基于复杂结构信息的图神经网络序列推荐算法

图结构因其在序列推荐场景中的自然适应性而备受关注,而现有的基于图神经网络的会话序列推荐算法虽然能够利用图结构信息达到较好的推荐效果,但是没有考虑用户在会话序列中的重复点击行为和项目之间的复杂转换,且未很好地利用图中复杂的结构信息,导致推荐的效果受到一定程度的限制。提出有向与无向信息同注意力相融合的图神经网络序列推荐算法,并基于推荐算法给出项目隐含向量建模算法,结合会话序列图中的有向结构信息与无向结构信息,通过考虑用户的重复点击行为和引入注意力机制建立会话中点击项目的复杂转换模型。图节点在特征传播的过程中平衡邻居节点信息与自身信息的比例,以更准确地预测推荐过程中生成的会话向量。在Diginetica、Yoochoose 1/64、Yoochoose 1/4 3个数据集上的实验结果表明,与SR-GNN、TAGNN算法相比,该算法精度最高提升4.34%,能够更好地预测用户在会话中的下一次点击精度。     

结合特征扰动与分配策略的集成辅助多目标优化算法

代理模型利用近似预测代替算法对多目标优化问题的真实评价,大幅减少了算法寻优所需的真实适应度评估次数。为提高代理模型在求解高维问题时的准确性并降低计算开销,提出一种基于特征扰动与分配策略的集成辅助多目标优化算法。将径向基函数网络代理模型与支持向量机回归代理模型作为集成过程中的基模型,降低算法在高维问题上的计算开销。结合特征扰动与基于记忆的影响因子分配策略构建集成代理模型,提高集成准确性。使用集成预测值与不确定信息加权辅助管理集成代理模型,平衡全局搜索与局部探索,增强算法在目标空间中的寻优能力。实验结果表明,该算法在ZDT1~ZDT3和ZDT6测试问题上所得解集的分布性与收敛性相比经典算法更好,并且当决策变量维数增加时,使用集成代理模型相比于Kriging代理模型约减少了90%的适应度评估次数,同时可获得更准确的预测结果。     

小断面岩石巷道掏槽爆破参数优化实验

针对小断面岩石巷道掏槽爆破效率低下的技术难题,依据掏槽爆破形成槽腔为后续炮孔提供自由面。通过分析施工过程中掏槽爆破存在的问题及其影响因素,采取了控制单一变量的方法,制定9组实验方案,同时配合规范的施工方法对掏槽爆破参数进行优化,从而获得最优的掏槽爆破参数组合。通过对实验数据的比较分析,优化的掏槽爆破参数使巷道掘进的炮孔利用率提高了20%,掘进综合成本节省了27%。     

Prototyping and modeling of the centrifugal casting process for paraffin waxes

Centrifugal casting is a technology used for manufacturing hybrid rocket paraffin grains. This technology helps avoiding voids formation inside the solid paraffin as it cools. Voids are formed because of air bubbles being entrapped while pouring and because the liquid wax shrinks by 17–19% upon cooling. In this work, the centrifugal casting process for the manufacturing of paraffin cylinders was prototyped at two different scales considering critical casting issues. The effects of process parameters (rotational speed, melt temperature, and flow rate) on the tensile properties of the manufactured grains were analyzed. The results of the optimization conducted at the lower scale (2.5?kg) were up scaled to manufacture 25?kg grains. The resulting mechanical properties complied with the design specifications, and they were better than those characterized from the gravity cast wax. A numerical model of growth and dissolution of bubbles during the process was then developed to predict the quality of the castings. The numerical results showed how increasing the mold rotational speed up to 1800?rpm reduced the removal time. However, compared to grains solidification time, the predicted removal times were much shorter, proving the advantage of centrifugal casting in counteracting voids formation.     

Investigation of machining characteristics in rotary ultrasonic machining of alumina ceramic

Alumina ceramic is well documented as a much-demanded advanced ceramic in the present competitive structure of manufacturing and industrial applications owing to its excellent and superior properties. The current article aimed to experimentally investigate the influence of several process variables, namely: spindle speed, feed rate, coolant pressure, and ultrasonic power, on considered machining characteristics of interest, i.e., chipping size and material removal rate in the rotary ultrasonic machining of alumina ceramic. Response surface methodology has been employed in the form of a central composite rotatable design to design the experiments. Variance analysis testing has also been performed with a view to observing the consequence of the considered parameters. The microstructure of machined rod samples was evaluated and analyzed using a scanning electron microscope. This analysis has revealed and confirmed the presence of plastic deformation that caused removal of material along with brittle fractures in rotary ultrasonic machining of alumina ceramic. The validity and competence of the developed mathematical model have been verified with test results. The multi-response optimization of machining responses (material removal rate and chipping size) has also been attempted by employing a desirability approach, and at an optimized parametric setting the obtained experimental values for material removal rate and chipping size were 0.4166?mm³/s and 0.5134?mm, respectively, with a combined desirability index value of 0.849.     

A data-driven surrogate-assisted evolutionary algorithm applied to a many-objective blast furnace optimization problem

A new data-driven reference vector-guided evolutionary algorithm has been successfully implemented to construct surrogate models for various objectives pertinent to an industrial blast furnace. A total of eight objectives have been modeled using the operational data of the furnace using 12 process variables identified through a principal component analysis and optimized simultaneously. The capability of this algorithm to handle a large number of objectives, which has been lacking earlier, results in a more efficient setting of the operational parameters of the furnace, leading to a precisely optimized hot metal production process.     

Optimization of annealing cycle parameters of dual phase and interstitial free steels by multiobjective genetic algorithms

Data-driven models have been constructed for Dual Phase (DP) and Interstitials Free (IF) steels using an evolutionary approach. DP steel data are utilized from an existing database, while for the IF steels, data generated at an integrated steel plant have been used. The objective function for Ultimate Tensile Strength (UTS) and % elongation, created as data-driven models, is simultaneously optimized for an optimum strength-ductility balance and the results indicate the possibilities of developing steels with better mechanical properties than what are known to have been existing so far.     

Multilevel assessment method for reliable design of composite structures

This work aims at demonstrating the interest of a new methodology for the design and optimization of composite materials and structures. Coupling reliability methods and homogenization techniques allow the consideration of probabilistic design variables at different scales. The main advantage of such an original micromechanics-based approach is to extend the scope of solutions for engineering composite materials to reach or to respect a given reliability level. This approach is illustrated on a civil engineering case including reinforced fiber composites. Modifications of microstructural components properties, manufacturing process, and geometry are investigated to provide new alternatives for design and guidelines for quality control.     

Plasmon‐Enhanced Spectroscopies with Shell‐Isolated Nanoparticles

Shell‐isolated nanoparticle‐enhanced Raman spectroscopy (SHINERS), due to its versatility, has been able to break the long‐term limitations of the material‐ and substrate‐specific generalities in the traditional field of surface‐enhanced Raman spectroscopy. With a shell‐isolated work principle, this method provides an opportunity to investigate successfully in surface, biological systems, energetic materials, and environmental sciences. Both the shell material and core morphology are being improved continuously to meet the requirements in diverse systems, such as the electrochemical studies at single crystal electrode surfaces, in situ monitoring of photoinduced reaction processes, practical applications in energy conversion and storage, inspections in food safety, and the surface‐enhanced fluorescence. Predictably, the concept of shell‐isolated nanoparticle‐enhancement could be expanded to the wider range for the performance of plasmon‐enhanced spectral modifications.     

Immobilization of Pt Nanoparticles via Rapid and Reusable Electropolymerization of Dopamine on TiO2 Nanotube Arrays for Reversible SERS Substrates and Nonenzymatic Glucose Sensors

Inspired by mussel‐adhesion phenomena in nature, polydopamine (PDA) coatings are a promising route to multifunctional platforms for decorating various materials. The typical self‐polymerization process of dopamine is time‐consuming and the coatings of PDA are not reusable. Herein, a reusable and time‐saving strategy for the electrochemical polymerization of dopamine (EPD) is reported. The PDA layer is deposited on vertically aligned TiO₂ nanotube arrays (NTAs). Owing to the abundant catechol and amine groups in the PDA layer, uniform Pt nanoparticles (NPs) are deposited onto the TiO₂ NTAs and can effectively prevent the recombination of electron–hole pairs generated from photo‐electrocatalysis and transfer the captured electrons to participate in the photo‐electrocatalytic reaction process. Compared with pristine TiO₂ NTAs, the as‐prepared Pt@TiO₂ NTA composites exhibit surface‐enhanced Raman scattering sensitivity for detecting rhodamine 6G and display excellent UV‐assisted self‐cleaning ability, and also show promise as a nonenzymatic glucose biosensor. Furthermore, the mussel‐inspired electropolymerization strategy and the fast EPD‐reduced nanoparticle decorating process presented herein can be readily extended to various functional substrates, such as conductive glass, metallic oxides, and semiconductors. It is the adaptation of the established PDA system for a selective, robust, and generalizable sensing system that is the emphasis of this work.