Data-driven Realization Research Articles

Distributed data-driven fault detection for industrial interconnected systems with unknown topology structure

Driven by the enhancing requirements for ensuring stable operation of complex industrial processes, this paper investigates a distributed data-driven fault detection (FD) method for industrial interconnected systems. The topology structure of the industrial interconnected system is presumed to be unknown. To this end, the input/output (I/O) data-set model for the interconnected system and the distributed input/output data-set models for the subsystems are derived first. Then, the topology structure of the interconnected system is reconstructed through data-driven realization of gap metric by utilizing the subspace Identification method. Subsequently, the distributed data-driven fault detection method with enhanced information exchange topology is developed. Finally, we validate the feasibility and efficiency of the proposed method by conducting a case study on a chemical process consisting of four continuous-stirred tank reactors (CSTRs).

Data-driven designs of observers and controllers via solving model matching problems

This paper targets the development of a data-driven framework for designing observers and controllers of close-loop systems with consideration of disturbances. Under this framework, both the design of the observer and optimization of the controller can be achieved by only using data. After parameterizing the feedback control systems subject to disturbances, the first step is to identify data-driven stable kernel and image representations (SKR and SIR) with the aid of time-series data. Then, SKR constructs a data-driven realization of a diagnostic observer. Through disturbance elimination and reference tracking, online optimization using SIR provides a data-driven solution to the model matching problem (MMP) whilst the controller is re-configured and optimized in real time. An example is used to demonstrate the effectiveness of the proposed data-driven designs.

Fault Detection for Nonlinear Dynamic Systems With Consideration of Modeling Errors: A Data-Driven Approach.

This article is concerned with data-driven realization of fault detection (FD) for nonlinear dynamic systems. In order to identify and parameterize nonlinear Hammerstein models using dynamic input and output data, a stacked neural network-aided canonical variate analysis (SNNCVA) method is proposed, based on which a data-driven residual generator is formed. Then, the threshold used for FD purposes is obtained via quantiles-based learning, where both estimation errors and approximation errors are considered. Compared with the existing work, the main novelties of this study include: 1) SNNCVA provides a new parameterization strategy for nonlinear Hammerstein systems by utilizing input and output data only; 2) the associated residual generator can ensure FD performance where both the system model and its nonlinearity are unknown; and 3) with consideration of modeling-induced errors, the quantiles are invoked and used to provide a reliable FD threshold in situations where only limited samples are available. Studies on a nonlinear hot rolling mill process demonstrate the effectiveness of the proposed method.

Construction of Data Driven Decomposition Based Soft Sensors with Auto Encoder Deep Neural Network for IoT Healthcare Applications

The architecture of IoT healthcare is motivated towards the data-driven realization and patient-centric health models, whereas the personalized assistance is provided by deploying the advanced sensors. According to the procedures in surgery, in the emergency unit, the patients are monitored till they are stable physically and then shifted to ward for further recovery and evaluation. Normally evaluation done in ward doesn’t suggest continuous parameters monitoring for physiological condition and thus relapse of patients are common. In real-time healthcare applications, the vital parameters will be estimated through dedicated sensors, that are still luxurious at the present situation and highly sensitive to harsh conditions of environment. Furthermore, for real-time monitoring, delay is usually present in the sensors. Because of these issues, data-driven soft sensors are highly attractive alternatives. This research is motivated towards this fact and Auto Encoder Deep Neural Network (AutoEncDeepNN) is proposed depending on Health Framework in the internet assisting the patients with trigger-based sensor activation model to manage master and slave sensors. The advantage of the proposed method is that the hidden information are mined automatically from the sensors and high representative features are generated by multiple layer’s iteration. This goal is consistently achieved and thus the proposed model outperforms few standard approaches which are considered like Hierarchical Extreme Learning Machine (HELM), Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). It is found that the proposed AutoEncDeepNN method achieves 94.72% of accuracy, 41.96% of RMSE, 34.16% of RAE and 48.68% of MAE in 74.64 ms.

A Data-Driven Scheme for Fault Detection of Discrete-Time Switched Systems.

This paper is concerned with the fault detection issue for a class of discrete-time switched systems via the data-driven approach. For the fault detection of switched systems, it is inevitable to consider the mode matching problem between the activated subsystem and the executed residual generator since the mode mismatching may cause a false fault alarm in all probability. Frequently, studies assume that the switching laws are available to the residual generator, by which the residual generator keeps the same mode as the system plant and then the mode mismatching is excluded. However, this assumption is conservative and impractical because many switching laws are hard to acquire in practical applications. This work focuses on the case of switched systems with unavailable switching laws. In view of the unavailability of switching information, the mode recognition is considered for the fault detection process and meanwhile, sufficient conditions are presented for the mode distinguishability. Moreover, a novel decision logic for the fault detection is proposed, based on which new algorithms are established for the data-driven realization. Finally, a benchmark case on a three-tank system is used to illustrate the feasibility and usefulness of the obtained results.

Data-driven computational prediction and experimental realization of exotic perovskite-related polar magnets

Rational design of technologically important exotic perovskites is hampered by the insufficient geometrical descriptors and costly and extremely high-pressure synthesis, while the big-data driven compositional identification and precise prediction entangles full understanding of the possible polymorphs and complicated multidimensional calculations of the chemical and thermodynamic parameter space. Here we present a rapid systematic data-mining-driven approach to design exotic perovskites in a high-throughput and discovery speed of the A2BB’O6 family as exemplified in A3TeO6. The magnetoelectric polar magnet Co3TeO6, which is theoretically recognized and experimentally realized at 5 GPa from the six possible polymorphs, undergoes two magnetic transitions at 24 and 58 K and exhibits helical spin structure accompanied by magnetoelastic and magnetoelectric coupling. We expect the applied approach will accelerate the systematic and rapid discovery of new exotic perovskites in a high-throughput manner and can be extended to arbitrary applications in other families.

Data-driven design of fault-tolerant control systems based on recursive stable image representation

Driven by the increasing needs in the process industry for designing fault-tolerant control systems based on process data and maintaining its performance during online operation, data-driven realization and design of feed-forward fault-tolerant control systems with embedded residual generation are studied. To this end, a parameterized and data-driven realization form of stable image representation in a feedback control loop is derived first. On this basis, a feed-forward controller design scheme is proposed for fault-tolerant purpose. It is followed by a recursive approach for online tuning the feed-forward controller in case of malfunctions, which is triggered by a fault detection scheme based on the so-called stable kernel representation. The effectiveness of the proposed fault-tolerant method is demonstrated by a case study on the laboratory three-tank system.

A Broad Learning Aided Data-Driven Framework of Fast Fault Diagnosis for High-Speed Trains

This paper proposes a new fault detection and diagnosis (FDD) architecture for high-speed trains, whose core is a modified broad learning system (BLS). This architecture is a data-driven realization, which enables fast and accurate FDD by effective feature extraction for online implementation. Under the proposed architecture, multiple FDD methods can be developed because of its inherent scalability.

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

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

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.

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

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 Fault Detection Approach for Nonlinear Systems Based on Data-Driven Realizations of Fuzzy Kernel Representations

This paper is devoted to the data-driven fault detection of nonlinear systems. For our purpose, the definition of Takagi–Sugeno fuzzy data-driven forms of kernel representations for nonlinear systems is introduced first, which builds the basis of our work. The major contributions consist of two parts. In the first part, a data-driven method for fuzzy process modeling is proposed, and associated with it, some modeling issues are addressed with the aid of the so-called randomized algorithm technique in the probabilistic framework. It is followed by a data-driven realization of fuzzy kernel representation and its implementation in the fault detection system design. To link the data-driven methods to the well-established observer-based fault detection approaches, the recursive form of the fuzzy kernel representation is proposed. In the second part, the fuzzy-observer-based fault detection design scheme is investigated based on the recursive fuzzy kernel representation. The main results of our study are illustrated by an experimental study on the laboratory setup of a three-tank system.

Data-driven Evolution Equation Reconstruction for Parameter-Dependent Nonlinear Dynamical Systems.

When studying observations of chemical reaction dynamics, closed form equations based on a putative mechanism may not be available. Yet when sufficient data from experimental observations can be obtained, even without knowing what exactly the physical meaning of the parameter settings or recorded variables are, data-driven methods can be used to construct minimal (and in a sense, robust) realizations of the system. The approach attempts, in a sense, to circumvent physical understanding, by building intrinsic "information geometries" of the observed data, and thus enabling prediction without physical/chemical knowledge. Here we use such an approach to obtain evolution equations for a data-driven realization of the original system - in effect, allowing prediction based on the informed interrogation of the agnostically organized observation database. We illustrate the approach on observations of (a) the normal form for the cusp singularity, (b) a cusp singularity for the nonisothermal CSTR, and (c) a random invertible transformation of the nonisothermal CSTR, showing that one can predict even when the observables are not "simply explainable" physical quantities. We discuss current limitations and possible extensions of the procedure.

A Data-Driven Computation Method for the Gap Metric and the Optimal Stability Margin

Gap metric and stability margin have been proven as important model-based analysis tools for linear time-invariant (LTI) systems. Due to the need for an accurate model, both the gap metric and the optimal stability margin are mostly used for offline analysis. In online analysis, accurate models are rarely available, whereas measurement data could be easily obtained from the systems under consideration. Therefore, in this paper, an approach toward the calculation of the gap metric and the optimal stability margin based on the available measurement data of LTI systems is proposed. A data-driven realization of the so-called stable kernel and stable image representation serves as the foundation of this framework.

Data-Driven Monitoring and Safety Control of Industrial Cyber-Physical Systems: Basics and Beyond

Industrial cyber-physical systems (ICPSs) are the backbones of Industry 4.0 and as such, have become a core transdisciplinary area of research, both in industry and academia. New challenges brought about by the growing scale and complexity of systems, insufficient information exchange, and the exploitation of knowledge available have started threatening the overall system safety and stability. This work is motivated by these challenges and the strategic and practical demands of developing ICPSs for safety-critical systems such as the intelligent factory and the smart grid. It investigates the current status of research in ICPS monitoring and control, and reviews the recent advances in monitoring, fault diagnosis, and control approaches based on data-driven realization, which can take full advantage of the abundant data available from past observations and those collected online in real time. The practical requirements in the typical ICPS applications are summarized as the major issues to be addressed for the monitoring and the safety control tasks. The key challenges and the research directions are proposed as references to the future work.

Recursive Subspace-based Predictive Control and Its Application to Fault-tolerant Control

This paper investigates the data-driven realization of predictive controllers, and its application to fault-tolerant control. With the aid of subspace identification method, the subspace predictor is first derived in the closed-loop setup. To cope with the change in the process, a recursive algorithm is adopted to recursive update the subspace matrices. The data-driven predictive controller is designed by seeking the solution of the quadratic programming problem, without the information of the predesigned controller. Then, it is applied to fault-tolerant control by implementing the recursive subspace predictor. In the end, the effectiveness of the proposed method is verified by a case study on the three-tank system.

Data-driven compensation method for sensor drift faults in digital PID systems with unknown dynamics

This paper investigates the problem of compensating for the slow-changing sensor drift failures occurring in digital PID systems with unknown dynamics. It is extremely difficult to ensure the tracking performance of the faulty systems, due to the system models unavailable, the measurements corrupted by the faults, and the impact of the sensor failures propagated under feedback control. Therefore, the existing data-driven fault-tolerant control (FTC) methods are not capable of dealing with the above problem. Contrary to the current state-of-the-art, a novel residual generator structure is devised. Furthermore, its data-driven realization is accomplished, along with the convergence analysis of the proposed closed-loop recursive identification algorithm. On this basis, such failures can be estimated continuously from the residual signals, using an iterative estimation procedure, the convergence of whose mean-square estimation error is theoretically proven. As a result, the effect of the aforementioned failures on the tracking properties is eliminated with the aid of a fault detection mechanism and based on the tracking error signal corrected with the estimated faults. Finally, the effectiveness and merits of the resultant data-driven FTC algorithm are validated by the continuous stirred tank heater benchmark process.

Data-driven interpolation of dynamical systems with delay

We present a data-driven realization for systems with delay, which generalizes the Loewner framework. The realization is obtained with low computational cost directly from measured data of the transfer function. The internal delay is estimated by solving a least-square optimization over some sample data. Our approach is validated by several examples, which indicate the need for preserving the delay structure in the reduced model.

Data-Driven Approach of KPI Monitoring and Prediction with Application to Wastewater Treatment Process

In this paper, a data-driven scheme of key performance indicator (KPI) monitoring, prediction and KPI related fault detection is applied to the wastewater treatment process (WWTP). By means of a data-driven realization of the so-called left coprime factorization (LCF) of the process, the efficient monitoring and prediction of chemical oxygen demand (COD) concentration in the effluent flow are realized both for the situation that COD is measurable and unmeasurable. The well established Benchmark Simulation Model no. 1 (BSM1) is utilized for the demonstration of the effectiveness of this approach.

Data-driven realizations of kernel and image representations and their application to fault detection and control system design

This paper deals with the data-driven design of observer-based fault detection and control systems. We first introduce the definitions of the data-driven forms of kernel and image representations. It is followed by the study of their identification. In the context of a fault-tolerant architecture, the design of observer-based fault detection, feed-forward and feedback control systems are addressed based on the data-driven realization of the kernel and image representations. Finally, the main results are demonstrated on the laboratory continuous stirred tank heater (CSTH) system.