过程系统的在线故障检测、诊断和预报技术(一)

编者按:过程系统的在线故障检测与诊断是一门新技术,起始于七十年代中期,其研究和应用对于保证现代化工业生产的安全、可靠具有重要意义.本讲座分四讲连载:一、概述;二、生产过程的在线故障检测与诊断方法:原理及应用;三、测量仪表的故障检测与诊断方法:原理及应用;四、智能化故障检测与诊断方法及故障在线预报原理.     

油气管道仪表通信故障智能诊断研究

为保障油气管道生产数据的准确性,降低管道的运行风险,有必要对仪表通信的故障进行实时诊断。针对油气管道自动化生产的特点,对采集的实时运行大数据进行特征分析,获取仪表通信故障特征信号,并且结合专家经验知识、维修人员故障处理实际经验等,建立油气管道仪表通信故障树,基于故障树设计并构建故障诊断专家系统,对仪表通信故障实现智能分析、准确定位,及时提醒相关人员进行仪表通信维检修,从而提高管网的运行安全,为油气管道生产安全的智能化发展提供指导。     

试论小波分析技术支持下的煤矿机电设备故障检测关键技术应用

煤矿机电设备工作环境恶劣,需加强设备状态监测,确保及时发现轴承等核心部件的早期故障。针对设备早期故障特征信号幅值小的情况,提出小波分析检测技术,根据故障信号突变特点实现故障精准识别。通过掌握故障特征提取、联动检测等故障检测关键技术,结合采煤机轴承故障信号特征对技术应用方法进行探索,最终确定故障检测准确率可达92%,成功解决了煤矿机电设备故障在线诊断难题。     

基于Delphi平台的喷雾干燥塔喷管故障在线监测软件的开发

针对喷雾干燥塔喷管堵塞的问题,引进自动控制的思想,提出使用Delphi平台,开发一套喷雾干燥塔喷管故障在线监测 系统。基本过程是:现场测量的振动频率信号,经过调制解调器、PLC处理后传输到PC机中,再对输入的信号进行实时 分析诊断,实现故障的在线监测和可视化。文中重点对PC机处理信号、实现在线监测和可视化软件开发的技术问题进 行了讨论。     

过程系统的在线故障检测、诊断和预报技术(二) 第二讲 生产过程的在线故障检测与诊断方法:原理及应用

本讲介绍工业生产过程在线故障检测与诊断的方法,针对静态系统和动态系统,分别讨论了故障检测与诊断方法的原理,并结合实例介绍故障检测与诊断方案的实施。在生产过程的在线故障检测与诊断中,状态和参数估计方法以及统计分析方法占有重要的地位。     

石化企业在线分析仪表的应用及故障排除

随着技术的不断进步,在线分析仪表在石油化工装置中的应用规模持续增加,石油化工企业在发展过程中需要面对复杂的生产环境。对工艺介质参数和物料组分等数据的在线实时监测,对装置优化生产工艺流程,提高收益率有着十分重要的意义。由于此类仪表通常结构相对复杂,自成系统,分析仪表的故障分析与处理逐渐成为行业普遍关注的问题。首先介绍了在线分析仪表的基本特点,其次对在线分析仪表应用于石化企业的情况进行了解析,最后对在线分析仪表故障原因、提质增效策略进行了探讨,希望可以提升仪表效能,充分发挥在线仪表的技术优势。     

污水在线监测仪表准确度探讨

针对水质在线监测仪表准确度,设计对比方案,对一款多参数水质在线监测仪表进行检测数据对比.结果 显示,比对试验的前2d检测效果不理想,在试验中后期,仪器正常运转下,总氮相对误差为-2.43％～13.29％,氨氮相对误差为-14.24％～12.32％,CODCr相对误差为-12.25％～14.89％,总磷相对误差为-11.86％～14.50％.研究表明,比对在线监测仪表仪器满足水污染源在线监测系统运行与考核技术规范相关要求.     

直流输电工程阀冷系统在线仪表可靠控制策略

阀冷系统是高压直流输电工程换流阀的必要辅助系统,通过准确采集冷却回路的温度、流量、压力、液位、电导率等在线仪表信号,实时反映阀冷系统当前运行的真实工况,有效控制阀冷系统各机电单元可靠动作,达到节能环保、高效冷却的目的,保证换流阀安全、稳定、可靠运行。根据直流输电的可靠性要求,结合不可修复系统可靠性分析理论,提出了阀冷系统在线仪表采用三选二冗余方式的经济性和可靠性,总结出阀冷系统在线仪表在故障自检、报警输出和判断取值等方面完整的可靠控制策略。     

基于信号特征的在线故障分析和智能诊断研究

研究开发基于电网故障信号特征自动生成电网故障诊断Petri网络的技术。通过在线获取调控一体系统的开关遥信变位、SOE信息、保护动作信号和微机保护软报文信息,对信号综合进行逻辑化、条理化、有效化分析,实现电网故障在线分析、辨识和智能诊断。     

丰镇发电厂在线化学仪表检验全过程微机管理系统

依照国标规程和技术标准,由标准表对常规在线化学仪表导电度表、PH表输入标准信号,在线仪表输出测量信号送入微机进行结果自动数据采集,其它化学仪表根据检验情况核查填写记录,系统按照国标化学规程自动进行了大量的复杂计算将对不合格仪表进行汇总进行配备率、投入率、准确率的三率计算,从而解决了检验仪表的操作繁琐和原始数据保存困难的问题。     

基于SVDD的冷水机组传感器故障检测及效率分析

传感器是制冷空调系统的重要组成部分,起着测量数据和监控状态的作用。传感器故障,尤其是输出偏差会引起测量值不准,影响控制策略,导致系统能耗增加。依据模式识别理论,故障检测可处理为一种单分类问题。据此采用一种单分类模式识别工具——支持向量数据描述(SVDD),针对冷水机组进行了偏差故障条件下的传感器故障检测工作。收集冷水机组实测正常运行数据,基于训练集建立SVDD模型,进行冷水机组传感器故障检测;在测试集中引入不同幅值水平的偏差故障,分析检测效率。结果表明:基于SVDD的冷水机组传感器故障检测效果明显,但对于不同传感器的不同幅值偏差故障,故障识别程度并不一致。     

基于MAF的传感器故障检测与诊断

针对工业控制系统中变量之间既存在线性相关性,且在时间结构上呈现自相关的特点,提出了一种基于最小/最大自相关因子(min/max autocorrelation factors, MAF)分析的传感器故障检测与诊断方法。首先,利用正常工况下的历史数据进行自相关因子分析,获得强自相关因子和弱自相关因子;在此基础上构造故障检测统计量,由核密度估计方法获得故障检测控制限,根据贡献图进行传感器故障定位。将所提出的方法应用于连续反应釜仿真过程的传感器故障检测与诊断,与经典的多变量统计方法——主元分析方法相比,所提出的方法能避免虚警,更快地检测缓变故障,并能更好地诊断和解释复杂故障。     

Development of a new soft sensor method using independent component analysis and partial least squares

Soft sensors are used widely to estimate a process variable which is difficult to measure online. One of the crucial difficulties of soft sensors is that predictive accuracy drops due to changes of state of chemical plants. To cope with this problem, a regression model can be updated. However, if the model is updated with an abnormal sample, the predictive ability can deteriorate. We have applied the independent component analysis (ICA) method to the soft sensor to increase fault detection ability. Then, we have tried to increase the predictive accuracy. By using the ICA‐based fault detection and classification model, the objective variable can be predicted, updating the PLS model appropriately. We analyzed real industrial data as the application of the proposed method. The proposed method achieved higher predictive accuracy than the traditional one. Furthermore, the nonsteady state could be detected as abnormal correctly by the ICA model. © 2008 American Institute of Chemical Engineers AIChE J, 2009     

一类非线性随机时滞系统的故障诊断

针对一类非线性随机时滞系统提出了一种新的故障检测算法,该方法不同于传统的故障检测方法,是通过构建一种带有Consensus滤波器的故障诊断滤波器的方法来进行故障诊断.首先采用一组传感器测量系统实际输出,然后根据传感器的测量值构建一组残差生成器,将每个残差生成器看作一个小世界网络模型中的一个节点,采用动态Consensus算法计算出残差生成器的残差,并根据残差来判断系统是否有故障发生.仿真结果表明了本文所提出方法的可行性和有效性.     

PVC生产过程故障传感器的检测与重构

Based on principal component analysis, this paper presents an application of faulty sensor detection and reconstruction in a batch process, polyvinylchloride (PVC) making process. To deal with inconsistency in process data, it is proposed to use the dynamic time warping technique to make the historical data synchronized first,then build a consistent multi-way principal component analysis model. Fault detection is carried out based on squared prediction error statistical control plot. By defining principal component subspace, residual subspace and sensor validity index, faulty sensor can be reconstructed and identified along the fault direction. Finally, application results are illustrated in detail by use of the real data of an industrial PVC making process.     

Applicability domains and accuracy of prediction of soft sensor models

Soft sensors are used to estimate process variables that are difficult to measure online. However, the predictive accuracy gradually decreases with changes in the state of chemical plants. Regression models can be updated, but if the model is updated with abnormal data, the predictive ability deteriorates. In practice, when the prediction error of an objective variable exceeds a threshold, an abnormal situation is detected. However, no effective method exists to decide this threshold. We have proposed a method to estimate the relationships between applicability domains and the accuracy of prediction of soft sensor models quantitatively. The larger the distances to models (DMs), the lower the estimated accuracy of prediction. Hence, the model between DMs and accuracy can separate variations in process variables and y‐analyzer fault. This method was applied to real industrial data. The fault detection ability of the proposed method was better than that of the traditional one. © 2010 American Institute of Chemical Engineers AIChE J, 2011     

Rubber injection molding: Applying multivariate statistics to identify quality issues solely from process signals

Injection-molded rubber parts are widely used in automotive, aeronautical, and industrial engineering applications Therefore, such rubber parts are often critical to the safe operation of the entire system, and part failure can result in significant human or environmental damage. To avoid shipping any parts of subpar quality, manufacturers need to continuously monitor the quality of their product. xIn this work, we apply a principal component analysis (PCA) based process monitoring method. This method is able to detect process fluctuations (faults) in real-time solely from sensor data features, only requiring pretraining on data from about 10 in-control cycles. Specific faults were set to critically affect the dynamic performance of the manufactured NBR rubber parts. Fisher discriminant analysis (FDA) was employed to automatically cluster individual molding cycles into those of being in control, those of defectives caused by unfavorable raw material storage and those of out-of-tolerance induced by an overheated mold, again solely from sensor data. Both PCA fault detection and FDA fault identification decisions were validated by oscillatory rheology and dynamic compression testing of the manufactured parts. This combined method approach is scalable, transferable, and can be implemented on standard industrial injection molding equipment.     

Multi-model sensor fault detection and data reconciliation: A case study with glucose concentration sensors for diabetes

Erroneous information from sensors affect process monitoring and control. An algorithm with multiple model identification methods will improve the sensitivity and accuracy of sensor fault detection and data reconciliation (SFD&DR). A novel SFD&DR algorithm with four types of models including outlier robust Kalman filter, locally weighted partial least squares, predictor-based subspace identification, and approximate linear dependency-based kernel recursive least squares is proposed. The residuals are further analyzed by artificial neural networks and a voting algorithm. The performance of the SFD&DR algorithm is illustrated by clinical data from artificial pancreas experiments with people with diabetes. The glucose-insulin metabolism has time-varying parameters and nonlinearities, providing a challenging system for fault detection and data reconciliation. Data from 17 clinical experiments collected over 896 h were analyzed; the results indicate that the proposed SFD&DR algorithm is capable of detecting and diagnosing sensor faults and reconciling the erroneous sensor signals with better model-estimated values. © 2018 American Institute of Chemical Engineers AIChE J, 65: 629–639, 2019     

一种新的间歇过程故障诊断策略

间歇过程的在线故障诊断近年来受到了越来越多的关注,目前比较通用的方法主要是多变量统计的方法。然而在实际过程尤其是多阶段的间歇过程中故障诊断效果往往不够理想,误诊率比较高。为解决上述问题,本文基于动态轨迹分析（DLA）和在线的动态时间规整方法（DTW）,将二者的优点有效地结合在一起提出了一种在线故障诊断策略,提高了故障诊断效率和准确性。青霉素发酵过程的在线故障诊断应用实例表明该方法具有比较好的诊断效果。     

在线压缩KECA的自适应算法在故障检测中的应用

在复杂的大规模工业过程系统中,实时过程监视、优化计算时间和降低运行内存是实现最终产品质量的最关键和最具挑战性的任务,提出一种在线压缩核熵成分分析（online reduced kernel entropy component analysis, ORKECA）的自适应故障检测算法。首先计算训练样本的核矩阵,根据保留的特征值与特征向量选择有代表性的观测值,构造一个符合全局数据信息特征的压缩集,计算监测统计数据的平方预测误差（squared prediction error, SPE）,并利用核密度估计确定控制限。对于在线实时采集的数据,计算该数据的统计量并与压缩集的控制限比较,根据过程状态分析核熵成分分析（kernel entropy component analysis, KECA）模型是否需要进行更新,可以有效提高实时监测过程数据的性能。最后,以一个非线性数值案例及TE过程数据对该方法进行仿真数值分析。结果表明,所提的方法具有有效的可行性。