Artificial Neural Network Prediction Research Articles

Specific Heat Analysis of Water and Ethylene Glycol Based rGO-ND Hybrid Nanofluids: Experimental and Artificial Neural Network Predictions

The isobaric specific heat was measured experimentally for two kind of hybrid nanofluids like water and ethylene glycol based reduced graphene oxide-nanodiamond (rGO-ND) hybrid nanofluids at different particle volume loadings of 0.2%, 0.4%, 0.6%, 0.8% and 1.0%, and in the temperature range from 293 K to 333 K, respectively. The obtained experimental specific heat data was used for the artificial neural network (ANN) algorithms of Support Vector Regression (SVR), and Levenberg-Marquardt (LM) models for the predictions. Results indicated that, the specific heat of water, and ethylene glycol-based hybrid nanofluids at 1.0% vol. of hybrid nanofluid is lowered by 1.09% and 1.10% at a temperature of 333 K, compared to their own base fluids. The SVR and LM models for the specific heat of water-based hybrid nanofluids predict accurately with a correlation coefficient of 0.99849, and 0.99957, similarly, the SVR and LM models for the specific heat of ethylene glycol-based hybrid nanofluids predict accurately with a correlation coefficient of 0.99998, and 0.99906, respectively. The obtained data was compared with other kind of nanofluids data. The polynomial regression equation was proposed for the water and ethylene glycol-based hybrid nanofluids through the SVR model.

Experimental and artificial neural network (ANN) study on the impact of three different metal oxide nanoparticle combustion enhancers enriched on mahua biodiesel-diesel fuelled CI engine

Abstract The prediction of CI engine parameters has acquired significant attention and is regarded as a crucial tool for engine research and diagnosis studies. This contribution compares two different approaches for diesel engine viz. experimental and artificial neural networks (ANNs) predictions of performance and emission outputs. The base fuel M30 blend consist of mahua biodiesel 30 (% v) and 70 (% v) of diesel. The M30 blend and 50 ppm concentration of NPs (CeO2, CuO, and TiO2) were chosen for basic experimentation. The findings indicate an increase in BTE by 9.1%, peak CP by 11.3%, and HRR by 10.2%, with a decrease in BSFC by 13.7%, CO by 30.4%, HC by 30.1%, smoke by 34.7%, and NOx by 7.1%, resulting from the addition of 50 ppm CeO2 NP to D70M30 blend. The widely used backpropagation technique for ANN is implemented in multilayered feedforward design. To forecast the engine characteristics of a CI engine, a network structures including two inputs and one output is used. The given ANN model examined D100, M30, M30CeNP50, M30CuNP50, and M30TNP50 blends, using engine load and biodiesel with nanoparticle blend as the two input factors. A data-driven ANN model was created to forecast the optimised engine characteristics. The lowest and highest value of correlation coefficient (R2) and mean square errors (MSE), mean relative error (MRE) were found to for peak CP, HRR, BTE, BSFC, CO, CO2, HC, NOx and smoke. Using ANN one can choose right blend ratio among the variety of fuels blends for an appropriate requirement without much experimentation.

Influence and prediction of chemical composition of alfalfa on the quality and specific energy consumption of alfalfa briquettes

The chemical components and water content are related to the physical and mechanical properties of straw, affecting the processing technology that utilizes straw as energy and feed. The ratio of the viscous component to the elastic component, denoted as q, characterizes different chemical components of alfalfa. The influence of eigenvalue q on the densification of alfalfa particles was analyzed. By examining the morphology of alfalfa briquettes, the main binding mode of particles in the alfalfa briquettes was identified as the solid bridge formed by viscous components. A GA-BP-ANN artificial neural network prediction model was established to predict energy consumption and alfalfa briquette quality using q, improving the model's accuracy and stability while reducing the number of iterations. The research results contribute to determining the appropriate compression process for alfalfa, thereby promoting the efficient and high-quality utilization of alfalfa.

Bioenergy and bioexergy analyses with artificial intelligence application on combustion of recycled hardwood and softwood wastes

Novel biomass bioenergy-bioexergy analyses via thermogravimetry analysis and artificial intelligence are employed to evaluate the three biofuels from wood wastes (softwood-SW, hardwood-HW, and woods blend-WB). The chemical characterization of SW has the highest bioenergy (higher heating value – HHV: 18.84 MJ·kg-1) and bioexergy (specific chemical bioexergy – SCB: 19.65 MJ·kg-1) with the SCB/HHV ratio of wood waste as about 1.043-1.046. The high C-element has a significant influence on the HHV-SCB. The SCB/HHV ratio of wood waste is recognized as about 1.043-1.046. The three distinct zones of wood waste combustion are identified: moisture evaporation (Zone I, up to 110 °C), combustion reaction – degradation of three major lignocellulosic components (hemicelluloses, cellulose, and lignin) at Zone II, 110-600 °C, and ash remains (Zone III, 600-800 °C). The ignition (Dig=0.01-0.04) and fuel reactivity (Rfuel=3.82-6.97 %·min-1·°C-1) indexes are evaluated. The comprehensive combustion index (Sn:>5×10-7%2·min-2·°C-3) suggests that wood waste has a better combustion performance than bituminous coal. The statistical evaluation presents that the highest HHV-SCB values are obtained by performing combustion for SW-250 μm at 15 °C·min-1. The S/N ratio and ANOVA results agree that the wood waste type and particle size denote the most influential parameters. The artificial neural network prediction shows an excellent result (R2=1) with 1 hidden layer and 5 neuron configurations.

Evaluation of mathematical models and artificial neural networks for prediction of sorption isotherm in microwave pre-heated mung bean

Sorption isotherms are essential for understanding the moisture sorption behavior of foods, which is critical for optimizing drying processes, predicting shelf life, and designing effective packaging. This study examined the moisture sorption characteristics of microwave pre-treated mung beans at different temperatures (25, 35, and 45 °C) and relative humidity levels (11–85%) using gravimetric static methods. The experimental data were modeled using BET, GAB, Caurie equations, and artificial neural networks (ANNs) to assess their accuracy in describing sorption behavior. The results revealed Type II isotherms, with equilibrium moisture content increasing with temperature and decreasing with water activity. ANNs demonstrated superior predictive accuracy compared to traditional semi-empirical models. Furthermore, the microwave pre-treated samples exhibited higher predicted moisture content thresholds, limiting microbial growth, suggesting that microwave treatment improves safe storage under higher moisture conditions while preserving quality. This study emphasizes the potential of combining microwave pre-treatment and ANNs to optimize the drying, packaging, and storage of mung beans, enhancing food preservation efforts.

Modelling and optimization for material removal rate while processing bio-compatible Ti-6Al-7Nb using wire electric discharge machining (WEDM)

Abstract This study utilizes machine learning methodologies, such as artificial neural networks (ANN) and TLBO (teaching Learning Based optimisation), to develop a model and Optimisation of the Material Removal Rate (MRR) in wire electrical discharge machining (WEDM) of Ti-6Al-7Nb. The material removal rate was determined by conducting WEDM experiments with different levels of control parameters, including spark on time, spark off time, peak current, servo voltage, and wire feed rate using a Full Factorial approach through 81 runs. The most effective architecture for the ANN model was 4–10–1, and the parameters were adjusted depending on R2. The Artificial Neural Network (ANN) predictions were compared to those produced by the Multiple Linear Regression (MLR) model. The performance of these models was assessed by calculating the correlation between the experimental values and predicted values by models (R2). MRR value is optimised using TLBO (Teaching Learning Based Optimisation), keeping the relation developed by MLR as the objective function and leading to an improved material removal rate. The proposed method ANN & TLBO would help accurately predict and optimise MRR while processing Ti-6Al-7Nb. These machine learning-based methods significantly enhance complex machining processes by providing predictive capabilities & optimizing parameters, hence playing a vital role in achieving higher efficiency, quality, and adaptability in manufacturing environments.

Optimizing food waste anaerobic digestion in Kuwait: Experimental insights and empirical modelling using artificial neural networks.

This study investigates, for the first time, the anaerobic digestion of food waste in Kuwait to optimize methane production through a combination of artificial neural network (ANN) modelling and continuous reactor experiments. The ANN model, utilizing eight hidden neurons and a 70-20-10 split for training, validation and testing sets, yielded mean squared error values of 0.0056, 0.0048 and 0.0059 and coefficient of determination (R²) values of 0.9942, 0.9986 and 0.9892, respectively. Methane percentages in biogas were predicted using six parameters: biomass type, pH, organic loading rate (OLR), hydraulic retention time (HRT), temperature and reactor volume. To validate the ANN results, continuous reactor experiments were conducted under an OLR of 3 kg VS m⁻³ d⁻¹ and HRT of 20 days at varying temperatures (35°C, 40°C, 45°C, 50°C and 55°C). The experiments demonstrated optimal methane production in the mesophilic range, with ANN predictions closely aligning with experimental data up to 45°C. However, deviations were observed at higher temperatures, particularly under thermophilic conditions beyond 50°C. This study provides novel insights into waste-to-energy initiatives in Kuwait and highlights the potential of integrating computational models with empirical data to enhance biogas production processes.

ANN prediction of mode I fracture energy in epoxy adhesive joints: Adherend, adhesive, and strain rate effects

In this investigation, the mode I fracture behavior of an epoxy adhesive joint has been investigated to probe the combined effects of adherend Young's modulus and thickness, strain rate, and adhesive length. Experimental fracture testing was conducted on double-cantilever beam (DCB) specimens under three various strain rate thresholds, namely, quasi-static (0.0005 s−1), low (0.015 s−1), and intermediate (0.5 s−1). The specimens were constructed with varying adherend materials (i.e., copper, aluminum), thickness (12–20 mm), and adhesive lengths (25–75 mm). The fracture load was measured in each experiment, and the critical strain energy release rate, JCi, was calculated via a finite element analysis (FEA) in each case. Results with a 95 % confidence interval showed adherend thickness had a negligible effect within the investigated range (p-value = 0.462). JCi was significantly impacted by adhesive length (p-value = 0.009) and two other investigated parameters (p-values = 0.000). The development of artificial neural networks (ANNs) with Levenberg-Marquardt (LM) led to the prediction of JCi based on the examined parameters. With a mean absolute percentage error (MAPE) of 8.9 % and a mean squared error (MSE) of 683 J2/m4 on unseen test data, the ANN model built in this study was able to predict the JCi in epoxy adhesive joints, indicating its potential to produce an accurate prediction for JCi in epoxy adhesive joints. This work offers insights for precise fracture behavior prediction under mode I stress conditions as well as some helpful information that can be utilized to optimize adhesive joint design.

Using data-driven models to simulate the performance of surfactants in reducing heavy oil viscosity

There is a substantial body of literature exploring the challenges associated with exploring and exploiting these underground resources. Unconventional resources, particularly heavy oil reservoirs, are critical for meeting ever-increasing global energy demand. By injecting surfactants into heavy oil, chemically enhanced oil recovery (EOR) may enable emulsification, which may reduce the viscosity of heavy oil and facilitate extraction and transportation. In this work, a large experimental dataset, containing 2020 data points, was extracted from the literature for modeling oil-in-water (O/W) emulsion viscosity using machine learning (ML) methods. The algorithms used pressure, temperature, salinity, surfactant concentration, type of surfactant, shear rate, and crude oil density as inputs. For this purpose, five ML algorithms were selected and optimized, including adaptive boosting (AB), convolutional neural network (CNN), ensemble learning (EL), artificial neural network (ANN), and decision tree (DT). A combined simulated annealing (CSA) method was utilized to optimize all algorithms. With AARE, R2, MAE, MSE, and RMSE values of 8.982, 0.996, 0.004, 0.0002, and 0.0132, respectively, the ANN predictor exhibited higher accuracy in predicting O/W emulsion viscosity for total data (train and test subsets combined). A Monte-Carlo sensitivity analysis was also performed to determine the impact of input features on the model output. By using the proposed ML predictor, expensive and time-consuming experiments can be eliminated and emulsion viscosity predictions can be expedited without the need for costly experiment.

Assessment of Socioeconomic Vulnerability in Selected Villages of Gosaba Block, Sundarban, India Using an Artificial Neural Network

The Indian Sundarban represent an endangered ecosystem with a distinct biogeographical composition. It is susceptible to natural disasters like storms, floods, and cyclones, hence jeopardizing its socioeconomic systems due to environmental stresses. This study aimed to evaluate the present socioeconomic vulnerability, identify key factors that exacerbate this vulnerability, and validate these factors using an Artificial Neural Network (ANN) prediction model. Researchers also wanted to validate this evaluation with ANN to promote substantive discussions between researchers, local authorities, and stakeholders. Comprehensive reviews and successful adaption plans will improve. The study conducted in selected villages with 160 households in the Gosaba Block, located on the periphery of the Sundarban. The present study employed an integrated vulnerability approach, calculating the exposure, adaptive capacity, and sensitivity index by weighting the initial eigenvalues of each indicator with a variance percentage through principal components analysis (PCA). Based on this criterion, 156 households (97.5%) exhibited an extremely high vulnerability score, while 4 households (2.5%) displayed a moderate vulnerability grade. The villages of Pakhiralay and Lahiripur exhibit significant vulnerability, with a markedly deficient adaptive capacity. The villages of Mathurakhand, Kumirmari, and Satjelia exhibit vulnerability alongside moderate adaptation capacity. All are priority villages, however, Villages with moderate adaptive capacity may become less vulnerable with adequate interventions Proximity to market strongly affects MLP neural networks' assessment of environmental, economic, and social variables' effects on exposure, sensitivity, and adaptive capacity. Respondent age, family size, social network, storm surges, supplementary sources of household income Dwelling years, temperature, embankment failure, and income greatly affect model performance. A policy initiative should prioritize the enhancement existing social and financial capital, facilitate access to local government, and promote community-oriented activities. National disaster, social welfare, and resource management strategies need separate action plans. The national government is also encouraged to decentralize governance to enable local governments to achieve their goals.

Optimizing Cylindrical Grinding Proficiency and Surface Finish for EN24 Steel Alloy with the Use of Taguchi Analysis and Artificial Neural Network

Grinding is a material removal procedure used at the end of manufacturing to obtain high dimensional precision and a desirable surface polish. External cylindrical grinding is a type of grinding procedure that used to grind cylindrical things such as engine shafts, connecting rods, spindles, and axles. This study examines how control settings affect response parameters using EN24 alloy steel on a cylindrical grinding machine. Response parameters are material removal rate (MRR) and surface roughness (Ra), whereas control parameters are workpiece speed (v), feed rate (f), and depth of cut (d). Taguchi DOE is employed with L16 orthogonal array to optimize control parameter levels, followed by cylindrical grinding tests.An artificial neural network (ANN) model was created to validate and predict cylindrical grinding reaction parameters. To train the network, experimental data was used, and ANN predictions were compared to real data. Data collection has also completed.In the purposed work minimum Ra is 0.52 µm and maximum MRR is 0.6588 g/sec found and results indicate that feed rate and workpiece speed are the most dominating parameters of cylindrical grinding. The experimental results can be employed by various manufacturing and industrial firms and they can select suitable combinations of input parameters for desired Ra and MRR

Performance assessment of sustainable asphalt concrete using steel slag, with an artificial neural network prediction of asphalt concrete behavior

This research evaluated the possibility of using Moroccan steelworks slag as a substitute for natural aggregates in asphalt mixtures, using chemical and mechanical analyses to demonstrate its compatibility with this application. Two granular mixtures, M1 and M2, were developed, incorporating respectively 15 % and 25 % natural sand (0/1.25) with slag aggregates to obtain granular mixtures complying with local standards. These mixtures were then tested with three different asphalt contents (4.7 %, 5.2 %, and 5.7 %). Mechanical tests, including a gyratory compactor, Marshall stability, and Duriez strength, were carried out. In particular, the M1:5.2 and M2:5.2 mixtures met compaction criteria and showed remarkable Marshall Stability values, reaching 23.49 kN and 21.81 kN respectively. In comparison, the control mixtures only achieved a maximum stability of 11 kN. Thermal properties were also assessed, showing that the maximum thermal conductivity was achieved at an asphalt content of 5.2 %. The slag-based mixtures, M1 and M2, showed higher thermal conductivity than the control mix M0, with maximum values of 0.74 W/mK for M1 and 0.86 W/mK for M2, compared with 0.56 W/mK for M0. The overall results show that the M1 and M2 mixtures had improved thermal and mechanical properties compared with the M0 control mix. Artificial neural network (ANN) modelling was carried out using Marshall Test data. It showed excellent performance in predicting the stability and flow properties of asphalt mixtures. These results suggest that incorporating steelmaking slag into asphalt concrete mixtures was an effective strategy for simultaneously improving their thermal and mechanical properties.

Prediction of evaporation temperature in air-water heat source heat pump based on artificial neural network

To improve the low-temperature heating stability and performance of the air-source heat pump (ASHP), a heat transfer model was established for an air-water heat source heat pump (A-WSHP) in this study. Key factors affecting A-WSHP evaporating temperature were analyzed through simulation. An artificial neural network (ANN) prediction model for refrigerant evaporating temperature was developed using fin pitch, air velocity, air temperature, spray flow rate, spray water temperature, and droplet diameter as inputs. In the winter climate of Xiangtan City, this model predicts the refrigerant evaporating temperature and regulates it by adjusting various input parameters. Results indicate that fin pitch and droplet size significantly impact the refrigerant evaporating temperature, more so than fin thickness. The air temperature (34.78 %) and spray water temperature (38.02 %) have the highest weights, while fin thickness has the least influence, with a weight of 0.75 %. The R2 value of the ANN refrigerant evaporating temperature prediction model is 0.974, indicating a good fit. By properly adjusting the heat pump fan and spray valve, changes in air velocity and spray flow rate can enhance the refrigerant evaporating temperature, leading to stable and efficient heat pump operation. This research not only provides a theoretical basis for the operational strategy of air-water heat pumps but also offers guidance for frost-free operation in low-temperature environments.

Examining the personal growth of college teacher educators through the lens of human development ecology: An approach utilizing artificial neural networks (ANNs) modeling

College teacher educators play a crucial role in improving teaching quality and have a significant impact on educational development. They must engage in a process of self-growth to achieve personal development, considering the interaction between individuals and their environment. This process involves deep exploration of their knowledge, skills, and attitudes, as well as an understanding of the broader institutional and cultural contexts. Through self-reflection and continuous learning, college teacher educators can foster personal growth by acquiring new teaching strategies, developing effective communication and interpersonal skills, and cultivating a reflective and adaptive teaching practice. Collaboration with colleagues, engagement with professional communities, and involvement in educational research and innovation are also essential aspects of personal growth. Creating supportive environments that facilitate the continuous development of college teacher educators is crucial for enhanced teaching quality and educational advancement. In this study, an artificial neural network (ANN) was employed to estimate the impact of changes in knowledge and skill development and reflection and continuous learning on the acquisition of new educational strategies, development of communication and interpersonal skills, and reflective and adaptive practice. The ANN's predictions indicate that increasing reflection and continuous learning has a more positive impact on acquiring new educational strategies compared to increasing knowledge and skill development alone. Additionally, when both knowledge and skill development and reflection and continuous learning are combined, it results in substantial growth in the development of communication and interpersonal skills and reflective and adaptive practice. The accuracy of the neural network's predictions was evaluated using linear regression, showing an acceptable level of error when compared to the experimental results.

Estimation of biogas potential from poultry manure to 2040 in Türkiye using time series and the artificial neural network (ANN)

The number of poultry in Türkiye constituted approximately 24 % of Europe’s total in 2020. Although Türkiye has a significant number of poultry animals, it has been relatively unsuccessful in terms of managing the associated poultry waste. The present study focuses on poultry manure-based biogas potential (PMBP), which represents an alternative means of poultry manure management in Türkiye. PMBPs were calculated for each year from 2003 to 2021, for which it was found that for 2021, Türkiye's PMBP had increased by 40 % since 2003, reaching 3469 GWh. The possible electrical energy savings that PMBP could provide for lighting, habitation, business, government offices, and industry throughout Türkiye were calculated, with PMBP spatial distribution maps for 2021 created according to geographical region and province. The province with the highest PMBP was found to be Manisa, at 390 GWh. The projected PMBPs were calculated to 2040 using the artificial neural network (ANN) and autoregressive integrated moving average (ARIMA). According to ARIMA, the PMBP for 2040 could potentially be increased by as much as 32 % from that of 2021, while according to ANN predictions, this same increase could be as much as 72 %. The ability to reduce greenhouse gas emissions resulting from poultry manure management in Türkiye through biogas production was calculated. Investors may need to prepare a feasibility study for the establishment of a biogas plant in a suitable region within Manisa province, as it has the highest PMBP among the regions evaluated.

Prediction of Performance and Emissions Diesel Engines Fueled-Biodiesel Using Artificial Neural Network (ANN) Resilient Backpropagation Algorithm (Rprop)

In order to increase energy security and improve environmental quality, the Indonesian Goverment set a target of 23% renewable energy mix in 2025, one of which is the Mandatory Bioediesel Program. A higher biodiesel blending ratio will affect the performance and emissions of diesel engines because biodiesel is chemically different from diesel oil. Research related to the prediction of diesel engine performance and emissions using Artificial Neural Network (ANN) has been conducted, but the author sees a research opportunity for the implementation of the ANN Resilient Backpropagation (Rprop) algorithm. The data used to create the ANN model prediction was secondary data from previous research. The model designed multi input and multi output (MIMO) with 4 input variables and 7 output variables. Model building done by varying the number of neurons and hidden layers. Model evaluation selected based on the largest coefficient of determination parameter R2 and the smallest RMSE or MAPE. The results showed that the ANN single layer 4-20-7 network architecture is the best model for predicting diesel engine performance and emissions with test data R2 , RMSE and MAPE of 0.962532, 6.699428 and 6.0% respectively, while for overall data testing has a performance of 0.982869, 3.908542 and 4.3%. The results also show that based on the ANN prediction results, the increasing biodiesel ratio can increase NOx emissions and decrease HC, CO and CO emissions2 . In terms of performance, the addition of biodiesel can increase BSFC and BP and decrease BTE. The results also show that the addition of ZnO concentration can reduce emissions while in terms of performance it will increase BTE and reduce BSFC and BP.

Artificial intelligence as a tool for predicting the quality attributes of garlic (Allium sativum L.) slices during continuous infrared-assisted hot air drying.

Effective drying methods are a highly suitable solution for ensuring stable food supply chains, reducing postharvest agricultural losses, and preventing the spoilage of perishable fruits and vegetables. Moreover, machine learning techniques are innovative and dependable, especially in addressing food spoilage and optimizing drying processes. This study utilized a continuous infrared (IR) hot air dryer to dry garlic (Allium sativum L.) slices. The experiments were conducted at different levels of IR power, air velocities (V), and temperature (T). The relationships between the input process parameters (IR, T, and V) and response parameters, including effective moisture diffusivity (Deff), drying time, and physicochemical properties of the dried slices (rehydration ratio [RR], total color change, flavor strength, and allicin content in the garlic), were modeled using an artificial neural network (ANN). Our findings showed that the maximum Deff of 6.8×10-10m2/s and minimum drying time of 225min were achieved with an IR of 3000W/m2, an air velocity of 0.7m/s, and a temperature of 60°C. The total color change and RR values increased with IR and higher air temperature but declined with higher air velocity. Furthermore, the garlic's flavor strength and allicin content levels decreased as the IR and air temperature increased. The results demonstrated a significant influence of the independent parameters on the response parameters (p<0.01). Interestingly, the ANN predictions closely matched the test data sets, providing valuable insights for understanding and controlling the factors affecting drying behaviors.

Artificial neural network models for forecasting the extracted yield of essential oils from Curcuma longa L. by hydro-distillation

Abstract Turmeric is commonly acknowledged in traditional medical practices for its strong healing properties. In the present work, hydro-distillation was employed to extract essential oils from turmeric powder. The response surface methodology (RSM) was applied to investigate the effects of various parameters, including evaporation rate (0.23, 0.5, 0.8, 0.97, 1.36, 2 ml/min), solid/liquid ratio (4:100, 6:100, 8:100, 1:10, 11:100 g/ml), and extraction duration (13–250 min) on the yield of essential oils. The central composite design (CCD) proved to be an effective tool for evaluating the extraction yield of essential oils. A three-layer artificial neural network (ANN) was utilized to develop the extraction model, employing the Levenberg–Marquardt (LM) optimization algorithm. The neural network’s input layer comprised the solid/liquid ratio, evaporation rate, and extraction time, while the output layer indicated the yield of essential oil extraction. The most appropriate model included a hidden layer with 16 neurons, achieving R 2 and MSE values of 0.9989 and 0.0013, respectively. This investigation indicates that an artificial neural network prediction model serves as an effective method for estimating essential oil yield.

Prediction of polarization curves of PEMFC membrane electrode assembly using artificial intelligence technics

Proton exchange membrane fuel cells (PEMFCs) are used commercially in automobiles, buses, uninterruptible power supplies, and combined heat power systems, holding a significant place in the fuel cell market. Fuel cell performance is characterized by polarization curves in design and manufacturing processes. This study predicts a PEMFC’s polarization curves using comparative artificial intelligence (AI) models trained and tested under different operational conditions. The AI model inputs are cell temperature, humidity, anode-cathode flow, and membrane resistance. The outputs are cell voltage and current density. The model outputs are compared with experimental values for 50°C, 100% humidity using MATLAB software. The average Root Mean Square Error (RMSE) for the ANFIS prediction is 0.056112, while for the ANN prediction it is 0.011919. These results indicate that the Artificial Neural Network (ANN) method outperforms the Adaptive Neuro Fuzzy Inference System (ANFIS) in predicting the behavior of the PEMFC’s Membrane Electrode Assembly (MEA). The models showed promising results with high accuracy.

Thermophysical properties, and figures-of-merit analyses of nanodiamond/CuO ionanofluids: Experimental and artificial neural network predictions

The nanodiamond/copper oxide (ND/CuO) nanoparticles were dispersed into 1-ethyl-3-methylimidazolium chloride [EMiM]Cl to create ionanofluids. The experiments were performed to analyse the thermophysical properties under particle volume loadings from 0.2 % to 1.0 %, and temperature ranging from 30 to 60 °C. Theoretical approach was made to understand the Figures-of-Merit (FoM) of the prepared ionanofluids, while they flow in a tube, and helical coil through the evaluated thermophysical properties. The lower thermal conductivity augment of 14.27 % was noticed at 0.2% vol. and larger thermal conductivity enhancement of 35.20 % was noticed at 1.0% vol. and at a temperature of 60 °C, against the base fluid. Moreover, the viscosity of 1.0% vol. of ionanofluid was enhanced by 61.66 % at a temperature of 30 °C, over the base fluid. The other properties like density was increased with an increase of volume loadings, and specific heat was decreased with an increase of volume loadings. The FoM results indicated that, all the prepared volume concentrations of ionanofluids flow in a tube was benefited fluid when the fluid operating temperature was exceeds to 35 °C, on the other side, the prepared ionanofluids flow in a helical coil was benefited fluid when its operating temperature was above 30 °C for 0.8 %, and 1.0% vol. loadings. The estimated thermophysical properties were also used as input and output data for an artificial neural network of Levenberg-Marquardt (LM) algorithm. It is noticed from the LM algorithm results, the predicted data is well agreed with an experimental data. For all the data, the correlation coefficient (R2) of thermal conductivity is 0.99283, viscosity is 0.9971, density is 0.99887, and specific heat is 0.99817, was observed, respectively.