Joint recurrence based root cause analysis of nonlinear multivariate chemical processes

PREFACE. ACKNOWLEDGMENTS. PROLOGUE. 1 INTRODUCTION. 1.1 Historical Perspective. 1.2 Diagnostic and Prognostic System Requirements. 1.3 Designing in Fault Diagnostic and Prognostic Systems. 1.4 Diagnostic and Prognostic Functional Layers. 1.5 Preface to Book Chapters. 1.6 References. 2 SYSTEMS APPROACH TO CBM/PHM. 2.1 Introduction. 2.2 Trade Studies. 2.3 Failure Modes and Effects Criticality Analysis (FMECA). 2.4 System CBM Test-Plan Design. 2.5 Performance Assessment. 2.6 CBM/PHM Impact on Maintenance and Operations: Case Studies. 2.7 CBM/PHM in Control and Contingency Management. 2.8 References. 3 SENSORS AND SENSING STRATEGIES. 3.1 Introduction. 3.2 Sensors. 3.3 Sensor Placement. 3.4 Wireless Sensor Networks. 3.5 Smart Sensors. 3.6 References. 4 SIGNAL PROCESSING AND DATABASE MANAGEMENT SYSTEMS. 4.1 Introduction. 4.2 Signal Processing in CBM/PHM. 4.3 Signal Preprocessing. 4.4 Signal Processing. 4.5 Vibration Monitoring and Data Analysis. 4.6 Real-Time Image Feature Extraction and Defect/Fault Classification. 4.7 The Virtual Sensor. 4.8 Fusion or Integration Technologies. 4.9 Usage-Pattern Tracking. 4.10 Database Management Methods. 4.11 References. 5 FAULT DIAGNOSIS. 5.1 Introduction. 5.2 The Diagnostic Framework. 5.3 Historical Data Diagnostic Methods. 5.4 Data-Driven Fault Classification and Decision Making. 5.5 Dynamic Systems Modeling. 5.6 Physical Model-Based Methods. 5.7 Model-Based Reasoning. 5.8 Case-Based Reasoning (CBR). 5.9 Other Methods for Fault Diagnosis. 5.10 A Diagnostic Framework for Electrical/Electronic Systems. 5.11 Case Study: Vibration-Based Fault Detection and Diagnosis for Engine Bearings. 5.12 References. 6 FAULT PROGNOSIS. 6.1 Introduction. 6.2 Model-Based Prognosis Techniques. 6.3 Probability-Based Prognosis Techniques. 6.4 Data-Driven Prediction Techniques. 6.5 Case Studies. 6.6 References. 7 FAULT DIAGNOSIS AND PROGNOSIS PERFORMANCE METRICS. 7.1 Introduction. 7.2 CBM/PHM Requirements Definition. 7.3 Feature-Evaluation Metrics. 7.4 Fault Diagnosis Performance Metrics. 7.5 Prognosis Performance Metrics. 7.6 Diagnosis and Prognosis Effectiveness Metrics. 7.7 Complexity/Cost-Benefit Analysis of CBM/PHM Systems. 7.8 References. 8 LOGISTICS: SUPPORT OF THE SYSTEM IN OPERATION. 8.1 Introduction. 8.2 Product-Support Architecture, Knowledge Base, and Methods for CBM. 8.3 Product Support without CBM. 8.4 Product Support with CBM. 8.5 Maintenance Scheduling Strategies. 8.6 A Simple Example. 8.7 References. APPENDIX. INDEX.

Fault diagnosis of chemical processes based on joint recurrence quantification analysis

Root cause analysis in multivariate statistical process monitoring: Integrating reconstruction-based multivariate contribution analysis with fuzzy-signed directed graphs

Considering the characteristic of fault diagnosis of large steam turbine unit for performance monitoring, a method for performance monitoring and fault diagnosis was designed based on versatile logical form. The logical form was proposed according to fault tree analysis. The diagnostic program can implement the entire process of fault analysis and diagnosis depending on the logical form. This method has characteristics of easy operation and good universality. Design idea and working process of the method were introduced by means of low feedwater temperature.

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

A Data-Driven Fault Detection and Diagnosis by NSGAII-t-SNE and Clustering Methods in the Chemical Process Industry

Recent evidence has suggested that measures of cognitive style may be good predictors of fault diagnosis performance. Experiments 1 and 2 explore the relationship between measures of cognitive style and fault diagnosis performance. A focusing‐scanning measure of style was significantly related to testing efficiency and quality of diagnosis in a context‐free fault diagnosis task. Focusers showed superior diagnostic performance. Experiment 3 examined the effect of training in fault diagnosis strategies for subjects selected at extremes of the focusing‐scanning dimension. Training did not improve the performance of either focusers or scanners although, as suggested by experiments 1 and 2, differences were observed between the fault diagnosis performance of scanners and focusers. Further research is required into the nature of cognitive ability and style and how they interact with fault diagnosis performance.

Fault diagnosis using fused reference model and Bayesian network for building energy systems

A systematic nonstationary causality analysis framework for root cause diagnosis of faults in manufacturing processes

Batch process performance monitoring has been achieved primarily using process measurements with the extracted information being associated with the physical parameters of the process. With increasing attention now being paid to the application of on‐line real‐time process analytics through spectrometry, together with the FDA Process Analytical Technologies (PAT) initiative, the use of spectroscopic information for enhanced monitoring of reactions is gaining impetus. The harmonious integration of process data and spectroscopic data then becomes a major challenge. By integrating the process and spectroscopic measurements for multivariate statistical data modelling and analysis, it is conjectured that improved process understanding and fault diagnosis can be achieved. An investigation into combining process and spectral data using multiblock and multiresolution analysis is proposed and the results from the analysis of experimental data from two industrial application studies are presented to demonstrate the improvements achievable in terms of process performance monitoring and fault diagnosis.

In this paper, a methodology for an affine quasilinear parameter varying (qLPV) model derivation is proposed. The nonlinear model of the system is converted into a qLPV model by hiding the nonlinearities in the scheduling parameters. In order to select the most suitable model among all the possible models, an algorithm is introduced and proposed to generate affine qLPV models for enhancing the fault diagnosis performance as measured in terms of the fault estimation accuracy. The fault diagnosis is accomplished by an H ∞ filter in a linear fractional transformation structure that is designed in the LMI framework. To assess the performance of the proposed approach, our scheme is applied to a gas turbine model. A number of different model structures are considered to design the fault diagnosis filter and performance comparisons conducted show the advantages of the proposed model derivation scheme.

With the increasing complexity and frequency of computer network faults, efficient fault diagnosis is crucial to the reliability and security of the network. To this end, this paper proposes an advanced fault diagnosis method based on the improved Teaching Learning-based Optimization (TLBO) algorithm and the Mini Batch Gradient Descent (MBGD) algorithm under the framework of Convolutional Neural Network (CNN). Different from the traditional CNN-based methods, this method innovatively integrates the TLBO algorithm with the Differential Evolution (DE) strategy, optimizes hyper-parameters and training convergence, and significantly improves the detection accuracy and speed. Meanwhile, MBGD can effectively refine the model parameters and prevent convergence to local minima. The experimental results using the public dataset prove the effectiveness of this method, achieving a high classification accuracy rate of up to 88.3% and significantly reducing the false detection rate to below 0.20%. Compared with the traditional CNN model and the latest methods, this method has a faster convergence speed, model stability and fault diagnosis performance. This research provides a robust solution for real-time fault detection and diagnosis, significantly enhancing the reliability and security of complex network systems.

In real industrial processes, fault diagnosis methods are required to learn from limited fault samples since the procedures are mainly under normal conditions and the faults rarely occur. Although attention mechanisms have become increasingly popular for the task of fault diagnosis, the existing attention-based methods are still unsatisfying for the above practical applications. First, pure attention-based architectures like transformers need a substantial quantity of fault samples to offset the lack of inductive biases thus performing poorly under limited fault samples. Moreover, the poor fault classification dilemma further leads to the failure of the existing attention-based methods to identify the root causes. To develop a solution to the aforementioned problems, we innovatively propose a supervised contrastive convolutional attention mechanism (SCCAM) with ante-hoc interpretability, which solves the root cause analysis problem under limited fault samples for the first time. First, accurate classification results are obtained under limited fault samples. More specifically, we integrate the convolutional neural network (CNN) with attention mechanisms to provide strong intrinsic inductive biases of locality and spatial invariance, thereby strengthening the representational power under limited fault samples. In addition, we ulteriorly enhance the classification capability of the SCCAM method under limited fault samples by employing the supervised contrastive learning (SCL) loss. Second, a novel ante-hoc interpretable attention-based architecture is designed to directly obtain the root causes without expert knowledge. The convolutional block attention module (CBAM) is utilized to directly provide feature contributions behind each prediction thus achieving feature-level explanations. The proposed SCCAM method is testified on a continuous stirred tank heater (CSTH) and the Tennessee Eastman (TE) industrial process benchmark. Three common fault diagnosis scenarios are covered, including a balanced scenario for additional verification and two scenarios with limited fault samples (i.e., imbalanced scenario and long-tail scenario). The effectiveness of the presented SCCAM method is evidenced by the comprehensive results that show our method outperforms the state-of-the-art methods in terms of fault classification and root cause analysis.

Nowadays, chemical processes are becoming more complex, and so the safety requirement is getting higher and higher. Intelligent and effective fault detection and diagnosis are becoming more and more important. However, complex industrial systems generate high-dimensional data, which has bad influence on fault detection and diagnosis. Thus, it is necessary to handle industrial data with high dimensionality. Discriminant Locality Preserving Projections (DLPP) has attracted much interest as a dimensionality reduction method. However, there is a small size sample problem when the data dimension is higher than the number of data classes. Under this condition, DLPP cannot achieve acceptable performance in reducing data dimension. In order to solve this problem, this paper proposes a novel DLPP based on improved Synthetic Minority Oversampling Technique (SMOTE-DLPP). The improved SMOTE is used to sample the original data set to generate new data sets so that the number of data classes is basically the same as the number of data dimension. Simulation results on the Tennessee Eastman process (TEP) show that the proposed SMOTE-DLPP can achieve acceptable performance in fault diagnosis.

This paper proposes a neural network-based process fault diagnosis system with Andrews plot for information pre-processing to enhance the performance of online process fault diagnosis. By using features extracted from Andrews plot as the inputs to a neural network, as a classifier, the diagnosis speed and reliability are improved. A method for determining the important features in the Andrews function is proposed. The proposed fault diagnosis system is applied to a simulated continuous stirred tank reactor process and is compared with two conventional neural network-based fault diagnosis systems: scheme B where the monitored measurements are directly fed to a neural network after scaling and scheme C where the monitored measurements are converted to qualitative trend data before feeding to a neural network. Of all the considered faults, the proposed fault diagnosis system diagnosed the abrupt faults on average 5.45 s and 2.66 s earlier than schemes B and C, respectively and diagnosed the incipient faults on average 13.82 s and 5.09 s earlier than schemes B and C, respectively. The results reveal that Andrews plot method utilized in online process monitoring has a great potential in industrial process monitoring.