|
Year | Input data and features | DL model | Application | Remarks |
|
2016 | Raw vibration | LSTM [102] | Motor fault detection | The model outperformed the existing models owing to its deep architecture |
|
2017 | Raw vibration from multiple sensors | LFGRU [103] | Motor fault classification | The model was able to effectively classify motor faults owing to deep structure without any extensive feature extraction |
Vibration + time domain features + frequency domain features | RNN [104] | Rolling bearing fault prediction | Model showed better prediction results with frequency domain features |
|
2018 | Raw vibration | LSTM [105] | Motor fault classification | The results confirmed effectiveness of the technique compared to existing methods owing to gated functions of the model |
Vibration + WTD + time domain features | SAE + LSTM [106] | Prediction of bearing performance degradation | Results confirmed effectiveness of the method in achieving the task compared to the conventional methods |
|
2019 | Vibration + hybrid feature + RQA | LSTM [107] | Induction motor fault classification | Method effectively classified the motor faults due to the antinoise feature extraction techniques |
Raw vibration | LSTM [108] | Rolling bearing fault classification | The results demonstrated efficiency in the bearing fault classification owing to inherent mechanism and deep architecture |
Vibration + temperature + WE | LSTM + PSO [109] | Bearing degradation assessment and RUL prediction | Results confirmed effectiveness of the method in estimating the bearing life states and degree of degradation |
Raw vibration | GRU + AFSA + ELM [110] | Adaptive rolling bearing fault classification | Results revealed robust performance of the model owing to optimized parameter selection by AFSA and accurate classification by ELM |
Raw vibration | BiD-LSTM [111] | Bearing fault classification | Results demonstrated effectiveness of the method owing to its long-term dependency in time series data |
Vibration + time, frequency, hybrid features | HRGUN + KPCA + EWMA [112] | Future HI prediction and RUL prediction of the bearing | KPCA and EWMA allowed to effectively track the degradation process and promisingly predicted the HI and RUL of the bearing |
|
2020 | Raw vibration + complex wavelet packet energy moment entropy | Enhanced deep GRU [113] | Early bearing fault classification | The monitoring health index technique and the modified training algorithm allowed to detect fault at an early stage |
|