A novel application of deep transfer learning with audio pre-trained models in pump audio fault detection

Anvar, Ali Akbar Taghizadeh; Mohammadi, Hossein

doi:10.1016/j.compind.2023.103872

Cited by 18 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dai et al considered a method for accurately identification of cavitation conditions, based on complementary ensemble empirical mode decomposition (CEEMD) and deep residual shrinkage network [14]. Anvar et al introduced an application for the early detection of pump failures use audio pre-trained by deep transfer learning [15]. Mousmoulis et al developed an experimental tool to analysis cavitation of centrifugal pump using acoustic emission, vibration measurements and flow visualization [16].…”

Section: Literature Reviewmentioning

confidence: 99%

Fault identification of centrifugal pump using WGAN-GP method with unbalanced datasets based on kinematics simulation and experimental case

Li,

Chu,

Sun

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

In practical engineering applications, the accuracy and stability of fault identification for centrifugal pump will be significantly reduced due to unbalanced distribution between normal and fault datasets, i.e., the number of normal working samples is far more than the fault samples. To alleviate this bottleneck issue, this paper explores the fault identification of centrifugal pump based on Wasserstein generative adversarial network with gradient penalty (WGAN-GP) through combining kinematics simulation and experimental case. Specifically, ideal unbalanced vibration datasets from failure patterns such as damaged impeller of centrifugal pump are simulated and collected by prototype ADAMS software, then the unbalanced vibration signals are transformed into 2D grey-scale images. Furtherly, the generated grey-scale image datasets are feed into the original grey-scale image dataset as new datasets for training when the Nash equilibrium of the WGAN-GP model is reached. Eventually, the fault patterns of centrifugal pump are identified using confusion matrix graph. Meanwhile, another public dataset of centrifugal pump is employed for verifying the accuracy of the WGAN-GP model. Results indicate that fault identification accuracies with 95.07% and 98.0% of both kinematics simulation and experimental case are obtained, respectively, and the issues of unbalanced distribution and insufficient dataset can be overcome effectively.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Fault identification of centrifugal pump using WGAN-GP method with unbalanced datasets based on kinematics simulation and experimental case

Li,

Chu,

Sun

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In summary, the CNN-ECA model showed excellent predictive performance, while also being lightweight. Taking advantage of this benefit, the PC-trained CNN-ECA model was transferred to the Raspberry Pi hardware platform using the concept of transfer learning [45,46]. This process culminated in the development of a real- time detection E-nose system, which integrated a microcontroller as the core processor, semiconductor resistive gas sensors comprising the sensor array, and Raspberry Pi serving both as the data inference and display terminal, as displayed in figure 8.…”

Section: E-nose Systemsmentioning

confidence: 99%

An E-nose system for identification and quantification of hazardous gas mixtures using a combined strategy of CNNs and attentional mechanisms

Yang,

Wang,

Zhao

et al. 2024

Phys. Scr.

View full text Add to dashboard Cite

The chemical industry generates a broad spectrum of hazardous gases, presenting significant challenges for conventional detection methods due to their diverse chemical properties and low concentration levels. E-nose systems, employing sensor arrays, offer significant potential for the determination of gas mixtures. This study presents a novel E-nose algorithm, CNN-ECA, which integrated CNNs and attention mechanisms to improve the recognition accuracy of E-nose systems. By integrating the attention mechanism module into CNN's convolutional operations, the algorithm emphasizes critical feature information. Three hazardous gases (ammonia, methanol, and acetone) and their mixtures were chosen as target gases. CNNs were combined with various attention mechanism networks (SENet, ECA, and CBAM) to construct models, which were then employed to train and evaluate data collected from the sensor array. The results were compared with traditional network models (KNN, SVM, and CNN). Experimental findings indicated that the prediction performance of CNN models combined with attention mechanism networks surpassed that of traditional network models. Particularly, the CNN-ECA network model demonstrated the highest performance in both qualitative and quantitative analyses. This study presents a promising solution for mixed gas detection by synergizing CNN and attention mechanism networks, thereby enhancing the accuracy and reliability of mixed gas measurements. Moreover, capitalizing on the lightweight architecture of the CNN-ECA model, transfer learning techniques were employed to adapt it for deployment on the Raspberry Pi hardware platform. This facilitates the development of a real-time E-nose system for gas detection.

show abstract

A branched Convolutional Neural Network for RGB-D image classification of ceramic pieces

Carreira,

Rodrigues,

Miragaia

et al. 2024

Applied Soft Computing

View full text Add to dashboard Cite

A novel application of deep transfer learning with audio pre-trained models in pump audio fault detection

Cited by 18 publications

References 21 publications

Fault identification of centrifugal pump using WGAN-GP method with unbalanced datasets based on kinematics simulation and experimental case

Fault identification of centrifugal pump using WGAN-GP method with unbalanced datasets based on kinematics simulation and experimental case

An E-nose system for identification and quantification of hazardous gas mixtures using a combined strategy of CNNs and attentional mechanisms

A branched Convolutional Neural Network for RGB-D image classification of ceramic pieces

Contact Info

Product

Resources

About