A Hybrid 1D-CNN-Bi-LSTM based Model with Spatial Dropout for Multiple Fault Diagnosis of Roller Bearing

Abstract

Fault diagnosis of roller bearings is a crucial and challenging task to ensure the smooth functioning of modern industrial machinery under varying load conditions. Traditional fault diagnosis methods involve preprocessing of the vibration signals and manual feature extraction. This requires domain expertise and experience in extracting relevant features to accurately detect the fault. Hence, it is of great significance to implement an intelligent fault diagnosis method that involves appropriate automatic feature learning and fault identification. Recent research has shown that deep learning is an effective technique for fault diagnosis. In this paper, a hybrid model based on 1D-CNN (One-Dimensional Convolution Neural Networks) with Bi-LSTM (Bi-directional Long-Short Term Memory) is proposed to classify 12 different fault types. Firstly, vibration signals are given as input to 1D-CNN to extract intrinsic features from the input signals. Then, the extracted features are fed into a Bi-LSTM model to identify the faults. The performance of the proposed method is enhanced by applying Softsign activation function in the Bi-LSTM layer and Spatial Dropout in the neural network. To analyze the effectiveness of the proposed method, Case Western Reserve University (CWRU) bearing data is considered for experimentation. The results demonstrated that the proposed model has attained an accuracy of 99.84% in classifying the various faults. The superiority of the proposed method is verified by comparing the predictive accuracy of the proposed method with the existing fault diagnosis methods.

Persian Typographical Error Type Detection Using Deep Neural Networks on Algorithmically-Generated Misspellings

“…Besides, Lilak [9] is another commonly used spell-checker among Persian writers which proofreads text after installing an extension in Mozilla Firefox or Google Chrome. Furthermore, we also compared our approach with two highly-developed applications called Virastman and Paknevis [10]. One dilemma when drawing comparisons is the non-identical set of error classes that these applications identify, including ours.…”

“…generalization performance of CNNs(Park et al 2017;Lee et al 2020). Spatial dropout can also be applied to LSTM based neural networks(Choudakkanavar and Mangai 2022). In our architecture, to address the risk of over tting, Spatial Dropout layers are included in the architecture before bidirectional LSTM.…”

Fault diagnosis of rotating machinery using novel self-attention mechanism TCN with soft thresholding method

“…Recognizing the complementary advantages of CNN and LSTM, researchers have gradually realized their combined potential in various applications such as the nuclear power plant fault diagnosis model by Ren et al, achieving an impressive problem recognition rate of 99.6% [22]. In 2022, Choudakkanavar and Mangai proposed a hybrid model combining 1D-CNN and Bi-LSTM for rolling bearing fault diagnosis with successful outcomes [23].…”

Ethereum Cryptocurrency Entry Point and Trend Prediction using Bitcoin Correlation and Multiple Data Combination

“…In addition to that, CNN can also provide satisfactory performance with 1-dimentional data [4], [5], [6], [7], [8]. When working with time series data, Long Short-Term Memory (LSTM) algorithm can also learn easily temporal patterns and dependencies using memory cells and gates [9], [10], [11], [12], [13]. To find the most effective architecture, two different 1-Dimensional Convolutional Neural Network training strategies are evaluated and tested : training from scratch strategy and transfer learning strategy.…”