Fault detection and diagnosis for data incomplete industrial systems with new Bayesian network approach

For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues： the missing data samples and the non-Gaussian property of the data. However, most of the existing data-driven methods cannot be able to handle both of them. Thus, a new Bayesian network classifier based fault detection and diagnosis method is proposed. At first, a non-imputation method is presented to handle the data incomplete samples, with the property of the proposed Bayesian network classifier, and the missing values can be marginalized in an elegant manner. Furthermore, the Gaussian mixture model is used to approximate the non-Gaussian data with a linear combination of finite Gaussian mixtures, so that the Bayesian network can process the non-Gaussian data in an effective way. Therefore, the entire fault detection and diagnosis method can deal with the high-dimensional incomplete process samples in an efficient and robust way. The diagnosis results are expressed in the manner of probability with the reliability scores. The proposed approach is evaluated with a benchmark problem called the Tennessee Eastman process. The simulation results show the effectiveness and robustness of the proposed method in fault detection and diagnosis for large-scale systems with missing measurements.

Deep learning technique for process fault detection and diagnosis in the presence of incomplete data

In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process operations. Various fault detection and diagnosis(FDD) methods have been proposed and implemented, the performance of which, however, could be drastically influenced by the common presence of incomplete or missing data in real industrial scenarios. This paper presents a new FDD approach based on an incomplete data imputation technique for process fault recognition. It employs the modified stacked autoencoder,a deep learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification. A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method.

A Reinforcement Learning System for Fault Detection and Diagnosis in Mechatronic Systems

With the increasing demand for the automation of operations and processes in mechatronic systems,fault detection and diagnosis has become a major topic to guarantee the process performance.There exist numerous studies on the topic of applying artificial intelligence methods for fault detection and diagnosis.However,much of the focus has been given on the detection of faults.In terms of the diagnosis of faults,on one hand,assumptions are required,which restricts the diagnosis range.On the other hand,different faults with similar symptoms cannot be distinguished,especially when the model is not trained by plenty of data.In this work,we proposed a reinforcement learning system for fault detection and diagnosis.No assumption is required.Feature exaction is first made.Then with the features as the states of the environment,the agent directly interacts with the environment.Optimal policy,which determines the exact category,size and location of the fault,is obtained by updating Q values.The method takes advantage of expert knowledge.When the features are unclear,action will be made to get more information from the new state for further determination.We create recurrent neural network with the long short-term memory architecture to approximate Q values.The application on a motor is discussed.The experimental results validate that the proposed method demonstrates a significant improvement compared with existing state-of-the-art methods of fault detection and diagnosis.

Robust fault detection and diagnosis for uncertain nonlinear systems

This paper considers robust fault detection and diagnosis for input uncertain nonlinear systems. It proposes a multi-objective fault detection criterion so that the fault residual is sensitive to the fault but insensitive to the uncertainty as much as possible. Then the paper solves the proposed criterion by maximizing the smallest singular value of the transformation from faults to fault detection residuals while minimizing the largest singular value of the transformation from input uncertainty to the fault detection residuals. This method is applied to an aircraft which has a fault in the left elevator or rudder. The simulation results show the proposed method can detect the control surface failures rapidly and efficiently.

Rotating machinery fault detection and diagnosis based on deep domain adaptation:A survey

In practical mechanical fault detection and diagnosis,it is difficult and expensive to collect enough large-scale supervised data to train deep networks.Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task,which performs well on small data and reduces the demand for high computation power.However,the detection performance is significantly reduced by the direct transfer due to the domain difference.Domain adaptation(DA)can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data.In this survey,we review various current DA strategies combined with deep learning(DL)and analyze the principles,advantages,and disadvantages of each method.We also summarize the application of DA combined with DL in the field of fault diagnosis.This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.

Deep learning in fault detection and diagnosis of building HVAC systems: A systematic review with meta analysis

Building sector account for significant global energy consumption and Heating Ventilation and Air Conditioning (HVAC) systems contribute to the highest portion of building energy consumption. Therefore, the potential for energy saving by improving the efficiency of HVAC systems is huge and various fault detection and diagnosis (FDD) methods have been studied for this purpose. Although amongst all types of existing FDD methods, datadriven based ones are regarded as the most effective methods. As a relatively new branch of data-driven approaches, deep learning (DL) methods have shown promising results, a comprehensive review of DL applications in this area is absent. To fill the research gap, this systematic review with meta analysis analyses the relevant studies both quantitatively and qualitatively. The review is conducted by searching Web of Science, ScienceDirect, and Semantic search. There are 47 eligible studies included in this review following the preferred reporting items for systematic reviews and meta-analyses (PRISMA) protocol. 6 out of the 47 studies are identified as eligible for meta analysis of the effectiveness of DL methods for FDD. The most used DL method is 2D convolutional neural network (CNN). Results suggest that DL methods show promising results as a HVAC FDD. However, most studies use simulation/lab experiment data and real-world complexities are not fully investigated. Therefore, DL methods need to be further tested with real-world scenarios to support decision-making.

Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN

Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of Things(IoT).The cyber-physical system greatly enhances the safety and security of the working facilities,reducing time,saving energy and protecting humans’health.Under the current trends of smart building design and energy management optimization,Automated Fault Detection and Diagnosis(AFDD)of chillers integrated with IoT is highly demanded.Recent studies show that standard machine learning techniques,such as Principal Component Analysis(PCA),Support Vector Machine(SVM)and tree-structure-based algorithms,are useful in capturing various chiller faults with high accuracy rates.With the fast development of deep learning technology,Convolutional Neural Networks(CNNs)have been widely and successfully applied to various fields.However,for chiller AFDD,few existing works are adopting CNN and its extensions in the feature extraction and classification processes.In this study,we propose to perform chiller FDD using a CNN-based approach.The proposed approach has two distinct advantages over existing machine learning-based chiller AFDD methods.First,the CNN-based approach does not require the feature selection/extraction process.Since CNN is reputable with its feature extraction capability,the feature extraction and classification processes are merged,leading to a more neat AFDD framework compared to traditional approaches.Second,the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.

Applied Fault Detection and Diagnosis for Industrial Gas Turbine Systems

The paper presents readily implementable approaches for fault detection and diagnosis （FDD） based on measurements from multiple sensor groups, for industrial systems. Specifically, the use of hierarchical clustering （HC） and self-organizing map neural networks （SOMNNs） are shown to provide robust and user-friendly tools for application to industrial gas turbine （IGT） systems. HC fingerprints are found for normal operation, and FDD is achieved by monitoring cluster changes occurring in the resulting dendrograms. Similarly, fingerprints of operational behaviour are also obtained using SOMNN based classification maps （CMs） that are initially determined during normal operation, and FDD is performed by detecting changes in their CMs. The proposed methods are shown to be capable of FDD from a large group of sensors that measure a variety of physical quantities. A key feature of the paper is the development of techniques to accommodate transient system operation, which can often lead to false-alarms being triggered when using traditional techniques if the monitoring algorithms are not first desensitized. Case studies showing the efficacy of the techniques for detecting sensor faults, bearing tilt pad wear and early stage pre-chamber burnout, are included. The presented techniques are now being applied operationally and monitoring IGTs in various regions of the world.

SPC and Kalman filter-based fault detection and diagnosis for an air-cooled chiller

Buildings worldwide account for nearly 40%of global energy consumption.The biggest energy consumer in buildings is the heating,ventilation and air conditioning(HVAC)systems.In HVAC systems,chillers account for a major portion of the energy consumption.Maintaining chillers in good conditions through early fault detection and diagnosis is thus a critical issue.In this paper,the fault detection and diagnosis for an air-cooled chiller with air coming from outside in variable flow rates is studied.The problem is difficult since the air-cooled chiller is operating under major uncertainties including the cooling load,and the air temperature and flow rate.A potential method to overcome the difficulty caused by the uncertainties is to perform fault detection and diagnosis based on a gray-box model with parameters regarded as constants.The method is developed and verified by us in another paper for a water-cooled chiller with the uncertainty of cooling load.The verification used a Kalman filter to predict parameters of a gray-box model and statistical process control(SPC)for measuring and analyzing their variations for fault detection and diagnosis.The gray-box model in the method,however,requires that the air temperature and flow rate be nearly constant.By introducing two new parameters and deleting data points with low air flow rate,the requirement can be satisfied and the method can then be applicable for an air-cooled chiller.The simulation results show that the method with the revised model and some data points dropped improved the fault detection and diagnosis(FDD)performance greatly.It can detect both sudden and gradual air-cooled chiller capacity degradation and sensor faults as well as their recoveries.

Detection and Diagnosis of Gear Fault By the Single Gear Tooth Analysis Technique

This paper presents a procedure of sing le gear tooth analysis for early detection and diagnosis of gear faults. The objec tive of this procedure is to develop a method for more sensitive detection of th e incipient faults and locating the faults in the gear. The main idea of the sin gle gear tooth analysis is that the vibration signals collected with a high samp ling rate are divided into a number of segments with the same time interval. The number of signal segments is equal to that of the gear teeth. The analysis of i ndividual segments reveals more sensitively the changes of the vibration signals in both time and frequency domain caused by gear faults. In addition, the locat ion of a failed tooth can be indicated in terms of the position of the segment t hat deviates from the normal segments. An experimental investigation verified th e advantages of the single gear tooth analysis.

Actuator fault diagnosis of time-delay systems based on adaptive observer

A novel approach for the actuator fault diagnosis of time-delay systems is presented by using an adaptive observer technique. Systems without model uncertainty are initially considered, followed by a discussion of a general situation where the system is subjected to either model uncertainty or external disturbance. An adaptive diagnostic algorithm is developed to diagnose the fault, and a modified version is proposed for general system to improve robustness. The selection of the threshold for fault detection is also discussed. Finally, a numerical example is given to illustrate the efficiency of the proposed method.

Robust fault diagnosis for linear time-delay systems with uncertainty

This paper deals with the problem of fault diagnosis problem for a class of linear systems with delayed state and uncertainty. The systems are transformed into two different subsystems. One is not affected by actuator faults so that a robust observer can be designed under certain conditions. The other whose states can be measured is affected by the faults. The proposed observer is utilized in an analytical-redundancy-based approach for actuator and sensor fault detection and diagnosis in time-delay systems. Finally, the applicability and effectiveness of the proposed method is illustrated through numerical examples.

Detecting and diagnosing faults in dynamic stochastic distributions using a rational B-splines approximation to output PDFs

This paper presents a novel approach to detect and diagnose faults in the dynamic part of a class of stochastic systems . the Such a group of systems are subjected to a set of crisp inputs but the outputs considered are the measurable probability density functions (PDFs) of the system output, rather than the system output alone. A new approximation model is developed for the output probability density functions so that the dynamic part of the system is decoupled from the output probability density functions. A nonlinear adaptive observer is constructed to detect and diagnose the fault in the dynamic part of the system. Conver-gency analysis is performed for the error dynamics raised from the fault detection and diagnosis phase and an applicability study on the detection and diagnosis of the unexpected changes in the 2D grammage distributions in a paper forming process is included.

Intrusion Detection System for PS-Poll DoS Attack in 802.11 Networks Using Real Time Discrete Event System

Wi-Fi devices have limited battery life because of which conserving battery life is imperative. The 802.11 Wi-Fi standard provides power management feature that allows stations(STAs) to enter into sleep state to preserve energy without any frame losses. After the STA wakes up, it sends a null data or PS-Poll frame to retrieve frame(s) buffered by the access point(AP), if any during its sleep period. An attacker can launch a power save denial of service(PS-DoS) attack on the sleeping STA(s) by transmitting a spoofed null data or PS-Poll frame(s) to retrieve the buffered frame(s) of the sleeping STA(s) from the AP causing frame losses for the targeted STA(s). Current approaches to prevent or detect the PS-DoS attack require encryption,change in protocol or installation of proprietary hardware. These solutions suffer from expensive setup, maintenance, scalability and deployment issues. The PS-DoS attack does not differ in semantics or statistics under normal and attack circumstances.So signature and anomaly based intrusion detection system(IDS) are unfit to detect the PS-DoS attack. In this paper we propose a timed IDS based on real time discrete event system(RTDES) for detecting PS-DoS attack. The proposed DES based IDS overcomes the drawbacks of existing systems and detects the PS-DoS attack with high accuracy and detection rate. The correctness of the RTDES based IDS is proved by experimenting all possible attack scenarios.

Leveraging graph convolutional networks for semi-supervised fault diagnosis of HVAC systems in data-scarce contexts

The continuous accumulation of operational data has provided an ideal platform to devise and implement customized data analytics for smart HVAC fault detection and diagnosis.In practice,the potentials of advanced supervised learning algorithms have not been fully realized due to the lack of sufficient labeled data.To tackle such data challenges,this study proposes a graph neural network-based approach to effectively utilizing both labeled and unlabeled operational data for optimum decision-makings.More specifically,a graph generation method is proposed to transform tabular building operational data into association graphs,based on which graph convolutions are performed to derive useful insights for fault classifications.Data experiments have been designed to evaluate the values of the methods proposed.Three datasets on HVAC air-side operations have been used to ensure the generalizability of results obtained.Different data scenarios,which vary in training data amounts and imbalance ratios,have been created to comprehensively quantify behavioral patterns of representative graph convolution networks and their architectures.The research results indicate that graph neural networks can effectively leverage associations among labeled and unlabeled data samples to achieve an increase of 2.86%–7.30%in fault classification accuracies,providing a novel and promising solution for smart building management.

Research on improved integrated FDD/FTC with effectiveness factors

This paper investigates the integrated fault detection and diagnosis（FDD） with fault tolerant control（FTC） method of the control system with recoverable faults.Firstly,a quasi-linear parameter-varying（QLPV） model is set up,in which effectiveness factors are modeled as time-varying parameters to quantify actuators and sensors faults.Based on the certainty equivalency principle,replacing the real time states in the nonlinear term of the QLPV model with the estimated states,the parameters and states can be estimated by a two-stage Kalman filtering algorithm.Then,a polynomial eigenstructure assignment（PEA） controller with time-varying parameters and states is designed to guarantee the performance of the system with recoverable faults.Finally,mathematical simulation is performed to validate the solution in a satellite closed-loop attitude control system,and simulation results show that the solution is fast and effective for on-orbit real-time computation.

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.

Actuator Fault Monitoring and Fault Tolerant Control in Distillation Columns

This paper presents, from a practical viewpoint accommodation in distillation columns. Addressing faults in an investigation of real-time actuator fault detection, propagation and industrial processes, coupled with the growing demand for higher performance, improved safety and reliability necessitates implementation of less complex alternative control strategies in the events of malfunctions in actuators, sensors and or other system components. This work demonstrates frugality in the design and implementation of fault tolerant control system by integrating fault detection and diagnosis techniques with simple active restructurable feedback controllers and with backup feedback signals and switchable reference points to accommodate actuator fault in distillation columns based on a priori assessed control structures. A multivariate statistical process monitoring based fault detection and diagnosis technique through dynamic principal components analysis is integrated with one-point control or alternative control structure for prompt and effective fault detection, isolation and accommodation. The work also investigates effects of disturbances on fault propagation and detection. Specifically, the reflux and vapor boil-up control strategy used for a binary distillation column during normal operation is switched to one point control of the more valued product by utilizing the remaining healthy actuator. The proposed approach was implemented on two distillation processes： a simulated methanol-water separation column and the benchmark Shell standard heavy oil fractionation process to assess its effectiveness.

Fault Diagnosis for Singular Stochastic Systems

This paper studies the fault diagnosis of singular stochastic systems.The probability distribution of output is measured by probability density functions(PDFs),which are modeled by a square root B-spline expansion.An adaptive nonlinear observer is proposed to estimate the size of the fault occurring in systems. Furthermore,the linear matrix inequality(LMI) approach is applied to establish sufficient conditions for the existence of the observer.Finally,the simulation results are given to indicate the method for diagnosing the fault.

A review on fault-tolerant cooperative control of multiple unmanned aerial vehicles

This paper presents the recent developments in Fault-Tolerant Cooperative Control(FTCC)of multiple unmanned aerial vehicles(multi-UAVs).To facilitate the analyses of FTCC methods for multi-UAVs.the formation control strategies under fault-free flight conditions of multi-UAVs are first summarized and analyzed,including the leader-following,behavior-based,virtual structure,collision avoidance,algebraic graph-based,and close formation control methods,which are viewed as the cooperative control methods for multi-UAVs at the pre-fault stage.Then,by considering the various faults encountered by the multi-UAVs,the state-of-the-art developments on individual,leader-following,and distributed FTCC schemes for multi-UAVs are reviewed in detail.Finally,conclusions and challenging issues towards future developments are presented.