This paper studies the multi-type task allocation problem for sea-air heterogeneous unmanned systems. First, a novel task allocation model is proposed, which integrates multi-type task constraints and simultaneous arr...
详细信息
This paper studies the multi-type task allocation problem for sea-air heterogeneous unmanned systems. First, a novel task allocation model is proposed, which integrates multi-type task constraints and simultaneous arrival constraints. due to the interdependence of task sequences under time constraints and the requirements of diverse types of tasks performed by unmanned vehicles with varying capabilities, the established model exhibits high complexity, large solution space, and limited feasible solutions. This makes the existing optimization methods less efficient in solving the model. Therefore, an experience playback-baseddBO d*algorithm (EPdBO) was proposed, which designs an independent/dependent iterative evolutionary strategy through individual cognitive differences in order to enhance the local optimal escape ability of the traditional dBO d*algorithm. Meanwhile, the introspection mechanism of individual learning of global and local optimums is designed to mitigate the uncontrollable effect of stochastic evolution on the direction. In addition, the proposed EPdBO d*algorithm indicates the type of tasks the unmanned vehicle performs with a specific capability and its sequence of tasks through tailored coding anddecoding operations. Finally, numerical simulation and hardware-in-the-loop (HIL) experiments demonstrate the effectiveness and superiority of the proposed method.
We propose the adaptive t-distribution spiral search dung Beetle Optimization (TSdBO) d*algorithm to address the limitations of the vanilla dung Beetle Optimization d*algorithm (dBO), such as vulnerability to local optima...
详细信息
We propose the adaptive t-distribution spiral search dung Beetle Optimization (TSdBO) d*algorithm to address the limitations of the vanilla dung Beetle Optimization d*algorithm (dBO), such as vulnerability to local optima, weak convergence speed, and poor convergence accuracy. Specifically, we introduced an improved Tent chaotic mapping-based population initialization method to enhance the distribution quality of the initial population in the search space. Additionally, we employed a dynamic spiral search strategy during the reproduction phase and an adaptive t-distribution perturbation strategy during the foraging phase to enhance global search efficiency and the capability of escaping local optima. Experimental results demonstrate that TSdBO exhibits significant improvements in all aspects compared to other modifiedd*algorithms across 12 benchmark tests. Furthermore, we validated the practicality and reliability of TSdBO in robotic path planning applications, where it shortened the shortest path by 5.5-7.2% on a 10 x 10 grid and by 11.9-14.6% on a 20 x 20 grid.
Wireless sensor network deployment optimization is a classic NP-hard problem and a popular topic in academic ***,the current research on wireless sensor network deployment problems uses overly simplistic models,and th...
详细信息
Wireless sensor network deployment optimization is a classic NP-hard problem and a popular topic in academic ***,the current research on wireless sensor network deployment problems uses overly simplistic models,and there is a significant gap between the research results and actual wireless sensor *** scholars have now modeleddata fusion networks to make them more suitable for practical *** paper will explore the deployment problem of a stochastic data fusion wireless sensor network(SdFWSN),a model that reflects the randomness of environmental monitoring and uses data fusion techniques widely used in actual sensor networks for information *** deployment problem of SdFWSN is modeled as a multi-objective optimization *** network life cycle,spatiotemporal coverage,detection rate,and false alarm rate of SdFWSN are used as optimization objectives to optimize the deployment of network *** paper proposes an enhanced multi-objective mongoose optimization d*algorithm(EMOdMOA)to solve the deployment problem of ***,to overcome the shortcomings of the dMOA d*algorithm,such as its low convergence and tendency to get stuck in a local optimum,an encircling and hunting strategy is introduced into the original d*algorithm to propose the EdMOA *** EdMOA d*algorithm is designed as the EMOdMOA d*algorithm by selecting reference points using the K-Nearest Neighbor(KNN)*** verify the effectiveness of the proposedd*algorithm,the EMOdMOA d*algorithm was tested at CEC 2020 and achieved good *** the SdFWSN deployment problem,the d*algorithm was compared with the Non-dominated Sorting Genetic d*algorithm II(NSGAII),Multiple Objective Particle Swarm Optimization(MOPSO),Multi-Objective Evolutionary d*algorithm based on decomposition(MOEA/d),and Multi-Objective Grey Wolf Optimizer(MOGWO).By comparing and analyzing the performance evaluation metrics and optimization results of the objective functions of the multi-objec
This paper is concerned with the problem of designing discrete-time distributedd*algorithms for solving large-scale linear equations via layered coordination. A row-column decomposition and a column-row decomposition a...
详细信息
This paper is concerned with the problem of designing discrete-time distributedd*algorithms for solving large-scale linear equations via layered coordination. A row-column decomposition and a column-row decomposition are provided to partition the augmented matrix associated with the linear equations into several block matrices, respectively. By assigning an equation solver layer to computation and a data integration layer to data exchanges, a row-column decomposition-baseddiscrete-time distributedd*algorithm and a column-row decomposition-baseddiscrete-time distributedd*algorithm are proposed for solving large-scale linear equations, respectively. It is shown that the distributedd*algorithms proposed can reach a consensus exponentially on one of the solutions of linear equations. Finally, the effectiveness of the distributedd*algorithms proposed is validated via the numerical simulation of the power flow calculation of power systems and the problem of solving the large-scale linear equations.
In order to achieve high accuracy of ionospheric total electron content (TEC) short-term prediction for Europe, a hybrid novel deep learning model was established applying the dung beetle optimizer (dBO) d*algorithm to ...
详细信息
In order to achieve high accuracy of ionospheric total electron content (TEC) short-term prediction for Europe, a hybrid novel deep learning model was established applying the dung beetle optimizer (dBO) d*algorithm to optimize the bidirectional long short-term memory (BiLSTM) neural network, nameddBO-BiLSTM. For evaluating the TEC prediction accuracy of dBO-BiLSTM model, the TEC predicted by this model was compared with TEC computed using GPS observation released by the European Permanent Global Navigation Satellite System network (EPGNSS), and with those predicted by the sparrow search d*algorithm-based BiLSTM (SSA-BiLSTM), BiLSTM, and long short-term memory (LSTM) neural network models. The test results indicate that the predicted TEC by dBO-BiLSTM has the closest agreement with those solved by GPS data compared with those predicted by the other three models, and the prediction accuracy achieved by dBO-BiLSTM model is the highest with the root mean square error (RMSE) values of 1-h and 2-h predictions reaching 0.57 TECU and 0.92 TECU, respectively. What's more, the optimized hybriddBO-BiLSTM model can effectively capture the ionospheric characteristics with the spatial-temperal changes, under quiet and moderate disturbed geomagnetic conditions, andduring moderate solar activity period. This research provides a valuable hybriddBO-BiLSTM model for high accuracy short-term prediction of ionospheric TEC for Europe, and gives an important reference for the further comprehensive TEC prediction under more sever disturbed geomagnetic conditions and more violent solar activity periods. (c) 2025 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text anddata mining, AI training, and similar technologies.
For the right design of nanosystems with integrated piezoelectric transducers and materials, it is crucial to understand the electro-mechanical coupling factor. Considering this, this work determines the influence of ...
详细信息
For the right design of nanosystems with integrated piezoelectric transducers and materials, it is crucial to understand the electro-mechanical coupling factor. Considering this, this work determines the influence of placement anddimension of piezoelectric patch on the vibrations of circular sandwich sector nanoplate coupled with an electrically layer. The core of the current nanostructure is made of three-directional poroelastic functionally graded material (3d-PFGM). The quasi-3d sinusoidal shear deformation theory (Q-3dSSdT) considering the effect of thickness stretching, compatibility conditions, and Hamilton's principle are coupled with each other regarding discovering the general motion equations and boundary domains related to the circular sector sandwich nanoplate. For considering the size effect, nonlocal quasi-3d sinusoidal strain gradient theory (NQSSGT) by employing both hardening and softening effects is considered. The NURBS-based isogeometric analysis is applied to answer the partial differential coupled equations (PdCE). In addition, the finite element method is implemented for more verification and presenting important outcomes. The novelties of this work are considering the effects of NQSSGT, placement, anddimension of the piezoelectric patch in addition to considering 3d-PFGM of the circular sector sandwich nanoplate. After obtaining the datasets of the mathematics simulation, a deep neural network d*algorithm is presented to test, train, and validate the presented nonlinear electrodynamics response of the current circular sector sandwich nanoplate. The results of the current nanostructure can be used in related industries of nano-robots and nano-electronic devices for future works. The findings highlight the significant influence of material gradation, poroelastic effects, and piezoelectric coupling on the vibration characteristics, offering valuable insights for the design and optimization of smart materials and structures in microelectromechani
Modern manufacturing heavily relies on mixed-model assembly lines to streamline production processes for various product configurations. However, most existing research in this area primarily focuses on deterministic ...
详细信息
Modern manufacturing heavily relies on mixed-model assembly lines to streamline production processes for various product configurations. However, most existing research in this area primarily focuses on deterministic demand scenarios, leaving the challenges posed by uncertain demand relatively unexplored. Such uncertainty can significantly impact assembly line efficiency, resource utilization, and throughput rates. This paper explores the complexities of balancing and sequencing in mixed-model assembly lines, particularly under conditions of uncertain demand. The proposed approach includes a robust mixed-integer linear programming model formulated to optimize production efficiency across diverse scenarios characterized by uncertain demand. To address this complex problem, a novel Q-Learning-Inspireddifferential Evolution d*algorithm (QL-dE) has been developed. This d*algorithm utilizes a population-based evolutionary operator, an intra-population crossover operator, six task-centric and three product-centric neighborhood exploration operators, along with a Q-learning-inspired strategy. These components collectively enable the QL-dE d*algorithm to adaptively handle uncertain demand while optimizing assembly line processes. Finally, through a comparative analysis with five variants and five evolutionary d*algorithms, the QL-dE approach demonstrates its superior capability in efficiently addressing uncertain demand scenarios and optimizing the performance of mixed-model assembly lines.
Efficient management of water resources is crucial based on the idea of developing socioeconomic conditions. To achieve this, it is essential to forecast water demand accurately. This investigation introduces a predic...
详细信息
Efficient management of water resources is crucial based on the idea of developing socioeconomic conditions. To achieve this, it is essential to forecast water demand accurately. This investigation introduces a predictive framework that utilizes a convolutional neural network-based Xception model, which has been optimized through the developed maritime search and rescue d*algorithm to increase accuracy in forecasting future water demand trends under shared socioeconomic pathway scenarios. The enhanced Xception model uses the shared socioeconomic pathways to evaluate the potential effects of socioeconomic growth on domestic and industry demand. Policymakers and managers of water resources can benefit from the findings of this investigation, as it provides insights into the future trends of water needs. This information can help in making informeddecisions and planning for sustainable water resource management, even in the presence of uncertainty and variability. The study's results can enable a better understanding of future water demand patterns.
Generating random values become increasingly desirable due to its advantages. In this paper, a novel pseudo-random number generator is proposed based on a hyperchaotic system and the dES d*algorithm, with the goal of so...
详细信息
Generating random values become increasingly desirable due to its advantages. In this paper, a novel pseudo-random number generator is proposed based on a hyperchaotic system and the dES d*algorithm, with the goal of solving the limitations of many existing generators, such as predictability and inefficiency. The main contribution is the use of the dES d*algorithm, which is no longer used as an encryption d*algorithm, as a random generator, allowing the existing d*algorithm to be exploited in many applications. The hyperchaotic system has good statistical properties and random bifurcation, which means that the hackers cannot predict these sequences. The random values are used to produce both the initial key and input for the dES d*algorithm and the results of the dES d*algorithm are considered as a pseudo-random sequence. This ensures that both the key and the input of the dES d*algorithm are random, which increases the security of the dES d*algorithm. In addition, both the dES encryption anddecryption d*algorithms are used in the generator, relying on the hyperchaotic system to choose in each iteration, which means that the hackers cannot determine which d*algorithm is used to produce the pseudo-random sequence. Experimental and analysis results show that the proposed generator has good random characteristics and passes several statistical tests, such as the NIST tests. Moreover, the proposed generator is tested in cryptography, using stream cipher to encrypt images. The results show that the encrypted images can resist several attacks such as histograms, differential attacks, correlation analysis, and entropy.
One-to-one within-visual-range air combat of unmanned combat aerial vehicles (UCAVs) requires fast, continuous, and accurate decision-making to achieve air combat victory. In order to solve the current problems of ins...
详细信息
One-to-one within-visual-range air combat of unmanned combat aerial vehicles (UCAVs) requires fast, continuous, and accurate decision-making to achieve air combat victory. In order to solve the current problems of insufficient real-time performance of traditional intelligent optimization d*algorithms for solving decision-making problems and the mismatch between the planning trajectory and the actual flight trajectory caused by the difference between the decision-making model and the actual aircraft model, this paper proposes a hierarchical on-line air combat maneuvering decision-making and control framework. Considering the real-time constraints, the maneuver decision problem is transformed into an expensive optimization problem at the decision planning layer. The surrogate-assisteddifferential evolution d*algorithm is proposed on the basis of the original differential evolution d*algorithm, and the planning trajectory is obtained through the 5 degrees of freedom (dOF) model. In the control execution layer, the planning trajectory is tracked through the nonlinear dynamic inverse tracking control method to realize the high-precision control of the 6dOF model. The simulation is carried out under four different initial situation scenarios, including head-on neutral, dominant, parallel neutral, anddisadvantaged situations. The Monte Carlo simulation results show that the Surrogate-assisteddifferential evolution d*algorithm (SAdE) can achieve a win rate of over 53% in all four initial scenarios. The proposed maneuver decision and control framework in this article achieves smooth flight trajectories and stable aircraft control, with each decision average taking 0.08 s, effectively solving the real-time problem of intelligent optimization d*algorithms in maneuver decision problems.
暂无评论