Fault diagnosis of rolling bearings with noise signal based on modified kernel principal component analysis and DC‐ResNet

In view of the influence of aliasing noise on the effectiveness and accuracy of bearing fault diagnosis,a bearing fault diagnosis algorithm based on the spatial decoupling method of modified kernel principal component analysis(MKPCA)and the residual network with deformable convolution(DC‐ResNet)is innovatively proposed.Firstly,the Gaussian noise with different signal‐to‐noise ratios(SNRs)is added to the data to simulate the different degrees of noise in the actual data acquisition process.The MKPCA is used to project the fault signal with different SNRs in the kernel space to reduce the data dimension and eliminate some noise effects.Finally,the DC‐ResNet model is used to further filter the noise effects and fully extract the fault features through the training of the preprocessed data.The proposed algorithm is tested on the Case Western Reserve University(CWRU)and Xi'an Jiaotong University and Changxing Sumyoung Technology Co.,Ltd.(XJTU‐SY)bearing data sets with different SNR noise.The fault diagnosis accuracy can reach 100%within 30 min,which has better performance than most of the existing methods.The experimental results show that the algorithm has an excellent effect on accuracy and computation complexity under different noise levels.

Comparison of the effectiveness and pregnancy outcomes of labor induction with dinoprostone or single-balloon catheter in term nulliparous women with borderline oligohydramnios

Backgrounds:At present,there is no consensus on the induction methods in term pregnancy with borderline oligohydramnios.This study aimed to compare the effectiveness and pregnancy outcomes of labor induction with dinoprostone or single-balloon catheter(SBC)in term nulliparous women with borderline oligohydramnios.Methods:We conducted a retrospective cohort study from January 2016 to November 2018.During the study period,a total of 244 cases were enrolled.Of these,103 cases were selected for induction using dinoprostone and 141 cases were selected for induction with SBC.The pregnancy outcomes between the two groups were compared.Primary outcomes were successful vaginal delivery rates.Secondary outcomes were maternal and neonatal adverse events.Multivariate logistic regression was used to assess the risk factors for vaginal delivery failure in the two groups.Results:The successful vaginal delivery rates were similar between the dinoprostone group and the SBC group(64.1%[66/103]vs.59.6%,[84/141]P=0.475),even after adjustment for potential confounding factors(adjusted odds ratio[aOR]:1.07,95%confidence interval[CI]:0.57-2.00,P=0.835).The incidence of intra-amniotic infection was lower in the dinoprostone group than in the SBC group(1.9%[2/103]vs.7.8%[11/141],P<0.001),but the presence of non-reassuring fetal heart rate was higher in the dinoprostone group than in the SBC group(12.6%[13/103]vs.0.7%,[1/141]P<0.001).Multivariate logistic regression showed that nuchal cord was a risk factor for vaginal delivery failure after induction with dinoprostone(aOR:6.71,95%CI:1.96-22.95).There were three factors related to vaginal delivery failure after induction with SBC,namely gestational age(aOR:1.51,95%CI:1.07-2.14),body mass index(BMI)>30 kg/m^(2)(aOR:2.98,95%CI:1.10-8.02),and fetal weight>3500 g(aOR:2.49,95%CI:1.12-5.50).Conclusions:Term nulliparous women with borderline oligohydramnios have similar successful vaginal delivery rates after induction with dinoprostone or SBC,with their advantages and disadvantages.In women with nuchal cord,the risk of vaginal delivery failure is increased if dinoprostone is used in the induction of labor.BMI>30 kg/m^(2),large gestational age,and estimated fetal weight>3500 g are risk factors for vaginal delivery failure after induction with SBC.

Bearing fault diagnosis with cascaded space projection and a CNN

Fault diagnosis is essential for the normal and safe operation of dynamic systems.To improve the spatial resolution among multiple channels and the discriminability among categories of the original data collected from actual operating equipments and to further achieve high diagnostic accuracy,this paper proposes a method for fault diagnosis by cascaded space projection(CSP)and a convolutional neural network(CNN)model.First,one of every kind of sample is selected from the original data to calculate the PCA transformation matrices.Second,the original data are expanded to 10 dimensions by the W2C projection matrix provided by Google-image searching,which is the main part of CSP.Third,the ten-dimensional matrix is multiplied by the PCA transformation matrix,which corresponds to its fault type,to make the data more representative by reducing unnecessary dimensions.Finally,the processed data are converted into images to input into a CNN,the backbone structure for fault diagnosis.To verify the effectiveness and reliability of the proposed method,the Case Western Reserve University(CWRU)and Xi’an Jiaotong University(XJTU-SY)rolling bearing datasets are used to perform experiments.Comparison with other methods is carried out to show the superiority of the proposed method.The experimental results demonstrate that the method proposed in this paper can effectively achieve 100%accuracy.

Prediction of birth weight in pregnancy with gestational diabetes mellitus using an artificial neural network

Gestational diabetes mellitus(GDM)is common during pregnancy,with the prevalence reaching as high as 31.0%in some European regions(McIntyre et al.,2019).Dysfunction of the glucose metabolism in pregnancy can influence fetal growth via alteration of the intrauterine environment,resulting in an increased risk of abnormal ofispring birth weight(McIntyre et al.,2019).Infants with abnormal birth weight will be foced with increased risks of neonatal complications in the perinatal period and chronic non-communicable diseases in childhood and adulthood(Mitanchez et al.,2015;McIntyre et al.,2019).