Fault diagnosis system for GIS using an artificial neural network

Ogi, H.; Tanaka, Hideaki; Akimoto, Y.; Izui, Yoshio

doi:10.1109/ann.1991.213507

Cited by 6 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compared the proposed CTFNNC model with several machine learning or deep learning models to evaluate its diagnostic performance. Chang (34) proposed an FNN-based diagnostic technique, Ogi et al (35) proposed an ANN for gas insulated switchgear (GIS) diagnostic system application, Li et al (36) improved LeNet-5 for rolling bearing fault diagnosis, and Lin et al (37) proposed a convolutional fuzzy neural network (CFNN) for use in intelligent traffic-monitoring systems. To clearly present the differences in the classification performance of various models, we used a confusion matrix (38) to evaluate the performance of the proposed classification model for bearing fault diagnosis compared with those in Refs.…”

Section: Bearing Fault Diagnosis and Evaluation Experimentsmentioning

confidence: 99%

“…Because the orthogonal outer race faults were located at the 3 o'clock and 12 o'clock positions, they are denoted as @3 and @12, respectively. Table 7 indicates that the CFNN, LeNet-5, and CTFNNC (34) 58.53 63.66 60.15 66064 ANN (35) 59.06 65.72 62.94 68208 CFNN (37) 88.26 98.29 94.96 7574 LeNet-5 (36) 95 (34) 100.00 57.34 60.56 93.66 100.00 ANN (35) 100.00 37.06 50.00 61.27 58.87 CFNN (37) 100.00 100.00 97.89 100.00 100.00 LeNet-5 (36) 100.00 99.30 92.25 100.00 99.29 CTFNNC 100.00 100.00 100.00 100.00 100.00…”

Section: Bearing Fault Diagnosis and Evaluation Experimentsmentioning

confidence: 99%

“…Classification accuracy for ball faults. Classifier DEB_007 (%) DEB_014 (%) DEB_021 (%) DEB_028 (%) FNN (34) 85.21 20.28 69.23 100.00 ANN (35) 61.27 50.00 57.34 39.72 CFNN (37) 94.37 96.50 88.81 100.00 LeNet-5 (36) 93 Classification accuracy for outer race faults. Classifier DEOR@6_007 (%) DEOR@6_014 (%) DEOR@6_021 (%) FNN (34) 85.21 20.28 69.23 ANN (35) 61.27 50.00 57.34 CFNN (37) 94.37 96.50 88.81 LeNet-5 (36) 93.66 95.80 90.91 CTFNNC 93.66 95.80 93.01…”

Section: Tablementioning

confidence: 99%

“…Classification accuracy for orthogonal outer race faults. Classifier DEOR@3_007 (%) DEOR@3_014 (%) DEOR@12_007 (%) DEOR@12_021 (%) FNN (34) 0.00 32.87 78.32 16.20 ANN (35) 71.13 55.24 60.14 42.25 CFNN (37) 100.00 100.00 99.3 97.18 LeNet-5 (36) 100.00 98.60 97.2 96.48 CTFNNC 100.00 100.00 98.6 97.89 models accurately diagnosed these fault types. However, the ANN and FNN achieved diagnostic accuracies of only about 60 and 80% for DEOR@12_007, respectively, which were much lower than the results for the other types of orthogonal outer race faults.…”

Section: Tablementioning

confidence: 99%

See 3 more Smart Citations

Convolutional Takagi–Sugeno–Kang-type Fuzzy Neural Network for Bearing Fault Diagnosis

Jhang¹,

Lin²,

Kuo³

2023

Sensors and Materials

View full text Add to dashboard Cite

Rotating machines are widely used in modern industry. In a mechanical system, rolling bearings are essential. Bearings must be able to operate in extreme environments, in which they are prone to various faults. To address the challenge related to accurately classify bearing fault types using vibration sensors, we propose a convolutional Takagi-Sugeno-Kang (TSK)-type fuzzy neural network classifier (CTFNNC) that comprises a convolutional layer and a TSK-type fuzzy neural network. In the CTFNNC, convolutional layers are used to extract the features of a vibration signal, and a TSK-type fuzzy neural network is used to classify bearing faults under various categories. In our experiment, the proposed CTFNNC was compared with other methods, such as a fuzzy neural network, an artificial neural network, and the LeNet-5 convolutional neural network. The experimental results indicate that the proposed CTFNNC has a bearing fault classification accuracy of 98.3% and requires half the number of parameters as LeNet-5.

show abstract