Monitoring power supply current and using a neural network routineto diagnose circuit faults

As a circuit is tested, the current drawn from a power supply can vary as different functions are invoked by the test. The current draw can be plotted against time, showing a characteristic trace for the test performed. Sensors in the ATS power supply can be used to monitor the current flow during test execution. Defective components can be classified using a Neural Network according to the pattern of variation from the “trace” of a good card. This can be performed as a background function, with the network gaining in accuracy over time. This paper discusses the Neural Network Routine for diagnosing circuit faults using monitored power supply current     

Force measurement using strain-gauge balance in shock tunnel based on deep learning

When a force test is conducted in a shock tunnel, vibration of the Force Measurement System (FMS) is excited under the strong flow impact, and it cannot be attenuated rapidly within the extremely short test duration of milliseconds order. The output signal of the force balance is coupled with the aerodynamic force and the inertial vibration. This interference can result in inaccurate force measurements, which can negatively impact the accuracy of the test results. To eliminate inertial vibration interference from the output signal, proposed here is a dynamic calibration modeling method for an FMS based on deep learning. The signal is processed using an intelligent Recurrent Neural Network (RNN) model in the time domain and an intelligent Convolutional Neural Network (CNN) model in the frequency domain. Results processed with the intelligent models show that the inertial vibration characteristics of the FMS can be identified efficiently and its main frequency is about 380 Hz. After processed by the intelligent models, the inertial vibration is mostly eliminated from the output signal. Also, the data processing results are subjected to error analysis. The relative error of each component is about 1%, which verifies that the modeling method based on deep learning has considerable engineering application value in data processing for pulse-type strain-gauge balances. Overall, the proposed dynamic calibration modeling method has the potential to improve the accuracy and reliability of force measurements in shock tunnel tests, which could have significant implications for the field of aerospace engineering.     

信号仿真系统离散信号发送功能研究

离散量信号是民用飞机地面模拟试验中不可缺少的信号之一。基于某型号飞机地面模拟试验的需求,提出了简单可靠的离散信号电路设计方案,利用CMOS管和光电耦合器作为输入输出隔离器件,将TTL电平转换成离散量信号。采用电路仿真软件Multisim进行仿真分析,并结合某型号铁鸟试验验证。仿真分析及试验结果表明,该电路满足某型号飞机地面模拟试验对离散量信号的要求。     

龚氏桥全可控整流电路

论述桥式和全波相结合的单相可控整流电路,该电路突破可控整流电路最大输出电流点和最佳功率因数点只能在最高输出电压点上的传统,可在低电压输出电流达到桥式电路的2倍以上。桥全可控整流电路只要在桥式电路上增加一只整流或可控整流器件即可获得,不但吸取全波和桥式二类经典电路的优点,而且把二类电路包含在内,成为性能最好、电路数量最多、最高形式的单相可控整流电路。     

基于球体描述Vague决策的模拟电路故障诊断方法(英文)

提出一种基于球体描述Vague决策的模拟电路故障诊断方法。首先,采用小波变换预处理待测电路输出的电压故障特征。然后,每类样本集训练成一个最小超球体。最后,测试样本由本文定义的模糊决策规则进行判断,其中该规则由测试样本和描述球体中心之间的Vague加权距离得到。该模糊决策规则融合了测试样本正反隶属度值和描述球体的权值,可以有效地处理不确定信息。本文从理论上证明了该决策方法的可靠性。将该诊断方法应用于两种实际电路的测试,并与其他两种诊断方法进行对比。实验结果表明本文方法取得了良好的诊断性能,并减少诊断时间。     

Excitation control of a synchronous generator using a lookup table

A scheme involving the use of a lookup table is developed for the excitation control of a synchronous generator. The proposed control scheme, generator speed deviation, and acceleration deviation are taken as the input signals. These input signals are sampled and converted to linguistic terms before they are fed into the controller. The controller generates the desired output (control) signal by using a set of production rules (if-then rules) that are based on previous experience to relate the input signals to the output. The output signal is converted from linguistic terms to a numerical value before it is sent to the excitation system of the synchronous machine. To demonstrate the effectiveness of the proposed control scheme, digital simulations of a synchronous generator subject to a three-phase fault under different operating conditions were performed. It was found that the controller can improve the dynamic performance of a synchronous generator over a wide range of operating conditions. Since the controller does not require model identification, it is computationally efficient and is suitable for online excitation control, using a microcomputer     

盒式六分量应变天平热态试验气动结构特性

为了探索盒式六分量应变天平热态试验时三维力传感器输出信号异常的现象,从四分量机械单台式天平与盒式六分量应变天平的气动布局、主体结构及热态试验方面展开了对比分析,受结构及安装制约,盒式六分量应变天平无法消除或补偿高温热流在稳定段上产生的热应力.为保留喷管模型试验器最具特色的高温试验功能,利用对称布置方案,调换燃油加温器至稳定段出口.热态试验证明:在增强天平的平衡性、减少天平机械连接、简化燃油加温器安装和调试的情况下,天平的推力测量值从异常的负值恢复正常,解决天平输出信号异常问题,满足天平热态试验性能要求.      

基于LMD与AO-PNN的中介轴承故障诊断方法

针对航空发动机中介轴承受噪声干扰大、传递路径复杂导致采用传统方法难以进行故障诊断的问题,提出了一种基于局部均值分解（LMD）与相关系数-能量比-峭度准则、结合天鹰座优化算法（AO）优化概率神经网络（PNN）的中介轴承故障诊断方法。使用LMD对传感器采集的振动信号进行分解;利用相关系数-能量比-峭度准则判决筛选分解得到的PF分量,重构筛选后的信号;计算重构信号的多尺度排列熵（MPE）,以构建特征向量;通过AO优化的PNN的平滑因子,将优化后的神经网络用于中介轴承的故障诊断。基于中介轴承故障试验数据对诊断结果进行了分析,结果表明：提出的方法可以有效诊断高背景噪声、复杂路径干扰下的航空发动机中介轴承的典型故障,与粒子群优化的概率神经网络方法（PSO-PNN）和传统的PNN方法相比,其诊断准确率分别提高了3.875%和8.125%,具有较好的全局收敛性和计算鲁棒性。     

Tracking of conventional beamforming with hydrophone array ofvarying geometry

In conventional beamformers of a large towed hydrophone array of fixed linear array geometry the sensors may be displaced from their nominal positions due to various kinds of force on the array. The displacements are usually time varying and can severely degrade the performance of the beamformer. This problem is approached by restoring the sensor output signals before beamforming by adaptively tracking and compensating for the displacements. This approach does not require modifications of the conventional shipboard beamformer and hence can be used cost-effectively to upgrade existing conventional systems. Two adaptive algorithms are used for two different cases: known sensor moving trajectories and unknown trajectories with relatively small displacements compared with the intersensor spacing. Tracking performance of the algorithms is analyzed. Simulation results show that for known sensor trajectories the algorithm significantly improves the performance of the conventional shipboard beamformer whereas only limited improvement can be achieved when the trajectories are unknown     

基于逆系统方法的多输入多输出非高斯驱动信号生成

多输入多输出(MIMO)振动环境试验是振动试验的新方法,该方法比传统的单输入单输出(SISO)方法更真实地模拟了结构在实际工作下的振动环境。传统随机振动试验的频域方法所模拟的是平稳高斯信号,但是实际振动环境往往是超高斯的,且超高斯激励和高斯激励对结构的损害差异很大,因此对MIMO超高斯振动环境试验的研究十分重要。驱动信号的产生是振动环境试验的关键。提出一种基于逆系统的MIMO超高斯驱动信号生成方法。首先,根据给定的响应参考功率谱密度(PSD)和参考峭度值采用相位调节法生成参考响应超高斯伪随机信号;其次,利用逆系统方法生成超高斯伪随机驱动信号;最后,对伪随机驱动信号进行时域随机化处理得到超高斯真随机驱动信号。对一根两输入两输出的悬臂梁模型进行了仿真验证,结果表明,采用本文方法所得到的驱动信号加载在梁上后,其输出响应谱与给定参考谱之间的误差完全满足工程中常用的±3 dB的要求,而且峭度也与给定的参考值十分接近,证实了所提方法的有效性。     

基于神经网络的预膜雾化模型

为了实现对预膜雾化质量的快速预估，基于神经网络建立了以结构参数和工况参数为输入,SMD值为输出的预膜雾化模型。使用试验数据训练和测试网络模型,结果显示,模型在较宽的工作范围内具有较高的精度和较好的泛化能力。SMD预测值随输入参数的变化规律符合试验结论,可作为给定工况参数下预膜式雾化装置的结构参数优化依据。神经网络能够较好地学习预膜雾化过程中的隐含规律。随着供油压差的增大,预膜器逐渐出现阻雾化效应,导致其雾化效果比单喷嘴和直混式雾化均差。     

一种转台低速检测电路设计

转台低速性能的提高对转台低速检测方法提出了新的要求,本文针对转台低速检测要求设计了基于LS7266R1的转台低速检测电路,详细介绍了电路的工作原理和具体实现方法。该电路采用LS7266R1的增/减计数功能,以单片机为控制核心,通过对编码器细分信号的分频计数来实现速率转台指定角度间隔脉冲输出。经过调试验证,该电路可以在转台低速检测或定角度脉冲输出中应用,调试结果可以满足实际应用要求。     

Bidirectional DC-to-AC inverter with improved performance

Switch-mode DC-to-AC inverters using DC-to-DC converter topology have many advantages over the traditional bridge-type inverter. A bidirectional power circuit combined with a nonlinear robust control is proposed to form a high performance inverter. The output voltage of the inverter can be stabilized regardless of large changes in input voltage and output current. The distortion near the zero crossing point can be minimized. The load of the inverter can be resistive, inductive, or capacitive. Simulation results and experimental verification are provided     

基于域对抗门控网络的变工况刀具磨损精确预测方法

刀具磨损的精确预测对保证零件加工质量、提高生产效率和降低制造成本具有重要作用。在实际加工过程中,切削参数、刀具几何参数、刀具材料等工况复杂多变,工况信息和刀具磨损量对监测信号的耦合作用为刀具磨损的精确预测带来了很大挑战。针对以上问题,提出了一种基于域对抗门控网络（DAGNN）的变工况刀具磨损精确预测方法。引入工况分类网络并利用无磨损量标签样本,通过域对抗和门控过滤机制自适应地从不同工况的原始监测信号中提取表征刀具磨损且对工况变化不敏感的关键信号特征。对信号特征提取网络和刀具磨损预测网络进行迭代优化,从而实现变工况刀具磨损的精确预测。实验结果表明：相比已有的方法,本文方法能够利用少量带磨损量标签的目标工况样本实现刀具材料和刀具直径变化情况下的刀具磨损量精确预测,预测精度大幅提高。     

一种高速数字复数乘加器的研制

复数乘加运算是实时数字信号处理系统经常使用的主要运算之一,随着实时数字信号处理的发展,复乘加的运算速度要求越来越高。本文研制了一种基于复杂可编程逻辑器件(CPLD)的高速数字复乘加器,其复乘加的次数可以用外部的输入信号控制,还可以同时共轭输出。该复乘加器成本低,编程灵活,可根据不同的要求广泛应用于各种数字信号处理系统中。     

应用神经网络模型评价社保基金运营效果方法研究

社会保障基金是社会成员普遍关注的资金,他的利用关系到全社会成员的公共利益。因此,社会保障基金运用效果的评价问题一直是社会各界争论的焦点,正确评价其运用效果是值得学术界探讨的问题。运用神经网络模型对社会保障基金运用效果进行评价是对神经网络模型的应用及对社会保障基金运用效果的评价进行尝试和探讨。     

飞行控制系统的输出反馈最优设计

本文在频域范畴内,利用输出反馈方法论述了在二次型性能指标下多变量线性最优调节器的控制问题,通过把多变量系统的前馈解耦控制与最优控制结合起来,得到了最优控制解的频域形式。这种最优控制规律既可使系统的能耗和输出偏差综合最优,具有较好的抗干扰性,又可满足给定的时域性能指标。方法简单,求解方便,便于工程应用。作为例子,文中对某纵向飞行控制系统进行了最优设计。     

TC18钛合金疲劳断裂过程声发射信号特征分析

声发射技术通过实时监测结构服役过程中发出的声发射信号,判断结构是否出现损伤,是一种重要的在线监测损伤的技术。为了明确TC18钛合金在疲劳试验中产生微裂纹、裂纹扩展及断裂等过程中声发射信号的特性,设计TC18钛合金试验件,进行其疲劳试验并全程采集声发射信号;采用参数分析方法,得到声发射信号在时域、频域方面的参数特征。结果表明:在裂纹萌生及扩展阶段,声发射信号幅值为40~65dB,低于相同条件下铝合金的信号幅值;在200~280kHz频段上,裂纹萌生阶段与后续过程的能量分布存在较大差异。结合上述研究结果,给出TC18钛合金试验件声发射监测的参考原则。     

用热流探针测量激波速度

激波速度测量是激波管和激波风洞运行状态的一个重要参数,压电传感器或光学方法测速系统成本高,而传统电离探针在激波马赫数较低、波后温度达不到空气电离程度的情况下无法满足实验要求。提出了一种使用同轴热电偶作为测速探针来测激波速度的方法,弥补了电离探针在激波马赫数较低时的不足。介绍了同轴热电偶探针测速原理,并设计了测量激波速度的系统电路。通过信号放大电路锁定激波冲激信号,触发脉冲信号发生电路,实现了一种单通道、多测点的激波风洞测速系统。分别开展以温度与热流为触发信号的风洞实验,结果表明只有使用热流信号才能满足激波测速的时间要求。     

Detection of long-duration narrowband processes

Detecting long, weak signals that are narrowband but of unknown frequency structure is an important signal processing challenge, with many applications in remote sensing and process monitoring. An ad hoc scheme is developed. Its stages include the discrete Fourier transform (DFT), a multiresolution decomposition in the frequency domain, and a generalized likelihood ratio test (GLRT). The computational load is light, and the performance is remarkably good. This is so not just in the original narrowband situation, but also, due to an inherent adaptivity to the data, in the detection of signals that are relatively broadband in nature. Generalizations are given to constant false alarm rate (CFAR) operation in both prewhitened and unwhitened cases, and to the detection of multiband signals. As regards the last, it is discovered that there is little loss from overestimating the number of bands