Using artificial intelligence strategies for process-related automated inspection in the production environment

This paper describes a prototype of a computing platform dedicated to artificial intelligence explorations. The platform, dubbed as PakCarik, is essentially a high throughput computing platform with GPU (graphics processing units) acceleration. PakCarik is an Indonesian acronym for Platform Komputasi Cerdas Ramah Industri Kreatif, which can be translated as “Creative Industry friendly Intelligence Computing Platform”. This platform aims to provide complete development and production environment for AI-based projects, especially to those that rely on machine learning and multiobjective optimization paradigms. The method for constructing PakCarik was based on a computer hardware assembling technique that uses commercial off-the-shelf hardware and was tested on several AI-related application scenarios. The testing methods in this experiment include: high-performance lapack (HPL) benchmarking, message passing interface (MPI) benchmarking, and TensorFlow (TF) benchmarking. From the experiment, the authors can observe that PakCarik's performance is quite similar to the commonly used cloud computing services such as Google Compute Engine and Amazon EC2, even though falls a bit behind the dedicated AI platform such as Nvidia DGX-1 used in the benchmarking experiment. Its maximum computing performance was measured at 326 Gflops. The authors conclude that PakCarik is ready to be deployed in real-world applications and it can be made even more powerful by adding more GPU cards in it.

Download Full-text

New Way of Monitoring of the Production Environment with Application of Augmented Reality and Artificial Intelligence

Multidisciplinary Aspects of Production Engineering ◽

10.2478/mape-2018-0039 ◽

2018 ◽

Vol 1 (1) ◽

pp. 307-313 ◽

Cited By ~ 1

Author(s):

Andrzej Szajna ◽

Janusz Szajna ◽

Roman Stryjski ◽

Josef Basl ◽

Jarosław Brodny

Keyword(s):

Artificial Intelligence ◽

Augmented Reality ◽

Mixed Reality ◽

Production Environment ◽

Virtual Objects ◽

The Future ◽

Augmented Reality Technology

Abstract Augmented reality technology (AR), also known as mixed reality, allows to enhance the seen reality with additional, virtual objects, displayed right in front of the user’s eyes. The article presents the concept of using Augmented Reality glasses, to support the user with pre-defined knowledge and instructions, giving the ability to do the job without almost any idea of what should be done. The operator simply follows the instructions shown in front of the eyes and communicate with the system with simple gesture and voice. Additionally, the article touches the topic of Artificial Intelligence (AI) which will allow the system in the future to have not only the pre-defined, hard coded instructions, but also the flexibility to give different hints to the user based on a different situation observed.

Download Full-text

Motion Capturing in Connection With Human Model Simulation and Artificial Intelligence AI for Employee Training in the Area of Joint-gentle Assembly Workflows in Production Environment

SSRN Electronic Journal ◽

10.2139/ssrn.3869762 ◽

2021 ◽

Author(s):

Beate Brenner ◽

Daniel Estler ◽

Vera Hummel

Keyword(s):

Artificial Intelligence ◽

Model Simulation ◽

Employee Training ◽

Human Model ◽

Production Environment ◽

Motion Capturing

Download Full-text

AUTOMATED INSPECTION OF FRUITS AND VEGETABLES

HortScience ◽

10.21273/hortsci.26.6.712b ◽

1991 ◽

Vol 26 (6) ◽

pp. 712B-712

Author(s):

C. Morrow ◽

P Heinemann ◽

H. Sommer ◽

R. Crassweller ◽

R. Cole ◽

...

Keyword(s):

Artificial Intelligence ◽

Image Processing ◽

Fruits And Vegetables ◽

Surface Defects ◽

Quality Score ◽

Inspection System ◽

Automated Inspection ◽

Monochromatic Image ◽

Manual Inspection ◽

Current Emphasis

Research is described on the development of an automated inspection system which uses digital images and artificial intelligence techniques. Procedures have been developed for evaluating size, shape, and color of apples, potatoes, and mushrooms. Current emphasis is being placed on developing algorithms for detection of surface defects. A major effort will also be expended toward the development of an overall “quality” score for automated inspection of fruit and vegetables. The automated results are compared with those obtained using conventional manual inspection methods. Apples, potatoes, and mushrooms are the primary crops being inspected although the algorithms and techniques are applicable to many different fruits and vegetables. Color and monochromatic image processing components in “MS-DOS” and “Macintosh” computers are being used in this study.

Download Full-text