Search results

This paper aims to predicting the behavior of welded angle connections (moment-rotation-temperature) in fire using artificial neural network 10.

An artificial neural networking model is described to predict the moment-rotation response of semi-rigid beam-to-column joints at elevated temperature.

Data from 47 experimental fire tests and verified finite element model are used for training and testing and validating the neural network models. The model’s predicted values are compared with actual test results. The results indicate that the models can predict the moment-rotation-temperature behavior of semi-rigid beam-to-column joints with very high accuracy. The developed model can be modified easily to investigate other parameters that influence the performance of joints in fire.

The results indicate that the models can predict the moment-rotation-temperature behavior of semi-rigid beam-to-column joints with very high accuracy. The developed model can be modified easily to investigate other parameters that influence the performance of joints in fire.

The aim of this paper is to develop a suitable artificial neural network (ANN) model that fits best in predicting the experimental flow stress values to the closet proximity for mechanically alloyed Al6063/0.75Al2O3/0.75Y2O3 hybrid nanocomposite.

The ANN model is implemented on neural network toolbox of MATLAB^® using feed‐forward back propagation network and logsig functions. A set of 80 training data and 20 testing data were used in the ANN model. The layout of the network is arranged with three input parameters that include temperature, strain and strain rate, one hidden layer with 22 neurons and one output parameter consisting of flow stress. Flow stress was also predicted using Arrhenius constitutive model.

Based on the comparison of the predicted results using ANN model and Arrhenius constitutive model, it was observed that the ANN model has higher accuracy and could be used to estimate the flow stress values during hot deformation of Al6063/0.75Al2O3/0.75Y2O3 hybrid nanocomposite.

The ANN trained with feed forward back propagation algorithm developed, presents the excellent performance of flow stress prediction of Al6063/0.75Al2O3/0.75Y2O3 hybrid nanocomposite with minimum error rates.

Modeling Wastewater Treatment Plant (WWTP) constitutes an important tool for controlling the operation of the process and for predicting its performance with substantial influent fluctuations. The purpose of this paper is to apply an artificial neural network (ANN) approach with a feed-forward back-propagation in order to predict the ten-month performance of Touggourt WWTP in terms of effluent Chemical Oxygen Demand (CODeff).

The influent variables such as (pHinf), temperature (TEinf), suspended solid (SSinf), Kjeldahl Nitrogen (KNinf), biochemical oxygen demand (BODinf) and chemical oxygen demand (CODinf) were used as input variables of neural networks. To determine the appropriate architecture of the neural network models, several steps of training were conducted, namely the validation and testing of the models by varying the number of neurons and activation functions in the hidden layer, the activation function in output layer as well as the learning algorithms.

The better results were achieved with an architecture network [6-50-1], hyperbolic tangent sigmoid activation functions at hidden layer, linear activation functions at output layer and a Levenberg – Marquardt method as learning algorithm. The results showed that the ANN model could predict the experimental results with high correlation coefficient 0.89, 0.96 and 0.87 during learning, validation and testing phases, respectively. The overall results indicated that the ANN modeling approach can provide an effective tool for simulating, controlling and predicting the performance of WWTP.

This work is the first of its kind in this region due to the remarkable development in terms of population and agricultural activity in the region, which drove to the increase of water pollutants, so it is necessary to use the modern technologies to modeling and controlling of WWTP.

The aim of this paper is to redesign of morphing unmanned aerial vehicle (UAV) using neural network for simultaneous improvement of roll stability coefficient and maximum lift/drag ratio.

Redesign of a morphing our UAV manufactured in Faculty of Aeronautics and Astronautics, Erciyes University is performed with using artificial intelligence techniques. For this purpose, an objective function based on artificial neural network (ANN) is obtained to get optimum values of roll stability coefficient (C_lβ) and maximum lift/drag ratio (E_max). The aim here is to save time and obtain satisfactory errors in the optimization process in which the ANN trained with the selected data is used as the objective function. First, dihedral angle (φ) and taper ratio (λ) are selected as input parameters, C*_lβ and E_max are selected as output parameters for ANN. Then, ANN is trained with selected input and output data sets. Training of the ANN is possible by adjusting ANN weights. Here, ANN weights are adjusted with artificial bee colony (ABC) algorithm. After adjusting process, the objective function based on ANN is optimized with ABC algorithm to get better C_lβ and E_max, i.e. the ABC algorithm is used for two different purposes.

By using artificial intelligence methods for redesigning of morphing UAV, the objective function consisting of C*_lβ and E_max is maximized.

It takes quite a long time for E_max data to be obtained realistically by using the computational fluid dynamics approach.

Neural network incorporation with the optimization method idea is beneficial for improving C_lβ and E_max. By using this approach, low cost, time saving and practicality in applications are achieved.

This method based on artificial intelligence methods can be useful for better aircraft design and production.

It is creating a novel method in order to redesign of morphing UAV and improving UAV performance.

This paper aims to explore the effectiveness of an artificial neural network (ANN) in predicting fraudulent financial reporting in small market capitalization companies in Malaysia.

Based on the concepts of ANN, a mathematical model was developed to compare non-fraud and fraud companies selected from among small market capitalization companies in Malaysia; the fraud companies had already been charged by the Securities Commission for falsification of financial statements. Ten financial ratios are used as fraud risk indicators to predict fraudulent financial reporting using ANN.

The findings indicate that the proposed ANN methodology outperforms other statistical techniques widely used for predicting fraudulent financial reporting.

The study is one of few to adopt the ANN approach for the prediction of financial reporting fraud.

The purpose of this paper is to demonstrate the applicability of swarm and evolutionary techniques for regularized machine learning. Generally, by defining a proper penalty function, regularization laws are embedded into the structure of common least square solutions to increase the numerical stability, sparsity, accuracy and robustness of regression weights. Several regularization techniques have been proposed so far which have their own advantages and disadvantages. Several efforts have been made to find fast and accurate deterministic solvers to handle those regularization techniques. However, the proposed numerical and deterministic approaches need certain knowledge of mathematical programming, and also do not guarantee the global optimality of the obtained solution. In this research, the authors propose the use of constraint swarm and evolutionary techniques to cope with demanding requirements of regularized extreme learning machine (ELM).

To implement the required tools for comparative numerical study, three steps are taken. The considered algorithms contain both classical and swarm and evolutionary approaches. For the classical regularization techniques, Lasso regularization, Tikhonov regularization, cascade Lasso-Tikhonov regularization, and elastic net are considered. For swarm and evolutionary-based regularization, an efficient constraint handling technique known as self-adaptive penalty function constraint handling is considered, and its algorithmic structure is modified so that it can efficiently perform the regularized learning. Several well-known metaheuristics are considered to check the generalization capability of the proposed scheme. To test the efficacy of the proposed constraint evolutionary-based regularization technique, a wide range of regression problems are used. Besides, the proposed framework is applied to a real-life identification problem, i.e. identifying the dominant factors affecting the hydrocarbon emissions of an automotive engine, for further assurance on the performance of the proposed scheme.

Through extensive numerical study, it is observed that the proposed scheme can be easily used for regularized machine learning. It is indicated that by defining a proper objective function and considering an appropriate penalty function, near global optimum values of regressors can be easily obtained. The results attest the high potentials of swarm and evolutionary techniques for fast, accurate and robust regularized machine learning.

The originality of the research paper lies behind the use of a novel constraint metaheuristic computing scheme which can be used for effective regularized optimally pruned extreme learning machine (OP-ELM). The self-adaption of the proposed method alleviates the user from the knowledge of the underlying system, and also increases the degree of the automation of OP-ELM. Besides, by using different types of metaheuristics, it is demonstrated that the proposed methodology is a general flexible scheme, and can be combined with different types of swarm and evolutionary-based optimization techniques to form a regularized machine learning approach.

This study aims to the three major problems of low cleaning efficiency, high labor intensity and difficult to evaluate the cleaning effect for manual insulators cleaning in ultra high voltage (UHV) converter station, the purpose of this paper is to propose a basic configuration of UHV vertical insulator cleaning robot with multi-freedom-degree mechanical arm system on mobile airborne platform and its innovation cleaning operation motion planning.

The main factors affecting the insulators cleaning effect in the operation process have been analyzed. Because of the complex coupling relationship between the influencing factors and the insulators cleaning effect, it is difficult to establish its analytical mathematical model. Combining the non-linear mapping and approximation characteristics of back propagation (BP) neural network, the insulator cleaning effect evaluation can be abstracted as a non-linear approximation process from actual cleaning effect to ideal cleaning effect. An evaluation method of robot insulator cleaning effect based on BP neural network has been proposed.

Through the BP neural network training, the robot cleaning control parameters can be obtained and used in the robot online operation control, so that the better cleaning effect can be also obtained. Finally, a physical prototype of UHV vertical insulator cleaning robot has been developed, and the effectiveness and engineering practicability of the proposed robot configuration, cleaning effect evaluation method are all verified by simulation experiments and field operation experiments. At the same time, this method has the remarkable characteristics of sound versatility, strong adaptability, easy expansion and popularization.

An UHV vertical insulator cleaning robot operation system platform with multi-arm system on airborne platform has been proposed. Through the coordinated movement of the manipulator each joint, the manipulator can be positioned to the insulator strings, and the insulator can be cleaned by two pairs high-pressure nozzles located at the double manipulator. The influence factors of robot insulator cleaning effect have been analyzed. The BP neural network model of insulator cleaning effect evaluation has been established. The evaluation method of robot insulator cleaning effect based on BP neural network has also been proposed, and the corresponding evaluation result can be obtained through the network training. Through the system integration design, the robot physical prototype has been developed. For the evaluation of other operation effects of power system, the validity and engineering practicability of the robot mechanism, motion planning and the method for evaluating the effect of robot insulator cleaning have been verified by simulation and field operation experiments.

This paper provides an effective study to detect and locate the inter-turn short-circuit faults (ITSC) in a three-phase induction motor (IM) using the support vector machine (SVM). The characteristics extracted from the analysis of the phase shifts between the stator currents and their corresponding voltages are used as inputs to train the SVM. The latter automatically decides on the IM state, either a healthy motor or a short-circuit fault on one of its three phases.

To evaluate the performance of the SVM, three supervised algorithms of machine learning, namely, multi-layer perceptron neural networks (MLPNNs), radial basis function neural networks (RBFNNs) and extreme learning machine (ELM) are used along with the SVM in this study. Thus, all classifiers (SVM, MLPNN, RBFNN and ELM) are tested and the results are compared with the same data set.

The obtained results showed that the SVM outperforms MLPNN, RBFNNs and ELM to diagnose the health status of the IM. Especially, this technique (SVM) provides an excellent performance because it is able to detect a fault of two short-circuited turns (early detection) when the IM is operating under a low load.

The original of this work is to use the SVM algorithm based on the phase shift between the stator currents and their voltages as inputs to detect and locate the ITSC fault.

The purpose of this paper is to propose a control approach for small unmanned helicopters, and a novel swarm intelligence algorithm is used to optimize the parameters of the proposed controller.

Small unmanned helicopters have many advantages over other unmanned aerial vehicles. However, the manual operation process is difficult because the model is always instable and coupling. In this paper, a novel optimized active disturbance rejection control (ADRC) approach is presented for small unmanned helicopters. First, a linear attitude model is built in hovering condition according to small perturbation linearization. To realize decoupling, this model is divided into two parts, and each part is equipped with an ADRC controller. Finally, a novel Levy flight-based pigeon-inspired optimization (LFPIO) algorithm is developed to find the optimal ADRC parameters and enhance the performance of controller.

This paper applies ADRC method to the attitude control of small unmanned helicopters so that it can be implemented in practical flight under complex environments. Besides, a novel LFPIO algorithm is proposed to optimize the parameters of ADRC and is proved to be more efficient than other homogenous methods.

The model of proposed controller is built in the hovering action, whereas it cannot be used in other flight modes.

The optimized ADRC method can be implemented in actual flight, and the proposed LFPIO algorithm can be developed in other practical optimization problems.

ADRC method can enhance the response and robustness of unmanned helicopters which make it valuable in actual environments. The proposed LFPIO algorithm is proved to be an effective swarm intelligence optimizer, and it is convenient and valuable to apply it in other optimized systems.

This paper aims to predict the needle penetration force (NPF) in denim fabrics using the artificial neural network (ANN) and multiple linear regression (MLR) models based on the effects of various sewing parameters.

In order to design the ANN and MLR models, four parameters including fabric weight, number of fabric layers, weave pattern, and sewing needle size are taken into account as the input parameters and NPF as the output parameter. According to these parameters, 140 samples of data were resulted. Each sample was tested five times. From these 140 data (input-output data pairs), 112 were used for training the ANN and MLR models and 28 samples were used to test the performance of ANN and MLR. Also, the NPF was measured on the Instron tensile tester to simulate sewing process.

The results indicated that the NPF in denim fabrics can be well predicted in terms of sewing parameters by using ANN and MLR models, in which the ANN model exhibits greater performance than MLR (RANN=0.989> RMLR=0.901).

The NPF measurement method is limited at low speed.

Using the ANN model for forecasting NPF in denim fabrics can help the garment manufactures to produce high-quality denim products and improve the sewing process through reducing seam damage. The NPF could be also measured in the cycle loading conditions similar to sewing machine process by using a special designed tools mounted on the Instron tensile tester.