Smart and fast reinforcement design for anti-dip bedding rock slopes

Rock slopes are usually reinforced by a number of rock bolts due to the high efficiency and low price.However,where should the rock bolts be installed is still a troublesome issue.For anti-dip bedding rock slopes(ABRSs),the installation position of rock bolts is a controlling factor that determines the reinforcement effect.In this work,a theoretical method is firstly proposed for assessing the stability of ABRSs reinforced by rock bolts using a limit equilibrium model.A comparison of theoretical calculations and numerical results was conducted to test the correctness of the theoretical method.Based on the stability assessment of ABRSs,we introduce adaptive moment estimation method(Adam)to optimize the installation location of rock bolts.Using Adam optimizer,the optimal layout of rock bolts with the maximum factor of safety can be determined,and the factor of safety of the slope increases by about 25%using the same amount of rock bolts but with different installation locations.The proposed method enables the fast stability analysis and supporting design for reinforced ABRSs,which paves the way to smart supporting design of slopes.

A disk failure prediction model for multiple issues

Disk failure prediction methods have been useful in handing a single issue,e.g.,heterogeneous disks,model aging,and minority samples.However,because these issues often exist simultaneously,prediction models that can handle only one will result in prediction bias in reality.Existing disk failure prediction methods simply fuse various models,lacking discussion of training data preparation and learning patterns when facing multiple issues,although the solutions to different issues often conflict with each other.As a result,we first explore the training data preparation for multiple issues via a data partitioning pattern,i.e.,our proposed multi-property data partitioning(MDP).Then,we consider learning with the partitioned data for multiple issues as learning multiple tasks,and introduce the model-agnostic meta-learning(MAML)framework to achieve the learning.Based on these improvements,we propose a novel disk failure prediction model named MDP-MAML.MDP addresses the challenges of uneven partitioning and difficulty in partitioning by time,and MAML addresses the challenge of learning with multiple domains and minor samples for multiple issues.In addition,MDP-MAML can assimilate emerging issues for learning and prediction.On the datasets reported by two real-world data centers,compared to state-of-the-art methods,MDP-MAML can improve the area under the curve(AUC)and false detection rate(FDR)from 0.85 to0.89 and from 0.85 to 0.91,respectively,while reducing false alarm rate(FAR)from 4.88%to 2.85%.