Showing papers by "Hao Luo published in 2020"

A Data-Driven Realization of the Control-Performance-Oriented Process Monitoring System

Abstract: The stability margin is an important attribute for the robustness analysis of the closed loop in a control system design, which indicates the tolerant-ability of the closed-loop stability to system uncertainty (or fault). Seeking to develop an advanced data-driven monitoring and management framework for control performance (especially for robust stability) of the closed-loop system, this paper presents a study on the data-driven realization of the closed-loop stability margin, and its application to control-performance-oriented process monitoring. Specifically, without identifying the system parameters, a data-driven realization of the stability margin is first determined based on the identified multiplication operator of the closed-loop transfer function matrices using time-domain closed-loop measurements. Second, a control-performance-oriented process monitoring approach is proposed based on the determined data-driven realization of the stability margin. The contributions of this paper will bridge the gap between the model-based robustness analysis/design and the data-driven techniques for the future research. The main results of this paper are verified and demonstrated through the case studies on a dc motor benchmark system.

A Robust Data-Driven Fault Detection Approach for Rolling Mills With Unknown Roll Eccentricity

Abstract: This brief proposes a robust subspace-aided fault detection approach for rolling mill processes with roll eccentricity. The novelty of this brief relies on the closed-loop identification of the so-called data-driven realization of the stable kernel representation (SKR) of the rolling mill process. In order to ensure an accurate and robust closed-loop identification, the mappings among the closed-loop process data and the unknown disturbance are analyzed analytically based on the process model, which play essential roles in the data-driven realizations and designs. By determining the kernel subspace of the rolling mill process, a robust data-driven fault detection approach is derived and a disturbance-decoupled residual signal can be obtained. The effectiveness of the proposed approach in comparison to conventional data-driven designs is demonstrated through case studies on a rolling mill benchmark process.

A Review of Intelligent Fault Diagnosis for High-Speed Trains: Qualitative Approaches

Abstract: For ensuring the safety and reliability of high-speed trains, fault diagnosis (FD) technique plays an important role. Benefiting from the rapid developments of artificial intelligence, intelligent FD (IFD) strategies have obtained much attention in the field of academics and applications, where the qualitative approach is an important branch. Therefore, this survey will present a comprehensive review of these qualitative approaches from both theoretical and practical aspects. The primary task of this paper is to review the current development of these qualitative IFD techniques and then to present some of the latest results. Another major focus of our research is to introduce the background of high-speed trains, like the composition of the core subsystems, system structure, etc., based on which it becomes convenient for researchers to extract the diagnostic knowledge of high-speed trains, where the purpose is to understand how to use these types of knowledge. By reasonable utilization of the knowledge, it is hopeful to address various challenges caused by the coupling among subsystems of high-speed trains. Furthermore, future research trends for qualitative IFD approaches are also presented.

Data-Driven Incipient Fault Detection and Diagnosis for the Running Gear in High-Speed Trains

Abstract: Incipient fault detection and diagnosis (FDD) is an important measure to improve the efficient, safe and stable operation of high-speed trains This paper proposes a data-driven FDD method, namely deep slow feature analysis and belief rule base method (DSFA-BRB), for the running gears of high-speed trains The method uses two kinds of statistics to perform fault detection on the multi-dimensional data of the running gears In addition, the characteristics of more accurate data are extracted, which greatly reduces the complexity of constructing a diagnostic and quantitative model Further, by constructing a BRB model combining expert knowledge and data, it is possible to avoid misjudgment caused by data incompleteness Compared with the traditional methods, the DSFA-BRB algorithm has better performance in reducing fault alarm probability Finally, the validity of the algorithm is verified by the actual running gears system

Performance-Based Fault-Tolerant Control Approaches For Industrial Processes With Multiplicative Faults

Abstract: In this article, two performance-based fault-tolerant control strategies are investigated for multiplicative faults in industrial processes. This is motivated by the fact that the changes in the system parameters caused by malfunctions generally lead to multiplicative faults, which may cause remarkable changes in system dynamics and performance. To be specific, the representation forms of the faulty plants are first given in terms of the so-called stable image and kernel representations, respectively. Then, by measuring the fault-induced system performance degradation, two performance-based fault-tolerant control strategies are formulated. Specifically, a residual-driven dynamic controller, which is also called plug-and-play control, is implemented to achieve control performance recovery in the context of stability margin. Finally, a benchmark study is demonstrated to show the efficiency of the proposed methods.

Principal component analysis and belief-rule-base aided health monitoring method for running gears of high-speed train

Abstract: School of Computer Science and Engineering, Changchun University of Technology, Changchun 130012, China; National Engineering Laboratory, CRRC Changchun Railway Vehicles Co., Ltd., Changchun 130062, China; Department of Automation, Tsinghua University, Beijing 100084, China; School of Mechatronic Engineering, Changchun University of Technology, Changchun 130012, China; Academy of Astronautics, Harbin Institute of Technology, Harbin 150001, China

Subspace-Aided Closed-Loop System Identification With Application to DC Motor System

Abstract: A novel closed-loop numerical algorithm for subspace state space system identification (CN4SID) is proposed in this paper. Different from standard schemes, CN4SID algorithm can extend the standard LQ decomposition to the closed-loop cases by incorporating the controller information. Moreover, the proposed method can deliver unbiased pole estimation in the closed-loop framework. To this end, CN4SID algorithm shows superior pole estimation performance compared with a class of subspace identification method via principal component analysis algorithms. The effectiveness of the proposed CN4SID algorithm is finally verified through a practical dc motor system.

A Novel Control-Performance-Oriented Data-Driven Fault Classification Approach

Abstract: This paper selected nine novel feature quantities that can reflect control performance in the closed-loop. Combined with support vector machine (SVM) and k-nearest neighbor (KNN), they are used to perform accurate fault diagnosis. Stability margin describes the degree of stability of the transfer function matrix of system, and thus can be used as an indicator to reflect system’s control performance. Similarly to stability margin, the reciprocals of $\boldsymbol {H_{\infty }}$ -norms of eight subsystems related to stability margin can also be selected as the other eight features describing the control performance. To get the data-driven realization of nine feature quantities, stable image representation and stable kernel representation are constructed by data-driven method without system identification in closed-loop system. Through trained SVM and KNN, different types of faults can be accurately categorized by these feature quantities and the correctness of the entire algorithm is testified and demonstrated by a dc motor benchmark system.

Parity-based robust data-driven fault detection for nonlinear systems using just-in-time learning approach:

Abstract: This paper discusses a framework for fault detection in nonlinear processes. A novel subspace aided parity-based data-driven technique is proposed using the so-called just-in-time learning (JITL) a...

State-Degradation-Oriented Fault Diagnosis for High-Speed Train Running Gears System.

Abstract: As one of the critical components of high-speed trains, the running gears system directly affects the operation performance of the train. This paper proposes a state-degradation-oriented method for fault diagnosis of an actual running gears system based on the Wiener state degradation process and multi-sensor filtering. First of all, for the given measurements of the high-speed train, this paper considers the information acquisition and transfer characteristics of composite sensors, which establish a distributed topology for axle box bearing. Secondly, a distributed filtering is built based on the bilinear system model, and the gain parameters of the filter are designed to minimize the mean square error. For a better presentation of the degradation characteristics in actual operation, this paper constructs an improved nonlinear model. Finally, threshold is determined based on the Chebyshev’s inequality for a reliable fault diagnosis. Open datasets of rotating machinery bearings and the real measurements are utilized in the case studies to demonstrate the effectiveness of the proposed method. Results obtained in this paper are consistent with the actual situation, which validate the proposed methods.

A Data-driven Fault Prediction Integrated Design Scheme Based on Ensemble Learning for Thermal Boiler Process

Abstract: As modern industrial systems are becoming more and more sophisticated, the reliability and safety issues of these complex industrial systems have become the most critical parts in system design. Data-driven fault diagnosis and fault prediction technology play important roles in the field of fault prediction and health management of complex industrial systems. This paper studies the machine learning aided data-driven fault prediction techniques. Three kinds of machine learning algorithms, i.e. random forest (RF), lasso regression (Lasso) and support vector machine regression (SVR), are employed to predict the fault related key performance indicator (KPI) of the thermal boiler system. The boiler's monitoring data is preprocessed, after which the characteristic variables are selected with the algorithm of RF and support vector machine-recursive feature elimination (SVM-RFE). The stacking algorithm is finally used to combine the three basic models. The proposed prediction model performs much better in fault prognosis in comparison with the original prediction model.

A Novel Multivariate Statistical Analysis Aided Deep Learning Approach for Nonlinear System Process Monitoring with Comparison Studies

Abstract: The safety, stability and reliability of the modern complex processes have always been the focus of the industry. An abnormity can lead to failures in the production and manufacturing processes or even dramatic accidents. The fault diagnosis techniques aim to enhance the aforementioned aspects by detecting the system’s deviations from the normal operating conditions and providing early warnings. By mining the hidden system features in the historical data, complex physical modeling procedures and the dependence on large amounts of prior knowledge can be avoided. In many practical scenarios, data-driven fault diagnosis algorithms are more suitable for modern industrial diagnosis. In this paper, a novel approach is proposed which integrates both multivariate statistical analysis and deep neural network to deal with the nonlinearities in the complex systems. Based on the theory of traditional data-driven methods, deep learning methods and the newly proposed method, a MATLAB-based fault diagnosis toolbox is developed and published online. Plentiful function libraries are provided to the researchers to analyze those algorithms and satisfy the need of practical industrial applications. By applying the developed toolbox, the characteristics of those algorithms are also compared, especially on the time-consumption feature and the fault discrimination feature.

Data-driven SOC Estimation with Adaptive Residual Generator for Li-ion Battery

Abstract: Lithium-ion batteries are widely used in many fields of modern life, e.g. wearable devices, electric vehicles and electric grids, etc. The safety and reliability of the lithium-ion battery are critical issues during the battery operation, where the battery management system (BMS) plays a key role. An accurate estimation of the state-of-charge (SOC) of the battery is essential for the BMS. However, due to the intrinsic nonlinearity of the lithium-ion battery, the accurate estimation of the SOC is technically challenging and has drawn lots of attention both from academic and industrial fields. In order to tackle this difficulty, many SOC estimation approaches have been proposed, in which an identification method for the parameters of the battery is normally implemented. However, the additional parameter identification approach greatly reduces the efficiency of SOC estimation and the bias from identification may significantly affect the accuracy of the SOC estimation. This paper proposes a novel data-driven SOC estimation approach based on the adaptive residual generator, which realizes integrating the parameter identification and the SOC estimation into a simultaneous procedure, where the convergences for both the parameter identification and SOC estimation are guaranteed. The proposed adaptive residual generator can estimate the SOC of the battery accurately due to real-time parameter identification that proactively minimizes the modeling error. The effectiveness and the performance of the proposed method are demonstrated through the case studies on a battery simulator. Also, owing to accurately identified parameters, the SOC of the battery is estimated accurately with almost 0% SOC estimation error.

A Data-Driven Fault Diagnosis Approach for Anemometers in Wind Farm

Abstract: Cup anemometers are widely used instruments for wind turbines to measure wind speed in wind farm. Aimed to reduce the adverse impact on wind energy resource estimation, this paper proposes a data-driven fault diagnosis approach for assessing the anemometer health status. Auto-associative netural network (AANN) is developed to reconstruct the anemometer measurement data after data pre-processing, and residual analysis is performed between the anemometer measurement data and the AANN reconstruction data. In addition, the quantitative indicators that can reflect the health status of the anemometer gained from residuals are obtained through the K-Means clustering algorithm, based on which the faulty anemometers in the wind farm can be identified. The approach can provide guidance for the production and operation of the wind farm.

An Intelligent Fault Classification Method Based on Data-Driven Stability Margin

Abstract: Thanks to rapid development of artificial intelligence (AI), a new branch of computer science, modern industry system becomes increasingly intelligent. What's more, mountains of data in industrial process can be saved for data-driven intelligent fault detection and classification. A method of intelligent data-driven fault classification based on stability margin is proposed in this paper, which gives a data-driven stability margin solution. As an important feature, the stability margin, together with the input and output (I/O) data, is input into the LM-BP neural network multi-classifier for fault classification. Moreover, the proposed method is demonstrated to be effective with high accuracy through a DC motor benchmark.

A Cross-block Connection Network for Retinal Vessel Segmentation

Abstract: The appearance and structure of retinal vessels is one of the diagnostic criterias for ophthalmic, cardiovascular and cerebrovascular diseases, which makes the segmentation of retinal vessels worthwhile in clinical medicine. Retinal images have low contrast, complex tissue structures, and diverse pathological conditions. Due to the difficulty to accurately and effectively identify these information, existing segmentation methods often have neglection on subtle vessels and have blurry segmentation on overlap area. This paper proposed a new vascular segmentation method based on deep learning. Considering the necessity of feature extraction from multi-aspect and multi-level, a cross-block dense connection was proposed to improve the feature identify and extract ability. It use additional mapping to connect and share features between different blocks of the network. Further, the residual connection is used inside the block to solve the degradation problem. Powerful extraction capability enables the network to obtain ideal segmentation results with less parameters, which immensely reduces the computing resource consumption of the network. Extensive experiments demonstrate that our approach achieves better performance based on multiple criteria with a much faster speed.