共查询到20条相似文献,搜索用时 203 毫秒
1.
2.
基于模糊距离的核电厂瞬态分段识别方法 总被引:1,自引:0,他引:1
近年来发展的核电厂瞬态识别技术,可为操纵员提供处于发展阶段的故障信息,有助于了解核电厂状态并及时采取相应的操作动作,保证核电厂的安全运行。将瞬态过程曲线分为两段,前段利用聚类方法用于快速识别,后段利用提取的瞬态过程的特征进行更准确的识别。利用待识别瞬态与参考瞬态间的模糊距离描述二者的相近程度,可以消除噪声等扰动的影响,并得到更符合认知习惯的结果。利用高温气冷堆核电厂仿真机的故障数据验证瞬态识别方法的有效性。 相似文献
3.
计算机画面是数字化核电站人机界面的基本组成元素,画面的复杂程度会影响操纵员对核电站情况的掌握。为对单幅画面进行快速有效的复杂度定量评价,本文提出了一种基于图像熵的定量评价方法。首先对画面做图像化处理,并转化为灰度图,然后利用图像熵的定义,计算整个画面的熵值,并将其作为画面复杂度的度量。实验结果表明,图像熵作为画面复杂度的定量评价指标,与人工评价结果具有一致性,能反映人对画面复杂度的综合感受。此方法可应用于实际工程设计,特别是在设计初期不具备实验评价和专家评价的条件时,用来对画面进行复杂度测量,可避免画面过度复杂、改善人机交互。 相似文献
4.
保护轴承是电磁轴承结构的最后一道安全屏障。由于拆机检查成本较高,且因为保护轴承的特殊性,拆机后单独对保护轴承检查难以判断其还能否继续工作,迫切需要一种在线评估方法。本文首先开展电磁轴承高速跌落试验,直到某型号保护轴承完全失效。记录每次高速跌落前转子低速跌落过程中的位移数据。基于上述数据,分别应用多尺度排列熵、马氏距离、多尺度模糊熵等方法,研究保护轴承随着高速跌落次数增加的衰退规律。研究发现,应用多尺度模糊熵指标可反映多次高速跌落后保护轴承性能的衰退,实现对保护轴承性能在线评估。马氏距离指标也可用于辅助判断,但效果不如多尺度模糊熵方法。而多尺度排列熵指标不适合这一应用。 相似文献
5.
根据高温气冷堆核电站计算机化运行规程系统的设计准则,给出了高温气冷堆核电站计算机化运行规程的总体设计方案,指出计算机化运行规程系统的一个重要作用就是提供规程入口选择。高温气冷堆核电站的异常事件处理规程是基于事件的,因此选择规程入口的关键在于异常事件的识别。为解决该问题,采用具有图形描述能力和严密数学理论的模糊Petri网,构建了异常事件识别专家系统。相较于传统方法,模糊Petri网结构化特性和知识表达能力更强,推理效率大幅提高,便于计算机编程实现。通过典型异常事件识别的仿真,表明所构建的异常事件识别专家系统是合理可行的,为高温气冷堆核电站计算机化运行规程系统的研制打下了基础。 相似文献
6.
针对核级闸阀卡滞故障,提出一种基于运行过程变量特征分析的闸阀故障诊断方法。闸阀开关运行过程往往包含故障特点及变化规律,因此该方法首先利用Shannon熵对闸阀开关过程振动信号功率谱进行信息化度量,计算出功率谱熵均值作为目标过程变量,分析闸阀健康情况下和故障情况下的目标过程变量的特征变化,进而划分故障区域和非故障区域,对闸阀进行故障诊断。最后基于核级闸阀实验,对该方法进行实验验证,结果表明该方法能够有效地诊断出核级闸阀故障,并且该方法具有一定的故障预测能力。因此该方法的使用能够降低因为闸阀卡滞故障造成的核设施事故发生概率,同时该方法能够用于其他领域闸阀故障诊断。 相似文献
7.
针对核级闸阀卡滞故障,提出一种基于运行过程变量特征分析的闸阀故障诊断方法。闸阀开关运行过程往往包含故障特点及变化规律,因此该方法首先利用Shannon熵对闸阀开关过程振动信号功率谱进行信息化度量,计算出功率谱熵均值作为目标过程变量,分析闸阀健康情况下和故障情况下的目标过程变量的特征变化,进而划分故障区域和非故障区域,对闸阀进行故障诊断。最后基于核级闸阀实验,对该方法进行实验验证,结果表明该方法能够有效地诊断出核级闸阀故障,并且该方法具有一定的故障预测能力。因此该方法的使用能够降低因为闸阀卡滞故障造成的核设施事故发生概率,同时该方法能够用于其他领域闸阀故障诊断。 相似文献
8.
《核工程研究与设计》2008,(3)
在核电站系统中应用模糊控制技术是控制技术发展的新课题,研究分析国内外核电站系统中的模糊控制技术的应用发展是十分必要的。本文分析了模糊控制在核电站系统中的应用,分析结果表明模糊控制可以很好地提高核电站系统运行的稳定性和安全性,是一种有效并且可行的先进控制方法。国外核电站系统中应用成功的模糊神经网络技术融合了模糊控制与神经网络技术的优点,是一种新兴的控制技术,研究表明,在核电站系统中应用模糊神经网络技术可以大大提高反应堆运行的安全性和可靠性,具有广阔的应用前景。本文对模糊控制、模糊神经网络技术在核电站系统中应用的研究成果进行了全面回顾和总结,并探讨了在应用研究和实践中需要重点解决的问题。 相似文献
9.
10.
11.
In order to help nuclear power plant operator reduce his cognitive load and increase his available time to maintain the plant operating in a safe condition, transient identification systems have been devised to help operators identify possible plant transients and take fast and right corrective actions in due time. In the design of classification systems for identification of nuclear power plants transients, several artificial intelligence techniques, involving expert systems, neuro-fuzzy and genetic algorithms have been used. In this work we explore the ability of the Particle Swarm Optimization algorithm (PSO) as a tool for optimizing a distance-based discrimination transient classification method, giving also an innovative solution for searching the best set of prototypes for identification of transients. The Particle Swarm Optimization algorithm was successfully applied to the optimization of a nuclear power plant transient identification problem. Comparing the PSO to similar methods found in literature it has shown better results. 相似文献
12.
利用可信性模糊回归模型研究核电厂操纵员事故响应时 总被引:1,自引:0,他引:1
利用模糊数学中的模糊数概念,采用可信性模糊回归模型研究核电厂操纵员的事故响应.对影响操纵员事故响应时间的绩效形成因子PSF进行了定量化的分析,得到了核电厂操纵员事故响应时间的可信性模糊回归模型定量计算公式.对所得到的结论进行了相应的分析,说明了在小样本情况下所采用研究方法的正确性.研究方法不仅对核电厂的安全运行可以提供相应的参考借鉴而且可以推广到其他研究领域. 相似文献
13.
The classification of objects or patterns is an important area of research with practical applications in a variety of fields. In this paper we are interested in the classification of signal transients for the reliable monitoring and timely diagnosing of nuclear components and systems. These represent fundamental tasks for the operation, control and accident management of nuclear power plants. The problem is tackled within a fuzzy clustering approach. The choice of the metrics upon which the clustering is based is critical for obtaining geometric clusters in the features space as close as possible to the real physical classes. In this respect, here the a priori known information regarding the true classes to which the objects belong will be exploited to select, by means of an evolutionary algorithm of literature, an optimal metrics for the clustering. In case the classification thereby obtained were still unsatisfactory, an iterative procedure is used to split the less compact physical classes in further subclasses. 相似文献
14.
Ünal Kurt 《Journal of Nuclear Science and Technology》2013,50(10):1241-1255
The location selection for nuclear power plant (NPP) is a strategic decision, which has significant impact on the economic operation of the plant and sustainable development of the region. This paper proposes fuzzy TOPSIS and generalized Choquet fuzzy integral algorithm for evaluation and selection of optimal locations for NPP in Turkey. Many sub-criteria such as geological, social, touristic, transportation abilities, cooling water capacity and nearest to consumptions markets are taken into account. Among the evaluated locations, according to generalized Choquet fuzzy integral method, Inceburun–Sinop was selected as a study site due to its highest performance and meeting most of the investigated criteria. The Inceburun-Sinop is selected by generalized Choquet fuzzy integral and fuzzy TOPSIS I?neada–K?rklareli took place in the first turn. The Mersin–Akkuyu is not selected in both methods. 相似文献
15.
The natural circulation boiling type SMR can experience flow instability during the startup transients due to the void reactivity feedback. A BWR-type natural circulation test loop has been built to perform the nuclear coupled startup transient tests for Purdue Novel Modular Reactor (NMR). This test loop is installed with different instruments to measure various thermal hydraulic parameters. The testing process can be monitored and controlled through PC with the assistance of LabVIEW procedure. The effects of power ramp rate on the flow instability during the nuclear coupled tests were investigated by controlling the power supply based on the point kinetics model with coolant void reactivity feedback. Two power ramp rates were investigated and the results were compared with those of the thermal hydraulic startup transients without void reactivity feedback. The time trace of power supply, system pressure, natural circulation rate, and void fraction profile are used to determine the flow stability during the transients. The results show that nuclear coupled startup transients also experience flashing instability and density wave oscillations. The power curves calculated from point kinetics model for startup transients show some fluctuations due to void reactivity feedback. However, the void reactivity feedback does not have significant effects on the flow instability during the startup procedure for the NMR. 相似文献
16.
17.
18.
19.
Los Alamos National Laboratory is a participant in the Integral System Test (IST) program initiated in June 1983 for the purpose of providing integral system test data on specific issues/phenomena relevant to post-small-break loss-of-coolant accidents, loss of feedwater and other transients in Babcock and Wilcox (B&W) nuclear plant designs. The Multi-Loop Integral System Test (MIST) facility is the largest single component in the IST program. MIST is a 2 × 4 [two hot legs and steam generators (SGs), four cold legs and reactor coolant pumps] representation of B&W lowered-loop reactor systems. It is a full-height, full-pressure facility with 1/817 power and volume scaling. Efforts are under way at Los Alamos to assess TRAC-PF1/MOD1 against data from the MIST facility.Calculations and data comparisons for TRAC-PF1/MOD1 assessment are presented for three transients run in the MIST facility. The energy removal and depressurization mechanisms in these tests are identified and the phenomena occurring in these tests compared. The tests analyzed are MIST Test 3109AA, the nominal small-break LOCA, Test 330302, a feed and bleed test with delayed high-pressure injection; and Test 3404AA, an SG tube-rupture test with the affected SG isolated. TRAC was able to predict these phenomena although the timing and magnitude of events were not always in good agreement.The MIST test have demonstrated the thermal-hydraulic phenomena expected to occur during transients in B&W nuclear plants. Because of scaling atypicalities, test results cannot be extrapolated directly to plant conditions. Although the phenomena were demonstrated in the MIST tests, there may be differences in the timing, magnitude and sequences of events in plant transients. Assessment calculations, three of which are presented here, have shown that the TRAC computer code can predict the major trends and phenomena occurring during the MIST tests with reasonable qualitative agreement. This includes complex sequences of events. Reasonable qualitative agreement is defined as meaning that major trends are predicted correctly, although TRAC values are frequently outside the range of data uncertainty. These assessment results, taken with assessment results from other facilities at a wide range of scales, provide us with confidence that the TRAC code can adequately simulate the transient phenomena possible in B&W nuclear plants. 相似文献
20.
针对蒸汽发生器U形传热管泄漏,本文提出了一种基于时间序列神经网络对蒸汽发生器传热管泄漏程度进行诊断研究的方法。首先,对核电厂蒸汽发生器U型传热管泄漏进行机理分析,构建其数学模型,提取其泄漏的直接特征参数,再依据Fisher得分法,提取其间接特征参数;其次,通过滑动时间窗口法从预处理后的时间序列数据中生成数据样本,作为时间序列神经网络的输入,并以蒸汽发生器U形传热管泄漏程度信息为标注,基于反向传播(BP)算法对五层神经网络系统进行训练,得到蒸汽发生器U形传热管泄漏的时间序列神经网络模型;最后,模拟核电厂运行过程蒸汽发生器U形传热管泄漏时的时间序列测试数据。仿真结果表明,时间序列神经网络对演变事件的处理具有较好的有效性和较高的泛化能力,对故障程度的诊断研究具有参考价值。 相似文献