Ensemble Multiple Distinct ResNet Networks With Channel-Attention Mechanism for Multisensor Fault Diagnosis of Hydraulic Systems

Peng, Xiangyu; Xu, Huoyao; Wang, Junlang; Liu, Jie; He, Chaoming

doi:10.1109/jsen.2023.3263924

Cited by 15 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the energy eigenvalue, the accuracy of the proposed method increased by 8.7% and the verification accuracy increased by 42.11%. In order to solve the problem that most intelligent diagnosis methods based on DL only use single channel signals and cannot distinguish the sensitivity of features between channels, a multi-channel data-driven hydraulic system fault diagnosis framework was proposed [86]. The signals of each channel trained multiple base learners, connected the class probability of each base learner into a new feature vector, and used the new feature vector to train the meta-learner and perform fault diagnosis.…”

Section: Feature-level Fusionmentioning

confidence: 99%

Intelligent fault diagnosis methods for hydraulic components based on information fusion: review and prospects

Guan,

Ren,

Tang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Hydraulic component faults have the characteristics of nonlinear time-varying signal, strong concealment, and difficult feature extraction, etc. Timely and accurately fault diagnosis of hydraulic components is helpful to curb economic losses and accidents, so researches have carried out a lot of research on hydraulic components. Information fusion technology can combine multi-source data from multiple dimensions to mine fault data characteristics, which effectively improves the accuracy and reliability of fault diagnosis results. However, there is currently a lack of a comprehensive and systematic review in this domain. Therefore, in this paper, the hydraulic components information fusion fault diagnosis technologies are summarized and analyzed, including the main process information fusion fault diagnosis and the research status of information fusion fault diagnosis of hydraulic system. The methods and techniques involved in the fusion process, data source and fusion method of fault diagnosis of hydraulic components information fusion are described and summarized. The problems of information fusion in fault diagnosis of hydraulic components are analyzed, the solutions are discussed, and the research ideas of improving information fusion fault diagnosis are put forward. Finally, digital twin technology is introduced, and the advantages and research status of intelligent fault diagnosis based on digital twin are summarized. On this basis, the intelligent fault diagnosis of hydraulic components based on information fusion is summarized, and the challenges and future research ideas of applying information fusion and digital twin to intelligent fault diagnosis of hydraulic components are put forward and analyzed comprehensively.

show abstract

Section: Feature-level Fusionmentioning

confidence: 99%

Intelligent fault diagnosis methods for hydraulic components based on information fusion: review and prospects

Guan,

Ren,

Tang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Although the authors of Ref. [42] recently proposed a framework that can diagnose multiple faults in hydraulic systems and identify the different degradation levels of the components, it still requires validation for the FCAS models.…”

Section: Future Work and Challengesmentioning

confidence: 99%

Modeling a Hydraulically Powered Flight Control Actuation System

Iyaghigba,

Petrunin,

Avdelidis

2024

Applied Sciences

View full text Add to dashboard Cite

Many different types of aircraft designs have flight control systems (FCS) powered by hydraulic systems. With respect to the torques, moments, surface areas, and opposing forces to be acted upon, components introduce faults into the hydraulic system when these components are aging or degrading. The diagnostics of a hydraulically powered flight control actuation system (HPFCAS) rely on the faults produced within the subsystem components as well as the entire system’s mechanism itself. In this paper, a model for an HPFCAS is developed to analyze faults where the HPFCAS was approached as a system of systems (SOS). The identified faults were injected into the system. It is established that some of the faults from the different subsystems had similar characteristic effects and were propagated with attendant consequences. For instance, a measured decrease in the pressure value is observed because of the decrease in the pump speed. A similar characteristic is observed if there is leakage on the line or if there is a clogging valve. These form complex integrated responses in determining where the fault is coming from if only one component is analyzed since it involves components serving different subsystems. Results show that only models that can describe the real characteristics or attributes of the specific systems, due to their defined components, are sufficient for effective diagnostics. This is because the data obtained are more accurate at predicting the behavior of components.

show abstract

“…Shi et al [31] proposed a multi-sensor, multidimensional feature-weighted adaptive fusion diagnostic method to realize hydraulic directional valve fault diagnosis. Peng et al [32] proposed a multi-channel signal-driven ensemble learning framework based on multiple distinct residual networks (ResNet) with a channel-attention mechanism (CM-ResNet) for fault diagnosis of hydraulic systems. Graph neural networks [33,34] can effectively utilize the relationships between nodes and edges in a graph to propagate information, which effectively captures the interconnections among the data.…”

Section: Introductionmentioning

confidence: 99%

Intelligent fault diagnosis for electro-hydrostatic actuator based on multisource information convolutional residual network

Liu,

Hu,

Zhu

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The electro-hydrostatic actuator (EHA), known for its advantages such as minimal throttling loss, high efficiency, and a significant volume-to-power ratio, has found extensive application in the fields of aeronautics and astronautics. However, ensuring the safety of aircraft that utilize EHAs requires efficient fault diagnosis due to the demanding operational conditions and prolonged usage. Traditional diagnostic approaches face challenges such as intricate fault modeling, complex multi-channel monitoring data, and a limited number of fault samples within the electro-hydraulic system. To overcome these challenges, we propose an intelligent diagnosis method based on a multi-source information convolutional residual network. Specifically, a multis-cale kernel is implemented to capture features at different scales, enhancing model expressiveness. The efficiency channel attention mechanism dynamically focuses on relevant channel features to improve feature learning ability. The residual network adaptively recalibrates features at each layer to facilitate fault feature learning. Additionally, the activate or not activation function is introduced to selectively activate shallow features, thereby improving the feature representation and generalization capability of the model. Experimental data from the EHA system validates the superiority of the proposed method, demonstrating a significant enhancement in the diagnostic accuracy of EHAs with limited samples.

show abstract

Ensemble Multiple Distinct ResNet Networks With Channel-Attention Mechanism for Multisensor Fault Diagnosis of Hydraulic Systems

Cited by 15 publications

References 40 publications

Intelligent fault diagnosis methods for hydraulic components based on information fusion: review and prospects

Intelligent fault diagnosis methods for hydraulic components based on information fusion: review and prospects

Modeling a Hydraulically Powered Flight Control Actuation System

Intelligent fault diagnosis for electro-hydrostatic actuator based on multisource information convolutional residual network

Contact Info

Product

Resources

About