Deep learning-based evaluation of factor of safety with confidence interval for tunnel deformation in spatially variable soil

The random finite difference method(RFDM) is a popular approach to quantitatively evaluate the influence of inherent spatial variability of soil on the deformation of embedded tunnels.However,the high computational cost is an ongoing challenge for its application in complex scenarios.To address this limitation,a deep learning-based method for efficient prediction of tunnel deformation in spatially variable soil is proposed.The proposed method uses one-dimensional convolutional neural network(CNN) to identify the pattern between random field input and factor of safety of tunnel deformation output.The mean squared error and correlation coefficient of the CNN model applied to the newly untrained dataset was less than 0.02 and larger than 0.96,respectively.It means that the trained CNN model can replace RFDM analysis for Monte Carlo simulations with a small but sufficient number of random field samples(about 40 samples for each case in this study).It is well known that the machine learning or deep learning model has a common limitation that the confidence of predicted result is unknown and only a deterministic outcome is given.This calls for an approach to gauge the model’s confidence interval.It is achieved by applying dropout to all layers of the original model to retrain the model and using the dropout technique when performing inference.The excellent agreement between the CNN model prediction and the RFDM calculated results demonstrated that the proposed deep learning-based method has potential for tunnel performance analysis in spatially variable soils.

任意边界条件下功能梯度阶梯圆柱壳的振动特性研究

对金属-陶瓷功能梯度材料阶梯圆柱壳在任意边界条件下的振动特性展开了研究.首先,采用Voigt模型和幂函数体积分数得到金属-陶瓷功能梯度材料属性.其次,引入人工弹簧技术,模拟各壳段间的连续耦合及壳体两端的边界条件,并基于一阶剪切变形理论推导出壳体的能量表达式.最后,选取Chebyshev多项式构造容许函数,基于Rayleigh-Ritz法对任意边界条件下壳体的动力学微分方程进行求解计算,通过与现有文献对比,验证了本文方法的有效性与收敛性.结果表明:体积分数指数增长,壳体固有频率也随之增长;而长径比和厚径比对壳体的振动特性影响均不同,随着长径比的增加壳体的固有频率减小,随着厚径比的增加壳体的固有频率增大;且相较于旋转弹簧,平动弹簧的刚度值对壳体振动特性的影响显著.

Editorial for Machine learning and AI for underground metaverse

It is widely recognized that civil engineering practice,including underground construction,is lagging the fast pace digital transformation taking place in many industries.The key reason for this revolution is the emergence and convergence of digital technologies that include machine learning,artificial intelligence(AI),blockchain,cloud/edge computing,Internet of Things,5G communication,automation,digital twin,and metaverse.In parallel,Industry 4.0 is now complemented by Industry 5.0 that advocates a shift from economic value to societal value(sustainability,well-being,etc.).This means a shift from enterprises benefiting shareholders(profits)to stakeholders(people).

O-alg-THAM/gel hydrogels functionalized with engineered microspheres based on mesenchymal stem cell secretion recruit endogenous stem cells for cartilage repair

Lacking self-repair abilities,injuries to articular cartilage can lead to cartilage degeneration and ultimately result in osteoarthritis.Tissue engineering based on functional bioactive scaffolds are emerging as promising approaches for articular cartilage regeneration and repair.Although the use of cell-laden scaffolds prior to implantation can regenerate and repair cartilage lesions to some extent,these approaches are still restricted by limited cell sources,excessive costs,risks of disease transmission and complex manufacturing practices.Acellular approaches through the recruitment of endogenous cells offer great promise for in situ articular cartilage regeneration.In this study,we propose an endogenous stem cell recruitment strategy for cartilage repair.Based on an injectable,adhesive and self-healable o-alg-THAM/gel hydrogel system as scaffolds and a biophysio-enhanced bioactive microspheres engineered based on hBMSCs secretion during chondrogenic differentiation as bioactive supplement,the as proposed functional material effectively and specifically recruit endogenous stem cells for cartilage repair,providing new insights into in situ articular cartilage regeneration.

Monotonic uplift behavior of anchored pier foundations in soil overlying rock

Rock-embedded foundations with good uplift and bearing capacity are often used in mountains or hilly areas.However,there are soil layers with a certain thickness on the rocks in these mountainous areas,and the utilization of those soil layers is a problem worthy of attention in foundation construction.Considering construction-and cost-related factors,traditional single-form foundations built on such sites often cannot provide sufficient resistance against uplift.Therefore,an anchored pier foundation composed of anchors and belled piers,specifically constructed for such conditions,can be invaluable in practice.This paper introduces an experimental and analytical study to investigate the uplift capacity and the uplift mobilization coefficients(UMCs)of the anchored pier foundation.In this study,three in-situ monotonic pullout tests were carried out to analyze the load–displacement characteristics,axial force distribution,load transfer mechanism,and failure mechanism.A hyperbolic model is used to fit the load–displacement curves and to reveal the asynchrony of the ultimate limit states(ULSs)of the anchor group and the belled pier.Based on the results,the uplift capacity can be calculated by the UMCs and the anchor group and pier uplift capacities.Finally,combined with the estimation of the deformation modulus of the soil and rock,the verification calculation of the uplift capacity and UMC was carried out on the test results from different anchored pier foundations.

Dexamethasone implant for refractory macular edema secondary to diabetic retinopathy and retinal vein occlusion

AIM:To evaluate the efficacy,timing of retreatment and safety of dexamethasone(DEX)implant on macular edema(ME)secondary to diabetic retinopathy(DME)and retinal vein occlusion(RVO-ME)patients who were refractory to anti-vascular endothelial growth factor(VEGF)treatment.METHODS:This retrospective study included 37 eyes received at least one DEX implant treatment for DME or RVO-ME between January 1,2019,and January 1,2023.These refractory DME and RVO-ME cases received at least 5 anti-VEGF injections and failure to gain more than 5 letters or a significant reduction in central retinal thickness(CRT).The best corrected visual acuity(BCVA)and CRT were measured at baseline,and at 1,3,4 and 6mo post-DEX implant injection.Adverse events such as elevated intraocular pressure(IOP)and cataract were recorded.RESULTS:For RVO cases(n=22),there was a significant increase in BCVA from 0.27±0.19 to 0.35±0.20 at 6mo post-DEX injection(P<0.05)and CRT decreased from 472.1±90.6 to 240.5±39.0μm at 6mo(P<0.0001).DME cases(n=15)experienced an improvement in BCVA from 0.26±0.15 to 0.43±0.20 at 6mo post-DEX implant injection(P=0.0098),with CRT reducing from 445.7±55.7 to 271.7±34.1μm at 6mo(P<0.0001).Elevated IOP occurred in 45.9% of patients but was well-controlled with topical medications.No cases of cataract or other adverse events were reported.CONCLUSION:DEX implants effectively improve BCVA and reduce CRT in refractory DME and RVO-ME.Further research with larger cohorts and longer follow-up periods is needed to confirm these findings and assess long-term outcomes.

Azacytidine targeting SARS-CoV-2 viral RNA as a potential treatment for COVID-19

The COVID-19 pandemic is a global health crisis.Moreover,emerging mutated virus strains present an even greater challenge for existing vaccines and medications.One possible solution is to design drugs based on the properties of the virus epigenome.