Fault detection is one of the key steps in Fault Detection and Isolation (FDI) and, therefore, critical for subsequent prognosis or implementation of Fault Tolerant Control (FTC). It is, therefore, advisable to utilize detection algorithms which are quick and can detect the smallest faults. Model-based detection methods satisfy both these criteria and should be preferred. However, a big limitation for model-based methods is that they require the accurate value of the component parameters, which is difficult to obtain in real situations. This limits the accuracy of model-based methods. This paper proposes a new method for fault detection using Energy Activity (EA) which can detect minute levels of fault in systems with high component uncertainty. Different forms of EA are developed for use as an FDI metric. The proposed forms are simulated using a two-tank system under various types of faults. The results are compared with each other and with the traditional model-based FDI method using... [more]

Most photovoltaic (PV) plants conduct operation and maintenance (O&M) by periodical inspection and cleaning. Such O&M is costly and inefficient. It fails to detect system faults in time, thus causing heavy loss. To ensure their operations are at an ideal state, this work proposes an unsupervised method for intelligent performance evaluation and data-driven fault detection, which enables engineers to check PV panels in time and implement timely maintenance. It classifies monitoring data into three subsets: ideal period A, transition period S, and downturn period B. Based on A and B datasets, we build two non-continuous regression prediction models, which are based on a tree ensemble algorithm and then modified to fit the non-continuous characteristic of PV data. We compare real-time measured power with both upper and lower reference baselines derived from two predictive models. By calculating their threshold ranges, the proposed method achieves the instantaneous performance monitoring o... [more]

Continuous stirring tank reactors are widely used in the chemical production process, which is always accompanied by nonlinearity, time delay, and uncertainty. Considering the characteristic of the actual reaction of the continuous stirring tank reactors, the fault detection problem is studied in terms of the T-S fuzzy model. Through a fault detection filter performance analysis, the sufficient condition for the filtering error dynamics is obtained, which meets the exponential stability in the mean square sense and the given performance requirements. The design of the fault detection filter is transformed into one that settles the convex optimization issue of linear matrix inequality. Numerical analysis shows the effectiveness of this scheme.

Feature extraction plays a key role in fault detection methods. Most existing methods focus on comprehensive and accurate feature extraction of normal operation data to achieve better detection performance. However, discriminative features based on historical fault data are usually ignored. Aiming at this point, a global-local marginal discriminant preserving projection (GLMDPP) method is proposed for feature extraction. Considering its comprehensive consideration of global and local features, global-local preserving projection (GLPP) is used to extract the inherent feature of the data. Then, multiple marginal fisher analysis (MMFA) is introduced to extract the discriminative feature, which can better separate normal data from fault data. On the basis of fisher framework, GLPP and MMFA are integrated to extract inherent and discriminative features of the data simultaneously. Furthermore, fault detection methods based on GLMDPP are constructed and applied to the Tennessee Eastman (TE) p... [more]

This paper is concerned with the real-time configuration of fault detection systems by exploiting an gradient optimization scheme. It is known that industrial processes may often encounter some uncertainties or changes of operating points and environment, which would lead to an unsatisfactory fault detection result. To handle this problem, a real-time (or online) configuration strategy is introduced, which plays an important role in ensuring the efficiency of the fault detection method without a high industrial cost. In this paper, a gradient-based iterative optimization scheme is taken into account for the real-time configuration implementation. By utilizing the gradient-based iterative algorithm to minimize the K-gap between the residual generator and the current system, the parameters of the residual generator can be configured from the online input/output data. Based on this, real-time configuration of the residual generator parameters is achieved and, correspondingly, the fault de... [more]

The laminar cooling process is an important procedure in hot steel strip rolling. The spatial distribution and the drop curve of the strip temperature are crucial for the production and the quality of the steel strip. Traditionally, lumped parameter methods are often used for the modeling of the laminar cooling process, making it difficult to consider the impact of the variation of state variables and related parameters on the system, which seriously affect the stability of the steel strip quality. In this paper, a modeling and monitoring method with a time−space nature for the laminar cooling process is proposed to monitor the spatial variation of the strip temperature. Firstly, the finite-dimensional model is obtained by time−space separation to describe the temperature variation of the steel strip. Next, a global model is constructed by using the multi-modeling integration method. Then, a residual generator is designed to monitor the strip temperature where the statistics and the th... [more]

The k-nearest neighbor (kNN) method only uses samples’ paired distance to perform fault detection. It can overcome the nonlinearity, multimodality, and non-Gaussianity of process data. However, the nearest neighbors found by kNN on a data set containing a lot of outliers or noises may not be actual or trustworthy neighbors but a kind of pseudo neighbor, which will degrade process monitoring performance. This paper presents a new fault detection scheme using the mutual k-nearest neighbor (MkNN) method to solve this problem. The primary characteristic of our approach is that the calculation of the distance statistics for process monitoring uses MkNN rule instead of kNN. The advantage of the proposed approach is that the influence of outliers in the training data is eliminated, and the fault samples without MkNNs can be directly detected, which improves the performance of fault detection. In addition, the mutual protection phenomenon of outliers is explored. The numerical examples and Ten... [more]

Nonlinearity may cause a model deviation problem, and hence, it is a challenging problem for process monitoring. To handle this issue, local kernel principal component analysis was proposed, and it achieved a satisfactory performance in static process monitoring. For a dynamic process, the expectation value of each variable changes over time, and hence, it cannot be replaced with a constant value. As such, the local data structure in the local kernel principal component analysis is wrong, which causes the model deviation problem. In this paper, we propose a new two-step dynamic local kernel principal component analysis, which extracts the static components in the process data and then analyzes them by local kernel principal component analysis. As such, the two-step dynamic local kernel principal component analysis can handle the nonlinearity and the dynamic features simultaneously.

In this brief, we consider the mean-field type H− index problem for stochastic Markovian jump systems. A sufficient condition is derived for stochastic Markovian jump systems with (x,u)-dependent noise based on generalized differential Riccati equations. Especially for stochastic Markovian jump systems with only x-dependent noise, a sufficient and necessary condition is developed to characterize H− index larger than some ξ>0. Finally, a numerical example is addressed to verify the effectiveness of our obtained results.

In manufacturing processes using computerized numerical control (CNC) machines, machine tools are operated repeatedly for a long period for machining hard and difficult-to-machine materials, such as stainless steel. These operating conditions frequently result in tool breakage. The failure of machine tools significantly degrades the product quality and efficiency of the target process. To solve these problems, various studies have been conducted for detecting faults in machine tools. However, the most related studies used only the univariate signal obtained from CNC machines. The fault-detection methods using univariate signals have a limitation in that multivariate models cannot be applied. This can restrict in performance improvement of the fault detection. To address this problem, we employed empirical mode decomposition to construct a multivariate dataset from the univariate signal. Subsequently, auto-associative kernel regression was used to detect faults in the machine tool. To v... [more]

Due to the growing complexity of industrial processes, it is no longer adequate to perform precise fault detection based solely on the global information of process data. In this study, a silhouette stacked autoencoder (SiSAE) model is constructed for process data by considering both global/local information and silhouette information to depict the link between local/cross-local. Three components comprise the SiSAE model: hierarchical clustering, silhouette loss, and the joint stacked autoencoder (SAE). Hierarchical clustering is used to partition raw data into many blocks, which clarifies the information’s characteristics. To account for silhouette information between data, a silhouette loss function is constructed by raising the inner block’s data distance and decreasing the distance of the cross-center block. Each data block has a properly sized SAE model and is jointly trained via silhouette loss to extract features from all available data. Using the Tennessee Eastman (TE) benchmar... [more]

Most industrial systems today are nonlinear and dynamic. Traditional fault detection techniques show their limits because they can hardly extract both nonlinear and dynamic features simultaneously. Canonical variate analysis (CVA) shows its excellent monitoring performance in fault detection for dynamic processes but is not applicable to nonlinear processes. Inspired by the CVA method, a novel nonlinear dynamic process monitoring method, namely, the “canonical variate kernel analysis” (CVKA), is proposed in this work. The way to extract nonlinear features is different from a traditional kernel canonical variate analysis (KCVA). In a sequential structure, the new approach firstly extracts the linear dynamic features from the data through the CVA method, followed by a kernel principal component analysis to extract nonlinear features from the CVA residual space. The new CVKA method is then applied to a TE process case study, proving the excellent performance of CVKA compared to other comm... [more]

For decades, industrial companies have been collecting and storing high amounts of data with the aim of better controlling and managing their processes. However, this vast amount of information and hidden knowledge implicit in all of this data could be utilized more efficiently. With the help of data mining techniques unknown relationships can be systematically discovered. The production of semiconductors is a highly complex process, which entails several subprocesses that employ a diverse array of equipment. The size of the semiconductors signifies a high number of units can be produced, which require huge amounts of data in order to be able to control and improve the semiconductor manufacturing process. Therefore, in this paper a structured review is made through a sample of 137 papers of the published articles in the scientific community regarding data mining applications in semiconductor manufacturing. A detailed bibliometric analysis is also made. All data mining applications are... [more]

In order to reduce pollutants of the emission from diesel vehicles, complex after-treatment technologies have been proposed, which make the fault detection of diesel engines become increasingly difficult. Thus, this paper proposes a canonical correlation analysis detection method based on fault-relevant variables selected by an elitist genetic algorithm to realize high-dimensional data-driven faults detection of diesel engines. The method proposed establishes a fault detection model by the actual operation data to overcome the limitations of the traditional methods, merely based on benchmark. Moreover, the canonical correlation analysis is used to extract the strong correlation between variables, which constructs the residual vector to realize the fault detection of the diesel engine air and after-treatment system. In particular, the elitist genetic algorithm is used to optimize the fault-relevant variables to reduce detection redundancy, eliminate additional noise interference, and im... [more]

Rotary lime kilns are large-scale, energy-intensive unit operations that serve critical functions in a variety of industrial processes including cement production, pyrometallurgy, and kraft pulping. As massive expensive vessels that operate at high temperatures it is imperative from economic, environmental, and safety perspectives to optimize preventative maintenance and production efficiency. To achieve these objectives rotary kilns are increasingly outfitted with more sophisticated sensing technology that can provide additional operating insights. Although increasingly intricate data is collected from industrial operations the extent to which value is extracted from this data is often far from optimal. Our research aims to improve this situation by developing data analytics methods that leverage advanced industrial sensor data to address outstanding process faults. Specifically, this research investigates the use of infrared thermal cameras to detect and diagnose ring formation in r... [more]

This paper proposes a motor fault detection method based on wavelet transform (WT) and improved PSO-BP neural network which is combined with improved particle swarm optimization (PSO) and a back propagation (BP) neural network with linearly increasing inertia weight. First, this research used WT to analyze the current signals of the healthy motor, bearing damage motor, stator winding inter-turn short circuit motor, and broken rotor bar motor. Second, features after completing the signal analysis were extracted, and three types of classifiers were used to classify. The results show that the improved PSO-BP neural network can effectively detect the cause of failure. In addition, in order to simulate the actual operating environment of the motor, this study added white noise with signal noise ratios of 30 dB, 25 dB, and 20 dB to verify that this model has a better anti-noise ability.

The main roles of fault detection and diagnosis (FDD) for industrial processes are to make an effective indicator which can identify faulty status of a process and then to take a proper action against a future failure or unfavorable accidents. In order to enhance many process performances (e.g., quality and throughput), FDD has attracted great attention from various industrial sectors. Many traditional FDD techniques have been developed for checking the existence of a trend or pattern in the process or whether a certain process variable behaves normally or not. However, they might fail to produce several hidden characteristics of the process or fail to discover the faults in processes due to underlying process dynamics. In this paper, we present current research and developments of FDD approaches for process monitoring as well as a broad literature review of many useful FDD approaches.

Data-based process monitoring methods have received tremendous attention in recent years, and modern industrial process data often exhibit dynamic and nonlinear characteristics. Traditional autoencoders, such as stacked denoising autoencoders (SDAEs), have excellent nonlinear feature extraction capabilities, but they ignore the dynamic correlation between sample data. Feature extraction based on manifold learning using spatial or temporal neighbors has been widely used in dynamic process monitoring in recent years, but most of them use linear features and do not take into account the complex nonlinearities of industrial processes. Therefore, a fault detection scheme based on temporal-spatial neighborhood enhanced sparse autoencoder is proposed in this paper. Firstly, it selects the temporal neighborhood and spatial neighborhood of the sample at the current time within the time window with a certain length, the spatial similarity and time serial correlation are used for weighted reconst... [more]

This paper proposes a feature selection (FS) approach, namely, correlation and fitness value-based feature selection (CFFS). CFFS is an improvement feature selection approach of correlation-based feature selection (CFS) for the common failure cases of the induction motor. CFFS establishes the induction motor fault detection (FD) system with artificial neural network (ANN). This study analyzes the current signal of the induction motor with multiresolution analysis (MRA), extracts the features, and uses feature selection approaches (ReliefF, CFS, and CFFS) to reduce the number of features and maintain the accuracy of the induction motor fault detection system. Finally, the induction motor fault detection system is trained by the feature selection approaches selected features. The best induction motor fault detection system will be established through the comparison of the efficiency of these FS approaches.

This article states a condition monitoring strategy for wind turbines using a statistical data-driven modeling approach by means of supervisory control and data acquisition (SCADA) data. Initially, a baseline data-based model is obtained from the healthy wind turbine by means of multiway principal component analysis (MPCA). Then, when the wind turbine is monitorized, new data is acquired and projected into the baseline MPCA model space. The acquired SCADA data are treated as a random process given the random nature of the turbulent wind. The objective is to decide if the multivariate distribution that is obtained from the wind turbine to be analyzed (healthy or not) is related to the baseline one. To achieve this goal, a test for the equality of population means is performed. Finally, the results of the test can determine that the hypothesis is rejected (and the wind turbine is faulty) or that there is no evidence to suggest that the two means are different, so the wind turbine can be... [more]

Kernel methods are a class of learning machines for the fast recognition of nonlinear patterns in any data set. In this paper, the applications of kernel methods for feature extraction in industrial process monitoring are systematically reviewed. First, we describe the reasons for using kernel methods and contextualize them among other machine learning tools. Second, by reviewing a total of 230 papers, this work has identified 12 major issues surrounding the use of kernel methods for nonlinear feature extraction. Each issue was discussed as to why they are important and how they were addressed through the years by many researchers. We also present a breakdown of the commonly used kernel functions, parameter selection routes, and case studies. Lastly, this review provides an outlook into the future of kernel-based process monitoring, which can hopefully instigate more advanced yet practical solutions in the process industries.

In this paper, we address the problem of real-time fault detection in wind turbines. Starting from a data-driven fault detection method, the contribution of this paper is twofold. First, a sensor selection algorithm is proposed with the goal to reduce the computational effort of the fault detection method. Second, an analysis is performed to reduce the data acquisition time needed by the fault detection method, that is, with the goal of reducing the fault detection time. The proposed methods are tested in a benchmark wind turbine where different actuator and sensor failures are simulated. The results demonstrate the performance and effectiveness of the proposed algorithms that dramatically reduce the number of sensors and the fault detection time.

This paper proposes a fault detection and the improved fault-tolerant control for an open fault in the five-phase inverter driving system. The five-phase induction machine has a merit of fault-tolerant control due to its increased number of phases. This paper analyzes an open fault pattern of one switch and proposes an effective fault detection method based upon this analysis. The proposed fault detection method using the analyzed patterns is applied in the power inverter. In addition, when the open fault occurs in the one switch of the induction machine driving system, the proposed fault-tolerant control method is used to operate the induction machine using the remaining healthy phases, after performing the fault detection method. Simulation and experiment results are provided to validate the proposed technique.

This paper addresses the problem of online fault detection of an advanced wind turbine benchmark under actuators (pitch and torque) and sensors (pitch angle measurement) faults of different type: fixed value, gain factor, offset and changed dynamics. The fault detection scheme starts by computing the baseline principal component analysis (PCA) model from the healthy or undamaged wind turbine. Subsequently, when the structure is inspected or supervised, new measurements are obtained are projected into the baseline PCA model. When both sets of data—the baseline and the data from the current wind turbine—are compared, a statistical hypothesis testing is used to make a decision on whether or not the wind turbine presents some damage, fault or misbehavior. The effectiveness of the proposed fault-detection scheme is illustrated by numerical simulations on a well-known large offshore wind turbine in the presence of wind turbulence and realistic fault scenarios. The obtained results demonstrat... [more]

Gas turbine hot component failures often cause catastrophic consequences. Fault detection can improve the availability and economy of hot components. The exhaust gas temperature (EGT) profile is usually used to monitor the performance of the hot components. The EGT profile is uniform when the hot component is healthy, whereas hot component faults lead to large temperature differences between different EGT values. The EGT profile swirl under different operating and ambient conditions also cause temperature differences. Therefore, the influence of EGT profile swirl on EGT values must be eliminated. To improve the detection sensitivity, this paper develops a fault detection method for hot components based on a convolutional neural network (CNN). This paper demonstrates that a CNN can extract the information between adjacent EGT values and consider the impact of the EGT profile swirl. This paper reveals, in principle, that a CNN is a viable solution for dealing with fault detection for hot... [more]