The biggest challenge of this article is how to maximize the rest time of intermittent controllers. This paper mainly uses intermittent quantized controller (IQC) to examine asymptotic synchronization between fraction...
详细信息
The biggest challenge of this article is how to maximize the rest time of intermittent controllers. This paper mainly uses intermittent quantized controller (IQC) to examine asymptotic synchronization between fractional-order neural networks (FONNs). Firstly, by utilizing the advantages of intermittent properties, a novel lemma with asymptotic stability inequalities is proposed. Secondly, combining intermittent properties with quantization technique, two different categories of aperiodically intermittent quantized controllers (AIQCs) are designed to ensure asymptotic convergence of FONNs. Due to the certain correlation between control interval, rest interval, and convergence rate parameters, thus, optimization algorithm becomes particularly important in maximizing rest time as much as possible. Thirdly, by constructing Lyapunov functions, several useful conditions are established for the asymptotic synchronization of FONNs. Finally, the rationality of the proposed theoretical analysis is confirmed by two numerical examples.
This article proposes a method for obtaining the refractive index and thickness of thin films based on reflectivity at different angles combined with optimization algorithms. This method has high computational accurac...
详细信息
This article proposes a method for obtaining the refractive index and thickness of thin films based on reflectivity at different angles combined with optimization algorithms. This method has high computational accuracy for both high absorption films (such as aluminum films, gold films, etc.) and low absorption films (such as MgF2 films). Since this study did not adopt the inversion scheme of refractive index dispersion equation fitting, it can be used for optical constant inversion in the case of unknown composition of coating materials. The results indicate that this method can simultaneously obtain high-precision information on the complex refractive index and film thickness of the coating material on the substrate. The calculation example achieved a thickness inversion error of 0.165 % for a 2nm metal aluminum film layer and 0.3303 % for a 150 nm MgF2 transparent film layer. Therefore, this study may provide further guidance for high absorption and measurement of the complex refractive index and thickness of transparent films.
Aims In the case of uneven vegetation coverage, it is still facing many problems that using UAV-remote sensing to assess the canopy nutrient status. The research objective is to determine the optimal ground feature cl...
详细信息
Aims In the case of uneven vegetation coverage, it is still facing many problems that using UAV-remote sensing to assess the canopy nutrient status. The research objective is to determine the optimal ground feature classification and establish the leaf nitrogen concentration (LNC) inversion model. Methods UAV-Phantom 4 multispectral platform was used to acquire apple orchard images. The ground features of remote sensing image were classified with the minimum distance, maximum likelihood, and object-oriented feature extraction classifications (MDC, MLC, OFEC), while spectral vegetation indices were used to perform LNC inversion using the backpropagation neural network (BP) and extreme learning machine (ELM). Further, genetic algorithm (GA) and particle swarm optimization (PSO) were used to optimize two inversion models. Results Compared with the MDC, the overall accuracy of MLC increased 20.30% and 26.69% in 2021 and 2022, while the OFEC increased 30.48% and 31.04%, respectively. The LNC inversion model of BP and ELM produced an acceptable performance (R-c (2)> R(2)p > 0.60, RRMSE < 15%). The use of GA and PSO algorithms did not improve the prediction performance of the BP inversion model. Compared with ELM, the RRMSE of GA_ELM and PSO_ELM inversion models decreased 2.63% and 20.39%. Furthermore, the PSO_ELM inversion model decreased the RRMSE 10.95% compared to the BP model. ConclusionThe combination of reverse thinking iterative approach with the PSO algorithm significantly enhances the predictive performance of the ELM inversion model, which can present a rapid assessment method for leaf nitrogen nutrition diagnosis based on the relationship between LNC and fruit yield.
The location of nodes is critical in underwater wireless sensor networks (UWSNs), which is an ocean monitoring platform. UWSNs are motivated by the popular usage of localization and play a major role in several techno...
详细信息
The location of nodes is critical in underwater wireless sensor networks (UWSNs), which is an ocean monitoring platform. UWSNs are motivated by the popular usage of localization and play a major role in several technologies that depend primarily on innovations and localization of these nodes. Underwater node localization is a critical technology that enables the deployment of a variety of underwater applications. In this study, the underwater nodes are divided into two levels. Firstly, a clock asynchronous localization system (LS-AC) for base layer's node localization is presented. In order to eradicate the original ranging strategy's dependence on active nodes and address the problem of energy consumption, LS-AC performs in-network situation-based monitoring by relying on asynchronous clocks. Secondly, we propose a backtracking search algorithm (OTKL-BSA) based on optimal topology and knowledge learning. It is used to address the issues associated with traditional algorithms' lack of diversity and the imbalance between exploration and exploitation. Thirdly, to solve the problems that the traditional gray wolf optimizer (GWO) is prone to falling into local optimal values and has a low search efficiency, this paper proposes a GWO scheme based on hunting step size (GWO-HSS). Finally, simulation results show that the proposed algorithm outperforms SLMP, MCL-MP, MP-PSO, and MGP in aspects of localization performance.
This paper aims to provide a comprehensive guide to the application of the inverse tech-nique to the miniaturized tests, on material parameter identification, without investigating the aspects related to the correct c...
详细信息
This paper aims to provide a comprehensive guide to the application of the inverse tech-nique to the miniaturized tests, on material parameter identification, without investigating the aspects related to the correct choice of a specific material model. Firstly, a brief introduction to the fundamental principles and procedures associated with the inverse method is given. In general, the strategy described relies on the coupling of the finite element (FE) modelling with an optimization scheme. The FE method allows for the eval-uation of the response of the material under various types of tests, test conditions, and complex constitutive equations, and avoids the use of approximation techniques for the interpretation of the experimental results. Then, on this based, an example of FE-based inverse processes using small punch creep tests is given to illustrate the process and capability of identifying the creep damage properties. Finally, several sensitive issues, related to the application of the inverse approach, are addressed.(c) 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).
In traditional structural crane design, the fatigue strength of the structure is qualitatively evaluated, only depending on the steel type, working level and joint form, which leads to the excessive service life of so...
详细信息
In traditional structural crane design, the fatigue strength of the structure is qualitatively evaluated, only depending on the steel type, working level and joint form, which leads to the excessive service life of some parts of the existing main girder structure, resulting in a waste of industrial resources and manufacturing costs. Based on the concept of equal life design, this paper obtained the service information of the crane in the scheduled inspection period through the rapid prediction method of "field collection+machine learning." Combined with the bearing capacity evaluation method and the fatigue life assessment method of "S-N curve+fracture mechanics," a nonlinear mixed integer equal life optimization model of crane girder structure was established, and the multi-specular reflection optimization algorithm was used to optimize the life distribution at different positions and overall weight of the main girder. The structural design parameters of the crane main girder which meet the bearing capacity and have the characteristics of "equal life+lightweight" were obtained. The performance of the optimized main girder structure was verified by finite element simulation. The results show that this method can realize the quantitative control of the life distribution of each position of the crane main girder structure and the lightweight design of the whole structure, and provides a scientific reference for the equal life and lightweight design of large construction machinery products.
As one of continuous concern all over the world, the problem of water quality may cause diseases and poisoning and even endanger people's lives. Therefore, the prediction of water quality is of great significance ...
详细信息
As one of continuous concern all over the world, the problem of water quality may cause diseases and poisoning and even endanger people's lives. Therefore, the prediction of water quality is of great significance to the efficient management of water resources. However, existing prediction algorithms not only require more operation time but also have low accuracy. In recent years, neural networks are widely used to predict water quality, and the computational power of individual neurons has attracted more and more attention. The main content of this research is to use a novel dendritic neuron model (DNM) to predict water quality. In DNM, dendrites combine synapses of different states instead of simple linear weighting, which has a better fitting ability compared with traditional neural networks. In addition, a recent optimization algorithm called AMSGrad (Adaptive Gradient Method) has been introduced to improve the performance of the Adam dendritic neuron model (ADNM). The performance of ADNM is compared with that of traditional neural networks, and the simulation results show that ADNM is better than traditional neural networks in mean square error, root mean square error and other indicators. Furthermore, the stability and accuracy of ADNM are better than those of other conventional models. Based on trained neural networks, policymakers and managers can use the model to predict the water quality. Real-time water quality level at the monitoring site can be presented so that measures can be taken to avoid diseases caused by water quality problems.
Increased space sensing enables new measurements of a wide range of Earth science phenomena including volcanism, flooding, wildfires, and weather. Large-scale observation constellations of hundreds of assets have alre...
详细信息
Increased space sensing enables new measurements of a wide range of Earth science phenomena including volcanism, flooding, wildfires, and weather. Large-scale observation constellations of hundreds of assets have already been deployed (for example, Planet Labs's Dove satellites), and several constellations of tens of thousands of assets are planned. New challenges exist to rapidly assimilate available data and to optimize measurements by directing spacecraft assets to best observe complex Earth science phenomena. Centralized approaches to managing request allocation in these large constellations are constrained by 1) the need to assign/elect a central node to assign requests to spacecraft and 2) reliance on a single agent communicating with potentially thousands of dependent agents. On the other hand, entirely decentralized approaches to request allocation and observation are prone to oversatisfaction of some requests and undersatisfaction of others due to a lack of communication among agents. In large constellations, an intermediary method is necessary to solve the request allocation problem in a distributed manner. We present distributed artificial intelligence/multiagent methods that leverage existing work on distributed constraint optimization to allocate observations in a satellite constellation. We compare their performance to centralized and highly decentralized approaches using realistic orbits and observation request distributions. Our distributed algorithms can find approximate solutions to the large-scale constellation request allocation problem with low data volume for agent coordination and extend to continuous planning problems with varying request sets and availability of spacecraft agents.
暂无评论