Today’s metrology equipment are complex cyber-physical systems, and as it is demonstrated in the cyber components contribute to controlling the inspection uncertainty no less than the hardware components. However, controlling the inspection uncertainties by only focusing on the hardware and the physical equipment is always limited and can become very expensive. The robust design of inspection equipment by modeling the deformations, displacements, vibration, and other sources of the imperfection of the components, or by creating mechanisms with the capabilities for self-calibration are among the major approaches in reducing the inspection uncertainty by improving the physical inspection components. Controlling the inspection uncertainty is always a challenging task in automated inspection. Automated inspection has been an important topic for many industries for the past decades, to allow a highly consistent, unaided inspection process while maintaining the desired levels of uncertainties and precision. Therefore, it is important that computers can be taught how to inspect a workpiece, as well as make important decisions about its quality, without the need for human intervention.Īs Industry 4.0 further becomes the norm for the manufacturing sector, employing intelligent inspection systems is required. The removal of human subjectivity from the inspection process could lead to better finished parts overall. Ideally, the human element could be removed entirely, and cyber intelligence could be used to determine whether a manufactured product is up to standards or not. Typically, inspection is a human-driven process that is conducted by using cyber-physical systems including Coordinate Metrology Machines (CMM), optical and tactile scanners, and vision systems. Digital metrology of the geometric and dimensional characteristics of the workpiece can be a very useful feature in this paradigm to assist the creation of knowledge about the process and product. Intelligence in these complex processes is generated based on accurate knowledge about the process. The fourth industrial revolution demands for intelligence in manufacturing when dynamic data collection and data analytics are needed to support learning the production condition, prognostics, and production health monitoring. The developed algorithm provides a fast and efficient method for noise reduction in optical coordinate metrology and scanning. The change in the standard deviation of point-plane distances is examined, and an optimal amount of noisy data is removed to reduce uncertainty in representing the workpiece. Utilizing a global statistic-based iterative approach, noise is gradually removed from the dataset at increasing percentages. This paper discusses a method for noise reduction and removal in datapoints resulting from scanning the reflective planar surfaces. As many on-line inspection paradigms require the use of optical sensors, this reflectivity can lead to large amounts of noise, rendering the scan inaccurate. The optical metrology-based inspection of highly reflective parts in a production line, such as parts with metallic surfaces, is a difficult challenge. On-line data collection from the manufactured parts is an essential element in Industry 4.0 to monitor the production’s health, which required strong data analytics.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |