Article
Energy & Fuels
Abouzar Rajabi Behesht Abad, Hamzeh Ghorbani, Nima Mohamadian, Shadfar Davoodi, Mohammad Mehrad, Saeed Khezerloo-ye Aghdam, Hamid Reza Nasriani
Summary: Condensate reservoirs present unique challenges in the oil and gas industry, and machine learning methods show promise in predicting gas flow rates, with the MELM-PSO model demonstrating the highest accuracy.
Article
Energy & Fuels
Hossein Shojaei Barjouei, Hamzeh Ghorbani, Nima Mohamadian, David A. Wood, Shadfar Davoodi, Jamshid Moghadasi, Hossein Saberi
Summary: The study compares the prediction performance of traditional empirical, ML, and DL algorithms for Q(L) using data from the Sorush oil field, finding that the DL algorithm surpasses others in accuracy. The gas-liquid ratio has the greatest influence on Q(L), while choke size has the least influence on Q(L).
JOURNAL OF PETROLEUM EXPLORATION AND PRODUCTION TECHNOLOGY
(2021)
Article
Energy & Fuels
Sulaiman A. Alarifi
Summary: Multiphase flow metering plays a crucial role in monitoring the production performance of oil and gas reservoirs. The current practice involves monthly production rate tests for connected wells. This study aims to develop a machine learning model that outperforms existing correlations in predicting the flow rate of critical and subcritical multiphase flow through the wellhead choke.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Environmental Sciences
Kouao Laurent Kouadio, Loukou Nicolas Kouame, Coulibaly Drissa, Binbin Mi, Kouamelan Serge Kouamelan, Serge Pacome Deguine Gnoleba, Hongyu Zhang, Jianghai Xia
Summary: This study applied support vector machines (SVMs) to predict flow rates in groundwater exploration, aiming to minimize unsuccessful drillings. The SVM models achieved prediction accuracies of 77% and 83% on multiclass and binary datasets, respectively. The use of optimal polynomial and radial basis function kernels resulted in higher accuracies of 81.61% and 87.36%. Learning curves showed that larger training data could improve prediction performance on the multiclass dataset, but not necessarily on the binary dataset.
WATER RESOURCES RESEARCH
(2022)
Article
Chemistry, Multidisciplinary
Xiuzhen Li, Shengwei Li
Summary: Forecasting large-scale landslides development is complex, and a study has utilized multi-factor support vector regression machines to predict displacement rates, finding relationships between rainfall, reservoir water levels, and landslide displacement. The models showed high accuracies, with the two-factor model exhibiting the highest accuracy.
APPLIED SCIENCES-BASEL
(2021)
Article
Engineering, Chemical
Zihao Wang, Zhen Song, Teng Zhou
Summary: Machine learning models were developed to predict the toxicity of ionic liquids, with the support vector machine algorithm slightly outperforming the feedforward neural network algorithm; after structure optimization through five-fold cross validation, the models exhibited high predictive accuracy and can be useful for computer-aided molecular design of environmentally friendly ILs.
Article
Chemistry, Multidisciplinary
Yang Liu, Shuaiwen Huang, Di Wang, Guoli Zhu, Dailin Zhang
Summary: This paper proposes a new predictive model for determining the need to replace disc cutters in tunnel boring machines (TBM) based on operational parameters and geological conditions. The model achieves high accuracy and F-1 scores in predicting cutter replacement using specific parameters and established features.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Geological
Yankun Wang, Huiming Tang, Jinsong Huang, Tao Wen, Junwei Ma, Junrong Zhang
Summary: This paper compares the performance of five popular machine learning methods in predicting reservoir landslide displacement and finds that PSO-KELM and PSO-LSSVM have better mean prediction accuracy and prediction stability.
ENGINEERING GEOLOGY
(2022)
Article
Energy & Fuels
Heng Chen, Jinying Duan, Rui Yin, Vadim V. Ponkratov, John William Grimaldo Guerrero
Summary: This paper focuses on field data analysis using mathematical programming and optimization-based methods to improve drilling operations. By presenting a comprehensive multi-objective optimization model, the study aims to bridge the gap between new multi-objective programming models and existing classification methods. Through the geometric representation of the model, the characteristics of the proposed model are easier to understand.
Article
Engineering, Aerospace
Lingfeng Zhong, Rui Liu, Xiaodong Miao, Yufeng Chen, Songhong Li, Haocheng Ji
Summary: Compressors are crucial in energy and power systems, and accurate performance calculation under different operating conditions is essential. This study combines interpolation with support vector machine (SVM) to predict compressor performance using limited data. The SVM is trained using interpolation samples obtained from known data points, and the genetic algorithm optimizes its parameters. The results show that SVM with Gaussian kernel function has the highest prediction accuracy, and linear interpolation provides better predictions compared to cubic spline interpolation. GA-SVM outperforms other optimized neural networks in terms of generalization and predicting boundary data accuracy.
Article
Computer Science, Information Systems
Zichen Zhang, Shifei Ding, Yuting Sun
Summary: This paper introduces a new method called multiple birth support vector regression (MBSVR), which constructs the regressor from multiple hyperplanes obtained by solving small quadratic programming problems, aiming for faster computation and better fitting precision.
INFORMATION SCIENCES
(2021)
Article
Engineering, Civil
Miaomiao Wei, Genshen Fang, Yaojun Ge
Summary: This study introduces a machine-learning-based approach utilizing a support vector machine to predict tropical cyclone genesis. By extracting historical data and mapping meteorological parameters, it enables the simultaneous determination of TC genesis locations and counts, significantly enhancing computational efficiency.
JOURNAL OF WIND ENGINEERING AND INDUSTRIAL AERODYNAMICS
(2023)
Article
Thermodynamics
Jiale Huang, Tao Jin, Menglin Liang, Houlei Chen
Summary: This study experimentally studied the heat exchanger performance in cryogenic oscillating-flow conditions and established machine learning models for data processing. Support vector machine models showed distinguishable improvement in predicting accuracy compared with non-dimensional correlations in the exponential form.
APPLIED THERMAL ENGINEERING
(2021)
Article
Energy & Fuels
Xingye Liu, Guangzhou Shao, Cheng Yuan, Xiaohong Chen, Jingye Li, Yangkang Chen
Summary: This paper proposes a reservoir properties prediction method based on a mixture of relevance vector regression experts. By incorporating multiple learning models, the method decomposes the complicated problem into simple sub-problems and improves the accuracy of prediction.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Civil
Bing-Chen Jhong, Hsi-Ting Fang, Cheng-Chia Huang
Summary: This study proposes an assessment framework based on the DIKW hierarchy, utilizing SRH2D to simulate suspended sediment concentration data and combining SVM and MOGA methods for sediment flux prediction. It is found that data from monitoring stations near the inflow point and dam face are more useful for sediment flux prediction.
WATER RESOURCES MANAGEMENT
(2021)
Article
Energy & Fuels
Alireza Baghban, Shahaboddin Shamshirband
Summary: This paper investigates the accurate prediction of higher heating value (HHV) for municipal solid wastes using intelligent algorithms. The proposed MLP-ANN and LSSVM methods achieve better performance and are considered as reliable predictive tools for estimating HHV values of solid wastes.
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
(2022)
Article
Energy & Fuels
Alireza Baghban, Narjes Nabipour
Summary: A new approach based on the ANFIS algorithm was developed to predict the solution gas oil ratio (R-s) as a function of other properties of crude oil in operational conditions. The method showed high accuracy in predicting R-s and outperformed existing correlations in the literature.
ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
(2023)
Article
Green & Sustainable Science & Technology
Farhad Keivanimehr, Alireza Baghban, Sajjad Habibzadeh, Ahmad Mohaddespour, Amin Esmaeili, Muhammad Tajammal Munir, Mohammad Reza Saeb
Summary: The study focuses on using advanced oxidation processes (AOP) to degrade water contaminants, with hydroxyl radicals as efficient oxidants. A new stochastic gradient boosting (SGB) decision tree technique was developed to model the degradation rate constant of the hydroxyl radicals based on the quantitative structure-property relationship (QSPR) method. The developed model showed promising estimation of the hydroxyl radical rate constants with high accuracy, and outperformed previous models in a comparison study.
ENVIRONMENTAL PROGRESS & SUSTAINABLE ENERGY
(2021)
Article
Chemistry, Multidisciplinary
Amir Dashti, Mojtaba Raji, Pouria Amani, Alireza Baghban, Amir H. Mohammadi
Summary: This study focuses on modeling the solubility of CO2 in various deep eutectic solvents using artificial intelligent methods, with LSSVM and MPR models identified as robust and precise models for estimating CO2 solubility in these solvents.
SEPARATION SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Chemical
Savyasachi Shrikhande, Gunavant Deshpande, Ashish N. Sawarkar, Z. Ahmad, Dipesh S. Patle
Summary: This study presents new processes for biodiesel production using wet microalgal feedstock, ionic liquid catalyst, and ultrasonication. Retrofitting with DWC and MVR led to significant cost savings in various aspects. The study highlights the importance of experimental design and economic analysis for improving biodiesel production processes.
CHEMICAL ENGINEERING RESEARCH & DESIGN
(2021)
Article
Engineering, Chemical
Dinie Muhammad, Fakhrony S. Rohman, Zainal Ahmad, Norashid Aziz
Summary: This study developed and explored the application of neural Wiener MPC in controlling LDPE tubular reactor process, utilizing Aspen Plus and Aspen Dynamic software for LDPE tubular reactor model development, and neural network model identification using Matlab software, demonstrating the successful identification capability of NWMPC for the nonlinear LDPE tubular reactor process, improving the practical application ability of tubular reactor control.
ASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING
(2021)
Review
Engineering, Chemical
Rasheed O. Kelani, Zainal Ahmad, Dipesh Patle
Summary: This paper provides an overview of studies on mechanistic model-based control of biodiesel production process, focusing on control strategies such as plantwide control, model predictive control, and optimal control. It is found that there is limited application of advanced control strategies in the biodiesel production process, especially within the plantwide control framework. Decentralized plantwide control using a heuristic-based method and simulations is currently being employed to improve the performance of biofuel production. The review highlights the need for a simple, effective, and easily implementable plantwide design control for achieving optimal profitability, controllability, and safety.
CHEMICAL ENGINEERING COMMUNICATIONS
(2023)
Review
Chemistry, Multidisciplinary
Mohd-Nasir Nor Shafiqah, Tan Ji Siang, Ponnusamy Senthil Kumar, Zainal Ahmad, A. A. Jalil, Mahadi B. Bahari, Quyet Van Le, Leilei Xiao, M. Mofijur, Changlei Xia, Shams Forruque Ahmed, Dai-Viet N. Vo
Summary: There is an intense research in ethanol dry reforming, which converts bioethanol and carbon dioxide into syngas and ultimately into chemicals and energy. The focus of this review is on the thermodynamics, catalysts, and operating conditions of dry reforming. Noble metal-based catalysts can achieve high conversions of ethanol and CO2 above 85% in the temperature range of 923-1073 K, but their potential applications are limited due to high cost. H-2 yield of 90% and above is achieved at temperatures of 1073 K or above, but improving catalytic performance and inhibiting coke formation is a challenge that may be addressed using bimetallic catalysts and other metal oxides.
ENVIRONMENTAL CHEMISTRY LETTERS
(2022)
Review
Chemistry, Multidisciplinary
Mukhtar Ahmed, Anas Abdullah, Dipesh S. Patle, Mohammad Shahadat, Zainal Ahmad, Moina Athar, Mohammad Aslam, Dai-Viet N. Vo
Summary: Biodiesel is a sustainable alternative to petroleum diesel, but faces challenges in commercialization due to production costs and suitable industrial techniques. The one-pot extraction-transesterification method can potentially solve these issues by efficiently processing cheap, low-quality feedstocks with high conversion rates. Intensification techniques, such as microwave irradiation and ultrasonication, can further enhance the efficiency of biodiesel production.
ENVIRONMENTAL CHEMISTRY LETTERS
(2022)
Review
Chemistry, Multidisciplinary
Cham Q. Pham, Tan Ji Siang, Ponnusamy Senthil Kumar, Zainal Ahmad, Leilei Xiao, Mahadi B. Bahari, Anh Ngoc T. Cao, Natarajan Rajamohan, Amjad Saleh Qazaq, Amit Kumar, Pau Loke Show, Dai-Viet N. Vo
Summary: Dihydrogen (H-2), commonly known as hydrogen, has attracted research interest due to its potential applications in fuel cells, vehicles, pharmaceuticals, and gas processing. The catalytic decomposition of methane is a promising technology to generate COx-free hydrogen and carbon nanomaterials, which have various applications in electronics, fuel cells, clothing, as well as biological and environmental treatments. This paper reviews the decomposition of methane on Ni-based catalysts and investigates the factors influencing the reaction.
ENVIRONMENTAL CHEMISTRY LETTERS
(2022)
Article
Engineering, Chemical
Hafiz Gadafi Abdul Aziz, Boon Seng Ooi, Abdul Latif Ahmad, Zainal Ahmad, Mohd Azmier Ahmad, Choe Peng Leo
Summary: This study successfully improved the removal of phosphate by producing and modifying calcium carbonate nanoparticles. The incorporation of iron increased the surface area of CaCO3, resulting in significantly enhanced phosphate removal. CaCO3-Fe exhibited different adsorption behavior for phosphate compared to traditional pH-responsive materials.
CHEMICAL ENGINEERING & TECHNOLOGY
(2022)
Article
Energy & Fuels
Mukhtar Ahmed, Anas Abdullah, Abdullah Laskar, Dipesh S. Patle, Dai-Viet N. Vo, Zainal Ahmad
Summary: This study focuses on the simulation and multiobjective optimization of a dry microalgae-based in-situ biodiesel plant. Using economic and environmental criteria, the plant operation was optimized to reduce total annualized cost, organic waste generation, and CO2 emissions. Different scenarios were studied and the results showed significant improvements in plant performance with reductions in cost, waste, and emissions.
Article
Thermodynamics
Mukhtar Ahmed, Khwaja Alamgir Ahmad, Dai-Viet N. Vo, Mohammad Yusuf, Ahteshamul Haq, Anas Abdullah, Mohammad Aslam, Dipesh S. Patle, Zainal Ahmad, Ejaz Ahmad, Moina Athar
Summary: Biodiesel, a biofuel with multiple advantages over petroleum diesel, has seen significant growth in utilization from oil-bearing edible biomasses. However, due to increasing global prices, energy demand, and greenhouse gas emissions, edible feedstocks are not sustainable. Inedible biomasses, via catalyzed transesterification, have been proposed as potential feedstocks for biodiesel production. Nanocatalysts, favored for their easy separation and ability to retain catalytic activity, play a crucial role in biodiesel production due to their high efficiency. Nanocatalysts, such as zirconium oxide (ZrO2) and nano CaO, offer high biodiesel conversion rates and environmental friendliness. This review extensively discusses the significance of nanocatalysts in biodiesel synthesis, including reaction mechanisms, support and promoter functions, renewable feedstocks, synthesis routes, and characterization techniques. The review also covers kinetics, thermodynamics, process simulation, and optimization of heterogeneous nanocatalyzed biodiesel production. Ultimately, this review provides researchers with valuable information on developing cost-effective nanocatalysts for sustainable biodiesel production.
ENERGY CONVERSION AND MANAGEMENT
(2023)
Proceedings Paper
Materials Science, Multidisciplinary
Iylia Idris, Zainal Ahmad, Mohd Roslee Othman, Fakhrony Sholahudin Rohman, Ahmad Ilyas Rushdan, Ashraf Azmi
Summary: This paper presents the development of a mathematical model for predicting water flux, using an artificial neural network, in the context of direct contact membrane distillation. The model has been shown to be accurate and sensitive, with the potential to contribute to the efficient and economical design of separation processes.
MATERIALS TODAY-PROCEEDINGS
(2022)
Article
Multidisciplinary Sciences
M. R. Izham Rusdi, T. Bashkeran, Z. Ahmed
Summary: Statistical Process Control is used to monitor the quality of palm oil mill boilers and boiler feedwater in Perak State, Malaysia, in order to address efficiency issues caused by solid waste layer in boilers.
MALAYSIAN JOURNAL OF FUNDAMENTAL AND APPLIED SCIENCES
(2022)