Fault detection of nonlinear dynamic processes using dynamic kernel principal component analysis

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.

The practical application of traditional data‐driven techniques for process monitoring encounters significant challenges due to the inherent nonlinear and dynamic nature of most industrial processes. Aiming at the problem of nonlinear dynamic process monitoring, a novel fault detection method based on dynamic kernel principal component analysis combined with weighted structural difference (DKPCA‐WSD) is proposed in this paper. Initially, the proposed method leverages a sophisticated nonlinear transformation to project the augmented matrix of the original input data into a high‐dimensional feature space, thereby facilitating the establishment of a DKPCA model. Subsequently, the WSD statistic is computed, utilizing a widely known sliding window technique, to quantify the mean and standard deviation differences across data structures. Ultimately, the WSD statistic is utilized for fault detection, completing the process monitoring task. By integrating the capability of DKPCA to capture nonlinear dynamic characteristics with the effectiveness of the WSD statistic in mitigating the impact of non‐Gaussian data distributions, DKPCA‐WSD significantly enhances the monitoring performance of traditional DKPCA in nonlinear dynamic processes. The proposed method is evaluated through a numerical case exhibiting nonlinear dynamic behaviors and a simulation model of a continuous stirred tank reactor. A comparative analysis with conventional methods, including principal component analysis (PCA), dynamic principal component analysis, KPCA, PCA similarity factor (SPCA), DKPCA, and moving window KPCA (MWKPCA), demonstrates that DKPCA‐WSD outperforms traditional fault detection techniques in nonlinear dynamic processes, offering a substantial improvement in monitoring performance.

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.

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

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.

Many researches have been carried out on incipient fault prediction technology for key machine components (such as bearings) based on historical and real-time condition monitoring data. However, there is still lack of well-understood systematic methodologies for detecting incipient fault for rotating machines. Based on machine learning technology, this paper studies an incipient fault prediction model applying with wavelet packet decomposition and dynamic kernel principal component analysis (WPD-DKPCA) to meet the needs of engineering applications. The incipient fault prediction WPD-DKPCA model, which does not require knowledge on equipment structure and failure mechanisms, only requires normal state data of the machine, and incipient fault prediction can be achieved through self-learning. Run-to-failure experimental data and engineering case data have been used to verify the constructed model, and the verification results show that the constructed model can reliably and accurately detect an incipient bearing fault. Comparisons of fault prediction effects prove that using T2 statistic monitoring can detect upcoming faults of machines much earlier than Kurtosis and Root Mean Square (RMS).

Monitoring large-scale processes is a crucial task to ensure the safety and reliability of the plants. This paper proposes an approach for decentralized fault detection in large-scale processes. The measured variables of the plant are divided into multiple and possibly overlapping blocks using different techniques based on data. Local monitoring methods are applied in each block using DPCA (Dynamic Principal Component Analysis) model. The local results are then fused by the Bayesian inference strategy. This paper also compares different techniques to decompose the plant looking for the best strategy from the point of view of the fault detection results. The proposed method was applied to the widely used benchmark Tennessee Eastman Process, showing its effectiveness when compared with a centralized method and another decentralized technique.

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 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.

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.

Comparison Between Statistical and Observer-Based Approaches for Fault Detection and Isolation in a Chemical Process

Switch Open-circuit Fault Diagnosis and Fault-Tolerant Control for Boost DC-DC Converter

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.

Viewing to monitoring the continuous casting process, a nonlinear fault detection method based on kernel principal component analysis (KPCA) was introduced. KPCA can efficiently compute principal components in high-dimensional feature spaces by means of integral operators and nonlinear kernel functions, which is to first map the input space into a feature space via nonlinear mapping and then to compute the principal components in that feature space. Based on T2 and SPE charts in feature space, principal component analysis(PCA)can be used to detect faults.. The simulation results show that the proposed approach effectively captured the nonlinear relationship in the process variables and showed superior process monitoring performance compared to linear PCA.

Recently, principal component analysis (PCA) and independent component analysis (ICA) have attracted increasing attention for fault detection in industrial processes. However, industrial processes usually have multimodal characteristics, in which case, the performance of traditional PCA and ICA methods is poor. A fault detection method based on the local entropy double subspace (LEDS) is proposed that effectively supervises the multimodal process with multiple steady modes. The proposed method uses the local probability density (LPD) to eliminate the multimodal characteristics of the data. Furthermore, local entropy (LE) is applied to mine the statistical information associated with the process data. The process variables are classified into Gaussian and non-Gaussian subspaces by the Kolmogorov–Smirnov (KS) test. PCA and ICA models are built in Gaussian and non-Gaussian subspaces, respectively, for fault detection. A Bayesian decision method is employed to transform the detection results into fault probabilities, and the detection results are combined with the final statistical information. This method effectively eliminates the multicentre structure of the data and improves the fault detection performance of traditional PCA and ICA. The proposed method is applied to the Tennessee Eastman multimodal process. The simulation results show that the fault detection rate of LEDS is better than the rates of traditional methods when the false alarm rate is low for most faults.