Influence of aging treatment on mechanical properties and wear resistance of medium manganese steel reinforced with Ti(C,N) particles

In this study,the hot rolled medium manganese steel containing titanium was solution treated at 1,000°C and followed by aging treatment at 500,550,and 600°C.The influence of aging treatment on mechanical properties and wear resistance of medium manganese steel reinforced with Ti(C,N)particles was investigated.It was found that the matrix of medium manganese steel was austenite.The austenite grain size was refined,and Ti(C,N)particles were precipitated after aging treatment.Compared to that of the as-hot rolled sample,the initial hardness of 500°C aged sample increased by 9.5%to 312.86 HV,whose impact energy was more than doubled to 148.5 J.As the aging temperature raised to 600°C,the initial hardness changed slightly.However,the impact energy dropped significantly to 8 J due to the aggregation of Mn at the grain boundaries.In addition,the main wear mechanisms of the samples were fatigue wear and abrasive wear.It was worth noting that 500°C aged sample exhibited the best wear resistance under a 300 N applied load,whose wear loss was just half of the as-hot rolled sample.The relationship between wear loss and mechanical properties indicated that the wear resistance of medium manganese steel was independent of the initial hardness.The large difference in the wear resistance was predominately due to the outstanding work hardening ability of 500°C aged sample,whose strengthening mechanisms were contributed from transformation induced plasticity(TRIP)effect,dislocation strengthening,twinning induced plasticity(TWIP)effect,and precipitation strengthening.

Detection method of absence seizures based on Resnet and bidirectional GRU

Background Epilepsy is a common chronic neurological disease.Its repeated seizure attacks have a great negative impact on patients’physical and mental health.The diagnosis of epilepsy mainly depends on electroencephalogram(EEG)signals detection and analysis.There are two main EEG signals detection methods for epilepsy.One is the detection based on abnormal waveform,the other is the analysis of EEG signals based on the traditional machine learning.The feature extraction method of the traditional machine learning is difcult to capture the high-dimension information between adjacent sequences.Methods In this paper,redundant information was removed from the data by Gaussian fltering,downsampling,and short-time Fourier transform.Convolutional Neural Networks(CNN)was used to extract the high-dimensional features of the preprocessed data,and then Gate Recurrent Unit(GRU)was used to combine the sequence information before and after,to fully integrate the adjacent information EEG signals and improve the accuracy of the model detection.Results Four models were designed and compared.The experimental results showed that the prediction model based on deep residual network and bidirectional GRU had the best efect,and the test accuracy of the absence epilepsy test set reached 92%.Conclusions The prediction time of the network is only 10 sec when predicting four-hour EEG signals.It can be efectively used in EEG software to provide reference for doctors in EEG analysis and save doctors’time,which has great practical value.