Trends in extreme learning machines

Structural systems often show nonlinear behavior under severe excitations generated by natural hazards. In that condition, the restoring force becomes highly nonlinear showing significant hysteresis. The hereditary nature of this nonlinear restoring force indicates that the force cannot be described as a function of the instantaneous displacement and velocity. Accordingly, many hysteretic restoring force models were developed to include the time dependent nature using a set of differential equations. This survey contains a review of the past, recent developments and implementations of the Bouc-Wen model which is used extensively in modeling the hysteresis phenomenon in the dynamically excited nonlinear structures.

The Hysteresis Bouc-Wen Model, a Survey

Piezo-actuated stages have become more and more promising in nanopositioning applications due to the excellent advantages of the fast response time, large mechanical force, and extremely fine resolution. Modeling and control are critical to achieve objectives for high-precision motion. However, piezo-actuated stages themselves suffer from the inherent drawbacks produced by the inherent creep and hysteresis nonlinearities and vibration caused by the lightly damped resonant dynamics, which make modeling and control of such systems challenging. To address these challenges, various techniques have been reported in the literature. This paper surveys and discusses the progresses of different modeling and control approaches for piezo-actuated nanopositioning stages and highlights new opportunities for the extended studies.

Modeling and Control of Piezo-Actuated Nanopositioning Stages: A Survey

The partitional clustering concept started with K-means algorithm which was published in 1957. Since then many classical partitional clustering algorithms have been reported based on gradient descent approach. The 1990 kick started a new era in cluster analysis with the application of nature inspired metaheuristics. After initial formulation nearly two decades have passed and researchers have developed numerous new algorithms in this field. This paper embodies an up-to-date review of all major nature inspired metaheuristic algorithms employed till date for partitional clustering. Further, key issues involved during formulation of various metaheuristics as a clustering problem and major application areas are discussed.

A survey on nature inspired metaheuristic algorithms for partitional clustering

Recursive algorithms where random observations enter are studied in a fairly general framework. An important feature is that the observations may depend on previous ?outputs? of the algorithm. The considered class of algorithms contains, e.g., stochastic approximation algorithms, recursive identification algorithms, and algorithms for adaptive control of linear systems. It is shown how a deterministic differential equation can be associated with the algorithm. Problems like convergence with probality one, possible convergence points and asymptotic behavior of the algorithm can all be studied in terms of this differential equation. Theorems stating the precise relationships between the differential equation and the algorithm are given as well as examples of applications of the results to problems in identification and adaptive control.

/pdf/analysis-of-recursive-stochastic-algorithms-2jezx55px8.pdf

Analysis of Recursive Stochastic Algorithms

A method for the identification of the rate-dependent hysteresis in piezoceramic actuators is proposed. In this approach, both a so-called generalized gradient of the output with respect to the input of the hysteresis and the derivative of the input that represents the frequency change of the input are introduced into the input space. Then an expanded input space is established. Thus, the multi-valued mapping of the rate-dependent hysteresis can be transformed into a one-to-one mapping based on the expanded of the input space. In this case, the neural network method can be applied to the modeling of the rate-dependent hysteresis. Finally, the experimental results are presented to illustrate the performance of the proposed approach.

A neural networks based model for rate-dependent hysteresis for piezoceramic actuators

A two-stage genetic algorithm for automatic clustering

Neural-network-based d-step-ahead predictors for nonlinear systems with time delay

A neural network based approach of identification for Preisach-type hysteresis is proposed. In this method, a hysteretic operator is introduced to transform the multi-valued mapping of hysteresis into a one-to-one mapping so that neural networks can be applied to the approximation of the behavior of hysteresis. The proposed model has a simple architecture that simplifies identification procedure and is available to different operating conditions. Finally, an example of simulation and the result of modeling the hysteresis existing in a piezoelectric actuator based on the proposed method are presented.

Neural network based identification of Preisach-type hysteresis in piezoelectric actuator using hysteretic operator

In this paper, a modeling method of XY micropositioning stage with piezoelectric actuators is proposed. In the modeling scheme, a sandwich model consists of both input and output linear submodels, and an embedded neural-network-based hysteresis submodel is used to describe the motion behavior of each axis of the stage. Moreover, a neural-network-based submodel is constructed to describe the nonlinear interactive dynamics caused by the movement of another axis. Then, a tracking control scheme combined with a nonlinear decoupling control is proposed to compensate for the effect of the interactions between axes and track the reference trajectory. Then, the robust design method for the tracking and decoupling control is discussed. Finally, the experimental results on an XY micropositioning stage are presented.

Yonghong Tan

Papers

A neural networks based model for rate-dependent hysteresis for piezoceramic actuators

A two-stage genetic algorithm for automatic clustering

Neural-network-based d-step-ahead predictors for nonlinear systems with time delay

Neural network based identification of Preisach-type hysteresis in piezoelectric actuator using hysteretic operator

Nonlinear Modeling and Decoupling Control of XY Micropositioning Stages With Piezoelectric Actuators