Bayesian Regularization Backpropagation Research Articles

The Development of PSO-ANN and BOA-ANN Models for Predicting Matric Suction in Expansive Clay Soil

Disasters have different shapes, and one of them is sudden landslides, which can put the safety of highway users at risk and result in crucial economic damage. Along with the risk of human losses, each day a highway malfunctions causes high expenses to citizens, and repairing a failed highway is a time- and cost-consuming process. Therefore, correct highway functioning can be categorized as a high-priority reliability factor for cities. By detecting the failure factors of highway embankment slopes, monitoring them in real-time, and predicting them, managers can make preventive, preservative, and corrective operations that would lead to continuing the function of intracity and intercity highways. Expansive clay soil causes many infrastructure problems throughout the United States, and much of Mississippi’s highway embankments and fill slopes are constructed of this clay soil, also known as High-Volume Change Clay Soil (HVCCS). Landslides on highway embankments are caused by recurrent volume changes due to seasonal moisture variations (wet-dry cycles), and the moisture content of the HVCCS impacts soil shear strength in a vadose zone. Soil Matric Suction (SMS) is another indication of soil shear strength, an essential element to consider. Machine learning develops high-accuracy models for predicting the SMS. The current work aims to develop hybrid intelligent models for predicting the SMS of HVCCS (known as Yazoo clay) based on field instrumentation data. To achieve this goal, six Highway Slopes (HWS) in Jackson Metroplex, Mississippi, were extensively instrumented to track changes over time, and the field data was analyzed and generated to be used in the proposed models. The Artificial Neural Network (ANN) with a Bayesian Regularization Backpropagation (BR-BP) training algorithm was used, and two intelligent systems, Particle Swarm Optimization (PSO) and Butterfly Optimization Algorithm (BOA) were developed to optimize the ANN-BR algorithm for predicting the HWS’ SMS by utilizing 13,690 data points for each variable. Several performance indices, such as coefficient of determination (R2), Mean Square Error (MSE), Variance Account For (VAF), and Regression Error Characteristic (REC), were also computed to analyze the models’ accuracy in prediction outcomes. Based on the analysis results, the PSO-ANN outperformed the BOA-ANN, and both had far better performance than ANN-BR. Moreover, the rainfall had the highest impact on SMS among all other variables and it should be carefully monitored for landslide prediction HWS. The proposed hybrid models can be used for SMS prediction for similar slopes.

Overfitting Prevention in Accident Prediction Models: Bayesian Regularization of Artificial Neural Networks

In the present paper, we implemented the Bayesian regularization (BR) backpropagation algorithm for calibrating an artificial neural network (ANN) as an accident prediction model (APM) to be used on Italian four-lane divided roads. We chose the BR-ANN since it efficiently allows for dealing with small sample size and avoiding overfitting issues by adding a regularization term in the objective function to be minimized during training. Moreover, BR-ANNs are sparsely employed in road safety analyses, and their peculiarities deserve to be emphasized. In our work, the BR-ANN aims to predict the number of fatal and injury (FI) crashes across 236 road elements, for a total length of 78 km. The input features are road element length, horizontal and vertical alignment, cross-section geometry, operating speed, traffic flow, sight distance, and road area type (i.e., a categorical predictor accounting for the potential influence of merge and diverge influence areas). Training and test phases of the BR-ANN have been evaluated by determination coefficient ( R2), root mean square error (RMSE), overfitting ratio (OR), scatterplots, residuals analysis, and by the same ANN architecture trained with the gradient descent (GD) with momentum and adaptive learning rate backpropagation algorithm (GD-ANN). Results demonstrate that the BR-ANN markedly outperforms the GD-ANN, which suffers severe overfitting issues. Furthermore, BR-ANN does not overfit data (OR close to the unity), reports a satisfactory R2 (0.726), and shows a Gaussian residual distribution with zero mean. Therefore, road authorities could consider regularized ANNs for performing appropriate safety analyses, especially when dealing with small road sample sizes.

Using ANN to study VIV of flexible cylinders in uniform and shear flows

The ANN model trained on experimental datasets is developed, especially based on the characteristics of flexible cylinder's VIV, the Bayesian regularization back propagation algorithm is employed to train the presented neural network. Nine intuitive physical parameters are selected according to the governing equations of cylinder dynamics. The results show that the neural network trained with intuitive physical quantity can acceptable predictions predict VIV, and the linear regression value is 0.940. In addition, the range of model parameters is limited in the trained neural network, with around 20% error.

Experimental study and implementation of supervised machine learning algorithm to predict the flowability of two-phase water-oil in pipeline

In the middle-stream petroleum industry, the concurrent flow of oil and water in pipes is a typical occurrence. Several factors have been reported to influence the flowability of two-phase water-oil in pipeline. However, the non-linear relationship between these factors and the flowability of the two-phase water-oil is not yet known. The understanding of these relationships could help in developing models that might be employed in predicting flow behavior. In this study, two-phase water-oil flowability was experimentally investigated and modeled using supervised machine learning algorithms. The performance of each of the models was optimized by evaluating the model with the best-hidden neuron. For the Levenberg-Marquardt backpropagation, Bayesian regularization backpropagation, and scaled conjugate gradient backpropagation networks, the best topologies of 4-8-4, 4-9-4, and 4-10-4 were obtained, and coefficient of determination (R2) of 0.998, 0.999, 0.996 respectively. The predicted kinematic viscosity, dynamic viscosity, pressure drop, and power consumption were consistent with the observed values. The sensitivity analysis revealed that the temperature has the most significant effect on the predicted output. The robustness of using the supervised machine learning technique in modeling the flowability of two-phase water-crude oil mixes in pipelines based on the relationship between the predictors and the targeted variables was demonstrated.

Assessment of Algorithm Performance on Predicting Total Dissolved Solids Using Artificial Neural Network and Multiple Linear Regression for the Groundwater Data

Estimating groundwater quality parameters through conventional methods is time-consuming through laboratory measurements for megacities. There is a need to develop models that can help decision-makers make policies for sustainable groundwater reserves. The current study compared the efficiency of multivariate linear regressions (MLR) and artificial neural network (ANN) models in the prediction of groundwater parameters for total dissolved solids (TDS) for three sub-divisions in Lahore, Pakistan. The data for this study were collected every quarter of a year for six years. ANN was applied to investigate the feasibility of feedforward, backpropagation neural networks with three training functions T-BR (Bayesian regularization backpropagation), T-LM (Levenberg–Marquardt backpropagation), and T-SCG (scaled conjugate backpropagation). Two activation functions were used to analyze the performance of algorithmic training functions, i.e., Logsig and Tanh. Input parameters of pH, electrical conductivity (EC), calcium (Ca2+), magnesium (Mg2+), chloride (Cl−), and sulfate (SO42−) was used to predict TDS as an output parameter. The computed values of TDS by ANN and MLR were in close agreement with their respective measured values. Comparative analysis of ANN and MLR showed that TDS root means square error (RMSE) for city sub-division and Pearson’s coefficient of correlation (r) for ANN and MLR were 2.9% and 0.981 and 4.5% and 0.978, respectively. Similarly, for the Farrukhabad sub-division, RMSE and r for ANN were 4.9% and 0.952, while RMSE and r for MLR were 5.5% and 0.941, respectively. For the Shahadra sub-division, RMSE was 10.8%, r was 0.869 for ANN, RMSE was 11.3%, and r was 0.860 for MLR. The results exhibited that the ANN model showed less error in results than MLR. Therefore, ANN can be employed successfully as a groundwater quality prediction tool for TDS assessment.

Effect of Hidden Neuron Size on Different Training Algorithm in Neural Network

We use different types of training algorithms in the neural network. But, we cannot say which kind of training algorithm is fast for a given problem. So, in this survey paper, we are trying to find which types of training algorithm are better for categorization problems. For this purpose, we used ten types of training algorithms in the pattern network in MATLAB. We used Levenberg-Marquardt (LM), Bayesian regularization backpropagation (BR), BFGS Quasi-Newton (BFG), Resilient Backpropagation (RP), Scaled Conjugate gradient backpropagation (SCG), Conjugate Gradient with Powell/Beale Restarts (CGB), Fletcher-Powell Conjugate Gradient (CGF), Polak-Ribiere Conjugate Gradient (GDM), One Step Secant (OSS), and Variable Learning Rate Backpropagation (GD) algorithm. In this survey paper, we also check, affects of these algorithms on neural network when we applied different types of hidden neuron size. During this survey we found some new facts. We found that RP, SCG, CGB, CGF and OSS are fastest algorithms. BFG takes more time with respect to hidden neuron size. GDM and GD take more epochs. BR algorithm is not acceptable for image categorization.

Artificial Neural Network (ANN) Modelling for Biogas Production in Pre-Commercialized Integrated Anaerobic-Aerobic Bioreactors (IAAB)

The use of integrated anaerobic-aerobic bioreactor (IAAB) to treat the Palm Oil Mill Effluent (POME) showed promising results, which successfully overcome the limitation of a large space that is needed in the conventional method. The understanding of synergism between anaerobic digestion and aerobic process is required to achieve maximum biogas production and COD removal. Hence, this work presents the use of artificial neural network (ANN) to predict the COD removal (%), purity of methane (%), and methane yield (LCH4/gCODremoved) of anaerobic digestion and COD removal (%), biochemical oxygen demand (BOD) removal (%), and total suspended solid (TSS) removal (%) of aerobic process in a pre-commercialized IAAB located at Negeri Sembilan, Malaysia. MATLAB R2019b was used to develop the two ANN models. Bayesian regularization backpropagation (BR) showed the best performance among the 12 training algorithms. The trained ANN models showed high accuracy (R2 > 0.997) and demonstrated good alignment with the industrial data obtained from the pre-commercialized IAAB over a 6-month period. The developed ANN model is subsequently used to create the optimal operating conditions which maximize the output parameters. The COD removal (%) was improved by 33.9% (from 68.7% to 92%), while the methane yield was improved by 13.4% (from 0.23 LCH4/gCODremoved to 0.26 LCH4/gCODremoved). Sensitivity analysis shows that COD inlet is the most influential input parameters that affect the methane yield, anaerobic COD, BOD and TSS removals, while for aerobic process, COD removal is most affected by mixed liquor suspended solids (MLSS). The trained ANN model can be utilized as a decision support system (DSS) for operators to predict the behavior of the IAAB system and solve the problems of instability and inconsistent biogas production in the anaerobic digestion process. This is of utmost importance for the successful commercialization of this IAAB technology. Additional input parameters such as the mixing time, reaction time, nutrients (ammonium nitrogen and total phosphorus) and concentration of microorganisms could be considered for the improvement of the ANN model.

Application of Bayesian regularization back propagation neural network in sensorless measurement of pump operational state

Under the strategic framework of global carbon emission reduction, it is urgent to reduce the energy consumption of centrifugal pumps. Monitoring pump’s operational states can effectively help people to understand system’s behavior, and achieve the optimal energy management on pump equipment. In view of installation space, cost, reliability and other factors, it is necessary to find an alternative to the traditional sensor monitoring scheme. Therefore, it is significant to develop a prediction method for the operational state of centrifugal pump using sensorless technology. In this paper, a neural network estimation model based on Bayesian regularization back propagation (BRBP) algorithm is proposed. Compared with the traditional QP estimation model, the new model has better nonlinearity and higher precision. Using power and rotational frequency as input neurons, BRBP model realizes the output of flow rate and head through neuronal calculations. By comparing the predicted flow rate and head values of a multistage centrifugal pump with the measured values at different rotational frequencies, it is found that the mean relative error of flow rate of BRBP model is in the range of 1% to 4%, and the mean relative error of head is in the range of 1% to 2%. The prediction accuracy of BRBP neural network model is obviously higher than that of QP model, which meets the requirements of industrial application.

Novel Adaptive Bayesian Regularization Networks for Peristaltic Motion of a Third-Grade Fluid in a Planar Channel

In this presented communication, a novel design of intelligent Bayesian regularization backpropagation networks (IBRBNs) based on stochastic numerical computing is presented. The dynamics of peristaltic motion of a third-grade fluid in a planar channel is examined by IBRBNs using multilayer structure modeling competency of neural networks trained with efficient optimization ability of Bayesian regularization method. The reference dataset used as inputs and targets parameters of IBRBN has been obtained via the state-of-the-art Adams numerical method. The data of solution dynamics is created for multiple scenarios of the peristaltic transport model by varying the volume flow rate, material parametric of a third-grade fluid model, wave amplitude, and inclination angles. The designed integrated IBRBNs are constructed by exploiting training, testing, and validation operations at each epoch via optimization of a figure of merit on mean square error sense. Exhaustive simulation of IBRBNs with comparison on mean square error, histograms, and regression index substantiated the precision, stability, and reliability to solve the peristaltic transport model.

Data-driven prediction of flame temperature and pollutant emission in distributed combustion

The flame temperature and pollutant emission (of NO and CO) characteristics in distributed combustion were examined using data-driven artificial neural network (ANN) approach. Experimental results collected from swirl-assisted distributed combustion using methane fuel at an equivalence ratio 0.9 were utilized for dataset preparation. The distributed combustion condition was created in a swirl-assisted burner (at thermal intensity of 5.72 MW/m3-atm) by diluting the main airstream with carbon dioxide. Experimental results of exhaust NO and CO concentrations and adiabatic flame temperature (AFT) derived from Chemkin-Pro® simulation were selected as the target output. The ANN model was developed with inlet airflow rates and O2 concentrations as the input, and pollutant emission and AFT as the output variables. The ANN possessed one hidden layer with variable number of neurons (10, 15, and 20). Tangent sigmoid and Log sigmoid transfer functions were tested along with feed forwards and cascade forward network schemes having Levenberg–Marquardt backpropagation training algorithms. Different learning rates of model training were investigated to determine the optimized training model. The best model (with learning rate 0.2) was selected based on the mean square error (MSE) and the strength of correlation (R) predicted for individual outputs. The model predicted very well the target outputs in both conventional swirl combustion and distributed combustion regime for wider applicability in a range of applications. A very strong correlation was predicted by the current ANN model for the overall data as indicated by the R value of 0.9842. Furthermore, the results obtained with Bayesian Regularization backpropagation method demonstrated better prediction than those from Levenberg–Marquardt algorithm.

A Deep Learning Based Multiobjective Optimization for the Planning of Resilience Oriented Microgrids in Active Distribution System

When facing severe weather events, a distribution system may suffer from the loss or failure of one or more of its components, the so-called N-K contingencies. Nevertheless, taking advantage of the system’s isolate switches and the increasing availability of distributed energy resources (DERs), a distribution system may be clustered into microgrids able to withstand such contingencies with minimal power interruption. In this perspective, this work proposes a novel bilevel optimization framework for planning microgrids in active distribution systems under a resilience-oriented perspective. For this, first, the outer level optimization features a multi-objective problem seeking to optimally allocate DERs and isolate switches in the distribution network while balancing the competing objectives of cost, resilience, and environmental impact. Next, the inner level handles the optimization problem pertaining to the optimal operation of the microgrids that can be created by harnessing local DERs and isolate switches allocated in the outer level. Further, given the proposed approach resilience-oriented focus, the developed framework employes deep learning models based on deep neural network (DNN) architectures trained using Bayesian Regularization Backpropagation (BRB) technique. This strategy allows for avoiding the modeling simplifications typically employed to alleviate the computational burden that can otherwise jeopardize planning solutions’ feasibility. Thus, enabling the accurate consideration of microgrids’ operational behavior, including hierarchal controls and the stochastic nature of loads, generation, and weather-induced line failures, especially critical aspects under resilience-oriented planning. Simulation case studies are developed to demonstrate the effectiveness of the developed planning framework.

Prediction of floodwater impacts on vehicle blockages at bridges using artificial neural network

During extreme flood events, various debris like floating vehicles can block the bridges in urban rivers and floodplains. Blockage of vehicles can influence the floodwater hydrodynamics and potentially on the flood risk implications. Such obstructions often raise upstream water levels with back water effects, causing more water to be redirected into nearby metropolitan areas. This study attempts at evaluating artificial neural network (ANN) model in predicting the variations in floodwater depths and velocities along the channel centreline based on the changes in flowrate and distances from the inlet. The floodwater depth and velocity variations were obtained for three different types of bridges at specified sites along the channel centreline with three incoming discharges. A multilayer feedforward neural network (FFNN) model was used to investigate the effects of discharge (Q) and distance, on depth variation rate (D) or velocity (V). Additionally, a comparison study was done between 2 input 1 output and 2 input 2 output i.e. single output (depth variation rate (D) or velocity (V) versus multi-output depth variation rate (D) and velocity (V) for all the three models of bridges that are blocked by vehicles. The study has applied 12 training algorithms (TA) in the ANN modelling to optimize the TA that is most suitable for the dataset of three different bridges. The optimization is based on the performance criterion namely regression (R), mean squared error (MSE), mean absolute error (MAE), mean absolute percentage (MAPE), accuracy and coefficient of determinant (R2). Bayesian regularization backpropagation (BR) training algorithm gives a highest accuracy when compared in all three bridges. The scenario 2 input 2 output gave greatest accuracy results compared to 2 input 1 output. The findings showed a reliable estimation of significant impacts on the flow propagations and the hydrodynamic processes along rivers and floodplains. This study can help the decision makers in effective river and floodplain management practices.

Comparative Evaluation of Predicting Energy Consumption of Absorption Heat Pump with Multilayer Shallow Neural Network Training Algorithms

The performance of various multilayer neural network algorithms to predict the energy consumption of an absorption chiller in an air conditioning system under the same conditions was compared and evaluated in this study. Each prediction model was created using 12 representative multilayer shallow neural network algorithms. As training data, about a month of actual operation data during the heating period was used, and the predictive performance of 12 algorithms according to the training size was evaluated. The prediction results indicate that the error rates using the measured values are 0.09% minimum, 5.76% maximum, and 1.94 standard deviation (SD) for the Levenberg–Marquardt backpropagation model and 0.41% minimum, 5.05% maximum, and 1.68 SD for the Bayesian regularization backpropagation model. The conjugate gradient with Polak–Ribiére updates backpropagation model yielded lower values than the other two models, with 0.31% minimum, 5.73% maximum, and 1.76 SD. Based on the results for the predictive performance evaluation index, CvRMSE, all other models (conjugate gradient with Fletcher–Reeves updates backpropagation, one-step secant backpropagation, gradient descent with momentum and adaptive learning rate backpropagation, gradient descent with momentum backpropagation) except for the gradient descent backpropagation model yielded results that satisfy ASHRAE (American Society of Heating, Refrigerating and Air-Conditioning Engineers) Guideline 14. The results of this study confirm that the prediction performance may differ for each multilayer neural network training algorithm. Therefore, selecting the appropriate model to fit the characteristics of a specific project is essential.

Optimized Artificial Neural Network for Evaluation: C4 Alkylation Process Catalyzed by Concentrated Sulfuric Acid.

In this work, an artificial neural network was first achieved and optimized for evaluating product distribution and studying the octane number of the sulfuric acid-catalyzed C4 alkylation process in the stirred tank and rotating packed bed. The feedstock compositions, operating conditions, and reactor types were considered as input parameters into the artificial neural network model. Algorithm, transfer function, and framework were investigated to select the optimal artificial neural network model. The optimal artificial neural network model was confirmed as a network topology of 10-20-30-5 with Bayesian Regularization backpropagation and tan-sigmoid transfer function. Research octane number and product distribution were specified as output parameters. The artificial neural network model was examined, and 5.8 × 10–4 training mean square error, 8.66 × 10–3 testing mean square error, and ±22% deviation were obtained. The correlation coefficient was 0.9997, and the standard deviation of error was 0.5592. Parameter analysis of the artificial neural network model was employed to investigate the influence of operating conditions on the research octane number and product distribution. It displays a bright prospect for evaluating complex systems with an artificial neural network model in different reactors.

Machine Learning Algorithm for Delay Prediction in IoT and Tactile Internet

The next-generation cellular systems, including fifth-generation cellular systems (5G), are empowered with the recent advances in artificial intelligence (AI) and other recent paradigms. The internet of things (IoT) and the tactile internet are paradigms that can be empowered with AI solutions and integrated with 5G systems to deliver novel services that impact the future. Machine learning technologies (ML) can understand examples of nonlinearity from the environment and are suitable for network traffic prediction. Network traffic prediction is one of the most active research areas that integrates AI with information networks. Traffic prediction is an integral approach to ensure security, reliability, and quality of service (QoS) requirements. Nowadays, it can be used in various applications, such as network monitoring, resource management, congestion control, network bandwidth allocation, network intrusion detection, etc. This paper performs time series prediction for IoT and tactile internet delays, using the k-step-ahead prediction approach with nonlinear autoregressive with external input (NARX)-enabled recurrent neural network (RNN). The ML was trained with four different training functions: Bayesian regularization backpropagation (Trainbr), Levenberg–Marquardt backpropagation (Trainlm), conjugate gradient backpropagation with Fletcher–Reeves updates (Traincgf), and the resilient backpropagation algorithm (Trainrp). The accuracy of the predicted delay was measured using three functions based on ML: mean square error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE).

Prediction of the Near-Infrared Absorption Spectrum of Single-Walled Carbon Nanotubes Using a Bayesian Regularized Back Propagation Neural Network Model

DNA-wrapped single-walled carbon nanotubes (DNA-SWCNTs) in stable dispersion are expected to be used as biosensors in the future, because they have the property of absorption of light in the near infrared (NIR) region, which is safe for the human body. However, this practical application requires the understanding of the DNA-SWCNTs’ detailed response characteristics. The purpose of this study is to predict, in detail, the response characteristics of the absorption spectra that result when the antioxidant catechin is added to oxidized DNA-SWCNTs, from a small amount of experimental data. Therefore, in the present study, we predicted the characteristics of the absorption spectra of DNA-SWCNTs using the Bayesian regularization backpropagation neural network (BRBPNN) model. The BRBPNN model was trained with the catechin concentration and initial absorption peaks as inputs and the absorption spectra after catechin addition as outputs. The accuracy of the predicted absorption peaks and wavelengths after the addition of catechin, as predicted by the BRBPNN model, was within 1% of the error of the experimental data. By inputting the catechin concentrations under hundreds of conditions into this BRBPNN model, we were able to obtain detailed prediction curves for the absorption peaks. This method has the potential to help to reduce the experimental costs and improve the efficiency of investigating the properties of high-cost materials such as SWCNTs.

Cotton yield estimation model based on machine learning using time series UAV remote sensing data

Crop yield prediction is of great practical significance for farmers to make reasonable decisions, such as decisions on crop insurance, storage demand, cash flow budget, fertilizer, water and other input factors. The traditional yield measurement method is sampling surveys, which require a large area of destructive sampling of cotton fields and consume considerable time and labor costs. This study established a cotton yield estimation model based on time series Unmanned Aerial Vehicle (UAV) remote sensing data. The U-Net semantic segmentation network is used to recognize and extract the boll opening pixels in high-resolution visible images, and the boll opening pixel percentage (BOP) is calculated according to the network extraction results. By combining the multispectral images and the pixel coverage of cotton bolls, a Bayesian regularization BP (back propagation) neural network was used to predict cotton yields. In order to simplify the input parameters of the model, the stepwise sensitivity analysis method is used to eliminate redundant variables and obtain the optimal input feature set. The experimental results show that the R2 of the proposed model is 0.853 at the scale of 0.81 m2 (average results of ten-fold cross validation). This study provides a method that can simultaneously meet the requirements of large-area and small-scale forecasting of cotton yields and provides a new idea for cotton yield measurement and breeding screening.

Plant Leaves Disease Classification Using Bayesian Regularization Back propagation Deep Neural Network

Automatic leaf disease segmentation and detection from plant images has recently become a major research area around the world. The proposed method uses plant images to automatically segment and classify different leaf disease regions. The proposed procedure consists of four steps: Pre-processing is used in the first step to reduce the amount of background noise in the plant image using the Wiener filter. The disease spot is then detected using the hue histogram on the HIS model and these disease spots are then segmented using the K-means algorithm applied on the L*a*b* colour model and highest hue value calculation on HSV colour model. Finally, seventeen colour and texture features are extracted from the disease segment and these features are fed to a forward-propagation deep neural network (FPDNN) classifier which classifies the diseases. We have used the Bayesian regularization back propagation algorithm to fine-tune the results. We have applied FPDNN on varying hidden layers ranging from 1 to 40 and achieved highest accuracy i.e. 97.18% at 19 hidden layers which is larger than other state of art classifiers. Proposed method is implemented in matlab 14a.

Drone Trajectory Segmentation for Real-Time and Adaptive Time-Of-Flight Prediction

This paper presents a method developed to predict the flight-time employed by a drone to complete a planned path adopting a machine-learning-based approach. A generic path is cut in properly designed corner-shaped standard sub-paths and the flight-time needed to travel along a standard sub-path is predicted employing a properly trained neural network. The final flight-time over the complete path is computed summing the partial results related to the standard sub-paths. Real drone flight-tests were performed in order to realize an adequate database needed to train the adopted neural network as a classifier, employing the Bayesian regularization backpropagation algorithm as training function. For the network, the relative angle between two sides of a corner and the wind condition are the inputs, while the flight-time over the corner is the output parameter. Then, generic paths were designed and performed to test the method. The total flight-time as resulting from the drone telemetry was compared with the flight-time predicted by the developed method based on machine learning techniques. At the end of the paper, the proposed method was demonstrated as effective in predicting possible collisions among drones flying intersecting paths, as a possible application to support the development of unmanned traffic management procedures.

A tool to predict the evolution of phase and Young’s modulus in high entropy alloys using artificial neural network

We report an artificial neural network (ANN) based tool to predict the evolution of phase(s) in high entropy alloys (HEAs) and their Young’s modulus. Two independent networks as single channel output and four channel binary output methods have been adopted for testing as well as for predicting the evolution of either single-phase BCC, FCC solid solution (SS) phase, or a mixture of SS phase(s) and intermetallic compound (IM). The data of as-solidified HEAs were collected from the literature, and various thermo-physical as well as electronic parameters, such as mixing entropy (ΔSmix), mixing enthalpy (ΔHmix), atomic size difference (δr), Allen electronegativity ΔχA, Pauling electronegativity (ΔχP), and valence electron concentration (VEC) were calculated for each alloy composition, which was used as input features. The Bayesian regularization backpropagation has been adopted as the learning algorithm. Furthermore, the model has been trained and validated by developing eutectic CoCrFeNiNbx (x = 0.45, 0.5, 0.55 and 0.65) and CoCrFeNiTay (y = 0.2, 0.4, 0.455 and 0.5) HEAs experimentally. The single channel output approach and four channel binary output approach generate the matching accuracy of 85.95% and 92.97% for the main dataset, where the same is 70.83% and 91.67% for the deployment dataset, respectively for phase prediction. The predicted values of Young’s modulus have achieved the relative accuracy of 94.96% and 96.44% for the main and deployment dataset, respectively. TheANN suggests that VECbecomes the dominant factor for phase stability when δr < 3%, whereas the higher value of δr promotes the evolution of two phases in HEAs.