Dual arm electrical transmission line robot: motion through straight and jumper cable

Shruthi, C. M.; Sudheer, A. P.; Joy, M. L.

doi:10.1080/00051144.2019.1609256

Cited by 19 publications

(15 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Drones and robots that are capable of patrolling are made to increase inspection safety and lower costs [4][5][6] . After images and videos are collected from robots, trained workers spend huge amounts of time to analyze these images in order to recognize any faults.…”

Section: Overviewmentioning

confidence: 99%

Data Augmentation Using Generative Adversarial Networks for Electrical Insulator Anomaly Detection

Luo

Hsu

Wang

2020

Proceedings of the 2020 2nd International Conference on Management Science and Industrial Engineering

View full text Add to dashboard Cite

Electricity has been an essential part of our life. Insulators, which are widely used for electricity transmission, are prone to be damaged and need constant maintenance. Traditionally, the inspection job is time-consuming and dangerous as workers would have to climb up the electricity tower. Deep learning has offered a safe and quick way to inspections. About 3000 insulators images are taken from different angles using a drone. Due to great difference in number of good and damaged insulator, directly training a classifier on the imbalanced data lead to low recall value on the damaged insulators. Generative adversarial networks (GANs) were introduced as a novel way to augment data. However, traditional GANs are either incapable of generating high quality images or fail to generate minority class images when minority class examples are far less. In this study, a novel GAN model, Balancing and Progressive GANs (BPGANs), was proposed for effectively making use of all classes information and generating high quality minority images at the same time. Results show that PGANs, StyleGANs, and BPGANs were able to generate high-resolution images and improve classification performance. PGANs achieved the better results than BPGANs. This may be because BPGANs only provides 2 additional latent codes since it is a binary classification, having little effect on generating desired images. BPGANs seemed to have difficulties generating class-specific images, which might be because that the classification loss is too little compared to the source loss and optimization was more focused to optimize the source loss. This indicates that learning representations of data progressively from low resolution to high resolution is an effective approach, however, embedding class label information in the fashion of AC-GANs and BGANs might not be appropriate for augmenting binary class data sets.

show abstract

Section: Overviewmentioning

confidence: 99%

Data Augmentation Using Generative Adversarial Networks for Electrical Insulator Anomaly Detection

Luo

Hsu

Wang

2020

Proceedings of the 2020 2nd International Conference on Management Science and Industrial Engineering

View full text Add to dashboard Cite

show abstract

“…Moreover, the external forces Q i of the Lagrangian dynamics of equation (1) comprises the actuator force f r , the wind force f w , and the sinusoidal force f s that cause the flexible line to oscillate along y-axis when the robot moves along the line. us, the complete dynamics of the robot under the influence of wind can be calculated by solving equation (1) using equations (17) and (18) as expressed in equation (19) to equation (21). It can be seen that the final dynamics of equations (20) and (21) are for the angular accelerations of the robot trunk.…”

Section: Wind F W Robotmentioning

confidence: 99%

“…us, the complete dynamics of the robot under the influence of wind can be calculated by solving equation (1) using equations (17) and (18) as expressed in equation (19) to equation (21). It can be seen that the final dynamics of equations (20) and (21) are for the angular accelerations of the robot trunk. To determine the linear accelerations, the results should be multiplied by the radius of rotation, here, l.…”

Section: Wind F W Robotmentioning

confidence: 99%

“…To study the dynamic response of the system derived in equation (19) to equation (21), the robot was controlled at the speed of 10 m/min, and the flexibility of the line f s was measured experimentally to have a maximum amplitude of 3 cm at 2 rad/sec. In addition to this, the parameters of Table 2 were used for the simulations.…”

Section: Simulation Analysismentioning

confidence: 99%

“…However, the stability of Expliner is not guaranteed due to its complex maneuvers during automation. Other types of climbing PTLIRs include the line-walking mechanism [15,16], three-arm prototype [17,18], four-arm POLIBOT [19], five-arm structure [20,21], and snake-like mechanism [22,23], among others. However, most of the existing climbing PTLIRs are either heavy or relatively large and can easily be affected by external wind.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Investigation of Aerodynamic Stability of a Lightweight Dual‐Arm Power Transmission Line Inspection Robot under the Influence of Wind

Alhassan

Zhang

Shen

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

To efficiently transmit electric power to consumers, the power lines need to be inspected routinely for early fault detection. Thus, power line inspection robots are designed to replace the tedious and dangerous manual inspection using linemen or helicopters. However, most of the existing inspection robots are heavy, which make them slow and prone to external wind disturbance. This paper developed a lightweight dual-arm robot and investigates its robustness to wind disturbance on a lab-scale power line structure. The dynamic equations of the robot are derived using the Lagrangian equation for appropriate motor selection. Also, the components of the robot are designed to ensure low drag coefficient to wind flow, and the mechanism of the wind force on the robot-line coupled system is presented. To study the real-time impact of the wind, a wind speed of 4.5 m/s representing one of the windiest cities in China is considered as a case study. The experimental results for different wind directions, namely, 0°, 45°, and 90°, show that the maximum vibration is 8% higher than the normal vibration of the system in a controlled environment without wind. The results demonstrate that there is little influence of the wind on the system; hence, the robot has been successfully designed and can be applied for power line inspection.

show abstract

Control System of Intelligent Inspection Robot for Substation Based on “Internet+”

Gao¹,

Ijaz²

2023

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Dual arm electrical transmission line robot: motion through straight and jumper cable

Cited by 19 publications

References 38 publications

Data Augmentation Using Generative Adversarial Networks for Electrical Insulator Anomaly Detection

Data Augmentation Using Generative Adversarial Networks for Electrical Insulator Anomaly Detection

Investigation of Aerodynamic Stability of a Lightweight Dual‐Arm Power Transmission Line Inspection Robot under the Influence of Wind

Control System of Intelligent Inspection Robot for Substation Based on “Internet+”

Contact Info

Product

Resources

About