敦煌莫高窟北区岩体变异变形及修复对策

敦煌莫高窟北区岩体长期以来在特殊的地形地貌、气象水文、岩土性质、地质构造条件下,受人工开挖、重力、风蚀、雨蚀和洪水冲刷等共同作用,岩体发生风化、卸荷等变异以及崩塌、坍塌和危岩、开裂与裂隙(构造裂隙、卸荷裂隙)等多种变形,严重影响岩体的稳定和洞窟的安全。针对上述变异、变形破坏情况,采用PS材料加粉煤灰浆液灌浆封闭裂隙和岩面喷浆加固相结合的修复方法,有效地防止了岩体变异的进一步扩展和表面风化的加剧,减少了岩体变形和表面风化程度,使石窟得以保护和修复。该方法对黄土及干旱地区石窟保护具有良好的借鉴作用。     

Reinforcement learning for optimal error correction of toric codes

We apply deep reinforcement learning techniques to design high threshold decoders for the toric code under uncorrelated noise. By rewarding the agent only if the decoding procedure preserves the logical states of the toric code, and using deep convolutional networks for the training phase of the agent, we observe near-optimal performance for uncorrelated noise around the theoretically optimal threshold of 11%. We observe that, by and large, the agent implements a policy similar to that of minimum weight perfect matchings even though no bias towards any policy is given a priori.     

Balancing module in evolutionary optimization and Deep Reinforcement Learning for multi-path selection in Software Defined Networks

Software Defined Network (SDN) has been used in many organizations due to its efficiency in transmission. Machine learning techniques have been applied in SDN to improve its efficiency in resource scheduling. The existing models in SDN have limitations of overfitting, local optima trap and lower efficiency in path selection. This study applied Balancing Module (BM)-Spider Monkey Optimization (SMO)-Crow Search Algorithm (CSA) for multi path selection in SDN to improve its efficiency. The balancing module applies Gaussian distribution to balance between exploration and exploitation in the multi-path selection process. The Balancing module helps to escape local optima trap and increases the convergence rate. Deep Reinforcement learning is applied for resource scheduling in SDN. The Deep reinforcement learning technique uses the reward function to improve the learning performance, and the BM-SMO-CSA technique has 30 J energy consumption, where the existing models: DRL has 40 J energy consumption, and Graph-ACO has 62 J energy consumption.     

Multi-index evaluation learning-based computation offloading optimization for power internet of things

Cloud–edge-device collaborative computation offloading can provide flexible and real-time data processing services for massive resource-constrained devices in power internet of things (PIoT). However, the computation offloading optimization in PIoT still faces several challenges such as high computation offloading delay caused by uncertain information, coupling between task offloading and computation resource allocation, and degraded optimization performance due to the lack of multi-index consideration. To address the above challenges, we formulate a joint optimization problem of task offloading and computation resource allocation to minimize the average computation offloading delay. Specifically, a multi-index evaluation learning-based two-stage computation offloading (MINCO) algorithm is proposed to decouple the joint optimization problem into two-stage subproblems and solve them with evaluation and learning of multiple indexes including data flow characteristic, service priority, empirical average computation offloading delay, and empirical arm selection times. Simulation results show that compared with the baseline 1 and baseline 2 algorithms, MINCO improves the average computation offloading delay by 14.67% and 30.71%. Moreover, MINCO can evaluate different service priorities and data flow characteristics to meet different requirements of computation offloading delay.     

尼龙短纤维/白炭黑填充天然橡胶的流变与动态力学行为

以尼龙短纤维(NSF)增强天然橡胶(NR)混炼胶为研究体系,以马来酸酐接枝天然橡胶(MNR)为增容剂,考察增容剂、NSF含量对NR/NSF母胶动态流变行为的影响;将NR/NSF母胶加入30份白炭黑(Si O2)填充NR混炼胶中,对比研究NR/NSF、NR/NSF/Si O2混炼胶的线性与非线性流变行为及动态力学行为,采用修正的两相模型分析"粒子相"的增强作用,探讨硫化胶储能模量E'和损耗因子tanδ的变化.结果表明,MNR影响NSF在基体中的分散性和NSF/NR混炼胶的动态流变行为;高填充Si O2和少量NSF之间存在协同增强作用,使NR/NSF/Si O2混炼胶的补强因子和应变放大因子均高于NR/NSF混炼胶,显著增加"粒子相"的黏性与弹性贡献,限制"粒子相"的松弛;硫化胶的E'和tanδ峰值随NSF体积分数增加分别升高和降低.     

土工格栅路堤加筋效果的影响因素分析

土工格栅作为一种新型的土工合成材料,由于具有高强度、低延伸率等特点而被选作主要的路堤加筋材料,在路堤中适当位置加入土工格栅能有效地减少路堤的沉降和侧向变形。本文采用通用非线性有限元程序ABAQUS分析了加筋前后的路堤底部的竖向位移、堤址点垂线下地基深度的水平位移和地表的水平位移,计算中采用D rucker-Prager模型和C lay p las-tic ity模型模拟土体的非线性,土工格栅采用一维杆单元来模拟。通过对加筋层数、筋材模量、软基模量、填土高度和软土层厚度等影响加筋效果的因素进行对比分析,从计算结果分析可知,路堤加筋虽然对软土地基的竖向位移影响不大,但加筋能有效抑制侧向位移的发展,这样增大了路堤边坡的稳定性,分析结果与大多数实际工程的实测资料相吻合。     

对岩体缺陷调查与工程处理方法的研究

在各类岩体内 ,存在着许多影响工程地质与水文地质性质的岩体缺陷 ,对这些缺陷必须进行工程处理方能达到某种要求。目前几乎普遍存在着对处理方向和处理工艺不考虑或很少考虑岩体的工程地质与水文地质条件 ,因而获效不甚理想 ,本文提出了解决这些问题的研究成果     

Reinforcement learning enhanced multi-neighborhood tabu search for the max-mean dispersion problem

This paper presents a highly effective reinforcement learning enhancement of multi-neighborhood tabu search for the max-mean dispersion problem. The reinforcement learning component uses the Q-learning mechanism that incorporates the accumulated feedback information collected from the actions performed during the search to guide the generation of diversified solutions. The tabu search component employs 1-flip and reduced 2-flip neighborhoods to collaboratively perform the neighborhood exploration for attaining high-quality local optima. A learning automata method is integrated in tabu search to adaptively determine the probability of selecting each neighborhood. Computational experiments on 80 challenging benchmark instances demonstrate that the proposed algorithm is favorably competitive with the state-of-the-art algorithms in the literature, by finding new lower bounds for 3 instances and matching the best known results for the other instances. Key elements and properties are also analyzed to disclose the source of the benefits of our integration of learning mechanisms and tabu search.     

Effect of clay modification on the structure and mechanical properties of polyamide-6 nanocomposites

Polyamide-6 nanocomposites were prepared from a new phosphonium organoclay obtained at pilot scale in supercritical carbon dioxide (scCO₂) and a commercially available ammonium modified-silicate. The composites were homogenised by twin-screw extrusion, then specimens for testing were prepared by injection moulding. The clay content of the composites was varied from 0 to 7 vol.% in 7 steps. The clays were characterised in detail; they differed in their surface coverage and gallery structure, while their particle size was similar and their surface energy differed only slightly. X-ray diffraction, electronic microscopy and rheology were used for the characterisation of composite structure. Different gallery structure of the clays led to dissimilar extent of exfoliation. The phosphonium organoclay exfoliated better in PA than the silicate treated with the ammonium salt in spite of its smaller surface coverage. The nanocomposites showed the usual complex structure: besides individual platelets and intercalated stacks, large particles were also present and the development of a silicate network could be shown at large clay contents. Quantitative determination of the extent of reinforcement revealed two determining factors: contact surface and strength of interaction. The first increases with exfoliation, but the latter decreases as an effect of organophilisation. The extent of exfoliation was also estimated quantitatively, and the calculation confirmed the results of qualitative evaluation showing larger extent of exfoliation for the scCO₂-prepared phosphonium clay.