Fault diagnosis of large-scale industrial processes using the multi-block probabilistic kernel partial least squares method

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.

In order to meet the requirements of multi-parameter and real-time fault diagnosis of China VI vehicle emission standards diesel engine air system, this paper focuses on the research of the diesel engine air system fault detection and diagnosis method based on deep learning to improve the operational safety and fault diagnosis efficiency. In this paper, the air system fault detection and diagnosis are completed based on the AE model and the CNN model, combined with the actual operation of the diesel engine. Among them, the AE model successfully detected all real-time operation faults, and the false detection rate on the health data was 0.1162%; the CNN model obtained a 90.77% fault diagnosis accuracy rate on the test set of the real-time operation data set. The results show that the model has high accuracy in the diagnosis of diesel engine faults, which is of great significance to the application of deep learning based on big data processing.

The speed and localization information of the high-speed trains are essential and significant for train control systems. The occurrence of faults in SDUs (Speed Distance Units) will affect the accuracy and effectiveness of location reports to ensure the operation safety of high-speed trains. The fault detection and diagnosis method for SDUs are focused in this paper. By using the on-board GPS (Global Positioning System) measurements, we propose a parallel-filtering-based architecture for detecting the faults in odometers that use the pulse-counting information to estimate the speed and travelling distance of the trains. According to the characteristics of different fault modes, including the hard fault, soft fault and implicated fault, a rule-based fault diagnosis approach is proposed to identify the detected fault and take suggested maintenance measures, where a conservative determination strategy for utilizing the results of the two filters is demonstrated to decrease the missed detection probability. The field operation data from the high-speed train is employed to build the simulation scenarios. The simulation results demonstrate the performance of the proposed method and illustrate its potentials in real-time fault diagnosis and maintenance for speed distance units.

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

This paper discusses gate open-circuit fault detection and diagnosis method in SPWM modulated symmetric cascaded H-bridge multilevel inverter. First, an output voltage modelling under fault condition in cascaded H-bridge multilevel inverter is presented. Further, simulations of fault conditions have been carried out for the development of the fault detection and diagnosis method. Based on fault modelling and simulations, a fault detection and diagnosis method have been proposed based on the mean values of the bridge voltages as the diagnostic feature. Further, the proposed method has been validated experimentally on a 5-level symmetric sine pulse width modulated cascaded H-bridge multilevel inverter.

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

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.

The present paper proposes a novel data-driven Fault Detection and Diagnosis algorithm for induction motors based on Motor Current Signature Analysis. Principal Component Analysis is used to reduce the three-phase currents space in two dimensions. Then, Kernel Density Estimation is adopted to estimate the Probability Density Function of healthy and of each faulty motors, which will give typical patterns that can be used to identify each fault. Kullback-Leibler divergence is used as an index to identify the dissimilarity between two determined probability distributions, that allows the automatic identification of distinct fault types. Several simulations and experimental results are carried out using two benchmarks in order to verify the effectiveness of the proposed methodology: the first is used to prove appropriateness of the method for air gap eccentricity fault diagnosis and the second is used to prove suitability of the method for rotor broken bars and connectors fault diagnosis. Simulations and classification results prove that the proposed Fault Detection and Diagnosis procedure is able to detect and diagnose different induction motor fault types.

Angular velocity sensor detection and diagnosis become increasingly essential for the improvement of reliability, safety, and efficiency of the control system on aircraft. The classical methods for fault detection and diagnosis are limit or trend checking of some measurable output variables. Due to they do not give a deeper insight and usually do not allow a fault diagnosis, model-based methods of fault detection and diagnosis were developed by using input and output signals and applying dynamic process models. These approaches are based on parameter estimation, parity equations, or state observers. This paper presents an improvement method to build algorithm fault diagnosis for angular velocity sensors on aircraft. Based on proposed method, results of paper can be used in designed intelligent systems that can automatically fault detection on aircraft.

Deep residual network based fault detection and diagnosis of photovoltaic arrays using current-voltage curves and ambient conditions

The application of artificial neural networks for developing a fault detection and diagnosis method in complex heating systems is presented in this paper. The 6 operating modes with faults used to develop this tool stemmed from the results of a detailed investigation in co-operation with heating systems maintenance experts, and are among the most important operating faults for this type of system. This paper presents the method development by simulation data. It demonstrates the feasibility of using neural networks for fault detection and diagnosis of a specific heating system provided training data representative of the behaviour of the system with and without faults are available.

Vehicle engine faults are major faults which take place inside the engine of vehicle. Diagnosis of these faults is highly related to the technical expertise of the person and results in low success rates, so there is duly need of improving the diagnosing methods by improvising the innovative algorithms for faults diagnosis. A fault detection and diagnosis method for an engine's comprises of collecting a sensor signal from an acoustic of bike engine, extracting a feature set from the sensor signal using Mel-Frequency Cepstral Coefficients (MFCC) algorithms. Fault and non-fault states are reported based on comparison between the feature set and a library of fault and non-fault feature profiles corresponding to fault and non-fault states of the bike engine with inspected bike engine. In this paper we have presented the fault diagnosis method using the sound analysis by implementation of MFCC algorithm.

Due to the increasing interest in safety and consistent product quality over a past few decades, demand for effective quality monitoring and safe operation in the modern industry has propelled research into statistical based fault detection and diagnosis methods. This paper describes the application of Hotelling <TEX>$T^2$</TEX> index based Principal Component Analysis (PCA) method for fault detection and diagnosis in industrial processes. Multivariate statistical process control techniques are now widely used for performance monitoring and fault detection. Conventional methods such as PCA are suitable only for steady state processes. These conventional projection methods causes false alarms or missing data for the systems with transient values of processes. These issues significantly compromise the reliability of the monitoring systems. In this paper, a reliable method is used to overcome false alarms occur due to varying process conditions and missing data problems in transient states. This monitoring method is implemented and validated experimentally along with matlab. Experimental results proved the credibility of this fault detection method for both the steady state and transient operations.

In this paper, we present a synergistic approach to startup fault detection and diagnosis in gas turbine engines. The method employs statistics, signal processing and soft computing techniques in a complementary manner to address fault detection at transient conditions. Traditional turbine engine fault detection and diagnosis methods are based on engine data collected at steady-state conditions. However, insipient faults are difficult to diagnose using steady-state engine date; only engine faults that are fairly developed can be detected using conventional methods. Because incipient engine component faults are often manifested in the engine startup characteristics, we present a method of characterizing the engine transient startup using the following steps: engine sensor data during startup are recorded in time series format. The sensor profiles corresponding to "good" and "bad" engine startups are sampled using the bootstrap technique. A feature vector is extracted from these data using principal component analysis (PCA). Then, several important discriminating features are distilled from the feature vector. The features obtained from this step are then classified using neural-network-based methods. The "leave-one-out" approach to cross-validation is applied to obtain an objective evaluation of the neural network training. The proposed fault detection and diagnosis method is evaluated using actual engine startup data and the results are presented.

A probabilistic model with spike-and-slab regularization for inferential fault detection and isolation of industrial processes