Design of Variable Spray System for Plant Protection UAV Based on CFD Simulation and Regression Analysis

Ni, Ming; Wang, Hongjie; Liu, Xudong; Liao, Yi; Fu, Lin; Wu, Qiqi; Mu, Jiong; Xiao-yan, Chen; Li, Jun

doi:10.3390/s21020638

Cited by 12 publications

(4 citation statements)

References 58 publications

(83 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a widely-used method for investigating underlying relationships between interested variables, or in other words, to determine the causal effect of one variable to the other. Some examples of similar use of regression analysis method to this study include Japar et al, [22], Ni et al, [23] and Jalasabri et al, [24]. The regression analysis in this study is done using MINITAB statistical software and the resultant analysis of variance (ANOVA) table is presented in Table 2.…”

Section: Resultsmentioning

confidence: 99%

Optimization of a Blended-Wing-Body Unmanned Aerial Vehicle Design for Maximum Aerodynamic Lift-to-Drag Ratio

Romli

Sabri²,

Nasir³

2023

CFDL

View full text Add to dashboard Cite

Although unmanned aerial vehicle (UAV) has found many applications in various fields, its operation has been constrained by its low flight endurance. To date, several design efforts are pursued to improve this performance and one of them is the exploration of blended-wing-body (BWB) design. In this study, parametric study is conducted on the BWB UAV design of Baseline-VII that is developed by Flight Technology and Test Center (FTTC), Universiti Teknologi MARA Shah Alam, Malaysia. The primary goal is to optimize the current Baseline-VII design for maximum lift-to-drag ratio, which in turn implies a higher flight endurance. Three design parameters are considered: inboard wing sweep angle, outboard wing sweep angle and also inboard wing span. A full-factorial design of experiments (DoE) is applied to set the total 27 design case settings for this study, with three different values considered for each design parameter: 10°, 25° and 50° for inboard and outboard wing sweep angles, and 200 mm, 300 mm and 400 mm for the inboard wing span. The computer-aided design (CAD) models for the design cases are constructed using Solidworks and the resultant aerodynamic lift-to-drag ratio is found through computational fluid dynamics (CFD) simulation analysis using ANSYS Fluent. The collected data is then statistically analysed using regression analysis in MINITAB to construct a representative regression model that aptly capture the effects of the varied design parameters on the design aerodynamic lift-to-drag ratio. Based on the results, it has been found that the maximum lift-to-drag ratio for the modified Baseline-VII UAV design is 2.8119, which is obtained with optimal settings of inboard wing sweep angle = 17.2727°, outboard wing sweep angle = 20.9091° and inboard wing span = 400 mm. This is about 28.4% increment of lift-to-drag ratio from the original Baseline-VII design.

show abstract

Section: Resultsmentioning

confidence: 99%

Optimization of a Blended-Wing-Body Unmanned Aerial Vehicle Design for Maximum Aerodynamic Lift-to-Drag Ratio

Romli

Sabri²,

Nasir³

2023

CFDL

View full text Add to dashboard Cite

show abstract

“…In this work, the RMSE (Root Mean Square Error, Equation 2) is utilized as the fitness function for GP. It is used to measure the performance of candidate solutions, since RMSE is widely-used to evaluate regression tasks in existing works [10,13,21]. The main GP parameters are provided in Table 2.…”

Section: Other Settingsmentioning

confidence: 99%

Improving the search ability of GP using semantic diversity and local search

Liang,

Lu,

2023

Preprint

View full text Add to dashboard Cite

Genetic programming (GP) is one of evolutionary computation algorithms, which simulates the evolution procedure in nature. To improve the search ability of GP, the integration of semantics and/or local search into GP has attracted significant attention. Since the existing works have shown the advantage of preserving semantic diversity through genetic operators (crossover and mutation) during evolution in GP, this work focuses on investigating new genetic operators aware of semantic diversity for GP. However, the existing semantic diversity operators rarely consider local search that may further improve their search ability. To address this issue, two new genetic operators (a crossover and a mutation) are designed, which involve both a mechanism of increasing semantic diversity and a step of local search. They are termed as semantic crossover with local search (SCls) and semantic mutation with local search (SMls), based on which two new GP-based methods are developed, i.e. GP_SCls and GP_SMls. The proposed methods are compared with GP, three reference semantic diversity methods and five non-GP regression methods for regression tasks. Results show that GP_SCls and GP_SMls are generally better than both GP and the reference semantic diversity methods, since their evolved solutions achieve lower RMSE (root mean square error) values and they converge faster for most test cases. In addition, compared with five non-GP regression methods, the proposed methods perform consistently better for the given tasks.

show abstract

“…Sisyanto et al [8] created a system that allows farmers to monitor their hydroponics through Telegram Messenger. Ni et al [24] considered the effects of the use of a variable spray system in Unmanned Aerial Vehicles (UAVs). The work used a data set to train support vector regression and back propagation neural network.…”

Section: Related Workmentioning

confidence: 99%

IndoorPlant: A Model for Intelligent Services in Indoor Agriculture Based on Context Histories

Martini

Helfer

Barbosa

et al. 2021

Sensors

View full text Add to dashboard Cite

The application of ubiquitous computing has increased in recent years, especially due to the development of technologies such as mobile computing, more accurate sensors, and specific protocols for the Internet of Things (IoT). One of the trends in this area of research is the use of context awareness. In agriculture, the context involves the environment, for example, the conditions found inside a greenhouse. Recently, a series of studies have proposed the use of sensors to monitor production and/or the use of cameras to obtain information about cultivation, providing data, reminders, and alerts to farmers. This article proposes a computational model for indoor agriculture called IndoorPlant. The model uses the analysis of context histories to provide intelligent generic services, such as predicting productivity, indicating problems that cultivation may suffer, and giving suggestions for improvements in greenhouse parameters. IndoorPlant was tested in three scenarios of the daily life of farmers with hydroponic production data that were obtained during seven months of cultivation of radicchio, lettuce, and arugula. Finally, the article presents the results obtained through intelligent services that use context histories. The scenarios used services to recommend improvements in cultivation, profiles and, finally, prediction of the cultivation time of radicchio, lettuce, and arugula using the partial least squares (PLS) regression technique. The prediction results were relevant since the following values were obtained: 0.96 (R2, coefficient of determination), 1.06 (RMSEC, square root of the mean square error of calibration), and 1.94 (RMSECV, square root of the mean square error of cross validation) for radicchio; 0.95 (R2), 1.37 (RMSEC), and 3.31 (RMSECV) for lettuce; 0.93 (R2), 1.10 (RMSEC), and 1.89 (RMSECV) for arugula. Eight farmers with different functions on the farm filled out a survey based on the technology acceptance model (TAM). The results showed 92% acceptance regarding utility and 98% acceptance for ease of use.

show abstract

Design of Variable Spray System for Plant Protection UAV Based on CFD Simulation and Regression Analysis

Cited by 12 publications

References 58 publications

Optimization of a Blended-Wing-Body Unmanned Aerial Vehicle Design for Maximum Aerodynamic Lift-to-Drag Ratio

Optimization of a Blended-Wing-Body Unmanned Aerial Vehicle Design for Maximum Aerodynamic Lift-to-Drag Ratio

Improving the search ability of GP using semantic diversity and local search

IndoorPlant: A Model for Intelligent Services in Indoor Agriculture Based on Context Histories

Contact Info

Product

Resources

About