In this paper, a Non-dominated Sorting Genetic Algorithm-II (NSGA-II) based approach is presented for distribution System reconfiguration. In contrast to the conventional GA based methods, the proposed approach does not require weighting factors for conversion of multi-objective function into an equivalent single objective function. In order to illustrate the performance of the proposed method, 33-bus and 69-bus distribution networks have been employed which have led to the desired results.

Machine vision System is one of the emerging technologies for the quality assessment of agricultural products. Quality of agricultural products is a crucial factor in marketability. In this study, a device was fabricated and developed to evaluate the quality of strawberry using machine vision technology. Strawberry is a rich source of anthocyanins in the nature. Because of the beneficial effects of anthocyanins on health, especially due to its antioxidant, anticancer and anti-inflammatory activites, especial attention is paid to strawberry consumption. In the present study, the possibility of using image processing algorithms to determine the maturity of strawberry fruits based on color and its relationship with the features extracted by destructive methods (weight, antioxidants, sugar, chlorophyll and carotenoids) was evaluated. For this purpose, 12 single-channel color spaces were developed and 228 color features were extracted. To determine the most effective features, correlation analyses were performed between destructive and non-destructive properties at 5% confidence level. The results showed the color space R / (R G B) as the most desired space whose features including sweetness and mean resulted in correlation coefficients of 0. 93 and 0. 91, respectively with anthocyanins. In addition, the maturity of strawberry could be classified during different growth stages using machine vision with an accuracy of 90%.

The objective of this research was to develop a suitable method for color Sorting of fruits. Accordingly, a color-Sorting System was designed and a prototype developed and then tested. This System includes an optic head which is designed to develop a reflection of the fruit. Output of the head is then processed in an electronic control System which generates the appropriate signal for ejection or admittance of the fruit in accordance with its color. This is accomplished by sending the signal to an electrical ejector mechanism that effects the Sorting operation. Tests were conducted to check the System's performance and to study the effect of some such parameters as type of fruit and ambient light intensity on accuracy of the System. Results indicated that main and interaction effects of these parameters on accuracy are not significant. Hence, this System is suitable for Sorting of fruits, with its performance not being affected by either fruit type or ambient light intensity.

An automatic fruit color Sorting System should have high operation accuracy as well as high speed and capacity. In order to improve the accuracy, it is useful to investigate the effect of important parameters on System performance. The objective of this research is thus to determine the effects of fruit and machine parameters on detection and ejection accuracy of an optoelectronic tomato color Sorting machine. This System consists of an optic head which is designed to develop a reflection of the fruit. Output of the head is then processed in an electronic control System which generates the appropriate signal for ejection or admittance of the fruit in accordance with its color. This is accomplished by sending the signal to an electrical ejector mechanism that affects the Sorting operation. In this research, the effect of three independent variables on detection and ejection accuracy of the System has been evaluated. Independent variables and their levels are: percentage of green tomatoes (at three levels of 30%, 60% and 90%), the fruit size (at two levels of 4-6 and 6-8 cm), shape of tomatoes (spherical and ellipsoidal), and slope of the fruit conveyor System (at three levels of 20, 35 and 50 degrees). Results of performance tests indicated that this System could detect and sort red tomatoes from green, yellow and white ones. The evaluated data from this System show that the effect of color (percentage of green tomatoes among non-red ones), slope of the conveyor System, and tomato size on detection and ejection accuracy and interaction effects of color-size on color detection accuracy of the System were significant (p< 0.05). Based on the results, the highest level of accuracy in color detection for non-red tomatoes is associated with slopes lower than 50° and color-size combination 90% green – 4-6 cm size range. The highest ejection accuracy was achieved at slopes lower than 50°, 4-6cm size range, the highest green percentage (90%), and spherical shape of tomato.

Introduction: Pistachio nut is one of the most important agricultural products of Iran and it is priced due to the quality and type. One of the significant factors of pistachio cost is its type in terms of shell. Filled split pistachio nut has the most quality and is utilized as nuts, while the closed shell type has lower cost, at the same time is economically efficient in food industry such as confectionery.....

One of the efficient, cost-effective, and rapid methods for non-destructive quality evaluation of horticultural and agricultural products is the acoustic analysis response generated by impact. In this research, the possibility of using sound processing resulting from the collision of hazelnuts with a galvanized iron plate for separating large, medium, and small hazelnuts, as well as separating nutty and hollow types, has been investigated. First, hazelnuts were divided into four groups based on size: large, medium, small, and empty. The hazelnuts of each group were weighed to separate the nutty and hollow types from the composition. Based on this approach, a System was designed and developed using a single-impact method to generate sound from hazelnuts upon impact with an iron surface. Artificial intelligence techniques were employed to analyze and classify the product based on features extracted from their acoustic signals. Then, in order to take samples, all hazelnuts were dropped from a height of 35 and 45 cm and hit an iron plate. The sound of the collision was recorded by the microphone. The recorded data is taken from the time domain to the frequency domain by Fast Fourier Transform (FFT) and graded using the features obtained from the gradation. The results of audio tests show that by comparing the direct ratio of weight with amplitude and sound pressure level, a hazelnut that has a pass range of less than 0.121Pa, and a sound pressure level of less than 75.2 dB is hollow or has an immature kernels. The study also revealed that the drop height did not significantly affect the quality classification, and a height of 35 cm, along with a sound pressure level above 75.2 dB, yielded the best results for hazelnuts classification. The results of this research, in combination with the common methods of separating hazelnuts, show that acoustic response analysis as a non-destructive method of grading hazelnuts can reduce their damage in addition to increasing the speed and accuracy of calssification.