A Deep Learning Based Fault Diagnosis Method With Hyperparameter Optimization by Using Parallel Computing

Guo, Chaozhong; Li, Lin; Hu, Yuanyuan; Yan, Jihong

doi:10.1109/access.2020.3009644

Cited by 27 publications

(17 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data used in this paper for experimental validation were provided by the Case Western Reserve University (CWRU), Cleveland, Ohio, USA [23]. As shown in Fig.…”

Section: Vibration Test Datamentioning

confidence: 99%

Vibration performance prediction and reliability analysis for rolling bearing

Meng¹,

Gong²,

Du³

et al. 2021

J. vibroeng.

View full text Add to dashboard Cite

The bearing vibration signal is a rich dynamic symptom of bearing wear, and the vibration signal of rolling bearing presents chaotic characteristics. Input and output variables of vibration signal can be constructed through phase space reconstruction, the Input and output variables can be imported into the prediction model for prediction. The prediction accuracy of the extreme learning machine (ELM) model, Kriging model and RBF model are compared, the results show that ELM has higher accuracy, so ELM chaos model is used to predict the future vibration time series data, and the forecasting error can be obtained by comparing the prediction value with the actual values so as to verity the feasibility of the ELM model. The prediction results of the future state of the bearing are processed as the grey-bootstrap method, and the performance reliability prediction of the bearing is realized by the Poisson counting process. The experimental data show that with the deepening of the fault degree, the reliability performance decreases gradually. The reliability performance of the bearing without fault is 100 %, and the reliability performance is 47.56 % when the inner ring faulty size is 0.72 mm.

show abstract

“…The data used in this paper for experimental validation were provided by the Case Western Reserve University (CWRU), Cleveland, Ohio, USA [23]. As shown in Fig.…”

Section: Vibration Test Datamentioning

confidence: 99%

Vibration performance prediction and reliability analysis for rolling bearing

Meng¹,

Gong²,

Du³

et al. 2021

J. vibroeng.

View full text Add to dashboard Cite

show abstract

“…Aktürk [22] has shown that the difficulty level of the minefield game can be increased and decreased at the desired level by using the genetic algorithm and pixelization method together. Guo et al [23] have proposed an intelligent diagnostic method for rolling bearings based on depth. The training speed has been improved by adapting the parallel computing to the DBN training process in order to achieve global optimization with the genetic algorithm and to achieve more successful results in diagnosis accuracy.…”

Section: Literature Reviewmentioning

confidence: 99%

Route Optimization for Medication Delivery of Covid-19 Patients with Drones

Kaya

Akdağ

2021

Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım Ve Teknoloji

View full text Add to dashboard Cite

With the developments in information technologies and the intense use of online commerce, the use of drones in distribution process has gained importance. In order to transport products to more than one location, drones can perform the distribution by following a specific route, as in the traveling salesman problem. Drones provide advantages over land transportation since they are not affected by the traffic congestion and can be used autonomously. However, the limited battery durations increase the importance of using the optimum route in distribution processes. In this study, it is aimed to use drones in drug distribution. Nowadays, due to the Covid-19 pandemic, it is aimed to distribute the drugs for the patients in an optimum way with drones. In this study, it is aimed to find the optimized routes for drones in drug distribution since Covid-19 medicine distribution is a time-critic mission. Since the number of patients in a certain area may increase very quickly, it is ensured that the patients are divided into clusters and the optimum route is determined for each cluster. We propose a hybrid model consisting of a combination of K-means clustering and Ant Colony algorithms. In particular, Covid-19 patients use the mobile part of the developed application on their smartphones and transmit their medication requests to our central server. We have compared the performance of Ant Colony, Artificial Bee and Genetic algorithm metaheuristics at the stage of determining the most suitable route according to the demands collected dynamically on the central server. In the process of determining the most suitable route, Ant Colony algorithm yields the closest to optimum results for different location groups. We have developed the mobile and web site of the application to validate the proposed drug delivery model.

show abstract

“…Deep learning technology has shown good performance in fault detection and diagnosis with its powerful feature extraction ability and excellent classification performance, thus, it has become a research hotspot. Guo et al [11] proposed an intelligent method based on deep belief network (DBN) and hyperparameter optimization for fault diagnosis of rolling bearings. Li et al [12] proposed a deep autoencoder network for cross-machine fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

A Novel Generative Method for Machine Fault Diagnosis

et al. 2022

View full text Add to dashboard Cite

Deep learning is widely used in fault diagnosis of mechanical equipment and has achieved good results. However, these deep learning models require a large number of labeled samples for training, which is difficult to obtain enough labeled samples in the actual production process. However, it is easier to obtain unlabeled samples in the industrial environment. To overcome this problem, this paper proposes a novel method to generative enough label samples for training deep learning models. Unlike the generative adversarial networks, which required complex computing time, the calculation of the proposed novel generative method is simple and effective. First, we calculate the Euclidean distance between the training sample and the test sample; then, the weight coefficient between the training sample and the test sample is settled to generate pseudosamples; finally, combine with the pseudosamples, the deep learning method is training for machine fault diagnosis. In order to verify the effectiveness of the proposed method, two experiment datasets with planetary gearboxes and wind gearboxes are carried out with different activation functions. Experimental results show that the proposed method is effective for most activation function models.

show abstract

A Deep Learning Based Fault Diagnosis Method With Hyperparameter Optimization by Using Parallel Computing

Cited by 27 publications

References 44 publications

Vibration performance prediction and reliability analysis for rolling bearing

Vibration performance prediction and reliability analysis for rolling bearing

Route Optimization for Medication Delivery of Covid-19 Patients with Drones

A Novel Generative Method for Machine Fault Diagnosis

Contact Info

Product

Resources

About