Search results

This paper aims to represent an improved whale optimization algorithm (WOA) based on a Lévy flight trajectory and called the LWOA algorithm to solve engineering optimization problems. The LWOA makes the WOA faster, more robust and significantly enhances the WOA. In the LWOA, the Lévy flight trajectory enhances the capability of jumping out of the local optima and is helpful for smoothly balancing exploration and exploitation of the WOA. It has been successfully applied to five standard engineering optimization problems. The simulation results of the classical engineering design problems and real application exhibit the superiority of the LWOA algorithm in solving challenging problems with constrained and unknown search spaces when compared to the basic WOA algorithm or other available solutions.

In this paper, an improved WOA based on a Lévy flight trajectory and called the LWOA algorithm is represented to solve engineering optimization problems.

It has been successfully applied to five standard engineering optimization problems. The simulation results of the classical engineering design problems and real application exhibit the superiority of the LWOA algorithm in solving challenging problems with constrained and unknown search spaces when compared to the basic WOA algorithm or other available solutions.

An improved WOA based on a Lévy flight trajectory and called the LWOA algorithm is first proposed.

Sparrow search algorithm (SSA) is a novel global optimization method, but it is easy to fall into local optimization, which leads to its poor search accuracy and stability. The purpose of this study is to propose an improved SSA algorithm, called levy flight and opposition-based learning (LOSSA), based on LOSSA strategy. The LOSSA shows better search accuracy, faster convergence speed and stronger stability.

To further enhance the optimization performance of the algorithm, The Levy flight operation is introduced into the producers search process of the original SSA to enhance the ability of the algorithm to jump out of the local optimum. The opposition-based learning strategy generates better solutions for SSA, which is beneficial to accelerate the convergence speed of the algorithm. On the one hand, the performance of the LOSSA is evaluated by a set of numerical experiments based on classical benchmark functions. On the other hand, the hyper-parameter optimization problem of the Support Vector Machine (SVM) is also used to test the ability of LOSSA to solve practical problems.

First of all, the effectiveness of the two improved methods is verified by Wilcoxon signed rank test. Second, the statistical results of the numerical experiment show the significant improvement of the LOSSA compared with the original algorithm and other natural heuristic algorithms. Finally, the feasibility and effectiveness of the LOSSA in solving the hyper-parameter optimization problem of machine learning algorithms are demonstrated.

An improved SSA based on LOSSA is proposed in this paper. The experimental results show that the overall performance of the LOSSA is satisfactory. Compared with the SSA and other natural heuristic algorithms, the LOSSA shows better search accuracy, faster convergence speed and stronger stability. Moreover, the LOSSA also showed great optimization performance in the hyper-parameter optimization of the SVM model.

The first order reliability method requires optimization algorithms to find the minimum distance from the origin to the limit state surface in the normal space. The purpose of this paper is to develop an improved version of the new metaheuristic algorithm inspired from echolocation behaviour of bats, namely, the bat algorithm (BA) dedicated to perform structural reliability analysis.

Modifications have been embedded to the standard BA to enhance its efficiency, robustness and reliability. In addition, a new adaptive penalty equation dedicated to solve the problem of the determination of the reliability index and a proposition on the limit state formulation are presented.

The comparisons between the improved bat algorithm (iBA) presented in this paper and other standard algorithms on benchmark functions show that the iBA is highly efficient, and the application to structural reliability problems such as the reliability analysis of overhead crane girder proves that results obtained with iBA are highly reliable.

A new iBA and an adaptive penalty equation for handling equality constraint are developed to determine the reliability index. In addition, the low computing time and the ease implementation of this method present great advantages from the engineering viewpoint.

The purpose of this paper is three-fold: to review the categories explaining mainly optimization algorithms (techniques) in that needed to improve the generalization performance and learning speed of the Feedforward Neural Network (FNN); to discover the change in research trends by analyzing all six categories (i.e. gradient learning algorithms for network training, gradient free learning algorithms, optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) collectively; and recommend new research directions for researchers and facilitate users to understand algorithms real-world applications in solving complex management, engineering and health sciences problems.

The FNN has gained much attention from researchers to make a more informed decision in the last few decades. The literature survey is focused on the learning algorithms and the optimization techniques proposed in the last three decades. This paper (Part II) is an extension of Part I. For the sake of simplicity, the paper entitled “Machine learning facilitated business intelligence (Part I): Neural networks learning algorithms and applications” is referred to as Part I. To make the study consistent with Part I, the approach and survey methodology in this paper are kept similar to those in Part I.

Combining the work performed in Part I, the authors studied a total of 80 articles through popular keywords searching. The FNN learning algorithms and optimization techniques identified in the selected literature are classified into six categories based on their problem identification, mathematical model, technical reasoning and proposed solution. Previously, in Part I, the two categories focusing on the learning algorithms (i.e. gradient learning algorithms for network training, gradient free learning algorithms) are reviewed with their real-world applications in management, engineering, and health sciences. Therefore, in the current paper, Part II, the remaining four categories, exploring optimization techniques (i.e. optimization algorithms for learning rate, bias and variance (underfitting and overfitting) minimization algorithms, constructive topology neural networks, metaheuristic search algorithms) are studied in detail. The algorithm explanation is made enriched by discussing their technical merits, limitations, and applications in their respective categories. Finally, the authors recommend future new research directions which can contribute to strengthening the literature.

The FNN contributions are rapidly increasing because of its ability to make reliably informed decisions. Like learning algorithms, reviewed in Part I, the focus is to enrich the comprehensive study by reviewing remaining categories focusing on the optimization techniques. However, future efforts may be needed to incorporate other algorithms into identified six categories or suggest new category to continuously monitor the shift in the research trends.

The authors studied the shift in research trend for three decades by collectively analyzing the learning algorithms and optimization techniques with their applications. This may help researchers to identify future research gaps to improve the generalization performance and learning speed, and user to understand the applications areas of the FNN. For instance, research contribution in FNN in the last three decades has changed from complex gradient-based algorithms to gradient free algorithms, trial and error hidden units fixed topology approach to cascade topology, hyperparameters initial guess to analytically calculation and converging algorithms at a global minimum rather than the local minimum.

The existing literature surveys include comparative study of the algorithms, identifying algorithms application areas and focusing on specific techniques in that it may not be able to identify algorithms categories, a shift in research trends over time, application area frequently analyzed, common research gaps and collective future directions. Part I and II attempts to overcome the existing literature surveys limitations by classifying articles into six categories covering a wide range of algorithm proposed to improve the FNN generalization performance and convergence rate. The classification of algorithms into six categories helps to analyze the shift in research trend which makes the classification scheme significant and innovative.

In this paper, we present a new hybrid binary version of bat and enhanced particle swarm optimization algorithm in order to solve feature selection problems. The proposed algorithm is called Hybrid Binary Bat Enhanced Particle Swarm Optimization Algorithm (HBBEPSO). In the proposed HBBEPSO algorithm, we combine the bat algorithm with its capacity for echolocation helping explore the feature space and enhanced version of the particle swarm optimization with its ability to converge to the best global solution in the search space. In order to investigate the general performance of the proposed HBBEPSO algorithm, the proposed algorithm is compared with the original optimizers and other optimizers that have been used for feature selection in the past. A set of assessment indicators are used to evaluate and compare the different optimizers over 20 standard data sets obtained from the UCI repository. Results prove the ability of the proposed HBBEPSO algorithm to search the feature space for optimal feature combinations.

The purpose of this paper is to create a new fuel flow rate model using cuckoo search algorithm (CSA) for the descending stage of the flight.

Using the actual flight data record data of the B737-800 aircraft, a new fuel flow rate model has been developed for this aircraft type. The created model is to predict the fuel flow rate with high accuracy depending on the altitude and true airspeed. In addition, the CSA fuel flow rate model was used to calculate the fuel consumption for the point merge system, which is used for combining the initial approach to the final approach at Istanbul Airport, the largest airport of Turkey.

As a result of the analysis, the correlation coefficient value is found as 0.996858 for Flight 1, 0.998548 for Flight 2, 0.995363 and 0.997351 for Flight 3 and Flight 4, respectively. The values that are so close to 1 indicate that the model predicts the real fuel flow rate data with high accuracy.

This model is considered to be useful in air traffic management decision support systems, aircraft performance models, models used for trajectory prediction and strategies used by the aviation community to reduce fuel consumption and related emissions.

The importance of this study lies in the fact that to the best of the authors’ knowledge, it is the first fuel flow rate model developed using CSA for the descent stage in the existing literature; the data set used is real values.

The purpose of this study is to create a new fuel flow rate model adopting cuckoo search algorithm (CSA) for the climbing phase of the flight.

Using the real flight data records (FDRs) of B737-800 passenger aircraft, a new fuel flow rate model for the climbing phase of the flight was developed by incorporating CSA. In the model, fuel flow rate is given as a function of altitude and true airspeed. The aim is to create a model that yields results that are closest to the real fuel flow rate values obtained from flight data records. Various error analysis methods were used to test the accuracy of the obtained values. Finally, the effect of change of some CSA parameters on the model was investigated.

It was observed that the derived model is able to predict real fuel flow rate values with high accuracy. It has been deduced that increasing the number of nest (n) and discovery rate of alien nests (pa) values of CSA parameters to a certain value gradually decreases the model’s accuracy.

This model is considered to be useful in air traffic management decision support systems, simulation applications, aircraft trajectory prediction models and aircraft performance modelling studies because of the high accuracy accomplished by the CSA model.

The originality of this study is the development of a new fuel flow rate model using CSA as a first attempt in the literature. The use of real flight data is important for the originality and reliability of the model.

The purpose of this paper is to explore the effects of the camber on gliding and hovering performance of two-dimensional corrugated airfoils. While the flying mechanism of natural flyers remains a myth up to nowadays, the simulation serves as a minor step toward understanding the steady and unsteady aerodynamics of the dragonfly flight.

The lattice Boltzmann method is used to simulate the flow past the cambered corrugated dragonfly airfoil at low Reynolds numbers. For gliding flight, the maximum camber, the distance of the location of maximum camber point from the leading edge and Reynolds number are regarded as control variables; for hovering flight, the maximum camber, the flapping amplitude and trajectory are considered as control variables. Then corresponding simulations are performed to evaluate the implications of these factors.

Greater gliding ratio can be reached by increasing the maximum camber of the dragonfly wing section. When the location of the maximum camber moves backward along the wing chord, large scale flow separation can be delayed. These two effects result in better gliding performances. For hovering performances, it is found that for different flapping amplitudes along an inclined plane, the horizontal force exerted on the airfoils increases with the camber, and the drag growths first but then drops. It is also found that the elliptic flapping trajectory is most sensitive to the camber of the cambered corrugated dragonfly wing section.

The effects of the camber on gliding and hovering performance of the cambered dragonfly wing section are explored in detail. The data obtained can be helpful when designing micro aerial vehicles.

This paper aims to design a global controller that is operational throughout all flight modes and less dependent on an accurate model.

By adopting the interconnection and damping assignment passivity-based control (IDA-PBC) technology and compensating extra inputs for handling the unknown dynamics and time-varying disturbances, a model-free control (MFC)-based global controller is proposed.

Test results indicate that the designed controllers are more suitable for actual flight as they have smaller position tracking errors and energy consumption in all flight phases than the excellent model-free controller intelligent-PID.

The designed global controller, which works in all flight modes without adjusting its structure and parameters, can realize a stable and accurate tracking control of a tail-sitter and improve the resistance to unknown disturbances and model uncertainties.

The newly-designed controller is considered as an enhanced version of the traditional MFC. It further improves the control effect by using the poorly known dynamics of the system and choosing the IDA-PBC as the control auxiliary input. This method eliminates the unnecessary dynamics to continuously stabilize the vehicle with suitable energy consumption covering its entire flight envelope.

European air transport policy, emerged through the confluence of case law and legislation, in four broad areas: liberalization, safety and security, greening, and the external policy. Following the implementation of the single market for air transport, policy shifted to liberalizing and regulating associated services and in recent years to greening, the external aviation policy, and safety and security. Inclusion of air transport in the Environmental Trading Scheme of the European Union exemplifies the European Commission’s proactive stand on bringing the industry in line with emission reduction trajectories of other industries. However, the bid to include flights to third countries in the trading scheme pushed the EU into a controversial position, causing the Commission to halt implementation and to give ICAO time to seek a global multilateral agreement. The chapter also discusses how the nationality clauses in air services agreements breached the Treaty of Rome, and a court ruling to that effect enabled the EC to extend EU liberalization policies beyond the European Union, resulting in the Common Aviation Area with EU fringe countries and the Open Aviation Area with the USA. Another important area of progress was aviation safety, where the EU region is unsurpassed in the world, yet the Commission has pushed the boundary even further, by establishing the European Safety Agency to oversee the European Aviation Safety Management System. Another important area of regulatory development was aviation security, a major focus after the woeful events in 2001, but increasingly under industry scrutiny on costs and effectiveness. The chapter concludes by arguing that in the coming decade, the EU will strive to strengthen its position as a global countervailing power, symbolized in air transport by a leadership position in environmental policy and international market liberalization, exemplified in the EU’s external aviation policy.