Article
Engineering, Civil
Sami Ghordoyee Milan, Abbas Roozbahani, Naser Arya Azar, Saman Javadi
Summary: The study developed a predictive model based on machine learning, and combining ANFIS with HHO significantly improved the prediction accuracy of groundwater extraction amount. The results indicated that ANFIS-HHO performed well on test data and had better predictive accuracy compared to other algorithms.
JOURNAL OF HYDROLOGY
(2021)
Article
Thermodynamics
Dalibor Petkovic, Miljana Barjaktarovic, Slavisa Milosevic, Nebojsa Denic, Boban Spasic, Jelena Stojanovic, Milos Milovancevic
Summary: In order to reduce the cost of biodiesel production, it is necessary to use non-edible oils and establish computational models. The study found that fuel injection pressure and engine load have a significant impact on the performance and emission parameters of biodiesel.
Article
Engineering, Marine
Mudassir Iqbal, Khalid Elbaz, Daxu Zhang, Lili Hu, Fazal E. Jalal
Summary: This study used particle swarm optimization, genetic algorithm, and support vector machine to optimize the adaptive neuro-fuzzy inference system model for more accurate prediction of the tensile strength of GFRP bars in alkaline environments. Through the collection of experimental samples and k-fold cross-validation, robust and reliable prediction models were developed.
JOURNAL OF OCEAN ENGINEERING AND SCIENCE
(2023)
Article
Energy & Fuels
Bandar M. Fadhl, Basim M. Makhdoum, Alfian Ma'arif, Iswanto Suwarno, Hudhaifa Hamzah, Mohamed Salem
Summary: Two intelligent approaches (ANFIS and GMDH) were used to model the dynamic viscosity of nanofluids with MgO nanoparticles. Comparing the predicted values with the actual values, it was found that the GMDH method was more accurate and could be widely used in nanofluid research.
Article
Energy & Fuels
Sunil Kumar
Summary: This study investigated the production of biodiesel from Karanja oil under different operating conditions, optimizing process variables using Box-Behnken response surface design. RSM and ANFIS models were developed with correlation coefficients of 0.85 and 0.95, respectively, to predict biodiesel production. Standard methods were used to characterize the physico-chemical properties of Karanja oil methyl ester.
Article
Mechanics
Andrew K. Dickerson, M. D. Erfanul Alam, Jacob Buckelew, Nicholas Boyum, Damla Turgut
Summary: This study investigates the impact forces resulting from collisions between drops and curved surfaces. Through experimental data and machine learning algorithms, the five main parameters influencing impact force are identified and the force is predicted for different parameter values. The results indicate that the deformation of the drop and the surface wettability are important factors for impact forces on concave targets.
Article
Computer Science, Artificial Intelligence
Wei Zhu, Hima Nikafshan Rad, Mahdi Hasanipanah
Summary: This study introduces a new hybrid model that combines CRANFIS and PSO to predict ground vibration, which outperforms other methods in prediction accuracy.
APPLIED SOFT COMPUTING
(2021)
Article
Environmental Sciences
Hussam Eldin Elzain, Sang Yong Chung, Kye-Hun Park, Venkatramanan Senapathi, Selvam Sekar, Chidambaram Sabarathinam, Mohamed Hassan
Summary: Enhanced assessment of groundwater contamination vulnerability is essential for sustainable management of groundwater resources due to increasing contamination worldwide. This study compared ANFIS-MOA models in assessing vulnerability in a nitrate-contaminated area, with ANFIS-PSO model showing superior performance and potential for application in other regions.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2021)
Article
Energy & Fuels
Siti Norhafiza Mohd Khazaai, Prakash Bhuyar, Vladimir Strezov, Natanamurugaraj Govindan, Mohd Hasbi Ab Rahim, Gaanty Pragas Maniam
Summary: This study investigates the effects of different factors on the extraction of rubber seed oil (RSO) and discovers that extracting with a non-polar solvent gives a higher yield. The study also uses an ANFIS model to predict the extraction yield and confirms the compositional results obtained by GC-MS. The high extraction yield and low cost of RSO make it a cost-effective alternative for biodiesel synthesis.
BIOENERGY RESEARCH
(2023)
Article
Geosciences, Multidisciplinary
Rahul Ray, Deepak Kumar, Pijush Samui, Lal Bahadur Roy, A. T. C. Goh, Wengang Zhang
Summary: This research focuses on using three soft computing techniques to analyze the shallow foundation settlement based on reliability criteria. The study found that Minimax Probability Machine Regression model outperformed Particle Swarm Optimization based Artificial Neural Network and Particle Swarm Optimization based Adaptive Network Fuzzy Inference System, making it a reliable soft computing technique for nonlinear settlement problems in soil foundations.
GEOSCIENCE FRONTIERS
(2021)
Article
Engineering, Civil
Alireza Oliaye, Seon-Ho Kim, Deg-Hyo Bae
Summary: This study proposed a novel approach, ANFIS-PSO, to adjust radar rainfall by combining adaptive-network-based fuzzy inference system and particle swarm optimization. Six geographical variables were utilized to adjust the rainfall at three South Korean stations. The adjusted rainfall showed good agreement with Marshall-Palmer-based rainfall and significantly improved the mean absolute percentage error and correlation value. The sensitivity analysis revealed the high sensitivity of adjusted rainfall to elevation and distance from the sea.
JOURNAL OF HYDROLOGY
(2023)
Article
Chemistry, Multidisciplinary
Haolin Jia, Xiaohui Lu, Deling Cai, Yingjian Xiang, Jiahao Chen, Chengle Bao
Summary: In recent years, high-performance grinding has shifted from traditional manual grinding to robotic grinding. Accurate material removal poses a challenge for workpieces with complex profiles. Digital processing of grinding has shown great potential for optimizing manufacturing processes and operational efficiency, leading to the inevitable trend of quantifying the material removal process. This research establishes a three-dimensional model of the grinding workstation, designs the blade back arc grinding trajectory, and develops a prediction model for blade material removal depth (MRD) using the Adaptive Neuro-Fuzzy Inference System (ANFIS). Experimental investigations using the Taguchi method and Analysis of Variance (ANOVA) revealed the impact of certain elements on the outcomes and demonstrated the superior performance of ANFIS compared to other prediction models.
APPLIED SCIENCES-BASEL
(2023)
Article
Thermodynamics
Morteza Esfandyari, Amin Amiri Delouei, Ali Jalai
Summary: In this study, two intelligent optimization methods, artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS), with particle swarm optimization (PSO), were used to forecast the heat transfer rate, Nusselt number, number of transfer units (NTU), and effectiveness of a double-pipe counter-flow heat exchanger. The results of the experiments were verified through the ANN, ANFIS, ANN-PSO, and ANFIS-PSO methods. Both the ANN and ANFIS models were developed using backpropagation and the optimal hybrid method, and were optimized using the PSO algorithm. The comparison of experimental and predicted data showed that both models were accurate, with the ANN-PSO model slightly outperforming the ANFIS-PSO model. The maximum MSE value of 2.592 indicated good performance of the model in predicting results.
INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER
(2023)
Article
Automation & Control Systems
Malika Lazreg, Nacera Benamrane
Summary: This article highlights the importance of mobile robotics in achieving rapid and collision-free movement. It introduces the use of hybridization effect by combining two methods, ANFIS and PSO, to optimize the controller's speed and positions. The simulation results demonstrate the improved performance of the hybrid method in measuring distances traveled by the robot in pixels.
ROBOTICS AND AUTONOMOUS SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Naif Alharbi
Summary: This study experimentally demonstrated that increasing the vibration amplitude in incremental forming process can reduce forming force and dimensional deviation, as well as result in thinning in critical regions. Optimization results indicated that superimposing high vibration amplitude can lead to minimized process time and desired quality characteristics of workpiece.
ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
(2022)