A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals

Wang, Huaqing; Shi, Li; Song, Liuyang; Cui, Lingli

doi:10.1016/j.compind.2018.12.013

Cited by 280 publications

(129 citation statements)

References 34 publications

Supporting

Mentioning

115

Contrasting

Unclassified

Order By: Relevance

“…The higher the odor concentration value of individual was, the higher the probability of mutation was. Whenever a random number is generated between [0,1], the location of the mutant fruit fly is updated according to formula (9), where λ = 10, the location of the fruit fly before the mutation is X j , Y j , and the location of the individual after the mutation is X j , Y j , j = 1, 2 . .…”

Section: Immune Fruit Fly Optimization Algorithmmentioning

confidence: 99%

“…So, composite fault extraction of the gearbox is critical [4][5][6]. At present, the methods used in gearbox fault extraction include Wavelet transform (WT), Empirical mode decomposition (EMD), Local mean decomposition (LMD), and Ensemble empirical mode decomposition (EEMD), these methods successfully extract the fault information, but they will show their own weaknesses when extracting composite faults [7][8][9][10]. When using WT to decompose signals, we need to give a basis function and the number of decomposing layers ahead of time, that is, WT is not adaptive [11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Research on Fault Extraction Method of Variational Mode Decomposition Based on Immunized Fruit Fly Optimization Algorithm

Zhou

Guo

Wang

et al. 2019

Entropy

View full text Add to dashboard Cite

In recent years, a new method of fault diagnosis, named variational mode decomposition (VMD), has been widely used in industrial production, but the decomposition accuracy of VMD is determined by two parameters, which are respectively the decomposition layer number k and the penalty factor α, if the parameters are not properly selected, there will be over-decomposition or under-decomposition. In order to find an approach to determine the parameters adaptively, a method to optimize VMD by using the immune fruit fly optimization algorithm (IFOA) is proposed in this paper. In this method, permutation entropy is used as the fitness function, firstly, the immune fruit fly optimization algorithm is used to search the combined parameters of k and α in VMD, searching for the best combination parameters of k and α by iteration, and then uses the combined parameters to perform VMD, finally, the center frequency is determined through frequency spectrum analysis. The method mentioned is applied to the fault extraction of a simulated signal and a measured signal of a wind turbine gearbox, and the fault frequency is successfully extracted. Using ensemble empirical mode decomposition (EEMD) and singular spectrum decomposition (SSD) to compare with the proposed method, which validated feasibility of the proposed method.

show abstract

Section: Immune Fruit Fly Optimization Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Research on Fault Extraction Method of Variational Mode Decomposition Based on Immunized Fruit Fly Optimization Algorithm

Zhou

Guo

Wang

et al. 2019

Entropy

View full text Add to dashboard Cite

show abstract

“…Operational monitoring data obtained from mechanical equipment generally includes vibration signals, pressure, sound, and temperature. Among these parameters, the vibration signal contains a significant amount of useful information related to mechanical equipment [1,2] which can accurately reflect the operating state. At the same time, with the rapid development of communication technology and the improvement of computing capacity in recent years, the cost of vibration sensing data acquisition from mechanical equipment has been significantly reduced.…”

Section: Introductionmentioning

confidence: 99%

Research on Mechanical Fault Prediction Method Based on Multifeature Fusion of Vibration Sensing Data

Huang

Liu

2019

Sensors

View full text Add to dashboard Cite

Vibration sensing data is an important resource for mechanical fault prediction, which is widely used in the industrial sector. Artificial neural networks (ANNs) are important tools for classifying vibration sensing data. However, their basic structures and hyperparameters must be manually adjusted, which results in the prediction accuracy easily falling into the local optimum. For data with high levels of uncertainty, it is difficult for an ANN to obtain correct prediction results. Therefore, we propose a multifeature fusion model based on Dempster-Shafer evidence theory combined with a particle swarm optimization algorithm and artificial neural network (PSO-ANN). The model first used the particle swarm optimization algorithm to optimize the structure and hyperparameters of the ANN, thereby improving its prediction accuracy. Then, the prediction error data of the multifeature fusion using a PSO-ANN is repredicted using multiple PSO-ANNs with different single feature training to obtain new prediction results. Finally, the Dempster-Shafer evidence theory was applied to the decision-level fusion of the new prediction results preprocessed with prediction accuracy and belief entropy, thus improving the model's ability to process uncertain data. The experimental results indicated that compared to the K-nearest neighbor method, support vector machine, and long short-term memory neural networks, the proposed model can effectively improve the accuracy of fault prediction.

show abstract

“…Gearbox is one of the most important components in mechanical industry and daily life. With constant development of modern industrial technology, fault monitoring of gearbox is more and more valued in research field [1][2][3][4][5][6][7][8][9][10]. As the key component of gearbox, the study of gear fault diagnosis method [11][12][13][14] is of great significance.…”

Section: Introductionmentioning

confidence: 99%

Improvement on Meshing Stiffness Algorithms of Gear with Peeling

et al. 2019

Self Cite

View full text Add to dashboard Cite

This paper investigates the effect of a gear tooth peeling on meshing stiffness of involute gears. The tooth of the gear wheel is symmetric about the axis, and its symmetry will change after the gear spalling, and its meshing stiffness will also change during the meshing process. On this basis, an analytical model was developed, and based on the energy method a meshing stiffness algorithm for the complete meshing process of single gear teeth with peeling gears was proposed. According to the influence of the change of meshing point relative to the peeling position on the meshing stiffness, this algorithm calculates its stiffness separately. The influence of the peeling sizes on mesh stiffness is studied by simulation analysis. As a very important parameter, the study of gear mesh stiffness is of great significance to the monitoring of working conditions and the prevention of sudden failure of the gear box system.

show abstract

A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals

Cited by 280 publications

References 34 publications

Research on Fault Extraction Method of Variational Mode Decomposition Based on Immunized Fruit Fly Optimization Algorithm

Research on Fault Extraction Method of Variational Mode Decomposition Based on Immunized Fruit Fly Optimization Algorithm

Research on Mechanical Fault Prediction Method Based on Multifeature Fusion of Vibration Sensing Data

Improvement on Meshing Stiffness Algorithms of Gear with Peeling

Contact Info

Product

Resources

About