1
|
Lee D, Choo H, Jeong J. GCN-Based LSTM Autoencoder with Self-Attention for Bearing Fault Diagnosis. SENSORS (BASEL, SWITZERLAND) 2024; 24:4855. [PMID: 39123903 PMCID: PMC11314809 DOI: 10.3390/s24154855] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/04/2024] [Revised: 07/21/2024] [Accepted: 07/24/2024] [Indexed: 08/12/2024]
Abstract
The manufacturing industry has been operating within a constantly evolving technological environment, underscoring the importance of maintaining the efficiency and reliability of manufacturing processes. Motor-related failures, especially bearing defects, are common and serious issues in manufacturing processes. Bearings provide accurate and smooth movements and play essential roles in mechanical equipment with shafts. Given their importance, bearing failure diagnosis has been extensively studied. However, the imbalance in failure data and the complexity of time series data make diagnosis challenging. Conventional AI models (convolutional neural networks (CNNs), long short-term memory (LSTM), support vector machine (SVM), and extreme gradient boosting (XGBoost)) face limitations in diagnosing such failures. To address this problem, this paper proposes a bearing failure diagnosis model using a graph convolution network (GCN)-based LSTM autoencoder with self-attention. The model was trained on data extracted from the Case Western Reserve University (CWRU) dataset and a fault simulator testbed. The proposed model achieved 97.3% accuracy on the CWRU dataset and 99.9% accuracy on the fault simulator dataset.
Collapse
Affiliation(s)
- Daehee Lee
- Department of Electrical and Computer Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea;
| | - Hyunseung Choo
- Department of Electrical and Computer Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea;
| | - Jongpil Jeong
- Department of Smart Factory Convergence, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Gyeonggi-do, Republic of Korea
| |
Collapse
|
2
|
Qian B, Cai Y, Ran Y, Sun W. Nonlinear mechanical response analysis and convolutional neural network enabled diagnosis of single-span rotor bearing system. Sci Rep 2024; 14:10321. [PMID: 38710790 DOI: 10.1038/s41598-024-61180-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/17/2023] [Accepted: 05/02/2024] [Indexed: 05/08/2024] Open
Abstract
The wide application of rotating machinery has boosted the development of electricity and aviation, however, long-term operation can lead to a variety of faults. The use of different measures to deal with corresponding malfunctions is the key to generating benefits, so it is significant to carry out the fault diagnosis of rotating machinery. In this work, a test bench for single-span rotor bearings was established, three faults, including spindle bending, spindle crack without end loading and spindle crack with end loading, are experimental analyzed with basic mechanical response. Moreover, a diagnosis is performed using a convolutional neural network, according to the differences in mechanical responses of the three faults obtained from experiments. For three faults, the change in the properties of spindle itself results in different axis trajectories and spectra. Compared with spindle bending fault, spindle crack fault not only cause 1×, 2×, 3× frequency component excitation, also 4×, 5× frequency component excitation. Additionally, the classification accuracy of the training set and the test set under machine learning for the three types of working conditions is 100%. This indicates that the network can significantly identify signal features so as to make effective fault classification.
Collapse
Affiliation(s)
- Bing Qian
- CHN Energy Dadu River Repair & Installation Co., Ltd., Leshan, 614900, China
| | - Yinhui Cai
- CHN Energy Dadu River Repair & Installation Co., Ltd., Leshan, 614900, China
| | - Yinkang Ran
- CHN Energy Dadu River Repair & Installation Co., Ltd., Leshan, 614900, China
| | - Weipeng Sun
- Institute of Water Resources and Hydroelectric Engineering, Xi'an University of Technology, Xi'an, 710048, China.
| |
Collapse
|
3
|
Wan M, Xiao Y, Zhang J. Research on fault diagnosis of rolling bearing based on improved convolutional neural network with sparrow search algorithm. THE REVIEW OF SCIENTIFIC INSTRUMENTS 2024; 95:045111. [PMID: 38591963 DOI: 10.1063/5.0192639] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/20/2023] [Accepted: 03/21/2024] [Indexed: 04/10/2024]
Abstract
Traditional approaches to the intelligent fault diagnosis of rolling bearings have predominantly relied on manual expertise for feature extraction, a practice that compromises robustness. In addition, the existing convolutional neural network (CNN) is characterized by an overabundance of parameters and a substantial requirement for training samples. To address these limitations, this study introduces a novel fault diagnosis algorithm for rolling bearings, integrating a one-dimensional convolutional neural network (1DCNN) with a support vector machine (SVM) to form an enhanced 1DCNN-SVM model. This model is further refined using the sparrow search algorithm (SSA) for the optimal adjustment of the parameters of 1DCNN-SVM. Specifically, by substituting the CNN's final softmax layer with an SVM, the model becomes better suited for processing limited data volumes. In addition, the incorporation of batch normalization and dropout layers within the CNN framework significantly augments its fault classification accuracy for rolling bearings, concurrently mitigating the risk of overfitting. The SSA is subsequently applied to refine three principal hyper-parameters: batch size, initial learning rate, and the L2 regularization coefficient, thereby overcoming the challenges associated with manually adjusting parameters, such as extended processing times and unpredictable outcomes. Empirical tests on Case Western Reserve University (CWRU) datasets revealed the model's superior performance, with the SSA-optimized 1DCNN-SVM showcasing diagnostic accuracies over 98%, marked improvements over conventional models, and a significant reduction in processing times. This method not only marks a significant advancement in intelligent fault diagnosis for rolling bearings but also demonstrates the potential of integrating machine learning for more precise and efficient diagnostics. The SSA-1DCNN-SVM model, optimized for accuracy and minimal data use, sets a new standard in fault diagnosis, relevant for machinery health monitoring and maintenance strategies across various industries.
Collapse
Affiliation(s)
- Min Wan
- School of Mechatronic Engineering, Southwest Petroleum University, Chengdu 610500, China
| | - Yujie Xiao
- School of Mechatronic Engineering, Southwest Petroleum University, Chengdu 610500, China
| | - Jingran Zhang
- School of Mechatronic Engineering, Southwest Petroleum University, Chengdu 610500, China
| |
Collapse
|
4
|
Manis O, Skoumperdis M, Kioroglou C, Tzilopoulos D, Ouzounis M, Loufakis M, Tsalikidis N, Kolokas N, Georgakis P, Panagoulias I, Tsolkas A, Ioannidis D, Tzovaras D, Stankovski M. Data-Driven AI Models within a User-Defined Optimization Objective Function in Cement Production. SENSORS (BASEL, SWITZERLAND) 2024; 24:1225. [PMID: 38400383 PMCID: PMC10892291 DOI: 10.3390/s24041225] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/15/2023] [Revised: 02/05/2024] [Accepted: 02/09/2024] [Indexed: 02/25/2024]
Abstract
This paper explores the energy-intensive cement industry, focusing on a plant in Greece and its mill and kiln unit. The data utilized include manipulated, non-manipulated, and uncontrolled variables. The non-manipulated variables are computed based on the machine learning (ML) models and selected by the minimum value of the normalized root mean square error (NRMSE) across nine (9) methods. In case the distribution of the data displayed in the user interface changes, the user should trigger the retrain of the AI models to ensure their accuracy and robustness. To form the objective function, the expert user should define the desired weight for each manipulated or non-manipulated variable through the user interface (UI), along with its corresponding constraints or target value. The user selects the variables involved in the objective function based on the optimization strategy, and the evaluation is based on the comparison of the optimized and the active value of the objective function. The differential evolution (DE) method optimizes the objective function that is formed by the linear combination of the selected variables. The results indicate that using DE improves the operation of both the cement mill and kiln, yielding a lower objective function value compared to the current values.
Collapse
Affiliation(s)
- Othonas Manis
- Titan Cement Group, 11143 Athens, Greece; (O.M.); (P.G.); (I.P.); (A.T.)
| | - Michalis Skoumperdis
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Christos Kioroglou
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Dimitrios Tzilopoulos
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Miltos Ouzounis
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Michalis Loufakis
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Nikolaos Tsalikidis
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Nikolaos Kolokas
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | | | - Ilias Panagoulias
- Titan Cement Group, 11143 Athens, Greece; (O.M.); (P.G.); (I.P.); (A.T.)
| | - Alexandros Tsolkas
- Titan Cement Group, 11143 Athens, Greece; (O.M.); (P.G.); (I.P.); (A.T.)
| | - Dimosthenis Ioannidis
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Dimitrios Tzovaras
- Centre of Research & Technology—Hellas (CERTH), Information Technologies Institute, 57001 Thessaloniki, Greece; (C.K.); (D.T.); (M.L.); (N.T.); (N.K.)
| | - Mile Stankovski
- Faculty of Electrical Engineering and Information Technologies, Cyril and Methodius University, 1000 Skopje, North Macedonia;
| |
Collapse
|
5
|
Gao Y, Ahmad Z, Kim JM. Fault Diagnosis of Rotating Machinery Using an Optimal Blind Deconvolution Method and Hybrid Invertible Neural Network. SENSORS (BASEL, SWITZERLAND) 2024; 24:256. [PMID: 38203118 PMCID: PMC10781317 DOI: 10.3390/s24010256] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/10/2023] [Revised: 12/29/2023] [Accepted: 12/29/2023] [Indexed: 01/12/2024]
Abstract
This paper proposes a novel approach to predicting the useful life of rotating machinery and making fault diagnoses using an optimal blind deconvolution and hybrid invertible neural network. First, a new optimal adaptive maximum second-order cyclostationarity blind deconvolution (OACYCBD) is developed for denoising vibration signals obtained from rotating machinery. This technique is obtained from the optimization of traditional adaptive maximum second-order cyclostationarity blind deconvolution (ACYCBD). To optimize the weights of conventional ACYCBD, the proposed method utilizes a probability density function (PDF) of Monte Carlo to assess fault-related incipient changes in the vibration signal. Cross-entropy is used as a convergence criterion for denoising. Because the denoised signal carries information related to the health of the rotating machinery, a novel health index is calculated in the second step using the peak value and square of the arithmetic mean of the signal. The novel health index can change according to the degradation of the health state of the rotating bearing. To predict the remaining useful life of the bearing in the final step, the health index is used as input for a newly developed hybrid invertible neural network (HINN), which combines an invertible neural network and long short-term memory (LSTM) to forecast trends in bearing degradation. The proposed approach outperforms SVM, CNN, and LSTM methods in predicting the remaining useful life of bearings, showcasing RMSE values of 0.799, 0.593, 0.53, and 0.485, respectively, when applied to a real-world industrial bearing dataset.
Collapse
Affiliation(s)
- Yangde Gao
- Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea; (Y.G.); (Z.A.)
| | - Zahoor Ahmad
- Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea; (Y.G.); (Z.A.)
| | - Jong-Myon Kim
- Department of Electrical, Electronic and Computer Engineering, University of Ulsan, Ulsan 44610, Republic of Korea; (Y.G.); (Z.A.)
- Prognosis and Diagnostics Technologies Co., Ltd., Ulsan 44610, Republic of Korea
| |
Collapse
|