Search

Featured Application: The proposed method can be utilized to determine whether an aircraft encountered turbulence during or after flight, rather than relying on EDR estimation to ascertain turbulence encounters. By integrating swarm intelligence and machine learning and adopting a data-driven approach to turbulence identification, the method addresses previous challenges encountered in turbulence identification, thereby enhancing the efficacy of aviation safety. This approach demonstrates a certain degree of applicability in improving aviation safety. Turbulence is a significant operational aviation safety hazard during all phases of flight. There is an urgent need for a method of airline turbulence identification in aviation systems to avoid turbulence hazards to aircraft during flight. Integrating flight data and machine learning significantly enhances the efficacy of turbulence identification. Nevertheless, present studies encounter issues including unstable model performance, challenges in data feature extraction, and parameter optimization. Hence, it is imperative to propose a superior approach to enhance the accuracy of turbulence identification along airline. The paper presents a combined swarm intelligence and machine learning model based on data mining for identifying airline turbulence. Based on the theory of swarm-intelligence-based optimization algorithm, the optimal parameters of Categorical Boosting (CatBoost) are obtained by introducing the whale optimization algorithm (WOA), and the corresponding WOA-CatBoost fusion model is established. Then, the Recursive Feature Elimination algorithm (RFE) is used to eliminate the data with lower feature weights, extract the effective features of the data, and the combination with the WOA brings robust optimization effects, whereby the accuracy of CatBoost increased by 11%. The WOA-CatBoost model can perform accurate turbulence identification from QAR data, comparable to that with established EDR approaches and outperforms traditional machine learning models. This discovery highlights the effectiveness of combining swarm intelligence and machine learning algorithms in turbulence monitoring systems to improve aviation safety. [ABSTRACT FROM AUTHOR]

Traditional methods often ignore the direct influences of vehicle vibration on the flywheel battery system, which leads to an inaccurate analysis of the dynamic performance of the flywheel battery system and its control effect. Therefore, to make up for the deficiencies of existing studies, a more accurate dynamic performance analysis method and efficient control parameter adjustment algorithm for flywheel batteries based on automotive direct action are proposed in this study. First, the influence of road conditions and vehicle driving conditions on the stability of a vehicle is analyzed primarily. Then, the vibration signal generated by the vehicle is transmitted to the vehicle's magnetic flywheel battery system for analysis, and the accuracy of the analysis process is realized. Then, according to the stability analysis results for the direct action of the vehicle and the actual PID controller, the control parameter adjustment algorithm is summarized using the curve-fitting method. Finally, a performance test is carried out on the mobile experimental platform. Good experimental results show that the flywheel can quickly return to its equilibrium position and effectively reduce the influence of interference from road conditions and different working conditions and improve the robustness. Therefore, the correctness of the theoretical analysis and parameter adjustment method proposed in this paper was effectively verified. [ABSTRACT FROM AUTHOR]

This paper investigates the problem of fault tolerant control (FTC) for autonomous underwater vehicles (AUVs) with multiple thrusters in the presence of current disturbances, thruster faults, and modelling uncertainty. This paper focuses on the problems of reducing the energy consumption caused by the chattering of control signals and improving the tracking accuracy of an AUV operating in deep-sea environments. In view of the problem of large energy consumption in some other methods, a fault tolerant control method for multiple-thruster AUVs based on a finite-time extended state observer (FTESO) is proposed. More specifically, a FTESO based on an integral sliding mode surface is designed to estimate the generalized uncertainty compounded using current disturbances, thruster faults, and modelling uncertainty. The fast finite-time uniformly ultimately bounded stability of the proposed FTESO is analyzed. Then, based on the estimated value of FTESO, an FTC method based on non-singular fast terminal sliding mode surfaces is developed for AUVs. The finite-time convergence of the closed-loop control system is proved theoretically. In this design, two different sliding mode surfaces are used to design FTESO and FTC, in order to avoid the appearance of singularities. Moreover, a parameter adjustment method is designed to improve tracking accuracy. Finally, comparative numerical simulations show that the proposed control scheme is effective at reducing energy consumption and improving tracking accuracy. [ABSTRACT FROM AUTHOR]

In order to solve the tracking accuracy problem of the redundant manipulator, a PI control method with Henry gas solubility optimization parameter regulator (PI-HGSO) is proposed in this paper. This method consists of the controller and the parameter regulator. The characteristic is that the position deviation of a manipulator is equivalent to a specific function; namely, the proportional-integral (PI) controller is used to adjust the deviation input. The error can be better corrected by the processing of the PI controller so that the inverse kinematics solution of the minimum error can be realized. At the same time, the parameter selection of PI controllers has always been a difficulty in controller design. To address the problem, Henry gas solubility optimization (HGSO) is selected as a parameter regulator to optimize the parameters and obtain the optimal controller, thereby achieving high-precision trajectory tracking. Experiments on 9-DOF redundant manipulator show that our method achieves competitive tracking accuracy in contrast with others. Meanwhile, the efficiency and accuracy of the PI controller are greatly guaranteed by using HGSO to automatically optimize controller parameters instead of making approximate adjustments through infinite manual trial and error. Therefore, the feasibility and competitive superiority of PI-HGSO is fully proved in trajectory planning of redundant manipulators. [ABSTRACT FROM AUTHOR]

Fast iterative soft threshold algorithm (FISTA) is one of the algorithms for the reconstruction part of compressed sensing (CS). However, FISTA cannot meet the increasing demands for accuracy and efficiency in the signal reconstruction. Thus, an improved algorithm (FIPITA, fast iterative parametric improved threshold algorithm) based on mended threshold function, restart adjustment mechanism and parameter adjustment is proposed. The three parameters used to generate the gradient in the FISTA are carefully selected by assessing the impact of them on the performance of the algorithm. The developed threshold function is used to replace the soft threshold function to reduce the reconstruction error and a restart mechanism is added at the end of each iteration to speed up the algorithm. The simulation experiment is carried out on one-dimensional signal and the FISTA, RadaFISTA and RestartFISTA are used as the comparison objects, with the result that in one case, for example, the residual rate of FIPITA is about 6.35% lower than those three and the number of iterations required to achieve the minimum error is also about 102 less than that of FISTA. [ABSTRACT FROM AUTHOR]

In this work, aiming at the problem of cooperative task assignment for multiple unmanned aerial vehicles (UAVs) in actual combat, battlefield tasks are divided into reconnaissance tasks, strike tasks and evaluation tasks, and a cooperative task-assignment model for multiple UAVs is built. Meanwhile, heterogeneous UAV-load constraints and mission-cost constraints are introduced, the UAVs and their constraints are analyzed and the mathematical model is established. The exploration performance and convergence performance of the harmony search algorithm are analyzed theoretically, and the more general formulas of exploration performance and convergence performance are proved. Based on theoretical analysis, an algorithm called opposition-based learning parameter-adjusting harmony search is proposed. Using the algorithm to test the functions of different properties, the value range of key control parameters of the algorithm is given. Finally, four algorithms are used to simulate and solve the assignment problem, which verifies the effectiveness of the task-assignment model and the excellence of the designed algorithm. Simulation results show that while ensuring proper assignment, the proposed algorithm is very effective for the multi-objective optimization of heterogeneous UAV-cooperation mission planning with multiple constraints. [ABSTRACT FROM AUTHOR]

How well parameterization will improve gross primary production (GPP) estimation using the MODerate-resolution Imaging Spectroradiometer (MODIS) algorithm has been rarely investigated. We adjusted the parameters in the algorithm for 21 selected eddy-covariance flux towers which represented nine typical plant functional types (PFTs). We then compared these estimates of the MOD17A2 product, by the MODIS algorithm with default parameters in the Biome Property Look-Up Table, and by a two-leaf Farquhar model. The results indicate that optimizing the maximum light use efficiency (εmax) in the algorithm would improve GPP estimation, especially for deciduous vegetation, though it could not compensate the underestimation during summer caused by the one-leaf upscaling strategy. Adding the soil water factor to the algorithm would not significantly affect performance, but it could make the adjusted εmax more robust for sites with the same PFT and among different PFTs. Even with adjusted parameters, both one-leaf and two-leaf models would not capture seasonally photosynthetic dynamics, thereby we suggest that further improvement in GPP estimaiton is required by taking into consideration seasonal variations of the key parameters and variables. [ABSTRACT FROM AUTHOR]

Reinforcement learning, as a branch of machine learning, has been gradually applied in the control field. However, in the practical application of the algorithm, the hyperparametric approach to network settings for deep reinforcement learning still follows the empirical attempts of traditional machine learning (supervised learning and unsupervised learning). This method ignores part of the information generated by agents exploring the environment contained in the updating of the reinforcement learning value function, which will affect the performance of the convergence and cumulative return of reinforcement learning. The reinforcement learning algorithm based on dynamic parameter adjustment is a new method for setting learning rate parameters of deep reinforcement learning. Based on the traditional method of setting parameters for reinforcement learning, this method analyzes the advantages of different learning rates at different stages of reinforcement learning and dynamically adjusts the learning rates in combination with the temporal-difference (TD) error values to achieve the advantages of different learning rates in different stages to improve the rationality of the algorithm in practical application. At the same time, by combining the Robbins–Monro approximation algorithm and deep reinforcement learning algorithm, it is proved that the algorithm of dynamic regulation learning rate can theoretically meet the convergence requirements of the intelligent control algorithm. In the experiment, the effect of this method is analyzed through the continuous control scenario in the standard experimental environment of "Car-on-The-Hill" of reinforcement learning, and it is verified that the new method can achieve better results than the traditional reinforcement learning in practical application. According to the model characteristics of the deep reinforcement learning, a more suitable setting method for the learning rate of the deep reinforcement learning network proposed. At the same time, the feasibility of the method has been proved both in theory and in the application. Therefore, the method of setting the learning rate parameter is worthy of further development and research. [ABSTRACT FROM AUTHOR]