×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerThis paper explores the potential of using artificial neural networks to predict the ultimate moment capacity of steel-concrete composite beams with metal deck slabs. Basic information on artificial neural networks and parameters suitable for the analysis of experimental results are given. A multilayer backpropagation neural network is used for training and testing the experimental data. A comparison study between the experimental values and two models (neural network and AJSC models) is also carried out. It was found that 1he neural network model provides better results. The proposed neural network is also used to explore the effect of the various parameters on the behavior of beams.
Artificial Neural Networks (ANN) have been applied to structural engineering in recent years. Most of the researches are based on backpropagation neural networks due to its well-studied theory. A backpropagation neural network has been used to predict the ultimate torsional strength of reinforced concrete rectangular beams. The effects of the parameters, such as the number of nodes in the input, output and hidden layers and the pre-process of the training patterns, on the behaviour of the neural network have been investigated. The algorithm called 'resilient propagation algorithm' has been used to the performance of the neural network. After training, the generalization of the neural network was tested by the patterns not included in the training patterns. Once the neural network has been trained, the ultimate torsional strength of reinforced concrete is obtained very easily and efficiently. Based on the ANN results, a parametric analysis was carried out to study the influence of parameters affecting the ultimate torsional strength of reinforced concrete beams and these results are compared with the equations of ACI-code.
An experimental study has been implemented to study the effect of the central radial groove on the bearing pressure distribution. This study is based on the artificial neural network in the prediction of the complex and uncertain positions. Both width and depth of the groove have been varied at some magnitudes in order to investigate their effects on the pressure distribution and the stability of the bearing. Also, the effect of the groove parameters on the noise at the bearing situation in the systems have been analyzed and discussed. The results show that the use of neural network in the prediction of some points with range is very powerful in the minimization of the overall cost of groove design.
The accurate prediction of machinery faults is considered an effective strategy to increase the operation life of machines, ensure smooth operation, and provide a safe environment. Accordingly, the demands on predictive tools such as machine learning to detect machinery faults before catastrophic failure occurs has increased rapidly. In this research, a diagnosis algorithm based on using a 2D color-coded map as the input to a deep artificial neural network is proposed. These maps are called RDEgram after the processing of vibrational signals based on reverse dispersion entropy (RDE) method. The effectiveness of the proposed algorithm is investigated by testing its capability to detect different faults located at different locations on ball bearings under constant speed conditions. First, the squared envelope signal is extracted by applying the short time Fourier transform to vibration signal. Then, the RDE is used to process the squared envelope to detect the range of frequencies at which the transients occur. The RDEgram color-coded map is used to represent the RDE values as a function of frequency and frequency resolution. The maps from different fault features are collected to form the diagnostic patterns. Finally, a pretrained convolutional neural network (CNN) is applied to learn the feature pattern and diagnose the bearing faults. The CNN is trained using fixed- speed data and then it is applied to diagnose faults in the test data recorded at the same speed. The prediction method adopted in the current research shows a 100% level of accuracy for predicting two types of faults (pit and slot) located at various positions a ball bearing (KOYO 1205 C3 type) running at two constant speeds (25 and 30 Hz).
Impact energy prediction of thermal aged cast stainless steel from impact test was studied using artificial neural network (ANN) modeling. Impact energy data for specimens from eleven cast stainless steel alloys at different aging times and temperatures, were used to evaluate possible artificial neural network architecture for prediction impact energy. These data are taken from Argonne National Laboratories (ANL) in USA that involved impact test results of cast stainless steel after aging between 200 and 400oC for up to 30000 hour. The ANN model exhibited excellent comparison with experimental results of ANL i.e. correlation coefficient (R=0.9451) and mean square error (MSE=1.2*10-5). Since a large number of variables were used during training the ANN model, a reliable and useful predictor for impact energy in thermal aged cast stainless steel was provided.
In this research, the effect of seawater environments and surface roughness on uniform corrosion rate of carbon steel (A516 grade 65) was studied depending on the experimental work and artificial neural network modeling. The experimental work involves chemical composition, samples machining, roughness measurements (for carbon steel specimens), conductivity and salinity measurements (for seawater), and uniform corrosion test. Weight loss technique was employed in determining the uniform corrosion rate in carbon steel material. Also, artificial neural network (ANN) model was built to predict the values of uniform corrosion rate (mpy) at different values of conductivity, salinity for seawater and roughness factor for carbon steel depending on the experimental results which were used train and test the ANN. The results obtained of uniform corrosion rate by ANN predictions are shown to be agreed well against experimental values. i.e. correlation coefficient, R=0.9974
In this paper, a Neural Network (NN) model system for self-organization fish school system is identified. Monitoring and data extraction from fish school video has been achieved by using image processing technique in order to generate the data suitable for parameter identification of NN model system. Data obtained have been used to identify the parameters of a model based on a black-box represented by nonlinear autoregressive exogenous model (NARX). The obtained results show that this system can be used for multi robot formation system.
Diagnosing faults in rotary machines is critical, as early fault detection is a precise and essential task in minimizing operational risks and economic losses. Bearings are vital components in rotary machines and are subject to gradual degradation due to continuous operation. Failure to detect early damage can lead to problem escalation, resulting in severe damage and increased costs. In this study, two types of signals from rotary machines are analyzed: acoustic emission (AE) signals and vibration signals. These signals are utilized as input features for a deep learning neural network based on images, where the features are extracted using the Kurtogram, a powerful fourth-order spectral analysis tool that generalizes spectral kurtosis (SK) for a given signal. The results demonstrate that the accuracy of diagnosing the machine’s operational condition whether healthy or faulty ranges from 99.2% to 100%, while the accuracy of fault classification reaches 96.6%. These findings highlight the high efficiency of this methodology in fault detection and classification, establishing it as one of the most important techniques for diagnosing faults in rotary machines.
The discovery and identification of damages in engineering structures is very important in the field of engineering maintenance, as it is a great challenge in presenting new methods in measuring vibrations and discovering damages with the development in the field of automation and high accuracy in discovering damages. In this study, natural frequencies and mode shapes of transverse vibration for damage detection in structures are investigated. The study is performed for various crack depth and crack location. And suggested a new technique based on Continuous Wavelet Transform (CWT) and Convolution Neural Network (CNN). The comparison will be done by simulating the oscillations of a cantilever steel beam with and without defect as a numerical case. The proposed new technique proved to outperform classical methods and has achieved a100% accuracy in the identification of defect position for the data studied.
The dieless drawing process is an innovative method emanated and appeared in coincidence with development of the concept of metal superplasticity. It is utilized from the local heating of a wire or tube to a specified temperature and followed by a local cooling, so an additional deformation is inhibited. In this study, a special dieless drawing machine was designed to carry out an experimental program on SUS304-stainless steel wire having diameter of (1.6-2) mm to investigate the main process parameters such as speeds, heat quantity, heating coil width and heating-cooling separation distance. Also, a numerical model based on thermo-mechanical analysis was developed and validated with experimental program. Furthermore, an artificial neural network ANN model based on current experimental data was prepared to predict the dieless drawing behavior. A maximum area reduction of 40.7% was obtained in single pass. A 3.12mm/s feeding velocity and 4.97mm/s drawing velocity were realized through the experimental tests. The results showed that both drawing force and wire profile were effected by increasing of feeding speed, heating coil width and separation distance. Also, it is confirmed that strain rate was reduced by increasing the heating coil width and the reduction ratio was promoted. A maximum error of 21% was recorded between ANN model and experimental results. The results showed a good agreement among experimental, numerical and ANN models.
The paper deals with neural networks identification of ultimate moment capacity of steel-concrete composite beams on base of experimental results. Basic information on artificial neural networks and its parameters suitable for analysis of experimental results are given. Two types of neural network algorithms are used. Results of identification are reported. The results show that artificial neural networks are highly suitable for assessing the ultimate moment capacity of composite section. The proposed neural network was also used to explore the effect of the various parameters on the behaviour of composite beams.
Safwan-Zubair area is regarded as one of the important agricultural areas in Basrah province, South of Iraq. The aim of this study is to predict groundwater level in this area using ANNs model. The data required for building the ANNs model are generated using MODFLOW model (V.5.3). MODFLOW model was calibrated based on field measurements of groundwater level in 13 monitoring wells during a period of one year (Nov./2013 to Oct/2014). The neural network toolbox available in MATLAB version 7.1 (2010B) was used to develop the ANN models. Three layers feed-forward network with Log- sigmoid transfer function was used. The networks were trained using Levenberg-Marquradt back-propagation algorithm. The ANN modes are divided into two groups, each of four models. The input data of the first group include hydraulic heads, while, the input data of the second group include hydraulic heads and recharge rates. Based on results of this study it was found that; the best ANN model for predicting groundwater levels in the study area is obtained when the input data includes hydraulic heads and recharge rates of two successive months preceding the target month, the best structure of ANN model is of three layers feed-forward network type composes of two hidden layers, each of ten nodes, and the including of recharge rates as input data, beside the hydraulic heads has improved slightly the results.
The present study deals with the analysis of short reinforced concrete columns subjected to axial load. One of the efficient techniques is applied, known as artificial neural networks. The descent gradient backpropagation algorithm is employed for analysis. The optimum topology (which gives the least mean square error for both training and testing with a fewer number of epochs) is presented. The effects of the number of nodes in input and hidden layer(s), and selecting of leaming rate and momentum coefficient, on the behavior of the neural network, have been investigated. Due to the slow convergence of results when using descent gradient backpropagation, the faster algorithm called "resilient backpropagation algorithm" has been used to improve the performance of the neural network and the results have been compared with those obtained using the descent gradient backpropagation algorithm.
This paper considers the neural network based PID controller. The learning and generalization properties of neural network are utilized in improving the performance of a conventional PID controller. Two different schemes are introduced. Both schemes are studied and their performances are comparatively evaluated on an example for uncertain system.
This study uses intelligent techniques to regulate brushless direct current speed (BLDC) motors. After these motors solved the problem of using brushes and commutators in traditional DC motors, they succeeded in replacing brushes and commutators with electronic commutators. Due to the use of electronic switching, brushless motor algorithms are more complex than those of conventional motors. In this study, to adjust the PID controller's settings (Kp, Ki, and Kd), a trial-and-error approach was taken, and a completely new method known as the settings of known PID controllers have been modified using the new Gray Wolf algorithm. A BLDC motor's main benefit is that it has easy speed adjustment across a broad range, whereas AC motors often cannot be controlled in this way. Through the use of Matlab/Simulink, the BLDC motor's mathematical model was developed and implemented. The simulation results show that in the first case, a PID controller effectively induces the turbulent dynamic behavior of BLDC under load and no-load conditions, and in the second case, the speed shows the lowest rise time, stability, overshoot, and stability conditions, and performs at its best. The characteristics of the traditional PID controller that regulates the engine speed must be regulated online to achieve the use of intelligent technologies, and the adjustment is done online using the neural network. The results showed that this technology, or feature - online tuning - is the most effective and reliable of all.
The land surface erosion is controlled by multifarious of different parameters, such as slope, soil physical properties (texture, structure, permeability, etc.), rainfall, runoff, and crop cover. However, it is impossible to develop precise simplest mathematical model that can predict the values of land surface soil erosion due to the behavior of controlled parameters. This paper presents the Neural Networks Model for assessing land surface soil erosion as amass per unit area per unit of time. The model derives from the analysis data obtained from available literature and was formulated as linear regression model and back propagation algorithm neural model. Both models were built by correlating firstly five watersheds variables with land surface erosion and secondly ten watershed variables with land surface erosion. The coefficients for independent variables were highly significant for both models. The case of correlating 10- watershed variables with land surface erosion gives R=0.978 & 0.976 for both models which is higher than that for 5- watershed variables. The mean absolute relative error (MARE%) is another procedure that used in order to evaluate the accuracy of the model and The average error % is 0.025 for (5) variables and 0.0064 for (10) variables. Both the supporting practices (P) and the slope length and slope steepness (LS) coefficients have a marked effect on the amount of land surface erosion in the case of 5- watershed variables. The amount of land surface erosion show a high level of sensitivity to the content of fine sand% in soil (FS) watershed variables on The amount of land surface soil erosion.
An intelligent and anticipatory speed controller for internal combustion engines was designed theoretically and examined experimentally. This design was based on the addition of a torque loop to the main speed loop. The model can sense the external load with the help of a load cell and send this signal to a soft computing unit for analysis and processing. This scheme will improve the ability of anticipation of controller since it treats the factors that affect the speed, not the speed itself. The experimental design was implemented using two types of actuating techniques; an intelligent throttling actuator and an intelligent injection actuator. The signal was analyzed by using intelligent techniques such as fuzzy logic, neural network and genetic algorithm. The experimental data were used to train the neural and the Adaptive Neuro–Fuzzy Inference System. The comparison of the results obtained in this work with other available models proved the efficiency and the robustness of the present model.
A spandrel beam is a structural member lies at the edge of a frame and is connected by a joint to the floor beam extending into the slab. The spandrel beams are primarily responsible for transferring forces from a slab to the supporting edge columns. This work investigates the possibility of using the artificial neural networks to model the complicated nonlinear relationship between the various input parameters associated with reinforced concrete spandrel beams and the actual ultimate strength of them. The descent gradient backpropagation algorithm was employed for predicting the ultimate strength of the reinforced concrete spandrel beams. The optimum topology (which gives least mean square error for both training and testing with fewer number of epochs) is presented. Effects of parameters such as, number of hidden layer(s), number of nodes in the input layer, output layer and hidden layer(s), initialization weight factors and selection of the learning rate and momentum coefficient on the behaviour of the neural network have been investigated. Because of the slow convergence of results when using descent gradient backpropagation, another algorithm which is faster called "resilient backpropagation algorithm" has been used. The neural network trained with the resilient backpropagation RPROP algorithm gives better results than that trained with the steepest descent algorithm with momentum GDM algorithm.
Castor Oil is a natural raw material, used to prepare Brominated Castor Oil (BCO) and quaternary ammonium salt based castor oil (TEt-CO). The two products were tested as demulsifiers and compared with a commercial demulsifier (Chimec2439) by using bottle test method. BCO showed a high ability on water separation efficiency 90% with a dose of 150µl at 120min time settling while TEt- CO showed a low water separation efficiency reached to 10%. The effect of the demulsifier BCO was tested by varying different variables which have an obvious effect on water separation efficiency such as: dose, temperature, time of mixing emulsion, pH and salinity of aqueous phase of emulsion, and water ratio. The effect of some additives (i.e. methanol, ethanol, xylene and toluene) on the efficiency of the BCO was tested for the purpose of enhancing its effectiveness to break the crude oil emulsion. The experimental data obtained by using BCO were formulated as a model using the Artificial Neural Networks (ANNs) to evaluating the water separation efficiency. Multi-layer perceptron artificial neural network was developed based on the collected data of this study. The results showed that the training algorithm of back propagation (BP) is sufficient enough in predicting BCO efficiency under different operation conditions. It was found that the correlation coefficient values are 0.9995 and 0.9999 for the testing and training data, respectively and the mean square error (MSE) was 6.18*10^-5 at 200 epochs.
This paper is concerned with the design of a new controller for active suspension system. The model is considered as a quarter-car. The presented controller depends on the fuzzy technique and NARMA-L2 linearization algorithm. The compensation system that added by the fuzzy rules improves the performance of the controller, while the neural network produces the required control signal. The new controller can achieve an improvement of the ride comfort with a reasonable value of power consumption. The mathematical analysis of the mechanical power used by the model is focused on the average and the RMS of the power supplied to the system, regardless of the frequency content of the vibration signal. The simulation results which are verified by a practical examples of road profiles, demonstrate the efficacy of the proposed controller.
Interest in neural networks as an alternative to the conventional algorithmic techniques has grown rapidly in recent years. Noise removal or noise suppression is an important task in image processing. In general, the results of the noise removal have a strong influence on the quality of the following image processing techniques. In this paper, two feed forward NN schemes have been presented for impulsive noise removal. The computation is reduced by using an artificial image in training. Results of NN schemes show high performance especially when the ratio of impulsive noise in testing are the same or greater than that of training image. The presented schemes are used for grayscale and also for truecolor.
This paper introduces a radial distribution feeder protection scheme based on certain features extraction from current signals measurement at the substation. The features are captured using the discrete wavelet transform (DWT). Two digital signals processing methods are used to introduce those features to the 1) fault detection 2) identification and 3) localization schemes; the first one is the energy method and the second one is the root mean square method. For the purpose of fault type identification, two systems are tested and compared, a Fuzzy Inference System (FIS) and Artificial Neural Network (ANN). Fault location scheme is then built based on ANNs. An effort is made to reduce the computational burden and the speed of detection provided by the fault detection and identification schemes. Since the short circuit faults are the most likely types of faults that can occur in power systems, the ten types of these faults taking into account different fault resistances are simulated in MATLAB environment and the protection scheme is built based on the idea of over current. The power quality disturbances such as switching transient events on the feeder is also taken into account in order to build a reliable and secure protection scheme.