Search results

This paper aims to investigate the profile of the wind speed of a Cameroonian city for the very first time, as there is a growing trend for new wind energy installations in the West region of Cameroon. Two well-known artificial neural networks, namely, multi-layer perceptron (MLP) and nonlinear autoregressive network with exogenous inputs (NARX), were used to model the wind speed profile of the city of Bapouh in the West-region of Cameroon.

In this work, the profile of the wind speed of a Cameroonian city was investigated for the very first time since there is a growing trend for new wind energy installations in the West region of Cameroon. Two well-known artificial neural networks namely multi-layer perceptron (MLP) and nonlinear autoregressive network with exogenous inputs (NARX) were used to model the wind speed profile of the city of Bapouh in the West-region of Cameroon. The meteorological data were collected every 10 min, at a height of 50 m from the NASA website over a period of two months from December 1, 2016 to January 31, 2017. The performance of the model was evaluated using some well-known statistical tools, such as root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). The input variables of the model were the mean wind speed, wind direction, maximum pressure, maximum temperature, time and relative humidity. The maximum wind speed was used as the output of the network. For optimal prediction, the influence of meteorological variables was investigated. The hyperbolic tangent sigmoid (Tansig) and linear (Purelin) were used as activation functions, and it was shown that the combination of wind direction, maximum pressure, maximum relative humidity and time as input variables is the best combination.

Maximum pressure, maximum relative humidity and time as input variables is the best combination. The correlation between MLP and NARX was computed. It was found that the MLP has the highest correlation when compared to NARX.

Two well-known artificial neural networks namely multi-layer perceptron (MLP) and nonlinear autoregressive network with exogenous inputs (NARX) were used to model the wind speed profile.

Energy management is critical to data centres (DCs) majorly because they are high energy-consuming facilities and demand for their services continue to rise due to rapidly increasing global demand for cloud services and other technological services. This projected sectoral growth is expected to translate into increased energy demand from the sector, which is already considered a major energy consumer unless innovative steps are used to drive effective energy management systems. The purpose of this study is to provide insights into the expected energy demand of the DC and the impact each measured parameter has on the building's energy demand profile. This serves as a basis for the design of an effective energy management system.

This study proposes novel tunicate swarm algorithm (TSA) for training an artificial neural network model used for predicting the energy demand of a DC. The objective is to find the optimal weights and biases of the model while avoiding commonly faced challenges when using the backpropagation algorithm. The model implementation is based on historical energy consumption data of an anonymous DC operator in Cape Town, South Africa. The data set provided consists of variables such as ambient temperature, ambient relative humidity, chiller output temperature and computer room air conditioning air supply temperature, which serve as inputs to the neural network that is designed to predict the DC’s hourly energy consumption for July 2020. Upon preprocessing of the data set, total sample number for each represented variable was 464. The 80:20 splitting ratio was used to divide the data set into training and testing set respectively, making 452 samples for the training set and 112 samples for the testing set. A weights-based approach has also been used to analyze the relative impact of the model’s input parameters on the DC’s energy demand pattern.

The performance of the proposed model has been compared with those of neural network models trained using state of the art algorithms such as moth flame optimization, whale optimization algorithm and ant lion optimizer. From analysis, it was found that the proposed TSA outperformed the other methods in training the model based on their mean squared error, root mean squared error, mean absolute error, mean absolute percentage error and prediction accuracy. Analyzing the relative percentage contribution of the model's input parameters based on the weights of the neural network also shows that the ambient temperature of the DC has the highest impact on the building’s energy demand pattern.

The proposed novel model can be applied to solving other complex engineering problems such as regression and classification. The methodology for optimizing the multi-layered perceptron neural network can also be further applied to other forms of neural networks for improved performance.

Based on the forecasted energy demand of the DC and an understanding of how the input parameters impact the building's energy demand pattern, neural networks can be deployed to optimize the cooling systems of the DC for reduced energy cost.

The use of TSA for optimizing the weights and biases of a neural network is a novel study. The application context of this study which is DCs is quite untapped in the literature, leaving many gaps for further research. The proposed prediction model can be further applied to other regression tasks and classification tasks. Another contribution of this study is the analysis of the neural network's input parameters, which provides insight into the level to which each parameter influences the DC’s energy demand profile.

In this paper, a newly proposed hybridization algorithm namely constriction coefficient-based particle swarm optimization and gravitational search algorithm (CPSOGSA) has been employed for training MLP to overcome sensitivity to initialization, premature convergence, and stagnation in local optima problems of MLP.

In this study, the exploration of the search space is carried out by gravitational search algorithm (GSA) and optimization of candidate solutions, i.e. exploitation is performed by particle swarm optimization (PSO). For training the multi-layer perceptron (MLP), CPSOGSA uses sigmoid fitness function for finding the proper combination of connection weights and neural biases to minimize the error. Secondly, a matrix encoding strategy is utilized for providing one to one correspondence between weights and biases of MLP and agents of CPSOGSA.

The experimental findings convey that CPSOGSA is a better MLP trainer as compared to other stochastic algorithms because it provides superior results in terms of resolving stagnation in local optima and convergence speed problems. Besides, it gives the best results for breast cancer, heart, sine function and sigmoid function datasets as compared to other participating algorithms. Moreover, CPSOGSA also provides very competitive results for other datasets.

The CPSOGSA performed effectively in overcoming stagnation in local optima problem and increasing the overall convergence speed of MLP. Basically, CPSOGSA is a hybrid optimization algorithm which has powerful characteristics of global exploration capability and high local exploitation power. In the research literature, a little work is available where CPSO and GSA have been utilized for training MLP. The only related research paper was given by Mirjalili et al., in 2012. They have used standard PSO and GSA for training simple FNNs. However, the work employed only three datasets and used the MSE performance metric for evaluating the efficiency of the algorithms. In this paper, eight different standard datasets and five performance metrics have been utilized for investigating the efficiency of CPSOGSA in training MLPs. In addition, a non-parametric pair-wise statistical test namely the Wilcoxon rank-sum test has been carried out at a 5% significance level to statistically validate the simulation results. Besides, eight state-of-the-art meta-heuristic algorithms were employed for comparative analysis of the experimental results to further raise the authenticity of the experimental setup.

The internal (farmer-controlled) and external (non-farmer-controlled) factors affect crop yield. However, not a single study has identified and analyzed yield predictors in India using effective predictive models. Thus, this study aims to investigate how internal and external predictors impact pearl millet yield and Stover yield.

Descriptive analytics and artificial neural network are used to investigate the impact of predictors on pearl millet yield and Stover yield. From descriptive analytics, 473 valid responses were collected from semi-arid zone, and the predictors were categorized into internal and external factors. Multi-layer perceptron-neural network (MLP-NN) model was used in Statistical Package for the Social Sciences version 25 to model them.

The MLP-NN model reveals that rainfall has the highest normalized importance, followed by irrigation frequency, crop rotation frequency, fertilizers type and temperature. The model has an acceptable goodness of fit because the training and testing methods have average root mean square errors of 0.25 and 0.28, respectively. Also, the model has R² values of 0.863 and 0.704, respectively, for both pearl millet and Stover yield.

To the best of the authors’ knowledge, the current study is first of its kind related to impact of predictors of both internal and external factors on pearl millet yield and Stover yield.

The literature reveals that most studies have estimated crop yield using limited parameters and forecasting approaches. However, this research will examine the impact of various predictors such as internal and external of both yields. The outcomes of the study will help policymakers in developing strategies for stakeholders. The current work will improve pearl millet yield literature.

This paper aims to find the minimum possible number of phasor measurement units (PMUs) to achieve maximum and complete observability of the power system and improve the redundancy of measurements, in normal cases (with and without zero injection bus [ZIB]), and then in conditions of a single PMU failure and outage of a single line.

An efficient approach operates adequately and provides the optimal solutions for the PMUs placement problem. The finest function of optimal PMUs placement (OPP) should be mathematically devised as a problem, and via that, the aim of the OPP problem is to identify the buses of the power system to place the PMU devices to ensure full observability of the system. In this paper, the grey wolf optimizer (GWO) is used for training multi-layer perceptrons (MLPs), which is known as Grey Wolf Optimizer (GWO) based Neural Network (“GW-NN”) to place the PMUs in power grids optimally.

Following extensive simulation tests with MATLAB/Simulink, the results obtained for the placement of PMUs provide system measurements with less or at most the same number of PMUs, but with a greater degree of observability than other approaches.

The efficiency of the suggested method is tested on the IEEE 14-bus, 24-bus, New England 39-bus and Algerian 114-bus systems.

This paper proposes a new method for placing PMUs in the power grids as a multi-objective to reduce the cost and improve the observability of these grids in normal and faulty cases.

The increasing complexity of industrial systems is at the heart of the development of many fault diagnosis methods. The artificial neural networks (ANNs), which are part of these methods, are widely used in fault diagnosis due to their flexibility and diversification which makes them one of the most appropriate fault diagnosis methods. The purpose of this paper is to detect and locate in real time any parameter deviations that can affect the operation of the blowout preventer (BOP) system using ANNs.

The starting data are extracted from the tables of the HAZOP (HAZard and OPerability) method where the deviations of the parameters of normal BOP operating (pressure, flow, level and temperature) are associated with an initial rule base for establishing cause and effect of relationships between the causes of deviations and their consequences; these data are used as a database for the neural network. Three ANNs were used, the multi-layer perceptron network (MLPN), radial basis functions network (RBFN) and generalized regression neural networks (GRNN). These models were trained and tested, then, their comparative performances were presented. The respective performances of these models are highlighted following their application to the BOP system.

The performances of the models are evaluated using determination coefficient (R2), root mean square error (RMSE) and mean absolute error (MAE) statistics and time execution. The results of this study show that the RMSE, MAE and R2 values of the GRNN model are better than those corresponding to the RBFN and MLPN models. The GRNN model can be applied with better performance, to establish a diagnostic model that can detect and to identify the different causes of deviations in the parameters of the BOP system.

The performance of the trained network is found to be satisfactory for the real-time fault diagnosis. Therefore, future studies on modeling the BOP system with soft computing techniques can be concentrated on the ANNs. Consequently, with the use of these techniques, the performance of the BOP system can be ensured performing only a limited number of monitoring operations, thus saving engineering effort, time and funds.

This paper aims to use different machine learning (ML) algorithms for the prediction of inverse kinematic solutions in parallel manipulators (PMs) to overcome the computational difficulties and approximations involved with the analytical methods. The results obtained from the ML algorithms and the Denavit–Hartenberg (DH) approach are compared with the experimental results to evaluate their performances. The study is performed on a novel 6-degree of freedom (DoF) PM that offers precise motions with a large workspace for the end effector.

The kinematic model for the proposed 3-PPSS PM is obtained using the modified DH approach and its inverse kinematic solutions are determined using the Levenberg–Marquardt algorithm. Various prediction algorithms such as the multiple linear regression, multi-variate polynomial regression, support vector, decision tree, random forest regression and multi-layer perceptron networks are applied to predict the inverse kinematic solutions for the manipulator. The data set required to train the network is generated experimentally by recording the poses of the end effector for different instantaneous positions of the slider using the concept of ArUco markers.

This paper fully demonstrates the possibility to use artificial intelligence for the prediction of inverse kinematic solutions especially for complex geometries.

As the analytical models derived from the geometrical method, Screw theory or numerical techniques involve approximations and needs more computational power, it is not advisable for real-time control of the manipulator. In addition, the data set obtained from the derived inverse kinematic equations to train the network may lead to inaccuracies in the predicted results. This error may generate significant deviations in the end-effector position from the desired position. The present work attempts to resolve this issue by proposing a camera-based approach that uses ArUco library and ML algorithms to create the data set experimentally and predict the inverse kinematic solutions accurately.

The purpose of this study was develop a computer-based cost prediction model for institutional building projects in Nigeria through the use of artificial neural network (ANN) technique. The back-propagation network learns by example and provides good prediction to novel cases.

The input variables were derived from related works with modification and advices from professionals through a field survey. Two hundred and sixty completed project data were used for training and development of the ANN model. Back-propagation algorithm using the gradient descent delta learning rule with a learning coefficient of 0.4 was used. The input layer of the model comprised of nine variables; building height, compactness of building, construction duration, external wall area, gross floor area, number of floors, proportion of opening on external walls, location index and time index.

Several multi-layer perceptron networks were developed with varying architecture from which the network 9-7-5-1 was selected. The performance of the model over the validation sample revealed that the model has a mean absolute per cent error of 5.4 per cent and average error of prediction of −2.5 per cent over the sample. The ANN model was considered to be effective for construction cost prediction.

The model may not be suitable for other building types because of the uniqueness of such facility even though significant difference is not anticipated for buildings such as commercial and residential. The models were evaluated based on the prediction errors; other means of evaluation were not used.

The study thus provides a simple, yet effective means of predicting construction costs of institutional building projects in Nigeria using an ANN model.

This study aims to focus on an adaptive method for fault detection and classification of fault types that trigger in three-phase transmission lines using artificial neural networks (ANNs). The proposed scheme can detect and classify several types of faults, including line-to-ground, line-to-line, double-line-to-ground, triple-line and triple-line-to-ground faults.

The fundamental components of three-phase current and voltage were used as inputs in the ANNs. An analysis of the impact of variations in the fault resistance, fault type and fault inception time was conducted to evaluate the ANNs performance. The survey compares the performance of the multi-layer perceptron neural network (MLPNN) and Elman recurrent neural network trained with the backpropagation learning technique to improve each of the three phases of the fault detection and classification process. A detailed analysis validates the choice of the ANNs architecture based on the variation in the number of hidden neurons in each step.

The mean square error, root mean square error, mean absolute error and linear regression are measured to improve the efficiency of the ANN models for both fault detection and classification. The results indicate that the MLPNN can detect and classify faults with a satisfactory performance.

The smart adaptive scheme is fast and accurate for fault detection and classification in a single circuit transmission line when faced with different conditions and can be useful for transmission line protection schemes.

The power system is complex multi‐component dynamic system with many operational levels made up of a wide range of energy sources with many interaction points. Low frequency oscillations are observed when large power systems are interconnected by relatively weak tie lines. These oscillations may sustain and grow to cause system separation if no adequate damping is available. The present paper aims to propose an on‐line self‐learning PID (OLSL‐PID) controller in order to damp the low frequency power system oscillations in a single‐machine system.

The proposed OLSL‐PID is used as a controller in order to damp the low frequency power system oscillations. It has a local nature because of its powerful adaption process based on back‐propagation (BP) algorithm that is implemented through an adaptive self‐recurrent wavelet neural network identifier (ASRWNNI). In fact PID controller parameters are updated in on‐line mode, using BP algorithm based on the information provided by the ASRWNNI which is a powerful fast‐acting identifier because of its local nature, self‐recurrent structure and stable training algorithm with ALRs based on discrete lyapunov stability theorem.

The proposed control scheme is applied to a single machine infinite bus power system under different operating conditions and disturbances. The nonlinear time‐domain simulation results are promising and show the effectiveness and robustness of the proposed controller and also reveal that: because of the high adaptability, the local behavior and high flexibility of the OLSL‐PID controller, it can be damp the low frequency oscillations in the best possible manner and significantly improves the stability performance of the system.

The proposed controller adaption process is done in each sampling period using a powerful adaption law based on BP algorithm. Also during the process the system sensitivity is provided by a powerful fast‐acting identifier. As an alternative to multi‐layer perceptron neural network, self‐recurrent wavelet neural networks (SRWNNs) which combine the properties such as attractor dynamics of recurrent neural network and the fast convergence of the wavelet neural network were proposed to identify synchronous generator. Also to help the OLSL‐PID stability first, PID parameters tuning problem under a wide range of operating conditions is converted to an optimization problem which solved by a chaotic optimization algorithm (COA), and afterwards PID controller is hooked up in the system and on‐line tuning is done in each sampling period.