Deep learning and its applications to machine health monitoring

This paper studies a number of quantized feedback design problems for linear systems. We consider the case where quantizers are static (memoryless). The common aim of these design problems is to stabilize the given system or to achieve certain performance with the coarsest quantization density. Our main discovery is that the classical sector bound approach is nonconservative for studying these design problems. Consequently, we are able to convert many quantized feedback design problems to well-known robust control problems with sector bound uncertainties. In particular, we derive the coarsest quantization densities for stabilization for multiple-input-multiple-output systems in both state feedback and output feedback cases; and we also derive conditions for quantized feedback control for quadratic cost and H/sub /spl infin// performances.

The sector bound approach to quantized feedback control | NOVA. The University of Newcastle's Digital Repository

Applications of machine learning to machine fault diagnosis: A review and roadmap

The free-weighting matrix and integral-inequality methods are widely used to derive delay-dependent criteria for the stability analysis of time-varying-delay systems because they avoid both the use of a model transformation and the technique of bounding cross terms. This technical note presents a new integral inequality, called a free-matrix-based integral inequality, that further reduces the conservativeness in those methods. It includes well-known integral inequalities as special cases. Using it to investigate the stability of systems with time-varying delays yields less conservative delay-dependent stability criteria, which are given in terms of linear matrix inequalities. Two numerical examples demonstrate the effectiveness and superiority of the method.

Free-Matrix-Based Integral Inequality for Stability Analysis of Systems With Time-Varying Delay

In modern industries, machine health monitoring systems (MHMS) have been applied wildly with the goal of realizing predictive maintenance including failures tracking, downtime reduction, and assets preservation. In the era of big machinery data, data-driven MHMS have achieved remarkable results in the detection of faults after the occurrence of certain failures (diagnosis) and prediction of the future working conditions and the remaining useful life (prognosis). The numerical representation for raw sensory data is the key stone for various successful MHMS. Conventional methods are the labor-extensive as they usually depend on handcrafted features, which require expert knowledge. Inspired by the success of deep learning methods that redefine representation learning from raw data, we propose local feature-based gated recurrent unit (LFGRU) networks. It is a hybrid approach that combines handcrafted feature design with automatic feature learning for machine health monitoring. First, features from windows of input time series are extracted. Then, an enhanced bidirectional GRU network is designed and applied on the generated sequence of local features to learn the representation. A supervised learning layer is finally trained to predict machine condition. Experiments on three machine health monitoring tasks: tool wear prediction, gearbox fault diagnosis, and incipient bearing fault detection verify the effectiveness and generalization of the proposed LFGRU.

Machine Health Monitoring Using Local Feature-Based Gated Recurrent Unit Networks

This paper provides an overview of the recent developments in data-based techniques focused on modern industrial applications. As one of the hottest research topics for complicated processes, the data-based techniques have been rapidly developed over the past two decades and widely used in numerous industrial sectors nowadays. The core of data-based techniques is to take full advantage of the huge amounts of available process data, aiming to acquire the useful information within. Compared with the well-developed model-based approaches, data-based techniques provide efficient alternative solutions for different industrial issues under various operating conditions. The main objective of this paper is to review and summarize the recent achievements in data-based techniques, especially for complicated industrial applications, thus providing a referee for further study on the related topics both from academic and practical points of view. This paper begins with a brief evolutionary overview of data-based techniques in the last two decades. Then, the methodologies only based on process measurements and the model-data integrated techniques will be further introduced. The recent developments for modern industrial applications are, respectively, presented mainly from perspectives of monitoring and control. The new trends of data-based technique as well as potential application fields are finally discussed.

Data-Based Techniques Focused on Modern Industry: An Overview

This technical note focuses on analyzing a new model transformation of uncertain linear discrete-time systems with time-varying delay and applying it to robust stability analysis. The uncertainty is assumed to be norm-bounded and the delay intervally time-varying. A new comparison model is proposed by employing a new approximation for delayed state, and then lifting method and simple Lyapunov-Krasovskii functional method are used to analyze the scaled small gain of this comparison model. This new approximation results in a much smaller error than the existing ones. Based on the scaled small gain theorem, new stability criteria are proposed in terms of linear matrix inequalities. Moreover, it is shown that the obtained conditions can be established through direct Lyapunov method. Two numerical examples are presented to illustrate the effectiveness and superiority of our results over the existing ones.

A New Model Transformation of Discrete-Time Systems With Time-Varying Delay and Its Application to Stability Analysis

Consensus of multi-agent systems via fully distributed event-triggered control

This article researches the problem of finite frequency (FF) H∞ filtering for linear discrete-time state-delayed systems. The disturbance is assumed to reside in low/middle/high frequency ranges. To reduce the conservatism of the results, delay-partitioning idea is used to derive a new FF bounded real lemma (BRL). By applying the generalized Kalman-Yakubovich-Popov lemma, two equivalent approaches to the proof of the proposed FF BRL are given, respectively, starting from transfer function and Lyapunov-Krasovskii functional. A new FF H∞ filter design method is proposed in terms of solving a set of linear matrix inequalities. Finally, a numerical example clearly demonstrates the merits and effectiveness of the proposed method.

${H}_{\infty }$ Filtering for Discrete-Time State-Delayed Systems With Finite Frequency Specifications

This article systematically studies consensus of linear multiagent systems (MASs) on directed graphs through adaptive event-triggered control. It presents innovative adaptive event-triggered state-feedback protocols with novel composite event-triggering conditions. Two specific designs in terms of different event-triggering conditions and laws of adaption are first discussed for linear MASs on strongly connected directed graphs, which are then extended to general directed graphs that contain a spanning tree. Moreover, another adaptive event-triggered protocol is proposed for solving leader–follower consensus that tracks a leader of a bounded control input. The protocols inherit the merits of both adaptive control and event-triggered control: the protocols can be implemented in a fully distributed way, since the Laplacian is avoided in design, and each agent only needs to know the relative information between neighbors at discrete instants determined by event-triggering conditions. Compared with the existing related results, the proposed protocols are applicable for linear MASs on general directed graphs, and moreover, the time-dependent term in the event-triggering conditions is allowed to be a class of positive $L_1$ functions. Two numerical examples clearly verify the effectiveness of the proposed protocols.

Xianwei Li

Papers

Data-Based Techniques Focused on Modern Industry: An Overview

A New Model Transformation of Discrete-Time Systems With Time-Varying Delay and Its Application to Stability Analysis

Consensus of multi-agent systems via fully distributed event-triggered control

${H}_{\infty }$ Filtering for Discrete-Time State-Delayed Systems With Finite Frequency Specifications

Adaptive Event-Triggered Consensus of Multiagent Systems on Directed Graphs