Search results

Determining the performance parameters of the propulsion systems of the aircraft, which is the key product of the aviation industry, plays a critical role in reducing adverse environmental impacts. Therefore, the purpose of this paper is to present a temperature performance template for turbojet engines at the design stage using a neural network model that defines the relationship between the performance parameters obtained from ground tests of a turbojet engine used in unmanned aerial vehicles (UAV).

The main parameters of the flow passing through the engine of the UAV propulsion system, where ground tests were performed, were obtained through the data acquisition system and injected into a neural network model created. Fifteen sensors were mounted on the engine – six temperature sensors, six pressure sensors, two flow meters and one load cell were connected to the data acquisition system to make sense of this physical environment. Subsequently, the artificial neural network (ANN) model as a complement to the approach was used. Thus, the predicted model relationship with the experimental data was created.

Fuel flow and thrust parameters were estimated using these components as inputs in the feed-forward neural network. In the network experiments to estimate fuel flow parameter, r-square and mean absolute error were calculated as 0.994 and 0.02, respectively. Similarly, for thrust parameter, these metrics were calculated as 0.994 and 1.42, respectively. In addition, the correlation between fuel flow, thrust parameters and each input parameters was examined. According to this, air compressor inlet (AC_inlet,temp) and outlet (AC_outlet,temp) temperatures and combustion chamber (CC_inlet,temp, CC_outlet,temp) temperature parameters were determined to affect the output the most. The proposed ANN model is applicable to any turbojet engines to model its behavior.

Today, deep neural networks are the driving force of artificial intelligence studies. In this study, the behavior of a UAV is modeled with neural networks. Neural networks are used here as a regressor. A neural network model has been developed that predicts fuel flow and thrust parameters using the real parameters of a UAV turbojet engine. As a result, satisfactory findings were obtained. In this regard, fuel flow and thrust values of any turbojet engine can be estimated using the neural network hyperparameters proposed in this study. Python codes of the study can be accessed from https://github.com/tekinonlayn/turbojet.

The originality of the study is that it reports the relationships between turbojet engine performance parameters obtained from ground tests using the neural network application with open source Python code. Thus, small-scale unmanned aerial propulsion system provides designers with a template showing the relationship between engine performance parameters.

The selection criteria for contractor pre‐qualification are characterized by the co‐existence of both quantitative and qualitative data. The qualitative data is non‐linear, uncertain and imprecise. An ideal decision support system for contractor pre‐qualification should have the ability of handling both quantitative and qualitative data, and of mapping the complicated non‐linear relationship of the selection criteria, such that rational and consistent decisions can be made. In this research paper, an artificial neural network model was developed to assist public clients identifying suitable contractors for tendering. The pre‐qualification criteria (variables) were identified for the model. One hundred and twelve real pre‐qualification cases were collected from civil engineering projects in Hong Kong, and 88 hypothetical pre‐qualification cases were also generated according to the ‘If‐then’ rules used by professionals in the pre‐qualification process. The results of the analysis totally comply with current practice (public developers in Hong Kong). Each pre‐qualification case consisted of input ratings for candidate contractors' attributes and their corresponding pre‐qualification decisions. The training of the neural network model was accomplished by using the developed program, in which a conjugate gradient descent algorithm was incorporated for improving the learning performance of the network. Cross‐validation was applied to estimate the generalization errors based on the ‘re‐sampling’ of training pairs. The case studies show that the artificial neural network model is suitable for mapping the complicated non‐linear relationship between contractors' attributes and their corresponding pre‐qualification (disqualification) decisions. The artificial neural network model can be concluded as an ideal alternative for performing the contractor pre‐qualification task.

The purpose of this paper is to optimize the simultaneous flight performance of a hexarotor unmanned aerial vehicle (UAV) by using simultaneous perturbation stochastic approximation (i.e. SPSA), deep neural network and proportional integral derivative (i.e. PID) according to varying arm length (i.e. morphing).

In this paper, proper PID gain coefficients and morphing ratio were obtained using the stochastic optimization method, also known as SPSA to maximize flight efficiency. Because it is difficult to establish an analytical connection between the morphing ratio and hexarotor moments of inertia, the deep neural network was used to obtain the moments of inertia according to the morphing ratio. By using SPSA and deep neural network, the best performance indexes were obtained and both longitudinal and lateral flight simulations were performed with the obtained data.

With SPSA, the best PID coefficients and morphing ratio are obtained for both longitudinal and lateral flight. Because the hexarotor solid body model changes according to the morphing ratio, the moment of inertia values used in the simulations also change. According to the morphing ratio, the moment of inertia values was obtained with the deep neural network over a created data set.

It takes a long time to obtain the morphing ratio suitable for the hexarotor model and the PID gain coefficients suitable for this morphing ratio. However, this situation can be overcome with the proposed SPSA. In addition, it takes a long time to obtain the appropriate moments of inertia according to the morphing ratio. However, in this case, it was overcome using the deep neural network.

Determining the morphing ratio and PID gain coefficients using the optimization method, as well as determining the moments of inertia using the deep neural network, is very useful as it can increase the efficiency of hexarotor flight and flight efficiently with different arm lengths. With the proposed method, the hexarotor design performance criteria (i.e. rise time, settling time and overshoot) values were significantly improved compared to similar studies.

Determining the hexarotor flight parameters using SPSA and deep neural network provides advantages in terms of time, cost and applicability.

The hexarotor flight efficiency is improved with the proposed SPSA and deep neural network approaches. In addition, the desired flight parameters can be obtained more quickly and reliably with the proposed approaches. The design performance criteria were also improved, enabling the hexarotor UAV to follow the given trajectory in the best way and providing convenience for end users. SPSA was preferred because it converged faster than other methods. While other methods perform 2n operations per iteration, SPSA only performs two operations. To obtain the moment of inertia, many physical parameter values of the UAV are required in the existing methods. In the proposed method, by creating a date set, only arm length and moment of inertia were estimated without the need to obtain physical parameters with the deep neural network structure.

In order to accomplish real‐time alignment of Shipborne strapdown inertial navigation system (SINS) on moving bases, a novel solution method of utilizing neural networks for rapid transfer alignment of Shipborne SINS was investigated.

The system error state equations and measurement equations of the Shipborne transfer alignment were established. Based on the nonlinear and time‐variant SINS model on moving bases, a neural network learning algorithm based on Kalman filtering was presented, and the methods of constructing and training of neural networks input‐output sample pairs suitable for Shipborne SINS were proposed.

Velocity and attitude errors between the master and slave inertial navigation system (INS) are chosen as network's inputs, and the information of sample pairs is affluent, which can advance the stability and generalization of the neural networks. The neural networks algorithms based on Kalman filtering not only have the self‐learning ability, but also remain recursive optimal estimation capability of Kalman filtering. Through the introducing of the local level trajectory frame, the trained neural networks can be independent on a ship heading, and only dependent on the relative position errors between master with slave INS and the inertial sensor errors.

This article presents an innovative solution method of utilizing neural networks for rapid transfer alignment of Shipborne SINS.

Cost estimation is an important decision‐making process where many factors are interrelated in a complex manner, thus making it difficult to analyse and model using conventional mathematical methods. Artificial neural networks (ANNs) offer an alternative approach to modelling cost estimation. ANNs are simple mathematical models that self‐organize information from training data. This paper explores the use of ANNs in cost estimation. Research issues investigated are twofold. First, this paper compares the performance of ANNs to a regression‐based method which leads to a better understanding of the applicability of ANNs. Second, this paper identifies the effect of different configurations of neural networks on estimating accuracy. Experimental results demonstrate the many advantages and disadvantages of using neural networks in modelling cost estimation.

Viscosity is an important basic physical property of liquid solders. However, because of the very complex nonlinear relationship between the viscosity of the liquid ternary Sn-based lead-free solder and its determinants, a theoretical model for the viscosity of the liquid Sn-based solder alloy has not been proposed. This paper aims to address the viscosity issues that must be considered when developing new lead-free solders.

A BP neural network model was established to predict the viscosity of the liquid alloy and the predicted values were compared with the corresponding experimental data in the literature data. At the same time, the BP neural network model is compared with the existing theoretical model. In addition, a mathematical model for estimating the melt viscosity of ternary tin-based lead-free solders was constructed using a polynomial fitting method.

A reasonable BP neural network model was established to predict the melt viscosity of ternary tin-based lead-free solders. The viscosity prediction of the BP neural network agrees well with the experimental results. Compared to the Seetharaman and the Moelwyn–Hughes models, the BP neural network model can predict the viscosity of liquid alloys without the need to calculate the relevant thermodynamic parameters. In addition, a simple equation for estimating the melt viscosity of a ternary tin-based lead-free solder has been proposed.

The study identified nine factors that affect the melt viscosity of ternary tin-based lead-free solders and used these factors as input parameters for BP neural network models. The BP neural network model is more convenient because it does not require the calculation of relevant thermodynamic parameters. In addition, a mathematical model for estimating the viscosity of a ternary Sn-based lead-free solder alloy has been proposed. The overall research shows that the BP neural network model can be well applied to the theoretical study of the viscosity of liquid solder alloys. Using a constructed BP neural network to predict the viscosity of a lead-free solder melt helps to study the liquid physical properties of lead-free solders that are widely used in electronic information.

Modelling of the multiproject cash flow decisions in a contracting firm facilitates optimal resource utilization, financial planning, profit forecasting and enables the inclusion of cash‐flow liquidity in forecasting. However, a great challenge for contracting firm to manage his multiproject cash flow when large and multiple construction projects are involved (manipulate large amount of resources, e.g. labour, plant, material, cost, etc.). In such cases, the complexity of the problem, hence the constraints involved, renders most existing regular optimization techniques computationally intractable within reasonable time frames. This limit inhibits the ability of contracting firms to complete construction projects at maximum efficiency through efficient utilization of resources among projects. Recently, artificial neural networks have demonstrated its strength in solving many optimization problems efficiently. In this regard a novel recurrent‐neural‐network model that integrates multi‐objective linear programming and neural network (MOLPNN) techniques has been developed. The model was applied to a relatively large contracting company running 10 projects concurrently in Hong Kong. The case study verified the feasibility and applicability of the MOLPNN to the defined problem. A comparison undertaken of two optimal schedules (i.e. risk‐avoiding scheme A and risk‐seeking scheme B) of cash flow based on the decision maker's preference is described in this paper.

In recent years, neural networks have become popular in the scientific and business fields. In the hotel industry, researchers have recently devoted attention to the application of neural networks to the classification of tourist segments and the prediction of visitor behaviour. However, no previous attempt has been made to incorporate neural networks into hotel occupancy rate forecasting. This paper reports on a study about applying neural networks to the forecasting of room occupancy rates. The significance of this approach was tested with actual data from the Hong Kong hotel industry. Estimated room occupancy rates were compared with actual room occupancy rates. Experimental results indicate that using neural networks to forecast room occupancy rates outperforms multiple regression and naïve extrapolation, two commonly used forecasting approaches.

The purpose of this paper is to examine the feasibility of committee neural network (CNN) theory for the improvement of accuracy and consistency of the neural network model on the estimation of preconsolidation pressure from the field piezocone measurements.

In this study, CNN theory is introduced to improve the initial weight dependency of the neural network model on the prediction of preconsolidation pressure of soft clay from a piezocone test result. It was found that the proposed CNN model can improve the initial weight dependency of the NN model and provide a more consistent and precise inference result than existing NN models, as well as empirical and theoretical models.

It was found that the CNN overcomes the initial weight dependency of the single neural network model. Various committees of the single multilayer perceptrons (MLPs) were tested. It was found that if eight single MLPs, which have the same structure but have been trained with a different initial weight and bias, are accumulated in the committee with the same weighting factor, any variation on the prediction of the preconsolidation pressure from the piezocone test result can be simply and successfully eliminated.

In recent years, ANN has been found to be a powerful theory for analyzing complex relationships involving a multitude of variables, on many geotechnical applications. However, single MLP, when repeatedly trained on the same patterns, tends to reach different minima of the objective function each time and hence give a different set of neuron weights, because the solution is not unique for noisy data, as in most geotechnical problems. The authors observed that a committee neural network system is able to provide improved performance compared with a single optimal neural network.

Artificial Neural Networks (ANNs) have many potential applications virtually in wide areas ranging from engineering to management. Recently, a great deal of interest (and effort) has been directed towards using ANNs in business practice. In particular, they have been used in areas which were once reserved for multivariate statistical analysis. Owing to this they are often considered to be statistical methods. Marketing researchers and managers who are not aware of the conceptual differences between these two methods cannot use this new “cutting‐edge” technology effectively. Discusses the conceptual differences and similarities between the two methods, having in mind market researchers and managers who are looking for new tools to support their decision making.