization algorithm based on the soft actor-critic(SAC)deep reinforcement learning strategy to optimize gasoline blending without relying on a single blending model and to be robust against disturbances.Our approach constructs the environment using nonlinear blending models and feedstocks with disturbances.The algorithm incorporates the Lagrange multiplier and path constraints in reward design to manage sparse product constraints.Carefully abstracted states facilitate algorithm convergence,and the normalized action vector in each optimization period allows the agent to generalize to some extent across different target production scenarios.Through these well-designed components,the algorithm based on the SAC outperforms real-time optimization methods based on either nonlinear or linear programming.It even demonstrates comparable performance with the time-horizon based real-time optimization method,which requires knowledge of uncertainty models,confirming its capability to handle uncertainty without accurate models.Our simulation illustrates a promising approach to free real-time optimization of the gasoline blending process from uncertainty models that are difficult to acquire in practice.

Influence of Blended Course Teaching Reform on Student Satisfaction

With the rapid development of information technology in contemporary times,the blended teaching mode that blends online and offline courses has become an international trend in higher education.Taking blended tourism management courses at Chongqing Three Gorges University as an example,we explored the impact of such teaching reform on student satisfaction based on the SERVPERF model.Empirical analysis of 179 valid questionnaires revealed that five elements of the reform,namely,reliability,assurance,valuableness,responsiveness,and empathy,have a significant positive impact on students’learning satisfaction.Specifically,in the context of blended courses,factors such as a stable and reliable teaching environment,comprehensively guaranteed educational conditions,teaching content that highly aligns with students’demands and value expectations,prompt responses to students’needs and feedback,and empathetic consideration of students’perspectives are critical for enhancing student satisfaction.Based on these conclusions,we propose several strategies and methods for improving the effectiveness of blended teaching in the hope of propelling its continuous improvement and optimization,thus further elevating the quality of higher education.

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.

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。

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.

Research Status,Practical Dilemmas,and Optimization Strategies of Blended Teaching in Universities

Blended teaching has emerged as a prominent subject in the recent reform and innovation of higher education.It has become imperative and guiding for colleges and universities to embrace a mixed teaching approach that aligns with the evolving needs of education and teaching in the new era.This paper aims to provide a comprehensive overview of the research status surrounding blended teaching,encompassing fundamental issues,teaching design,practical guidance,teaching effectiveness,and evaluation.By critically examining the current challenges associated with blended teaching,this study proposes optimization strategies including enhancing student participation and interaction,promoting deep learning,improving teachers’preparedness,teaching technologies,and curriculum design capabilities,strengthening top-level design,and perfecting evaluation and incentive mechanisms.These strategies provide new directions for the reform of blended teaching.

Effects of Perceived Teacher Support on Student Behavioral Engagement in the Blended Learning Environment:Learning Experience as a Mediator

Blended learning(BL)has been widely adopted to improve students’academic achievements in higher education.However,its success relies mainly on student engagement,which plays an essential role in active learning and provides a rich understanding of students’experiences.The study utilized three self-designed scales-the Teacher Support Scale,Student Engagement Scale,and Student Learning Experience Scale-to gauge and examine the impact and relationship between perceived teacher support,student behavioral engagement,and the intermediary role of learning experiences.A cohort of 899 college students undertaking the obligatory College English course through BL modes across five Chinese universities actively participated by completing a comprehensive questionnaire.The results showed significant correlations between perceived teacher support,learning experience,and behavioral engagement.Perceived teacher support significantly predicted students’behavioral engagement,with socio-affective support exerting the most substantial predictive effects.All predictive effects were partially mediated by learning experience(learning mode,online resources,overall LMS-based learning,interaction with their instructor and peers,and learning outcome).The influence of perceived teacher support on behavioral engagement differed between students who reported the most positive(vs.negative)learning experiences.Suggestions for further research are offered for consideration.

Research and Practice of the Blended Teaching Model of BOPPPS Teaching Method Under the Background of Digital Education: Taking Operations Research Course as an Example

The rapid development of digital education provides new opportunities and challenges for teaching model innovation.This study aims to explore the application of the BOPPPS(Bridge-in,Objective,Pre-assessment,Participatory learning,Post-assessment,Summary)teaching method in the development of a blended teaching model for the Operations Research course under the background of digital education.In response to the characteristics of the course and the needs of the student group,the teaching design is reconstructed with a student-centered approach,increasing practical teaching links,improving the assessment and evaluation system,and effectively implementing it in conjunction with digital educational technology.This teaching model has shown significant effectiveness in the context of digital education,providing valuable experience and insights for the innovation of the Operations Research course.

Application Effect of Blended Education Strategy Based on the Learning Pass Platform in Phase III Cardiac Rehabilitation of Patients with Coronary Artery Disease

Objective:To explore the application effect of the blended education strategy based on the Learning Pass platform in the phase III cardiac rehabilitation of patients with coronary artery disease.Methods:90 patients diagnosed with coronary artery disease in the Department of Cardiology of our hospital from January 2019 to January 2021 were selected and divided into the control group and the experimental group according to the method of randomized numerical table,with 45 cases in each group.Both the experimental group and the control group received pre-discharge cardiac rehabilitation education by conventional means.The control group received education and supervision information via WeChat after discharge,while the experimental group joined the Learning Pass platform to receive online and offline hybrid education and supervision,with online as the mainstay and offline as a supplement.The disease cognitive level,self-management skills,quality of life,medication adherence,and emotional status of the two groups were compared.Results:The disease cognitive levels in the experimental group were significantly higher than those of the control group(P<0.05);the scores of the experimental group in terms of quality of life,self-management skills,and medication adherence were significantly higher than those of the control group(P<0.05);and the scores of anxiety and depression in the experimental group were significantly lower than those of the control group(P<0.05).Conclusion:The blended education strategy based on the Learning Pass platform has a significant application effect in phase III cardiac rehabilitation of patients with coronary artery disease.It can improve patients’disease cognitive level,self-management skills,and quality of life,and provide a basis for improving patients’prognosis.

Terminal Blend橡胶泡沫沥青制备及性能评价

为弥补传统泡沫沥青高温稳定性和黏附性的不足,解决传统橡胶沥青发泡效果不理想的缺陷,对terminal blend(TB)橡胶泡沫沥青进行了研究,探究了TB橡胶泡沫沥青发泡效果的影响规律,对其微观形貌与特征进行了表征,同时评估了TB橡胶泡沫沥青的高温性能、温度敏感性和黏度.结果表明:采用TB橡胶沥青制备泡沫沥青具备可行性;相比传统泡沫沥青,TB橡胶泡沫沥青在温度敏感性降低的同时,还显著提升了高温性能和黏度;微观结果显示TB橡胶泡沫沥青的发泡过程仅为物理过程,而且受发泡温度和发泡用水量的影响,其中后者对整体发泡效果的影响更加明显;TB橡胶泡沫沥青的最佳发泡温度为160°C、发泡用水量为2.7%.

Separation of a C_(3)H_(6)/C_(2)H_(4) mixture using Pebax^(■) 2533/PEG600 blend membranes

In industry, ethylene(C_(2)H_(4))/propylene(C_(3)H_(6)) separations are usually performed by a cryogenic process,which is energy intensive. Membrane separation technology is an alternative separation process that saves energy and is efficient. In this study, blend membranes were prepared by doping polyethylene glycol(PEG600) into a poly(ether-block-amide)(Pebax^(■) 2533) matrix and were used to separate the C_(2)H_(4)/C_(3)H_(6) mixture. The PEG 600 and Pebax^(■) 2533 polymers have good compatibility because they share hydrogen bonds. The addition of PEG600 is conducive to the hydrophilicity and the free volume of blend membranes, and it is also conducive to the solubility of C_(2)H_(4) and C_(3)H_(6) in the membranes, which improves the ability of the membranes to separate this gas pair. The Pebax^(■) 2533/PEG600 blend membrane with 15%(mass) PEG600 showed the highest separation performance in our investigated membranes, with a C_(3)H_(6)/C_(2)H_(4) selectivity of 8.9 and a C_(3)H_(6) permeability of 196 barrer(1 barrer = 1.33×10^(14)m^(3)(STP)·m·m^(-2)·s^(-1)·kPa^(-1)) at 238 K and 0.2 MPa, which is higher than that of the Pebax^(■) 2533/NaY-6%(mass) membrane(α_(C_(3)H_(6)/C_(2)H_(4)) =6.5, P_(C_(3)H_(6))=211 barrer) reported in our previous work. It is confirmed that incorporating PEG600 into the Pebax^(■) 2533 matrix to fabricate blend membranes is an efficient strategy for separating light olefins.

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。