Multilayer Artificial Neural Network Model Research Articles

Neural Network Modelling for Prediction of Coagulant Dosage

Water treatment plants (WTP) in Indonesia commonly applied conventional treatment that, among others, relies on the coagulation process to treat turbid surface water to produce clean and safe water for daily purposes. Meanwhile, standard Jar-Test methods for coagulant dosage determination are inefficient, inaccurate, and possibly will not function well for water with high variability of quality. This study aims to improve and optimize the coagulant dosing process by considering the main parameter that greatly affects the coagulation process, i.e., turbidity. For this purpose, a multilayer artificial neural network model (ANN) with an adaptive backpropagation algorithm was developed using MATLAB software. A network architecture with 1 input, 5 hidden and 1 output was implemented. For the input, 4465 turbidity data of the raw water taken from Surabaya Municipal Water Enterprise (PDAM) were used, while the output is the optimal dose obtained from the results of the Jar-test. This study resulted in an empirical model of the optimum dosage of coagulants as a function of the turbidity of the raw water. Training and testing on the given ANN resulted in R2 (determination coefficient) of 0.99444 from regression analysis with the following equation: output = 0.99 x target + 0.66. This study showed that the ANN model provides a very high success rate for coagulant dose prediction.

Pressure drop for subcooled water boiling in microchannels under high heat fluxes: Experiments and predictions from artificial neural networks

Subcooled flow boiling in microchannels holds considerable promise in compact cooling applications. This study reports experimental measurements of the pressure drop of subcooled flow boiling of water in microchannels with inner diameters ranging from 0.5875 mm to 2 mm. The experiments are conducted over a range of operating parameters, including q = 3.0–10 MW/m2, p = 3.0–5.0 MPa, and G = 2000–10,000 kg/(m2∙s). The influences of diameter, heated length, and operating parameters are comprehensively analyzed. The results indicate that an increase in heat flux and pressure leads to an advancement of the pressure drop under the same thermodynamic vapor quality. Furthermore, a multi-layer artificial neural networks model optimized by a genetic algorithm is established using over 1000 experimental data. This model is employed to predict the subcooled boiling pressure drop and determine the optimal dimensionless parameter combination for developing a new pressure drop empirical correlation. The optimal combination of parameters includes Ja, ρl/ρg, Lsb/Lsat, Co and We, and the new correlation is proposed to calculate subcooled boiling pressure drop for high-heat-flux and microchannels applications, exhibiting a mean absolute error (MAE) of 10.64%. The results provide a novel approach that integrates machine learning techniques with empirical correlation, aiming to meet the requirements of the design optimization for thermal management solutions.

A combined scheme of parallel-reaction kinetic model and multi-layer artificial neural network model on pyrolysis of Reed Canary

A comprehensive understanding of pyrolysis kinetics is crucial for the design of biomass pyrolysis. In this study, a combined scheme was proposed for biomass pyrolysis. A kinetic model, serving as a knowledge-based model, was established to capture the primary trend of biomass pyrolysis. An ANN model, as an experience-based model, was developed to provide “details” on the process. The kinetic model incorporated a least-square optimization model to calculate optimal kinetic parameters for pyrolysis reaction steps. The ANN model utilized metaheuristic algorithms such as Particle Swarm Optimization, Pattern Search, Genetic Algorithms, and Surrogate Optimization to optimize the hyperparameters of the ANN model. By combining the kinetic model with the ANN model, comprehensive predictions of biomass pyrolysis were obtained, and the combined Kinetic-ANN model was validated with experimental data at 4 heating rates. Finally, the combined model was compared with the solo-kinetic and solo-ANN models, confirming the advanced performance of the combined approach.

Reliability study of generalized Rayleigh distribution based on inverse power law using artificial neural network with Bayesian regularization

Using the generalized Rayleigh distribution and the inverse power law, this paper proposes a new reliability model and investigates the effect of the key parameters on reliability measurements. This proposed new model offers a more accurate way to model the performance of electronic components over their lifetimes. In order to analyze the reliability parameters, a multi-layer artificial neural network model has been developed by using the datasets generated by numerical methods and obtained in four different scenarios. Using the artificial neural network model with 5 neurons in the hidden layer, the reliability parameters Hazard Rate Function, Odds function, Reversed Hazard Rate Function, Mean Time to Failure and Mean Time Between Failures have been estimated. The results obtained have been analyzed comprehensively and explained with graphics. The study findings showed that there was a direct relationship between the reliability parameters examined in all scenarios and an increase in the Mean Time Between Failures value appeared for each scenario. However, it has also been seen that the developed artificial neural network can make predictions with very high accuracy and is a powerful engineering tool that can be utilized in reliability analysis.

Prediction of Compressive Strength of Fly Ash-Slag Based Geopolymer Paste Based on Multi-Optimized Artificial Neural Network.

The fly ash-slag geopolymer is regarded as one of the new green cementitious materials that can replace cement, but it is difficult to predict its mechanical properties by conventional methods. Therefore, in the present study, the back propagation (BP) artificial neural network technique is used to predict the compressive strength of the fly ash-slag geopolymer. In this paper, data from the published literature were collected as the training set and the experimental results from laboratory experiments were used as the test set. Eight input parameters were determined, as follows: the percentage of fly ash, the percentage of slag, the water-cement ratio, the curing age, the modulus of alkali activator, the mass ratio of NaOH to Na2SiO3 and the moles of Na2O and SiO2 in the alkali activator. Three multilayer artificial neural network models were constructed using the Levenberg-Marquardt (LM), Bayesian regularization (BR) and scaled conjugate gradient (SCG) algorithms to compare the prediction accuracy of the compressive strength of the fly ash-slag geopolymer paste at different ages (3, 7, and 28 d). It was concluded that the training set error of the BR-BP neural network was the smallest. Ultimately, the hyperparameter optimization of the BR-BP neural network was carried out to compare the training set and the test set errors before and after the optimization, and the results show that the BR-BP neural network model with hyperparameter optimization had the highest prediction accuracy.

Using Artificial Neural Network Application in Modeling the Mechanical Properties of Loading Position and Storage Duration of Pear Fruit

In the study, rupture energy values of Deveci and Abate Fetel pear fruits were predicted using artificial neural network (ANN). This research aimed to develop a simple, accurate, rapid, and economic model for harvest/post-harvest loss of efficiently predicting rupture energy values of Deveci and Abate Fetel pear fruits. The breaking energy of the pears was examined in terms of storage time and loading position. The experiments were carried out in two stages, with samples kept in cold storage immediately after harvest and 30 days later. Rupture energy values were estimated using four different single and multi-layer ANN models. Four different model results obtained using Levenberg–Marquardt, Scaled Conjugate Gradient, and resilient backpropagation training algorithms were compared with the calculated values. Statistical parameters such as R2, RMSE, MAE, and MSE were used to evaluate the performance of the methods. The best-performing model was obtained in network structure 5-1 that used three inputs: the highest R2 value (0.90) and the lowest square of the root error (0.018), and the MAE (0.093).

Towards Predictive Maintenance of a Heavy-Duty Gas Turbine A New Hybrid Intelligent Methodology for Performance Simulation

As the increasing demands of global clean power for the main purpose of lowering environmental pollution, heavy-duty gas turbines are playing an increasingly important role in energy fields because of their low emission, high thermal efficiency and flexible start-up capacity. Accurate modeling and simulation of the turbine performance is extremely needed to precisely design a large-watt industrial heavy-duty gas turbine, which is still very challenging due to the high nonlinearity, system complexity, varying conditions, and strong coupling interaction of high-dimension parameters under the harsh operation environment of the turbine. In order to improve the accuracy and efficiency of the performance simulation model for a heavy-duty gas turbine at various operating conditions, this paper presents a new hybrid intelligent methodology to adeptly integrate system thermodynamic balance mechanism with multivariate data by seamlessly combing advanced signal processing, machine learning and artificial neural network modeling techniques. The thermodynamic model of a complicated single-shaft gas turbine is first created based on the balances of both flow and power in various subsystems including inlet, compressor, turbine, combustor and exhaust. The characteristic curves of compressor and turbine are utilized to accurately represent the physical mechanism and effectively simulate the high nonlinear behaviors of subsystems. Wavelet signal processing and machine learning based feature extraction are employed to preprocess the multivariate raw data of the turbine. Multilayer artificial neural network models are explored to efficiently simulate the start-up transient process of the turbine, thus improve the simulation efficiency and accuracy of the complicated system. Multivariate data collected from a real-world industrial heavy-duty gas turbine is employed to illustrate the effectiveness and feasibility of the proposed methodology.

Investigation of the usability of machine learning algorithms in determining the specific electrical parameters of Schottky diodes

Schottky diodes continue to be the favorite of the electronics industry with their ever-expanding usage areas. The electrical parameters that can be obtained by the characterization of Schottky diodes are of high importance as they provide important information in terms of the usage area of the diode. In this study, the usability of the machine learning algorithm has been investigated in the determination of important electrical parameters such as ideality factor, barrier height and resistance of Schottky diodes. Voltage and temperature values were defined in the hidden layer of the multi-layer artificial neural network model, which was developed with a total of 368 data sets, and current values were estimated in the output layer. The developed neural network model was able to predict the electrical parameters of Schottky diodes with an average deviation of 0.11%. Using the data obtained from the artificial neural network, the Ideality factor was calculated with an error margin of 1.645, and the resistance value with a margin of error of 5.694.

An Estimation of the Performance of a Passive Cooling System Incorporating a Ground Heat Exchanger Using a Multilayer Artificial Neural Network

Objective: This paper examines the cooling of an office building without a heat pump, using only ground heat exchangers (GHE) and implementing artificial neural network (ANN) to train it on experimental data. Methods: The office building is situated at 38° 40' 57" N latitude and 39° 10' 29" E longitude in the province of Elazig. Each minute, the installed system was monitoring the office's external meteorological data, the office's indoor meteorological data, the GHE inlet and outlet temperatures, and the amount of heat load developed during the cooling process. In this study, the passive cooling system's cooling load and coefficient of performance (COP) were experimentally examined. A second important contribution of this paper is the multilayer ANN model that was created using data selected from the experimental setup, which was measured and recorded. Results: During the summer months of 2018, the COP of the system was measured to be 1.67 on average. The accuracy rates of the multilayer ANN model proposed for cooling systems were calculated to be over 99% and 95% in the training and test datasets, respectively. It was observed that the performance value estimated by ANN converges to the true value by 99%. Conclusion: Having performed this study, it has been demonstrated that passive cooling can be achieved with GHE, and by conducting this study without utilizing a heat pump system, we intend to contribute significantly to the relevant scientific literature.

Artificial neural network model and multi-objective optimization of microchannel heat sinks with diamond-shaped pin fins

In this study, laminar, steady-state, incompressible flow with conjugate heat transfer was investigated for one flow passage of a microchannel with staggered diamond-shaped pin fin array. CFD analyzes were performed with OpenFOAM for various configurations and in all cases, the rhomboidal area of each pin fin was kept constant at 0.16 mm2, and the bottom surface of the substrate was subjected to a uniform heat flux of 69.3 kW/m2. Water with temperature-sensitive viscosity was taken as the cooling fluid, and copper with constant thermophysical properties was used for the solid domain. Parametric analyzes have been conducted for various combinations of geometric design variables such as pin fin angle (α), longitudinal pitch-to-diameter ratio (SL/D) and transverse pitch-to-diameter ratio (ST/D) with the flow attribute represented by pin fin Reynolds number (ReD). In the parametric investigations, α ranged from 30∘ to 90∘; ReD ranged from 20 to 100, and SL/D and ST/D were between 2.5 and 4.5. A multi-layer artificial neural network model (ANN), which was coded in Python and trained with parametric CFD results, was utilized to estimate off-design pin fin Nusselt numbers (NuD) and pin fin Poiseuille numbers (PoD), two objective functions representing thermal and hydrodynamic character, respectively. Non-dominated Sorting Genetic Algorithm (NSGA-II) was used to optimize the microchannel configuration, in which the individuals have been evaluated based on the multi-layer neural network prediction model. The constructed multi-layer neural network model predicted NuD and PoD with average errors of 1.39% and 1.02%, respectively. Among all design variables considered, α was found to be the most dominant one on NuD and PoD. Following the genetic algorithm, the majority of the optimal solutions appeared at ST/D around 2.5 and at ReD equal to 20 or 100. Over the entire range of ReD, NSGA-II suggested combinations of optimal α and SL/D yielding 4<NuD<11 and 6<PoD<32 appropriate for thermal or hydrodynamic demands.

Comparative study of artificial neural network versus parametric method in COVID-19 data analysis

Since the previous two years, a new coronavirus (COVID-19) has found a major global problem. The speedy pathogen over the globe was followed by a shockingly large number of afflicted people and a gradual increase in the number of deaths. If the survival analysis of active individuals can be predicted, it will help to contain the epidemic significantly in any area. In medical diagnosis, prognosis and survival analysis, neural networks have been found to be as successful as general nonlinear models. In this study, a real application has been developed for estimating the COVID-19 mortality rates in Italy by using two different methods, artificial neural network modeling and maximum likelihood estimation. The predictions obtained from the multilayer artificial neural network model developed with 9 neurons in the hidden layer were compared with the numerical results. The maximum deviation calculated for the artificial neural network model was −0.14% and the R value was 0.99836. The study findings confirmed that the two different statistical models that were developed had high reliability.

Reliability modeling and analysis of mixture of exponential distributions using artificial neural network

In recent years, statisticians have become more and more interested in the study of mixture models, especially in the last decade, without adequately considering the difficulty of modeling the reliability measures of mixture models using artificial neural networks. In this study, in which artificial neural networks and mixed model reliability criteria are analyzed, various reliability parameters are calculated considering different scenarios. In order to estimate the obtained numerical reliability parameters, a multilayer artificial neural network model has been developed. Seven different reliability parameter values have been obtained from the artificial neural network model designed with four input parameters. The prediction values obtained from the artificial neural network model developed with five neurons in the hidden layer have been compared with numerical data, and the performance of the model has been analyzed comprehensively. The mean squared error (MSE) value for the network model has been calculated as 1.98E‐08 and the R value as 0.99991. The results clearly revealed that the artificial neural network model developed using data from the appropriate statistical model is an excellent tool that can be used to estimate reliability measures.

Reference evapotranspiration modeling using radial basis function neural network in different agro-climatic zones of Chhattisgarh

Precise estimation of evapotranspiration (ET) is extremely essential for efficient utilization of available water resources. Among the empirical models, FAO-Penman-Monteith equation (FAO-PM) is considered as standard method to determine reference evapotranspiration (ET ). In developing countries like India, application of FAO-PM equation for ET estimation has certain limitations due to unavailability of specific data requirements. Several empirical models such as Hargreaves, Turc, Blaney-Criddle etc., arealso considered for ET estimation. However, ET estimates obtain with these models are not comparable with benchmark FAO-PM ET . To address this issue, potential of radial basis function neural network (RBFNN) is investigated to estimate FAO-PM ET . Result obtained with proposed RBFNN models are compared with equivalent multi-layer artificial neural network (MLANN) and empirical approach of Hargreaves, Turc and Blaney-Criddle. Lower RMSE values obtained with RBFNN and MLANN models is an indication of improved performance over empirical models. Similarly, higher R2 and Efficiency Factor obtained with RBFNN and MLANN models also approves the superiority of machine learning techniques over empirical models. Among the two machine learning techniques, RBFNN models performed better as compared to MLANN. In a nut shell, proposed RBFNN models can simulate FAO-PM ET even with limited meteorological parameters and consistence degree of accuracy level.

Forecasting the CO2 Emissions at the Global Level: A Multilayer Artificial Neural Network Modelling

Better accuracy in short-term forecasting is required for intermediate planning for the national target to reduce CO2 emissions. High stake climate change conventions need accurate predictions of the future emission growth path of the participating countries to make informed decisions. The current study forecasts the CO2 emissions of the 17 key emitting countries. Unlike previous studies where linear statistical modeling is used to forecast the emissions, we develop a multilayer artificial neural network model to forecast the emissions. This model is a dynamic nonlinear model that helps to obtain optimal weights for the predictors with a high level of prediction accuracy. The model uses the gross domestic product (GDP), urban population ratio, and trade openness, as predictors for CO2 emissions. We observe an average of 96% prediction accuracy among the 17 countries which is much higher than the accuracy of the previous models. Using the optimal weights and available input data the forecasting of CO2 emissions is undertaken. The results show that high emitting countries, such as China, India, Iran, Indonesia, and Saudi Arabia are expected to increase their emissions in the near future. Currently, low emitting countries, such as Brazil, South Africa, Turkey, and South Korea will also tread on a high emission growth path. On the other hand, the USA, Japan, UK, France, Italy, Australia, and Canada will continuously reduce their emissions. These findings will help the countries to engage in climate mitigation and adaptation negotiations.

A novel fractional discrete grey model with an adaptive structure and its application in electricity consumption prediction

PurposeElectricity consumption prediction has been an important topic for its significant impact on electric policies. Due to various uncertain factors, the growth trends of electricity consumption in different cases are variable. However, the traditional grey model is based on a fixed structure which sometimes cannot match the trend of raw data. Consequently, the predictive accuracy is variable as cases change. To improve the model's adaptability and forecasting ability, a novel fractional discrete grey model with variable structure is proposed in this paper.Design/methodology/approachThe novel model can be regarded as a homogenous or non-homogenous exponent predicting model by changing the structure. And it selects the appropriate structure depending on the characteristics of raw data. The introduction of fractional accumulation enhances the predicting ability of the novel model. And the relative fractional order r is calculated by the numerical iterative algorithm which is simple but effective.FindingsTwo cases of power load and electricity consumption in Jiangsu and Fujian are applied to assess the predicting accuracy of the novel grey model. Four widely-used grey models, three classical statistical models and the multi-layer artificial neural network model are taken into comparison. The results demonstrate that the novel grey model performs well in all cases, and is superior to the comparative eight models.Originality/valueA fractional-order discrete grey model with an adaptable structure is proposed to solve the conflict between traditional grey models' fixed structures and variable development trends of raw data. In applications, the novel model has satisfied adaptability and predicting accuracy.

Modelling of Nicotiana Tabacum L. Oil Biodiesel Production: Comparison of ANN and ANFIS

Among the modern computational techniques, Artificial Neural Network (ANN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) are preferred because of their ability to deal with non-linear modelling and complex stochastic dataset. Nondeterministic models involve some computational complexities while solving real-life problems but would always produce better outcomes. For the first time, this study utilized the ANN and ANFIS models for modelling tobacco seed oil methyl ester (TSOME) production from underutilized tobacco seeds in the tropics. The dataset for the models was obtained from an earlier study which focused on design of the experiment on TSOME production. This study is an an exposition of the influence of transesterification parameters such as reaction duration (T), methanol/oil molar ratio (M:O), and catalyst dosage on the TSOME/biodiesel yield. A multi-layer ANN model with ten hidden layers was trained to simulate the methanolysis process. The ANFIS approach was further implemented to model TSOME production. A comparison of the formulated models was completed by statistical criteria such as coefficient of determination (R2), mean average error (MAE), and average absolute deviation (AAD). The R2 of 0.8979, MAE of 4.34468, and AAD of 6.0529 for the ANN model compared to those of the R2 of 0.9786, MAE of 1.5311, and AAD of 1.9124 for the ANFIS model. The ANFIS model appears to be more reliable than the ANN model in predicting TSOME production in the tropics.

Differential evolution based radial basis function neural network model for reference evapotranspiration estimation

The present study is an effort to examine the capability of a differential evolution based radial basis function neural network (RBFDE) to model weekly reference evapotranspiration (ET0) as a function of climatic parameters in different agro-climatic zones (ACZs) of a moist sub-humid region in East-Central India. The ET0 computed using the empirical equation of Penman–Monteith suggested by the Food and Agricultural Organization (FAO56-PM) is considered as a target variable for investigation. The performance of the proposed RBFDE model is compared with particle swarm optimization based radial basis function (RBFPSO), radial basis function neural network (RBFNN), multilayer artificial neural network (MLANN) models and conventional empirical equations of Hargreaves, Turc, Open-Pan, and Blaney-Criddle. Weekly ET0 estimates that are obtained using RBFDE, RBFPSO, and RBFNN and MLANN are observed to be more consistent than equivalent empirical methods. For a critical analysis of simulation results, mean absolute percentage error (MAPE), root means square error (RMSE), determination coefficient (R2) and Nash–Sutcliffe efficiency factor (NSE) is computed. Low MAPE and RMSE values along with higher R2 and NSE close to 1, obtained with soft computing models exhibit that, soft computing models produce better estimates of ET0 than empirical methods. Among the soft computing models, RBFDE provides improved results as compared to RBFPSO, RBFNN, and MLANN models. This method can be extended for ET0 estimation in other ACZs.

Modeling solar potential in Semarang, Indonesia using artificial neural networks

Artificial neural network shows a good performance in predicting renewable energy. Many versions of Artificial Neural Network (ANN) models have been implemented to predict solar potential. This study aims to determine the monthly solar radiation in Semarang, Indonesia using ANN, and to visualize monthly solar irradiance as a map of the solar system of Semarang. This research applied the perceptron multi-layer ANN model, with 7 variables as input data of network learning, which were maximum temperature, relative humidity, wind speed, rainfall, longitude, latitude, and elevation. The input data set was obtained from a NASA normalized geo-satellite database website with a 5-year average daily score. Network training used backpropagation with one of the input layers, two of hidden layers, and one of the output layer. The performance of the model during the analysis of mean absolute percentage error was highly accurate (6.6%) when 12 and 10 neurons were respectively installed in the first and second hidden layers. The result was presented in a monthly map of solar potential within the geographical information system (GIS) environment. The result showed that ANN was able to be one of the alternatives to estimate solar irradiance data. The sun irradiance map can be used by the government of Semarang City to provide information about the solar energy profile for the implementation of the solar energy system.

Development of a Real-time System for Detecting Driver"s Cognitive Load using Multi-Layer Artificial Neural Network on ECG Signals

Objective: This study developed a real-time system to detect driver"s cognitive load using a multi-layer artificial neural network (MANN) based on electrocardiography (ECG) signals. The real-time system was aimed at classifying driver"s status into either normal or overload.Background: Driving with cognitive load is considered as one of significant factors for traffic accidents. Thus, an early detection of this risky status while driving is needed to prevent vehicle accidents.Method: The ECG signals of this study were measured from 22 participants who performed simulator-based driving experiment under two different conditions (1: normal driving, 2: overload driving (driving while doing a two-back task or an arithmetic task)). A real-time detection system was developed using MANN on the ECG signals and its effectiveness was evaluated for two new participants who drove under the two driving conditions.Results: The MANN model used for the real-time detection system showed perfect accuracy (100%), sensitivity (100%), and specificity (100%) for both of the training and testing data sets. In addition, the proposed real-time detection system successfully detected the change of participant"s status with a reasonable time delay (mean = 4.5 seconds).Conclusion: This study demonstrated that the ECG signals can be used as a biometric measure for the detection of the driver"s cognitive status in real-time.Application: The proposed detection system would be useful for the development of an intelligent vehicle that can provide timely interventions and/or warnings at the early onset of cognitive overload.

Impact of COVID-19 on GDP of major economies: Application of the artificial neural network forecaster

The ongoing COVID-19 pandemic has caused global health impacts, and governments have restricted movements to a certain extent. Such restrictions have led to disruptions in economic activities. In this paper, the GDP figures for the April–June quarter of 2020 for eight countries, namely, the United States, Mexico, Germany, Italy, Spain, France, India, and Japan, are forecasted. Considering that artificial neural network models have higher forecasting accuracy than statistical methods, a multilayer artificial neural network model is developed in this paper. This model splits the dataset into two parts: the first with 80% of the observations and the second with 20%. The model then uses the first part to optimize the forecasting accuracy and then applies the optimized parameters to the second part of the dataset to assess the model performance. A forecasting error of less than 2% is achieved by the model during the testing procedure. The forecasted GDP figures show that the April–June quarter of the current year experienced sharp declines in GDP for all countries. Moreover, the annualized GDP growth is expected to reach double-digit negative growth rates. Such alarming prospects require urgent rescue actions by governments.