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.

A benchmark study on housing defects in Victoria, Australia

The construction industry consists of many small businesses employing less than five people. A challenge to the construction industry is to ensure that the many small firms and sub-contractors keep producing quality housing to meet the needs of their customers and clients. In attempts to continually improve the quality of housing various policies and mechanisms have been adopted. These have included industry sponsored quality programs and industry administered builder registration. However, these attempts have failed because of consumer mistrust of industry-sponsored programs. In addition, these mechanisms have been introduced in isolation and not as a part of an integrated industry initiative that includes education and training from the trade to tertiary level construction management courses. This work contributes to knowledge through a detailed on-going study of housing quality and defects. This research identifies the common forms of defects, which occur in housing and their incidences. The overall aim of this paper is to report the identification of defects in housing and the establishment of benchmarks (or a baseline) for the incidence defects in various functional elements within a house. It also suggests the areas where defects are likely to occur. From the knowledge gained from the study, industry and governments may make informed decisions of where resources may be directed to the areas where it will be most beneficial both to the house builder and the end user (customer). For this to occur the findings of this research will be disseminated into the housing industry and eventually integrated into tertiary courses in building and construction
management.

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.

Seeding of single crystal superalloys--Role of seed melt-back on casting defects

Single crystal seeds of the nickel-base superalloy CMSX-4 have been partially melted in a temperature gradient and then quenched. Small islands of random orientation are observed throughout the melted-back semi-solid. These random orientations appear to be pinched-off secondary dendrite arms, but there is no evidence that they are transported ahead of the dendrite tips to nucleate stray grains during directional solidification.

Modelling of porosity defects in high pressure die casting with a neural network

High Pressure Die Casting (HPDC) is a complex process that results in casting defects if configured improperly. However, finding out the optimal configuration is a non-trivial task as eliminating one of the casting defects (for example, porosity) can result in occurrence of other casting defects. The industry generally tries to eliminate the defects by trial and error which is an expensive and error -prone process. This paper aims to improve current modelling and understanding of defects formation in HPDC machines. We have conducted conventional die casting tests with a neural network model of HPDC machine and compared the obtained results with the current understanding of formation of porosity. While most of our findings correspond well to established knowledge in the field, some of our findings are in conflict with the previous studies of die casting.

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.

Numerical modeling of interactions between a macro-crack and a cluster of micro-defects

The interactions between a macro-crack and a cluster of micro-defects are studied numerically by using a series of special finite elements each containing a defect. These special finite elements, which contain defects such as holes, cracks, and inhomogeneities, are developed based on the hybrid displacement, complex potential and conformal mapping techniques. These hybrid-type elements can be used together with the conventional finite elements without any difficulty. Thus, simple finite element models can be devised to study the interactions between a macro-crack and a cluster of micro-defects. In this paper, the mathematical and finite element modeling procedures for the study of the above-mentioned problems are presented.

Cultured muscle cells display defects of mitochondrial myopathy ameliorated by anti-oxidants

The mitochondrial DNA A3243G mutation causes neuromuscular disease. To investigate the muscle-specific pathophysiology of mitochondrial disease, rhabdomyosarcoma transmitochondrial hybrid cells (cybrids) were generated that retain the capacity to differentiate to myotubes. In some cases, striated muscle-like fibres were formed after innervation with rat embryonic spinal cord. Myotubes carrying A3243G mtDNA produced more reactive oxygen species than controls, and had altered glutathione homeostasis. Moreover, A3243G mutant myotubes showed evidence of abnormal mitochondrial distribution, which was associated with down-regulation of three genes involved in mitochondrial morphology, Mfn1, Mfn2 and DRP1. Electron microscopy revealed mitochondria with ultrastructural abnormalities and paracrystalline inclusions. All these features were ameliorated by anti-oxidant treatment, with the exception of the paracrystalline inclusions. These data suggest that rhabdomyosarcoma cybrids are a valid cellular model for studying muscle-specific features of mitochondrial disease and that excess reactive oxygen species production is a significant contributor to mitochondrial dysfunction, which is amenable to anti-oxidant therapy.

The effect of artificial defects on the compressive properties of hollow sphere cellular aluminium (HSCA)

Hollow sphere cellular aluminium (HSCA) samples were fabricated by bonding together two kinds of single aluminium hollow spheres with the same outside diameter of 4 mm but different wall thicknesses of 0.1 mm and 0.3 mm, in which the hollow spheres with the thinner sphere wall thickness were used as artificial defects. Four types of HSCA samples with the same relative density but various distributions of artificial defects were prepared by simple cubic packing. For comparing, HSCA sample without defective hollow spheres inside was also prepared. The effects of the distribution of the artificial defects on the deformation behaviours and mechanical properties were investigated by compressive tests. Results indicated that the nominal stress - nominal strain curve and the deformation behavior of the HSCA samples varied with the distribution of the artificial defects in spite of the same relative density. It is therefore suggested that the deformation behavior and mechanical property of cellular materials were also significantly affected by the distribution of defects. In particular, the plateau stress of the HSCA samples increased with the decrease in number of contact points between the normal hollow spheres and the defective hollow spheres in the loading direction during deformation.

Exposure to fumes and gases during welding operations

The exposure to fumes and gases is one of the hazards associated with welding operations. Apart from research conducted on the mechanism of fume and gas formation and the relationship between fume formation rates and common welding parameters, little is known about the exposure process during welding. This research project aimed to identify the factors that influence exposure, develop an understanding of their role in the exposure process and through this understanding formulate strategies for the effective control of exposure during welding. To address these aims a literature review and an experimental program was conducted The literature review surveyed epidemiological, toxicological and exposure data. The experimental program involved three approaches, the first, an evaluation of the factors that influence exposure by assessing a metal inert gas/mild steel welding process in a workshop setting. The second approach involved the study of exposure in a controlled environment provided by a wind tunnel and simulated welding process. The final approach was to investigate workplace conditions through an assessment of exposure and control strategies in industry. The exposure to fumes and gases during welding is highly variable and frequently in excess of the health based exposure standards. Exposure is influenced by a number of a factors including the welding process, base material, arc time, electrode, arc current, arc voltage, arc length, electrode polarity, shield gas, wire-to-metal-work distance (metal inert gas), metal transfer mode, intensity of the UV radiation (ozone), the frequency of arc ignitions (ozone), thermal buoyancy generated by the arc process, ventilation (natural and mechanical), the welding environment, the position of the welder, the welders stance, helmet type, and helmet position. Exposure occurs as a result of three processes: the formation of contaminants at or around the arc region; their transport from the arc region, as influenced by the entry and thermal expansion of shield gases, the vigorous production of contaminants, thermal air currents produced by the heat of the arc process, and ventilation; and finally the entry of contaminants into the breathing zone of the welder, as influenced by the position of the welder, the welders stance, helmet type, and the helmet position. The control of exposure during welding can be achieved by several means: through the selection of welding parameters that generate low contaminant formation rates; through the limitation of arc time; and by isolating the breathing zone of the welder from the contaminant plume through the use of ventilation, welder position or the welding helmet as a physical barrier. Effective control is achieved by careful examination of the workplace, the selection of the most appropriate control option, and motivation of the workforce.

Comparison of defects in houses constructed by owners and registered builders in Victoria 1988-1996

The lack of attention to quality control by house builders in the Australian State of Victoria has been a contentious issue for more than two decades. Ina an attempt to improve the quality of housing, various mechanisms such as voluntary and compulsory registration schemes have been adopted and discarded by industry-based organisations and government. While builders are encouraged to improve construction quality, little is known and published about the quality of housing produced by owner builders specifically during the seven year warranty period after construction is completed. With this in mind, this thesis presents research findings that compare the latent defects in houses built by owner builders with those of registered builders. Using inspection reports provided by Archicentre a sample of 1772 houses, of which 1002 were owner builders and 770 were registered builders

Hexavalent chromium in welding fume

Evaluates the current Australian Standard method (AS3853.1) for the determination of total hexavalent chromium (Cr(VI)) in stainless steel welding fume. Investigates the extraction kinetics of this Cr(VI) into a range of media. Develops an analytical method for the determination of Cr(VI) in acidic extract solutions and investigates the extraction of Cr(VI) under simulated in vivo conditions.