Combined inspection strategy of bionic substation inspection robot based on improved Biological Inspired Neural Network

We have previously proposed a navigation system for autonomous mobile robots that can recognize regular ceiling landmarks. This system can find square air diffusers on ceilings by sensing their multiple-quadrangle characteristics. We have now developed a new system that is able to recognize circular air diffusers. In addition, certain lighting conditions which obstructed recognition in the original system do not interfere with the newly proposed system. Here we applied Fuzzy and Neural Network Logic technology. A pre-processed image of a landmark is compared with a fuzzy template made from the fuzzy membership function. In order to find specific landmarks, the system determines the degrees of similarity by comparing the sited object with a variety of templates stored in its memory. Then a Neural Network uses results of this calculation to hone in on its target. So, the system can recognize many different kinds of landmarks. This paper shows the principle of this system and experimental results.

Download Full-text

Development of Hanger-Rope Inspection Robot for Suspension Bridges

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2019.p0855 ◽

2019 ◽

Vol 31 (6) ◽

pp. 855-862

Author(s):

Hidekazu Kajiwara ◽

◽

Naohiko Hanajima ◽

Kentarou Kurashige ◽

Yoshinori Fujihira

Keyword(s):

High Speed ◽

Suspension Bridge ◽

Suspension Bridges ◽

Electromagnetic Brake ◽

Drive Roller ◽

Inspection Robot ◽

Main Cable ◽

Inspection Strategy

This paper describes the development of a hanger-rope inspection robot for suspension bridges. The inspection robot inspects the hanger rope by going up and down the rope installed vertically downward from the main cable of a suspension bridge. The going-up-and-down mechanism of the robot consists of a drive roller driven by a motor and a non-excitation electromagnetic brake, and the robot can safely descend after climbing the rope at high speed. The developed robot is small in size and light in weight, and an inspection worker can easily install the robot on the rope. In addition, the robot can be wirelessly controlled with ease from the controller. First, this paper describes the hanger-rope inspection strategy of the suspension bridge. Then, the developed prototype 2 robot is introduced. Next, the result of the hanger-rope inspection in an actual suspension bridge and the problems are clearly revealed by experiment. Finally, the newly developed prototype 3 robot is introduced, and the result of the going-up-and-down experiment is described.

Download Full-text

Application of Joint Immune Ant Colony Algorithm and Fuzzy Neural Network to Path Planning and Visual Image Processing of Inspection Robot in Substation

2020 3rd International Conference on Artificial Intelligence and Big Data (ICAIBD) ◽

10.1109/icaibd49809.2020.9137437 ◽

2020 ◽

Author(s):

Zhang Shiling

Keyword(s):

Neural Network ◽

Image Processing ◽

Path Planning ◽

Fuzzy Neural Network ◽

Ant Colony Algorithm ◽

Visual Image ◽

Ant Colony ◽

Inspection Robot ◽

Fuzzy Neural

Download Full-text

UT System Composition and Welding Flaw Classification for SWP Stability Estimation

Key Engineering Materials ◽

10.4028/www.scientific.net/kem.261-263.1385 ◽

2004 ◽

Vol 261-263 ◽

pp. 1385-1390

Author(s):

Jae Yeol Kim ◽

Young Tae Yoo ◽

Kyung Seok Song ◽

Chang Hyun Kim ◽

Dong Jo Yang

Keyword(s):

Neural Network ◽

Signal Processing ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Bayesian Classifier ◽

Ultrasonic Probe ◽

Inspection Method ◽

Stability Estimation ◽

Inspection Robot ◽

Flaw Classification

The purpose of this research is stability estimation of plant structure through classification and recognition about welding flaw in SWP(Spiral Welding Pipe). And, In this research, we used nondestructive test based on ultrasonic test as inspection method, and made up inspection robot in order to control of ultrasonic probe on the SWP surface, and programmed to signal processing code and pattern classifying code by user made programming code. Inspection robot is simply constructed as 2-axes because of welding bead with fixed pitch. So, inspection of welding part can be possible as composition of inspection part for tracking on welding line. For evaluation of flaw signal is reflected on welding flaw, user-made program codes are composed of signal processing and Bayesian classifier and perceptron neural network and back-propagation neural network. And then, we confirmed to superiority of neural network method compared with Bayesian classifier for classification and recognition rate. According to this result, we selected back-propagation neural network as classification and recognition method about the system of SWP stability Estimation[2]. Through this process, we proved efficiency on the system of SWP stability Estimation, and constructed on the base of the system of SWP stability Estimation for the application in industrial fields.

Download Full-text

Remote drain inspection framework using the convolutional neural network and re-configurable robot Raptor

Scientific Reports ◽

10.1038/s41598-021-01170-0 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Lee Ming Jun Melvin ◽

Rajesh Elara Mohan ◽

Archana Semwal ◽

Povendhan Palanisamy ◽

Karthikeyan Elangovan ◽

...

Keyword(s):

Neural Network ◽

Object Detection ◽

Convolutional Neural Network ◽

Urban Environment ◽

Field Trial ◽

Detection Algorithm ◽

Data Set ◽

Detection Model ◽

Inspection Robot ◽

Online Test

AbstractDrain blockage is a crucial problem in the urban environment. It heavily affects the ecosystem and human health. Hence, routine drain inspection is essential for urban environment. Manual drain inspection is a tedious task and prone to accidents and water-borne diseases. This work presents a drain inspection framework using convolutional neural network (CNN) based object detection algorithm and in house developed reconfigurable teleoperated robot called ‘Raptor’. The CNN based object detection model was trained using a transfer learning scheme with our custom drain-blocking objects data-set. The efficiency of the trained CNN algorithm and drain inspection robot Raptor was evaluated through various real-time drain inspection field trial. The experimental results indicate that our trained object detection algorithm has detect and classified the drain blocking objects with 91.42% accuracy for both offline and online test images and is able to process 18 frames per second (FPS). Further, the maneuverability of the robot was evaluated from various open and closed drain environment. The field trial results ensure that the robot maneuverability was stable, and its mapping and localization is also accurate in a complex drain environment.

Download Full-text