Evolutionary System Identification Research Articles

A new binary genetic programming approach to design public transportation systems according to transit-oriented development criteria

This study introduces a new evolutionary approach called binary genetic programming (BGP) to design and assess public transportation systems from a sustainable development perspective. The BGP combines evolutionary system identification techniques with k-fold cross-validation to obtain an accurate model between the land use and transportation parameters from a sustainable urban development point of view. To assess the new model, two public transportation systems including the new tram line of Antalya (Turkey) and the bus rapid transit line of Bhopal (India) were considered. The model was applied to classify the transportation systems into transit-oriented development (TOD) and non-TOD. The solutions generated by the new model were compared with those of classic decision tree (DT) as well as the state-of-the-art random forest (RF) models evolved as the benchmarks in this study. The results showed that the BGP is highly efficient and may provide less than 5% classification error. It is superior to the DT and RF solutions, which typically require higher datasets to avoid overfitting. Furthermore, the explicit formulation of BGP in combination with the multicriteria evaluation method increases human insight on the factors affecting the design of public transportations from a sustainable urban development point of view.

Framework of model selection criteria approximated genetic programming for optimization function for renewable energy systems

Abstract For the realization of complex renewable energy systems (such as nano-fluids based direct absorption solar collector), an evolutionary system identification method such as genetic programming (GP) can be applied to develop mathematical models/functional relationships between the process parameters. The system complexity is attributed to interaction among the design variables influencing the outputs. There are also uncertainties in the system due to random and unknown variations in the design and response variables. GP suffers from the higher complexity structure of its solutions and non-optimal convergence, which leads to poor fitness values. Therefore, to address these uncertainties and problems, the framework based on the model selection criteria approximated genetic programming (MSC-GP) is proposed for the formulation of geometry design based thermal efficiency and entropy generation optimization function for direct absorption solar collector (DASC) system. In this proposed method, the four mathematical model selection criteria are used as an approximation for objective functions in GP framework for the evaluation of fitting degree and structure of the model. The results based on statistical measures (best fitness, mean fitness, standard deviation of fitness, number of nodes) show that models obtained from the mathematical selection criteria, Predicted Residual error sum of squares (PRESS), have performed the best. Based on Pareto front analysis of PRESS function, it is found that the best objective values and the number of nodes of models (complexity) follows more or less gradually slow increasing trend which is a good symbolic desirable sign of minimal increase of complexity of model with a decrease in objective values as the values of generation increases. The results of the sensitivity analysis show that the main factor affecting the efficiency of DASC is its geometry of the structure. 3-D interaction analysis shows that increasing the thickness, length and reducing the width of the collector can make the system maintain its higher thermal efficiency and a smaller entropy generation, which is useful for the optimized operation of DASC. Non-dominated sorting genetic algorithm-II (NSGA-II) is applied in the acquisition of the optimal geometric settings of DASC system based on the selected models. The optimal settings achieved is 5 cm in length, 5 cm in width, and 2 cm in thickness. Systems when operated using these settings results in a satisfactory performance with 77.8117% in thermal efficiency and 6.0004E+3 in entropy generation).

On evolutionary system identification with applications to nonlinear benchmarks

Abstract This paper presents a record of the participation of the authors in a workshop on nonlinear system identification held in 2016. It provides a summary of a keynote lecture by one of the authors and also gives an account of how the authors developed identification strategies and methods for a number of benchmark nonlinear systems presented as challenges, before and during the workshop. It is argued here that more general frameworks are now emerging for nonlinear system identification, which are capable of addressing substantial ranges of problems. One of these frameworks is based on evolutionary optimisation (EO); it is a framework developed by the authors in previous papers and extended here. As one might expect from the ‘no-free-lunch’ theorem for optimisation, the methodology is not particularly sensitive to the particular (EO) algorithm used, and a number of different variants are presented in this paper, some used for the first time in system identification problems, which show equal capability. In fact, the EO approach advocated in this paper succeeded in finding the best solutions to two of the three benchmark problems which motivated the workshop. The paper provides considerable discussion on the approaches used and makes a number of suggestions regarding best practice; one of the major new opportunities identified here concerns the application of grey-box models which combine the insight of any prior physical-law based models (white box) with the power of machine learners with universal approximation properties (black box).

An application of evolutionary system identification algorithm in modelling of energy production system

The present work introduces the literature review on System Identification (SI) by classifying it into several fields. The review summarizes the need of evolutionary SI method that automates the model structure selection and its parameter evaluation based on only the system data. In this context, the evolutionary SI approach of genetic programming (GP) is applied in modeling and optimization of cleaner energy system such as direct methanol fuel cell. The functional response of the power density of the fuel cell with respect to input conditions is selected based on the minimum training error. Further, an experimental data is used to validate the robustness of the formulated GP model. The analysis based on 2-D and 3-D parametric procedure is further conducted to reveals insights into functioning of the fuel cell. The pareto front obtained from optimization of model reveals that the operating temperature of 64.5°C, methanol flow rate of 28.04mL/min and methanol concentration of 0.29M are the optimum settings for achieving the maximum power density of 7.36mW/cm2 for DMFC.

Performance evaluation of warping characteristic of fused deposition modelling process

In recent years, fused deposition modelling (FDM) is gaining more popularity due to its distinct advantages in terms of cost-effectiveness, lower build times, and flexibility. Compared to other 3-D printing processes such as SLS, this process does not use any kind of high-intensity laser power to build functional parts out of CAD models and, hence, makes the process much simpler, cheaper, and adaptable. Past studies reveal that productivity of the FDM process can be further increased by effectively controlling its process parameters such as layer thickness, part orientation, extrusion temperature, and so on. In this regard, many authors have investigated the optimal parameter settings for improving part strength, surface finish, wear, and fatigue properties of FDM made prototypes. However, warping performance behavior has got very recent attention due to complex heat transfer mechanism involved during this process. Experimental investigations are necessary to understand the deformation behavior of prototypes. In addition, the quantification and optimization of warp deformation along with dimensional error poses a challenging multi-objective optimization problem. Therefore, this work proposes an evolutionary system identification (SI) approach to explicitly quantify the warp deformation and dimensional error based on the four inputs such as line width compensation, extrusion velocity, filling velocity, and layer thickness of FDM prototypes. The two models’ performance analysis comprising of error metrics evaluation, cross-validation, and hypothesis tests is performed to validate its robustness. The analysis concluded that the layer thickness and extrusion velocity influence the warp deformation and, while filling velocity and line width compensation, influences the dimensional error the most.

GENERALIZED CELLULAR NEURAL NETWORKS (GCNNs) CONSTRUCTED USING PARTICLE SWARM OPTIMIZATION FOR SPATIO-TEMPORAL EVOLUTIONARY PATTERN IDENTIFICATION

Particle swarm optimization (PSO) is introduced to implement a new constructive learning algorithm for training generalized cellular neural networks (GCNNs) for the identification of spatio-temporal evolutionary (STE) systems. The basic idea of the new PSO-based learning algorithm is to successively approximate the desired signal by progressively pursuing relevant orthogonal projections. This new algorithm will thus be referred to as the orthogonal projection pursuit (OPP) algorithm, which is in mechanism similar to the conventional projection pursuit approach. A novel two-stage hybrid training scheme is proposed for constructing a parsimonious GCNN model. In the first stage, the orthogonal projection pursuit algorithm is applied to adaptively and successively augment the network, where adjustable parameters of the associated units are optimized using a particle swarm optimizer. The resultant network model produced at the first stage may be redundant. In the second stage, a forward orthogonal regression (FOR) algorithm, aided by mutual information estimation, is applied to refine and improve the initially trained network. The effectiveness and performance of the proposed method is validated by applying the new modeling framework to a spatio-temporal evolutionary system identification problem.

An intelligent condition‐based maintenance scheduling model

PurposeCondition‐based maintenance (CBM) has increasingly drawn attention in industry because of its many benefits. The CBM problem is a kind of state‐dependent scheduling problem, and is very hard to solve within the conventional Markov decision process framework. The purpose of this paper is to present an intelligent CBM scheduling model for which incremental decision tree learning as an evolutionary system identification model and dynamic programming as a control model are developed.Design/methodology/approachTo fully exploit the merits of CBM, this paper models CBM scheduling as a state‐dependent, sequential decision‐making problem. The objective function is formulated as the minimization of the total maintenance cost. Instead of interpreting the problem within the widely used Markovian framework, this paper proposes an intelligent maintenance scheduling approach that integrates an incremental decision tree learning method and deterministic dynamic programming techniques.FindingsAlthough the intelligent maintenance scheduling approach proposed in this paper does not guarantee an optimal scheduling policy from a mathematical viewpoint, it is verified through a simulation‐based experiment that the intelligent maintenance scheduler is capable of providing a good scheduling policy that can be used in practice.Originality/valueThis paper presents an intelligent maintenance scheduler. As a system identification model, we devise a new incremental decision tree learning method by which interaction patterns among attributes and machine condition are disclosed in an evolutionary manner. A deterministic dynamic programming technique is then applied to select the best safe state in terms of the total maintenance cost.

Evolutionary modal identification utilizing coupled shear–flexural response—implication for multistory buildings. Part II : Application

AbstractA novel solution of dynamic response of multistory buildings is utilized in an evolutionary system identification algorithm for rapid and robust estimation of dynamic characteristics of instrumented structures. The method is fully automated such that it can be used virtually without delay in the aftermath of an urban earthquake. The application of the proposed method and its capabilities are exhibited through numerous examples of building structures shaken by multiple earthquakes in their lives; a number of them are amongst the most intensively studied instrumented buildings. The introduction of stiffness ratio into the reduced‐order dynamic response algorithm that is used in this study (Miranda and Taghavi, 2005) makes it possible to monitor any loss of flexural and/or shear stiffness in a structure subject to strong ground shaking. The system identification scheme presented here is part of a comprehensive structural health‐monitoring software system that is developed for the instrumented building structures at the R&D Department of John A. Martin & Associates with collaboration with research universities. Copyright © 2006 John Wiley & Sons, Ltd.

Evolutionary modal identification utilizing coupled shear–flexural response—implication for multistory buildings. Part I : Theory

AbstractA novel solution of dynamic response of multistory buildings is utilized in an evolutionary system identification algorithm for rapid and robust estimation of dynamic characteristics of instrumented building structures. The empirical characteristics obtained can be used for detection of possible seismic damage and for validating design assumptions with actual recorded structural response. Most structural identification procedures proposed to date only provide some estimates of the modal quantities from which inference to commencement of damage may not be trivial. In this proposed method, besides modal properties such as mode shapes and periods, an overall estimate of the participation of shear to flexural deformations in the lateral response of a building structure is examined. Therefore, any alteration in the mode of response between flexural and shear dominated can be monitored in a time‐varying fashion. The method is fully automated such that it can be used virtually without any delay in the aftermath of an urban earthquake. In a companion paper (Alimoradi and Naeim, 2006), the application of the proposed methodology and its capabilities are exhibited through numerous examples on building structures shaken by multiple earthquakes in their lives; many of them are amongst the most intensively studied instrumented building worldwide. The structural identification work presented here is a component of a comprehensive structural health‐monitoring system for instrumented building structures. Copyright © 2006 John Wiley & Sons, Ltd.

Nonlinear System Identification for Mechatronics Systems by Genetic Algorithm

This paper presents an evolutionary system identification strategy for mechatronics systems which include various nonlinearities. In the research, the saturation in power converters and the friction in mechanisms are considered as the nonlinear elements, some of which are generally difficult to detect and/or identify directly. The proposed scheme can evolutionally determine the structure of both linear and nonlinear elements in the system, where the observable input/output variables with time delay are used to express the linear components, and power series of the variables and nonlinear functions are used to express the nonlinear ones, respectively. In the evolutionary process, Genetic Algorithm (GA) is applied to optimize the combination of these variables and, as a result, the sub-optimal mathematical model for the whole system can be achieved. The effectiveness of the proposed scheme is verified by experiments using a 2-mass resonant vibration system.

Evolutionary system identification in the time domain

This paper develops a genetic algorithm based technique that may be used to identify multivariable system identification directly from plant step response data. Using this technique, globally optimized models for linear and non-linear systems can be identified without the need for a differentiable cost function or linearly separable parameters. Results are validated against a benchmark identification problem and a laboratory test-rig for continuous and discrete-time systems.

Evolutionary programming IV: Proceedings of the fourth annual conference on evolutionary programming

From the Publisher: March 1-3, 1995, San Diego, California Evolutionary programming is one of the predominate algorithms withing the rapidly expanding field of evolutionary computation. These edited contributions to the Fourth Annual Conference on Evolutionary Programming are by leading scientists from academia, industry, and defense. The papers describe both the theory and practical application of evolutionary programming, as well as other methods of evolutionary computation including evolution strategies, genetic algorithms, genetic programming, and cultural algorithms. Topics include: Novel Areas of Evolutionary Programming and Evolution Strategies. Evolutionary Computation with Medical Applications. Issues in Evolutionary Optimization Pattern Discovery, Pattern Recognition, and System Identification. Hierarchical Levels of Learning. Self-Adaptation in Evolutionary Computation. Morphogenic Evolutionary Computation. Issues in Evolutionary Optimization. Evolutionary Applications to VLSI and Part Placement. Applications of Evolutionary Computation to Biology and Biochemistry Control. Applications of Evolutionary Computation. Genetic and Inductive Logic Programming. Genetic Neural Networks. The Future of Evolutionary Computation. A Bradford Book. Complex Adaptive Systems series