Order-Information-Based Phase Partition and Fault Detection for Batch Processes

Different operation phases in batch processes cover distinguishing behaviors, so establishing statistical models for each identical phase become an effective way for batch monitoring. In this paper, a new adaptive phase partition and online fault detection method is proposed, which can track the phase’s transition by time sequence and has less reliance on parameters’ selection. The discussion and analysis of this proposed method follows. In this proposed method, the information contained in every sample time will be evaluated, and the change tendency of feature is demonstrated on a batch prospect. Then, two control bounds are designed for the feature tendency, the stable, and the transitional phases that have a different feature level and play certainly roles in process operation, will be identified automatically. For online monitoring, the new fault detection strategy is composed of modeling the PCA and PLS statistical methods for each identified phase, three statistics are established to ensure the data-decomposing reliable. The proposed method is applied to the industrial penicillin fermentation process, and the experimental result shows better performance in phase partition and fault detection.

Nonlinear fault detection for batch processes via improved chordal kernel tensor locality preserving projections

Aiming at the dynamic characteristic of batch production process changes fast and the accurate modeling of it is difficult, so this paper proposes an intermittent fault detection method of the principal component analysis based on process segment. According to the different dynamic characteristics of process data, the process is divided into multiple stages, with the method of piecewise linear approximation of nonlinear modeling to model different stages of the process, in order to make up the deficiency of traditional MPCA fault diagnosis methods. Through the fault detection of the beer fermentation process experiments to verify that the method can detect process faults promptly and improve the speed and accuracy of process monitoring.

The self-attention mechanism has advantages in analyzing the internal characteristics of data and capturing local information. Therefore, it is applied to fault detection. Since complex industrial processes usually contain a mixture of properties, such as nonlinearity, dynamics, and non-Gaussianity, this places higher demands on fault detection methods. To further improve the performance of the self-attention mechanism for fault detection in complex industrial processes, an innovative self-attention mechanism integrating the adaptive double subspace (ISA-ADS) method is proposed for fault detection. First, the query matrix, the key matrix, and the value matrix of the self-attention mechanism are designed so that they can better focus on local information through the adaptive sample weight allocation strategy. At the same time, this design reduces the interference of nonlinear and noisy information and amplifies the impact of important fault information in the sample. Second, considering the problem of Gaussian and non-Gaussian distributions of the data and the different degrees of influence of different subspaces on the final process monitoring results, an adaptive Gaussian and non-Gaussian double subspace fault detection model based on the self-attention output matrix is established, which adaptively assigns different weights to different subspaces by determining their importance. The statistics of different subspaces are fused using the Bayesian inference and a new adaptive monitoring statistic is constructed to obtain a more accurate monitoring of the process state. Finally, the ISA-ADS is validated using the Tennessee Eastman (TE) process and the actual polyethylene production process. The results show that ISA-ADS has a low false alarm rate and a high fault detection rate, verifying the effectiveness of its fault detection performance.

SummaryIn order to improve fault detection (FD) performance, integrated design of residual generation and evaluation is investigated in this paper for trade‐offs between fault detection rate and false alarm rate (FAR). A set‐membership approach is proposed in residual evaluation by adopting a threshold ellipsoid, which enables more design freedom than a conventional threshold value. With the set‐based definitions of fault detection rate and FAR, the integrated design problem is formulated by maximizing the FD performance under a predefined FAR. The joint optimal selection of a residual generator and a threshold ellipsoid is equivalently transformed into a simplified optimization problem of determining an optimal threshold ellipsoid for any given residual generator. A suboptimal solution for the set‐membership‐based integrated FD system design is obtained based on approximated computation of the FD performance. Monte Carlo simulations show the performance improvement of the proposed method compared with an existing integrated design method. Copyright © 2016 John Wiley & Sons, Ltd.

A Two-step Parallel Phase Partition Algorithm for Monitoring Multiphase Batch Processes with Limited Batches

Variable selection constitutes an essential step to reduce dimensionality and improve performance of fault detection and diagnosis in large scale industrial processes. For this reason, in this paper, variable selection approaches based on causality are proposed and compared, in terms of model adjustment of available data and fault detection performance, with several other filter-based, wrapper-based, and embedded-based variable selection methods. These approaches are applied in a simulated benchmark case and an actual oil and gas industrial case considering four different learning models. The experimental results show that obtained models presented better performance during the fault detection stage when variable selection procedures based on causality were used for purpose of model building.

Decentralized adaptively weighted stacked autoencoder-based incipient fault detection for nonlinear industrial processes

A two-stage anomaly decomposition scheme based on multi-variable correlation extraction for wind turbine fault detection and identification

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.

Aiming at the difficulty of detecting time‐lag faults in dynamic processes, a fault detection strategy based on time neighborhood difference (TND) is proposed, and it is introduced into the partial least squares (PLS) method to suggest the PLS‐TND fault detection method. The TND method takes the mean to the multibatch training set to obtain a baseline training set, and it constructs the mean squared Euclidean distance (MSED) statistic by calculating the average distance between the sample's first k ‐moments neighborhood samples and samples at the same moment in the baseline training set. The TND method can help the PLS method to effectively detect time‐lag faults and significantly improve the fault detection capability of PLS by measuring the overall positional difference between the temporal neighborhood sample set of the sample and its temporal neighborhood sample set in the baseline training set. The PLS‐TND method is compared with some classical fault detection methods through a numerical simulation process and a Continuous Stirred Tank Reactor (CSTR) system design fault detection experiment. The PLS‐TND method gives the best performance of fault detection.

Dynamic model-based fault diagnosis for (bio)chemical batch processes

Fault discriminant enhanced kernel principal component analysis incorporating prior fault information for monitoring nonlinear processes

In this paper, the fault detection problem is investigated for a class of wireless networked systems with compressed measurements. A new compressed fault detection framework is proposed. The measurement data is compressed with a compressed sensing technique before being transferred to the fault detection node via wireless communication channel. Besides, the influence of compressed measurements on fault detectability is analyzed and a new fault detection method is provided based on the integration of model-based and statistical methods. The residual generator is designed by the available compressed measurements and priori knowledge about the system, and the statistic testing method is developed to determine whether there is a fault. Maintaining the acceptable fault detection performance, the compressed fault detection framework can greatly reduce the cost of data acquisition, transmission and storage. As the compressed data is utilized directly in the fault detection process, our method can also reduce computational requirements and enhance the efficiency of the whole fault detection system. Finally, a simulation study is carried out to demonstrate the effectiveness and applicability of the proposed method.

By taking rotary machine as the research object, a fault detection method based on improved capsule network and adaptive wavelet noise reduction is proposed to guarantee the stability of daily operation of mechanical equipment. Among them, capsule network is used as the basic fault detection method, which is improved by introducing residual module and other methods. In addition, the fault detection performance is further improved by combining the method of adaptive wavelet noise reduction. The experimental results show that after introducing adaptive wavelet noise reduction method, the detection accuracy of the constructed detection method in noisy environments is significantly improves, indicating that the introduction of adaptive wavelet noise reduction is necessary. Compared with other commonly used detection methods, the fault detection method based on improved capsule network and adaptive wavelet noise reduction has better fault detection performance, and the detection accuracy reaches 99.89%. The fluctuation range is 99.89% ± 0.15%, with good stability. Meanwhile, in the noisy environment, the detection accuracy of the method fluctuates less, indicating that it has better anti-noise ability. In summary, the equipment fault detection method based on improved capsule network and adaptive wavelet noise reduction has excellent performance and good anti-noise ability, and it can be applied to the actual working scene of rotary machine for fault detection, effectively ensuring the normal operation of the equipment.