Article
Materials Science, Multidisciplinary
Chunlei Lin, Junhui Zhou, Qianqian Lu, Mohamad Khaje Khabaz, Amirreza Karimi Andani, Mortatha Al-Yasiri, Guangyong Pan
Summary: One way to enhance thermal conduction in heating systems is to attach substances with high thermal conductivity to the base fluids. In this study, the thermal conductivity of WO3-CuO-Ag/water nanofluid is investigated and predicted using Artificial Neural Network and back-propagation algorithm. The results show that increasing the solid volume fraction and temperature leads to an increase in the thermal conductivity of the nanofluid.
MATERIALS TODAY COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Kunming Zheng, Qiuju Zhang, Li Peng, Shuisheng Zeng
Summary: This study proposes an adaptive memetic differential evolution-back propagation-fuzzy neural network (AMDE-BP-FNN) control method for efficient and precise control of robots with complex dynamic characteristics, while reducing control costs.
INFORMATION SCIENCES
(2023)
Article
Engineering, Environmental
Guangyuan Meng, Liqiang Fang, Yao Yin, Zhijie Zhang, Tong Li, Peng Chen, Yongdi Liu, Lehua Zhang
Summary: This study utilized artificial intelligence technology to enhance the electrochemical process of nitrate removal by constructing a prediction and control model using artificial neural network in machine learning. It demonstrated the potential of artificial intelligence in achieving intelligent control and reducing energy consumption.
JOURNAL OF WATER PROCESS ENGINEERING
(2022)
Article
Construction & Building Technology
Xiaorui Zhang, Frederic Otto, Markus Oeser
Summary: An ANN-based back-calculating program combined with a GA optimization algorithm was developed to back-calculate flexible pavement layer moduli. The moduli of asphaltic layers decreased with temperature and number of APT load cycles, while the unbound base layer and subgrade moduli were insensitive to temperature changes. The integrated GABP algorithm showed potential in accurately back-calculating pavement layer moduli from geophone measured deflections.
CONSTRUCTION AND BUILDING MATERIALS
(2021)
Article
Food Science & Technology
Vali Rasooli Sharabiani, Sajad Sabzi, Razieh Pourdarbani, Mariusz Szymanek, Slawomir Michalek
Summary: The paper presents a non-destructive method based on spectral data to estimate total soluble solids and BrimA in Gala apples. The study includes steps such as collecting apple samples, preprocessing spectral data, measuring chemical properties, selecting optimal wavelengths, and estimating properties using regression algorithms. Results show that the method is effective with high correlation coefficients and low root mean squared error.
Article
Automation & Control Systems
Jie Zheng, Liang Liu, Zhimin Zhang, Qiang Wang, Zhaoming Yan, Yong Xue
Summary: This study proposes a new method for preparing thin-walled square tubes with longitudinal ribs by breaking through the technological bottleneck of integral forming using preformed ribs and multi-pass rolling-extrusion process. Finite element simulation is used to reveal the metal flow deformation behavior and strain distribution, while a physical forming experiment verifies the feasibility of the proposed forming process.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2023)
Article
Environmental Sciences
Kangle Liu, Tao Lin, Tingting Zhong, Xinran Ge, Fuchun Jiang, Xue Zhang
Summary: Monitoring THMs levels in water supply systems is crucial for ensuring drinking water safety, but it is time-consuming. This study explored the feasibility of using neural network models (BPNN, GABP, GRNN) to predict THMs occurrence. The results showed that GRNN had the best prediction performance, although the accuracy for BDCM prediction was not high. Accurate predictions by GRNN made THMs monitoring in real water supply systems possible and practical.
SCIENCE OF THE TOTAL ENVIRONMENT
(2023)
Article
Environmental Sciences
Ying Deng, Xiaoling Zhou, Jiao Shen, Ge Xiao, Huachang Hong, Hongjun Lin, Fuyong Wu, Bao-Qiang Liao
Summary: This study investigated the feasibility of different prediction models for estimating the occurrence of haloketones in water supply systems. The results showed that RBF and BP artificial neural networks outperformed linear/log linear models in terms of prediction ability, with RBF ANN demonstrating the capability to recognize complex nonlinear relationships between haloketones occurrence and water quality.
SCIENCE OF THE TOTAL ENVIRONMENT
(2021)
Article
Multidisciplinary Sciences
Hongwei Bai, Qianqian Cao, Subang An
Summary: This paper proposes a prediction model and algorithm for the clock bias of the BP neural network based on the optimization of the mind evolutionary algorithm (MEA), which is used to optimize the initial weights and thresholds of the BP neural network. The accuracy of the comparison between clock bias data is verified with and without one-time difference processing. The results demonstrate that the MEA-BP model has good stability in predicting the accuracy of satellite clock bias.
SCIENTIFIC REPORTS
(2023)
Article
Geosciences, Multidisciplinary
Ali M. Rajabi, Mahdi Khodaparast, Mostafa Mohammadi
Summary: This study used an artificial neural network to conduct risk studies on landslides in the area affected by the Manjil-Rudbar earthquake in Iran in 1990. The results showed that the ANN method is relatively efficient for accurate prediction of landslides, covering 50% of the inventory map of the study area. The hazard map developed through Newmark displacement analysis was compared with other research findings, highlighting the effectiveness of the ANN approach.
Article
Engineering, Chemical
Gaiqiang Yang, Yunfei Xu, Lijuan Huo, Dongpeng Guo, Junwei Wang, Shuang Xia, Yahong Liu, Qi Liu
Summary: In this study, the GA-BP-ANN method is used to predict the cost of a wastewater treatment plant. The method has advantages in improving data stability and providing better help for decision makers compared to the linear algorithm. The theoretical proof and simulation verification demonstrate the effectiveness and feasibility of this method, which can guide the design and operation of sewage treatment plants.
DESALINATION AND WATER TREATMENT
(2023)
Article
Energy & Fuels
Sarvapriya Singh, Siddharth Suman, Santanu Mitra, Manish Kumar
Summary: A hybrid CFD-ANN approach is used to predict the thermo-hydraulic performance of a solar air heater with rotating circular ribs. An optimized ANN model is developed based on CFD simulations, and it shows good agreement with experimental results. The optimized ANN model significantly reduces the computational time compared to CFD simulations.
Article
Mathematical & Computational Biology
Hong Gao, Cuiyun Wu, Dunnian Huang, Dahui Zha, Cuiping Zhou
Summary: The study proposed a fetal weight prediction model based on genetic algorithm optimized neural network, which achieved an accuracy of 76.3% and reduced prediction error to within 6%, marking a 14.5% improvement compared to traditional methods.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2021)
Article
Polymer Science
Ming Ma, Huchen Zhou, Suhan Gao, Nan Li, Wenjuan Guo, Zhao Dai
Summary: Electrospinning technology was used to fabricate polyacrylonitrile (PAN) nanofibers, and their morphology and size were characterized. An artificial neural network (ANN) was developed to establish the relationship between the electrospinning process parameters and the diameter of PAN nanofibers. The results showed that polymer concentration had the greatest influence on the diameter. This study provides guidance for the preparation of specific-sized PAN nanofibers.
Article
Automation & Control Systems
Syed Fawad Hussain, Ghulam Hussain, Naila Rahman
Summary: This paper discusses the differences between traditional polymer processing techniques and incremental sheet forming, highlighting the spring back issue with the latter that requires process control for desired part accuracy. It proposes using machine learning methods for error prediction and parameter optimization, utilizing a hybrid model of genetic algorithm and artificial neural network to minimize shape error. Experiments on Polypropylene sheet demonstrate the effectiveness of this approach in minimizing mean squared error compared to statistical techniques.
INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY
(2022)