Nozzle Case Research Articles

Numerical study of nozzle erosion and its cascading impact on jet quality

Abstract Sediment erosion is one of the major factors affecting the overall efficiency of hydro-turbines working under sediment laden conditions. The erosion not only decreases the efficiency but also changes the flow characteristics. However, the research regarding the changes in flow characteristics due to erosion is limited. The objective of this study is to identify the changes in flow characteristics of a Pelton nozzle due to erosion. Particularly, in a Pelton turbine system, the nozzle and the bucket are the components that are mostly affected by the erosion. The flow in the nozzle is unaffected by the erosion in the bucket. Nonetheless, the overall flow characteristics in the bucket can be affected by nozzle erosion. The erosion in the nozzle decreases the jet velocity and make it bit more dispersed which eventually decreases its impact force on the bucket and eventually leads to the decrement in overall efficiency of the turbine. A numerical study was conducted to compare the pressure loss, jet diameter, velocity, and dispersion angle between eroded and uneroded nozzle. Some wavy perturbations were induced on the needle and nozzle casing of the reference uneroded case to create the eroded nozzle case. The CFD simulation was then performed in OpenFOAM using its inbuilt multiphase solver, incompressibleVoF (interFoam). It was observed that, with erosion the total pressure loss, jet diameter, and dispersion angle increases but the velocity of the flow decreases. If these changes in flow get detected during operation, it can be used to develop real-time condition monitoring system.

Numerical Simulation of Steam Jet Condensation Through a Triple Nozzle Submerged into a Subcooled Water Pool

Submerged steam jet condensation is widely applied in many industrial fields due to its high heat and mass transfer efficiency during the process of direct contact condensation (DCC). The injection of steam into a water pool usually passes through an array of nozzles. It is important to understand the interaction between neighboring jets from different nozzles. In this paper, two thermal resistance models for DCC are implemented into the computational fluid dynamics code ANSYS Fluent through a user-defined function. The triple steam nozzle cases, in which the inlet pressure ranges from 0.1 to 0.6 MPa, were investigated to understand the interaction of nozzles and their configuration as well as their mechanisms. The distributions of temperature, velocity, volumetric fraction, and pressure fields were analyzed for different cases. Furthermore, the plumes of steam jets always attract each other toward the center of the plumes, and when the inlet pressure is over 0.3 MPa, the mixing of neighboring steam plumes will occur. In addition, the location where the peak value occurs for the parameters of steam velocity, pressure, and temperature, etc. is getting closer and closer to the center of the flow domain. In addition, the curve of the pressure along the centerline of the nozzle verified the existence of compression and expansion of steam inside the plume.

Cleaning performance improvement of a cone filter cartridge using a Venturi nozzle

To address the problem of the insufficient regeneration of dust filter cartridges, a Venturi nozzle is introduced to improve the cleaning performance. The jet distance, cone height, and compressed air pressure effects on the pulsed-jet pressure distribution were experimentally investigated. Changes in the filtration pressure drop, fallen dust mass, and dust emission were also studied. As the jet distance increased, the pulsed-jet pressure and the total pulsed-jet intensity first increased and then decreased for both cases of common and Venturi nozzles, but the pulsed-jet uniformity increased. In the Venturi nozzle case, the pulsed-jet pressure in the lower section of the cartridge was effectively increased due to the larger induced airflow. As the cone height increased, the pulsed-jet pressure in the lower section of the cartridge decreased and that in the upper section increased for both nozzle cases. The dust filtration-cleaning experiment showed that the Venturi nozzle improved the operation performance of the dust collector.

Numerical analysis of thermal and hydrodynamic characteristics in aquaculture tanks with different tank structures

Improving hydrodynamic performance by changing the geometries of aquaculture tanks can facilitate salmon growth. Thus, this study proposed to redesign the aquaculture tank by varying the tank shape, numbers of inlets, and nozzle angles. The hydrodynamic and thermal characteristics of an aquaculture tank were numerically investigated via computational fluid dynamics simulations. The results indicated that the circular tanks mixed better than the octagonal tanks. Secondary vortices were more extensive in a two-inlet than a one-inlet tank. The vortex column in a two-inlet tank was smaller than that in the one-inlet tank. Therefore, the mixing performance of the two-inlet tank was better than that of the one-inlet tank. Further, the flow uniformity could be improved by optimizing the nozzle angle. Consequently, the mixing performance of the radial nozzle tank was better than that of the tangential nozzle tank because the secondary vortices were prominent and vortex column was smaller. A comparison of all the cases revealed the flow uniformity of the radial nozzle case was the highest. The volume percentages corresponding to the suitable velocity for salmon growth and velocity uniformity were 52.27% and 0.878, respectively. Furthermore, the vortex size was reduced and the velocity uniformity was increased by 2.23% by changing the nozzle angle to a radial angle. Therefore, changing the nozzle angle along the radial direction better improved the hydrodynamic characteristics.

Improved Pulsed-Jet Cleaning of Cone Filter Cartridges Using an Annular-Slit Nozzle

There is a problem with the insufficient cleaning of the dust filter cartridge by the pulsed-jet cleaning method. This paper examines the improvement in the pulse-jet performance of cone filter cartridges achieved by using an annular-slit nozzle. Off-line pulse jet experiments were conducted to study the influence of initial compressed air pressure, jet distance, and Venturi tube on injection pressure. This paper compared the filtration performance of conventional nozzles versus slit nozzles by conducting an online dust filtration-cleaning experiment and investigating the effect of a Venturi tube. The results demonstrated that the jet produced by the slit nozzle had a bigger surface area in contact with the surrounding air, enhancing the entrainment effect, boosting the overall pulsed-jet pressure, and significantly elevating the pressure in the upper and middle section of the cartridge, particularly in the upper section. In both common nozzle and slit nozzle cases, the pulsed-jet intensity initially increased and then decreased with the jet distance. The corresponding optimal jet distances were 500 mm and 400 mm, respectively. The slit nozzle provoked an increment of 16% and 44% in the pulsed-jet intensity and uniformity (to 619 Pa and 0.19), respectively. And there was an 8% reduction in residual pressure drop, a 6% improvement in fallen dust mass, and a 7% improvement in comprehensive filtration performance. The fallen dust mass produced by a single cleaning of the slit nozzle was 0.64 kg and the comprehensive filtration performance was 0.18. While the addition of a Venturi tube improved the cleaning of the filter cartridge, it also led to a higher filtration pressure drop in the dust collector and reduced comprehensive filtration performance.

Study on Multiphase Flow Characteristics During RH Refining Process Affected by Nonradial Arrangement of Gas‐Blowing Nozzle

Bath stirring, degassing, and decarburization in steel refining are strongly related to flow behaviors. The bubble plume produced in Ruhrstahl–Heraeus (RH) up‐snorkel plays an important role during refining, since it not only acts as a bubble pump, but also provides the reaction interface. Herein, it is aimed to form a new flow pattern in the up‐snorkel by using a nonradially arranged gas‐injection nozzle to enhance the 260 ton RH refining process. The results show that an upward spiral steel flow is produced, when nonradial gas‐injection nozzles are used in the up‐snorkel. Meanwhile, some bubbles moved toward the center region of the up‐snorkel, which may be caused by the centripetal effect in a rotational steel flow. This leads to a more uniform bubble distribution on the cross section of the snorkel, compared to that of the conventional case. Specifically, the circulation flow rate is increased by about 18.0%, and the mixing time are shortened by about 26.2% (criteria of ±5%), compared to that of the conventional case. In addition, the inclusion removal rate is increased by 0.5%, 4.8%, and 11.3% for the inclusion size of 20, 50, and 100 μm, respectively, compared to the conventional radial nozzle case.

Thrust characteristics of nano-carbon/Al/oxygenated salt nanothermites for micro-energetic applications

Combustion within small motors is key in the application-specific development of nanothermite-based micro-energetic systems. This study evaluates the performance of nanothermite mixtures in a converging-diverging nozzle and an open tube. Mixtures were prepared using nano-aluminum (n-Al), potassium perchlorate (KClO4), and different carbon nanomaterials (CNMs) including graphene-oxide (GO), reduced GO, carbon nanotubes (CNTs) and nanofibers (CNFs). The mixtures were packed at different densities and ignited by laser beam. Performance was measured using thrust measurement, high-speed imaging, and computational fluid dynamics modeling, respectively. Thrust, specific impulse (ISP), volumetric impulse (ISV), as well as normalized energy were found to increase notably with CNM content. Two distinctive reaction regimes (fast and slow) were observed in combustion of low and high packing densities (20% and 55%TMD), respectively. Total impulse (IFT) and ISP were maximized in the 5% GO/Al/KClO4 mixture, producing 7.95 mN·s and 135.20 s respectively at 20%TMD, an improvement of 57% compared to a GO-free sample (5.05 mN·s and 85.88 s). CFD analysis of the motors over predicts the thrust generated but trends in nozzle layout and packing density agree with those observed experimentally; peak force was maximized by reducing packing density and using an open tube. The numerical force profiles fit better for the nozzle cases than the open tube scenarios due to the rapid nature of combustion. This study reveals the potential of GO in improving oxygenated salt-based nanothermites, and further demonstrates their applicability for micro-propulsion and micro-energetic applications.

Improving a rotating steel milling tool cooling by an air jet impingement flow

Turbulent jets impacting flat or curved surfaces have been the subject of several research reports in the literature over the past decades, and it is all about the improvement of localized heat and/or mass transfer in part of a system, to achieve this goal, it is necessary to understand the dynamic behavior of the fluid and its effect on local heat and/or mass transfer. The aim of our work is the numerical investigation of a steel milling tool cooling driven in rotation, emitting a heat flux caused by machining a surface, using an impacting cold air jet; Although the technology of cooling the machining tools exists by using liquid jets, it signaled that it is less economical and efficient then using the impinging air jet. The milling tool is cooled using forced convection produced by the air jet at different Reynolds numbers, this phenomenon is governed by the equations of conservation of mass, momentum, and energy. We adopted a mathematical model based on the finite volume method; the calculation code was validated using experimental results available in the literature. We obtained our results by varying the Reynolds number between 12,000 and 26,000 values for an impact distance ratio h/D = 4, and two configurations: one nozzle and two nozzles. Our results showed that when using two cold air jet inlets to cool the milling tool, the distribution of the Nusselt number on the surface is enhanced compared to the one nozzle case, mainly because of the two impact points of the jet on the surface. We also note that increasing the Reynolds number has a significant influence on the distribution of the averaged Nusselt number.

Numerical Study of Free Liquid Jet Primary Breakup Phenomenon in Still Gases

The present paper consists of a numerical investigation carried out for primary break up analysis of a vertical water jet. Many parameters impact the flow development such as velocity, turbulence and nozzle shape. In this work, two types of nozzle geometries have been performed, the first is a capillary circular and the second is conical. The calculations have been performed using the CFD Code Fluent of ANSYS, considering laminar and turbulent flow regimes. While turbulence was modelled using RNG k-ε of RANS approach. The main results show that the jet evolves differently in the two considered nozzle geometries comparing the jet intact lengths, drop sizes and distance between successive drops. It is observed that the turbulence increases substantially the jet intact length and enables the jet breakup at the lower part of the water column. For the conical nozzle case, the jet instabilities grow quickly resulting a drop size in the same order of the jet diameter and an intact length larger in comparison with the circular nozzle case.

Film Cooling in Gas Turbine and Nozzle.

A gas turbine is a rotating engine that generates its power through the flow of combustion gases. With either an axial or centrifugal compressor, air from the surrounding environment is drawn into the engine intake, where it is compressed and heated before being sent to combustion chamber. Every gas turbine engine has a nozzle as a standard part. Among its many responsibilities include propelling the engine forward, returning exhaust gases to the free stream, and regulating mass flow through the engine. When the power turbine's exhaust exits, the nozzle is directly in the direction of the fumes. Simply put, nozzles are just tubes that allow hot gases to flow through them; they're not much more complicated than that. The highest point on each of these deals is around 2500 kelvin. This research illustrates the film cooling method for gas turbine and nozzle longevity. For film cooling to work, the temperature of the airfoil and nozzle case must be decreased.

Inverse Design of Nozzle Using Convolutional Neural Network

A new approach based on convolutional neural network (CNN) technology is proposed for efficient inverse design of nozzle that can be designed according to the required pressure distribution. The regularization term is proposed to improve the smoothness of the nozzle configuration generated by the CNN. Firstly, the details of CNN technology are introduced. Secondly, the details of the numerical method are presented, including code validation and gird resolution study. Thirdly, the nozzle dataset is obtained using the design of experiments method. Then, the regularization for nozzle contour smoothness is considered and the weight of the regularization term is discussed. Finally, the nozzle cases are predicted to show the effectiveness of the proposed model. The results show that the proposed model can obtain the required nozzle configuration accurately, and the mean square error and mean absolute error are and , respectively. Besides, the smoothness of the nozzle configuration can be improved using the proposed regularization term in the training process. The average relative errors between the required and predicted pressure distribution are less than 10% under satisfying smoothness. Therefore, the nozzle configuration can be predicted using the proposed model under the required pressure distribution.

Oscillation mitigation of hyperbolicity-preserving intrusive uncertainty quantification methods for systems of conservation laws

In this article we study intrusive uncertainty quantification schemes for systems of conservation laws with uncertainty. While intrusive methods inherit certain advantages such as adaptivity and an improved accuracy, they suffer from two key issues. First, intrusive methods tend to show oscillations, especially at shock structures and second, standard intrusive methods can lose hyperbolicity. The aim of this work is to tackle these challenges with the help of two different strategies. First, we combine filters with the multi-element approach for the hyperbolicity-preserving stochastic Galerkin (hSG) scheme. While the limiter used in the hSG scheme ensures hyperbolicity, the filter as well as the multi-element ansatz mitigate oscillations. Second, we derive a multi-element approach for the intrusive polynomial moment (IPM) method. Even though the IPM method is inherently hyperbolic, it suffers from oscillations while requiring the solution of an optimization problem in every spatial cell and every time step. The proposed multi-element IPM method leads to a decoupling of the optimization problem in every multi-element. Thus, we are able to significantly decrease computational costs while improving parallelizability. Both proposed strategies are extended to adaptivity, allowing to adapt the number of basis functions in each multi-element to the smoothness of the solution. We finally evaluate and compare both approaches on various numerical examples such as a NACA airfoil and a nozzle test case for the two-dimensional Euler equations. In our numerical experiments, we observe the mitigation of spurious artifacts. Furthermore, using the multi-element ansatz for IPM significantly reduces computational costs.

Numerical Study of Spray-Induced Turbulence Using Industrial Fire-Mitigation Nozzles

A numerical investigation of the spray-induced turbulence generated from industrial spray nozzles is carried out to better understand the roles of the nozzle spray on the fires or explosions in different accidental scenarios. Numerical simulations are first validated against experimental data in the single nozzle case using the monodisperse and polydisperse assumption for droplet diameters. The polydispersion of the nozzle spray is proven to be necessary to correctly predict the gas and droplet velocities. The turbulent kinetic energy has dominant values inside the spray cone, decreases rapidly with the vertical distance from the spray nozzle, and is strongly affected by the spray droplet diameter. On the contrary, the integral length scale is found to have high values outside the spray cone. Two interacting sprays injected from different nozzles are then investigated numerically using the validated polydisperse model. The water sprays generated from such industrial nozzles can generate turbulence of high intensity in the near-nozzle region, and this intensity decreases with the distance from the nozzles. A better understanding of the turbulence generated by the spray system can be beneficial for the evaluation of several important phenomena such as explosion enhancement. The guideline values obtained from this investigation of single and double nozzles can be useful for large-scale numerical simulations.

Effects of ambient pressure and nozzle diameter on ignition characteristics in diesel spray combustion

Numerical simulations are performed to investigate the effects of ambient density (ρam) and nozzle diameter (Dnoz) on the ignition characteristic of diesel spray combustion under engine-like conditions. A total of nine cases which consist of different ρam of 14.8, 30.0, and 58.5 kg/m3 and different Dnoz of 100, 180, and 363μm are considered. The results show that the predicted ignition delay times are in good agreement with measurements. The current results show that the mixture at the spray central region becomes more fuel-rich as Dnoz increases. This leads to a shift in the high-temperature ignition location from the spray tip towards the spray periphery as Dnoz increases at ρam of 14.8 kg/m3. At higher ρam of 30.0 and 58.5 kg/m3, the ignition locations for all Dnoz cases occur at the spray periphery due to shorter ignition timing and the overly fuel-rich spray central region. The numerical results show that the first ignition location during the high-temperature ignition occurs at the fuel-rich region at ρam⩽30.0 kg/m3 across different Dnoz. At ρam=58.5 kg/m3, the ignition occurs at the fuel-lean region for the 100 and 180μm cases, but at the fuel-rich region for the 363μm nozzle case. This distinctive difference in the result at 58.5 kg/m3 is likely due to the relatively longer ignition delay time in the 363μm nozzle case. Furthermore, the longer ignition delay time as Dnoz increases can be related to the higher local scalar dissipation rate in the large nozzle case.

Pressure Control of High Pressure Tubing Based on Fluid Mechanics

This paper studies the problem of the constant pressure control for high pressure tubing. The main factors affecting the pressure change in high pressure oil pipe are the opening time of check valve and the cam angular velocity. Based on the theory of fluid mechanics, ordinary differential equation and Fourier series, the flow-pressure model and pressure-cam angular velocity model are established, respectively. Furthermore, the above model is extended to the case of multiple nozzles. These three models accurately express the functional relationship between the fuel flow rate, the pressure in the tubing and the cam angular velocity. According to the established models, the pressure in the high-pressure oil pipe can be accurately controlled by adjusting some parameters. Finally, a simulation example is given to verify the effectiveness of the proposed method.

Experimental Assessment on Exploiting Low Carbon Ethanol Fuel in a Light-Duty Dual-Fuel Compression Ignition Engine

Compression ignition (CI) engines are widely used in modern society, but they are also recognized as a significative source of harmful and human hazard emissions such as particulate matter (PM) and nitrogen oxides (NOx). Moreover, the combustion of fossil fuels is related to the growing amount of greenhouse gas (GHG) emissions, such as carbon dioxide (CO2). Stringent emission regulatory programs, the transition to cleaner and more advanced powertrains and the use of lower carbon fuels are driving forces for the improvement of diesel engines in terms of overall efficiency and engine-out emissions. Ethanol, a light alcohol and lower carbon fuel, is a promising alternative fuel applicable in the dual-fuel (DF) combustion mode to mitigate CO2 and also engine-out PM emissions. In this context, this work aims to assess the maximum fuel substitution ratio (FSR) and the impact on CO2 and PM emissions of different nozzle holes number injectors, 7 and 9, in the DF operating mode. The analysis was conducted within engine working constraints and considered the influence on maximum FSR of calibration parameters, such as combustion phasing, rail pressure, injection pattern and exhaust gas recirculation (EGR). The experimental tests were carried out on a single-cylinder light-duty CI engine with ethanol introduced via port fuel injection (PFI) and direct injection of diesel in two operating points, 1500 and 2000 rpm and at 5 and 8 bar of brake mean effective pressure (BMEP), respectively. Noise and the coefficient of variation in indicated mean effective pressure (COVIMEP) limits have been chosen as practical constraints. In particular, the experimental analysis assesses for each parameter or their combination the highest ethanol fraction that can be injected. To discriminate the effect on ethanol fraction and the combustion process of each parameter, a one-at-a-time-factor approach was used. The results show that, in both operating points, the EGR reduces the maximum ethanol fraction injectable; nevertheless, the ethanol addition leads to outstanding improvement in terms of engine-out PM. The adoption of a 9 hole diesel injector, for lower load, allows reaching a higher fraction of ethanol in all test conditions with an improvement in combustion noise, on average 3 dBA, while near-zero PM emissions and a reduction can be noticed, on the average of 1 g/kWh, and CO2 compared with the fewer nozzle holes case. Increasing the load insensitivity to different holes number was observed.

Fast and Accurate Analysis of Steam Condensing Flows Using Ideal Gas Equation

AbstractWhen the steam is used in fluid machinery, the phase-transition can occur and it affects not only the flow fields but also the machine performance. Therefore, to achieve accurate prediction on steam condensing flow using computational fluid dynamics, the phase-transition phenomena should be considered and the proper model which can reflect the non-equilibrium characterisic is required. In the previous study of us, a non-equilibrium condensation model was implemented in T-flow, and several cases on nozzles and cascades were under the consideration. The model showed quite good predictions on the pressure variations including condensation shock. However, the pressure discrepancies in downstream regions were found in all nozzle cases, and the use of ideal gas law as equation of state seemed to be responsible for them. Therefore, IAPWS-95 or IF97 are usually adopted for wet-steam codes, but it entails highly increased computational costs. In this study, the wet-steam model is modified to ensure the accuracy of pressure in nozzle’s downstream region while maintaining the usage of ideal gas equation, which has a benefit to solve the problem quickly. The numerical results of the nozzles are compared with those of the previous wet-steam model, and the results of equilibrium condensation model are also appended. As a result, the accurate predictions are feasible by using the modified non-equilibrium condensation model. In addition, the corrections on liquid surface tension and droplet growth rate are carried out for underestimated droplet sizes and enthalpy, entropy changes throughout the nozzles are investigated.

Real Gas Models in Coupled Algorithms Numerical Recipes and Thermophysical Relations

In the majority of compressible flow CFD simulations, the standard ideal gas state equation is accurate enough. However, there is a range of applications where the deviations from the ideal gas behaviour is significant enough that performance predictions are no longer valid and more accurate models are needed. While a considerable amount of the literature has been written about the application of real gas state equations in CFD simulations, there is much less information on the numerical issues involved in the actual implementation of such models. The aim of this article is to present a robust implementation of real gas flow physics in an in-house, coupled, pressure-based solver, and highlight the main difference that arises as compared to standard ideal gas model. The consistency of the developed iterative procedures is demonstrated by first comparing against results obtained with a framework using perfect gas simplifications. The generality of the developed framework is tested by using the parameters from two different real gas state equations, namely the IAPWS-97 and the cubic state equations state equations. The highly polynomial IAPWS-97 formulation for water is applied to a transonic nozzle case where steam is expanded at transonic conditions until phase transition occurs. The cubic state equations are applied to a two stage radial compressor setup. Results are compared in terms of accuracy with a commercial code and measurement data. Results are also compared against simulations using the ideal gas model, highlighting the limitations of the later model. Finally, the effects of the real gas formulations on computational time are compared with results obtained using the ideal gas model.

Downhole working conditions analysis and drilling complications detection method based on deep learning

Drilling complications, which are usually hard to be discovered in time using the traditional surface detecting methods, result in much time and money wasted in handling these problems. Restricted to data transmission speed with the measurement while drilling (MWD), downhole measured data is usually ignored in downhole complications detection. And the surface detection methods with some pressure and rate of flow sensors always demand much professional knowledge and contain detection delay. In this paper, we used the measured downhole parameters to discover the drilling complications combined with deep leaning methods. Firstly, we described the difficulties of applying deep learning methods into the exploring drilling data. Then we used wavelet decomposition and reconstruction method to reduce the influence of the data trend with well depth and remove the high frequency noise. The fluctuation items coupling analysis method, consisted with rock breaking theory and transient fluctuating pressure theory, was established to make sure whether the wavelet reconstruction results contain the information to do detection. We applied a deep learning method called Bidirectional Generative Adversarial Network (BiGAN) in complications detection. BiGAN can distinguish whether the data belongs to normal working condition data or not. An end to end deep neural network mainly composed with one dimensional convolutional neural network was established to determine the specific kind of normal working condition. Then, large numbers of real field drilling data collected by the measuring tool were used to test the detection method. The testing results indicated that BiGAN indeed learned the normal working condition data distribution and the end to end network performed high accuracy in the normal working conditions classification. Therefore, we chose the combination of BiGAN and the supervised neural network to detect drilling complications with six field cases. The experiment results showed that the detection method can detect the complications much earlier than the surface detection results except for nozzle clogging case.

Application of Machine Learning Method to Quantitatively Evaluate the Droplet Size and Deposition Distribution of the UAV Spray Nozzle

Unmanned Aerial Vehicle (UAV) spray has been used for efficient and adaptive pesticide applications with its low costs. However, droplet drift is the main problem for UAV spray and will induce pesticide waste and safety concerns. Droplet size and deposition distribution are both highly related to droplet drift and spray effect, which are determined by the nozzle. Therefore, it is necessary to propose an evaluating method for a specific UAV spray nozzles. In this paper, four machine learning methods (REGRESS, least squares support vector machines (LS-SVM), extreme learning machine, and radial basis function neural network (RBFNN)) were applied for quantitatively evaluating one type of UAV spray nozzle (TEEJET XR110015VS), and the case of twin nozzles was investigated. The results showed REGRESS and LS-SVM are good candidates for droplet size evaluation with the coefficient of determination in the calibration set above 0.9 and root means square errors of the prediction set around 2 µm. RBFNN achieved the best performance for the evaluation of deposition distribution and showed its potential for determining the droplet size of overlapping area. Overall, this study proved the accuracy and efficiency of using the machine learning method for UAV spray nozzle evaluation. Additionally, the study demonstrated the feasibility of using machine learning model to predict the droplet size in the overlapping area of twin nozzles.