Search results

1 – 10 of over 21000
Article
Publication date: 15 November 2022

Jun Wu, Cheng Huang, Zili Li, Runsheng Li, Guilan Wang and Haiou Zhang

Wire and arc additive manufacturing (WAAM) is a widely used advanced manufacturing technology. If the surface defects occurred during welding process cannot be detected…

Abstract

Purpose

Wire and arc additive manufacturing (WAAM) is a widely used advanced manufacturing technology. If the surface defects occurred during welding process cannot be detected and repaired in time, it will form the internal defects. To address this problem, this study aims to develop an in situ monitoring system for the welding process with a high-dynamic range imaging (HDR) melt pool camera.

Design/methodology/approach

An improved you only look once version 3 (YOLOv3) model was proposed for online surface defects detection and classification. In this paper, improvements were mainly made in the bounding box clustering algorithm, bounding box loss function, classification loss function and network structure.

Findings

The results showed that the improved model outperforms the Faster regions with convolutional neural network features, single shot multibox detector, RetinaNet and YOLOv3 models with mAP value of 98.0% and a recognition rate of 59 frames per second. And it was indicated that the improved YOLOv3 model satisfied the requirements of real-time monitoring well in both efficiency and accuracy.

Originality/value

Experimental results show that the improved YOLOv3 model can solve the problem of poor performance of traditional defect detection models and other deep learning models. And the proposed model can meet the requirements of WAAM quality monitoring.

Article
Publication date: 2 August 2011

Chern‐Sheng Lin, Jung Kuo, Chi‐Chin Lin, Yun‐Long Lay and Hung‐Jung Shei

The purpose of this paper is to apply an on‐line automatic inspection and measurement of surface defect of thin‐film transistor liquid‐crystal display (TFT‐LCD) panels in…

Abstract

Purpose

The purpose of this paper is to apply an on‐line automatic inspection and measurement of surface defect of thin‐film transistor liquid‐crystal display (TFT‐LCD) panels in the polyimide coating process with a modified template matching method and back propagation neural network classification method.

Design/methodology/approach

By using the technique of searching, analyzing, and recognizing image processing methods, the target pattern image of TFT‐LCD cell defects can be obtained.

Findings

With template match and neural network classification in the database of the system, the program judges the kinds of the target defects characteristics, finds out the central position of cell defect, and analyzes cell defects.

Research limitations/implications

The recognition speed becomes faster and the system becomes more flexible in comparison to the previous system. The proposed method and strategy, using unsophisticated and economical equipment, is also verified. The proposed method provides highly accurate results with a low‐error rate.

Practical implications

In terms of sample training, the principles of artificial neural network were used to train the sample detection rate. In sample analysis, character weight was implemented to filter the noise so as to enhance discrimination and reduce detection.

Originality/value

The paper describes how pre‐inspection image processing was utilized in collaboration with the system to excel the inspection efficiency of present machines as well as for reducing system misjudgment. In addition, the measure for improving cell defect inspection can be applied to production line with multi‐defects to inspect and improve six defects simultaneously, which improves the system stability greatly.

Details

Assembly Automation, vol. 31 no. 3
Type: Research Article
ISSN: 0144-5154

Keywords

Article
Publication date: 1 March 1997

Abdulmohsen Al‐Hammad, Sadi Assaf and Mansoor Al‐Shihah

Outlines the defects and faults during the design stage that affect building maintenance in Saudi Arabia and their relative degree of importance. Performed a survey of a…

5290

Abstract

Outlines the defects and faults during the design stage that affect building maintenance in Saudi Arabia and their relative degree of importance. Performed a survey of a randomly selected sample of 90 contractors, 30 architectural/engineering firms (A/Es), and 20 owners from the Eastern Province of Saudi Arabia. The survey included 35 defects and the respondents were asked to indicate their degree of importance. The defects were grouped into six groups. The level of importance of the defects and the groups were measured and ranked by their severity index for contractors, owners and A/Es. The following results were obtained: contractors, A/Es and owners generally agree on the ranking of the individual defects; contractors and A/Es agree on the ranking of the defect groups whereas contractors and owners, A/Es and owners do not agree; the construction drawings group of defects was ranked highly by all three parties whereas the architectural design group of defects received a low ranking.

Details

Journal of Quality in Maintenance Engineering, vol. 3 no. 1
Type: Research Article
ISSN: 1355-2511

Keywords

Article
Publication date: 6 November 2017

Yunfeng Li and Shengyang Li

The purpose of this paper is to propose a defect detection method of bare printed circuit boards (PCB) with high accuracy.

Abstract

Purpose

The purpose of this paper is to propose a defect detection method of bare printed circuit boards (PCB) with high accuracy.

Design/methodology/approach

First, bilateral filtering of the PCB image was performed in the uniform color space, and the copper-clad areas were segmented according to the color difference among different areas. Then, according to the chaotic characteristics of the spatial distribution and the gradient direction of the edge pixels on the boundary of the defective areas, the feature vector, which evaluates quantitatively the significant degree of the defect characteristics by using the gradient direction information entropy and the uniform local binary patterns, was constructed. Finally, support vector machine classifier was used for the identification and localization of the PCB defects.

Findings

Experimental results show that the proposed algorithm can accurately detect typical defects of the bare PCB, such as short circuit, open circuit, scratches and voids.

Originality/value

Considering the limitations of describing all kinds of defects on bare PCB by using single kind of feature, the gradient direction information entropy and the local binary patterns were fused to build a feature vector, which evaluates quantitatively the significant degree of the defect features.

Article
Publication date: 18 July 2018

Ruidong Xie, Dichen Li, Bin Cui, Lianzhong Zhang and Feng Gao

Laser metal deposition (LMD) is an important additive manufacturing (AM) technology, but the metallurgical defects, such as cracks and porosities, produced in LMD process…

Abstract

Purpose

Laser metal deposition (LMD) is an important additive manufacturing (AM) technology, but the metallurgical defects, such as cracks and porosities, produced in LMD process will seriously affect the mechanical properties of the parts. The purpose of this paper is to propose a novel in-process defects detection method based on infrared scanning for LMD.

Design/methodology/approach

The defects detection principle is that, after every three to five layers have been deposited, the optical head of a high-precision infrared two-color pyrometer is driven to scan the defects by measuring the abnormal temperature peaks on the deposited surface. The experiments for verifying the defects detection principle were carried out.

Findings

The relationship between the temperature peak value and the dimensions of the defect was analyzed based on the heat conduction theory and curves of temperature peak value versus crack width or diameter of porosity.

Originality/value

This method can effectively improve the detection accuracy and the defects can be precisely located, which can meet the requirement of laser targeting re-melting and elimination of the defects.

Details

Rapid Prototyping Journal, vol. 24 no. 6
Type: Research Article
ISSN: 1355-2546

Keywords

Article
Publication date: 1 March 2017

Bong-Kuk Ko, Woo-Jung Lee and Jae-Hoon Lee

The purpose of this study is to understand what health and safety hazards low-income households are subject to by surveying the real conditions of the defective housing of…

Abstract

The purpose of this study is to understand what health and safety hazards low-income households are subject to by surveying the real conditions of the defective housing of low-income households, and to find improvement strategies. For this purpose, we visited the concentrated areas of the multi-dwelling unit (MDU) (also known as multi-family residential) housing in Jungwon-gu and Sujeong-gu in Seongnam City, Kyunggi-do, one of the representative areas in Korea with a massive distribution of the low-income class. Based on the survey data, the level of housing defects were comparison analyzed per income decile (decile 1, decile 2, deciles 3–4), and per housing location, in the categories of subsidence, cracks in the wall, delamination, water leakage/infiltration, condensation, and contamination. The housing condition per income class was more defective in the decile 2 households rather than in the decile 2 households, and in the substructure more than in the superstructure. Among the six defects, contamination problems, caused by sub-standard living conditions, were the most frequent cases. Structural defects, subsidence and cracks in the wall, were found in the main living areas—the bedrooms and the living rooms. It was confirmed in this study that the conditions of low-income housing are serious, and that it is necessary to explore specific countermeasures in the near future.

Details

Open House International, vol. 42 no. 1
Type: Research Article
ISSN: 0168-2601

Keywords

Article
Publication date: 12 March 2018

Jing Liu, Zhifeng Shi and Yimin Shao

Combined defects in ball bearings may be caused during the use or manufacturing process, which can significantly affect their vibration characteristics. The previous defect

Abstract

Purpose

Combined defects in ball bearings may be caused during the use or manufacturing process, which can significantly affect their vibration characteristics. The previous defect models in the literature can only describe single defects such as the surface waviness and localized defect. This paper aims to propose an in-depth understanding of radial vibrations of a ball bearing with the combined defect.

Design/methodology/approach

A dynamic model for a ball bearing with the combined defect including the surface waviness and localized defect on its races is proposed. The effects of the combined defect sizes on the radial bearing vibrations are investigated. The results from the proposed model considering the combined defect are compared with the available results from the previous methods considering the single defects.

Findings

The acceleration amplitude is significantly affected by the surface waviness, localized defect and the combined defect on its races. The effect of the combined defect on the acceleration amplitude is larger than that of the single defect. The amplitude and peak frequency of the spectrum of acceleration for the combined defect increases with the defect sizes. The RMS value of the accelerations for the combined defect increases with the combined defect sizes.

Originality/value

Consequently, the proposed model can predict more accurate and in-depth understanding of the radial vibrations caused by the combined defect in the ball bearing.

Details

Industrial Lubrication and Tribology, vol. 70 no. 2
Type: Research Article
ISSN: 0036-8792

Keywords

Article
Publication date: 27 May 2014

Zhijie Wen, Junjie Cao, Xiuping Liu and Shihui Ying

Fabric defects detection is vital in the automation of textile industry. The purpose of this paper is to develop and implement a new fabric defects detection method based…

Abstract

Purpose

Fabric defects detection is vital in the automation of textile industry. The purpose of this paper is to develop and implement a new fabric defects detection method based on adaptive wavelet.

Design/methodology/approach

Fabric defects can be regarded as the abrupt features of textile images with uniform background textures. Wavelets have compact support and can represent these textures. When there is an abrupt feature existed, the response is totally different with the response of the background textures, so wavelets can detect these abrupt features. This method designs the appropriate wavelet bases for different fabric images adaptively. The defects can be detected accurately.

Findings

The proposed method achieves accurate detection of fabric defects. The experimental results suggest that the approach is effective.

Originality/value

This paper develops an appropriate method to design wavelet filter coefficients for detecting fabric defects, which is called adaptive wavelet. And it is helpful to realize the automation of textile industry.

Details

International Journal of Clothing Science and Technology, vol. 26 no. 3
Type: Research Article
ISSN: 0955-6222

Keywords

Article
Publication date: 31 May 2011

S. Thirunavukkarasu, B.P.C. Rao, G.K. Sharma, Viswa Chaithanya, C. Babu Rao, T. Jayakumar, Baldev Raj, Aravinda Pai, T.K. Mitra and Pandurang Jadhav

Development of non‐destructive methodology for detection of arc strike, spatter and fusion type of welding defects which may form on steam generator (SG) tubes that are in…

Abstract

Purpose

Development of non‐destructive methodology for detection of arc strike, spatter and fusion type of welding defects which may form on steam generator (SG) tubes that are in close proximity to the circumferential shell welds. Such defects, especially fusion‐type defects, are detrimental to the structural integrity of the SG. This paper aims to focus on this problem.

Design/methodology/approach

This paper presents a new methodology for non‐destructive detection of arc strike, spatter and fusion type of welding defects. This methodology uses remote field eddy current (RFEC) ultrasonic non‐destructive techniques and K‐means clustering.

Findings

Distinctly different RFEC signals have been observed for the three types of defects and this information has been effectively utilized for automated identification of weld fusion which produces two back‐wall echoes in ultrasonic A‐scan signals. The methodology can readily distinguish fusion‐type defect from arc strike and spatter type of defects.

Originality/value

The methodology is unique as there is no standard guideline for non‐destructive evaluation of peripheral tubes after shell welding to detect arc strike, spatter and fusion type of welding defects.

Details

International Journal of Structural Integrity, vol. 2 no. 2
Type: Research Article
ISSN: 1757-9864

Keywords

Article
Publication date: 1 May 1939

Konrad Kornfeld

AN exceedingly careful control of the surface of aero‐engine parts has beyond doubt become an excellent habit both with manufacturers and those who are to use the engine…

Abstract

AN exceedingly careful control of the surface of aero‐engine parts has beyond doubt become an excellent habit both with manufacturers and those who are to use the engine. A crack on a new part, or one which will cause a fatigue failure in work—these are the defects looked for by inspectors during manufacture, overhaul, or repairs. Cracks are very frequent causes of accidents and this fear often underlies the rejection of parts which are only suspect but which might work quite well until normal wear and tear would cause them to exceed permissible tolerances. In many cases, electro‐magnetic examination or etching reveal defects on the surface of engine parts which cannot be defined: in such cases, for the sake of certainty the part is rejected on the ground that it is cracked or made from faulty material.

Details

Aircraft Engineering and Aerospace Technology, vol. 11 no. 5
Type: Research Article
ISSN: 0002-2667

1 – 10 of over 21000