This study introduces a novel algorithm known as the dung beetle optimization algorithm based on bounded reflection optimization andmulti-strategy fusion(BFDBO),which is designed to tackle the complexities associated ...This study introduces a novel algorithm known as the dung beetle optimization algorithm based on bounded reflection optimization andmulti-strategy fusion(BFDBO),which is designed to tackle the complexities associated with multi-UAV collaborative trajectory planning in intricate battlefield environments.Initially,a collaborative planning cost function for the multi-UAV system is formulated,thereby converting the trajectory planning challenge into an optimization problem.Building on the foundational dung beetle optimization(DBO)algorithm,BFDBO incorporates three significant innovations:a boundary reflection mechanism,an adaptive mixed exploration strategy,and a dynamic multi-scale mutation strategy.These enhancements are intended to optimize the equilibrium between local exploration and global exploitation,facilitating the discovery of globally optimal trajectories thatminimize the cost function.Numerical simulations utilizing the CEC2022 benchmark function indicate that all three enhancements of BFDBOpositively influence its performance,resulting in accelerated convergence and improved optimization accuracy relative to leading optimization algorithms.In two battlefield scenarios of varying complexities,BFDBO achieved a minimum of a 39% reduction in total trajectory planning costs when compared to DBO and three other highperformance variants,while also demonstrating superior average runtime.This evidence underscores the effectiveness and applicability of BFDBO in practical,real-world contexts.展开更多
Despite deep learning’s high precision in emotion identification,centralized training is associated with privacy and scalability concerns.The privacy-preserving federated learning model,Federated Hybrid-Optimized Emo...Despite deep learning’s high precision in emotion identification,centralized training is associated with privacy and scalability concerns.The privacy-preserving federated learning model,Federated Hybrid-Optimized Emotion Recognition(Fed-HOER),introduced in this paper is an auto-tuning hyperparameters optimizer based on a hybrid Dung Beetle Optimizer-Fick’s Law Algorithm(DBO-FLA)optimizer.The global and local searches are optimized at two levels,and validation loss is minimized by 22%–24%without sharing raw data.The experiments on Extended Cohn–Kanade(CK+),Japanese Female Facial Expressions(JAFFE),and Karolinska Directed Emotional Faces(KDEF)exhibit a high generalization rate with a mean accuracy of 98.14.The findings demonstrate that Fed-HOER is statistically significantly better than baseline configurations.The results show that the suggested framework offers a favorable trade-off between predictive accuracy and privacy protection,which is why it can be used in the healthcare,educational,and other emotion-related fields.展开更多
This paper aims to address the problem of multi-UAV cooperative search for multiple targets in a mountainous environment,considering the constraints of UAV dynamics and prior environmental information.Firstly,using th...This paper aims to address the problem of multi-UAV cooperative search for multiple targets in a mountainous environment,considering the constraints of UAV dynamics and prior environmental information.Firstly,using the target probability distribution map,two strategies of information fusion and information diffusion are employed to solve the problem of environmental information inconsistency caused by different UAVs searching different areas,thereby improving the coordination of UAV groups.Secondly,the task region is decomposed into several high-value sub-regions by using data clustering method.Based on this,a hierarchical search strategy is proposed,which allows precise or rough search in different probability areas by adjusting the altitude of the aircraft,thereby improving the search efficiency.Third,the Elite Dung Beetle Optimization Algorithm(EDBOA)is proposed based on bionics by accurately simulating the social behavior of dung beetles to plan paths that satisfy the UAV dynamics constraints and adapt to the mountainous terrain,where the mountain is considered as an obstacle to be avoided.Finally,the objective function for path optimization is formulated by considering factors such as coverage within the task region,smoothness of the search path,and path length.The effectiveness and superiority of the proposed schemes are verified by the simulation.展开更多
文章采用一种直接转矩控制(direct torque control,DTC)方案,将参考扭矩直接与估计扭矩进行比较,并将误差提供给控制器,从而实现极低转矩纹波下的直流无刷电机(brushless direct current motor,BLDC)控制。相较于传统的整数阶比例-积分...文章采用一种直接转矩控制(direct torque control,DTC)方案,将参考扭矩直接与估计扭矩进行比较,并将误差提供给控制器,从而实现极低转矩纹波下的直流无刷电机(brushless direct current motor,BLDC)控制。相较于传统的整数阶比例-积分-微分(proportion-integration-differentiation,PID)控制器,分数阶PID(fractional order PID,FOPID)控制器的可调参数由过去的KP、KI、KD增加为KP、KI、KD、λ、μ,可调参数数量的增加能够更好地反映控制对象的非线性特性和时变性质,从而提升控制系统的鲁棒性。为避免PID参数过于依赖专家经验的缺点,采用蜣螂优化(dung beetle optimization,DBO)算法对FOPID进行自适应参数整定;并在MATLAB/Simulink环境中搭建BLDC的DTC控制模型,将所提出的基于DBO-FOPID控制器的BLDC直接转矩控制与基于粒子群优化(particle swarm optimization,PSO)算法的FOPID控制器的BLDC直接转矩控制、基于麻雀搜索优化算法(sparrow search algorithm,SSA)的FOPID控制器的BLDC直接转矩控制以及基于PI(proportion integration)控制器的BLDC速度控制等方法进行对比。仿真对比结果验证了所提出的控制器能够以极低的转矩脉动实现对电机转矩的有效控制。展开更多
【目的】为及时发现海上风电机组发电机轴承的故障,提出一种基于蜣螂优化(Dung Beetle Optimizer,DBO)算法和极端梯度提升树(eXtreme Gradient Boosting,XGBoost)模型的DBO-XGBoost发电机轴承温度预测模型,并结合指数加权移动平均值(Exp...【目的】为及时发现海上风电机组发电机轴承的故障,提出一种基于蜣螂优化(Dung Beetle Optimizer,DBO)算法和极端梯度提升树(eXtreme Gradient Boosting,XGBoost)模型的DBO-XGBoost发电机轴承温度预测模型,并结合指数加权移动平均值(Exponentially Weighted Moving Average,EWMA)控制图实现发电机轴承的故障预测。【方法】首先,通过最大互信息系数(Maximal Information Coefficient,MIC)选取数据采集与监视控制(Supervisory Control And Data Acquisition,SCADA)系统中能准确表征发电机轴承状态的关键特征,并将其输入DBO-XGBoost模型中,对正常工况下的发电机轴承温度进行预测。其次,使用马氏距离(Mahalanobis Distance,MD)衡量真实值与预测值之间的偏差,并将MD序列输入基于EWMA控制图的变点检测算法中,以获取故障出现的变点,从而实现故障预测。最后,基于特征的重要性构建轴承故障模式知识图谱。【结果】结果表明,所提方法能对正常工况下发电机轴承的温度实现较为精准的预测,并能提前3天对故障进行预警,与通过设定单一阈值进行故障预警的方法相比,所提方法能更准确地检测到故障发生的时间。构建的轴承故障模式知识图谱为运维人员提供了可视化的运维决策支持。展开更多
The end tidal carbon dioxide(EtCO2)is crucial for monitoring patients respiratory function,which reflects the status of lung ventilation and gas exchange.Therefore,achieving accurate measurements of EtCO2holds s...The end tidal carbon dioxide(EtCO2)is crucial for monitoring patients respiratory function,which reflects the status of lung ventilation and gas exchange.Therefore,achieving accurate measurements of EtCO2holds significant importance in clinical practice.The measurements of EtCO2based on wavelength modulation-direct absorption spectroscopy(WM-DAS)had great advantages and the noise reduction of spectrum was very important.An optimized variational mode decomposition(VMD)algorithm improved by the dung beetle optimization algorithm and wavelet packet denoising algorithm was proposed to enhance the measurement accuracy of EtCO2concentration.The dung beetle optimization algorithm was used to obtain the optimal number of decomposition mode layers K and secondary penalty factorα.The optimal parameters were used to decompose the original transmitted light intensity signal with noise,and a series of intrinsic mode functions(IMFs)were obtained.Pearson correlation coefficient(R)was used to select the pure signal and the noisy signal,and the noisy signal was denoised by wavelet packet denoising algorithm.The transmitted light intensity signal was reconstructed by the signal processed by wavelet packet denoising algorithm and the pure signal.The results showed that the proposed algorithm could effectively remove the noise of signal of transmitted light intensity and improve the accuracy of concentration measurements of EtCO2.展开更多
基金funded by the National Defense Science and Technology Innovation project,grant number ZZKY20223103the Basic Frontier InnovationProject at the Engineering University of PAP,grant number WJY202429+2 种基金the Basic Frontier lnnovation Project at the Engineering University of PAP,grant number WJY202408the Graduate Student Funding Priority Project,grant number JYWJ2024B006Key project of National Social Science Foundation,grant number 2023-SKJJ-A-116.
摘要This study introduces a novel algorithm known as the dung beetle optimization algorithm based on bounded reflection optimization andmulti-strategy fusion(BFDBO),which is designed to tackle the complexities associated with multi-UAV collaborative trajectory planning in intricate battlefield environments.Initially,a collaborative planning cost function for the multi-UAV system is formulated,thereby converting the trajectory planning challenge into an optimization problem.Building on the foundational dung beetle optimization(DBO)algorithm,BFDBO incorporates three significant innovations:a boundary reflection mechanism,an adaptive mixed exploration strategy,and a dynamic multi-scale mutation strategy.These enhancements are intended to optimize the equilibrium between local exploration and global exploitation,facilitating the discovery of globally optimal trajectories thatminimize the cost function.Numerical simulations utilizing the CEC2022 benchmark function indicate that all three enhancements of BFDBOpositively influence its performance,resulting in accelerated convergence and improved optimization accuracy relative to leading optimization algorithms.In two battlefield scenarios of varying complexities,BFDBO achieved a minimum of a 39% reduction in total trajectory planning costs when compared to DBO and three other highperformance variants,while also demonstrating superior average runtime.This evidence underscores the effectiveness and applicability of BFDBO in practical,real-world contexts.
摘要Despite deep learning’s high precision in emotion identification,centralized training is associated with privacy and scalability concerns.The privacy-preserving federated learning model,Federated Hybrid-Optimized Emotion Recognition(Fed-HOER),introduced in this paper is an auto-tuning hyperparameters optimizer based on a hybrid Dung Beetle Optimizer-Fick’s Law Algorithm(DBO-FLA)optimizer.The global and local searches are optimized at two levels,and validation loss is minimized by 22%–24%without sharing raw data.The experiments on Extended Cohn–Kanade(CK+),Japanese Female Facial Expressions(JAFFE),and Karolinska Directed Emotional Faces(KDEF)exhibit a high generalization rate with a mean accuracy of 98.14.The findings demonstrate that Fed-HOER is statistically significantly better than baseline configurations.The results show that the suggested framework offers a favorable trade-off between predictive accuracy and privacy protection,which is why it can be used in the healthcare,educational,and other emotion-related fields.
基金supported by the Natural Science Foundation of China(62273068)the Fundamental Research Funds for the Central Universities(3132023512)Dalian Science and Technology Innovation Fund(2019J12GX040).
摘要This paper aims to address the problem of multi-UAV cooperative search for multiple targets in a mountainous environment,considering the constraints of UAV dynamics and prior environmental information.Firstly,using the target probability distribution map,two strategies of information fusion and information diffusion are employed to solve the problem of environmental information inconsistency caused by different UAVs searching different areas,thereby improving the coordination of UAV groups.Secondly,the task region is decomposed into several high-value sub-regions by using data clustering method.Based on this,a hierarchical search strategy is proposed,which allows precise or rough search in different probability areas by adjusting the altitude of the aircraft,thereby improving the search efficiency.Third,the Elite Dung Beetle Optimization Algorithm(EDBOA)is proposed based on bionics by accurately simulating the social behavior of dung beetles to plan paths that satisfy the UAV dynamics constraints and adapt to the mountainous terrain,where the mountain is considered as an obstacle to be avoided.Finally,the objective function for path optimization is formulated by considering factors such as coverage within the task region,smoothness of the search path,and path length.The effectiveness and superiority of the proposed schemes are verified by the simulation.
摘要文章采用一种直接转矩控制(direct torque control,DTC)方案,将参考扭矩直接与估计扭矩进行比较,并将误差提供给控制器,从而实现极低转矩纹波下的直流无刷电机(brushless direct current motor,BLDC)控制。相较于传统的整数阶比例-积分-微分(proportion-integration-differentiation,PID)控制器,分数阶PID(fractional order PID,FOPID)控制器的可调参数由过去的KP、KI、KD增加为KP、KI、KD、λ、μ,可调参数数量的增加能够更好地反映控制对象的非线性特性和时变性质,从而提升控制系统的鲁棒性。为避免PID参数过于依赖专家经验的缺点,采用蜣螂优化(dung beetle optimization,DBO)算法对FOPID进行自适应参数整定;并在MATLAB/Simulink环境中搭建BLDC的DTC控制模型,将所提出的基于DBO-FOPID控制器的BLDC直接转矩控制与基于粒子群优化(particle swarm optimization,PSO)算法的FOPID控制器的BLDC直接转矩控制、基于麻雀搜索优化算法(sparrow search algorithm,SSA)的FOPID控制器的BLDC直接转矩控制以及基于PI(proportion integration)控制器的BLDC速度控制等方法进行对比。仿真对比结果验证了所提出的控制器能够以极低的转矩脉动实现对电机转矩的有效控制。
摘要【目的】为及时发现海上风电机组发电机轴承的故障,提出一种基于蜣螂优化(Dung Beetle Optimizer,DBO)算法和极端梯度提升树(eXtreme Gradient Boosting,XGBoost)模型的DBO-XGBoost发电机轴承温度预测模型,并结合指数加权移动平均值(Exponentially Weighted Moving Average,EWMA)控制图实现发电机轴承的故障预测。【方法】首先,通过最大互信息系数(Maximal Information Coefficient,MIC)选取数据采集与监视控制(Supervisory Control And Data Acquisition,SCADA)系统中能准确表征发电机轴承状态的关键特征,并将其输入DBO-XGBoost模型中,对正常工况下的发电机轴承温度进行预测。其次,使用马氏距离(Mahalanobis Distance,MD)衡量真实值与预测值之间的偏差,并将MD序列输入基于EWMA控制图的变点检测算法中,以获取故障出现的变点,从而实现故障预测。最后,基于特征的重要性构建轴承故障模式知识图谱。【结果】结果表明,所提方法能对正常工况下发电机轴承的温度实现较为精准的预测,并能提前3天对故障进行预警,与通过设定单一阈值进行故障预警的方法相比,所提方法能更准确地检测到故障发生的时间。构建的轴承故障模式知识图谱为运维人员提供了可视化的运维决策支持。
基金supported by the Key Research and Development Program of Hebei Province(No.22375415D).
摘要The end tidal carbon dioxide(EtCO2)is crucial for monitoring patients respiratory function,which reflects the status of lung ventilation and gas exchange.Therefore,achieving accurate measurements of EtCO2holds significant importance in clinical practice.The measurements of EtCO2based on wavelength modulation-direct absorption spectroscopy(WM-DAS)had great advantages and the noise reduction of spectrum was very important.An optimized variational mode decomposition(VMD)algorithm improved by the dung beetle optimization algorithm and wavelet packet denoising algorithm was proposed to enhance the measurement accuracy of EtCO2concentration.The dung beetle optimization algorithm was used to obtain the optimal number of decomposition mode layers K and secondary penalty factorα.The optimal parameters were used to decompose the original transmitted light intensity signal with noise,and a series of intrinsic mode functions(IMFs)were obtained.Pearson correlation coefficient(R)was used to select the pure signal and the noisy signal,and the noisy signal was denoised by wavelet packet denoising algorithm.The transmitted light intensity signal was reconstructed by the signal processed by wavelet packet denoising algorithm and the pure signal.The results showed that the proposed algorithm could effectively remove the noise of signal of transmitted light intensity and improve the accuracy of concentration measurements of EtCO2.