نوع مقاله : مقاله پژوهشی
نویسندگان
1 گروه مهندسی ماشینهای کشاورزی، دانشکدگان کشاورزی و منابع طبیعی دانشگاه تهران، دانشگاه تهران، کرج، ایران
2 استاد، گروه مهندسی ماشینهای کشاورزی، دانشکده مهندسی و فناوری کشاورزی، پردیس کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران
3 دانشیار، گروه مهندسی ماشینهای کشاورزی، دانشکدگان کشاورزی و منابع طبیعی دانشگاه تهران، دانشگاه تهران، کرج، ایران
چکیده
کلیدواژه‌ها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Chicken nugget is a popular processed form of chicken meat. Nugget’s special flavor and color are interesting for consumers. Healthy meat is an important quality factor of nuggets. In the production process, the nugget is deeply fried for 1 minute at 185 °C. So, oil quality has an important effect on the final quality and healthy aspects. In this research, for the first time, the meat and oil quality used in chicken nuggets was checked using automatic and non-destructive techniques including an electronic nose (E-nose) and machine vision system. Meat health (healthy and spoiled) and consumed oil (healthy and burnt) were considered quality indicators. After frying, the excess oil was removed, and then the samples were subjected to machine vision and electronic nose systems for quality evaluations. In this research, the optimum of important parameters in the E-nose and the required times for sensing and removing the odor were determined. Also, the sensors' response was investigated. Principal component analysis (PCA), linear discriminant analysis (LDA) and artificial neural network (ANN) were used to analyze and classify the data. The accuracy results of both machine vision and electronic nose systems were similar and healthy meat and healthy oil classes were detected with up to 90 % accuracy. The evaluation results of the E-nose were similar to the machine vision system. Therefore, the combination of the two methods can be used in the measurement of color and smell characteristics.
کلیدواژه‌ها [English]
Investigating meat and oil quality in chicken nuggets using electronic nose and image processing techniques
EXTENDED ABSTRACT
Automatic quality assessment of chicken nuggets is necessary due to the increase in consumers and market volumes. Also, the quality assessment methods should be fast, efficient, non-destructive, accurate and low-cost. This research instigates some quality characteristics of chicken nuggets using an electronic nose system for the detection of meat and oil health. Also, image processing performance is examined for quality assessment to provide an evaluation of color characteristics.
In this research nuggets were prepared based on industrial formulation and all required materials were obtained from standard research institutes. The deep frying process was carried out for one minute. To control the frying process temperature, a laboratory frying system was designed. The system consists of a pot, heating element, Arduino microcontroller, electric relay, temperature sensor module and netbook computer (mini laptop). Frying temperature was controlled with a PID controlling algorithm. The electronic nose system includes sensors, a sensor chamber, a sample chamber, pneumatic valves, a power supply, a pump, a data acquisition system and an oxygen gas source. In each test, the sample was placed in the chamber for 600 seconds to create a saturation of smell. Then, each E-nose test was performed in three steps: baseline correction, injection of sample smell into the sensor chamber and cleaning the sensors from the previous sample odor. In the first and third stages, oxygen gas is pumped to the sensor chamber for 120 and 60 seconds. In the second step, the nugget smell was pumped over the sensors for 120 seconds. The considered timings for each stage were obtained after several trials and errors and checking and monitoring the response of the sensors. The obtained E-nose data and image features were analyzed using PCA, LDA and ANN methods.
Artificial neural networks precisely distinguished healthy oil and healthy meat based on E-nose data. Healthy meat was separated and classified by LDA, PCA and ANN methods using E-nose with acceptable accuracy and LDA accuracy was higher than PCA and ANN. The E-nose data classification was associated with an accuracy of 90%,96% and 94% for PCA, LDA and ANN, respectively. It can be noted that 4 sensors MQ_138, MQ_136, MQ_135 and MQ_9 played an important role in modeling. Results showed for rearranging the sensor array, the MQ_3 sensor can be removed from the system. Also, image processing showed a good performance for detection of the healthy meat and healthy oil. PCA detected the healthy meat and oil using machine vision data with 88% and 88% accuracy, respectively.
The results showed that the E-nose system accurately detected healthy and spoiled meat as well as healthy and burnt oil in the production of chicken nuggets. This method provides a quick and efficient tool for quality evaluation in the formulation procedure and experiments in food engineering.
)