Artificial neural network (ANN)-based optimization of a numerically analyzed m-shaped piezoelectric energy harvester

2021 ◽  
Author(s):  
Ahsan Ali ◽  
Muhammad Abdullah heeraz ◽  
Saira Bibi ◽  
Muhammad Zubair Khan ◽  
Muhammad Sohail Malik ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Energy Harvester ◽  
Research Work ◽  
Electrical Performance ◽  
Optimization Approach ◽  
Maximum Output ◽  
Piezoelectric Energy ◽  
Artificial Neural

In this research work, the M-shaped cantilever piezoelectric energy harvester is modeled and optimized using advanced artificial intelligence algorithms. The proposed harvester adopts a single structure geometrical configuration in which two secondary beams are being connected to the principal bimorph. Finite element analysis is carried out on COMSOL Multiphysics to analyze the efficiency of the proposed energy harvester. The influence of frequency, load resistance, and acceleration on the electrical performance of the harvester is numerically investigated to enhance the bandwidth of the piezoelectric vibrational energy harvester. Numerical analysis is also utilized to obtain the iterative dataset for the training of the artificial neural network. Furthermore, a genetic multi-objective optimization approach is implemented on the trained artificial neural network to obtain the optimal parameters for the proposed energy harvester. It is observed that optimization using modern artificial intelligence approaches implies nonlinearities of the system and therefore, machine learning-based optimization has shown more convincing results, as compared to the traditional statistical methods. Results revealed the maximum output values for the voltage and electrical power are 15.34 V and 4.77 mW at 51.19 Hz, 28.09 k[Formula: see text], and 3.49 g optimal design input parameters. Based on the outcomes, it is recommended to utilize this reliable harvester in low-power micro-devices, electromechanical systems, and smart wearable devices.

scholarly journals Analyzing student performance using evolutionary artificial neural network algorithm

2018 ◽  
Vol 7 (2.26) ◽  
pp. 67 ◽  
Author(s):  
A S. Arunachalam ◽  
T Velmurugan
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Student Performance ◽  
Fitness Function ◽  
Research Work ◽  
Function Evaluation ◽  
Success Factor ◽  
Optimization Approach ◽  
Artificial Neural

Educational Data Mining (EDM) and Learning Systematic (LS) research have appeared as motivating areas of research, which are clarifying beneficial understanding from educational databases for many purposes such as predicting student’s success factor. The ability to predict a student’s performance can be beneficial in modern educational systems. This research work aims at developing an evolutionary approach based on genetic algorithm and the artificial neural network. The traditional artificial neural network lacks predicting student performance due to the poor modeling structure and the capability of assigning proper weights to each node under the hidden layer. This problem is overwhelmed with the aid of genetic algorithm optimization approach which produces appropriate fitness function evaluation in each iteration of the learning process. The performances gradually increase the accuracy of the prediction and classification more precisely.

scholarly journals Pioneer dataset and recognition of Handwritten Pashto characters using Convolution Neural Networks

2020 ◽  
pp. 002029402096482
Author(s):  
Sulaiman Khan ◽  
Abdul Hafeez ◽  
Hazrat Ali ◽  
Shah Nazir ◽  
Anwar Hussain
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Support Vector Machine ◽  
Research Work ◽  
Recognition Rate ◽  
Recognition Task ◽  
Convolution Neural Network ◽  
Medium Size ◽  
Support Vector ◽  
Artificial Neural

This paper presents an efficient OCR system for the recognition of offline Pashto isolated characters. The lack of an appropriate dataset makes it challenging to match against a reference and perform recognition. This research work addresses this problem by developing a medium-size database that comprises 4488 samples of handwritten Pashto character; that can be further used for experimental purposes. In the proposed OCR system the recognition task is performed using convolution neural network. The performance analysis of the proposed OCR system is validated by comparing its results with artificial neural network and support vector machine based on zoning feature extraction technique. The results of the proposed experiments shows an accuracy of 56% for the support vector machine, 78% for artificial neural network, and 80.7% for the proposed OCR system. The high recognition rate shows that the OCR system based on convolution neural network performs best among the used techniques.

Development of New Permeability Formulation From Well Log Data Using Artificial Intelligence Approaches

2018 ◽  
Vol 140 (7) ◽  
Author(s):  
Tamer Moussa ◽  
Salaheldin Elkatatny ◽  
Mohamed Mahmoud ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Well Log ◽  
Well Test ◽  
Log Data ◽  
Hydrocarbon Reservoir ◽  
Reservoir Permeability ◽  
Artificial Neural ◽  
Core Permeability

Permeability is a key parameter related to any hydrocarbon reservoir characterization. Moreover, many petroleum engineering problems cannot be precisely answered without having accurate permeability value. Core analysis and well test techniques are the conventional methods to determine permeability. These methods are time-consuming and very expensive. Therefore, many researches have been introduced to identify the relationship between core permeability and well log data using artificial neural network (ANN). The objective of this research is to develop a new empirical correlation that can be used to determine the reservoir permeability of oil wells from well log data, namely, deep resistivity (RT), bulk density (RHOB), microspherical focused resistivity (RSFL), neutron porosity (NPHI), and gamma ray (GR). A self-adaptive differential evolution integrated with artificial neural network (SaDE-ANN) approach and evolutionary algorithm-based symbolic regression (EASR) techniques were used to develop the correlations based on 743 actual core permeability measurements and well log data. The obtained results showed that the developed correlations using SaDE-ANN models can be used to predict the reservoir permeability from well log data with a high accuracy (the mean square error (MSE) was 0.0638 and the correlation coefficient (CC) was 0.98). SaDE-ANN approach is more accurate than the EASR. The introduced technique and empirical correlations will assist the petroleum engineers to calculate the reservoir permeability as a function of the well log data. This is the first time to implement and apply SaDE-ANN approaches to estimate reservoir permeability from well log data (RSFL, RT, NPHI, RHOB, and GR). Therefore, it is a step forward to eliminate the required lab measurements for core permeability and discover the capabilities of optimization and artificial intelligence models as well as their application in permeability determination. Outcomes of this study could help petroleum engineers to have better understanding of reservoir performance when lab data are not available.

scholarly journals Performance Evaluation of a Piezoelectric Energy Harvester Based on Flag-Flutter

Micromachines ◽  
2020 ◽  
Vol 11 (10) ◽  
pp. 933 ◽  
Author(s):  
Hassan Elahi ◽  
Marco Eugeni ◽  
Federico Fune ◽  
Luca Lampani ◽  
Franco Mastroddi ◽  
...  
Keyword(s):  
Performance Evaluation ◽  
Wind Tunnel ◽  
Energy Harvesting ◽  
Energy Harvester ◽  
Maximum Output Power ◽  
Research Work ◽  
Maximum Output ◽  
Operational Environment ◽  
Subsonic Wind Tunnel ◽  
Piezoelectric Energy

In the last few decades, piezoelectric (PZT) materials have played a vital role in the aerospace industry because of their energy harvesting capability. PZT energy harvesters (PEH) absorb the energy from an operational environment and can transform it into useful energy to drive nano/micro-electronic components. In this research work, a PEH based on the flag-flutter mechanism is presented. This mechanism is based on fluid-structure interaction (FSI). The flag is subjected to the axial airflow in the subsonic wind tunnel. The performance evaluation of the harvester and aeroelastic analysis is investigated numerically and experimentally. A novel solution is presented to extract energy from Limit Cycle Oscillations (LCOs) phenomenon by means of PZT transduction. The PZT patch absorbs the flow-induced structural vibrations and transforms it into electrical energy. Furthermore, the optimal resistance and length of the flag is predicted to maximize the energy harvesting. Different configurations of flag i.e., with Aluminium (Al) patch and PZT patch for flutter mode vibration mode are studied numerically and experimentally. The bifurcation diagram is constructed for the experimental campaign for the flutter instability of a cantilevered flag in subsonic wind-tunnel. Moreover, the flutter boundary conditions are analysed for reduced critical velocity and frequency. The designed PZT energy harvester via flag-flutter mechanism is suitable for energy harvesting in aerospace engineering applications to drive wireless sensors. The maximum output power that can be generated from the designed harvester is 6.72 mW and the optimal resistance is predicted to be 0.33 MΩ.

Effective Implementation of Value Engineering Using Artificial Neural Network Aid of Optimization Techniques

2019 ◽  
Vol 27 (03) ◽  
pp. 1950022 ◽  
Author(s):  
M. Prem Swarup ◽  
A. Prabhu Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Research Work ◽  
Optimization Techniques ◽  
Value Engineering ◽  
Training Algorithms ◽  
Air Conditioner ◽  
Ann Model ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Value Engineering (VE) is a method for characterizing the developed requirements of a product, and it is concerned with the selection of less excessive conditions. VE can understand and improve the optimal outcome such as quantity, security, unwavering quality and convertibility of each managerial unit. It is an incredible solving tool that can diminish costs while preserving or improving performance and quality requirements. In this research work, VE is presented to calculate the heating cost and cooling cost of the air conditioner with the assistance of an Artificial Neural Network (ANN) with an optimization model. This ANN model effectively chooses the maximum number of sources obtainable and the source respective method with low functional cost and energy consumption. For improving the prediction accuracy of VE in the ANN model, we have incorporated some training algorithms and optimized the network hidden layer and hidden neuron by Opposition Genetic Algorithm (OGA). From the results, trained ANN with OGA predicts the output with 96.02% accuracy and also minimum errors compared with the existing GA process.

Business viability of potential software projects using artificial neural network

2020 ◽  
Vol 26 (1) ◽  
Author(s):  
O. Okolo ◽  
B.Y Baha
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Intelligent Systems ◽  
Project Selection ◽  
Business Value ◽  
Synthetic Approach ◽  
Software Project ◽  
Unseen Data ◽  
Artificial Neural

Selection of a software project is a critical decision. This selection involves prediction to ascertain a project that provides the best business value to the organization. The process of selection is carefully undertaken to optimize scarce resources available, which makes it impossible to simultaneously invest in all business ideas and systems. The current traditional method of software selection does not consider risk factors among the many variables necessary to predict a project that could provide the best business value. More so, the current method such as an artificial intelligence approach, where project managers use more robust models to make predictions have not received the needed attention in developing models for software project selection. This research applied a branch of Artificial Intelligence called Artificial Neural Network to classify projects into three levels. The research designed an artificial neural network of four inputs, one hidden layer with twenty-seven (27) neurons, and three outputs. Keras, a python deep learning library that runs on a theano background was used to implement the model. This research used a secondary dataset, which was enhanced by the synthetic approach, to make the required data features needed in machine learning applications. Backpropagation Algorithm enabled the model to train and learn from the data, and K-fold cross-validation was used to measure the accuracy of the model on unseen data. The results of the simulation showed that the model performed up to 98.67% accuracy with a standard deviation of 2.6% performance on unseen data. The research concludes that using the artificial neural network for software project selection unleashes a new vista of opportunities in artificial i ntelligence where intelligent systems are developed based on robust models from data forproject selection.Keywords: Artificial Neural Network, Project selection, Machine LearningVol. 26, No. 1, June 2019

Prediction of Life of Compound Die Using Artificial Neural Network (ANN)

2014 ◽  
Vol 622-623 ◽  
pp. 664-671 ◽  
Author(s):  
Sachin Kashid ◽  
Shailendra Kumar
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Sheet Metal ◽  
Research Work ◽  
Fem Simulation ◽  
Fem Analysis ◽  
Ann Model ◽  
Sheet Metal Parts ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Prediction of life of compound die is an important activity usually carried out by highly experienced die designers in sheet metal industries. In this paper, research work involved in the prediction of life of compound die using artificial neural network (ANN) is presented. The parameters affecting life of compound die are investigated through FEM analysis and the critical simulation values are determined. Thereafter, an ANN model is developed using MATLAB. This ANN model is trained from FEM simulation results. The proposed ANN model is tested successfully on different compound dies designed for manufacturing sheet metal parts. A sample run of the proposed ANN model is also demonstrated in this paper.

Sign in / Sign up

Export Citation Format

Share Document