Design of DSP-Based Automatic Seam Tracking Underwater System

2014 ◽  
Vol 644-650 ◽  
pp. 845-848
Author(s):  
Fu Yang ◽  
Wen Ming Zhang ◽  
Wan Cai Jiao
Keyword(s):  
Tracking System ◽  
Low Cost ◽  
Human Machine Interface ◽  
Seam Tracking ◽  
Welding Seam ◽  
Automatic Tracking ◽  
Underwater Welding ◽  
Effect Of Water ◽  
Machine Interface ◽  
Hardware Structure

It is high difficult to control the underwater welding because of the effect of water and the leak proofness of the weld devices which is a troubling problem. In this paper, a DSP-based automatic seam tracking system for underwater welding is designed. This system has the advantages of simple hardware structure, low-cost, rich function software, friendly human-machine interface, and easily realizing. And the work of this paper can be used for further research in underwater welding seam automatic tracking.

Design of Human Machine Interface Based on ARM and Linux

2012 ◽  
Vol 241-244 ◽  
pp. 2714-2717
Author(s):  
Kun Zhang ◽  
Xi Wei Peng
Keyword(s):  
Low Cost ◽  
Hardware Design ◽  
Control Unit ◽  
Embedded Linux ◽  
Human Machine Interface ◽  
Device Drivers ◽  
Machine Interface ◽  
Micro Control Unit

In order to provide more convenient options for users and developers, the design of Human Machine Interface (HMI) based on ARM and embedded Linux is put forward. It makes full use of multiple peripherals of ARM and flexibility of Linux OS. Firstly, hardware design of the HMI system is presented. Then methods of embedded Linux transplanting and the device drivers programming are discussed. Finally, running results and applications of the designed HMI are considered. The design combines the features of traditional HMI and Micro Control Unit (MCU) HMI, including low cost, rich interfaces and easy programming.

KOMEKAMI Switch: A Novel Wearable Input Device Using Movement of Temple

2008 ◽  
Vol 20 (2) ◽  
pp. 260-272 ◽  
Author(s):  
Kazuhiro Taniguchi ◽  
◽  
Atsushi Nishikawa ◽  
Seiichiro Kawanishi ◽  
Fumio Miyazaki
Keyword(s):  
Low Cost ◽  
Wearable Computing ◽  
Computing System ◽  
Human Machine Interface ◽  
Input Device ◽  
Single Chip ◽  
Leading Role ◽  
Optical Distance ◽  
Machine Interface ◽  
Manual Manipulation

A wearable computing system plays a leading role in the ubiquitous computing era, in which computers are used at any place and at any time. Now the mobile multimedia communication technology based devices, such as mobile phone, handy-type PC, etc., have come to be used in such a broad range of areas, the features of wearable hands-free computing system, which people can constantly use in their daily life or workplace while doing some other job, are highly valued more than ever. However, the wearable computing system has not yet spread so widely owing to various factors. Among such factors is the delay in the development of human machine interface, which is applicable to the wearable computing system. Conventional technologies that require either manual manipulation of keyboard, mouse, touch panel, etc., or a large equipment to make use of electroencephalogram, eyeball movements, etc. for realizing hands-free interface, are not suitable for the wearable computing system. We, therefore, developed a human-machine interface for the wearable computing system. This interface makes it easy to manipulate machine with intentional movements of temple. User can constantly use machine with no interference, as well as with hands free. It is compact and lightweight, permitting ease of manufacturing at a low cost. It does not react to daily actions like conversation, diet, etc., other than movements intended to control the machine. This interface consists of one optical distance sensor mounted in the vicinity of the left and right temples each and of one single-chip microcomputer.

A Robust Detector for Automated Welding Seam Tracking System

2021 ◽  
Vol 143 (7) ◽  
Author(s):  
Yanbiao Zou ◽  
Mingquan Zhu ◽  
Xiangzhi Chen
Keyword(s):  
Object Detection ◽  
Weld Seam ◽  
Tracking System ◽  
Welding Current ◽  
Detection Algorithm ◽  
Seam Tracking ◽  
Detection Accuracy ◽  
Single Shot ◽  
Welding Seam ◽  
Laser Vision

Abstract Accurate locating of the weld seam under strong noise is the biggest challenge for automated welding. In this paper, we construct a robust seam detector on the framework of deep learning object detection algorithm. The representative object algorithm, a single shot multibox detector (SSD), is studied to establish the seam detector framework. The improved SSD is applied to seam detection. Under the SSD object detection framework, combined with the characteristics of the seam detection task, the multifeature combination network (MFCN) is proposed. The network comprehensively utilizes the local information and global information carried by the multilayer features to detect a weld seam and realizes the rapid and accurate detection of the weld seam. To solve the problem of single-frame seam image detection algorithm failure under continuous super-strong noise, the sequence image multifeature combination network (SMFCN) is proposed based on the MFCN detector. The recurrent neural network (RNN) is used to learn the temporal context information of convolutional features to accurately detect the seam under continuous super-noise. Experimental results show that the proposed seam detectors are extremely robust. The SMFCN can maintain extremely high detection accuracy under continuous super-strong noise. The welding results show that the laser vision seam tracking system using the SMFCN can ensure that the welding precision meets industrial requirements under a welding current of 150 A.

Sign in / Sign up

Export Citation Format

Share Document