Model selection and fault detection approach based on Bayes decision theory: Application to changes detection problem in a distillation column

The fault detection of industrial processes is very important for increasing the safety, reliability and availability of the different components involved in the production scheme. In this paper, a fault detection (FD) method is developed for nonlinear systems. The main contribution consists in the design of this FD scheme through a combination of the Bayes theorem and a neural adaptive black-box identification for such systems. The performance of the proposed fault detection system has been tested on a real plant as a distillation column. The simplicity of the developed neural model of normal condition operation, under all regimes (i.e. steady-state and unsteady state), used in this case is realised by means of a NARX (Nonlinear Auto-Regressive with eXogenous input) model and by an experimental design. To show the effectiveness of proposed fault detection method, it was tested on a realistic fault of a distillation plant of laboratory scale.     

基于多尺度排列熵和极限学习机的风机叶片覆冰故障检测方法*

针对风机叶片结冰故障检测中状态数据维度高和检测率低的问题,提出1种使用功率数据驱动的多尺度排列熵（multiscale permutation entropy,MPE）和极限学习机（extreme learning machine,ELM）的风机叶片结冰故障检测方法。首先,使用多尺度排列熵提取功率数据的多重尺度特征,得到特征向量;随后,采用极限学习机,结合环境温度,对结冰故障进行检测;最后,通过使用某风电场的数据采集与监视控制系统（supervisory control and data acquisition,SCADA）对数据进行仿真。研究结果表明:所提方法的故障检测率达到100％,同时虚警率仅有0.14％,表明所提方法在风机叶片的覆冰故障检测中的有效性。研究结果可为风机叶片覆冰故障检测提供1种有效方法。     

基于CNN_LSTM模型的复杂支路故障电弧检测*

在低压交流配电系统中,当多支路并联的复杂系统的某1支路中出现串联电弧故障时,识别难度大幅提升。为了预防此类情况引发的电气火灾,提出1种卷积神经网络(CNN)与长短时记忆网络(LSTM)结合的串联故障电弧检测方法。首先,搭建实验平台用以采集不同负载在不同支路下发生故障时和正常工作时的干路电流数据;然后,构建CNN_LSTM模型并做出相应改进,将电流数据直接输入到模型中,由模型自主提取波形特征并进行分类。研究结果表明:该方法可以快速、准确地识别出电弧故障,准确率达99.04%以上,且能够较为准确地检测出是哪类负载所在的支路发生电弧故障,准确率达97.90%,可为复杂支路下的电弧故障识别研究提供参考。     

A new fault detection method for non-Gaussian process based on robust independent component analysis

Conventional fault detection method based on fast independent component analysis (FastICA) is sensitive to outliers in the modeling data and thus may perform poorly under the adverse effects of outliers. To solve such problem, a new fault detection method for non-Gaussian process based on robust independent component analysis (RobustICA) is proposed in this paper. A RobustICA algorithm which can effectively reduce the effects of outliers is firstly developed to estimate the mixing matrix and extract non-Gaussian feature called independent components (ICs) by robust whitening and robust determination of the maximum non-Gaussian directions. Furthermore, a monitoring statistic for each extracted IC is constructed to detect process faults. Simulations on a simple example of the mixing matrix estimation and a fault detection example in the continuous stirred tank reactor system demonstrate that the RobustICA achieves much higher estimation accuracy for the mixing matrix and the ICs than the commonly used FastICA algorithm, and the RobustICA-based fault detection method outperforms the conventional FastICA-based fault detection method in terms of the fault detection time and fault detection rate.     

Statistical fault detection using PCA-based GLR hypothesis testing

Safe process operation requires effective fault detection (FD) methods that can identify faults in various process parameters. In the absence of a process model, principal component analysis (PCA) has been successfully used as a data-based FD technique for highly correlated process variables. Some of the PCA detection indices include the T² or Q statistics, which have their advantages and disadvantages. When a process model is available, however, the generalized likelihood ratio (GLR) test, which is a statistical hypothesis testing method, has shown good fault detection abilities. In this work, a PCA-based GLR fault detection algorithm is developed to exploit the advantages of the GLR test in the absence of a process model. In fact, PCA is used to provide a modeling framework for the develop fault detection algorithm. The PCA-based GLR fault detection algorithm provides optimal properties by maximizing the detection probability of faults for a given false alarm rate. The performance of the PCA-based GLR fault detection algorithm is illustrated and compared to conventional fault detection methods through two simulated examples, one using synthetic data and the other using simulated continuously stirred tank reactor (CSTR) data. The results of these examples clearly show the effectiveness of the developed algorithm over conventional methods.     

一种新的基于图模型的间歇过程故障监测方法

目前多元统计方法被广泛用于间歇过程故障监测并已经取得了比较好的效果。但是,统计模型的可解释性能比较差,很难直接利用操作人员积累的安全经验。为应对这些不足,提出了一种基于图模型的间歇过程故障监测方法。利用提出的定性建模方法,过程机理及操作人员的安全经验能够方便地表达。利用在线的过程变量数据和正向推理算法推断生产应处于的状态,利用安全知识及时地发现生产异常。当推断的结论与在线测得的结果矛盾或过程变量超过设定的安全限时,给出解释性输出。通过一个间歇反应案例,验证了提出的方法在模型的可解释性和利用安全经验方面的优势。     

地下氡气测量法-音频大地电磁法在隐伏断层探测中的应用*

为开展隐伏断层探测,明确断层空间位置和构造属性,在此基础上合理避让或采取有效的工程措施,可以有效减轻地震灾害损失。在昔格达断裂带某区域,采用地下氡气测量法与音频大地电磁法相结合的方法探测隐伏断层。结果表明:2种方法所推断的断层区域较为吻合。地下氡气测量法简单方便,但无法确定断裂结构的深部延伸及产状变化,音频大地电磁法勘探深度大、效率高但干扰因素较多,具有多解性,二者结合的断层探测方法在研究区效果良好,对类似地区开展断层探测具有一定的借鉴和指导意义。     

SVD在串联故障电弧检测及选相中的应用*

煤矿井下发生串联故障电弧易引发火灾等安全事故,为了预防电气火灾、指导线路维修,利用三相电动机及变频器负载开展不同线路、不同电流条件下的串联故障电弧实验,研究三相串联故障电弧的检测及选相方法。首先,对单相电流进行一阶差分处理后,建立改进的吸引子轨迹矩阵作为故障特征矩阵;其次,对故障特征矩阵进行奇异值分解,采用特征矩阵的奇异值构建串联故障电弧检测及选相的特征向量;最后,利用极限学习机建立故障电弧检测及选相模型,并测试检测及选相准确率。研究结果表明:提出的SVD方法可以利用单相电流实现三相电动机及变频器负载回路中的串联故障电弧检测及选相。     

基于深度置信网络的管网泄漏故障诊断方法研究

针对当前管网系统数据量大不利于传统模型方法诊断故障的问题,设计了1种基于深度置信网络的管网故障诊断算法。首先,对管网数据结构以及管网系统运行状态进行分析,选取管网主要数据作为故障诊断网络的输入,确定相应运行状态作为诊断网络输出;其次,设计了基于多个受限制玻尔兹曼机与Softmax分类器级联的深度置信网络,并且利用对比散度算法和BP算法对模型进行预训练与调优,使模型参数达到全局最优;最后,通过实验测试确定所设计的深度置信网络的训练迭代次数与网络层数,使算法诊断准确率达到最优。研究结果表明:提出的基于深度置信网络的管网故障诊断算法对管网故障诊断可以达到良好的诊断结果,泄漏预测准确率在验证集样本上可达96.87%,在管网泄漏检测方面,相较于传统基于模型的方法优势明显。     

A design method of a plant alarm system for first alarm alternative signals using a modularized CE model

Management of a plant alarm system has been identified as one of the key safety issues because of disasters caused by alarm floods. When a chemical plant is at abnormal state, an alarm system must provide useful information to operators as the third layer of an independent protection layer (IPL). Therefore, a method of designing a plant alarm system is important for plant safety. Because the plant is maintained in the plant lifecycle, the alarm system for the plant should be properly managed through the plant lifecycle. To manage changes, the design rationales of the alarm system should be explained explicitly. This paper investigates a logical and systematic alarm system design method that explicitly explains the design rationales from know-why information for proper management of changes through the plant lifecycle. In the method, the module structure proposed by Hamaguchi et al. (2011) to assign a fault origin to be distinguished is extended. Using modules to investigate the sets of alarm sensors and the alarm limits setting for first alarm alternative signals to distinguish the fault origin, an alarm system design method is proposed. Also, the completeness of fault propagation for a branch of the cause–effect model as the plant model is explained. Using the modules and the set of fault origins to be distinguished by the alarm system, we try to explicitly explain the design rationales of the alarm system.     

基于文本故障视角的通信保障应急预案有效性评估研究

应急通信预案作为应急通信保障的行动纲领,其文本有效性将直接影响预案有效性,进而影响到整个应急救援行动的有效性。针对预案文本有效性问题,从文本故障视角出发,基于故障树分析法构建通信保障应急预案有效性评估模型;采用语句成分分析法和伪代码转换法对预案进行故障形式诊断,结合标准故障树,计算预案的有效性并给出具体评估步骤;最终,通过4个样本预案对模型进行实例分析,结果表明:该模型能够提高预案文本故障的识别效率,对预案的编制或修订具有参考意义。     

基于KPLS数据重构的非线性过程监测与故障辨识

为适应快速变化的化工产品需求,过程工业逐步向柔性生产发展,使得间歇过程的应用日益广泛。这一类工艺过程具有动态和非线性的特征,过程故障带来的工艺波动和安全风险是较为突出的挑战。采用基于核函数的偏最小二乘方法,在高维特征空间提取特征变量,这些变量包含了生产过程的非线性结构特征,也反应了过程工况的模式特征。针对传统线性方法存在的故障漏报等问题,利用核函数技巧,在特征空间进行数据重构,进而计算统计监控指标SPE,并通过对SPE的在线监测实现更加有效地故障辨识。本方法针对标准非线性测试对象进行了过程监测,实现结果充分说明了方法的有效性。     

Fault diagnosis of pipeline and pump unit systems using status coupling analysis

Earlier studies on fault diagnosis of the pipeline and pump unit systems (PPU) relied mainly on independent equipment analyses, which usually lead to false alarms because of the loss of information fusion. The aim of this study is to utilize the status coupling relationship to improve fault detection sensitivity and reduce false alarm rate. A real-time status identification of related equipment step is added between capturing abnormal signals and listing out diagnosis results. For example, when the pipeline pressure fluctuation is found abnormal, a status analysis of pump units is performed immediately, if the pump units are proven to be operational normally, then the pipeline leak alarm is acknowledged valid. The logical reasoning algorithm is used to capture abnormal conditions of pipeline pressures. The pump unit faults are captured by combining information from multiple sources. Field applications show that the proposed method significantly improves the PPU fault detection capability on fault detection sensitive and accuracy.     

基于随机森林的阻变型通风网络故障诊断方法*

为了在矿井通风网络发生阻变型故障时,能够快速准确判断出故障位置和故障量,提出1种基于随机森林的通风网络故障位置和故障量诊断方法。利用矿井通风仿真系统IMVS将唐安矿模拟故障生成空间数据集并进行数据预处理,构建基于随机森林的故障诊断模型,并利用该诊断模型对唐安矿矿井通风网络模拟故障位置和故障量进行判断和预测。引用多种方法对模型进行度量,通过唐安矿模拟实验验证基于随机森林的故障诊断模型的有效性。将随机森林和决策树的故障诊断准确率进行对比,研究结果表明:随机森林较决策树故障准确率有进一步的提高,并发现故障地点失误诊断多是相邻巷道,在一定程度上工作人员对故障地点的判断并不受其影响。     

超声脉冲压缩法检测混凝土损伤的研究

为提高混凝土超声检测的信号噪声比,提高测量精度,研究脉冲压缩调频超声发射的方法。该方法发射具有包络的线性调频超声脉冲,在不提高发射声压的情况下增加了发射能量,可提高超声检测的有效作用距离和测量精度,提高信噪比。笔者给出脉冲压缩和解压的基本原理,设计了脉冲解压缩电路;经实验检测结果表明,脉冲压缩超声检测能在没有降低测量距离的情况下,明显提高检测的精度,检测到常规检测中不能发现的缺陷。     

大型游乐设施风险评估与分级方法研究

大型游乐设施的运行是一个动态管理过程,不仅涉及设备本身,而且与人、环境等因素密切相关。针对这个特点,提出大型游乐设施风险矩阵(RMM)的风险分级方法。提出了将事故树与模糊数学相结合的模糊事故树法(FFTA);采用3σ模糊表征法计算大型游乐设施各类风险事故的概率;再采用信息熵法来评价大型游乐设施的风险后果;最后利用风险矩阵法来确定大型游乐设施的风险等级,并通过实例验证了该分级模型有效。     

故障树法和改进PSO-PNN网络的电梯故障诊断模型

针对电梯故障问题,提出一种将故障树分析法、改进的粒子群优化算法和概率神经网络相结合的方法用于电梯的故障诊断。以电梯的安全回路系统为例,用故障树法对回路进行分析,获得训练样本与故障类型;使用粒子群算法对概率神经网络的平滑因子进行优化,在优化过程中,针对粒子群算法存在易陷入局部最优的缺陷,提出对惯性权重的改进策略;采用相对误差对诊断效果做出评估,并与传统的概率神经网络和基本粒子群算法优化的概率神经网络在各种故障类型输出和最大相对误差等方面进行比较,结果表明:该模型能够有效诊断电梯故障。     

基于车桥耦合振动分析的桥梁损伤诊断方法评述

车辆通过桥梁时,桥梁和车辆的动力响应都包含桥梁结构模态或者几何参数信息,对它们进行分析能识别桥梁的模态参数和损伤。结合国内外最新研究成果,综述基于车桥耦合振动分析的桥梁结构损伤识别技术,并与传统识别方法进行比较。指出其优缺点;详细介绍基于灵敏度分析和模型修正的方法、基于结构刚度搜索的方法、利用车辆响应傅立叶变换识别桥梁频率的方法、利用车激桥梁响应的小波变换识别桥梁模态参数的方法以及综合利用车辆和桥梁响应识别桥梁损伤的方法等5种参数识别与损伤诊断方法的基本原理,并总结上述方法的实施步骤和应用时应该注意的问题;指出了该领域的关键问题和进一步的研究方向。     

基于多故障冲击模型和故障树的PFDavg计算方法研究*

为提高安全仪表功能（SIF）要求时危险失效平均概率（PFDavg）计算结果的精确度,提出1种能准确计算SIF在多重共因失效影响下的PFDavg的数学模型。建立包含多重共因失效的系统失效故障树,然后利用多故障冲击模型区分普通失效率和多重共因失效率,根据瞬时不可用率的定义和故障树的逻辑关系计算出SIF的瞬时不可用率;基于PFDavg的定义,计算出SIF的PFDavg,以某化工企业SIF为例进行验证。结果表明:方法有效考虑了多重共因失效对SIF的影响,通过模型计算出SIF的PFDavg大于基于马尔可夫（Markov）方法的软件计算结果,但二者处于相同的数量级。模型在评估SIF的PFDavg时比传统方法偏保守,能提高安全仪表功能的安全性。     

Methodology for computer aided fuzzy fault tree analysis

Probabilistic risk assessment (PRA) is a comprehensive, structured and logical analysis method aimed at identifying and assessing risks of complex process systems. PRA uses fault tree analysis (FTA) as a tool to identify basic causes leading to an undesired event, to represent logical dependency of these basic causes in leading to the event, and finally to calculate the probability of occurrence of this event.To conduct a quantitative fault tree analysis, one needs a fault tree along with failure data of the basic events (components). Sometimes it is difficult to have an exact estimation of the failure rate of individual components or the probability of occurrence of undesired events due to a lack of sufficient data. Further, due to imprecision in basic failure data, the overall result may be questionable. To avoid such conditions, a fuzzy approach may be used with the FTA technique. This reduces the ambiguity and imprecision arising out of subjectivity of the data.This paper presents a methodology for a fuzzy based computer-aided fault tree analysis tool. The methodology is developed using a systematic approach of fault tree development, minimal cut sets determination and probability analysis. Further, it uses static and dynamic structuring and modeling, fuzzy based probability analysis and sensitivity analysis.This paper also illustrates with a case study the use of a fuzzy weighted index and cutsets importance measure in sensitivity analysis (for system probabilistic risk analysis) and design modification.