Sürdürülebilir Kalkınma Amaçları
Yazarlar
Yayınlar
- MakaleAçık Erişim2022Finite-Time Neuro-Sliding-Mode Controller Design for Quadrotor UAVs Carrying Suspended Payload
Bingöl, Özhan; Güzey, Hacı Mehmet
Due to the quadrotor’s underactuated nature, suspended payload dynamics, parametric uncertainties, and external disturbances, designing a controller for tracking the desired trajectories for a quadrotor that carries a suspended payload is a challenging task. Furthermore, one of the most significant disadvantages of designing a controller for nonlinear systems is the infinite-time convergence to the desired trajectory. In this paper, a finite-time neuro-sliding mode controller (FTNSMC) for a quadrotor with a suspended payload that is subject to parametric uncertainties and external disturbances is designed. By constructing a finite-time sliding mode controller, the quadrotor can follow the reference trajectories in finite time. Furthermore, despite time-varying nonlinear dynamics, parametric uncertainties, and external disturbances, a neural network structure is added to the controller to effectively reduce chattering phenomena caused by high switching gains, and significantly reduce the size of the control signals. Following the completion of the controller design, the system’s stability is demonstrated using the Lyapunov stability criterion. Extensive numerical simulations with various scenarios are run to demonstrate the effectiveness of the proposed controller.
- MakaleYalnız künye2021Neuro sliding mode control of quadrotor UAVs carrying suspended payload
Bingöl, Ö.; Güzey, H.M.
In this paper, a neuro-sliding mode controller (SMC) has been designed for a quadrotor transporting a suspended payload. SMCs are very efficient under uncertain conditions. However, if the uncertain dynamics change over time, SMC gains need to be updated to maintain the tracking performance. This study proposes a neuro-SMC to control a quadrotor UAV carrying a suspended payload in the existence of time-varying uncertain dynamics. Once the accuracy of the proposed controller is demonstrated theoretically using the Lyapunov stability criterion, the effectiveness of the proposed controller is shown in simulation, which confirms the theoretical claims.
- MakaleYalnız künye2021Analysis of Mining Lost Time Incident Duration Influencing Factors Through Machine Learning
Kahraman, Muhammet Mustafa
Despite technological advancements and organizational adjustments, lost time accidents are major issues in occupational safety. However, there is very limited work that focuses on variables influencing days lost as a result of occupational accidents. In this study, decision tree and artificial neural network methods were used as machine learning techniques to investigate the impact of factors on accident lost day duration. Degree of injury, worker age, and worker activity were found to be the top three variables impacting loss of time from work. It was also identified that the mining method, location, and nature of injury had a moderate influence on duration lost due to occupational accidents. However, worker experience and ore type did not have any significant impact on the duration, which is an unexpected result. These results confirmed that some accident factors that might have a large influence on the number of mine accidents can be less critical when it comes to accident lost day duration.
- MakaleYayıncıda açık erişim2016Modeling deformation modulus of a stratified sedimentary rock mass using neural network, fuzzy inference and genetic programming
Alemdag, S.; Gurocak, Z.; Cevik, A.; Cabalar, A.F.; Gokceoglu, C.
This paper investigates a series of experimental results and numerical simulations employed to estimate the deformation modulus of a stratified rock mass. The deformation modulus of rock mass has a significant importance for some applications in engineering geology and geotechnical projects including foundation, slope, and tunnel designs. Deformation modulus of a rock mass can be determined using large scale in-situ tests. This large scale sophisticated in-situ testing equipments are sometimes difficult to install, plus time consuming to be employed in the field. Therefore, this study aims to estimate indirectly the deformation modulus values via empirical methods such as the neural network, neuro fuzzy and genetic programming approaches. A series of analyses have been developed for correlating various relationships between the deformation modulus of rock mass, rock mass rating, rock quality designation, uniaxial compressive strength, and elasticity modulus of intact rock parameters. The performance capacities of proposed models are assessed and found as quite satisfactory. At the completion of a comparative study on the accuracy of models, in the results, it is seen that overall genetic programming models yielded more precise results than neural network and neuro fuzzy models.
- MakaleYalnız künye2013Prediction of offshore bar-shape parameters resulted by cross-shore sediment transport using neural network
Kömü rcü, Murat Ihsan; Kömür, Mehmet Aydin; Akpinar, Adem; Özölçer, Ismail Hakki; Yüksek, Ömer
In order to understand the features of coastal zone and to utilize the coastal areas, it is necessary to determine the sediment movement and the resulting transport. Waves, topographic features, and material properties are known as the most important factors affecting the sediment movement and coastal profiles. In this study, by taking into consideration of wave height and period (H0, T), bed slope (m) and sediment diameter (d50), cross-shore sediment movement was studied in a physical model and various bar-shape parameters of the resultant erosion type profile were determined. Using 80 experimental data which are obtained from physical model studies, a neural network (NN) has been calibrated to predict bar-shape parameters of beach profiles. A sensitivity analysis was firstly carried out to decide data of training and test sets. Four different models, in which the rates of their training and testing set data were 80% and 20%, 70% and 30%, 60% and 40%, 50% and 50% were constituted and their performances were compared. It was determined that the model, in which the rate of its training and testing set data was 80% and 20%, respectively, has the best results. Therefore, a total of 64 experimental data were used as training set and the remainders of the experimental data were used as a testing set for the model. The performance of the NN model was compared with the regression equations developed in a previous study and the equations cited in literature indicating better performance over the equations.