基于神经网络的智能刀具状态检测系统

可靠的在线刀具磨损状态检测是柔性制造系统、计算机集成制造系统以及自动化机床必不可少的一个环节。文中论述了用反传神经网络与一类模糊神经网络分析处理由力传感器和声发射传感器所测得的刀具状态信号，识别出刀具的磨损情况，从而进一步实现刀具磨损状态的在线检测，控制自动机床及时更换刀具。本研究对四种规格的钻头的磨损情况进行了全程检测，并比较分析了反传神经网络与模糊神经网络对这一问题的有效性。实验结果表明，这两种方法对处理刀具磨损状态检测均有显著的效果与很高的准确性。用一类模糊神经网络处理多传感器信息是实现刀具状态在线检测的一个极为有效的方法。     

Optimized Fuzzy Clustering Method for Health Monitoring of Shield Tunnels

Since health monitoring of shield tunnels generally employs multiple sensors belonging to different types,a fine analysis on massive monitoring data,as well as further quantitative health grading,is really challenging.An optimized fuzzy clustering analysis method based on the fuzzy equivalence relation is proposed for health monitoring of shield tunnels.Clustering results are auto-generated by using fuzzy similarity-valued map.The results follow the idea of unsupervised classification.Moreover,a convenient new health index HI is proposed for a fast tunnel-health grading.A case study on Nanjing Yangtze River Tunnel is presented to validate this method.Three types of indicators,namely soil pressure,pore water pressure and steel strain,are used to develop the clustering model.The clustering results are verified by analyzing the engineering geological conditions;the validity and the efficacy of the proposed method are also demonstrated.Further,the fuzzy clustering analysis also represents a potential for identifying abnormal monitoring data.This investigation indicates the fuzzy clustering analysis method is capable of characterizing the fuzziness of tunnel health,and beneficial to clarify the tunnel health evaluation uncertainties.     

利用偏振图像加权融合及CLAHE算法的水下成像方法

针对传统基于偏振差分原理的水下光学成像方法中目标退偏振特性差异引起的图像中局部反射光损失的问题,本文提出了基于偏振图像加权融合与限制对比度自适应直方图均衡（Contrast Limited Adaptive Histogram Equalization, CLAHE）算法的水下成像方法。一方面,将原始水下图像分解为偏振光强图像和非偏振光强图像,根据不同退偏振特性目标在两幅图像中的灰度值分布特点,设计相应的权重因子,对两幅图像进行加权融合。从而实现在压缩原始水下图像中散射光的同时,保留更多目标反射光,提升整体目标反射光在融合图像中所占的比例。另一方面,为了进一步提升融合图像的对比度,利用限制对比度自适应直方图均衡算法对融合图像进行处理。该算法能够在提升融合图像对比度的同时,有效避免图像噪声的放大。实验结果表明,相比于传统的偏振差分方法以及独立的直方图均衡化算法,本文提出的算法能够有效提升水下图像的清晰度和对比度。     

Data-driven prescribed performance control for satellite with large rotational component

In this paper, the high precision attitude control for satellite with large misaligned rotational component is investigated, proposing a novel model-free prescribed performance adaptive control (MF-PPAC) method. Based on the model-free adaptive control (MFAC) strategy, high-precision attitude control is achieved depending on the system measurement rather than the spacecraft mathematical model, which demonstrates the superiority in handling nonlinearity and uncertainty of the spacecraft system, especially for those with unbalance of the rotational component. Furthermore, the transient and the stable-state behavior of the tracking error using MFAC is constrained in the prescribed performance bounds and converges to zero gradually with the utilization of prescribed performance function (PPF) and error transformation method. Finally, the convergence and boundedness of the system error, the bounded-input bounded-output (BIBO) stability of the proposed MF-PPAC is demonstrated by the contraction mapping theory. Simulation and comparison with disturbance-observer-based PD control and MFAC illustrate the effectiveness of the proposed method.     

基于改进无模型自适应算法的涡扇发动机限制保护控制方法

针对发动机限制保护控制问题,提出了一种基于数据驱动的改进无模型自适应限制保护控制方法。以主回路闭环系统为设计对象,通过在常规无模型自适应控制律的准则函数中增加误差变化率,使超限保护系统具有更快的响应速度,给出了改进后系统的稳定性条件,并采用临界比例度法进行了控制器参数整定。仿真结果表明:在不同工作点,所设计的改进无模型自适应限制保护控制器相比常规无模型自适应限制保护控制器,最大超限平均减小2.97%,响应时间平均缩短2.30s,实现了发动机超限后的迅速回调,保证了发动机系统的安全运行。     

基于综合模糊聚类算法的液体火箭发动机故障诊断

基于液体火箭发动机正常及故障状况数据的完备程度和数据质量的不断提高,提出一种基于数据驱动的综合模糊聚类算法用于故障诊断。采用模糊c均值(FCM)算法对已知正常样本数据进行聚类得到最优的聚类中心,将所得到的聚类中心作为先验样本数据用于传递闭包法最优分类结果的选择从而得到故障检测结果,该算法只需要少量的正常先验样本数据就能快速、准确的检测出故障;随后采用FCM算法进行故障分类,可以根据现有的故障数据库进行聚类得到对应的故障类型,并且可以给出故障幅值范围。模型仿真结果表明:该算法对故障的检测率可达968%,故障隔离率达到94%。某型液体火箭发动机实际试车数据结果表明:该故障诊断算法能够准确及时的检测并隔离出故障。     

基于特征模型的火箭发动机伺服控制系统设计

以新型大推力火箭发动机为研究对象,提出了基于特征模型的伺服系统控制器设计方法。首先,介绍了特征建模理论并讨论了特征模型参数范围;其次,采用人工蜂群算法实时估计火箭发动机伺服系统特征模型参数,使其满足特征模型输出与实际系统输出特性等价条件;最后,使用黄金分割自适应控制律保证系统在参数估计过程中的闭环稳定性,同时引入前馈跟踪控制律,逻辑积分控制律和逻辑微分控制律使伺服控制系统快速、精确跟踪线位移指令并改善动态性能。仿真结果表明,设计的火箭发动机伺服控制系统指令跟踪精度高,动态特性良好,鲁棒性强。     

截断分布下广义失效概率的可靠性分析方法

提出基于随机变量为截断分布和失效域模糊下的结构可靠性分析方法。由于常规的可靠性分析方法不能直接用于截断分布情况下广义失效概率的计算,因此,先将截断分布情况下的可靠性分析模型转化为非截断分布情况下的多模式并联系统模型,在此基础上引入模糊失效域的隶属函数,将截断分布情况下的模糊可靠性分析问题转化为一般的随机可靠性问题,利用Monte Carlo法和重要抽样法求得广义失效概率。给出了方法的实现步骤和原理,并用不同算例验证了方法的合理性与可行性。     

Optimization Based on Convergence Velocity and Reliability for Hydraulic Servo System

This article presents an optimal hybrid fuzzy proportion integral derivative (HFPID) controller based on combination of proportion integral derivative (PID) and fuzzy controllers, by which the parameters could be evaluated by global optimization either in convergence velocity or in convergence reliability. Focusing on the nonlinear factors of hydraulic servo system, this article takes advantage of PID and fuzzy logic controller integrated with scaling factors to acquire precise tracking performances. To further improve the performances, it provides new developed optimization with rapid convergence to attain reliable approach probability. Focusing on the performance indictors of evolutionary algorithm, this article presents a new technique to predict reliability of the optimization algorithm. Statistics authenticates the effectiveness and robustness of the optimization. Further, many simulation and experimental results indicate that the optimal HFPID could acquire perfect immunity against parametric uncertainties with external disturbance.     

公共场所火灾公众责任险风险评估及核保模型研究

介绍了目前我国公共场所火灾的现状及火灾公众责任险强制性实施的必要性.通过建立公众场所火灾风险评价指标体系,运用多层次模糊综合评价理论对公众场所火灾危险性进行综合评估.最后依据评估结果对火灾公众责任险费率进行浮动,确定科学合理的费率水平和责任限额.