A novel algorithm of 3-D surface image registration is proposed. It makes use of the array information of 3-D points and takes vector/vertex-like features as the basis of the matching. That array information of 3-D po...A novel algorithm of 3-D surface image registration is proposed. It makes use of the array information of 3-D points and takes vector/vertex-like features as the basis of the matching. That array information of 3-D points can be easily obtained when capturing original 3-D images. The iterative least-mean-squared （LMS） algorithm is applied to optimizing adaptively the transformation matrix parameters. These can effectively improve the registration performance and hurry up the matching process. Experimental results show that it can reach a good subjective impression on aligned 3-D images. Although the algorithm focuses primarily on the human head model, it can also be used for other objects with small modifications.展开更多
In this paper,a new mission model,called a multi-debris active removal mission with partial debris capture strategy,is proposed.The model assumes that a platform only captures part of the scheduled debris at a time an...In this paper,a new mission model,called a multi-debris active removal mission with partial debris capture strategy,is proposed.The model assumes that a platform only captures part of the scheduled debris at a time and then releases these debris pieces to a disposal orbit.This process is then repeated until all of the scheduled debris is removed.A genetic algorithm with a multiparameter concatenated coding method is designed to optimize the plan of a multi-debris active removal mission with a partial debris capture strategy.A set of six pieces of debris and a set of 10 pieces of debris are selected to demonstrate the proposed planning method.The result confirms the effectiveness of the genetic algorithm with the multi-parameter concatenated coding method.The new mission model provides a more comprehensive decision-making framework than the existing mission models and makes it possible to further decrease mission costs.展开更多
碳捕集、利用与封存(Carbon Capture,Utilization and Storage,简称CCUS)是实现碳中和的关键技术,通过CO_(2)提高油气采收率和地质封存实现能源增产与减少CO_(2)排放的双重效益。然而,CCUS技术在大规模应用中面临工程设计和风险评估等...碳捕集、利用与封存(Carbon Capture,Utilization and Storage,简称CCUS)是实现碳中和的关键技术,通过CO_(2)提高油气采收率和地质封存实现能源增产与减少CO_(2)排放的双重效益。然而,CCUS技术在大规模应用中面临工程设计和风险评估等技术挑战。传统解决方法依赖经验公式、实验验证和物理模型,在处理复杂系统时,计算效率低下,模型精度不足,难以处理多维度耦合问题。机器学习(Machine Learning,简称ML)凭借其强大的数据驱动分析能力和自适应优化特性,能训练出高精度预测模型,优化操作参数、预测储层流体行为、评估泄漏风险等,实现对复杂系统的实时监控和智能化决策,提升CCUS技术的安全性和经济性。研究系统梳理了ML在CO_(2)提高油气采收率与地质封存方面的应用。在CO_(2)提高油气采收率方面涵盖了渗流机理建模、优化井网设计、产量预测与评价、多目标优化、预测最小混相压力、预测气体吸附曲线、评估CO_(2)-CH_(4)扩散等;在CO_(2)地质封存方面包含储层优选、CO_(2)溶解与扩散机制研究、地质封存效果预测、风险评估等。ML在提升预测精度、优化操作参数、提高计算效率等方面展现出显著优势,已在储层优选、气体吸附预测、封存效果预测等关键领域取得重要进展,但在复杂地质场景下的适应性、模型普适性、动态数据处理能力、物理解释性等方面仍有待提升。展开更多
该文针对可再生能源消纳和虚拟电厂碳减排的问题,提出了一种基于碳捕集系统(carbon capture and storage,CCS)、电转气(power to gas,P2G)和压缩液态CO_(2)储能(liquid carbon dioxide energy storage,LCES)的虚拟电厂(virtual power pl...该文针对可再生能源消纳和虚拟电厂碳减排的问题,提出了一种基于碳捕集系统(carbon capture and storage,CCS)、电转气(power to gas,P2G)和压缩液态CO_(2)储能(liquid carbon dioxide energy storage,LCES)的虚拟电厂(virtual power plant,VPP)优化调度模型。该模型综合考虑了CCS、P2G和LCES的运行特性,以最大化VPP的碳减排效益和经济效益为目标,通过优化调度VPP内部的可再生能源、储能设备和碳捕集装置,实现了可再生能源的高效利用。提出了一种改进的霜冰优化算法(particle swarm optimizationrime optimization algorithm,PSO-RIME)用以求解VPP调度模型,并通过算例分析去验证所提模型和算法的有效性。结果表明,该模型和算法可以显著提高可再生能源的消纳能力和净收益,降低VPP的碳排放.展开更多
针对红嘴蓝鹊优化算法(Red-billed Blue Magpie Optimization Algorithm,RBMO)存在多样性迅速退化、寻优精度差、易陷入局部最优的问题,提出了一种基于混合策略的自适应红嘴蓝鹊优化算法(Adaptive Red-Billed Blue Magpie Optimization ...针对红嘴蓝鹊优化算法(Red-billed Blue Magpie Optimization Algorithm,RBMO)存在多样性迅速退化、寻优精度差、易陷入局部最优的问题,提出了一种基于混合策略的自适应红嘴蓝鹊优化算法(Adaptive Red-Billed Blue Magpie Optimization Algorithm Based on Mixed Strategy,JRBMO)。首先,引入Hammersley序列初始化种群,使初始解分布更均匀,为寻优提供基础;其次,在勘探阶段,提出自适应螺旋围捕策略,通过动态控制个体的勘探范围与方向,提高RBMO的搜索能力。在开发阶段,引入莱维飞行策略,对当前最优解进行局部扰动,增强算法局部开发能力;最后,提出自适应维度变异策略,根据种群适应度分布的变化,对个体进行维度变异,避免算法陷入局部最优。在CEC2017与CEC2019测试集上对算法性能进行评估,结果显示JRBMO均值胜率分别达到88.9%和70%,验证了JRBMO的有效性。此外,将JRBMO应用于拉(压)弹簧设计问题和三维无线传感器网络(WSN)节点覆盖问题上,JRBMO均取得了最优的结果,其中WSN节点均值覆盖率高出原算法6.3%,体现了JRBMO在实际应用中的普适性。展开更多
文摘A novel algorithm of 3-D surface image registration is proposed. It makes use of the array information of 3-D points and takes vector/vertex-like features as the basis of the matching. That array information of 3-D points can be easily obtained when capturing original 3-D images. The iterative least-mean-squared （LMS） algorithm is applied to optimizing adaptively the transformation matrix parameters. These can effectively improve the registration performance and hurry up the matching process. Experimental results show that it can reach a good subjective impression on aligned 3-D images. Although the algorithm focuses primarily on the human head model, it can also be used for other objects with small modifications.
基金co-supported by the Open Fund Project of Space Intelligent Control Technology Laboratory(No.HTKJ2021KL502010)the Research Project of Space Debris and Near-earth Asteroid Defense Grants,China(No.KJSP 2020010303)the National Natural Science Foundation of China(No.11802130).
文摘In this paper,a new mission model,called a multi-debris active removal mission with partial debris capture strategy,is proposed.The model assumes that a platform only captures part of the scheduled debris at a time and then releases these debris pieces to a disposal orbit.This process is then repeated until all of the scheduled debris is removed.A genetic algorithm with a multiparameter concatenated coding method is designed to optimize the plan of a multi-debris active removal mission with a partial debris capture strategy.A set of six pieces of debris and a set of 10 pieces of debris are selected to demonstrate the proposed planning method.The result confirms the effectiveness of the genetic algorithm with the multi-parameter concatenated coding method.The new mission model provides a more comprehensive decision-making framework than the existing mission models and makes it possible to further decrease mission costs.
文摘碳捕集、利用与封存(Carbon Capture,Utilization and Storage,简称CCUS)是实现碳中和的关键技术,通过CO_(2)提高油气采收率和地质封存实现能源增产与减少CO_(2)排放的双重效益。然而,CCUS技术在大规模应用中面临工程设计和风险评估等技术挑战。传统解决方法依赖经验公式、实验验证和物理模型,在处理复杂系统时,计算效率低下,模型精度不足,难以处理多维度耦合问题。机器学习(Machine Learning,简称ML)凭借其强大的数据驱动分析能力和自适应优化特性,能训练出高精度预测模型,优化操作参数、预测储层流体行为、评估泄漏风险等,实现对复杂系统的实时监控和智能化决策,提升CCUS技术的安全性和经济性。研究系统梳理了ML在CO_(2)提高油气采收率与地质封存方面的应用。在CO_(2)提高油气采收率方面涵盖了渗流机理建模、优化井网设计、产量预测与评价、多目标优化、预测最小混相压力、预测气体吸附曲线、评估CO_(2)-CH_(4)扩散等;在CO_(2)地质封存方面包含储层优选、CO_(2)溶解与扩散机制研究、地质封存效果预测、风险评估等。ML在提升预测精度、优化操作参数、提高计算效率等方面展现出显著优势,已在储层优选、气体吸附预测、封存效果预测等关键领域取得重要进展,但在复杂地质场景下的适应性、模型普适性、动态数据处理能力、物理解释性等方面仍有待提升。
文摘该文针对可再生能源消纳和虚拟电厂碳减排的问题,提出了一种基于碳捕集系统(carbon capture and storage,CCS)、电转气(power to gas,P2G)和压缩液态CO_(2)储能(liquid carbon dioxide energy storage,LCES)的虚拟电厂(virtual power plant,VPP)优化调度模型。该模型综合考虑了CCS、P2G和LCES的运行特性,以最大化VPP的碳减排效益和经济效益为目标,通过优化调度VPP内部的可再生能源、储能设备和碳捕集装置,实现了可再生能源的高效利用。提出了一种改进的霜冰优化算法(particle swarm optimizationrime optimization algorithm,PSO-RIME)用以求解VPP调度模型,并通过算例分析去验证所提模型和算法的有效性。结果表明,该模型和算法可以显著提高可再生能源的消纳能力和净收益,降低VPP的碳排放.
文摘针对红嘴蓝鹊优化算法(Red-billed Blue Magpie Optimization Algorithm,RBMO)存在多样性迅速退化、寻优精度差、易陷入局部最优的问题,提出了一种基于混合策略的自适应红嘴蓝鹊优化算法(Adaptive Red-Billed Blue Magpie Optimization Algorithm Based on Mixed Strategy,JRBMO)。首先,引入Hammersley序列初始化种群,使初始解分布更均匀,为寻优提供基础;其次,在勘探阶段,提出自适应螺旋围捕策略,通过动态控制个体的勘探范围与方向,提高RBMO的搜索能力。在开发阶段,引入莱维飞行策略,对当前最优解进行局部扰动,增强算法局部开发能力;最后,提出自适应维度变异策略,根据种群适应度分布的变化,对个体进行维度变异,避免算法陷入局部最优。在CEC2017与CEC2019测试集上对算法性能进行评估,结果显示JRBMO均值胜率分别达到88.9%和70%,验证了JRBMO的有效性。此外,将JRBMO应用于拉(压)弹簧设计问题和三维无线传感器网络(WSN)节点覆盖问题上,JRBMO均取得了最优的结果,其中WSN节点均值覆盖率高出原算法6.3%,体现了JRBMO在实际应用中的普适性。
