Marko Hočevar

Estimation of number and diameter of apple fruits in an orchard during the growing season by thermal imaging

Abstract A new method for estimating the number of apple fruits and measuring their diameter in the orchard was developed and tested. A thermal camera captured images of apple trees five times during the vegetation period June–September 2001. Each time 120 images of twenty apple trees were recorded late in the afternoon to achieve a temperature gradient between fruits and their background. Recorded images were processed using several image processing algorithms. Correlation coefficients R 2 from 0.83 to 0.88 were established between the manually measured fruit number and the estimated number based on a fruit detection algorithm. According to fruit development and the established growing curve, the value of the correlation coefficient, R 2 , increased during the ripening period. For measuring the fruits diameter values of R 2 between 0.68 and 0.70 were established. These slightly increased according to the fruits colour and size development during the ripening period.

An Investigation of the Relationship Between Acoustic Emission, Vibration, Noise, and Cavitation Structures on a Kaplan Turbine

The goal of the study was to explain the relationship between different acoustic signals and visual appearance of cavitation. Measurements of acoustic emission, vibration, and noise were performed on a Kaplan turbine model, with only two blades, in a cavitating condition. Since a model with only two blades was used, most of the side effects were eliminated, and it was concluded that the cavitation itself is the source of the recorded signal. Results showed an interesting relationship between the extent of the cavitation and the recorded data from sensors. At a decreasing cavitation number, the recorded amplitudes from all measurements first rose, experienced a local maximum, then fell to a local minimum, and finally rose again. The cavitation was also visually observed. It was concluded from the measurements that there are distinct correlations between acoustic emission, vibration, and noise on one side and the topology, extent, and type of cavitation structures on the other side. A physical explanation for the phenomenon was introduced and included in a semi-empirical model that links the visual appearance of cavitation on the blade of the turbine to the generated noise and vibration.

Prediction of cavitation vortex dynamics in the draft tube of a francis turbine using radial basis neural networks

Application of radial basis neural networks (RBNN) for prediction of cavitation vortex dynamics in a Francis turbine draft tube is presented. The dynamics of the cavitation vortex was established by fluctuations of a void fraction in a selected region of the draft tube. The void fraction was determined by image acquisition and analysis. Pressure in the draft tube and images of the cavitation vortex were acquired simultaneously for the experiment. RBNN were used for prediction. The void fraction in the selected region of the cavitation vortex was predicted on the basis of experimentally provided pressure data. The learning set consisted of pressure – void fraction pairs. The prediction consisted in providing only the pressure. Regression coefficients r between the predicted and measured void fractions were in an interval of 0.82–0.98. A good agreement between power spectra and correlation functions of measured and predicted void fractions was shown.

Programmable Ultrasonic Sensing System for Targeted Spraying in Orchards

This research demonstrates the basic elements of a prototype automated orchard sprayer which delivers pesticide spray selectively with respect to the characteristics of the targets. The density of an apple tree canopy was detected by PROWAVE 400EP250 ultrasound sensors controlled by a Cypress PSOC CY8C29466 microcontroller. The ultrasound signal was processed with an embedded computer built around a LPC1343 microcontroller and fed in real time to electro-magnetic valves which open/close spraying nozzles in relation to the canopy structure. The analysis focuses on the detection of appropriate thresholds on 15 cm ultrasound bands, which correspond to maximal response to tree density, and this was selected for accurate spraying guidance. Evaluation of the system was performed in an apple orchard by detecting deposits of tartrazine dye (TD) on apple leaves. The employment of programmable microcontrollers and electro-magnetic valves decreased the amount of spray delivered by up to 48.15%. In contrast, the reduction of TD was only up to 37.7% at some positions within the tree crown and 65.1% in the gaps between trees. For all these reasons, this concept of precise orchard spraying can contribute to a reduction of costs and environmental pollution, while obtaining similar or even better leaf deposits.

Design and testing of an automated system for targeted spraying in orchards

The research aims to demonstrate the basic system elements of a prototype automated orchard sprayer, which can deliver pesticide spray selectively with respect to the characteristics of the targets. The shape of the apple tree canopy was detected by a machine vision system using an RGB camera and appropriate image analysis. Information captured by RGB camera and processed by specific software was fed in real-time to a spraying arm, with three individually controlled sections, which adapt the pesticide spray flow to the canopy shape. The system allows variation in the liquid flow rate and volume of chemicals by means of controlled electric valves, whereby the amount of spray depends on the shape of the tree crowns. The current project focuses on developing the critical elements for spraying an individual tree and evaluates them in independent field experiments with the use of water sensitive papers (WSP). The demonstrated concept of precise application of pesticide sprays supports decreasing of the amount of delivered spray, thereby reducing both costs and environmental pollution.ZusammenfassungDie Untersuchungen sollen grundlegende System-Elemente des Prototyps eines automatisierten Sprühgerätes darstellen, das geeignet ist, Pflanzenschutzmittel gezielt auf Zielobjekte auszubringen. Als Entscheidungs- und Steuerungselement wurde ein „Machine-vision-system” mit RGB-Kamera und nachfolgender Bildanalyse entwickelt und eingesetzt. Die Bildinformationen wurden in Echtzeit genutzt, um die drei verstellbaren Sprüheinheiten individuell hinsichtlich Ausbringmenge entsprechend der Kronenform zu steuern. Das System ermöglicht durch elektromagnetisch gesteuerte Ventile die Ausbringmenge entsprechend der Baumkronenform anzupassen. Das Projekt konzentrirt sich auf die Enwicklung der kritischen Elemente des Sprühgerätes zum Besprühung von einzelne Silhouetten in der Baumreihe. Das vorgestellte Konzept der genauen Anwendung von Pestiziden direkt auf die Baumkronen ist geeignet, die ausgebrachte Produktmenge und damit gleichzeitig auch Kosten und Umweltbelastungen zu reduzieren.

Experimental turbulent field modeling by visualization and neural networks

Turbulent flow field was modeled based on experimental flow visualization and radial-basis neural networks. Turbulent fluctuations were modeled based on the recorded concentration at various locations in the Karman vortex street, which were used as inputs and outputs of the neural network. From the measured and the modeled concentration the power spectra and spatial correlation functions were calculated. The measured and the modeled concentration power spectra correspond well to the -5/3 turbulence decay law, and exhibit the basic spectral peak of fluctuation power at the same frequency

Development of alternative plant protection product application techniques in orchards, based on measurement sensing systems

Sustainable application is a way to reduce harmful influence to the living environment.The establishment of an appropriate PPP dose expression in crop protection.Sensing systems for electronic canopy characterization.Decision-making models for controlling the dosage of PPP with the use of special algorithms. The development of alternative plant protection product (hereinafter PPP) application techniques in recent decades has been based on various principles of sprayer operation. So far, several researchers have tried with partial success to find a compromise (a uniform standard) to ensure continuous PPP application to selected tree canopies in an orchard. Researchers have offered certain solutions for controlling dosage rates of PPP, based on special measurement systems and decision-making models to optimize the dosage rate of PPP. With sensing systems for electronic canopy characterization, which originally functioned on the basis of ultrasound waving and later on the principle of spectral reflection, characteristics of tree canopies in an orchard could be adequately estimated. However, attention must be paid to the fact that discrepancies in the original measurement systems were too large, owing to imprecise operation of various sensor components. Nevertheless it is necessary to underline that advanced spectral laser technology is a strong tool for developers of alternative PPP application techniques, and with it, tree canopy properties are sensed in real time. So it is no longer a major problem in the precise application to establish the tree canopy properties, but to control artificial intelligence actuation, which in the future will properly direct the air flow and the dosage rate of PPP per tree canopy in the orchard.

Monitoring of the cavitation in the Kaplan turbine

The phenomena of cavitation in water machines usually causes mechanical damage to the vital parts of the turbine. Because cavitation is usually frequent and unpredictable, the development of a monitoring method is of great importance. Present methods for cavitation detection in water turbines are based on observation of pressure pulsations, acoustic emission and mechanical vibrations on the turbine casing. Changes of dynamic properties of the above variables enable empirical analysis and are measured for the presence of the cavitation and its consequences. On the vital parts of the turbine, a new method of cavitation detection was implemented. Cavitation, a two-phase phenomenon (gas flow in the liquid phase), can be optically established when using proper illumination of the control volume. A method of computer-aided visualization was used, which offers real time evaluation of the cavitation topological structures in the turbine flow field. A new method of cavitation monitoring was tested on a model Kaplan turbine where, besides the computer-aided visualization, various integral parameters were simultaneously observed. The procedure was tested and performed in different integral operational regimes. Results of the study indicate that visualization method is the most suitable for cavitation monitoring; further effort however should be made in this research sphere.

Modification of Axial Fan Flow by Trailing Edge Self-Induced Blowing

Blowing fans often show adverse flow conditions at the fan hub and at the tip of the blade. The modification of conventional axial fan blade is presented. Hollow blade was manufactured from the hub to the tip. It enables the formation of self-induced internal flow through internal passages. The internal flow enters the passage of the hollow blade through the opening near the fan hub and exits through the trailing edge slots at the tip of the hollow blade. The study of the influence of internal flow on the flow field of axial fan and modifications of axial fan aerodynamic characteristics is presented. The characteristics of the axial fan with the internal flow were compared to characteristics of a geometrically equivalent fan without internal flow. The results show integral measurements of performance testing using standardized test rig and the measurements of local characteristics. The measurements of local characteristics were performed with a hotwire anemometry and a five-hole probe. Reduction in adverse flow conditions near the trailing edge at the tip of the hollow blade, boundary-layer reduction in the hollow blade suction side, and reduction in flow separation were attained. The introduction of the self-induced blowing led to the preservation of external flow direction defined by the blade geometry, which enabled maximal local energy conversion. The integral characteristic reached a higher degree of efficiency. DOI: 10.1115/1.4000345

Reducing the noise emitted from a domestic clothes-drying machine

In recent years the development of large household appliances has increasingly focused on the reduction of noise. In this paper we report on attempts to reduce the sound-power level of an existing clothes dryer by investigating the aerodynamic noise sources. The critical points were determined on the basis of spatial sound-intensity measurements and sound-pressure-level spectra measurements. The changes to produce the modified dryer, version I, involved corrections to the secondary-flow fans inlet region. For version II a different design of the heat exchanger was considered. For this, a measurement station was set up in order to analyze the aerodynamic properties of heat exchangers. The velocity and the acoustic properties of the heat exchangers were measured to help in the selection of the heat exchanger in accordance with the aeroacoustics theory that connects turbulent fluctuations and noise generation. After performing all the modifications, the A - weighted total sound-power level was reduced from 76.0 to 66.5 dB for left rotation and from 73.8 to 64.7 dB for right rotation.