---

Biodiesel fuel, which is produced by transesterification reaction between alcohol and vegetable oil/animal fat is proposed as a clean alternative to petro diesel fuel. Today, one of the new technologies to produce biodiesel is using ultrasonic energy that makes production faster, with improved quality and less expensive. Various factors that affect the design of ultrasonic reactors are ratio of vibrating rod diameter to reactor diameter, reactor height, depth of horn penetration into fluid and chamber characteristics (material and shape). In this paper, two parameters namely the ratio of vibrating rod diameter to reactor diameter and reactor height were studied in order to increase the reaction efficiency. In all performed tests, the horn diameter of 14 mm, molar ratio of alcohol to oil of 5 to 1, catalyst concentration of 0.7% wt?? oil, depth of horn penetration into fluid of 15 mm and a cylindrical reactor were used. Experimental design involved the use of Central Composite Design (CCD) and the statistical Response Surface Methodology (RSM). Considering the empirical model, a significant relationship was found between independent and dependent variables with a regression coefficient of 0.99. Taking into account the desirability of increasing the efficiency, the optimal function of reactor diameter and reactor height were 63 and 110 mm, respectively with a reaction yield of 87%. In order to verify the model, function responses in the defined area were tested with five replicates and the average efficiency of the reaction was 87.2%. The obtained model suggests the simultaneous reverse effects of reactor diameter and height on the reaction efficiency.

---

A method based on Machine Vision System (MVS) is hereby employed to evaluate grape drying through an assessment of the fruit’s shrinkage and quality during the dehydration. Experimental data as well as captured images are obtained at an air velocity of 1.4 m s^-1 and different drying temperatures (50, 60, 70ºC). The results indicated the effect of temperature on the moisture content, shrinkage and color changes. The moisture content along with color changes (ΔE) were modeled and linear regressions applied to correlate the fruit’s shrinkage as well as color features to the moisture content. The results obtained, displayed that there existed good linear relationships between the fruit’s moisture content, and shrinkage as well as color. The results also revealed that the moisture content vs. quality of the grape could be online evaluated through machine vision during the drying process.

---

In this research, an intelligent method is introduced for remaining useful life prediction of an internal combustion engine timing belt based on its vibrational signals. For this goal, an accelerated durability test for timing belt was designed and performed based on high temperature and high pre tension. Then, the durability test was began and vibration signals of timing belt were captures using a vibrational displacement meter laser device. Three feature functions, namely, Energy, Standard deviation and kurtosis were extracted from vibration signals of timing belt in healthy and faulty conditions and timing belt failure threshold was determined. The Artificial Neural Network (ANN) was used for prediction and monitoring vibrational behavior of timing belt. Finally, the ANN method based on Energy, Standard deviation and kurtosis features of vibration signals was predicted timing belt remaining useful life with accuracy of 98%, 98% and 97%, respectively. The correlation factor (R2) of vibration time series prediction by ANN and based on Energy, Standard deviation and kurtosis features of vibration signals were determined as 0.87, 0.91 and 87, respectively. Also, Root Mean Square Error (RMSE) of ANN based on Energy, Standard deviation and kurtosis features of vibration signals were calculated as 3.6%, 5.4% and 5.6%, respectively.

---

In this research with utilization various neural networks models, the relationship between the amount of water production and the temperature of the vapor with different weather conditions, time of day and several water debit in desalination system equipped whit linear solar parabolic concentrator was investigated. The results showed that static and dynamic networks can be modeled the process of production fresh water with high accuracy. Static neural network can do the modelling process with higher speed than dynamic neural network. However it seems that the amount of error with using dynamic networks was reduced in process modeling. Coefficient of determination (R2) for training, validation and testing in static networks were 0.9898, 0.9899 and 0.9889, respectively. While coefficient of determination (R2) for training, validation and testing in dynamic networks were 0.9922, 0.9894 and 0.9901, respectively. Also the amount of mean square error (MSE) in static network for training, validation and testing was 0.0011, 0.0027 and 0.0024, respectively and for dynamic networks was 0.0018, 0.0007 and 0.0004, respectively. Comparison between dynamic and static networks show that the dynamic networks can be predicted the production of fresh water and vapor temperature according to changes in atmospheric parameters accurately than the static networks.

---

Determining the status of egg fertilization plays a major role in determining the quality of eggs and their products. In this regard, in order to achieve greater productivity and production, egg evaluation is considered necessary and important in terms of spermatogenesis. In this regard, spectroscopy was performed in the range of 0.01900 nm from 130 local egg samples in the direction of the main diameter for 3 days during the storage period. Spectrum data from spectrometers, in addition to sample information, include unwanted information and noise.  For this reason, in order to achieve accurate classification models, it is necessary to process spectral data before developing the appropriate model. In this regard, intelligent neural network classification was developed based on reference measurements and information of pre-processed spectra by combining different methods of smoothing, normalizing and increasing spectral separation power to determine the presence of sperm in the egg.  Classification results on day zero, first, second, warehousing with 72.3% accuracy, 73.1%, 75.5%, and detection, 86.31, 87.1%, 76% and sensitivity, respectively: 83 61%, 79.63% and 73.3% were obtained.

---

Sexing is a difficult task for most birds (especially ornamental birds) involving expensive, state-of-the-art equipment and experiments. An intelligent fowl sexing system was developed based on data mining methods to distinguish hen from cock hatchlings. The vocalization of one-day-old hatchlings was captured by a microphone and a sound card. To obtain more accurate information from the recordings, time-domain sound signals were converted into the frequency domain and the time-frequency domain using Fourier transform and discrete wavelet transform, respectively. During data-mining from signals of these three domains, 25 statistical features were extracted. The Improved Distance Evaluation (IDE) method was used to select the best features and also to reduce the classifier's input dimensions. Fowls’ sound signals were classified by Support Vector Machine (SVM) with a Gaussian Radial Basis Function (GRBF). This classifier identified and classified cocks and hens based on the selected features from time, frequency and time-frequency domains. The highest accuracy of the SVM at time, frequency and time-frequency domains was 68.51, 70.37 and 90.74 percent, respectively. Results showed that the proposed system can successfully distinguish between Hen and Cock hatchlings. The results further suggest that signal processing and feature selection methods can maximize the classification accuracy.