Triboelectric sensor for planetary gear fault diagnosis using data enhancement and CNN

Xie, Zhijie; Wang, Yu; Yu, Mingyu; Yu, Di; Lv, Jingliang; Yin, Jihui; Liu, Jiuqing; Wu, Rensuan

doi:10.1016/j.nanoen.2022.107804

Cited by 27 publications

(6 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The TENGs based on the triboelectric effect and electrostatic induction can effectively collect and convert micromechanical energy into electricity. 16 In addition, TENGs have been successfully applied to the fields of machine sensing, 17,18 smart homes, 19,20 and smart transportation. 21, 22 Zhang used TENG for the first time for a driver's steering action monitoring and verified the sensitivity and stability of TENG in monitoring the driver's steering actions.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Assisted Sensor with Multiple Perception Capabilities for an Intelligent Driver Assistance Monitoring System

Lv,

Wang,

et al. 2024

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

Driver assistance systems can help drivers achieve better control of their vehicles while driving and reduce driver fatigue and errors. However, the current driver assistance devices have a complex structure and severely violate the privacy of drivers, hindering the development of driver assistance technology. To address these limitations, this article proposes an intelligent driver assistance monitoring system (IDAMS), which combines a Kresling origami structure-based triboelectric sensor (KOS-TS) and a convolutional neural network (CNN)-based data analysis. For different driving behaviors, the output signals of the KOS-TSs contain various features, such as a driver’s pressing force, pressing time, and sensor triggering sequence. This study develops a multiscale CNN that employs different pooling methods to process KOS-TS data and analyze temporal information. The proposed IDAMS is verified by driver identification experiments, and the results show that the accuracy of the IDAMS in discriminating eight different users is improved from 96.25% to 99.38%. In addition, the results indicate that IDAMS can successfully monitor driving behaviors and can accurately distinguish between different driving behaviors. Finally, the proposed IDAMS has excellent hands-off detection (HOD), identification, and driving behavior monitoring capabilities and shows broad potential for application in the fields of safety warning, personalization, and human–computer interaction.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Assisted Sensor with Multiple Perception Capabilities for an Intelligent Driver Assistance Monitoring System

Lv,

Wang,

et al. 2024

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…[13] Recently, outstanding features of triboelectric nanogenerators (TENGs) such as low cost of materials, fabricability, and flexibility of structure attracted great attention to address those drawbacks. [14][15][16][17] Furthermore, TENGs can generate sufficient energy for self-powered sensors and for powering other electronic components. [18] TENGs convert mechanical energy into electrical energy via contact electrification and electrostatic induction principles when two surfaces with various electronegativity are brought together and separated.…”

mentioning

confidence: 99%

Small Size and Low‐Cost TENG‐Based Self‐Powered Vibration Measuring and Alerting System

Mehamud

Björling

Marklund

et al. 2023

Adv Elect Materials

View full text Add to dashboard Cite

design evaluation during research development, [4] quality assessment for inspection, [5] and conventional testing. [6] The following are the three main parameters directly collected during vibration measurement: displacement, velocity, and acceleration. Usually, these parameters are assessed based on the concept of frequency spectrum analysis (with their defined frequency value). [7] For instance, the presence of misalignment, unbalance, looseness, eccentricity, and defects in machine elements are indicated based on their frequency value, while severe vibration levels depend on displacement, velocity, and acceleration. [8] Vibration measurement is the process of converting the physical oscillation of an object from an equilibrium position into an electrical signal. Then transforming the electrical signal into digitized data for display, interpretation, and data storage, through a sensing mechanism, and data acquisition system. [9] The main components here are sensors, signal conditioning, and data acquisition devices. A sensor is a transducer that converts physical variables into a proportional electrical signal. Piezoelectric, electromagnetic, and piezoresistive transducers are widely used to convert vibration signals into electrical signals. [10,11] Outstanding development has been done in developing vibration sensors from the above-mentioned transducer that exhibit excellent sensitivity, broad range, accuracy, and stability. However, piezoelectric sensors are influenced by the production cost and material (demand smart materials), [10] while piezoresistive sensors generate low electrical signals and demand time for production [12] and electromagnetic sensors are influenced by their size, flexibility, and production cost. [13] Recently, outstanding features of triboelectric nanogenerators (TENGs) such as low cost of materials, fabricability, and flexibility of structure attracted great attention to address those drawbacks. [14][15][16][17] Furthermore, TENGs can generate sufficient energy for self-powered sensors and for powering other electronic components. [18] TENGs convert mechanical energy into electrical energy via contact electrification and electrostatic induction principles when two surfaces with various electronegativity are brought together and separated. [19] Accordingly, TENG converts vibration motion into an electrical signal by imitating vibration oscillation from the equilibrium position. TENGs have shown promising results in developing self-powered sensors due to their Vibration measurement systems containing sensors, signal conditioning, and data acquisition devices, are important for monitoring motors, gearboxes, turbines, etc. Microelectromechanical and piezoelectric sensors are predominantly used for vibration measurements. However, they are not cost-effective, flexible in design, and incapable of self-powering. Recently, triboelectric nanogenerator (TENG)-based vibration sensors have been considered as a possible alternative to resolve this problem, and tremendous progress has been achiev...

show abstract

“…[15] Xie et al proposed a triboelectric planetary gear sensor to monitor gear faults of the planetary reducer, and based on convolutional neural network (CNN), the classification accuracy can achieve 100%. [16] Additionally, aiming at realizing intelligent maintenance of devices, digital twin provides an effective strategy. Digital twin is regarded as the best technology to achieve the integration of the physical world and digital space, which possesses the characteristics of virtual-real mapping, data-driven, and so on.…”

Section: Introductionmentioning

confidence: 99%

“…proposed a triboelectric planetary gear sensor to monitor gear faults of the planetary reducer, and based on convolutional neural network (CNN), the classification accuracy can achieve 100%. [ 16 ]…”

Section: Introductionmentioning

confidence: 99%

Structure‐Crack Detection and Digital Twin Demonstration Based on Triboelectric Nanogenerator for Intelligent Maintenance

Xin

Xie

et al. 2023

Advanced Science

View full text Add to dashboard Cite

The accomplishment of condition monitoring and intelligent maintenance for cantilever structure‐based energy harvesting devices remains a challenge. Here, to tackle the problems, a novel cantilever‐structure freestanding triboelectric nanogenerator (CSF‐TENG) is proposed, which can capture ambient energy or transmit sensory information. First, with and without a crack in cantilevers, the simulations are carried out. According to simulation results, the maximum change ratios of natural frequency and amplitude are 1.1% and 2.2%, causing difficulties in identifying defects by these variations. Thus, based on Gramian angular field and convolutional neural network, a defect detection model is established to achieve the condition monitoring of the CSF‐TENG, and the experimental result manifests that the accuracy of the model is 99.2%. Besides, the relation between the deflection of cantilevers and the output voltages of the CSF‐TENG is first built, and then the defect identification digital twin system is successfully created. Consequently, the system is capable of duplicating the operation of the CSF‐TENG in a real environment, and displaying defect recognition results, so the intelligent maintenance of the CSF‐TENG can be realized.

show abstract

Triboelectric sensor for planetary gear fault diagnosis using data enhancement and CNN

Cited by 27 publications

References 34 publications

Deep-Learning-Assisted Sensor with Multiple Perception Capabilities for an Intelligent Driver Assistance Monitoring System

Deep-Learning-Assisted Sensor with Multiple Perception Capabilities for an Intelligent Driver Assistance Monitoring System

Small Size and Low‐Cost TENG‐Based Self‐Powered Vibration Measuring and Alerting System

Structure‐Crack Detection and Digital Twin Demonstration Based on Triboelectric Nanogenerator for Intelligent Maintenance

Contact Info

Product

Resources

About