Artificial Neural Network-based Model Research Articles

Artificial Neural Network-based Models for Short Term Forecasting of Solar PV Power Output and Battery State of Charge of Solar Electric Vehicle Charging Station

The main objective of this study is to develop ANN-based predictive models for short-term forecasting of solar PV power output and battery state of charge. The 3Ds energy model that integrates Decarbonization, Digitalization, and Decentralization of the energy system to facilitate the shift towards sustainable energy sources is used for this electric vehicle project. The experimental set up includes solar PV panels, a solar inverter, a battery inverter, and a battery bank. Additionally, smart meters were installed to collect real-time performance data from the solar PV-powered electric vehicle (EV) charging station. The weather and real-time system performance data were used to develop short term forecasting models based on Artificial Neural Networks (ANN) and the Levenberg-Marquardt method, to predict the performance of the system (power output and state of the charge) ahead. The R values for the prediction models of solar photovoltaic (PV) specific power and battery state of charge fall within the range of 0.9957 to 0.9969 and 0.9990 to 0.9996, respectively. Furthermore, the mean squared errors (MSEs) for the artificial neural network (ANN) models pertaining to solar photovoltaic (PV) power output and battery state of charge exhibit a variety of values. Specifically, the MSEs for solar PV power output range from 1.242 x 10ˆ-4 to 1.579 x 10ˆ-4, while the MSEs for battery status of charge range from 0.1889 to 0.3402. Artificial neural network (ANN) models possess considerable promise for practical implementations as they simplify intricate connections among inputs, parameters, and outputs in real-world scenarios. The level of accuracy and short-term predictive models of the solar PV powered EV charging station are very important for achieving a balance between the supply of solar photovoltaic (PV) system and the demand for electric vehicles (EVs). Predictive models will help build complex control mechanisms for controlling and optimizing solar PV-powered charging stations, supervising their operation and maintenance, and simplifying renewable energy pre-purchase. Future works will include the development of an energy management system to improve the efficiency of the solar stations charging the EVs, the establishment of blockchain networks for both the solar PV system and battery bank, and the integration of cybersecurity protocols for the charging station.

Predictive modelling of cooling consumption in nursing homes using artificial neural networks: Implications for energy efficiency and thermal comfort

The growing need for cooling within the built environment, propelled by climate change and the expansion of nursing homes due to the increase in life expectancy, highlights the urgency of implementing energy-efficient strategies in buildings occupied by older populations. As of today, there remains a need for comprehensive research into the influence of indoor and outdoor conditions, building, operational, and occupant characteristics, on energy consumption specifically for nursing homes. This study develops a systemic artificial neural network-based model with a multi-layer perceptron architecture to assess HVAC energy implications during the cooling season for older populations. Using monitored data from eight nursing homes, the model includes cooling area, construction age, outdoor and indoor temperatures, and outdoor relative humidity as inputs, and cooling consumption as the output. Results show excellent predictive capability (R2=0.95), with mean error of −0.5 kWh, root mean squared error of 13.7 kWh, mean absolute error of 10.2 kWh, and relative error of 0.051. These outcomes are better compared to linear models (R2≈0.65) under the same data set. Adjusting operative temperatures adaptively can significantly enhance resident comfort and achieve up to 23.4 % energy savings, particularly in hotter, drier climates. These findings are of paramount importance for effective energy management in buildings.

Investigation and prediction on emissions and performance of CI engine employing binary and ternary blends with Karanja oil, used cooking oil, and Dunaliella salina oil.

Massive consumption of fossil fuels and alarming environmental degradation are motivating researchers to learn about alternative fuels. Straight vegetable oils are an alternative to fossil fuels to meet the standards. Microalgae is also a viable carbon-neutral alternative to depleting conventional fuel sources, a solution to the industrial requirement of organic consumables and an option for a green and sustainable economy for biofuels. In the present study, lipid was extracted from Karanja seeds and Dunaliella salina biomass. These were used to prepare different binary and ternary fuel blends with conventional reference diesel fuel with different proportions along with used cooking oil with their concentrations ranging from 10 to 20% (v/v). The influence of these blends on performance and emissions characteristics in CI engines has delved at varying engine loads from 0 to 100%. The binary blend with Dunaliella salina oil has increased the performance characteristics while decreasing all the major emission parameters compared to reference diesel fuel and shows a significant improvement among binary blends. Ternary blends with Dunaliella salina oil, on the other hand, have improved performance while lowering emission parameters when compared to reference diesel fuel and demonstrate a substantial improvement across ternary blends. For predicting the performance and emission characteristics of binary and ternary blends, an artificial neural network-based model was developed. The optimum blends, OB6 (90% RDF, 10% DO) and OB8 (80% RDF, 10% DO, 10% UCO), improved BSFC by 10.71%, BTE by 14.23%, and reduced BSEC by 12.45% at full load. Emissions were generally reduced, with CO2 decreasing by up to 39.39%. The simulation results demonstrated that the created 4-7-7 model was capable of accurately predicting the performance and emission characteristics of various alternative fuel blends and indicating a stronger correlation between the predicted and observed values, having a high correlation coefficient of 0.9974. Binary and ternary blends with straight vegetable oils improved CI engine performance and pollutants compared to reference diesel fuel, indicating they have the potential to replace conventional fuels for sustainable development.

An artificial neural network-based model for predicting paratransit travel time

An artificial neural network-based model for predicting paratransit travel time

Experimental research and artificial neural network-based prediction model on compressive strength of hardened cement pastes containing fly ash and silica fume at high temperatures

Experimental research and artificial neural network-based prediction model on compressive strength of hardened cement pastes containing fly ash and silica fume at high temperatures

Artificial Neural Network-Based Model for Assessing the Whole-Body Vibration of Vehicle Drivers

Musculoskeletal disorders, which are epidemiologically related to exposure to whole-body vibration (WBV), are frequently self-reported by workers in the construction sector. Several activities during building construction and demolition expose workers to this physical agent. Directive 2002/44/CE defined a method of assessing WBV exposure that was limited to an eight-hour working day, and did not consider the cumulative and long-term effects on the health of drivers. This study aims to propose a methodology for generating individualised models for vehicle drivers exposed to WBV that are easy to implement by companies, to ensure that the health of workers is not compromised in the short or long term. A measurement campaign was conducted with a professional driver, and the collected data were used to formulate six artificial neural networks to predict the daily compressive dose on the lumbar spine and to assess the short- and long-term WBV exposure. Accurate results were obtained from the developed artificial neural network models, with R2 values above 0.90 for training, cross-validation, and testing. The approach proposed in this study offers a new tool that can be applied in the assessment of short- and long-term WBV to ensure that workers’ health is not compromised during their working life and subsequent retirement.

Artificial neural network-based modeling of Malachite green adsorption onto baru fruit endocarp: insights into equilibrium, kinetic, and thermodynamic behavior

In this study, artificial neural network (ANN) tools were employed to forecast the adsorption capacity of Malachite green (MG) by baru fruit endocarp waste (B@FE) under diverse conditions, including pH, adsorbent dosage, initial dye concentration, contact time, and temperature. Enhanced adsorption efficiency was notably observed under alkaline pH conditions (pH 10). Kinetic analysis indicated that the adsorption process closely followed a pseudo-second-order model, while equilibrium studies revealed the Langmuir isotherm as the most suitable model, estimating a maximum adsorption capacity of 57.85 mg g−1. Furthermore, the chemical adsorption of MG by B@FE was confirmed using the Dubinin–Radushkevich isotherm. Thermodynamic analysis suggested that the adsorption is spontaneous and endothermic. Various ANN architectures were explored, employing different activation functions such as identity, logistic, tanh, and exponential. Based on evaluation metrics like the coefficient of determination (R 2) and root mean square error (RMSE), the optimal network configuration was identified as a 5–11-1 architecture, consisting of five input neurons, eleven hidden neurons, and one output neuron. Notably, the logistic activation function was applied in both the hidden and output layers for this configuration. This study highlights the efficacy of B@FE as an efficient adsorbent for MG removal from aqueous solutions and demonstrates the potential of ANN models in predicting adsorption behavior across varying environmental conditions, emphasizing their utility in this field.

A prolegomenon to Design Input Energy Spectra for the Himalayan region

Energy-based design is becoming progressively significant as a new age of earthquake-resistant design unfolds. Thitherto, very little is known about energy-based design in India despite the fact that the Himalayan region is one of the most seismically active regions in the world. Therefore, the current work provides a preliminary analysis of the elastic input energy and equivalent velocity (Vea) spectra for the active regions in the Himalayas. In this regard, the ground motions of Himalayan databases are blended with NGA WEST2 to estimate the Vea spectra, an inertia-independent representation of the input energy spectra. Incipiently, an Artificial Neural Network-based ground motion model (GMM) is developed for Vea spectra based on the predictor variables as magnitude, distance, hypocentral depth and site conditions. Consequently, a Probabilistic Seismic Hazard analysis is performed to obtain the uniform hazard energy spectra for a 2475-year return period. In addition, a Design Input Energy Spectra is proposed for the active regions in the Indian Himalayas. In addition, the relationship between the Vea and pseudo-spectral velocity (PSV) is analyzed to develop a Vea-informed GMM for PSV. Furthermore, the PSA estimated from the Vea-PSV model is compared with the design spectra recommended by the Indian Standard Code of Practice (IS1893-1:2016).

Pore fractal characteristics and ANN model of polyacrylonitrile fiber reinforced concrete under the synergistic effects of freeze-thaw and erosion

The degradation of the concrete pore structure is a major concern among scholars due to its negative impact on durability. This study conducted a salt freezing test on polyacrylonitrile fiber concrete (PANFRC) using a composite freeze-thaw medium consisting of Na2SO4, MgSO4, and NaCl (5 % + 5% + 3.5 %). The pore volume fractal dimension was determined by analyzing the T2 spectrum obtained through nuclear magnetic resonance technology. The study explored the influence of different types of pores on frost resistance and developed an artificial neural network-based machine learning model to predict macroscopic frost resistance using the pore volume fractal dimension. The experimental findings indicate that plain concrete exhibits a density loss of 4.67 % upon failure, whereas the density loss in PANFRC is reduced to less than 3 %. The frost resistance durability index is observed to improve as the fiber mass fraction increases within specific ranges. Notably, when the fiber content surpasses 1.2 kg/m³, the durability factor (DF) can be effectively doubled. Drawing from the concept of freeze-thaw cycles, a novel frost-thaw erosion damage model was developed, which incorporates the influence of fiber content under the combined action of freeze-thaw cycles and erosion. The analysis of pore dimensions reveals that the fractal characteristics become more pronounced with the increase in pore size, although this does not extend to the micro-pore range (i.e., those smaller than 0.1 μm). In comparison to other machine learning algorithms, the ANN demonstrates its superiority by establishing a meso-macro transfer prediction model with enhanced generalization capabilities.

Artificial neural network-based positioning error modeling and compensation for low-cost encoders of four-wheeled vehicles

Artificial neural network-based positioning error modeling and compensation for low-cost encoders of four-wheeled vehicles

Artificial intelligence-based surrogate modeling for computational cost-effective optimization of hydrogen liquefaction process

The chemical processes are inherently complex, and obtaining desired product quality and high energy efficiency by optimizing the design variables is challenging. The progress in computing technologies can be a blessing since machine learning models can process the information and data for learning purposes and eventually help ease the simulation and optimization efforts. Against this backdrop, an artificial neural network-based surrogate model is developed in the present study and applied to the challenging process of hydrogen liquefaction. Optimization of hydrogen liquefaction processes is still an open challenge because of convergence issues and many design variables; only a handful of algorithms are considered successful. One of those algorithms, particle swarm optimization (PSO), is used here to compare computational effort and results accuracy. The percentage error of prediction of the ANN-based surrogate model compared to PSO was 4% for the minimum internal approach temperature, which is usually considered as a constraint, and 0.04% for specific energy consumption considered as the objective function. The optimization of the proposed model significantly reduced the time needed for PSO optimization of the existing model by more than 99.99%. As an extension of the current work, the ‘shallow' neural network model, with one hidden layer used in the present study, can be used to analyze the whole liquefaction process.

Artificial Neural Network-based model to predict the International Roughness Index of national highways in Nepal

Reliable predictions of pavement performance are crucial for road maintenance, rehabilitation, and reconstruction planning. To facilitate predictions of the International Roughness Index (IRI) changes over time on national highways in Nepal, this study develops a comprehensive overall model, along with regional models that consider climatic and traffic variations among the highways. The study models IRI over time using the Artificial Neural Network (ANN) approach and compares the results with those obtained from a multiple linear regression-based model. The models are developed using pavement IRI, traffic, and climatic (rainfall and temperature) data specific to national highways of Nepal, encompassing 1745 sections and 3710 total observations. The ANN-based overall model has a coefficient of determination (R2) value of 0.82 and outperforms the regression-based model, which has an R2 value of 0.76. The regional models developed for the Terai, Hill, high volume Terai and low volume Terai highways have R2 values of 0.87, 0.91, 0.85 and 0.88, respectively, indicating a good fit. Analysis of the IRI trend over time, as observed from the performance curves generated from the ANN-based model, revealed an S-shaped pattern and lower Root Mean Square Error (RMSE) compared to the regression-based model. Sensitivity analysis highlighted the initial pavement IRI as the most significant parameter in all cases. High temperature days emerged as the second most influential parameter in most models, except for the high volume Terai model, where the number of commercial vehicles serves as the second most sensitive parameter after the initial IRI.

An Overview of Demand Analysis and Forecasting Algorithms for the Flow of Checked Baggage among Departing Passengers

The research on baggage flow plays a pivotal role in achieving the efficient and intelligent allocation and scheduling of airport service resources, as well as serving as a fundamental element in determining the design, development, and process optimization of airport baggage handling systems. This paper examines baggage checked in by departing passengers at airports. The crrent state of the research on baggage flow demand is first reviewed and analyzed. Then, using examples of objective data, it is concluded that while there is a significant correlation between airport passenger flow and baggage flow, an increase in passenger flow does not necessarily result in a proportional increase in baggage flow. According to the existing research results on the influencing factors of baggage flow sorting and classification, the main influencing factors of baggage flow are divided into two categories: macro-influencing factors and micro-influencing factors. When studying the relationship between the economy and baggage flow, it is recommended to use a comprehensive analysis that includes multiple economic indicators, rather than relying solely on GDP. This paper provides a brief overview of prevalent transportation flow prediction methods, categorizing algorithmic models into three groups: based on mathematical and statistical models, intelligent algorithmic-based models, and combined algorithmic models utilizing artificial neural networks. The structures, strengths, and weaknesses of various transportation flow prediction algorithms are analyzed, as well as their application scenarios. The potential advantages of using artificial neural network-based combined prediction models for baggage flow forecasting are explained. It concludes with an outlook on research regarding the demand for baggage flow. This review may provide further research assistance to scholars in airport management and baggage handling system development.

Determining the minimum data size for the development of artificial neural network-based prediction models for rice pests in Korea

Sudden outbreaks of crop pests (insect pests and diseases) are increasing in Korea due to climate change and globalization. To prevent such outbreaks, it is necessary to predict and control pest occurrences in advance. Crop pests have been predicted through process-based or statistical modeling; however, the limitations of these models, which rely solely on historically acquired domain knowledge and data, have become increasingly prominent owing to climate change and rapidly changing agricultural ecosystems. To overcome these limitations, artificial neural network (ANN)-based models that use continuous pest survey data in the field have been investigated over the last decade. However, because pest survey data are collected by humans through process-mediated methods, fundamental problems exist in terms of data quality and size that may hinder the performance of the resulting ANN-based models. In this study, to determine the minimum pest data size required to ensure the optimal performance of ANN-based models, we developed feed-forward neural network models for 19 rice pests using 23 pest datasets collected from 149 districts by the Rural Development Administration of Korea over 19 years (2002–2020). Using each ANN-based model, the minimum data size required for the highest model performance achieved in this study was determined for all 19 rice pests. Furthermore, we developed a decision-tree rule to estimate the minimum data size based on the selected characteristics of each pest. The final Decision tree rule, based on the distinction between diseases and insect pests and the balance of pest data (the relative ratio of pest occurrence data to non-occurrence data), showed a relatively good performance (70.24 %) in the 3-fold cross-validation test. Overall, these results indicate that the minimum data sizes required for ANN modeling vary among rice pests, depending on the pest data characteristics, as indicated by the Decision tree rule developed in this study.

Deep learning-based solar power forecasting model to analyze a multi-energy microgrid energy system

Multi-energy microgrids (MEM) are a new class of power grids focusing on the distributed form of generation and integrating different energy sectors. The primary idea of MEM is to increase renewable energy share in the final energy demand while maintaining the energy balance at all times. However, integrating renewable technology into the grid has some technical limitations that must be analyzed before being deployed in the real world. This study examines the impact of increasing renewable penetration and portfolio design on a multi-energy microgrid energy system from a technical standpoint. As the accuracy of the system analysis is primarily a factor of modeling accuracy, an artificial neural network-based model is trained and deployed to develop forecasts for solar power generation. The forecasting model is integrated with the EnergyPLAN simulation tool to analyze the multi-energy microgrid system regarding renewable share in primary energy consumption and import/export of energy from the primary grid. The Norwegian energy system is considered a case study, as the energy generation and consumption patterns are interesting from both renewable energy and demand contexts for a cold country. One interesting conclusion is that the portfolio and capacities of coupling components such as combined heat and power plants negatively impact renewable integration, while heat pumps positively impact renewable integration by increasing renewable energy utilization. Additionally, the photovoltaic system size has a high degree of correlation to imports and exports compared to wind generation systems.

A neural network-based predictive decision model for customer retention in the telecommunication sector

Acquiring a new customer is far more expensive than retaining a customer. Hence, customer retention is a key aspect of business for a firm to maintain and improve on its market share and profit. The paper analyses customer retention strategies by employing an artificial neural network-based decision model to a real-life dataset collected from 311 mobile service users in India. Seven linear and non-linear adaptive models are developed using features related to customer dissatisfaction (DSF), customer disloyalty (DLF) and customer churn (CF). Findings of this study suggest that non-linear models are most efficient in predicting customer churn, and both DSF and DLF variables significantly affect the retention strategy. Three groups of customers are discussed in this study in the order of least likelihood of churning to most likelihood. Finally, a priority matrix based on key performance indicators is proposed to help service providers target potential customers to retain.

Artificial neural network-based home energy management system for smart homes

<p>Energy efficiency is widely recognized as one of the most significant and economical ways to lower greenhouse gas (GHG) emissions. The aims and goals are that smart meters can evaluate and communicate in-depth real-time electricity usage, enable remote real-time monitoring and management of power consumption, and provide consumers with real-time pricing and analyzed usage information. The house energy management controller decides which loads will be powered based on the real home energy demands and the predefined load priorities. Artificial intelligence (AI) is being used increasingly in control applications due to its great effectiveness and efficiency. As a result, in this work, the author designed, simulated, and optimized an artificial neural network-based model simulation framework that simulates a home with a variety of home appliances and optimizes the total energy consumption of the home realistically through intelligent control of home appliances. The MATLAB application was used to model and examine the performance of four common household appliances: the water heater (WH), washing machine (WM), air conditioner (AC), and refrigerator (RG). The result shows a considerable reduction and savings in energy consumption without a decrease in consumer comfort.<strong></strong></p>

Experimental investigation and artificial neural network-based modelling of thermal barrier engine performance and exhaust emissions for methanol-gasoline blends

In recent years, due to environmental concerns and the depletion of fossil fuels, alternative fuel use and alternative emission reduction methods have gained importance in the automotive industry. In addition, methanol is used as an alternative fuel in gasoline engines with coated piston engines. This study first presents an experimental investigation of engine performance and exhaust emissions for a partially thermal barrier lined piston engine operating on methanol-gasoline blends. In the second phase the obtained data is then used to develop an Artificial Neural Network (ANN) based model to predict engine performance and exhaust emissions for methanol-gasoline blends. The developed ANN model was trained and validated using MATLAB. The results of the experimental study showed that the use of methanol-gasoline blended fuel in the engine provides better engine performance and reduced exhaust emissions compared to gasoline fuel. According to the results obtained, an increase of 3.7 % in effective power and a decrease in NOx and HC emissions by 19 % and 18 %, respectively, compared to the STD case when both coating and alternative fuel are used in the engine. With the established ANN models, engine performance parameters and exhaust emission parameters were predicted with 99 % and 98 % accuracy respectively.

Surrogate model-assisted seismic resilience assessment of the interdependent transportation and healthcare system considering a two-stage recovery strategy

In this study, a two-stage post-earthquake recovery strategy optimization model is proposed for determining resource inputs and obtaining the optimal restoration sequence after earthquakes. An artificial neural network-based surrogate model for predicting the functionality of the interdependent transportation and healthcare system (ITHS) is established to avoid the significant time consumption arising from traffic assignment and path selection in functionality evaluation and recovery optimization. It is applied to the two-stage optimization and resilience assessment under different seismic scenarios, which can greatly improve computational efficiency. The resilience-based two-stage optimization decision-making method assisted by the surrogate model is applied to a real example and provides practical support for recovery strategies of the ITHS.

Artificial neural network-based modelling and prediction of white layer formation during hard turning of steels

During hard machining, steels subjected to very high thermal and mechanical loads can result in microstructural/phase changes such as the formation of a white layer. This layer, which is often harder than the raw material, is considered detrimental to the fatigue performance and in-service life of machined parts. This paper proposes a comprehensive study of white layer formation during hard machining of steels using statistical analysis and artificial neural networks (ANN) modeling. To this end, two steals, named AISI 52100 and AISI 4340, commonly used in the manufacturing of structural machines’ components and extensively studied in the last decade, have been considered in this study. First, Taguchi method combined with response surface methodology (RSM) was applied to analyze and to optimize the machining parameters regarding the white layer thickness. Second, an ANN model is developed to predict the white layer thickness during hard machining of the studied steels using a large amount of machining data. Three training algorithms were tested to find the most robust configuration. The equivalent carbon parameter was introduced for the first time in machining modeling which make the proposed ANN-based model capable of predicting the white layer thickness for different hardened steels. The results show a significant agreement between predictions and experimental results, avoiding costly experimental machining tests.