A novel improved full vector spectrum algorithm and its application in multi-sensor data fusion for hydraulic pumps

Yu, He; Li, Hongru; Li, Yaolong; Li, Yifan

doi:10.1016/j.measurement.2018.10.011

Cited by 30 publications

(22 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detection of series ac arc faults is requested to have high accuracy. Test results indicates that our method has higher precision than methods [20,27].…”

Section: 75%mentioning

confidence: 91%

“…Method proposed in this paper could be applied to resistive loads, inductive loads, resistive and inductive loads, and nonlinear loads. It is more general than methods presented in [20,26]. Wang et al [27] proposed a sparse representation and fully connected neural network (SRFCNN) method.…”

Section: Comparison With Prior Methodsmentioning

confidence: 99%

“…Yu et al [20] utilize current data measured by experiments to the improved AlexNet. five convolution layers, three pooling layers, three full connection layers.…”

Section: 6%mentioning

confidence: 99%

“…Joshua E. Siegel et al [19] developed a deep neural network taking Fourier coefficients, Mel-Frequency Cepstrum data, and Wavelet features as input for detecting and disrupting electronic arc faults. Qiongfang Yu et al [20] first carried out a method based on deep learning algorithm to detect series arc faults in ac system. This study directly sent the current signals to the improved AlexNet deep neural network for feature learning and state classification.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Identification Method for Series Arc Faults Based on Wavelet Transform and Deep Neural Network

Yang

2019

Energies

View full text Add to dashboard Cite

The power supply quality and power supply safety of a low-voltage residential power distribution system is seriously affected by the occurrence of series arc faults. It is difficult to detect and extinguish them due to the characteristics of small current, high stochasticity, and strong concealment. In order to improve the overall safety of residential distribution systems, a novel method based on discrete wavelet transform (DWT) and deep neural network (DNN) is proposed to detect series arc faults in this paper. An experimental bed is built to obtain current signals under two states, normal and arcing. The collected signals are discomposed in different scales applying the DWT. The wavelet coefficient sequences are used for forming training set and test set. The deep neural network trained by training set under 4 different loads adaptively learn the feature of arc faults. The accuracy of arc faults recognition is sent through feeding test set into the model, about 97.75%. The experimental result shows that this method has good accuracy and generality under different types of loading.

show abstract

“…The detection of series ac arc faults is requested to have high accuracy. Test results indicates that our method has higher precision than methods [20,27].…”

Section: 75%mentioning

confidence: 91%

Section: Comparison With Prior Methodsmentioning

confidence: 99%

“…Yu et al [20] utilize current data measured by experiments to the improved AlexNet. five convolution layers, three pooling layers, three full connection layers.…”

Section: 6%mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Identification Method for Series Arc Faults Based on Wavelet Transform and Deep Neural Network

Yang

2019

Energies

View full text Add to dashboard Cite

show abstract

“…In Ref. [23], three mutually perpendicular vibration sensors were installed to capture fault information as shown in figure 5(a) and (b). In this way, there was a certain inclination angle between the friction pair and the rotation axis; therefore, the vortex characteristics of the rotor containing information about the pump operational state transmitted not only in the spatial domain but also for the whole shell.…”

Section: B Vibration Monitoringmentioning

confidence: 99%

Overview of Applications of the Sensor Technologies for Construction Machinery

Jiang

2020

IEEE Access

View full text Add to dashboard Cite

In recent years, great development in sensor technologies have resulted in substantial progress in the construction efficiency and the degree of automation of construction machinery have made great progress. Applications of the sensor technologies, such as condition monitoring, autonomous construction and the Internet of Things (IoT), have been extensively studied for construction machinery. Firstly, this paper discusses the condition monitoring technology in construction machinery, which mainly involves the monitoring of oil pollution and leakage, vibration monitoring, emission monitoring and wholesystem monitoring. Second, regarding autonomous construction technology, this paper conducts analysis and discussion on linear motion, rotary motion, navigation/positioning systems, and visual systems. Third, research on IoT technology in construction machinery is comprehensively discussed, especially in term of life cycle maintenance, construction management and safety management. Finally, higher reliability, the development of smart sensors and big data management of sensor information are described as prospective issues that must be addressed for future construction machinery. INDEX TERMS Construction equipment, condition based maintenance (CBM), global navigation satellite system (GNSS), building information modelling (BIM), Internet of Things (IoT) This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.

show abstract

Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals

Chao

Gao

Tao

et al. 2021

Sci. China Technol. Sci.

View full text Add to dashboard Cite

A novel improved full vector spectrum algorithm and its application in multi-sensor data fusion for hydraulic pumps

Cited by 30 publications

References 35 publications

Identification Method for Series Arc Faults Based on Wavelet Transform and Deep Neural Network

Identification Method for Series Arc Faults Based on Wavelet Transform and Deep Neural Network

Overview of Applications of the Sensor Technologies for Construction Machinery

Adaptive decision-level fusion strategy for the fault diagnosis of axial piston pumps using multiple channels of vibration signals

Contact Info

Product

Resources

About