Prioritizing Maintenance Spare Parts Based on Supportability Analysis and Neural Network

In order to facilitate spare parts management,an integrated approach of BP neural network and supportability analysis(SA)was proposed to evaluate the criticality of spare parts as well as to prioritize spare parts.Influential factors of prioritizing spare parts were detailedly analyzed.Framework of the integrated method was established.The modelling process based on BP neural network was presented.As the input of the neural network,the values of influential factors were determined by supportability analysis data.Based on the presented method,spare parts could be automatically prioritized after supportability analysis for a new system.A case study results showed that the new method was applicable and effective.

Nanoparticle Exsolution on Perovskite Oxides:Insights into Mechanism,Characteristics and Novel Strategies

Supported nanoparticles have attracted considerable attention as a promising catalyst for achieving unique properties in numerous applications,including fuel cells,chemical conversion,and batteries.Nanocatalysts demonstrate high activity by expanding the number of active sites,but they also intensify deactivation issues,such as agglomeration and poisoning,simultaneously.Exsolution for bottomup synthesis of supported nanoparticles has emerged as a breakthrough technique to overcome limitations associated with conventional nanomaterials.Nanoparticles are uniformly exsolved from perovskite oxide supports and socketed into the oxide support by a one-step reduction process.Their uniformity and stability,resulting from the socketed structure,play a crucial role in the development of novel nanocatalysts.Recently,tremendous research efforts have been dedicated to further controlling exsolution particles.To effectively address exsolution at a more precise level,understanding the underlying mechanism is essential.This review presents a comprehensive overview of the exsolution mechanism,with a focus on its driving force,processes,properties,and synergetic strategies,as well as new pathways for optimizing nanocatalysts in diverse applications.

Is GDNF to Parkinson’s disease what BDNF is to Huntington’s disease?

Neurotrophic factors,or neurotrophins,are a group of molecules supporting the growth,survival,and differentiation of developing and mature neurons.Given their role in the survival of neurons,and often of specific subsets of brain cells,neurotrophins have been implicated in several ways with many neurodegenerative disorders.

Aqueous-phase reforming of hydroxyacetone solution to bio-based H_(2)over supported Pt catalysts

Aqueous-phase reforming(APR)is an attractive process to produce bio-based hydrogen from waste biomass streams,during which the catalyst stability is often challenged due to the harsh reaction conditions.In this work,three Pt-based catalysts supported on C,AlO(OH),and ZrO_(2)were investigated for the APR of hydroxyacetone solution in afixed bed reactor at 225℃and 35 bar.Among them,the Pt/C catalyst showed the highest turnover frequency for H_(2)production(TOF of 8.9 molH_(2)molPt^(-1)min^(-1))and the longest catalyst stability.Over the AlO(OH)and ZrO_(2)supported Pt catalysts,the side reactions consuming H_(2),formation of coke,and Pt sintering result in a low H_(2)production and the fast catalyst deactivation.The proposed reaction pathways suggest that a promising APR catalyst should reform all oxygenates in the aqueous phase,minimize the hydrogenation of the oxygenates,maximize the WGS reaction,and inhibit the condensation and coking reactions for maximizing the hydrogen yield and a stable catalytic performance.

Dynamics of a rotating ring-stiffened sandwich conical shell with an auxetic honeycomb core

The free vibration analysis of a rotating sandwich conical shell with a reentrant auxetic honeycomb core and homogenous isotropic face layers reinforced with a ring support is studied.The shell is modeled utilizing the first-order shear deformation theory(FSDT)incorporating the relative,centripetal,and Coriolis accelerations alongside the initial hoop tension created by the rotation.The governing equations,compatibility conditions,and boundary conditions are attained using Hamilton’s principle.Utilizing trigonometric functions,an analytical solution is derived in the circumferential direction,and a numerical one is presented in the meridional direction via the differential quadrature method(DQM).The effects of various factors on the critical rotational speeds and forward and backward frequencies of the shell are studied.The present work is the first theoretical work regarding the dynamic analysis of a rotating sandwich conical shell with an auxetic honeycomb core strengthened with a ring support.

Enhanced stability of nitrogen-doped carbon-supported palladium catalyst for oxidative carbonylation of phenol

Enhancing the stability of supported noble metal catalysts emerges is a major challenge in both science and industry.Herein,a heterogeneous Pd catalyst(Pd/NCF)was prepared by supporting Pd ultrafine metal nanoparticles(NPs)on nitrogen-doped carbon;synthesized by using F127 as a stabilizer,as well as chitosan as a carbon and nitrogen source.The Pd/NCF catalyst was efficient and recyclable for oxidative carbonylation of phenol to diphenyl carbonate,exhibiting higher stability than Pd/NC prepared without F127 addition.The hydrogen bond between chitosan(CTS)and F127 was enhanced by F127,which anchored the N in the free amino group,increasing the N content of the carbon material and ensuring that the support could provide sufficient N sites for the deposition of Pd NPs.This process helped to improve metal dispersion.The increased metal-support interaction,which limits the leaching and coarsening of Pd NPs,improves the stability of the Pd/NCF catalyst.Furthermore,density functional theory calculations indicated that pyridine N stabilized the Pd^(2+)species,significantly inhibiting the loss of Pd^(2+)in Pd/NCF during the reaction process.This work provides a promising avenue towards enhancing the stability of nitrogen-doped carbon-supported metal catalysts.

Research on the flow stability and noise reduction characteristics of quasi-periodic elastic support skin

To enhance flow stability and reduce hydrodynamic noise caused by fluctuating pressure,a quasiperiodic elastic support skin composed of flexible walls and elastic support elements is proposed for fluid noise reduction.The arrangement of the elastic support element is determined by the equivalent periodic distance and quasi-periodic coefficient.In this paper,a dynamic model of skin in a fluid environment is established.The influence of equivalent periodic distance and quasi-periodic coefficient on flow stability is investigated.The results suggest that arranging the elastic support elements in accordance with the quasi-periodic law can effectively enhance flow stability.Meanwhile,the hydrodynamic noise calculation results demonstrate that the skin exhibits excellent noise reduction performance,with reductions of 10 dB in the streamwise direction,11 dB in the spanwise direction,and 10 dB in the normal direction.The results also demonstrate that the stability analysis method can serve as a diagnostic tool for flow fields and guide the design of noise reduction structures.

Coalbursts in China: Theory, practice and management

Coalburst is one of the most serious disasters that threaten the safe production of coal mines, and this disaster is particularly serious in China. This paper presents an overview of coalbursts in China since 1980s. From the "stress and energy" and "regional and local" perspectives, the achievements in the theory, practice and management of coalbursts in China are systematically summarized. A theoretical system of coalbursts has been formed to reveal the deformational behavior of coalbursts and explain the mechanism of coalbursts. The occurrence conditions of coalbursts are put forward and the critical stress is obtained. The stress index method for risk evaluation of coalbursts before mining is proposed, and the deformation localization prediction method of coalbursts is put forward. The relationship between energy release and absorption in the process of coalbursts is found, and the prevention and control methods of coalbursts, including the regional method, the local method and support, are presented. The safety evaluation index of coalburst prevention and control is put forward. The integrated prevention and control method for coal and gas outbursts is proposed. The prevention and control technology and equipment of coalbursts have also been developed. Amongst them, the distribution law of the critical stress in China coalburst mines is discovered. The technology and equipment for monitoring, prevention and control of coalbursts, as well as for integrated prevention and control of combined coalbursts and other disasters, have been developed. The energy-absorbing and coalburst-preventing support technology for roadways is invented, and key engineering parameters of coalburst prevention and control are pointed out. In China, coalburst prevention and control laws and standards have been developed. Technical standards for coalbursts are formulated, statute and regulations for coal mines are established, and regulatory documents are promoted.

A Support Data-Based Core-Set Selection Method for Signal Recognition

In recent years,deep learning-based signal recognition technology has gained attention and emerged as an important approach for safeguarding the electromagnetic environment.However,training deep learning-based classifiers on large signal datasets with redundant samples requires significant memory and high costs.This paper proposes a support databased core-set selection method(SD)for signal recognition,aiming to screen a representative subset that approximates the large signal dataset.Specifically,this subset can be identified by employing the labeled information during the early stages of model training,as some training samples are labeled as supporting data frequently.This support data is crucial for model training and can be found using a border sample selector.Simulation results demonstrate that the SD method minimizes the impact on model recognition performance while reducing the dataset size,and outperforms five other state-of-the-art core-set selection methods when the fraction of training sample kept is less than or equal to 0.3 on the RML2016.04C dataset or 0.5 on the RML22 dataset.The SD method is particularly helpful for signal recognition tasks with limited memory and computing resources.

Mechanism of high-preload support based on the NPR anchor cable in layered soft rock tunnels

The control of large deformation problems in layered soft rock tunnels needs to solve urgently.The roof problem is particularly severe among the deformation issues in tunnels.This study first analyzes the asymmetric deformation modes in layered soft rock tunnels with large deformations.Subsequently,we construct a mechanical model under ideal conditions for controlling the roof of layered soft rock tunnels through high preload with the support of NPR anchor cables.The prominent roles of long and short NPR anchor cables in the support system are also analyzed.The results indicate the significance of high preload in controlling the roof of layered soft rock tunnels.The short NPR anchor cables effectively improve the integrity of the stratified soft rock layers,while the long NPR anchor cables effectively mobilize the self-bearing capacity of deep-stable rock layers.Finally,the high-preload support method with NPR anchor cables is validated to have a good effect on controlling large deformations in layered soft rock tunnels through field monitoring data.

Development of multi-functional anchorage support dynamic-static coupling performance test system and its application

In underground engineering with complex conditions,the bolt(cable)anchorage support system is in an environment where static and dynamic stresses coexist,under the action of geological conditions such as high stresses and strong disturbances and construction conditions such as the application of high prestress.It is essential to study the support components performance under dynamic-static coupling conditions.Based on this,a multi-functional anchorage support dynamic-static coupling performance test system(MAC system)is developed,which can achieve 7 types of testing functions,including single component performance,anchored net performance,anchored rock performance and so on.The bolt and cable mechanical tests are conducted by MAC system under different prestress levels.The results showed that compared to the non-prestress condition,the impact resistance performance of prestressed bolts(cables)is significantly reduced.In the prestress range of 50–160 k N,the maximum reduction rate of impact energy resisted by different types of bolts is 53.9%–61.5%compared to non-prestress condition.In the prestress range of 150–300 k N,the impact energy resisted by high-strength cable is reduced by76.8%–84.6%compared to non-prestress condition.The MAC system achieves dynamic-static coupling performance test,which provide an effective means for the design of anchorage support system.

Improved Twin Support Vector Machine Algorithm and Applications in Classification Problems

The distribution of data has a significant impact on the results of classification.When the distribution of one class is insignificant compared to the distribution of another class,data imbalance occurs.This will result in rising outlier values and noise.Therefore,the speed and performance of classification could be greatly affected.Given the above problems,this paper starts with the motivation and mathematical representing of classification,puts forward a new classification method based on the relationship between different classification formulations.Combined with the vector characteristics of the actual problem and the choice of matrix characteristics,we firstly analyze the orderly regression to introduce slack variables to solve the constraint problem of the lone point.Then we introduce the fuzzy factors to solve the problem of the gap between the isolated points on the basis of the support vector machine.We introduce the cost control to solve the problem of sample skew.Finally,based on the bi-boundary support vector machine,a twostep weight setting twin classifier is constructed.This can help to identify multitasks with feature-selected patterns without the need for additional optimizers,which solves the problem of large-scale classification that can’t deal effectively with the very low category distribution gap.

Comparison of debris flow susceptibility assessment methods:support vector machine,particle swarm optimization,and feature selection techniques

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility results.In this study,metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province,China,by using machine learning algorithms.In total,133 historical debris flow records and 16 related factors were selected.The support vector machine(SVM)was first used as the base classifier,and then a hybrid model was introduced by a two-step process.First,the particle swarm optimization(PSO)algorithm was employed to select the SVM model hyperparameters.Second,two feature selection algorithms,namely principal component analysis(PCA)and PSO,were integrated into the PSO-based SVM model,which generated the PCA-PSO-SVM and FS-PSO-SVM models,respectively.Three statistical metrics(accuracy,recall,and specificity)and the area under the receiver operating characteristic curve(AUC)were employed to evaluate and validate the performance of the models.The results indicated that the feature selection-based models exhibited the best performance,followed by the PSO-based SVM and SVM models.Moreover,the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model,showing the highest AUC,accuracy,recall,and specificity values in both the training and testing processes.It was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment results.Moreover,the PSO algorithm was found to be not only an effective tool for hyperparameter optimization,but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning algorithms.The high and very high debris flow susceptibility zone appropriately covers 38.01%of the study area,where debris flow may occur under intensive human activities and heavy rainfall events.

Meter-Scale Thin-Walled Structure with Lattice Infill for Fuel Tank Supporting Component of Satellite:Multiscale Design and Experimental Verification

Lightweight thin-walled structures with lattice infill are widely desired in satellite for their high stiffness-to-weight ratio and superior buckling strength resulting fromthe sandwich effect.Such structures can be fabricated bymetallic additive manufacturing technique,such as selective laser melting(SLM).However,the maximum dimensions of actual structures are usually in a sub-meter scale,which results in restrictions on their appliance in aerospace and other fields.In this work,a meter-scale thin-walled structure with lattice infill is designed for the fuel tank supporting component of the satellite by integrating a self-supporting lattice into the thickness optimization of the thin-wall.The designed structure is fabricated by SLM of AlSi10Mg and cold metal transfer welding technique.Quasi-static mechanical tests and vibration tests are both conducted to verify the mechanical strength of the designed large-scale lattice thin-walled structure.The experimental results indicate that themeter-scale thin-walled structure with lattice infill could meet the dimension and lightweight requirements of most spacecrafts.

Hypoxia in the pulmonary vein increases pulmonary vascular resistance independently of oxygen in the pulmonary artery

Introduction:Hypoxic pulmonary vasoconstriction(HPV)can be a challenging clinical problem.It is not fully elucidated where in the circulation the regulation of resistance takes place.It is often referred to as if it is in the arteries,but we hypothesized that it is in the venous side of the pulmonary circulation.Methods:In an open thorax model,pigs were treated with a veno-venous extra corporeal membrane oxygenator to either oxygenate or deoxygenate blood passing through the pulmonary vessels.At the same time the lungs were ventilated with extreme variations of inspired air from 5%to 100%oxygen,making it possible to make combinations of high and low oxygen content through the pulmonary circulation.A flow probe was inserted around the main pulmonary artery and catheters in the pulmonary artery and in the left atrium were used for pressure monitoring and blood tests.Under different combinations of oxygenation,pulmonary vascular resistance(PVR)was calculated.Results:With unchanged level of oxygen in the pulmonary artery and reduced inspired oxygen fraction lowering oxygen tension from 29 to 6.7 kPa in the pulmonary vein,PVR was doubled.With more extreme hypoxia PVR suddenly decreased.Combinations with low oxygenation in the pulmonary artery did not systematic influence PVR if there was enough oxygen in the inspired air and in the pulmonary veins.Discussion:The impact of hypoxia occurs from the alveolar level and forward with the blood flow.The experiments indicated that the regulation of PVR is mediated from the venous side.

A Dual-Task Learning Approach for Bearing Anomaly Detection and State Evaluation of Safe Region

Predictive maintenance has emerged as an effective tool for curbing maintenance costs,yet prevailing research predominantly concentrates on the abnormal phases.Within the ostensibly stable healthy phase,the reliance on anomaly detection to preempt equipment malfunctions faces the challenge of sudden anomaly discernment.To address this challenge,this paper proposes a dual-task learning approach for bearing anomaly detection and state evaluation of safe regions.The proposed method transforms the execution of the two tasks into an optimization issue of the hypersphere center.By leveraging the monotonicity and distinguishability pertinent to the tasks as the foundation for optimization,it reconstructs the SVDD model to ensure equilibrium in the model’s performance across the two tasks.Subsequent experiments verify the proposed method’s effectiveness,which is interpreted from the perspectives of parameter adjustment and enveloping trade-offs.In the meantime,experimental results also show two deficiencies in anomaly detection accuracy and state evaluation metrics.Their theoretical analysis inspires us to focus on feature extraction and data collection to achieve improvements.The proposed method lays the foundation for realizing predictive maintenance in a healthy stage by improving condition awareness in safe regions.

Dynamic Hand Gesture-Based Person Identification Using Leap Motion and Machine Learning Approaches

Person identification is one of the most vital tasks for network security. People are more concerned about theirsecurity due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, fingerprintsand faces have been widely used for person identification, which has the risk of information leakage as a resultof reproducing fingers or faces by taking a snapshot. Recently, people have focused on creating an identifiablepattern, which will not be reproducible falsely by capturing psychological and behavioral information of a personusing vision and sensor-based techniques. In existing studies, most of the researchers used very complex patternsin this direction, which need special training and attention to remember the patterns and failed to capturethe psychological and behavioral information of a person properly. To overcome these problems, this researchdevised a novel dynamic hand gesture-based person identification system using a Leap Motion sensor. Thisstudy developed two hand gesture-based pattern datasets for performing the experiments, which contained morethan 500 samples, collected from 25 subjects. Various static and dynamic features were extracted from the handgeometry. Randomforest was used to measure feature importance using the Gini Index. Finally, the support vectormachinewas implemented for person identification and evaluate its performance using identification accuracy. Theexperimental results showed that the proposed system produced an identification accuracy of 99.8% for arbitraryhand gesture-based patterns and 99.6% for the same dynamic hand gesture-based patterns. This result indicatedthat the proposed system can be used for person identification in the field of security.

Differentially Private Support Vector Machines with Knowledge Aggregation

With the widespread data collection and processing,privacy-preserving machine learning has become increasingly important in addressing privacy risks related to individuals.Support vector machine(SVM)is one of the most elementary learning models of machine learning.Privacy issues surrounding SVM classifier training have attracted increasing attention.In this paper,we investigate Differential Privacy-compliant Federated Machine Learning with Dimensionality Reduction,called FedDPDR-DPML,which greatly improves data utility while providing strong privacy guarantees.Considering in distributed learning scenarios,multiple participants usually hold unbalanced or small amounts of data.Therefore,FedDPDR-DPML enables multiple participants to collaboratively learn a global model based on weighted model averaging and knowledge aggregation and then the server distributes the global model to each participant to improve local data utility.Aiming at high-dimensional data,we adopt differential privacy in both the principal component analysis(PCA)-based dimensionality reduction phase and SVM classifiers training phase,which improves model accuracy while achieving strict differential privacy protection.Besides,we train Differential privacy(DP)-compliant SVM classifiers by adding noise to the objective function itself,thus leading to better data utility.Extensive experiments on three high-dimensional datasets demonstrate that FedDPDR-DPML can achieve high accuracy while ensuring strong privacy protection.

Machine learning-assisted efficient design of Cu-based shape memory alloy with specific phase transition temperature

The martensitic transformation temperature is the basis for the application of shape memory alloys(SMAs),and the ability to quickly and accurately predict the transformation temperature of SMAs has very important practical significance.In this work,machine learning(ML)methods were utilized to accelerate the search for shape memory alloys with targeted properties(phase transition temperature).A group of component data was selected to design shape memory alloys using reverse design method from numerous unexplored data.Component modeling and feature modeling were used to predict the phase transition temperature of the shape memory alloys.The experimental results of the shape memory alloys were obtained to verify the effectiveness of the support vector regression(SVR)model.The results show that the machine learning model can obtain target materials more efficiently and pertinently,and realize the accurate and rapid design of shape memory alloys with specific target phase transition temperature.On this basis,the relationship between phase transition temperature and material descriptors is analyzed,and it is proved that the key factors affecting the phase transition temperature of shape memory alloys are based on the strength of the bond energy between atoms.This work provides new ideas for the controllable design and performance optimization of Cu-based shape memory alloys.

Enhanced Steganalysis for Color Images Using Curvelet Features and Support Vector Machine

Algorithms for steganography are methods of hiding data transfers in media files.Several machine learning architectures have been presented recently to improve stego image identification performance by using spatial information,and these methods have made it feasible to handle a wide range of problems associated with image analysis.Images with little information or low payload are used by information embedding methods,but the goal of all contemporary research is to employ high-payload images for classification.To address the need for both low-and high-payload images,this work provides a machine-learning approach to steganography image classification that uses Curvelet transformation to efficiently extract characteristics from both type of images.Support Vector Machine(SVM),a commonplace classification technique,has been employed to determine whether the image is a stego or cover.The Wavelet Obtained Weights(WOW),Spatial Universal Wavelet Relative Distortion(S-UNIWARD),Highly Undetectable Steganography(HUGO),and Minimizing the Power of Optimal Detector(MiPOD)steganography techniques are used in a variety of experimental scenarios to evaluate the performance of the proposedmethod.Using WOW at several payloads,the proposed approach proves its classification accuracy of 98.60%.It exhibits its superiority over SOTA methods.