旋转机械故障诊断知识的表示推理

文中介绍了旋转机械故障诊断知识常用的框架和规则表示方法以及专家系统中常用的不精确推理，深入论述了规则的结构，功能和类型，讨论了不精确推理在实际应用中存在的问题，结合规则表示方法对不精推理算法进行了改进，提高了故障诊断的能力。     

火电厂锅炉运行故障诊断专家系统的研究

在火电厂锅炉运行故障诊断中,难以建立对象的精确数学模型,且故障征兆和故障原因之间具有一定的模糊性,采用模糊专家系统可以避免建模的困难,并能在信息不确定的情况下给出合理的解释。给出了该系统的结构,简单介绍了其各模块的功能。研究了模糊事实的表示和基于规则的知识的表示,介绍了推理过程,给出了汽包满水故障诊断实例。该系统通过检测实时数据库中出现的征兆,生成相应的模糊事实,结合规则库中的知识,诊断出可能出现的故障。     

分布式水电机组故障诊断集成专家系统的研究

针对水电机组故障诊断的多样性和复杂性，将分布式人工智能技术引入机组故障诊断技术的研究，提出一种适用于水电机组的分布式故障诊断专家系统结构和组织方法；并在此基础上，利用神经网络技术、可视化技术和模糊技术，提出了一种新的故障诊断集成知识表示方式和推理生策略，并已应用于某水电厂分布式故障诊断集成专家系统中。     

专家系统在发动机故障诊断中的应用

本文介绍了专家系统的结构及在发动机故障诊断中的应用。该系统将多种知识表示方法及多种故障推理策略融为一体。可以在实际诊断过程中提供给用户重要的辅助诊断，同时由于增加了多媒体的技术，因而又是学习故障诊断的好帮手。     

基于聚类分析与加权模糊逻辑的汽轮机组振动故障诊断方法研究

针对汽轮机组振动故障诊断中故障征兆的使用问题,提出了一种基于聚类分析与加权模糊逻辑相结合的故障诊断方法。利用振动的频谱特征对振动故障的几种常见故障模式进行分类,形成故障模式类,从而可以在故障模式类层次区分开属于不同性质的故障模式,解决类间的识别问题,进而缩小故障模式的识别范围。对于同一故障类中的故障模式,采集不同类型的故障征兆,利用粗糙集理论建立故障诊断决策表,提取对故障识别有贡献的故障征兆构建故障诊断规则,再应用知识依赖度为故障诊断规则的前提条件分配权重,克服了主观分配权重存在的不足,减少了故障诊断推理过程中的不确定性影响。再应用加权模糊逻辑对故障诊断规则进行推理,根据推理结果对故障模式进行识别。该方法既充分利用了振动的频谱特征这一重要故障征兆作为故障诊断的初步判断依据,又综合利用了反映故障不同方面信息的不同类型的故障征兆,从而做到更加准确地进行故障识别。     

电力系统继电保护专家系统的构建

针对电力系统继电保护故障诊断中存在的信息不完备和不确定性等问题,构建了电力系统继电保护专家系统。着重论述了该系统的构建,对结构、推理规则和数据采集等进行了分析,结果表明能很好地解决电力系统继电保护中的一些故障问题,提高了故障诊断的准确度,从而确保电力系统的可靠运行。     

粗糙集理论和贝叶斯网络在汽轮机振动故障诊断中的应用

针对实际的汽轮发电机组振动故障诊断中常存在冗余和不确定性信息这一问题,基于智能互补融合的思想,将粗糙集理论与贝叶斯网络有机结合在一起,提出了一种汽轮机振动故障诊断新方法.利用粗糙集信息表约简方法实现对故障特征的约简,以获取最小诊断规则.基于最小规则的贝叶斯网络模型可以有效降低网络构造的复杂性,同时利用贝叶斯网络来发现节点间的潜在关系,解决故障诊断过程中的不确定推理问题,从而提高诊断效率.最后,进行了故障实例分析,结果证明了该方法的有效性.     

基于模糊关系矩阵推理的发动机故障诊断专家系统

描述了一个在ＷＩＮＤＯＷＳ环境下开发的故障诊断专家系统的设计与实现,并介绍了有关模糊知识表示与推理的研究工作,详细介绍了该系统结构,知识表示与获取,推理机制的设计实现方法。     

基于不完备数据的汽轮机组故障诊断的粗糙集方法

通常从不完备数据中获取规则要比从完备数据中获取规则困难，为了在故障诊断信息不完备的情况下提取简单有效的诊断规则，提出了一种从不完备数据中获取确定和不确定诊断决策规则的粗糙集方法。以某汽轮发电机组振动故障为例给出了该方法的具体实现过程，并验证了该方法的有效性。     

柴油机故障的混合智能诊断方法研究

本文提出了一种综合智能故障诊断的方法，即首先利用常规的信号检测和分析手段，获得一些代表故障特征的时域或频域参数值，根据参数值确定故障的隶属度，利用已经训练好的模糊神经网络传递故障的隶属度，再根据网络输出的隶属度大小确定故障原因，然后利用规则推理滤除可疑原因，得到最终诊断结果。最后以6135ZC柴油机故障诊断为例，验证了该方法的有效性。     

Interpolation of missing wind data based on ANFIS

Measured wind data is one of the key input data for wind farm planning and design. There are always some missing and invalid data in wind measurement, which poses the main challenges for wind energy resources assessment. In this paper, the rules of integrity check and reasonableness check are introduced, then an adaptive neuro-fuzzy inference system (ANFIS) model is proposed, in which fuzzy inference algorithm are used to interpolate the missing and invalid wind data. A further comparison and analysis is given between the calculating result and measured data. Meanwhile Using methods of wind shear coefficient and ANFIS, 12 measured wind data sets from a wind farm in North China are interpolated and analyzed, respectively. The results proved the effectiveness of ANFIS.     

自适应模糊神经网络控制在锅炉过热汽温控制中的应用

常规的模糊控制系统不能自动地将专家知识经验转化为推理规则库,缺乏有效的方法来改进隶属度函数,而自适应神经模糊推理系统(ANFIS)将模糊逻辑和神经元相结合,采用反向传播算法和最小二乘法的混合算法来调整前提参数和结论参数,并能自动产生模糊规则.在此基础上提出了一种自适应模糊神经网络控制器,并将其应用于火电厂锅炉过热汽温控制中.结果表明:与常规的PID控制相比,该方法提高了锅炉汽温控制系统的动态稳定性和抗干扰性.     

竖向荷载作用下墙梁的弹塑性分析

通过分析总结近年来国内外对砖砌体的本构关系和破坏准则的理论研究成果,找出了较合理、适用的本构关系和破坏准则的组合,能较好地描述墙梁受力破坏的力学特性。并基于塑性理论,编制了“墙梁结构弹塑性有限元法计算程序”,对一些算例进行了验算,得到较好的结果。采用对比分析和图表显示的方法,得出在竖向荷载作用下,随着弹塑性的发展,墙体竖向压应力的变化规律。     

PG－PL调速器控制的小汽轮机振荡故障机理分析

本文推导了ＰＧ—ＰＬ调速器在故障状态下的数学模型，仿真分析了各种振荡故障的特征．可供诊断故障时参考。     

Impacts of electrode coating irregularities on polymer electrolyte membrane fuel cell lifetime using quasi in-situ infrared thermography and accelerated stress testing

In-line quality control diagnostics for roll-to-roll (R2R) manufacturing techniques will play a key role in the future commercialization of the polymer electrolyte membrane fuel cell (PEMFC) used in automotive applications. These diagnostics monitor the fabrication of the membrane electrode assembly (MEA), which detect and flag any non-uniformity that may potentially harm PEMFC performance and/or lifetime. This will require quantitative thresholds and a clear distinction between harmful defects and harmless coating irregularities. Thus, novel fuel cell hardware with quasi in-situ infrared (IR) thermography capabilities is utilized to understand how bare spots in the cathode electrode impact MEA lifetime. An accelerated stress test (AST) simulates chemical and mechanical degradation modes seen in vehicular operation. The actual open circuit voltage and rate of change of this voltage are used as in-situ indicators for MEA failure, enabling capture of the progression of failure point development. Bare spot coating irregularities located at the center of the electrode were found to have no impact on MEA lifetime when compared to a pristine MEA. However, MEA lifetime was found to be considerably shortened when these same irregularities are located at the cathode inlet and, especially, the anode inlet regions of the fuel cell.     

Optimization of the Thermal Efficiency of a Two-Phase Closed Thermosyphon using Active Learning on the Human Algorithm Interaction

Here, pristine and functionalized multi-walled carbon nanotubes with silver/water nanofluids were first synthesized. To investigate thermal performance of two-phase closed thermosyphon, thermal efficiency was experimentally obtained as a key parameter. To obtain optimal points in operational condition, the active learning method was employed in concentration ranges of 0–1 wt% as well as input power of 30–150 W which cannot be accessed. The active learning method is based on the fuzzy logic rules; here query synthesis and the measure human algorithm interaction (HAI) were used for learning. As the primary data obtained from experiments is small, this method was used to suggest the most optimal conditions. First, primary data obtained from experiments are given to the algorithm and then algorithm proposed some suggestions based on the maximum uncertainty. Subsequently, thermal efficiency is estimated based on fuzzy inference. Here, two mechanisms are employed as combined ones. The mentioned suggestions will be tested in the offered operational conditions. If the accuracy of the suggestions was confirmed by the obtained data, these data would be added to the primary ones. In fact, the used method can be considered in the area of HAI performing with the aid of experienced human simultaneously with intelligent algorithms. Meanwhile, the best working concentration to obtain the most optimum thermal efficiency obtained in the range 0.90 to 0.95 for both nanofluids.     

Developing a multipurpose sun tracking system using fuzzy control

The present work demonstrates the design and simulation of time controlled step sun tracking systems that include: one axis sun tracking with the tilted aperture equal to the latitude angle, equatorial two axis sun tracking and azimuth/elevation sun tracking. The first order Sugeno fuzzy inference system is utilized for modeling and controller design. In addition, an estimation of the insolation incident on a two axis sun tracking system is determined by fuzzy IF-THEN rules. The approach starts by generating the input/output data. Then, the subtractive clustering algorithm, along with least square estimation (LSE), generates the fuzzy rules that describe the relationship between the input/output data of solar angles that change with time. The fuzzy rules are tuned by an adaptive neuro-fuzzy inference system (ANFIS). Finally, an open loop control system is designed for each of the previous types of sun tracking systems. The results are shown using simulation and virtual reality. The site of application is chosen at Amman, Jordan (32° North, 36° East), and the period of controlling and simulating each type of tracking system is the year 2003.     

Neural network-based self-organizing fuzzy controller for transientstability of multimachine power systems

An efficient self-organizing neural fuzzy controller (SONFC) is designed to improve the transient stability of multimachine power systems. First, an artificial neural network (ANN)-based model is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the ANN model. With the excellent learning capability inherent in the ANN, the traditional heuristic fuzzy control rules and input/output fuzzy membership functions can be optimally tuned from training examples by the backpropagation learning algorithm. Considerable rule-matching times of the inference engine in the traditional fuzzy system can be saved. To illustrate the performance and usefulness of the SONFC, comparative studies with a bang-bang controller are performed on the 34-generator Taipower system with rather encouraging results