다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Remaining useful life prediction of lithium-ion batteries with adaptive unscented kalman filter and optimized support vector regression

Deep learning for prognostics and health management: State of the art, challenges, and opportunities

Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism

A Generalized Remaining Useful Life Prediction Method for Complex Systems Based on Composite Health Indicator

A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method

The running conditions of wheels of Heavy-duty Railway Train are complex, and the real-time running state data is Multi-Dimension and Time-Sequence. Aiming at the problems that the traditional deep learning models have weak learning ability, cannot extract different scale information and gradient explosion in the prediction of remaining useful life (RUL), this paper proposes a multi-scale deep long short-term memory (MDLSTM) network model, which extracts time-series features of different scales through different number of hidden layer units of LSTM networks. In order to obtain more robust features under the premise of reducing the loss of original information and better to predict RUL of wheels, A Dual Channel Multi-scale Deep convolutional Multi-scale Deep long short-term memory (DC-MDCNN-MDLSTM) is proposed which combined the CNN and LSTM to extract multi-scale feature of wheels under different conditions and extract the different time step features of wheels from time series data. Using the actual wheels data to experiments. The results show that DC-MDCNN-MDLSTM network model is effective in predicting the degradation state of the wheels and provides technical support for repairing on condition of Heavy- duty Railway Train.

Remaining Useful Life Prediction of Wheel of Heavy-duty Railway Train based on Dual Channel Multi-scale Deep convolution Multi-scale Deep Long Short-Term Memory network

The invention belongs to field of electrocardiogram atrial fibrillation prediction, and particularly discloses an atrial fibrillation prediction device and equipment based on deep learning. The devicecomprises an information extraction module, an information processing module and a result prediction module. The information extraction module is used for acquiring multi-lead original electrocardiogram data and obtaining electrocardiogram rhythm information corresponding to leads; the information processing module is used for determining R point positions in the electrocardiogram rhythm information, heartbeat cycles corresponding to the R point positions and waveform information of the heartbeat cycles by adopting a filter so as to construct waveform information sets. Feature extraction anddimensionality reduction are performed on the waveform information set corresponding to each heartbeat period by using a noise reduction autoencoder, multi-dimensional feature data corresponding to the waveform information set are obtained, and mean value and variance of feature data of each dimension are calculated. The result prediction module is used for comparing the mean value and the variance of the multi-dimensional feature data corresponding to different heartbeat periods with the adaptive threshold of the heartbeat period according to the time sequence, and judging whether atrial fibrillation occurs in the heartbeat period or not. The accuracy of atrial fibrillation prediction is improved.

Sen Zhao

Papers

A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method

Remaining Useful Life Prediction of Wheel of Heavy-duty Railway Train based on Dual Channel Multi-scale Deep convolution Multi-scale Deep Long Short-Term Memory network

Atrial fibrillation prediction device and equipment based on deep learning