基于改进QPSO-NN的冗余机械臂逆运动学算法

针对某种冗余机械臂逆运动学求解的问题,提出了一种基于改进量子粒子群神经网络的求解算法。以冗余机械臂末端位姿为输入,经神经网络求得其逆解;针对神经网络输出结果误差较大的问题,把神经网络求初值加入初始化的粒子群中,通过基于Metropolis准则改进量子粒子群算法,避免了量子粒子群算法的早熟现象;以关节坐标经正向运动学求得的末端位姿和期望位姿的误差为适应度函数,对机械臂关节坐标迭代寻优。仿真结果表明该方法结合了神经网络算法的快速性和改进量子粒子群算法的精确性,满足求冗余机械臂逆运动学问题的速度和精度要求。     

基于BP神经网络的多功能相控阵雷达威力评估

运用动态静态结合的方法以及厂家测试数据、查阅外军资料等手段获得多功能相控阵雷达指标参数,采用BP神经网络建立威力评估模型。研究表明:所建立的BP神经网络多功能相控阵雷达威力评估模型具有很高的评估精度,可以很好地反映雷达二级指标和雷达威力之间复杂的非线性关系,为多功能相控阵雷达威力评估提供了一种准确有效的方法。     

对数据后处理雷达的分段卷积转发干扰研究

针对现有基于DRFM的移频干扰和分段转发干扰在对数据后处理雷达干扰时存在的不足问题,提出了一种新的分段卷积转发干扰方法。该干扰方法立足于干扰机天线收发分时体制,首先对接收到的雷达信号进行均匀分段、重新排序与噪声卷积后再进行转发。该干扰方法产生的假目标信号不仅能量大,覆盖广,而且假目标幅度差异明显,位置分布不均匀。最后的仿真结果验证了该方法的有效性。     

对RWR/ESM系统中象限判别概率的研究

随着现代战场电磁环境日趋复杂,辐射源不断增多,脉冲丢失成为机载RWR/ESM系统的一个严重问题。在机载RWR/ESM系统各射频前端通道发生脉冲交叠的基础上,分析了机载RWR/ESM系统测向环节在象限判别过程中的脉冲丢失概率,推导出脉冲象限判别概率的工程估算公式。最后通过仿真验证了机载RWR/ESM系统象限判别过程中,脉冲的象限鉴别正确概率与其输入脉冲密度之间的关系。     

三关节机器人的神经网络补偿自适应控制器设计

三关节机器人广泛用于工业生产、轮式或履带式排爆机器人,为了补偿由于机器人结构参数、作业环境干扰等不确定性因素造成的机器人动力学模型的不确定性,将机器人动力学模型分解为名义模型和误差模型两部分,其误差模型采用RBF神经网络进行补偿,得到其估计信息,神经网络的输出权值根据Lyapunov稳定性理论采用自适应算法进行调整。所设计的神经网络补偿自适应控制器解决了不确定性机器人动力学系统控制器设计的不确定性问题,同时,通过定义Lyapunov函数,证明了控制器能渐近、稳定地跟踪期望轨迹。机器人的3个关节在控制器的作用下,约在5 s时达到期望轨迹,神经网络约在5 s时逼近机器人动力学模型的误差模型,实验结果表明了机器人关节对期望轨迹具有良好的轨迹跟踪性能。     

基于节点剩余能量的分时分簇LEACH改进算法

针对无线传感网络中高效路由协议的设计问题,基于传感器节点的剩余能量提出一种分时分簇的改进LEACH算法。算法通过分时分簇方式,有效克服了传统LEACH算法中簇首数目不稳定的缺陷,且不会额外增加网络的能耗,使得簇首在整个网络中的分布以及网络的能量消耗更加均衡,有效延长了传感器网络的正常工作时间。仿真实验验证了改进算法的有效性。     

脉冲高电压的频率对电容分压器性能的影响

研制了一种测量脉冲高电压的电容分压器,从理论和实验两个方面分析了高电压脉冲的频率对电容分压器分压比的影响。并用此电容分压器测量了Tesla变压器型强流电子束加速器的谐振特性波形,测量结果与理论分析一致。     

基于BP神经网络的空中目标威胁排序

研究了BP神经网络算法对空中目标进行威胁排序的方法.水面舰艇对空防御作战中,舰载平台多传感器系统获得空中目标属性信息不完全,利用BP神经网络建立目标各属性权值的分配模型,通过大量的实例对模型进行训练,可以使所获得的空中目标属性信息得到充分利用,从而得到基本符合战场环境的客观的空中目标威胁排序.     

An INS/GNSS integrated navigation in GNSS denied environment using recurrent neural network

In view of the failure of GNSS signals, this paper proposes an INS/GNSS integrated navigation method based on the recurrent neural network (RNN). This proposed method utilizes the calculation principle of INS and the memory function of the RNN to estimate the errors of the INS, thereby obtaining a continuous, reliable and high-precision navigation solution. The performance of the proposed method is firstly demonstrated using an INS/GNSS simulation environment. Subsequently, an experimental test on boat is also conducted to validate the performance of the method. The results show a promising application prospect for RNN in the field of positioning for INS/GNSS integrated navigation in the absence of GNSS signal, as it outperforms extreme learning machine (ELM) and EKF by approximately 30% and 60%, respectively.     

Effect of microstructure on short pulse duration shock initiation of TATB and initial response mechanism

Micro-TATB particles with different sizes and 3D nanoporous TATB architectures with different specific surface areas were prepared through recrystallization to study short pulse duration shock initiation properties by electric gun technology. For micro-TATB, the initiation threshold significantly decreases with TATB average size ranging from 79.7 μm to 0.5 μm. For 3D nanoporous TATB architecture, the initiation threshold decreases and then increases with specific surface areas increased from 9.6 m²/g to 36.2 m²/g. The lowest initiation thresholds are obtained for the micro-TATB with average sizes of 1.3 μm and 0.5 μm, and 3D nanoporous TATB architecture with specific surface area of 22.4 m²/g. The shock initiation thresholds of micro-TATB and 3D nanoporous TATB architectures show significantly decreases with the porosity increased. The decomposition reaction and thermal conductivity properties were further investigated to understand the initial response mechanism. High porosity provides more collapse sites to generate high temperature for formation of hot spots. The low thermal conductivity and decomposition temperature could enhance the formation and ignition of the hot spots, and initial decomposition reaction of TATB. The effect of the decomposition temperature is higher than that of the thermal conductivity on the shock initiation properties. The enhanced decomposition reaction could promote energy release and transfer process from the ignition to the combustion. This work offers a new insight to understand the effects of microstructure on the shock initiation properties and the initial response mechanism of TATB.