Fault Detection In Industrial Processes Research Articles

Comparison of autoencoder architectures for fault detection in industrial processes

Fault detection constitutes a fundamental task for predictive maintenance, requiring mathematical models that can be conveniently provided by data-driven techniques. Autoencoders are a particular type of unsupervised Artificial Neural Networks that can be suitable for fault detection applications. Diverse architectures might be used for autoencoders, resulting in different fault detection performances, which are usually compared by means of Fault Detection Rates for a fixed threshold of the False Alarm Rate, limiting the conclusions to particular cases. To improve the comparability, the present work uses the area under the receiver operating characteristic curve to compare autoencoder architectures for a range of false alarm rates using the Tennessee Eastman Process benchmark. Performances obtained for shallow and deep autoencoders were compared with those of the denoising and variational autoencoders for undercomplete and sparse structures. Overall, the results indicate better performances for sparse structures, especially for the variational autoencoder and the deep denoising autoencoder, with area under the curve of 98.35%.

Gaussian-kernel weighted neighborhood preserving embedding algorithm and its application in fault detection

Fault detection in industrial processes is essential for enhancing production safety. Despite the application of the neighborhood preserving embedding (NPE) algorithm in fault detection as a manifold learning technique, a notable limitation exists-NPE overlooks local geometric structure, leading to suboptimal fault detection and occasional false alarms. This paper introduces the Gaussian kernel weighted NPE (KW-NPE) algorithm to address this challenge. Specifically designed for precise weight assignment in local structures, KW-NPE strategically employs the Gaussian kernel method to project the spatial neighborhood set and capture comprehensive local structural characteristics. The weight assignment, dependent on feature values, enhances the retention of intrinsic structure during dimensionality reduction. A novel objective function further augments this process.To assess performance, a comprehensive composite index is introduced in a case study, amalgamating the false alarm rate and fault detection rate. The effectiveness of the KW-NPE algorithm is demonstrated through extensive simulations and its application to the Tennessee Eastman process dataset, highlighting its superiority over conventional approaches.

Deep Probabilistic Principal Component Analysis for Process Monitoring.

Probabilistic latent variable models (PLVMs), such as probabilistic principal component analysis (PPCA), are widely employed in process monitoring and fault detection of industrial processes. This article proposes a novel deep PPCA (DePPCA) model, which has the advantages of both probabilistic modeling and deep learning. The construction of DePPCA includes a greedy layer-wise pretraining phase and a unified end-to-end fine-tuning phase. The former establishes a hierarchical deep structure based on cascading multiple layers of the PPCA module to extract high-level features. The latter builds an end-to-end connection between the raw inputs and the final outputs to further improve the representation of the model to high-level features. After constructing the model structure of DePPCA, we first present the detailed training processes of the pretraining and fine-tuning stages, then clarify the theoretical merits of the proposed model from the perspective of variational inference. For process monitoring purposes, we develop two statistics based on the established DePPCA. The monitoring performance of these two statistics can remain superior even if the features extracted by DePPCA are significantly compressed to univariate. This makes the feature extraction process and online monitoring procedure of DePPCA quite fast. In other words, the proposed DePPCA can achieve accurate and efficient process monitoring by only extracting one feature for each sample. Finally, the effectiveness of DePPCA is evaluated on the Tennessee Eastman (TE) process and the multiphase flow (MPF) facility.

Online fault detection for industrial processes through Kalman filter

Industrial processes suffer from a wide range of damages including normal wear, environmental changes, physical structural defects and so on. This paper describes the possibility of system health management based on a prediction model, i.e., state space model realized by Kalman filter. The categorical target was mapped to numerical values in advance for this purpose. To deal with the time-varying and streaming characteristics of the industrial process, the model is applied in an online fashion. Comparing with conventional fault detection techniques, this model has the advantages of monitoring not only the production process of interests through observation equation, but also the structural anomalies described via unseen states estimation. In addition, the process and measurement noises provide valuable information about the unstructured uncertainties caused by other reasons. Experiments have been conducted to valid the effectiveness of the proposed method.

Modified q–[formula omitted] rule for incipient fault detection in industrial processes on analysis of intermittent process variation

Incipient faults usually have small impacts on systems. They are easily affected by noise and control effects. Thus, state variables will not deviate from their mean values in a sustained way, but in a fluctuating form. That is, fault samples will return to control limits in some time. I.e., the intermittent process variation occurs. Therefore, there will be lots of missed detection and high detection delay in traditional methods. It even causes the illusion that the system returns to normal. To address this issue, canonical variate residuals are firstly generated. The aim is to capture the system dynamic. Then the modified q–σ rule is proposed, it sets control limits for all variables. And it also monitors the intermittent process variation with fluctuating growth. When tested on a simulated process and a real industrial process, the proposed method is sensitive to the intermittent process variation in incipient faults and has a shorter detection delay.

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

Modern industrial processes often exhibit large-scale and nonlinear characteristics. Incipient fault detection for industrial processes is a big challenge because of the faint fault signature. To improve the performance of incipient fault detection for large-scale nonlinear industrial processes, a decentralized adaptively weighted stacked autoencoder (DAWSAE) -based fault detection method is proposed. First, the industrial process is divided into several sub-blocks and local adaptively weighted stacked autoencoder (AWSAE) is established for each sub-block to mine local information and obtain local adaptively weighted feature vectors and residual vectors. Second, the global AWSAE is established for the whole process to mine global information and obtain global adaptively weighted feature vectors and residual vectors. Finally, local statistics and global statistics are constructed based on local and global adaptively weighted feature vectors and residual vectors to detect the sub-blocks and the whole process, respectively. The advantages of proposed method are verified by a numerical example and Tennessee Eastman process (TEP).

Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processes

The ability of recurrent neural networks (RNN) to model nonlinear dynamics of high dimensional process data has enabled data-driven RNN-based fault detection algorithms. Previous studies have focused on detecting faults by identifying the discrepancies in data distribution between the faulty and normal data, as reflected in prediction errors generated by RNN models. However, in industrial processes, variations in data distribution can also result from changes in normal control setpoints and compensatory control adjustments in response to disturbances, making it hard to differentiate between normal and faulty conditions. This paper proposes a fault detection method utilizing a long short-term memory (LSTM) encoder–decoder structure with regularized hidden dynamics and reversible instance normalization (RevIN) to compactly represent high-dimensional measurements for effective monitoring. During training, the hidden states of the model are regularized to form a low-dimensional latent space representation of the original multivariate time series data. As a result, the prediction errors of the latent states can be used to monitor the abnormal dynamic variations, while the reconstruction errors of the measured variables are used to monitor the abnormal static variations. Furthermore, the proposed indices can reflect operating conditions, even when the distribution of test data changes, which helps distinguish faults from normal adjustments and disturbances that controllers can settle. Data from numerical simulation and the Tennessee Eastman process are used to illustrate the effectiveness of the proposed fault detection method.

Feature learning based on entropy estimation density peak clustering and stacked autoencoder for industrial process monitoring

AbstractRecently, stacked autoencoder (SAE)‐based deep learning has been widely employed for industrial process fault detection, which can extract representative low‐dimensional features. However, SAE fails to take the distribution structure of raw data into consideration in the unsupervised self‐reconstruction learning, and this may lead to limited monitoring performance. Focusing on this issue, this paper proposes a new fault detection method based on entropy estimation density peak clustering and stacked autoencoder (EEDPC‐SAE) for industrial process monitoring. First, an improved automatic clustering algorithm, namely, entropy estimation density peak clustering (EEDPC), is presented to analyze the distribution structure of process data. Then, the data distribution information is integrated into the learning procedure of SAE to capture the data intrinsic structure. EEDPC‐SAE can describe the distribution characteristics of process data, and more informative high‐level features can be learned for fault detection. Finally, two statistics, that is, Hotelling's T‐squared () and squared prediction error (SPE), are established based on the encoder features and residual features generated by EEDPC‐SAE. The effectiveness of the proposed method is evaluated by the Tennessee Eastman (TE) process and fed‐batch fermentation penicillin (FBFP) process.

Fault detection in multimodal processes based on the local entropy double subspace

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.

Applying Intelligent Multi-Agents to Reduce False Alarms in Wind Turbine Monitoring Systems

This study proposes a method for improving the capability of a data-driven multi-agent system (MAS) to perform condition monitoring and fault detection in industrial processes. To mitigate the false fault-detection alarms, a co-operation strategy among software agents is proposed because it performs better than the individual agents. Few steps transform this method into a valuable procedure for improving diagnostic certainty. First, a failure mode and effects analysis are performed to select physical monitoring signals of the industrial process that allow agents to collaborate via shared signals. Next, several artificial neural network (ANN) models are generated based on the normal behavior operation conditions of various industrial subsystems equipped with monitoring sensors. Thereafter, the agents use the ANN-based expected behavior models to prevent false alarms by continuously monitoring the measurement samples of physical signals that deviate from normal behavior. Finally, this method is applied to a wind turbine. The system and tests use actual data from a wind farm in Spain. The results show that the collaboration among agents facilitates the effective detection of faults and can significantly reduce false alarms, indicating a notable advancement in the industrial maintenance and monitoring strategy.

Interval-valued data correlation modeling approach for uncertain nonlinear and non-Gaussian process monitoring

Process monitoring is a crucial part of ensuring the safety and quality of industrial production, and fault detection is a particularly critical step. As a departure from the dimensionality reduction strategy commonly used in fault detection methods, this paper aims to create a statistical model by directly extracting complex correlations among variables with nonlinearity and non-Gaussian properties. Uncertainties in measurement data in an actual process can significantly impact the control decision based on a monitoring model, so interval-valued description strategy is introduced to effectively take the uncertainties into account. Moreover, we improved upon the traditional interval-valued data generation method using moving window technology combine the receiver-operator characteristic curve to construct intervals based on sample mean and standard deviation (SD), which makes full use of the data information. This paper proposes a mean-SD interval vine copula (MSIVC) model for complex industrial process fault detection. The high density region and density quantile theory are introduced to determine the control boundary. The process monitoring performance of the MSIVC method is evaluated by a numerical example and the Tennessee-Eastman process. The results show that the proposed model is stable, sensitive to process faults, and yields effective monitoring results.

MoniNet With Concurrent Analytics of Temporal and Spatial Information for Fault Detection in Industrial Processes

Modern industrial plants generally consist of multiple manufacturing units, and the local correlation within each unit can be used to effectively alleviate the effect of spurious correlation and meticulously reflect the operation status of the process system. Therefore, the local correlation, which is called spatial information here, should also be taken into consideration when developing the monitoring model. In this study, a cascaded monitoring network (MoniNet) method is proposed to develop the monitoring model with concurrent analytics of temporal and spatial information. By implementing convolutional operation to each variable, the temporal information that reveals dynamic correlation of process data and spatial information that reflects local characteristics within individual operation unit can be extracted simultaneously. For each convolutional feature, a submodel is developed and then all the submodels are integrated to generate a final monitoring model. Based on the developed model, the operation status of the newly collected sample can be identified by comparing the calculated statistics with their corresponding control limits. Similar to the convolutional neural network (CNN), the MoniNet can also expand its receptive field and capture deeper information by adding more convolutional layers. Besides, the filter selection and submodel development in MoniNet can be replaced to generalize the proposed network to many existing monitoring strategies. The performance of the proposed method is validated using two real industrial processes. The illustration results show that the proposed method can effectively detect process anomalies by concurrent analytics of temporal and spatial information.

Feature extraction and fault detection scheme via improved locality preserving projection and SVDD

Manifold learning is widely adopted for the fault detection of industrial processes. However, the quality of low-dimensional embedding coordinates can be adversely affected by ill-constructed graph Laplacian. An improved locality preserving projection (ILPP) scheme is proposed. ILPP is built on a geometrically inspired Laplacian, and the Riemannian metric is used to find the suitable bandwidth parameter. The proposed approach combines the advantages of ILPP in preserving manifold data structures and those of support vector data description (SVDD) in handling complex process data distributions. Case studies on helix data, hot strip mill, and Pensim benchmark processes demonstrate the utility and feasibility of the proposed approach. The average fault detection rate for proposed ILPP is 99%, which is higher than locality preserving projection (LPP; 87.8%), local tangent space alignment (LTSA; 74.9%), and principal component analysis (PCA; 90.6%).

Spectral radius-based interval principal component analysis (SR-IPCA) for fault detection in industrial processes with imprecise data

Data-driven process monitoring approaches like principal component analysis (PCA) have been widely used in many industrial processes, most of which assume that the data are precise and reliable. However, the data collected from actual processes are usually contaminated with uncertainties due to measurement noise, severe working scenarios and other reasons. Aiming at fault detection in the complex industrial processes with imprecise measurement data, a spectral radius-based interval PCA (SR-IPCA) method is proposed in this work. First, kernel density estimation (KDE)-based measurement error estimation strategy is presented to transform imprecise single-valued data into interval-valued data. Then, a spectral radius based eigen-decomposition method for interval matrix is developed to extract the process features by projecting high-dimensional interval data to low-dimensional space. Moreover, four monitoring statistics are defined to analyze process status and identify the fault. The proposed SR-IPCA method can effectively tackle the uncertainties by defining an interval domain and extract correlation structure with relative low computation complexity. The simulation results on the synthetic data sets and the Tennessee Eastman process (TEP) reveal that SR-IPCA significantly reduces the false alarm rate and the missed detection rate compared with PCA, vertices PCA (V-PCA) and centers PCA (C-PCA).

Industrial process fault detection and diagnosis framework based on enhanced supervised kernel entropy component analysis

Most existing industrial process fault detection and diagnosis (FDD) techniques operate on data collected at a single scale and focus only on known faults. However, actual process data are inherently multiscale and unknown faults are always inevitable during system running. Therefore, they may perform unsatisfactorily. To tackle this problem, this paper develops a decentralized industrial process FDD framework using multiple enhanced supervised kernel entropy component analysis (enhanced SKECA) models, where each model acts as a fault indicator for one specific fault. Faults can be easily diagnosed by monitoring the outputs of all models within the framework. In particular, when new faults are identified, the framework can update itself only by adding the corresponding enhanced SKECA models without a complete rebuilding process. The monitoring results for the continuous stirred tank reactor (CSTR) process show that the proposed framework is effective in diagnosing both known and unknown faults.

Critical Concurrent Feature Selection and Enhanced Heterogeneous Ensemble Learning Approach for Fault Detection in Industrial Processes

Machine learning approaches have been successfully applied to fault detection in complex industrial processes, while it is still challenging to design an optimal feature space and a stable model for various faults. To solve this problem, a hybrid approach with critical concurrent feature selection and enhanced heterogeneous ensemble learning is proposed. First, raw process variables from field instruments and slow features obtained by simple linear transformation are ingeniously combined to construct the concurrent feature space so as to contain static and dynamic information. Then, the critical concurrent feature space of each individual learner is automatically obtained by the optimal selection process, and the feature diversity of ensemble is realized simultaneously. Finally, an enhanced heterogeneous ensemble model is constructed by different optimized individual learners, which effectively improves the classification accuracy and stability in fault detection. The performance of the proposed approach is evaluated in a simulated Tennessee Eastman benchmark and a real-word three-phase flow process. The experimental results illustrate that the performance of each optimized individual learner outperforms classic random forest algorithm. The generalization and stability of the ensemble model are further improved. Compared with traditional classification algorithms, the proposed approach achieves superior performance with accuracy that exceeds 89% for the Tennessee Eastman process and exceeds 88% for the three-phase flow process respectively. Additionally, the selected critical concurrent features indicate that both static and dynamic information play important roles in fault detection of industrial processes.

Adversarial Autoencoder Based Feature Learning for Fault Detection in Industrial Processes

Deep learning has recently emerged as a promising method for nonlinear process monitoring. However, ensuring that the features from process variables have representative information of the high-dimensional process data remains a challenge. In this study, we propose an adversarial autoencoder (AAE) based process monitoring system. AAE which combines the advantages of a variational autoencoder and a generative adversarial network enables the generation of features that follow the designed prior distribution. By employing the AAE model, features that have informative manifolds of the original data are obtained. These features are used for constructing and monitoring statistics and improve the stability and reliability of fault detection. Extracted features help calculate the degree of abnormalities in process variables more robustly and indicate the type of fault information they imply. Finally, our proposed method is testified using the Tennessee Eastman benchmark process in terms of fault detection rate, false alarm rate, and fault detection delays.

Improving Fault Detection in Industrial Processes by Event-Driven Data Acquisition

Data acquisition in process industries usually takes place at each sampling. The disadvantage is that a considerable amount of data without new information about the state of the process is continuously transmitted and processed. This negatively affects the communication system and computational power, which is more critical nowadays given the number of variables measured, even in seconds. One solution concerns the event-driven paradigm, in which only relevant data according to a pre-defined criterion is forwarded for further processing. This work investigated the event-based threshold and delta methods in the context of fault detection. The data transmission rate was also analyzed. The well-know Tennessee Eastman problem (TEP) was used as a case study. The fault detection system was based on PCA (principal component analysis), which is widely used for this purpose in this benchmark. The results were compared with the commonly used time-based approach, for a fixed false alarm rate. The threshold rule provided similar results, but with much less data. For the delta rule, significant MDR (missed detection rate) gains of up to 74% were obtained for five of the six hard-to-detect faults, and of up to 69%, for two of the three very hard-to-detect faults. MDR values very close to zero were reached for two of the three intermediate detection faults and two of the hard-to-detect faults. The detection time was also evaluated. In this regard, considerably lower values were obtained for all intermediate detection faults, three of the hard-to-detect faults and all very hard-to-detect faults. In short, the delta method was able to improve fault detection performance, especially for hard-to-detect faults, with a considerably lower data transmission rate, around 20% on average. Event-driven data acquisition can be very attractive for process industries.

Industrial Process Fault Detection Based on Entropy Score Contribution Analysis

Aiming at the problem of poor fault detection ability in complex industrial processes, this paper proposes a fault detection method of entropy score contribution analysis, which can better determine the number of samples with a high contribution rate and achieve good fault detection results. First, normalize the input data to obtain the Euclidean distance of each line vector; Secondly, the number of samples with a high contribution rate is determined by entropy score contribution and determine the initial threshold; Thirdly, a parameter adaptive strategy is proposed to set the threshold of statistics; Finally, fault detection is carried out on the statistical data, and the size of fault detection rate and false alarm rate is calculated. In the fourth part of this paper, we use this fault detection method to detect the faults from the Tennessee Eastman process. The simulation results show that the method proposed has more advantages than the traditional methods, and can be effectively applied to complex industrial processes.

Visual Analytics: A New Paradigm for Process Monitoring

As a result of recent breakthroughs in computer vision technologies, significant research interest has emerged to encode process data into visual clues and treat process monitoring problems as computer vision tasks. Imaging time-series signals as a feature engineering step forms a new branch of data analytics called ”visual analytics”. In the context of process monitoring, we define visual analytics as the integration of visual representation of the data combined with the use of computer vision tools and analytical reasoning to support decision-making and knowledge extraction from the data. In this work, a novel end-to-end visual analytics pipeline for industrial process fault detection using 1D and 2D convolution operations is proposed. The proposed approach presents a visual representation of data that captures temporal and local features from historical time-series signals. Next, the learned features in a 2D format are visually recognized and classified using 2D convolution operations. Our experimental results demonstrate that this approach achieves better performance on an industrial multivariate dataset compared to other state-of-art signals imaging tools such as Gramian Angular Field (GAF) and Recurrence Plots (RP).