Adaptive Part Inspection Through Developmental Vision

2005 ◽  
Vol 127 (4) ◽  
pp. 846-856 ◽  
Author(s):  
Gil Abramovich ◽  
Juyang Weng ◽  
Debasish Dutta
Keyword(s):  
Hierarchical Classification ◽  
General Purpose ◽  
Inspection System ◽  
Inspection Method ◽  
Fast Recognition ◽  
Environmental Properties ◽  
Image Set ◽  
Part Inspection ◽  
Inspection Tasks ◽  
Online Inspection

We present a novel online inspection method for manufacturing processes that automatically adapts to variations in part and environmental properties. This method is based on a developmental learning architecture comprising a procedure that focuses attention to apparently defective regions, a recognition method that performs automatic feature derivation based on a set of training images and hierarchical classification, and an action step that controls attention and further decision processes. The method adapts to variations incrementally by updating rather than recreating the training information. Also, the method is capable of inspecting and training simultaneously. Addressing new inspection tasks requires neither re-programming and compatibility tests, nor quantitative knowledge about the image set, from a human developer. Instead, automatic or manual training of the inspection system according to simple guidelines is applied. These attributes allow the method to improve online performance with minimal ramp-up time. Our system performed inspection of three applications with low error rate and fast recognition, confirming its suitability for general-purpose, real-time, online inspection.

scholarly journals Brush-Holder Integrated Load Sensor Prototype for SAG Grinding Mill Motor

Electronics ◽  
2019 ◽  
Vol 8 (11) ◽  
pp. 1227 ◽  
Author(s):  
Carrasco ◽  
Álvarez ◽  
Velázquez ◽  
Concha ◽  
Pérez-Cotapos
Keyword(s):  
Measurement Errors ◽  
Large Scale ◽  
Mining Industry ◽  
Data Entry ◽  
Inspection Time ◽  
Inspection System ◽  
Design Development ◽  
Internal Parameters ◽  
Inspection Tasks ◽  
Grinding Mill

One of the most widely used electro-mechanical systems in large-scale mining is the electric motor. This device is employed in practically every phase of production. For this reason, it needs to be inspected regularly to maintain maximum operability, thus avoiding unplanned stoppages. In order to identify potential faults, regular check-ups are performed to measure the internal parameters of the components, especially the brushes and brush-holders. Both components must be properly aligned and calibrated to avoid electric arcs to the internal insulation of the motor. Although there is an increasing effort to improve inspection tasks, most inspection procedures are manual, leading to unnecessary costs in inspection time, errors in data entry, and, in extreme cases, measurement errors. This research presents the design, development, and assessment of an integrated measurement prototype for measuring spring tension and other key parameters in brush-holders used in electric motors. It aims to provide the mining industry with a new, fully automatic inspection system that will facilitate maintenance and checking. Our development research was carried out specifically on the brush system of a SAG grinding mill motor. These machines commonly use SIEMENS motors; however, the instrument can be easily adapted to any motor by simply changing the physical dimensions of the prototype.

Automatic Ultrasonic Inspection Method of Railway Axle and its Remaining Life Prediction

2011 ◽  
Vol 213 ◽  
pp. 291-296 ◽  
Author(s):  
Hong Wei Hu ◽  
Xiong Bing Li ◽  
Xiang Hong Wang ◽  
Yi Min Shao
Keyword(s):  
High Speed ◽  
Fatigue Cracks ◽  
Ultrasonic Inspection ◽  
Inspection System ◽  
Remaining Life ◽  
High Speed Railway ◽  
Inspection Method ◽  
Spiral Trajectory ◽  
Image Element ◽  
The Matrix

With the high speed railway utilization, the probability of defects or fatigue cracks in railway axles is increased. An automatic ultrasonic inspection system for railway axles is presented. This system uses combined probes and inspects the defects with spiral trajectory along the axis of the axle. Through the matrix representation of C-scan image element, a defect edge extraction method is adopted, with which the defect parameters of crack are obtained automatically. Based on these defect parameters, the stress intensity factor is assessed by svm regression and the method to predict remaining life is proposed.

scholarly journals Computer vision–based automatic rod-insulator defect detection in high-speed railway catenary system

2018 ◽  
Vol 15 (3) ◽  
pp. 172988141877394 ◽  
Author(s):  
Ye Han ◽  
Zhigang Liu ◽  
DJ Lee ◽  
Wenqiang Liu ◽  
Junwen Chen ◽  
...  
Keyword(s):  
Computer Vision ◽  
Defect Detection ◽  
High Speed ◽  
Power Transmission ◽  
Estimation Algorithm ◽  
Inspection System ◽  
High Speed Railway ◽  
Inspection Method ◽  
Railway Systems ◽  
Catenary System

Maintenance of catenary system is a crucial task for the safe operation of high-speed railway systems. Catenary system malfunction could interrupt railway service and threaten public safety. This article presents a computer vision algorithm that is developed to automatically detect the defective rod-insulators in a catenary system to ensure reliable power transmission. Two key challenges in building such a robust inspection system are addressed in this work, the detection of the insulators in the catenary image and the detection of possible defects. A two-step insulator detection method is implemented to detect insulators with different inclination angles in the image. The sub-images containing cantilevers and rods are first extracted from the catenary image. Then, the insulators are detected in the sub-image using deformable part models. A local intensity period estimation algorithm is designed specifically for insulator defect detection. Experimental results show that the proposed method is able to automatically and reliably detect insulator defects including the breakage of the ceramic discs and the foreign objects clamped between two ceramic discs. The performance of this visual inspection method meets the strict requirements for catenary system maintenance.

Online inspection system dedicated for OPC drum production

1998 ◽  
Author(s):  
Chuan-Yuan Chung ◽  
Wen-Chung Cheng ◽  
Wen-Ching Chao
Keyword(s):  
Inspection System ◽  
Online Inspection

A Study on the Laser Welding Characteristic and Welding Part Inspection Method

2014 ◽  
Vol 6 (9) ◽  
pp. 2051-2055
Author(s):  
Ka Ram Lee ◽  
Seung Hyun Choi ◽  
Sung Hyun Kim
Keyword(s):  
Laser Welding ◽  
Inspection Method ◽  
Welding Part ◽  
Part Inspection

Research about Online Inspection System for the Assembly Quality of Automobile Gearbox Sliding Bracket

2010 ◽  
Vol 152-153 ◽  
pp. 368-371
Author(s):  
Chun Dong Zhu ◽  
Fei Guo ◽  
Bo Wei
Keyword(s):  
Quality Management System ◽  
Good Condition ◽  
Quality Analysis ◽  
Inspection System ◽  
Central Control ◽  
Assembly Quality ◽  
Online Inspection ◽  
Qualification Rate ◽  
Central Control System

Gearbox sliding bracket is an important component of Automobile Gearbox. Because it has many parts which have little difference in shape and size, it is very easy to make mistake in assembly parts of this component. Due to mass production, it is high time to develop an online inspection system for the aseembly quality. Analysis the assembly characteristic of the component, this paper develop an online inspection system which is mainly composed of a central control system(CCS) and a sensor. Under the command of the CCS, the sensor is able to automatically inspect the component’s parts of which are wrong assmbly, reverse assembly and missing assmbly. Also the sensor can send the inspection information to the CCS. Subsequently, the CCS judges the information and dispalys the judgment result in time. At the same time, through the network, it is able to send the assembly quality information to the enterprise quality management system, such as the eligible amount, the reject amount, the qualification rate. This online automatic inspection system has run in good condition since it was officially put into operation at 2007 and its accuracy comes up to 100%.

Measurement of Trust in Humans in Hybrid Inspection for Different Levels of Error Randomness

2002 ◽  
Vol 46 (23) ◽  
pp. 1920-1924
Author(s):  
Neville Z. Ginwalla ◽  
Sittichai Kaewkuekool ◽  
Shannon R. Bowling ◽  
Anand K. Gramopadhye ◽  
Brian J. Melloy
Keyword(s):  
Experimental Designs ◽  
Inspection System ◽  
Four Levels ◽  
Inspection Tasks ◽  
Different Levels

The focus of this research is on the effect of human trust in a hybrid inspection system with different levels of error randomness. The experimental designs were developed to conduct inspection tasks with four levels of error randomness, and subjects were requested to rate their trust at different levels in the system. Each randomness level comprised of stages, and human trust variation for each stage was observed. These levels were administered through the use of a hybrid inspection simulator. Analysis of the results revealed that human trust in the hybrid inspection system is sensitive to error randomness.

Sign in / Sign up

Export Citation Format

Share Document