The main reason for applying microclimate control in greenhouses is to achieve optimal growing environment. Because of its complexity, excessive control in greenhouses can adversely affect the growing crops. Moreover, we need an optimal ambiental control to accomplish these complicated objectives, including low emissions and reduced production costs. This paper describes one practical approach to the real-time control system in a greenhouse. Control system considers internal and external ambient factors related to the regulation process. Control system cyclically reads the data from the sensors and implements appropriate response on the actuator, based on required greenhouse conditions. Most challenging was the design of the control algorithm for this kind of process, due to a complexity of influential greenhouse variables.

Welded joints are analysed as critical regions in a pressure vessel in respect to structural failure due to the elastic-plastic fracture/crack growth. To assess structural integrity of pressure vessels used in chemical industry the risk based procedure has been introduced and applied in the case of a large spherical pressure vessel used as a vinyl-chloride monomer (VCM) storage tank in HIP Azotara Pancevo. The risk matrix has been used, taking into account the basic definition of risk, being the product of the probability and consequence, and applied to different regions of welded joints, having different mechanical properties, i.e. crack resistance. To estimate probability, the failure assessment diagram (FAD) has been used, as an engineering tool, defined according to the position of the operating point for different regions of the welded joint, relative to the critical point on the limit curve. Generally speaking, consequence is estimated based on pressure vessel parameters, or by detailed analysis of health, safety, business and security issues, but in the analysed case, the worst case scenario is assumed, with the highest consequence due to potential disaster for environment and fatalities.

The difference in draft force is analyzed for six different passes during longitudinal plowing of the plot. The force is measured indirectly using four strain transducers. Values of the force are obtained by calculation after previous calibration and...

Color sorting is a technological operation performed with the aim of classifying compliant and noncompliant agricultural products in large-capacity industrial systems for agricultural product processing. This paper investigates the application of the YOLOv3 algorithm on raspberry images as a method developed for the detection, localization, and classification of objects based on convolutional neural networks (CNNs). To our knowledge, this is the first time a YOLO algorithm or CNN has been used with original images from the color sorter to focus on agricultural products. Results of the F1 measure were in the 92–97% range. Images in full resolution, 1024 × 1024, produced an average detection time of 0.37 s. The impact of the hyperparameters that define the YOLOv3 model as well as the impact of the application of the chosen augmentative methods on the model are evaluated. The successful classification of stalks, which is particularly challenging due to their shape, small dimensions, and variations, was achieved. The presented model demonstrates the ability to classify noncompliant products into four classes, some of which are appropriate for reprocessing. The software, including a graphic interface that enables the real-time testing of machine learning algorithm, is developed and presented.

Food processing industry is moving forward to a full automation of all processes, especially in technological line segments which represent critical control points of food safety. One of these points is color sorting by using machine...