Akademik Veri Yönetim Sistemi
2018 International Conference on Artificial Intelligence and Data Processing, IDAP 2018, Malatya, Türkiye, 28 - 30 Eylül 2018
Quality evaluation of agricultural products is most commonly conducted using destructive methods. Ripeness and maturity of fruits are determined by measuring internal and external characteristic of fruits. Destructive method enables to measure texture, color, sugar content etc. Destructive methods increase success rate of quality determination of fruits, however, it practically has many concerns about effectiveness, reliability and cost. Therefore, it is necessary to develop fast, portable and cost-effective techniques without harming fruits to meet demand of consumer for fresh and healthy fruits. Visual appearance is an important method to obtain external characteristic (size, color) of fruits for grading or sorting. This work aims to develop custom design non-destructive quality evaluation system to reduce conventional destructive quality evaluations processes of fruits. The developed system in this study for fruit quality determination consists of two parts: (a) volume estimation by automatic machine vision and (b) ultrasonic testing. Volume estimation part was finished by one of our previous study and in this study, we mostly focused on developing ultrasonic part of the system. The ultrasonic part consisted of a programmable bipolar remote pulser unit (Ultrasonar, US 100) with a frequency range between 1 Hz to 10 MHz, two of 55 kHz piezoelectric probes for ultrasonic signal transmission and reception, an oscilloscope, and a PC. Ultrasonic signal generated by US 100 was applied to fruits (tomato, apple, peach) by transmiter probe and sound waves that passthrough fruit was collected back by receiver probe. Correlation between ultrasonic parameters (velocity and attenuation) and fruits characteristic is evaluated for such fruits. However, our results showed that quality evaluation of fruits with ultrasonic testing is not expected as in literature.