Automatic inspection of metallic surface defects using genetic algorithms

This paper is concerned with the problem of automatic inspection of metallic surface using machine vision. An experimental system has been developed to take images of external metallic surfaces and an intelligent approach based on morphology and genetic algorithms is proposed to detect structural defects on bumpy metallic surfaces. The approach employs genetic algorithms to automatically learn morphology processing parameters such as structuring elements and defect segmentation threshold. This paper describes the detailed procedures which include encoding scheme, genetic operation and evaluation function.

The proposed method has been implemented and tested on a number of metallic surfaces. The results suggest that the method can provide an accurate identification to the defects and can be developed into a viable commercial visual inspection system.

Machine vision system for automatic inspection of surface defects in aluminum die casting

A camera based machine vision system for the automatic inspection of surface defects in aluminum die casting is presented. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

Genetic learning based texture surface inspection

This paper presents a novel approach of visual inspection for texture surface defects. It is based on the measure of texture energy acquired by a kind if high performance 2D detection mask, which is learned by genetic algorithms. Experimental results of texture defect inspection on textile images are presented to illustrate the merit and feasibility of the proposed method.

Machine vision system for automatic inspection of surface defects in aluminium die casting

A machine vision system is presented for the automatic inspection of surface defects in aluminium die casting. The system uses a hybrid image processing algorithm based on mathematic morphology to detect defects with different sizes and shapes. The defect inspection algorithm consists of two parts. One is a parameter learning algorithm, in which a genetic algorithm is used to extract optimal structuring element parameters, and segmentation and noise removal thresholds. The second part is a defect detection algorithm, in which the parameters obtained by a genetic algorithm are used for morphological operations. The machine vision system has been applied in an industrial setting to detect two types of casting defects: parts mix-up and any defects on the surface of castings. The system performs with a 99% or higher accuracy for both part mix-up and defect detection and is currently used in industry as part of normal production.

Auditor independence: regulation, oversight and inspection

Much of what auditors do is unobservable. Indeed, what goes on in an audit has been described as ‘secret audit business’. Audits in this context are of financial reports and those financial reports are the representations of the management of those companies, not the auditors. The audits of financial reports are of value in that they provide a competent and independent (of auditee management) attestation of the validity of those management representations. This attestation lowers the ‘information risk’ for the users of these financial reports. There has been a marked increase in activity to regulate matters relating to independence. The proposals outlined in CLERP 9 are one example of this. The requirements in the United States under the Sarbanes-Oxley Act are a further example.

Audit firms operate in a highly regulated yet highly competitive market. Evidence exists to suggest that audit firms are active competitors in respect of audit pricing and competency, including specialist industry expertise. Until recently, there has been little or no observable evidence that audit firms compete in respect of independence. The issues as they relate to audit independence are complex. One issue is that threats to independence are frequently subtle and difficult to observe and measure. Hence, controlling the decisions that relate to them cannot rely solely on regulation which itself inevitably relies on crude definitions and imprecise measures. Additionally, further regulation may not achieve the desired end without other processes being but in place in tandem.

This paper argues that:

1. auditors of certain classes of companies (in particular, those that are publicly traded) should be provided with incentives or requirements to have observable processes on independence
2. the means of observability should be in the form of an inspection and review process focussing on issues critical to the audit, such as independence
3. expert persons not having a current or past financial interest in the firm or in the commercial outcomes of the review should be used in the inspection and review process
4. the review process should have wide-ranging powers of inspection to examine the policies, processes, structures and ‘culture’ of audit firms
5. the report of the inspection and review should be made public, unedited and in full, and in a timely fashion. The primary objectives of this proposal are to (1) make more transparent to the market for information the characteristics of the audit firms and their process to ensure audit independence, and (2) provide a rigorous oversight of independence decision-making by persons who have no commercial interest in the outcome of the decision.

Power and passion:remoulded teamwork in a plastics factory

Purpose: – The purpose of this paper is to document the progress made in a specified period and the experience of managers and staff in sustaining the high performance team approach in a plastics factory.

Design/methodology/approach: – Single-case analysis was conducted on data collected through semi-structured interviews and site observations made with two managers and one team of six in a multinational plastics manufacturer (Visy) headquartered in Australia.

Findings: – Based on the authors' experiences and literature review a successful high performance team requires clear targets and efficiency standards, communication, rules of behaviour, continual input of facts and feedback, and last but not least – recognition of successes.

Research limitations/implications: – The findings are based on observations and interviews conducted in one part of a multinational organization in Australia. No follow-up interviews could be undertaken to track the progress.

Originality/value: – No other similar study had been undertaken in this organisation documenting the experiences of a quality improvement team and its interactions with managers. The findings have practical implications for industrial and other kinds of organisations engaged in implementing quality improvements through enhanced teamwork.

Depth estimation of metallic objects using multiwavelets scale-space representation

The problem of dimensional defects in aluminum die-castings is widespread throughout the foundry industry and their detection is of paramount importance in maintaining product quality. Due to the unpredictable factory environment and metallic with highly reflective nature, it is extremely hard to estimate true dimensionality of these metallic parts, autonomously. Some existing vision systems are capable of estimating depth to high accuracy, however are very much hardware dependent, involving the use of light and laser pattern projectors, integrated into vision systems or laser scanners. However, due to the reflective nature of these metallic parts and variable factory environments, the aforementioned vision systems tend to exhibit unpromising performance. Moreover, hardware dependency makes these systems cumbersome and costly. In this work, we propose a novel robust 3D reconstruction algorithm capable of reconstructing dimensionally accurate 3D depth models of the aluminum die-castings. The developed system is very simple and cost effective as it consists of only a pair of stereo cameras and a defused fluorescent light. The proposed vision system is capable of estimating surface depths within the accuracy of 0.5mm. In addition, the system is invariant to illuminative variations as well as orientation and location of the objects on the input image space, making the developed system highly robust. Due to its hardware simplicity and robustness, it can be implemented in different factory environments without a significant change in the setup. The proposed system is a major part of quality inspection system for the automotive manufacturing industry.

Inspection of drop-weight impact damage in woven CFRP laminates fabricated by different processes

The influence of manufacturing process on the drop-weight impact damage in woven carbon/epoxy laminates was inspected by visual observation, dyepenetrant X-ray technique, and optical microscopy observation. The MTM56/ CF0300 woven quasi-isotropic laminates were fabricated by two processes: the autoclave and the Quickstep processes. Quickstep^TM is a novel composite manufacturing process, which was designed for the out-of-autoclave production of high-quality composite parts at lower cost. It utilizes higher heat conduction of fluid other than gas to transfer heat to components, which results in much shorter cure cycles. The laminates cured by this fast heating process showed different impact failure modes from those cured by the conventional autoclave process. The residual indentation in the top side of the Quickstep-cured laminates had a bigger diameter, but a smaller depth at the same impact energy level. Dye-penetrant X-ray revealed more intense and connected impact damage regions in the autoclave-cured laminates. Optical micrography as a supplementary method showed less severe matrix damage in the quickstep-cured laminates indicating a more ductile property of the resin matrix cured at a faster heating rate.