Industrial process fault detection based on dynamic kernel principal component analysis combined with weighted structural difference

This paper proposes dynamic kernel principal components analysis (DKPCA) approach to bioprocesses monitoring. The basic idea of KPCA is to map the input data into a feature space first via a nonlinear mapping, and then perform a linear PCA in feature space F . The dynamic kernel matrix of DKPCA can capture the nonlinearity and the dynamics of bioprocesses. The proposed method was applied to the fault detection and diagnosis of a simulation benchmark of a biological treatment process. The simulation results clearly show the effectiveness of the proposed approach.

Torque tube is widely used on the offshore platform, and its quality plays an important role on the security of offshore platform. The cold bending forming process for torque tube production is nonlinear and dynamic seriously, with the fault types varied and complex, so the traditional PCA cannot get a good effect in the fault detection of cold bending forming. In this paper, a fault detection method based on dynamic kernel principal component analysis (DKPCA) algorithm is introduced to detect the faults of the cold bending forming. Eleven process variables were sampled from the actual manufacture process and used for fault diagnosis. PCA and DKPCA are used to carry out fault detection on the cold bending forming process, and the results show that the effect of DKPCA for fault detection is better than that of PCA. DKPCA can improve the detection effect greatly due to its advantage in nonlinear and dynamic characteristics, which can be applied widely in actual process.

Fault detection and diagnosis in process data using one-class support vector machines

For industrial process monitoring, instead of conventional principal component analysis (PCA), dynamic principal component analysis (DPCA) is a powerful tool to deal with dynamic relationship among process variable series. Similar to PCA, conventional DPCA methods are not suitable for many industry processes with variables containing nonlinear relationship. Neural networks possess the ability to approximate any nonlinear functions, it have been used is to capture the nonlinear function in DPCA. However, it often needs too many nodes in its layers. It is known that moving average techniques can capture time-dependent without adding the dimensionality of raw data set. Along the line, a method of industrial monitoring discussed in this paper combines moving average PCA (MAPCA) and neural network. As an application case, industrial chemical separation process is used to illustrate the method.

Data-driven method has gained its popularity in fault detection. Conventional methods are associated with one-single-layer process monitoring. Information extracted by such a method may not be sufficient to detect some faults for complicated process systems. Inspired by the deep learning conception, a multi-layer fault detection method, namely Deep Principal Component Analysis (DePCA) was proposed previously in the literature. DePCA has the capability to extract deep features for a process resulting in better fault detection performance. However, it assumes that the value of the variable at each moment is unrelated, which is not suitable for complex nonlinear dynamic system. To address the concerns, by adopting dynamic PCA to extract dynamic features, a new deep approach, namely Deep Dynamic Principal Component Analysis (DeDPCA), is proposed. In the new approach, both Dynamic feature and nonlinear feature can be extracted in different layers so that more process faults can be detected. A Tennessee Eastman process case study was then employed for application and validation of the DeDPCA, which indicates the proposed method is suitable for monitoring complex dynamic nonlinear processes.

Aiming at complicated faults detection of distillation column industrial process, it has faced a grave challenge. In this paper, a new indiscernibility dynamic kernel principal component analysis (I-DKPCA) method is presented and applied to distillation column. Compared with traditional statistical techniques, I-DKPCA not only can capture nonlinear property and dynamic characteristic of processes but also can extract relevant variables from all the variables. Applying this new method to distillation column process (a hardware-in-the-loop simulation system), the results prove the proposed method has great advantages, that is, lower missing rate and higher detection rate for the faults, compared with KPCA and DPCA.

Novel adaptive fault detection method based on kernel entropy component analysis integrating moving window of dissimilarity for nonlinear dynamic processes

In this paper, fault detection methods based on principal component analysis (PCA) have been investigated. The methods have been evaluated using the data acquired from a practical nuclear power plant simulation platform. PCA, dynamic principal component analysis (DPCA), kernel principal component analysis (KPCA), two-step principal component analysis (TS-PCA) have been considered. The performance of these methods in fault detection has been compared.

In traditional dynamic principal component analysis (DPCA) for fault detection, there are some drawbacks such as an excess of the number of principal components (PCs), low computational efficiency, etc. For dealing with the problem, this paper develops a hybrid dynamic principal component analysis (HDPCA) technique, this method can remove spacial and serial correlation by divide-and-conquer algorithm instead of parallel processing strategy, which can detect individual fault accurately and efficiently. The strip breaking fault in steel rolling process is used to demonstrate the improved performance of developed technique in comparison with traditional DPCA fault detection methods. It can be perceived that HDPCA algorithm has the better performance of fault detection and computational efficiency.

The Internet environmenthas provided massive data to the actualindustrial production process. It not only has large amounts of databut also has a high data dimension, which brings challenges to thetraditional statistical process monitoring. Aiming at the nonlinearityand dynamics of industrial large-scale high-dimensional data, an efficientiterative multiple dynamic kernel principal component analysis (IMDKPCA)method is proposed to monitor the complex industrial process withsuper-large-scale high-dimensional data. In KPCA, a new KKT matrix is first created by using kernel matrix K. According to theproperties of the symmetric matrix, the newly constructed matrix hasthe same eigenvector as the original matrix K; hence, each columnof the matrix K can be used as the input sample of the iteration algorithm.After iterative operation, the kernel principal component can be deducedfleetly without the eigen decomposition. Because the kernel matrixis not stored in the algorithm beforehand, it can effectively reducethe computation complexity of the kernel. Especially for a tremendousdata scale, the traditional eigen decomposition technology is no longerappropriate, yet the presented method can be solved quickly. The autoregressivemoving average (ARMA) time series model and kernel principal componentanalysis (KPCA) are combined to build the IDKPCA model for dealingwith the dynamics and nonlinearity in the industrial process. Eventually,it is applied to monitor faults in the penicillin fermentation processand compared with MKPCA to certify the accuracy and applicabilityof the proposed method.

Network operators are now facing bandwidth outages as well as a growing pressure to ensure good Quality of Service (QoS). An important practical issue for network service providers is to pay close attention to the load changes of network traffic, in particular, the stationary increase of load from a normal demand. Many network monitoring applications and performance analysis tools are based on the study of an aggregate measure of network traffic, e.g. number of packets in transit (NPT), which is a long-term univariate time series. To classify this type of network traffic data and detect any increase of network source load, we propose a dynamic principal component analysis (PCA) method, first to extract data features and then to detect a stationary load increase of network traffic. The proposed detection schemes are based on either the major or the minor principal components of network traffic data. To demonstrate the applications of the proposed feature extraction method and the detection schemes, we applied them to network traffic data simulated from the packet switching network (PSN) model. Additionally, we propose a combined detection scheme that uses both the major and the minor principal components. The proposed detection schemes, based on dynamic PCA, show enhanced performance in detecting an increase of network load for the simulated network traffic data. These results offer a new feature extraction method based on dynamic PCA that creates additional feature variables for event detection in a univariate time series.

Performance Monitoring of MPC Based on Dynamic Principal Component Analysis

Data-driven techniques have been receiving considerable attention in the industrial process monitoring field due to their major advantages of easy implementation and less requirement for the prior knowledge and process mechanism. Principal component analysis (PCA) method is known as a popular method for monitoring and fault detection in industrial systems but as it is basically a linear method. However, most practical systems are nonlinear. To make the extension to nonlinear systems, kernel PCA (KPCA) method has been proposed for process modeling and monitoring. We present in this paper an online reduced rank optimized KPCA (RR-KPCA) technique for fault detection in order to extend the advantages of the KPCA models to online processes. Following the fault detection, the identification of the variables correlated to the fault occurred is of great importance. For this purpose, it is proposed to extend the approaches of localization by partial PCA and by elimination in the linear case to the nonlinear case, by exploiting the solution of reduction of the dimension of the kernel matrix in the feature space. The partial RR-KPCA and the elimination sensor identification (ESI-RRKPCA) are generated based on the static RR-KPCA and the online RR-KPCA methods. The idea of these approaches is to generate partial RR-KPCA models with reduced sets of variables. In other words, their goal is to generate indices of fault detection sensitive to certain faults and insensitive to others. The proposed fault isolation methods are applied for monitoring an air quality monitoring network (AIRLOR) data.

Fault detection in continuous industrial processes is crucial to ensure production, quality, safety, environmental and economic aspects. Reliable fault detection systems have become even more necessary due to increasingly stringent regulations. The complexity of processes, on the one hand, and the availability of data, on the other, have spread the adoption of the data-driven approach for industrial fault detection. Deep Reinforcement Learning (RL) has recently been applied for this purpose, mainly in rotating machinery and rolling bearings. In chemical processes, most RL applications are in process control. The main contribution of this work lies in proposing a reinforcement learning (RL)-based framework for fault detection in continuous chemical processes. The challenges are related to the large number of variables, nonlinear relationships and changing operational dynamics, to name a few. The classic Tennessee Eastman Process (TEP) benchmark was used as a case study. The results were compared with Principal Component Analysis (PCA), commonly used for chemical process monitoring, dynamic PCA (DPCA), and neural networks. Compared to PCA, the RL approach showed considerably lower missed detection rate (MDR) and time to detection (TTD) while maintaining reasonable false alarm rate (FAR) for all hard-to-detect faults, contributing to early fault detectability. Similar results were obtained with regard to DPCA. Compared to the supervised approach, RL proved to be more flexible regarding model parameterization, which can be very useful for practical aspects of industrial fault detection. The results show that RL-based approaches can be very useful for fault detection in continuous, non-linear, and time-varying systems, such as chemical processes. For example, with regard to adaptive alarm thresholds and the detection of known and unknown faults. The latter represents a major challenge in industrial practice.

In this paper the false alarms issue, generated by a fault detection scheme based in a dynamic principal components analysis (DPCA) is tackled. This problem occurs if the nominal operation point of the system changes. It is shown how input-output models can be identified simultaneously from the DPCA based statistical modeling, and how this deterministic models can be used in a complementary way in order to develop a fault detection scheme able to distinguish between the variations due to changes in the operation point and those due to faults. During the monitoring stage, we propose to use a fixed statistical model and an adaptive standardization of the input and output signals. The effectiveness of the proposed methodology is evaluated for fault detection in an interconnected tanks system.