False alarm moderation for performance monitoring in industrial water distribution systems

While considerable attention has been given to data driven methods that analyse and control energy systems in buildings, the same cannot be said for building water systems. As a result, approaches which support enhanced efficiency in building water consumption are somewhat underdeveloped, particularly in industrial settings. Water consumption in industrial systems features non-stationarity (i.e., variations in statistical properties over time), making it challenging to distinguish between routine and non-routine water uses. In such scenarios, fault detection and diagnosis methods that leverage multivariate statistical process control with, for example, principal component analysis and detection indices (Hotelling T²-statistics and Q-statistics), can be successfully used to identify system alarms. However, even with these approaches there can be a high prevalence of false alarms leading to low industry uptake of fault detection and diagnosis systems, or where in place, alarms can be ignored. To efficiently detect and diagnose water distribution system faults, false alarms should be controlled through false alarm moderation approaches so that building managers/operators only need to focus on critical system alarms or system alarms with high risk levels. This paper utilises two statistical non-parametric false alarm moderation approaches (window-based, and trial-based) that generate a second control limit for T²-statistics and Q-statistics. The implementation of these false alarm moderation approaches was combined with principal component analysis to detect faults with real water time series data from two case-study sites. Using both approaches false alarms were reduced, and the overall performance and reliability of the fault detection and diagnosis approach was improved. The principal component analysis model with the window-based approach was shown to be particularly effective.     

Fault diagnosis in power transformers using multi-class logical analysis of data

This paper presents the implementation of a novel multi-class diagnostic technique for the detection and identification of faults based on an approach called logical analysis of data (LAD). LAD is a data mining, artificial intelligence approach that is based on pattern recognition. In the context of condition based maintenance (CBM), historical data containing condition indices and the state of the machine are the inputs to LAD. After training and testing phases, LAD generates patterns that characterize the faulty states according to the type of fault, and differentiate between these states and the normal state. These patterns are found by solving a mixed 0–1 integer linear programming problem. They are then used to detect and to identify a future unknown state of equipment. The diagnostic technique has already been tested on several known machine learning datasets. The results proved that the performance of this technique is comparable to other conventional approaches, such as neural network and support vector machine, with the added advantage of the clear interpretability of the generated patterns, which are rules characterizing the faults’ types. To demonstrate its merit in fault diagnosis, the technique is used in the detection and identification of faults in power transformers using dissolved gas analysis data. The paper reaches the conclusion that the multi-class LAD based fault detection and identification is a promising diagnostic approach in CBM.     

A recognition and novelty detection approach based on Curvelet transform,nonlinear PCA and SVM with application to indicator diagram diagnosis

Indicator diagram plays an important role in the health monitoring and fault diagnosis of reciprocating compressors. Different shapes of indicator diagram indicate different faults of reciprocating compressor. A proper feature extraction and pattern recognition method for indicator diagram is significant for practical uses. In this paper, a novel approach is presented to handle the multi-class indicator diagrams recognition and novelty detection problems. When multi-class faults samples are available, this approach implements multi-class fault recognition; otherwise, the novelty detection is implemented. In this approach, the discrete 2D-Curvelet transform is adopted to extract the representative features of indicator diagram, nonlinear PCA is employed for multi-class recognition to reduce dimensionality, and PCA is used for novelty detection. Finally, multi-class and one-class support vector machines (SVMs) are used as the classifier and novelty detector respectively. Experimental results showed that the performance of the proposed approach is better than the traditional wavelet-based approach.     

Almost certain fault diagnosis through algorithm-based faulttolerance

Algorithm-based fault tolerance has been proposed as a technique to detect incorrect computations in multiprocessor systems. In algorithm-based fault tolerance, processors produce data elements that are checked by concurrent error detection mechanisms. We investigate the efficacy of this approach for diagnosis of processor faults. Because checks are performed on data elements, the problem of location of data errors must first be solved. We propose a probabilistic model for the faults and errors in a multiprocessor system and use it to evaluate the probabilities of correct error location and fault diagnosis. We investigate the number of checks that are necessary to guarantee error location with high probability. We also give specific check assignments that accomplish this goal. We then consider the problem of fault diagnosis when the locations of erroneous data elements are known. Previous work on fault diagnosis required that the data sets produced by different processors be disjoint. We show, for the first time, that fault diagnosis is possible with high probability, even in systems where processors combine to produce individual data elements     

Scalable Distributed Sensor Fault Diagnosis for Smart Buildings

The enormous energy use of the building sector and the requirements for indoor living quality that aim to improve occupants’ productivity and health, prioritize Smart Buildings as an emerging technology. The Heating, Ventilation and Air-Conditioning (HVAC) system is considered one of the most critical and essential parts in buildings since it consumes the largest amount of energy and is responsible for humans comfort. Due to the intermittent operation of HVAC systems, faults are more likely to occur, possibly increasing eventually building’s energy consumption and/or downgrading indoor living quality. The complexity and large scale nature of HVAC systems complicate the diagnosis of faults in a centralized framework. This paper presents a distributed intelligent fault diagnosis algorithm for detecting and isolating multiple sensor faults in large-scale HVAC systems. Modeling the HVAC system as a network of interconnected subsystems allows the design of a set of distributed sensor fault diagnosis agents capable of isolating multiple sensor faults by applying a combinatorial decision logic and diagnostic reasoning. The performance of the proposed method is investigated with respect to robustness, fault detectability and scalability. Simulations are used to illustrate the effectiveness of the proposed method in the presence of multiple sensor faults applied to a 83-zone HVAC system and to evaluate the sensitivity of the method with respect to sensor noise variance.      

离散事件系统间歇性故障的安全诊断

离散事件系统的间歇性故障诊断能够将系统中发生的间歇性故障及时诊断出来,但在诊断期间的系统可能会执行不安全操作.针对间歇性故障在诊断期间的安全性问题,提出一种基于事件的安全诊断方法.首先对发生间歇性故障的离散事件系统进行建模,并给出系统间歇性故障的安全可诊断性的形式化定义.然后通过构造非法语言识别器对系统的非法操作进行识别,并在此基础上构建一个安全验证器,由此得到一个关于系统间歇性故障安全可诊断性的充分必要条件,实现离散事件系统对间歇性故障的安全诊断.这种安全诊断既保证了间歇性故障一旦发生即能被及时诊断出来,又确保了在故障诊断期间系统不会执行任何不安全操作.     

Robust fault diagnosis for non-Gaussian stochastic systems based on the rational square-root approximation model

The task of robust fault detection and diagnosis of stochastic distribution control （SDC） systems with uncertainties is to use the measured input and the system output PDFs to still obtain possible faults information of the system. Using the rational square-root B-spline model to represent the dynamics between the output PDF and the input, in this paper, a robust nonlinear adaptive observer-based fault diagnosis algorithm is presented to diagnose the fault in the dynamic part of such systems with model uncertainties. When certain conditions are satisfied, the weight vector of the rational square-root B-spline model proves to be bounded. Conver- gency analysis is performed for the error dynamic system raised from robust fault detection and fault diagnosis phase. Computer simulations are given to demon- strate the effectiveness of the proposed algorithm.     

Incipient sensor fault isolation based on augmented Mahalanobis distance

Incipient sensor fault diagnosis is important to an efficient and optimal operating condition for modern industrial systems. Recently, a new fault detection index called augmented Mahalanobis distance (AMD) has been proposed in our previous work for incipient fault detection. Following detection, fault isolation is also quite desired so as to investigate root causes of the occurred fault. In the present work, the AMD statistic is first revisited and a geometric illustration of AMD is provided, which intuitively shows its superiority for incipient fault detection. Then, with available fault direction information, an incipient sensor fault isolation approach is proposed. Its fault isolability condition is analyzed theoretically and compared with that of the conventional method. For complex sensor faults whose fault direction information is unknown, a corresponding fault isolation strategy is also briefly discussed. Case studies on a high-speed train air brake system and the continuous stirred tank reactor (CSTR) process are carried out, which demonstrate the effectiveness of the AMD based fault detection and isolation methods, in comparison with conventional approaches.     

General modeling for model-based FDD on building HVAC system

Fault detection and diagnosis (FDD) can be realized with models. It can be used to find the cause of the degradation on energy efficiency and indoor climate quality in building heating, ventilation and air-conditioning (HVAC) systems. Real buildings are diverse. It requires a general modeling method. General modeling concept comprises three steps: hierarchical modeling procedure, parameterization and tuning procedure. In the procedure of hierarchical modeling, the process is split into levels ranging from global to micro level. The objective is to detect faults on the various levels. Consequently, different models for each level should be built. It is important to increase the accuracy of the models and let the models applicable for FDD on building HVAC systems. Parameterization and tuning procedure are necessary. An example model for a real air-conditioned room shows the results of general models and the results after tuning.     

Detection,isolation and diagnosability analysis of intermittent faults in stochastic systems

Intermittent faults (IFs) have the properties of unpredictability, non-determinacy, inconsistency and repeatability, switching systems between faulty and healthy status. In this paper, the fault detection and isolation (FDI) problem of IFs in a class of linear stochastic systems is investigated. For the detection and isolation of IFs, it includes: (1) to detect all the appearing time and the disappearing time of an IF; (2) to detect each appearing (disappearing) time of the IF before the subsequent disappearing (appearing) time; (3) to determine where the IFs happen. Based on the outputs of the observers we designed, a novel set of residuals is constructed by using the sliding-time window technique, and two hypothesis tests are proposed to detect all the appearing time and disappearing time of IFs. The isolation problem of IFs is also considered. Furthermore, within a statistical framework, the definition of the diagnosability of IFs is proposed, and a sufficient condition is brought forward for the diagnosability of IFs. Quantitative performance analysis results for the false alarm rate and missing detection rate are discussed, and the influences of some key parameters of the proposed scheme on performance indices such as the false alarm rate and missing detection rate are analysed rigorously. The effectiveness of the proposed scheme is illustrated via a simulation example of an unmanned helicopter longitudinal control system.     

Unknown Input Fault Detection and Isolation Observer Design for Neutral Systems

This paper deals with actuator fault diagnosis of neutral delayed systems with multiple time delays using an unknown input observer. The main purpose is to design an observer that guarantees the asymptotic stability of the estimate error dynamics and the actuator fault detection. The existence conditions for such an observer are established. The main problem studied in this paper aims at designing observer‐based fault detection and isolation. The designed observer enhances the robust diagnosis performance, including rapidity and accuracy, and generates residuals that enjoy perfect decoupling properties among faults. Based on Lyapunov stability theory, the design of the observer is formulated in terms of linear matrix inequalities, and the diagnosis scheme is based on a bank of unknown input observers for residual generation that guarantees fault detection and isolation in the presence of external disturbances. A numerical example is presented to illustrate the efficiency of the proposed approach.     

基于指定元分析的多故障诊断方法

为了克服传统主元分析(Principal component analysis, PCA)因模式复合现象而无法进行多故障诊断和诊断结果难以解释的不足, 本文引入指定元分析(Designated component analysis, DCA)的思想, 建立DCA多故障诊断理论的空间投影框架, 从而把异常检测问题转化为将观测数据向故障子空间投影后投影能量的显著性检测问题. 在确定系统存在异常的情况下, 再将观测数据向故障子空间中各故障模式方向分别进行投影, 根据投影能量的显著性进行多故障诊断. 并利用正交补空间构造法证明了基于非正交模式指定元分解形式的可行性和收敛性, 建立了一种逐步DCA多故障诊断方法以解决指定模式非正交情况下的多故障诊断问题. 包含5种共存故障的观测数据的仿真研究验证了新方法的有效性.     

基于小波神经网络的空调系统传感器故障诊断

详细阐述了小波神经网络(WNN)的原理、结构,并对传统的BP算法进行了改进。以空调系统传感器故障检测问题为目标,提出了基于WNN的故障诊断方法。通过采集天津博物馆中的传感器数据,对训练好的WNN进行了传感器故障诊断能力的验证,对温度传感器的1℃偏差故障、0.05℃/s速率漂移故障、完全故障、与不同方差下的精度等级下降故障进行了仿真,结果表明:这种方法对传感器故障具有很好的诊断效果。     

离散时间线性时变系统的传感器故障估计滤波器设计

针对一类离散时间线性时变系统提出了一种传感器故障诊断方法.本文首先通过状态增广的方式将被研究的系统转化为描述系统的形式,并且基于该描述系统模型,采用方差最小化原则设计了一种能够同时估计系统状态和传感器故障的故障估计滤波器,然后利用一组故障估计滤波器提出了一种故障诊断方法.本文的主要贡献在于针对离散线性时变系统提出了一种不需要对故障动态进行假设的传感器故障诊断方法.所提出方法的另一个优点是该方法能够在存在过程和测量噪声的情况下实现故障检测、分离与估计.仿真结果说明了所提出方法的有效性.     

DTIF数据在数字电路故障诊断系统中的应用

为正确有效地使用IEEE标准的数字测试交换格式(DTIF),提高自动测试系统对数字电路进行故障诊断的水平和兼容性,深入分析和研究了该数据格式的结构和组成;在使用探测组数据进行探笔引导测试中提出智能动态关联网络技术,以提高探测效率;在使用故障字典组数据进行故障字典诊断中提出991匹配法则,以准确隔离故障集;通过对某数字电路的实际诊断,证明了这两种方法的有效性和准确可行性;该技术的实现对于DTIF数据格式的推广应用、数字电路故障诊断水平的提高具有重要意义。     

Design of unknown input functional observers for nonlinear systems with application to fault diagnosis

This paper considers the design of low-order unknown input functional observers for robust fault detection and isolation of a class of nonlinear Lipschitz systems subject to unknown inputs. The proposed functional observers can be used to generate residual signals to detect and isolate actuator faults. By using the generalized inverse approach, the effect of the unknown inputs can be decoupled completely from the residual signals. Conditions for the existence and stability of reduced-order unknown input functional observer are derived. A design procedure for the generation of residual signals to detect and isolate actuator faults is presented using the proposed unknown-input observer-based approach. A numerical example is given to illustrate the proposed fault diagnosis scheme in nonlinear systems subject to unknown inputs.     

Self adaptive growing neural network classifier for faults detection and diagnosis

Fault detection and diagnosis have gained widespread industrial interest in machine monitoring due to their potential advantage that results from reducing maintenance costs, improving productivity and increasing machine availability. This article develops an adaptive intelligent technique based on artificial neural networks combined with advanced signal processing methods for systematic detection and diagnosis of faults in industrial systems based on a classification method. It uses discrete wavelet transform and training techniques based on locating and adjusting the Gaussian neurons in activation zones of training data. The learning (1) provides minimization in the number of neurons depending on cost error function and other stopping criterions; (2) offers rapid training and testing processes; (3) provides accuracy in classification as confirmed by the results on real signals. The method is applied to classify mechanical faults of rotary elements and to detect and isolate disturbances for a chemical process. Obtained results are analyzed, explained and compared with various methods that have been widely investigated for fault diagnosis.