Feature Selection Using Tree Model and Classification Through Convolutional Neural Network for Structural Damage Detection

Structural damage detection(SDD)remains highly challenging,due to the difficulty in selecting the optimal damage features from a vast amount of information.In this study,a tree model-based method using decision tree and random forest was employed for feature selection of vibration response signals in SDD.Signal datasets were obtained by numerical experiments and vibration experiments,respectively.Dataset features extracted using this method were input into a convolutional neural network to determine the location of structural damage.Results indicated a 5%to 10%improvement in detection accuracy compared to using original datasets without feature selection,demonstrating the feasibility of this method.The proposed method,based on tree model and classification,addresses the issue of extracting effective information from numerous vibration response signals in structural health monitoring.

PxSy nanoparticles encapsulated in graphene as highly reversible cathode for sodium ion batteries

Herein,phosphorus-mediated sulfur nanoparticles encapsulated in reduced graphene oxide nanosheets(P-SrGO-T)were successfully synthesized as the cathode for sodium ion battery by a ball milling and the following thermal treatment.A series of covalent bonds,such as P–S,C–S–C,C–O–P and C–S–P,are formed in this process,which are in favor of fixing the sulfur and suppressing the parasitic shuttle effect of polysulfide.Benefiting from the graphene sheets and these covalent bonds,a high reversible capacity of 637.4 m Ah/g was achieved in P-SrGO-T after 100 cycles at the current density of 0.2 A/g.In addition,P-SrGO-T also delivers a high-rate capacity(330.7 m Ah/g at 5 A/g)attributing to low charge transfer resistance and faster ion diffusion kinetic.This work pushes the progress forward in developing phosphosulfide cathode for sodium ion batteries.

Association between Mental Health Literacy and Workplace Well-Being of Chinese Grassroots Civil Servants:The Chain Mediating Effects of Regulatory Emotional Self-Efficacy and Resilience

This study aimed to investigate the relationship between mental health literacy(MHL)and workplace well-being(WWB)of Chinese grassroots civil servants,with regulatory emotional self-efficacy(RESE)and resilience as mediating variables.A questionnaire survey was conducted among Chinese grassroots civil servants,with a valid sample size of 2673 after excluding missing values and conducting relevant data processing.The PROCESS was used to examine the relationship between MHL,RESE,resilience,and WWB.The study found that MHL among grassroots civil servants was positively and significantly correlated with WWB(r=0.73,p<0.01).RESE partially mediated the relationship between MHL and WWB(β=0.25,95%CI[0.22,0.28]).Resilience partially mediated the relationship between MHL and WWB(β=0.22,95%CI[0.19,0.26]).MHL had a positive effect on WWB through the chain mediating effect of RESE and resilience(β=0.05,95%CI[0.03,0.07]).There is a close relationship between MHL and WWB,where Chinese grassroots civil servants with higher levels of MHL can develop stronger RESE and resilience,leading to higher WWB.The results of this study remind organizational institutions of Chinese grassroots civil servants that enhancing MHL,RESE,and resilience is an important pathway to promoting their WWB.