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 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.

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。

Solid-phase microextraction of endogenous metabolites from intact tissue validated using a Biocrates standard reference method kit

Improved analytical methods for the metabolomic profiling of tissue samples are constantly needed.Currently,conventional sample preparation methods often involve tissue biopsy and/or homogenization,which disrupts the endogenous metabolome.In this study,solid-phase microextraction(SPME)fibers were used to monitor changes in endogenous compounds in homogenized and intact ovine lung tissue.Following SPME,a Biocrates AbsoluteIDQ assay was applied to make a downstream targeted metabolomics analysis and confirm the advantages of in vivo SPME metabolomics.The AbsoluteIDQ kit enabled the targeted analysis of over 100 metabolites via solid-liquid extraction and SPME.Statistical analysis revealed significant differences between conventional liquid extractions from homogenized tissue and SPME results for both homogenized and intact tissue samples.In addition,principal component analysis revealed separated clustering among all the three sample groups,indicating changes in the metabolome due to tissue homogenization and the chosen sample preparation method.Furthermore,clear differences in free metabolites were observed when extractions were performed on the intact and homogenized tissue using identical SPME procedures.Specifically,a direct comparison showed that 47 statistically distinct metabolites were detected between the homogenized and intact lung tissue samples(P<0.05)using mixed-mode SPME fibers.These changes were probably due to the disruptive homogenization of the tissue.This study's findings highlight both the importance of sample preparation in tissue-based metabolomics studies and SPME's unique ability to perform minimally invasive extractions without tissue biopsy or homogenization while providing broad metabolite coverage.

Scalable solid-phase synthesis of defect-rich graphene for oxygen reduction electrocatalysis

Defect-engineered carbon materials have been emerged as promising electrocatalysts for oxygen reduction reaction(ORR)in metal-air batteries.Developing a facile strategy for the preparation of highly active nanocarbon electrocatalysts remains challenging.Herein,a low-cost and simple route is developed to synthesize defective graphene by pyrolyzing the mixture of glucose and carbon nitride.Molecular dynamics simulations reveal that the graphene formation is ascribed to two-dimensional layered feature of carbon nitride,and high compatibility of carbon nitride/glucose systems.Structural measurements suggest that the graphene possesses rich edge and topological defects.The graphene catalyst exhibits higher power density than commercial Pt/C catalyst in a primary Zn-air battery.Combining experimental results and theoretical thermodynamic analysis,it is identified that graphitic nitrogen-modified topological defects at carbon framework edges are responsible for the decent ORR performance.The strategy presented in this work can be can be scaled up readily to fabricate defective carbon materials.

Carbon Doping Triggered Efficient Electrochemical Hydrogen Evolution of Cross-Linked Porous Ru-MoO_(2) Via Solid-Phase Reaction Strategy

The defect-free structure of Mo-based materials is a“double-edged sword”,which endows the material with excellent stability,but limits its chemical versatility and application in electrochemical hydrogen evolution reaction(HER).Carbon doping engineering is an attractive strategy to effectively improve the performance of Mo-based catalyst and maintain their stability.Herein,we report a cross-linked porous carbon-doped MoO_(2)(C–MoO_(2))-based catalyst Ru/C–MoO_(2) for electrochemical HER,which is prepared by the convenient redox solid-phase reaction(SPR)of porous RuO_(2)/Mo_(2)C composite precursor.Theoretical studies reveal that due to the presence of carbon atoms,the electronic structure of C–MoO_(2) has been properly adjusted,and the loaded small Ru nanoparticles provide a fast water dissociation rate and moderate H adsorption strength.In electrochemical studies under a pH-universal environment,Ru/C–MoO_(2) electrocatalyst exhibits a low overpotential at a current density of 10 mA cm^(-2) and has a low Tafel slope.Meanwhile,Ru/C-MoO_(2) has excellent stability for more than 100 h at an initial current density of 100 mA cm^(-2).

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.

Comparison of different approaches for direct coupling of solid-phase microextraction to mass spectrometry for drugs of abuse analysis in plasma

The direct coupling of solid-phase microextraction(SPME)to mass spectrometry(MS)(SPME-MS)has proven to be an effective method for the fast screening and quantitative analysis of compounds in complex matrices such as blood and plasma.In recent years,our lab has developed three novel SPME-MS techniques:SPME-microfluidic open interface-MS(SPME-MOI-MS),coated blade spray-MS(CBS-MS),and SPME-probe electrospray ionization-MS(SPME-PESI-MS).The fast and high-throughput nature of these SPME-MS technologies makes them attractive options for point-of-care analysis and anti-doping testing.However,all these three techniques utilize different SPME geometries and were tested with different MS instruments.Lack of comparative data makes it difficult to determine which of these methodologies is the best option for any given application.This work fills this gap by making a comprehensive comparison of these three technologies with different SPME devices including SPME fibers,CBS blades,and SPME-PESI probes and SPME-liquid chromatography-MS(SPME-LC-MS)for the analysis of drugs of abuse using the same MS instrument.Furthermore,for the first time,we developed different desorption chambers for MOI-MS for coupling with SPME fibers,CBS blades,and SPME-PESI probes,thus illustrating the universality of this approach.In total,eight analytical methods were developed,with the experimental data showing that all the SPME-based methods provided good analytical performance with R^(2)of linearities larger than 0.9925,accuracies between 81%and 118%,and good precision with an RSD%≤13%.

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.

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.