Gearbox fault identification based on lightweight multivariate multidirectional induction network

Zhu, Xiaofan; Wang, Ruijun; Fan, Zhixia; Xia, Danqing; Liu, Zhantian; Li, Zhentao

doi:10.1016/j.measurement.2022.110977

Cited by 12 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a consequence of this, users are aware of the expected output that the function that connects input and output should produce when it comes to making predictions (be it classification or regression). In the same way that supervised learning works, we need to find a system that can learn a functional approximation based on a predefined structure that exists between the input and the output [22]. The most basic form of neural network, also known as a shallow neural network (SNN), has just one hidden layer of nodes sitting in between the network input and output.…”

Section: Related Workmentioning

confidence: 99%

Application of Machine Learning in Multi-Directional Model to Follow Solar Energy Using Photo Sensor Matrix

Dhanalakshmi¹,

Venkatesh²,

Ranjit

et al. 2022

International Journal of Photoenergy

View full text Add to dashboard Cite

In this paper, we introduce a deep neural network (DNN) for forecasting the intra-day solar irradiance, photovoltaic PV plants, regardless of whether or not they have energy storage, can benefit from the work being done here. The proposed DNN utilises a number of different methodologies, two of which are cloud motion analysis and machine learning, in order to make forecasts regarding the climatological conditions of the future. In addition to this, the accuracy of the model was evaluated in light of the data sources that were easily accessible. In general, four different cases have been investigated. According to the findings, the DNN is capable of making more accurate and reliable predictions of the incoming solar irradiance than the persistent algorithm. This is the case across the board. Even without any actual data, the proposed model is considered to be state-of-the-art because it outperforms the current NWP forecasts for the same time horizon as those forecasts. When making predictions for the short term, using actual data to reduce the margin of error can be helpful. When making predictions for the long term, however, weather information can be beneficial.

show abstract

Section: Related Workmentioning

confidence: 99%

Application of Machine Learning in Multi-Directional Model to Follow Solar Energy Using Photo Sensor Matrix

Dhanalakshmi¹,

Venkatesh²,

Ranjit

et al. 2022

International Journal of Photoenergy

View full text Add to dashboard Cite

show abstract

“…Hence, the objective of this study is to mitigate the computational complexity of GMA-DRSN through the employment of a lightweight strategy while striving to uphold its superior diagnostic capacity. The currently prevalent lightweight strategies consist primarily of pruning [28,29], knowledge distillation [30,31], and lightweight module design [32,33]. For example, Zhu et al [28] enhanced the training efficiency of their denoising autoencoder network by utilizing a pruning strategy.…”

Section: Introductionmentioning

confidence: 99%

LGMA-DRSN: a lightweight convex global multi-attention deep residual shrinkage network for fault diagnosis

Zhang

Chen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Recently, the fault diagnosis domain has witnessed a surge in the popularity of the deep residual shrinkage network (DRSN) due to its robust denoising capabilities. In our previous research, an enhanced version of DRSN named global multi-attention DRSN (GMA-DRSN) is introduced to augment the feature extraction proficiency of DRSN specifically for noised vibration signals. However, the utilization of multiple attention structures in GMA-DRSN leads to an escalation in the computational complexity of the network, which may pose practical deployment challenges. To address this limitation, this paper proposes a lightweight variant of GMA-DRSN, referred to as LGMA-DRSN, building upon our prior work. Firstly, the numerical variation regularity of the adaptive inferred slope parameters in the global parametric rectifier linear unit (GPReLU) is analyzed, where we surprisingly find that a convex parameter combination always occurs in pairs. Based on this convex regularity, the sub-network structure of the adaptive inferred slope with attention mechanism is optimized, which greatly reduces the computational complexity compared to our previous work. Finally, the experimental outcomes demonstrate that LGMA-DRSN not only enhances diagnostic efficiency, but also ensures a high level of diagnostic accuracy in the presence of noise interference, when compared with our prior work.

show abstract

“…The Gearbox is the core rotating component in mechanical equipment. Its running status is directly related to whether the entire mechanical system can work efficiently [1,2]. In actual work, the operating conditions of gearbox are complex and changeable, and the measured signals are easy to show obvious non-linearity and nonstationary, which makes it difficult to extract fault features.…”

Section: Introductionmentioning

confidence: 99%

Gearbox Fault Diagnosis Method Based on Improved MobileNetV3 and Transfer Learning

2023

Teh. vjesn.

View full text Add to dashboard Cite

Under different working conditions of gearbox, the feature extraction of fault signals is difficult, and large difference in data distribution affects the fault diagnosis results. Based on the problems, the research proposes a method based on improved MobileNetV3 network and transfer learning (TL-Pro-MobilenetV3 network). Three timefrequency analysis methods are used to obtain time-frequency distribution. Among them, short time Fourier transform (STFT) combined with Pro-MobilenetV3 network takes the shortest time and has the highest accuracy. Furthermore, transfer learning is introduced into the model, and the optimal training parameters are selected training the network. Using the dataset from Southeast University, the TL-Pro-MobilenetV3 model is compared with four classical fault diagnosis models. The experimental results show the accuracy of the method proposed can reach 100% and the training time is the shortest in two working conditions, proving the proposed model has a good performance in generalization ability, recognition accuracy and training time.

show abstract

Gearbox fault identification based on lightweight multivariate multidirectional induction network

Cited by 12 publications

References 29 publications

Application of Machine Learning in Multi-Directional Model to Follow Solar Energy Using Photo Sensor Matrix

Application of Machine Learning in Multi-Directional Model to Follow Solar Energy Using Photo Sensor Matrix

LGMA-DRSN: a lightweight convex global multi-attention deep residual shrinkage network for fault diagnosis

Gearbox Fault Diagnosis Method Based on Improved MobileNetV3 and Transfer Learning

Contact Info

Product

Resources

About