CNN-BiLSTM deep learning method for vibration response prediction of the hydropower house
Open Access
- 19 April 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 249-253
Abstract
In response to the problem of insufficient model training and low prediction accuracy caused by insufficient load data samples in the target domain, this paper proposes a method for predicting the vibration response of hydropower houses by integrating the CNN-BiLSTM deep learning model. The CNN is utilized to extract the spatiotemporal features of high-frequency transient vibrations, which are then fed as input to the BiLSTM structure for further learning. Subsequently, the proposed model is employed to predict the vibration acceleration of the dam foundation and corridor in the hydropower station. The research findings demonstrate that the proposed CNN-BiLSTM model significantly enhances the accuracy of vibration prediction when compared to LSTM, BiLSTM, and CNN-LSTM data prediction algorithms.Keywords
Funding Information
- Natural Science Foundation of Jiangsu Province (BK20230956)
- Jiangsu Funding Program for Excellent Postdoctoral Talents (2022ZB188)
- Transportation Technology Plan Project of Jiangsu Province (2020QD28)
This publication has 15 references indexed in Scilit:
- Performance evaluation of LSTM and Bi-LSTM using non-convolutional features for blockage detection in centrifugal pumpEngineering Applications of Artificial Intelligence, 2023
- Prediction of significant wave height in hurricane area of the Atlantic Ocean using the Bi-LSTM with attention modelOcean Engineering, 2022
- A CNN-Bi_LSTM parallel network approach for train travel time predictionKnowledge-Based Systems, 2022
- Intelligent fault diagnosis of train axle box bearing based on parameter optimization VMD and improved DBNEngineering Applications of Artificial Intelligence, 2022
- CNN-LSTM architecture for predictive indoor temperature modelingBuilding and Environment, 2021
- Multi-resolution modulation-filtered cochleagram feature for LSTM-based dimensional emotion recognition from speechNeural Networks, 2021
- Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanismMeasurement, 2021
- The effect of image recognition traffic prediction method under deep learning and naive Bayes algorithm on freeway traffic safetyImage and Vision Computing, 2020
- Speech emotion recognition using deep 1D & 2D CNN LSTM networksBiomedical Signal Processing and Control, 2019
- Maxout neurons for deep convolutional and LSTM neural networks in speech recognitionSpeech Communication, 2016