Fault Diagnosis for a Three Mass Torsion Oscillator Using a Bank of Fault Models

Author(s):  
Joachim Baehr ◽  
Rolf Isermann

A fault diagnosis method for a three mass torsion oscillator is considered which is subject to different additive faults. By using a bank of fault models three faults of different type are detected, isolated and identified in size and time of occurrence. The bank of fault models is formed by a model of each considered fault. Comparison of simulated fault model outputs and measured signals leads to fault isolation. Fault size and time of occurrence are identified by a parity equation approach and used as fault model parameters. The method is capable to perform the tasks with use of one actuator and one sensor signal. It is shown that common approaches for fault isolation can not be used due to the small number of measured signals.

2014 ◽  
Vol 1014 ◽  
pp. 505-509 ◽  
Author(s):  
Ran Tao ◽  
You Cai Xu ◽  
Xin Shi Li ◽  
Shu Guo ◽  
Kun Li ◽  
...  

Empirical mode decomposition (EMD) can extract real time-frequency characteristics from the non-stationary and nonlinear signal. Variable prediction model based class discriminate (VPMCD) is introduced into roller bearing fault diagnosis in this paper. Therefore, a fault diagnosis method based on EMD and VPMCD is put forward in the paper. Firstly, the different feature vectors in the signal are extracted by EMD. Then, different fault models of roller bearing are distinguished by using VPMCD. Finally, an simulation example based on EMD and VPMCD is shown in this paper. The results show that this method can gain very stable classification performance and good computational efficiency.


2006 ◽  
Vol E89-D (11) ◽  
pp. 2756-2765 ◽  
Author(s):  
X. WEN ◽  
S. KAJIHARA ◽  
K. MIYASE ◽  
Y. YAMATO ◽  
K. K. SALUJA ◽  
...  

2008 ◽  
Vol E91-D (3) ◽  
pp. 667-674 ◽  
Author(s):  
Y. YAMATO ◽  
Y. NAKAMURA ◽  
K. MIYASE ◽  
X. WEN ◽  
S. KAJIHARA

2011 ◽  
Vol 71-78 ◽  
pp. 2424-2428
Author(s):  
Han Mei Hu ◽  
Jun Lei Zhao ◽  
Ping Wen Tu

Aiming at the smart grid self-healing characteristics, puts forward a Bayesian network fault diagnosis method. According to the protection movement signal and the circuit breaker tripping signal, establish the face of components of the smart grid line fault diagnosis model. The fault diagnosis method is real-time and accuracy, and fault-tolerant ability etc. characteristics. This method not only satisfy intelligent power grid self-healing characteristics on fault diagnosis real-time, accuracy and automatic fault diagnosis of the requirements, but also provide the smart grid fault isolation and system of self recover with strong guarantee.


2021 ◽  
Vol 11 (24) ◽  
pp. 12117
Author(s):  
Zhinong Li ◽  
Zedong Li ◽  
Yunlong Li ◽  
Junyong Tao ◽  
Qinghua Mao ◽  
...  

In engineering, the fault data unevenly distribute and difficultly share, which causes that the existing fault diagnosis methods cannot recognize the newly added fault types. An intelligent diagnosis method for machine fault is proposed based on federated learning. Firstly, the local fault diagnosis models diagnosing the existing fault data and the newly added fault data are established by deep convolutional neural network. Then, the weight parameters of local models are fused into global model parameters by federated learning. Finally, the global model parameters are transmitted to each local model. Therefore, each local model update into a global shared model which can recognize the newly added fault types. The proposed method is verified by bearing data. Compared with the traditional model, which can only diagnose the existing fault data but cannot recognize newly added fault types, the federated fault diagnosis model fusing weight parameters can diagnose newly added faults without exchanging the data, and the accuracy is 100%. The proposed method provides an effective method to solve the poor sharing of fault data and poor generalization of fault diagnosis model for mechanical equipment.


2011 ◽  
Vol 383-390 ◽  
pp. 5045-5049
Author(s):  
Chun Mei Xu ◽  
Hao Zhang ◽  
Dao Gang Peng

Analyzing grey correlation grade method, a fault diagnosis method of improved grey correlation grade is presented for turbine generator unit. The method calculates weight according to test sample, and then calculates the weighted grey correlation grade. And for the characteristics of turbine generation unit, a fault diagnosis method based on improved grey correlation grade is presented. Simulation results show that the proposed method can successfully diagnose all fault of turbine generation unit, and fault isolation capability is much stronger than traditional grey relation.


2021 ◽  
Vol 11 (2) ◽  
pp. 739
Author(s):  
Jingzhou Fei ◽  
Xinran Lv ◽  
Yunpeng Cao ◽  
Shuying Li

In order to achieve accurate fault diagnosis of rolling bearings, a hierarchical decision fusion diagnosis method for rolling bearings is proposed. The hierarchical back propagation neural networks (BPNNs) architecture includes a fault detection layer, fault isolation layer and fault degree identification layer, which reduce the calculation cost and enhance the maintainability of the fault diagnosis algorithm. By wavelet packet decomposition and signal reconstruction of the raw vibration signal of a rolling bearing, the time-domain features of the reconstructed signals are extracted as the input of each BPNN and the accuracy of fault detection, fault isolation and degree estimation are improved. By using the majority voting method, the diagnosis results of multiple BPNNs are fused, which avoids the missed diagnosis and misdiagnosis caused by the insensitivity of a vibration characteristic to a specific fault. Finally, the proposed method is verified experimentally. The results show that the proposed method can accurately detect the fault of rolling bearings, recognize the fault location and estimate the fault severity under different operating conditions.


Author(s):  
Yunpeng Cao ◽  
Yinghui He ◽  
Fang Yu ◽  
Jianwei Du ◽  
Shuying Li ◽  
...  

This paper presents a two-layer multi-model gas path fault diagnosis method for gas turbines that includes a fault detection layer and a fault isolation layer. A health model and a gas path fault model based on a back propagation neural network are used for the real-time estimation of the output parameters of a gas turbine in the fault detection layer and the output parameter residual in the fault isolation layer, respectively. A fault detection algorithm is proposed based on fuzzy inference, and the fuzzy membership function of the output parameters residual is realized using data statistics. A similarity distance method is used to realize fault isolation, and a fault probability algorithm based on the Mahalanobis distance is presented. Finally, the proposed method is verified by a three-shaft gas turbine simulation platform, and the simulation test results show that the two-layer multi-model gas path fault diagnosis method can detect and isolate the gas path fault accurately with a low calculation cost and good extensibility.


Sign in / Sign up

Export Citation Format

Share Document