Feed-forward Artificial Neural Network Model Research Articles

Forecast of wind turbine output power by a multivariate polynomial-RF model

Accurate prediction of wind turbine power is an important means to ensure the stable operation of wind turbines. The traditional wind speed-power curve only shows the relationship between wind turbine power and wind speed, without considering other influencing factors, such as rotor speed and pitch angle, and has certain limitations. Therefore, based on the supervisory control and data acquisition data of a wind farm, this paper proposes a hybrid multivariate prediction model that combines polynomial regression and random forest (RF) to predict wind turbine output power. First, to reduce the difficulty of expert analysis, the maximum information coefficient is used to analyze the correlation between data and select features. Wind speed, rotor speed, pitch angle, and wind direction are considered important and chosen for power prediction modeling. Then the relationship between multiple variables and output power is established through polynomial regression. Finally, the new polynomial features and output power are used to train the RF model to predict the output power. The experimental results show that the predicted wind speed and power diagram shows a band-like distribution, which matches closely with the real one; compared with multiple models such as a single RF model, a polynomial regression model, and a feedforward artificial neural network model, the polynomial-RF model has the highest prediction accuracy. The mean absolute percentage error (MAPE) of the polynomial-RF model prediction is 0.06, and the root mean square error (RMSE) is 114. Compared with the single RF model, the MAPE predicted by the polynomial-RF model is reduced by 14%, and the RMSE is reduced by 6%. It can be seen that the polynomial-RF model proposed in this paper has a good application prospect in the prediction of wind turbine output power.

An optimal feed-forward artificial neural network model and a new empirical correlation for prediction of the relative viscosity of Al2O3-engine oil nanofluid

This study presents the design of an artificial neural network (ANN) to evaluate and predict the viscosity behavior of Al2O3/10W40 nanofluid at different temperatures, shear rates, and volume fraction of nanoparticles. Nanofluid viscosity ({mu }_{nf}) is evaluated at volume fractions (varphi=0.25% to 2%) and temperature range of 5 to 55 °C. For modeling by ANN, a multilayer perceptron (MLP) network with the Levenberg–Marquardt algorithm (LMA) is used. The main purpose of this study is to model and predict the {mu }_{nf} of Al2O3/10W40 nanofluid through ANN, select the best ANN structure from the set of predicted structures and manage time and cost by predicting the ANN with the least error. To model the ANN, varphi, temperature, and shear rate are considered as input variables, and {mu }_{nf} is considered as output variable. From 400 different ANN structures for Al2O3/10W40 nanofluid, the optimal structure consisting of two hidden layers with the optimal structure of 6 neurons in the first layer and 4 neurons in the second layer is selected. Finally, the R regression coefficient and the MSE are 0.995838 and 4.14469E−08 for the optimal structure, respectively. According to all data, the margin of deviation (MOD) is in the range of less than 2% < MOD < + 2%. Comparison of the three data sets, namely laboratory data, correlation output, and ANN output, shows that the ANN estimates laboratory data more accurately.

The use of an artificial neural network for predicting the gloss of thermally densified wood veneers

In this study, an artificial neural network (ANN) model was developed to predict the gloss of thermally densified wood veneers. A custom application created with MATLAB codes was employed for the development of the multilayer feed-forward ANN model. The wood species, temperature, pressure, measurement direction, and angle of incidence were considered as the model inputs, while the gloss was the output of the ANN model. Model performance was evaluated by using the mean absolute percentage error (MAPE), the root mean square error (RMSE), and the coefficient of determination (R²). It was observed that the ANN model yielded very satisfactory results with acceptable deviations. The MAPE, RMSE, and R2 values of the testing period of the ANN model were found as 8.556%, 1.245, and 0.9814, respectively. Consequently, this study could be useful for the wood industry to predict the gloss with less number of tiring experimental activities.

Degradation of Bisphenol A by ozonation in a rotating packed bed: Modeling by response surface methodology and artificial neural network

The ozonation process of Bisphenol A (BPA) in a rotating packed bed (RPB) was modeled by response surface methodology (RSM) and artificial neural network (ANN). Experiments were performed according to the Box-Behnken design, and the interactive effects of various parameters including ozone concentration, pH, rotation speed of RPB and liquid flow rate on BPA degradation efficiency were investigated. Ozone concentration and pH had the most significant interactive effects on BPA degradation efficiency while rotation speed of RPB had no significant interactive effects with other variables. A second order polynomial equation was obtained to predict BPA degradation efficiency. Also, a multi-layered feed-forward ANN model was constructed based on the data of RSM experiments. Six neurons in hidden layer had the highest correlation coefficient (RANN = 0.99158). A comparison between RSM and ANN models suggested that both can accurately predict BPA degradation efficiency (RRSM = 0.99559). The highest BPA degradation efficiency (99.52 %) was achieved under the conditions of ozone concentration of 20 mg L−1, pH of 11, liquid flow rate of 10 L h−1 and rotation speed of RPB of 800 rpm, which was well predicted by the RSM model (99.54 %) and the ANN model (99.82 %). However, the RSM model was slightly better than the ANN model owing to its higher determination coefficient (R2RSM = 0.9912, R2ANN = 0.9827) and lower mean square error (MSERSM = 0.0001684, MSEANN = 0.0003305).

Neural network-crow search model for the prediction of functional properties of nano TiO2 coated cotton composites

This paper presents a new hybrid approach for the prediction of functional properties i.e., self-cleaning efficiency, antimicrobial efficiency and ultraviolet protection factor (UPF), of titanium dioxide nanoparticles (TiO2 NPs) coated cotton fabric. The proposed approach is based on feedforward artificial neural network (ANN) model called a multilayer perceptron (MLP), trained by an optimized algorithm known as crow search algorithm (CSA). ANN is an effective and widely used approach for the prediction of extremely complex problems. Various studies have been proposed to improve the weight training of ANN using metaheuristic algorithms. CSA is a latest and an effective metaheuristic method relies on the intelligent behavior of crows. CSA has been never proposed to improve the weight training of ANN. Therefore, CSA is adopted to optimize the initial weights and thresholds of the ANN model, in order to improve the training accuracy and prediction performance of functional properties of TiO2 NPs coated cotton composites. Furthermore, our proposed algorithm i.e., multilayer perceptron with crow search algorithm (MLP-CSA) was applied to map out the complex input–output conditions to predict the optimal results. The amount of chemicals and reaction time were selected as input variables and the amount of titanium dioxide coated on cotton, self-cleaning efficiency, antimicrobial efficiency and UPF were evaluated as output results. A sensitivity analysis was carried out to assess the performance of CSA in prediction process. MLP-CSA provided excellent result that were statistically significant and highly accurate as compared to standard MLP model and other metaheuristic algorithms used in the training of ANN reported in the literature.

Real Time Control Application of the Robotic Arm Using Neural Network Based Inverse Kinematics Solution

Robotic arms are widely used in many industrial applications at present. The control of robotic arms involves position coordination Cartesian space by a forward/inverse kinematics solution method. The inverse kinematics is difficult for real-time control applications, computational requirements are intensive and the run-time is high. The traditional solution methods used geometric, algebraic, and numerical iterative techniques are inadequate and slow in the inverse kinematics solution. Recently, alternative solution methods based on artificial intelligence techniques have been developed to solve the inverse kinematics problem. In this study, a multi-layered feed-forward Artificial Neural Network model was developed to solve the inverse kinematics of the 5 degrees of freedom robotic arm. Using the Proportional-Integral control algorithm combined with this Artificial Neural Network model, the real-time position control of the robotic arm was accomplished. The obtained results were compared with the PI control supported by an analytical inverse kinematics solution in real-time. The results showed that the PI control combined with Artificial Neural Network has superior tracking ability, smaller control error, and better absolute fit to the reference.

Comparison of traditional regression models and artificial neural network models for height-diameter modeling in uneven-aged fir stands

Forests have been constantly growing with their dynamic structure. In order for this dynamic structure must be managed based on sustainable perspective. Diameter, height, age, stand structure, etc. parameters are used in the inventory stage of the planning. The easiest to measure among these parameters is the diameter. Therefore, the developed models are usually aimed at reaching other forest parameters from the diameter. In this article, 9 different height-diameter models were fitted using regression models, and feed-forward backpropagation artificial neural network model methods for uneven-aged fir (Abies nordmanniana subsp. equi-trojani) stands in Kökez, Bolu region of Turkey. The models compared based on adjusted R², bias, absolute bias, and root mean square error (RMSE). It was observed that the best result was obtained from the artificial neural network model, and the worst result was obtained from the power model.

Artificial neural network for predicting nuclear power plant dynamic behaviors

A Nuclear Power Plant (NPP) is a complex dynamic system-of-systems with highly nonlinear behaviors. In order to control the plant operation under both normal and abnormal conditions, the different systems in NPPs (e.g., the reactor core components, primary and secondary coolant systems) are usually monitored continuously, resulting in very large amounts of data. This situation makes it possible to integrate relevant qualitative and quantitative knowledge with artificial intelligence techniques to provide faster and more accurate behavior predictions, leading to more rapid decisions, based on actual NPP operation data. Data-driven models (DDM) rely on artificial intelligence to learn autonomously based on patterns in data, and they represent alternatives to physics-based models that typically require significant computational resources and might not fully represent the actual operation conditions of an NPP. In this study, a feed-forward backpropagation artificial neural network (ANN) model was trained to simulate the interaction between the reactor core and the primary and secondary coolant systems in a pressurized water reactor. The transients used for model training included perturbations in reactivity, steam valve coefficient, reactor core inlet temperature, and steam generator inlet temperature. Uncertainties of the plant physical parameters and operating conditions were also incorporated in these transients. Eight training functions were adopted during the training stage to develop the most efficient network. The developed ANN model predictions were subsequently tested successfully considering different new transients. Overall, through prompt prediction of NPP behavior under different transients, the study aims at demonstrating the potential of artificial intelligence to empower rapid emergency response planning and risk mitigation strategies.

Modeling of phenol removal from water by NiFe2O4 nanocomposite using response surface methodology and artificial neural network techniques

This study demonstrates the synthesis, characterization, and modeling of nickel ferrite nanocomposite, NiFe2O4 (NFC) as an adsorbent for the phenol contaminated aqueous environment. The characterization of the prepared NFC was performed with X-ray diffraction spectroscopy (XRD), scanning electron microscopy (SEM), transmission electron microscopy (TEM) and vibrating sample magnetometer (VSM) techniques. The optimization and modeling of phenol removal using NFC was done through central composite design (CCD) and effective parameters of CCD were measured as input variables including the amount of NFC, pH, contact time and initial phenol concentration. The predicted results showed that the adsorption process using NFC as adsorbent had the maximum phenol removal (~99%) under predicted optimal conditions (pH = 7.67, NFC dosage = 0.15 g at room temperature), which also corresponded to the experimental values. In addition, a multilayer feed-forward artificial neural network (ANN) model was used to obtain a speculative phenol removal model. The network was trained for six replications after selection of the best neuron number for hidden layer. The value of MSE trained network was found to be 6.01718e-3 along with regression coefficient (R2 = 0.9934) that indicated satisfactory relationship. Isothermal modeling of phenol adsorption onto NFC was performed using well-known Temkin, Freundlich and Langmuir models and it was clear from the higher R2 value of 0.961 that the Langmuir model was significantly followed by experimental data. The maximum Langmuir adsorption capacity was found to be 274.72 mg/g at the optimal conditions. The obtained results prove that NFC could be an effective adsorbent for elimination of phenol contaminant from aqueous environment.

Türkiye’de Aylık İşsizlik Oranlarının Yapay Sinir Ağları ile Öngörüsü

Since the labor market contains human factors, unlike other markets, the economic policies that are implemented to stabilize the labor market cannot be effective alone, therefore, social and psychological factors also come into play. As of today, it is seen that the high unemployment rates appear to be increasing every day and become one of the main issues of Turkey's economy. Unemployment becomes prevalent especially in the younger population of Turkey, and individuals in the young age group are rendered advantageous since the burden of subsistence does not devolve upon most of them. Upon considering that the pressure and adverse conditions caused by unemployment may be different for each age group and the economic and social policies that are required to be developed against such necessity to be different in this context, it is quite crucial to forecast the unemployment rate, especially for different age groups.The aim of the study is constituted by the forecasting of the monthly unemployment rates in Turkey depending on age groups via artificial neural networks. In line with this purpose, based on official data obtained from the TSI by taking into account the monthly unemployment rates for the age groups over the period 2005-2019 as well as the general unemployment rates for the same period, the monthly unemployment rates for the year 2019 were forecasted using feed-forward and feed-back artificial neural network models. As a result of the study, it was revealed with both error criteria and some visual findings that the observed values for all age groups, overall monthly unemployment rates, and the forecasting by artificial neural networks (ANN) were quite close to each other.

Prediction of instantaneous real-world emissions from diesel light-duty vehicles based on an integrated artificial neural network and vehicle dynamics model

This paper presents a road vehicle emission model that integrates an artificial neural network (ANN) model with a vehicle dynamics model to predict the instantaneous carbon dioxide (CO2), nitrogen oxides (NOx) and total hydrocarbon (THC) emissions of diesel light-duty vehicles. Real-world measurement data were used to train a multi-layer feed-forward ANN model. The optimal combination of the various experimental variables was selected as the ANN input through a parametric study considering both practicality and accuracy. For CO2 prediction, two variables (engine speed and engine torque) are enough to develop an accurate ANN model. In order to achieve satisfactory accuracy for CO and NOx prediction, more variables were used for ANN training. The trained ANN model was used to predict road vehicle emissions by integrating the vehicle dynamics model, which was used as a supplementary tool to produce ANN input data. The integrated model is practical because it requires relatively simple data for input such as vehicle specifications, velocity, and road gradient. In the accuracy validation, the proposed model showed satisfactory prediction accuracy for road vehicle emissions.

A new ANN model for hourly solar radiation and wind speed prediction: A case study over the north & south of the Arabian Peninsula

Prediction models for renewable energy sources are frequently used to manage stand-alone micro grid systems. Such prediction models are important due to the high cost or even the unavailability of real-world data in many regions. Herein, a new technique based on the Feed-forward Back-propagation Artificial Neural Network (FBANN) model has been developed and used to predict both the hourly solar radiation and the wind speed simultaneously. The new model has been tested over the Northern and Southern regions of the Arabian Peninsula. The novelty of the model lies in the following characteristics: (i) a new integration between two different FBANN configurations has been established, (ii) only three input parameters are required for the model to run and (iii) solar radiation and wind speed are predicted simultaneously. The correlation coefficient (R) and the mean absolute percentage error (MAPE) have been selected as an accuracy evaluation index between inputs and targets. To ensure reliability, the input meteorological data is immense and covers a wide time span. Results reveal that the proposed FBANN model achieves high levels of accuracy. The R value of the hybrid model for all the investigated locations is more than 0.96 while the MAPE does not exceed 3%.

Using an artificial neural network to predict the probability of oviposition events of precision-fed broiler breeder hens

Identifying daily oviposition events for individual broiler breeders is important for bird management. Identifying non-laying birds in a flock that might be caused by improper nutrition or diseases can guide diet changes or disease treatments for these individuals. Oviposition depends on follicle maturation and egg formation, and follicle maturation can be variable. As such, the day and time of oviposition events of individual birds in a free-run flock can be hard to predict. Based on a precision feeding (PF) system that can record the feeding activity of individual birds, a recent study reported a machine learning model to predict daily egg-laying events of broiler breeders. However, there were 2 limitations in that study: 1) It could only be used to identify daily egg-laying events on a subsequent day; 2) The prediction outputs that were binary labels were unable to indicate more details among the outputs with the same label. To improve the previous approach, the current study aimed to predict and output the probability of daily oviposition events occurring using a specific time point in 1 day. In the current study, 706 egg-laying events recorded by nest boxes with radio frequency identification of hens and 706 randomly selected no-egg-laying events were used. The anchor point was newly defined in the current study as a specific time point in 1 day, and 26 features around the anchor point were created for all events (706 egg-laying events and 706 no-egg-laying events). A feed-forward artificial neural network (ANN) model was built for prediction. The area under the receiver operating characteristic (ROC) curve was 0.9409, indicating that the model had an outstanding classification performance. The ANN model could predict oviposition events on the current day, and the output was a probability that could be informative to indicate the likelihood of an oviposition event for an individual breeder. In situations where total egg production was known for a group, the ANN model could predict the probability of daily oviposition events occurring of all individual birds and then rank them to choose those most likely to have laid an egg.

Neuro-swarm intelligent computing paradigm for nonlinear HIV infection model with CD4+ T-cells

In the investigations presented here, an efficient computing approach is applied to solve Human Immunodeficiency Virus (HIV) infection spread. This approach involves CD4+ T-cells by feed-forward artificial neural networks (FF-ANNs) trained with particle swarm optimization (PSO) and interior point method (IPM), i.e., FF-ANN-PSO-IPM. In the proposed solver FF-ANN-PSO-IPM, the FF-ANN models of differential equations are used to develop the fitness functions for an infection model of T-cells. The training of networks through minimization problem are proficiently conducted by integrated heuristic capability of PSO-IPM. The reliability, stability and exactness of the proposed FF-ANN-PSO-IPM are established through comparison with outcomes of standard numerical procedure with Adams method for both single and multiple autonomous trials with precision of order 4 to 8 decimal places of accuracy. The statistical measures are effectively used to validate the outcomes of the proposed FF-ANN-PSO-IPM.

Machine Learning for Advanced Design of Nanocomposite Ultrafiltration Membranes

Although the incorporation of nanoparticles into ultrafiltration polymeric membranes has shown promising outcomes, their commercial implementation has yet to be fulfilled due to inconsistency in data, lack of a reliable recipe for the optimum filler content, and reluctance in disrupting the production line which requires significant time and resources. There is a growing demand among membrane communities for a design platform that can accelerate the discovery of new nanocomposite membranes. In this work, a feed-forward ANN (artificial neural network) model that has one hidden layer and the Bayesian regularization training algorithm were chosen for designing a graphical user interface platform to predict the ultrafiltration nanocomposite membrane performance, that is, solute rejection, flux recovery, and pure water flux, thereby saving time and resources used in membrane design. Experimental data (735 samples from 200 reports published between 2006 and 2020) were derived from the literature for training, validation, and testing of the ANN models. The results indicated that the best 30 ANN models produce the most accurate estimation of membrane performance using the seven input variables of polymer concentration, polymer type, filler concentration, average filler size, solvent concentration (in the dope solution), solvent type, and contact angle on the unseen data set. Furthermore, a sensitivity analysis was performed on the achieved models to identify the most effective input variables for each nanocomposite membrane performance. This work has the potential to be extended to other mixed matrix membrane types that are going to be used for microfiltration, nanofiltration, reverse osmosis, and so forth.

Leveraging artificial intelligence for more accurate and reliable predictions of anchors shear breakout capacity in thin concrete members

Understanding the shear behavior of post-installed anchors embedded in thin concrete members is considered complicated due to the many parameters involved including embedment depth, edge distance, concrete strength, anchor diameter, and member thickness. This study utilizes the Artificial Neural Network (ANN) concept to predict the capacity and behavior of adhesive and screw anchors with full-thickness embedment in thin concrete members and compare it with the adopted design model in ACI 318 standard. First, A multilayered feed-forward ANN model trained with Bayesian Regularization training algorithm is developed and compared against the proposed model based on the concrete capacity design method (CCD). Then, a parametric study is presented to evaluate the contribution of each variable to the shear capacity and ensure generalization. The study shows that ANN model provides a higher level of accuracy in predicting the shear capacity than CCD model by reducing the coefficient of variation from 18% to 11%. In addition, the parametric study shows that the CCD model does not capture the nonlinear effect of the variables on the capacity accurately and does not include the interaction effect between variables. For instance, CCD shows that the member thickness has a nearly linear effect on the capacity while ANN shows higher nonlinearity. In addition, the study presents a reliability analysis to assess the shift in safety level by adopting the ANN model. The ANN provided an average increase in reliability index by 32%. This study is considered the first study to utilize ANN to anchors embedded in thin concrete members with full embedment depth.

Modeling Energy LED Light Consumption Based on an Artificial Intelligent Method Applied to Closed Plant Production System

Artificial lighting is a key factor in Closed Production Plant Systems (CPPS). A significant light-emitting diode (LED) technology attribute is the emission of different wavelengths, called light recipes. Light recipes are typically configured in continuous mode, but can also be configured in pulsed mode to save energy. We propose two nonlinear models, i.e., genetic programing (GP) and feedforward artificial neural networks (FNNs) to predict energy consumption in CPPS. The generated models use the following input variables: intensity, red light component, blue light component, green light component, and white light component; and the following operation modes: continuous and pulsed light including pulsed frequency, and duty cycle as well energy consumption as output. A Spearman’s correlation was applied to generate a model with only representative inputs. Two datasets were applied. The first (Test 1), with 5700 samples with similar input ranges, was used to train and evaluate, while the second (Test 2), included 160 total datapoints in different input ranges. The metrics that allowed a quantitative evaluation of the model’s performance were MAPE, MSE, MAE, and SEE. Our implemented models achieved an accuracy of 96.1% for the GP model and 98.99% for the FNNs model. The models used in this proposal can be applied or programmed as part of the monitoring system for CPPS which prioritize energy efficiency. The nonlinear models provide a further analysis for energy savings due to the light recipe and operation light mode, i.e., pulsed and continuous on artificial LED lighting systems.

The Training of Pi-Sigma Artificial Neural Networks with Differential Evolution Algorithm for Forecasting

Looking at the artificial neural networks’ literature, most of the studies started with feedforward artificial neural networks and the training of many feedforward artificial neural networks models are performed with derivative-based algorithms such as levenberg–marquardt and back-propagation learning algorithms in the first studies. In recent years, although many new heuristic algorithms have been proposed for different aims these heuristic algorithms are also frequently used in the training process of many different artificial neural network models. Pi-sigma artificial neural networks have different importance than many artificial neural network models with its higher-order network structure and superior forecasting performance. In this study, the training of Pi-Sigma artificial neural networks is performed by differential evolution algorithm uses DE/rand/1 mutation strategy. The performance of the proposed method is evaluated by two data sets and seen that the proposed method has a very effective performance compared with many artificial neural network models.

Statistical foundation of Variational Bayes neural networks

Despite the popularism of Bayesian neural networks (BNNs) in recent years, its use is somewhat limited in complex and big data situations due to the computational cost associated with full posterior evaluations. Variational Bayes (VB) provides a useful alternative to circumvent the computational cost and time complexity associated with the generation of samples from the true posterior using Markov Chain Monte Carlo (MCMC) techniques. The efficacy of the VB methods is well established in machine learning literature. However, its potential broader impact is hindered due to a lack of theoretical validity from a statistical perspective. In this paper, we establish the fundamental result of posterior consistency for the mean-field variational posterior (VP) for a feed-forward artificial neural network model. The paper underlines the conditions needed to guarantee that the VP concentrates around Hellinger neighborhoods of the true density function. Additionally, the role of the scale parameter and its influence on the convergence rates has also been discussed. The paper mainly relies on two results (1) the rate at which the true posterior grows (2) the rate at which the Kullback–Leibler (KL) distance between the posterior and variational posterior grows. The theory provides a guideline for building prior distributions for BNNs along with an assessment of accuracy of the corresponding VB implementation.

Chemical coagulation-electro fenton as a superior combination process for treatment of dairy wastewater: performance and modelling

Dairy wastewater contains high levels of organic matter that would be a serious threat if being discharged to the environment without any treatment. This study investigated the influence of various parameters including the concentration of poly aluminum chloride (PAC) on the chemical coagulation process and the concentration of H2O2, pH of the solution, reaction time, voltage and distance of electrodes in the electro-Fenton (EF) process. The optimum conditions obtained in this study included PAC concentration of 100 mg/L, pH of 3, reaction time of 60 min, voltage of 20 V, H2O2 concentration of 1.5 g/L and electrode distance of 2 cm. This resulted in the removal efficiency of 90.3%, 87.25%, and 87% for chemical oxygen demand (COD), biochemical oxygen demand (BOD5), and total suspended solids, respectively. The estimated cost of the process in terms of 1 kg COD removal was about $1.16. Two experimental models, called the feed-forward artificial neural network (FF-ANN) and partial least squares (PLS), were developed to predict the behavior of the process in COD removal. The results confirmed that both FF-ANN and PLS were powerful tools in predicting COD removal in the EF process, as the correlation coefficients between the predicted COD and the actual COD for the PLS and FF-ANN models were 0.854 and 0.971, respectively. Sensitivity analysis of both models showed that the reaction time and electrode distance had the most influence on the output of PLS and FF-ANN, respectively. Therefore, this combined process can be regarded as a thought-provoking one for dairy wastewater treatment, and the FF-ANN model was a more powerful tool than the PLS one.