Prediction of Oxidation Stability of Biodiesel Derived from Waste and Refined Vegetable Oils by Statistical Approaches

The oxidation stability (OX) of the biodiesel is an essential parameter mainly during storage, which reduces the quality of the biodiesel, thus affecting the engine performance. Moreover, many factors affect oxidation stability. Therefore, determining the most significant parameter is essential for achieving accurate predictions. In this paper, an empirical equation (Poisson Regression Model (PRM)), machine learning models (Multilayer Feed-Forward Neural Network (MFFNN), Cascade Feed-forward Neural Network (CFNN), Radial Basis Neural Network (RBFNN), and Elman neural network (ENN)) with various combinations of input parameters are utilized and employed to identify the most relevant parameters for prediction of the oxidation stability of biodiesel. This study measured the physicochemical properties of 39 samples of waste frying methyl ester and their blends with various percentages of palm biodiesel and refined canola biodiesel. To this aim, 14 parameters including concentration amount of WFME (X1), PME (X2), and RCME (X3) in the mixture, kinematic viscosity (KV) at 40 °C, density at 15 °C (D), cloud point (CP), pour point (PP), the estimation value of the sum of the saturated (∑SFAMs), monounsaturated (∑MUFAMs), polyunsaturated (∑PUFAMs), degree of unsaturation (DU), long-chain saturated factor (LCSF), very-long-chain fatty acid (VLCFA), and ratio (∑MUFAMs+∑PUFAMs∑SFAMs) fatty acid composition were considered. The results demonstrated that the RBFNN model with the combination of X1, X2, X3, ∑SFAMs, ∑MUFAMs, ∑PUFAMs. VLCFA, DU, LCSF, ∑MUFAMs+∑PUFAMs∑SFAMs, KV, and D has the lowest value of root mean squared error and mean absolute error. In the end, the results demonstrated that the RBFNN model performed well and presented high accuracy in estimating the value of OX for the biodiesel samples compared to PRM, MFFNN, CFNN, and ENN.

Download Full-text

A Grey Wolf Optimization-Based Method for Segmentation and Evaluation of Scaling in Reinforced Concrete Bridges

International Journal of Information Technology & Decision Making ◽

10.1142/s0219622021500425 ◽

2021 ◽

pp. 1-54

Author(s):

Eslam Mohammed Abdelkader ◽

Osama Moselhi ◽

Mohamed Marzouk ◽

Tarek Zayed

Keyword(s):

Neural Network ◽

Reinforced Concrete ◽

Mean Squared Error ◽

Mean Absolute Error ◽

Absolute Error ◽

Concrete Bridges ◽

Grey Wolf Optimization ◽

Elman Neural Network ◽

Reinforced Concrete Bridges ◽

Squared Error

Bridges are prone to severe deterioration agents which promote their degradation over the course of their lifetime. Furthermore, maintenance budgets are being trimmed. This state of circumstances entails the development of a computer vision-based method for the condition assessment of bridge elements in an attempt to circumvent the drawbacks of visual inspection-based models. Scaling is progressive local flaking or loss in the surface portion of concrete that affects the functional and structural integrity of reinforced concrete bridges. As such, this research study proposes a self-adaptive three-tier method for the automated detection and assessment of scaling severity levels in reinforced concrete bridges. The first tier relies on the integration of cross entropy function and grey wolf optimization (GWO) algorithm for the segmentation of scaling pixels. The second tier is designated for the autonomous interpretation of scaling area. In this model, a hybrid feature extraction algorithm is proposed based on the fusion of singular value decomposition and discrete wavelet transform for the efficient and robust extraction of the most dominant features in scaling images. Then an integration of Elman neural network and GWO algorithm is proposed for the sake of improving the prediction accuracies of scaling area though optimization of both structure and parameters of Elman neural network. The third tier aims at establishing a unified scaling severity index to assess the extent of severities of scaling according to its area and depth. The developed method is validated through multi-layered comparative analysis that involved performance evaluation comparisons, statistical comparisons and box plots. Results demonstrated that the developed scaling detection model significantly outperformed a set of widely-utilized classical segmentation models achieving mean squared error, mean absolute error, peak signal to noise ratio and cross entropy of 0.175, 0.407, 55.754 and 26011.019, respectively. With regards to the developed scaling evaluation model, it accomplished remarkable better and more robust performance that other meta-heuristic-based Elman neural network models and conventional prediction models. In this context, it obtained mean absolute percentage error, root-mean squared error and mean absolute error 1.513%, 29.836 and 12.066, respectively, as per split validation. It is anticipated that the developed integrated computer vision-based method could serve as the basis of automated, reliable and cost-effective inspection platform of reinforced concrete bridges which can assist departments of transportation in taking effective preventive maintenance and rehabilitation actions.

Download Full-text

Improving Neural Network Based on Seagull Optimization Algorithm for Controlling DC Motor

Jurnal Elektronika dan Telekomunikasi ◽

10.14203/jet.v21.48-54 ◽

2021 ◽

Vol 21 (1) ◽

pp. 48

Author(s):

Widi Aribowo ◽

Supari Muslim ◽

Fendi Achmad ◽

Aditya Chandra Hermawan

Keyword(s):

Neural Network ◽

Optimization Algorithm ◽

Control Method ◽

Absolute Error ◽

Dc Motor ◽

Motor Speed ◽

Feed Forward Neural Network ◽

Feed Forward ◽

Control Approach ◽

Nature Inspired Algorithm

This article presents a direct current (DC) motor control approach using a hybrid Seagull Optimization Algorithm (SOA) and Neural Network (NN) method. SOA method is a nature-inspired algorithm. DC motor speed control is very important to maintain the stability of motor operation. The SOA method is an algorithm that duplicates the life of the seagull in nature. Neural network algorithms will be improved using the SOA method. The neural network used in this study is a feed-forward neural network (FFNN). This research will focus on controlling DC motor speed. The efficacy of the proposed method is compared with the Proportional Integral Derivative (PID) method, the Feed Forward Neural Network (FFNN), and the Cascade Forward Backpropagation Neural Network (CFBNN). From the results of the study, the proposed control method has good capabilities compared to standard neural methods, namely FFNN and CFBNN. Integral Time Absolute Error and Square Error (ITAE and ITSE) values from the proposed method are on average of 0.96% and 0.2% better than the FFNN and CFBNN methods.

Download Full-text

Role of Feed Forward Neural Networks Coupled with Genetic Algorithm in Capitalizing of Intracellular Alpha-Galactosidase Production byAcinetobactersp.

BioMed Research International ◽

10.1155/2014/361732 ◽

2014 ◽

Vol 2014 ◽

pp. 1-8 ◽

Cited By ~ 2

Author(s):

Sirisha Edupuganti ◽

Ravichandra Potumarthi ◽

Thadikamala Sathish ◽

Lakshmi Narasu Mangamoori

Keyword(s):

Genetic Algorithm ◽

Neural Networks ◽

Mean Squared Error ◽

Absolute Error ◽

Percentage Error ◽

Feed Forward Neural Network ◽

Feed Forward ◽

Squared Error ◽

Feed Forward Neural Networks ◽

Alpha Galactosidase

Alpha-galactosidase production in submerged fermentation byAcinetobactersp. was optimized using feed forward neural networks and genetic algorithm (FFNN-GA). Six different parameters, pH, temperature, agitation speed, carbon source (raffinose), nitrogen source (tryptone), and K2HPO4, were chosen and used to construct 6-10-1 topology of feed forward neural network to study interactions between fermentation parameters and enzyme yield. The predicted values were further optimized by genetic algorithm (GA). The predictability of neural networks was further analysed by using mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), andR2-value for training and testing data. Using hybrid neural networks and genetic algorithm, alpha-galactosidase production was improved from 7.5 U/mL to 10.2 U/mL.

Download Full-text