Научная статья на тему 'Machine vision in industry'

Machine vision in industry Текст научной статьи по специальности «Компьютерные и информационные науки»

CC BY
469
99
i Надоели баннеры? Вы всегда можете отключить рекламу.
Ключевые слова
МАШИННОЕ ЗРЕНИЕ / КОМПЬЮТЕРНОЕ ЗРЕНИЕ / АВТОМАТИЗАЦИЯ / РОБОТИЗАЦИЯ / 2D И 3D ВИЗУАЛИЗАЦИЯ

Аннотация научной статьи по компьютерным и информационным наукам, автор научной работы — Горгадзе Л. Н., Исраелян Г. М.

Машинное зрение одна из важнейших составляющих роботов на производстве. Этот инструмент позволяет улучшить не только качество товара, но и скорость его создания. В последнее время все больше отраслей используют роботов с 3D машинным зрением. Благодаря современному программному обеспечению управление этим инструментом стало легче и эффективнее. В этой статье описаны составные части машинного зрения в индустрии и алгоритм визуализации изображения.

i Надоели баннеры? Вы всегда можете отключить рекламу.
iНе можете найти то, что вам нужно? Попробуйте сервис подбора литературы.
i Надоели баннеры? Вы всегда можете отключить рекламу.

Текст научной работы на тему «Machine vision in industry»

_МЕЖДУНАРОДНЫЙ НАУЧНЫЙ ЖУРНАЛ «ИННОВАЦИОННАЯ НАУКА» №1/2018 ISSN 2410-6070_

УДК 004.732

L. Gorgadze

Don State Technical University H. Israelyan Don State Technical University Rostov - on - Don, the Russian Federation

MACHINE VISION IN INDUSTRY Abstract

Machine vision is one of the most important components of robots production. This tool allows you to improve the quality of goods and the creation speed. Recently, more and more industries are using 3D machine vision. Due to the modern software, this tool controlling has become easier and more efficient. The components of machine vision in the industry and the image visualization algorithm are described in this work.

Keywords

machine vision, computer vision, automation, robotics, 2D and 3D visualization

Л. Н. Горгадзе

Преподаватель каф.

«Научно - технический перевод и профессиональная коммуникация» Донской Государственный Технический Университет

Г. М. Исраелян

Студент первого курса факультета «Автоматизации,

Мехатроника и Управление»

Аннотация

Машинное зрение - одна из важнейших составляющих роботов на производстве. Этот инструмент позволяет улучшить не только качество товара, но и скорость его создания. В последнее время все больше отраслей используют роботов с 3D машинным зрением. Благодаря современному программному обеспечению управление этим инструментом стало легче и эффективнее. В этой статье описаны составные части машинного зрения в индустрии и алгоритм визуализации изображения.

Ключевые слова

Машинное зрение, компьютерное зрение, автоматизация, роботизация, 2D и 3D визуализация

Human capabilities are often lacking in production, the speed of performance and quality of work do not match the requirements of modern industry. People make mistakes and get tired, and some work cannot be done with the help of manual labor.

Machine vision is a young discipline in science and technology. This is a very useful tool for the industry, which is used in counting, sorting, quality control and many other tasks. Machine vision is a very useful tool, as costs are reduced, and reliability and quality are enhanced.

Cameras and computer systems that make up the machine vision system perform measurements with high accuracy and speed. Such advantages have led to the spread of machine vision in industry around the world. For example, in the food industry, technology has an important role in processes in which speed and accuracy are required. They help to provide a competitive advantage for manufacturers. Any product is tested for quality, packaging labeling. The pharmaceutical market needs vision systems that not only test the product, packaging, but also ensure the correct dosage of medicine.

The development of machine vision is associated with the development of optical systems. The development of modern optics began at the end of the 19th century, and a new era of optics, which was called the cyrillic image processing and machine vision systems, began in the 1980s.

_МЕЖДУНАРОДНЫЙ НАУЧНЫЙ ЖУРНАЛ «ИННОВАЦИОННАЯ НАУКА» №1/2018 ISSN 2410-6070_

Digital image processing involves extraction of information from an image, it is the backbone of machine vision systems. Digital images are the combinations of different light intensity level. Each point in a digital image is a representation of the pixel value that is solved that corresponds to x- and y- coordinates in the image plane; it determines the intensity at that point. Machine vision processes the image in real time, that is, processing occurs at the time the image is acquired. Thus, it represents a real image in real time. It extracts the 3D information from the 2D image of the object.

The use of machine vision has already been observed in various industries. An application designed for one purpose of machine vision can also be applied for another, but similar, purpose; for example, an application for sorting objects can also be used to track objects or geometric classification. [1]

For the last decade, computer vision has grown by leaps and bounds. New technologies have paved the way for creating modern image capture devices, such as high-resolution sensors and cameras. They are used to record the production processes-frequently from different angles-and-generate digital image. This means that production processes can be visually monitored and their strengths and weaknesses can be identified. The technology is fast: it process the digital image data in milliseconds, thus paving the way for real-time applications. In addition, machine vision is also influenced by robust identification processes and a high detection rate.

Technology plays an important role in the creation of new generation robots. A huge number of robots industrial robots have cameras with built-in machine vision. The preparation of such robots for different industries should be quick and convenient, without long preparation and cumbersome adjustment. Applications for machine vision should also be easily created with the help of special software. Its main element is the user interface, which helps the user in the program. They do not have to worry about complex programming tools, but use a convenient and readable display. Thus, machine vision applications can be created quickly and easily, without complex programming or in-depth knowledge of image processing. This is useful for all areas of industry that require new technologies in production.

The image forming apparatus may be separated from or in combination with the main image processing unit, in which case the combination is usually referred to as an intelligent camera or an intelligent sensor. [2]

The first step in any machine vision algorithm is image acquisition, in this process, the camera, lenses and lighting are specially designed to provide the differentiation that is required in further development. After receiving the image, its analysis begins, which is a sequence of processing processes, which gives the desired result. A sequence can start with tools such as filters that change the image, then extract the objects, then extract the data from those objects, and then report the data or compare them with the target values to create and report the results.

A large number of computer vision applications are solved using 2D visualization, applications that use 3D visualization are less common. The most famous method of 3D-visualization is triangulation based on scanning which uses the movement of a product or image during the process of image formation. This technology uses a laser (often IR) that scans the work piece one line at a time, and an imager that looks at each point generated. The imager and laser are located in known positions and (different) angles with respect to the product. Since the locations and angles of the imager and laser are known, this allows the processor to determine the position (in 3 -D space) of each point generated. This is done for one entire line. Then, as the imaging system or product is moved in a controlled "scanning" fashion, it repeats the process for the next line and hundreds or thousands of additional lines until the required portion of the work piece has been covered. All of the data is put together into a depth map 3 -D image of the scanned area of the product. [3]

The biggest problem for 3D MV imaging is time. Creating complex images is computationally intensive and therefore time consuming. So, it has been discovered in the past few years, and it has become a reality in the past. Contactless measurement and metrology.

Prosperous 3D applications depend on the software used, which is a decisive criterion. It must enable quick and precise 3D-deviation in measurement to allow for a quick on the verifiable object. [4]

The use of machine vision of robots in the industry became possible due to the emergence of modern manipulators. Their rigidity and accuracy, as well as a large number of controlled axes are very important. Different functions require different mechatronic systems, ranging from a simple capture mechanism to a robot that has a miniature finger pressure sensor, an intelligent grip and a vision sensor. The possibilities of machine vision can be

_МЕЖДУНАРОДНЫЙ НАУЧНЫЙ ЖУРНАЛ «ИННОВАЦИОННАЯ НАУКА» №1/2018 ISSN 2410-6070_

limited by the capabilities of manipulators. Therefore, during the design of robots with MV, it is very important to take into account the capabilities of modern manipulators. Caffaz and Cannata proposed the first prototype of the DIST - Hand dexterous gripper which is a 4 - fingered tendon driven device with 16 degrees of freedom. Park et al. (2003) developed a robotic gripper to enable control of both shape and vibration of thin - walled flexible payloads. The gripper was configured with multiple actuated fingers, which are comprised of linear actuators with. DC motors and laser proximity sensors. Lee et al. (2009) presented a service robot gripper, which has a miniaturized fingertip pressure sensor, a thumb, and two fingers. [5]

Automation and robotics is a key factor in improving productivity and competitiveness in the world of the markets, and in the automotive and pharmaceutical industries, where 100% inspection is critical. Using machine vision can save a lot of time and resources. With the latest systems, you can create systems that are not only inspectable but also handle the product. [4] References:

1. Bikarna Pokharel Machine vision and object sorting // HAMK University of applied sciences: May 2013. - Pages 1-2.

2. Machine Vision in IIoT by Maximilian Luckenhaus Quality Magazine, May 2016

3. 3-D Imaging: A practical Overview for Machine Vision by Fred Turek & Kim Jackson Quality Magazine, March 2014

4. http://www.ukiva.org/automated-inspection.html

5. HOLISTIC DESIGN OPTIMIZATION IN MECHATRONICS Грицай И. П., Якубов Б. Э. В сборнике: ТЕХНОЛОГИИ XXI ВЕКА: ПРОБЛЕМЫ И ПЕРСПЕКТИВЫ РАЗВИТИЯ сборник статей Международной научно-практической конференции:в 2 ч., 2017, С.4-7

© Gorgadze L., Israelyan H., 2018

УДК 67.02

И.В.Лещукова

студентка 5 курса Самарского национального исследовательского университета имени академика С.П.Королева, г. Самара, Российская Федерация

ПРИНЦИПИАЛЬНЫЕ ТЕХНОЛОГИИ ИЗГОТОВЛЕНИЯ АВИАЦИОННЫХ КОНСТРУКЦИЙ ИЗ КОМПОЗИЦИОННЫХ МАТЕРИАЛОВ: RTM И АВТОКЛАВНОЕ ФОРМОВАНИЕ

Аннотация

Конструкционные материалы во многом определяют высокий уровень современной авиационной техники, что связано с их высокой надежностью, весовой эффективностью, хорошими технологическими и эксплуатационными свойствами. В связи с ужесточением требований к эффективности летательных аппаратов, возрастают требования к материалам.

Новый уровень развития авиации в будущем могут обеспечить только принципиально новые материалы и технологии, так как традиционные уже исчерпали себя, дальнейшее их использование дает незначительные результаты при существенных затратах.

Ключевые слова Композиционные материалы, автоклавное формование, автоклав, «прямые» процессы, технология RTM

В настоящее время известно множество технологических процессов формования, применяемых в

i Надоели баннеры? Вы всегда можете отключить рекламу.