A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems

Huang, Ting; Zhang, Qiang; Tang, Xiaoan; Zhao, Shuangyao; Lu, Xin

doi:10.1007/s10462-021-09993-z

Cited by 135 publications

(40 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data collected by industrial processes are usually dynamic; that is, faults occurring at the current moment may depend on changes in system state at the previous moment. 28 It is difficult to describe the change characteristics of industrial processes accurately by establishing a single global diagnostic model. In this paper, an extended sliding window mechanism is introduced to transform raw data into augmented dynamic data.…”

Section: Proposed Methodsmentioning

confidence: 99%

“…Yuan et al 27 used a chemical process monitoring and fault diagnosis scheme based on multiscale CNN-LSTM, with the purpose of mining high-dimensional fault features in a multiscale and hierarchical manner. Huang et al 28 transformed the process data into two-dimensional data and input it into CNN-LSTM to extract the spatial and delay characteristics of the data. This method improved the diagnostic accuracy and noise sensitivity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fault Diagnosis of the Dynamic Chemical Process Based on the Optimized CNN-LSTM Network

et al. 2022

View full text Add to dashboard Cite

Deep learning provides new ideas for chemical process fault diagnosis, reducing potential risks and ensuring safe process operation in recent years. To address the problem that existing methods have difficulty extracting the dynamic fault features of a chemical process, a fusion model (CS-IMLSTM) based on a convolutional neural network (CNN), squeeze-and-excitation (SE) attention mechanism, and improved long short-term memory network (IMLSTM) is developed for chemical process fault diagnosis in this paper. First, an extended sliding window is utilized to transform data into augmented dynamic data to enhance the dynamic features. Second, the SE is utilized to optimize the key fault features of augmented dynamic data extracted by CNN. Then, IMLSTM is used to balance fault information and further mine the dynamic features of time series data. Finally, the feasibility of the proposed method is verified in the Tennessee-Eastman process (TEP). The average accuracies of this method in two subdata sets of TEP are 98.29% and 97.74%, respectively. Compared with the traditional CNN-LSTM model, the proposed method improves the average accuracies by 5.18% and 2.10%, respectively. Experimental results confirm that the method developed in this paper is suitable for chemical process fault diagnosis.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis of the Dynamic Chemical Process Based on the Optimized CNN-LSTM Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…WRCTD algorithm utilized the regional association of the wavelet decomposition coefficients and 3σ criterion to reduce noise in the raw sensor data and CNN-LSTM model reduced the hidden features of the pre-processed signal data to identify the fault type of the harmonic reducer under multiple working conditions. A novel fault diagnosis method was presented through application of sliding window processing to integrate the feature and time delay information from multivariate time series samples and then, the samples obtained were fed into the CNN-LSTM model to perform feature learning and capture time delay information to diagnose the fault of Tennessee Eastman chemical process [23]. A robust approach was proposed in [24] to predict the Remaining Useful Life (RUL) of roller bearing with combination of Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and LSTM to detect the damage state and identify the abnormal state of bearing to estimate the RUL through feature extraction from signals.…”

Section: Related Workmentioning

confidence: 99%

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

Choudakkanavar¹,

Mangai²

2022

IJACSA

View full text Add to dashboard Cite

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.

show abstract

“…Current data-driven monitoring techniques often rely on the sensor and signal analysis in the form of multivariate statistical approaches such as principal component analysis (PCA) or partial least-squares (PLS). − With the development of deep learning, big data can be used with models that can adapt to several processes and inputs and perform both fault detection and diagnosis. Deep learning algorithms such as the convolutional autoencoder or long short-term memory (LSTM) network have been explored for fault detection and diagnosis of chemical processes. − The potential of deep learning algorithms as compared to linear multivariate statistics-based methods is particularly significant for bioprocesses given their highly nonlinear behavior. − …”

Section: Introductionmentioning

confidence: 99%

Design and Optimization of a Penicillin Fed-Batch Reactor Based on a Deep Learning Fault Detection and Diagnostic Model

Hematillake

Freethy

McGivern

et al. 2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The application of a supervised deep convolutional autoencoder was tested against partial least-squares-discriminant analysis (PLS-DA) for fault detection and diagnosis in a penicillin fed-batch process. In silico data was generated with a comprehensive simulator (IndPenSim) of an industrial-scale penicillin fed-batch simulator of operation under normal batch conditions and 8 fault batch conditions. A composite face-centered design response surface was applied to optimize key bioreactor design parameters based on a profit function that was directly dependent on fault detection results. The application of PLS-DA and the NN modeling resulted in an average fault detection rate (FDR) across all faults and process parameter configurations of 72.5% and 95.9%, respectively. In classifying complex fault conditions, the deep learning model greatly surpassed the PLS-DA model, and this improvement translated into a 25.0% increase in realized profit with the supervised deep convolutional autoencoder when compared to PLS-DA monitoring.

show abstract

A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems

Cited by 135 publications

References 48 publications

Fault Diagnosis of the Dynamic Chemical Process Based on the Optimized CNN-LSTM Network

Fault Diagnosis of the Dynamic Chemical Process Based on the Optimized CNN-LSTM Network

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

Design and Optimization of a Penicillin Fed-Batch Reactor Based on a Deep Learning Fault Detection and Diagnostic Model

Contact Info

Product

Resources

About