With uncertainty, reliability assessment is fundamental in structural optimization, because optimization itself is often against safety. To avoid Monte Carlo methods, the Reliability Index Approach (RIA) approximates ...
详细信息
With uncertainty, reliability assessment is fundamental in structural optimization, because optimization itself is often against safety. To avoid Monte Carlo methods, the Reliability Index Approach (RIA) approximates the structural failure probability and is formulated as a minimization problem, usually solved with fast gradient-methods, at the expense of local convergence, or even divergence, particularly for highly dimensional problems and implicit physical models. In this paper, a new procedure for global convergence of the RIA, with practical efficiency, is presented. Two novel evolutionary operators and a mixed real-binary genotype, suitable to hybridize any evolutionary Algorithm with elitist strategy, are developed. As an example, a shell laminate structure is presented and the results validated, showing good convergence and efficiency. The proposed method is expected to set the basis for further developments on the design optimization of more complex structures with multiple failure criteria.
The computation of parameters for group contribution models in order to predict thermodynamic properties usually leads to a multiparameter optimization problem. The model parameters are calculated using a regression m...
详细信息
The computation of parameters for group contribution models in order to predict thermodynamic properties usually leads to a multiparameter optimization problem. The model parameters are calculated using a regression method and applying certain error criteria. A complex objective function occurs for which an optimization algorithm has to find the global minimum. For simple increment or group contribution models it is often sufficient to use simplex or gradient algorithms. However, if the model contains complex terms such as sums of exponential expressions, the search of the global or even of an fairly good optimum becomes rather difficult. evolutionary algorithms represent a possibility for solving such problems. In most cases, the use of biological principles for optimization problems yields satisfactory results. A genetic algorithm and an optimization method using an evolutionary strategy were programmed at the Institute for Thermodynamics at the University of Dortmund and were tested with an Enthalpy Based Group Contribution Model (EBGCM). The results obtained with these procedures were compared with the results obtained using a simplex algorithm. A test system was created and the corresponding objective function was examined in detail. For this purpose, 3D-plots were produced by varying two out of six model parameters. In this paper, the development of a genetic algorithm is presented and the fitting procedure of the model parameters is discussed. Part 2 of this article series will deal with the efficiency of evolutionary strategies applied to such a prototype of non-linear regression problems. (C) 1998 Published by Elsevier Science Ltd. All rights reserved.
This paper describes the novel application of an evolutionary algorithm to discriminate Parkinson's patients from age-matched controls in their response to simple figure-copying tasks. The reliable diagnosis of Pa...
详细信息
This paper describes the novel application of an evolutionary algorithm to discriminate Parkinson's patients from age-matched controls in their response to simple figure-copying tasks. The reliable diagnosis of Parkinson's disease is notoriously difficult to achieve with misdiagnosis reported to be as high as 25% of cases. The approach described in this paper aims to distinguish between the velocity profiles of pen movements of patients and controls to identify distinguishing artifacts that may be indicative of the Parkinson's symptom bradykinesia. Results are presented for 12 patients with Parkinson's disease and 10 age-match controls. An algorithm was evolved using half the patient and age-matched control responses, which was then successfully used to correctly classify the remaining responses. A more rigorous "leave one out" strategy was also applied to the test data with encouraging results.
The computation of parameters of group contribution models in order to predict thermodynamic properties usually leads to a multiparameter optimization problem where the model parameters are calculated using a regressi...
详细信息
The computation of parameters of group contribution models in order to predict thermodynamic properties usually leads to a multiparameter optimization problem where the model parameters are calculated using a regression method. A complex objective function occurs for which an optimization algorithm has to find the global minimum. Simple increment or simple group contribution models often result in unimodal regression problems, for which deterministically acting algorithms are suitable. If the model contains parameters in complex terms such as sums of exponential expressions, the optimization problem will be a nonlinear regression problem which often results in a multimodal optimization problem. In this case the search of the global or at least a fairly good optimum becomes rather difficult. evolutionary algorithms are suitable for solving such multimodal problems. Friese, T., Ulbig, P., & Schulz, S. (1998). Use of evolutionary algorithms for the calculation of group contribution parameters in order to predict thermodynamic properties (Part 1): Genetic algorithms. Computers and Chemical Engineering 22(11), 1559-1572 showed that the efficiency of genetic algorithms applied to the presented optimization problem, this paper shows that evolution strategies are suitable, as well. This work first describes the typical mode of acting of evolution strategies before a new variant, the so-called encapsulated evolution strategy using a multidimensional step-length control is introduced. This new type of strategy proved to be superior to conventional evolution strategies and genetic algorithms. In order to benefit from this new algorithm for other similar optimization problems, an optimum strategy type is determined and analyzed with the help of two visualized test systems representing the complex of optimization problems, which nonlinear parameter fittings of group contribution model parameters belong to. (C) 1999 Elsevier Science Ltd. All rights reserved.
Dynamic optimization problems involving two or more conflicting objectives appear in many real-world scenarios, and more cases are expected to appear in the near future with the increasing interest in the analysis of ...
详细信息
Dynamic optimization problems involving two or more conflicting objectives appear in many real-world scenarios, and more cases are expected to appear in the near future with the increasing interest in the analysis of streaming data sources in the context of Big Data applications. However, approaches combining dynamic multi objective optimization with preference articulation are still scarce. In this paper, we propose a new dynamic multi-objective optimization algorithm called InDM2 that allows the preferences of the decision maker (DM) to be incorporated into the search process. When solving a dynamic multi-objective optimization problem with InDM2, the DM can not only express her/his preferences by means of one or more reference points (which define the desired region of interest), but these points can be also modified interactively. InDM2 is enhanced with methods to graphically display the different approximations of the region of interest obtained during the optimization process. In this way, the DM is able to inspect and change, in optimization time, the desired region of interest according to the information displayed. We describe the main features of InDM2 and detail how It is implemented. Its performance is illustrated using both synthetic and real-world dynamic multi-objective optimization problems.
In this research, we synthesized an artificial neural network (ANN) with three metaheuristic algorithms, namely particle swarm optimization (PSO) algorithm, imperialist competition algorithm (ICA), and genetic algorit...
详细信息
In this research, we synthesized an artificial neural network (ANN) with three metaheuristic algorithms, namely particle swarm optimization (PSO) algorithm, imperialist competition algorithm (ICA), and genetic algorithm (GA) to achieve a more accurate prediction of 28-day compressive strength of concrete. Seven input parameters (including cement, water, slag, fly ash, superplasticizer (SP), coarse aggregate (CA), and fine aggregate (FA)) were considered for this work. 80% of data (82 samples) were used to feed ANN, PSO-ANN, ICA-ANN, and GA-ANN models, and their performance was evaluated using the remaining 20% (21 samples). Referring to the executed sensitivity analysis, the best complexities for the PSO and GA were indicated by the population size = 450 and for the ICA by the population size = 400. Also, to assess the accuracy of the used predictors, the accuracy criteria of root mean square error (RMSE), coefficient of determination (R-2), and mean absolute error (MAE) were defined. Based on the results, applying the PSO, ICA, and GA algorithms led to increasing R-2 in the training and testing phase. Also, the MAE and RMSE of the conventional MLP experienced significant decrease after the hybridization process. Overall, the efficiency of metaheuristic science for the mentioned objective was deduced in this research. However, the combination of ANN and ICA enjoys the highest accuracy and could be a robust alternative to destructive and time-consuming tests.
This paper introduces a software tool based on illustrative applications for the development, analysis and application of multiobjective evolutionary algorithms. The multiobjective evolutionary algorithms tool (MOEAT)...
详细信息
This paper introduces a software tool based on illustrative applications for the development, analysis and application of multiobjective evolutionary algorithms. The multiobjective evolutionary algorithms tool (MOEAT) written in C# using a variety of multiobjective evolutionary algorithms (MOEAs) offers a powerful environment for various kinds of optimization tasks. It has many useful features such as visualizing of the progress and the results of optimization in a dynamic or static mode, and decision variable settings. The performance measurements of well-known multiobjective evolutionary algorithms in MOEAT are done using benchmark problems. in addition, two case studies from engineering domain are presented. (C) 2009 Elsevier Ltd. All rights reserved.
This work introduces a new algorithmic trading method based on evolutionary algorithms and portfolio theory. The limitations of traditional portfolio theory are overcome using a multi-period definition of the problem....
详细信息
This work introduces a new algorithmic trading method based on evolutionary algorithms and portfolio theory. The limitations of traditional portfolio theory are overcome using a multi-period definition of the problem. The model allows the inclusion of dynamic restrictions like transaction costs, portfolio unbalance, and inflation. A Monte Carlo method is proposed to handle these types of restrictions. The investment strategies method is introduced to make trading decisions based on the investor's preference and the current state of the market. Preference is determined using heuristics instead of theoretical utility functions. The method was tested using real data from the Mexican market. The method was compared against buy-and-holds and single-period portfolios for metrics like the maximum loss, expected return, risk, the Sharpe's ratio, and others. The results indicate investment strategies perform trading with less risk than other methods. Single-period methods attained the lowest performance in the experiments due to their high transaction costs. The conclusion was investment decisions that are improved when information providing from many different sources is considered. Also, profitable decisions are the result of a careful balance between action (transaction) and inaction (buy-and-hold).
There has been renewed interest in modelling the behaviour of evolutionary algorithms (EAs) by more traditional mathematical objects, such as ordinary differential equations or Markov chains. The advantage is that the...
详细信息
There has been renewed interest in modelling the behaviour of evolutionary algorithms (EAs) by more traditional mathematical objects, such as ordinary differential equations or Markov chains. The advantage is that the analysis becomes greatly facilitated due to the existence of well established methods. However, this typically comes at the cost of disregarding information about the process. Here, we introduce the use of stochastic differential equations (SDEs) for the study of EAs. SDEs can produce simple analytical results for the dynamics of stochastic processes, unlike Markov chains which can produce rigorous but unwieldy expressions about the dynamics. On the other hand, unlike ordinary differential equations (ODEs), they do not discard information about the stochasticity of the process. We show that these are especially suitable for the analysis of fixed budget scenarios and present analogues of the additive and multiplicative drift theorems from runtime analysis. In addition, we derive a new more general multiplicative drift theorem that also covers non-elitist EAs. This theorem simultaneously allows for positive and negative results, providing information on the algorithm's progress even when the problem cannot be optimised efficiently. Finally, we provide results for some well-known heuristics namely Random Walk (RW), Random Local Search (RLS), the (1+1) EA, the Metropolis Algorithm (MA), and the Strong Selection Weak Mutation (SSWM) algorithm.
evolutionary algorithms (EAs) are proficient in solving the controlled, nonlinear multimodal, non-convex problems that limit the use of deterministic approaches. The competencies of EA have been applied in solving var...
详细信息
evolutionary algorithms (EAs) are proficient in solving the controlled, nonlinear multimodal, non-convex problems that limit the use of deterministic approaches. The competencies of EA have been applied in solving various environmental and water resources problems. In this study, the storm water management model (SWMM) was set up to authenticate the capability of the model for simulating catchment response in the upper Damodar River basin. Auto-calibration and validation of SWMM were done for the years 2002-2011 at a daily scale using three EAs: genetic algorithms (GAs), particle swarm optimisation (PSO) and shuffled frog leaping algorithm (SFLA). Statistical parameters like Nash-Sutcliffe effectiveness (NSE), percent bias (PBIAS) and root-mean-squared error-observations standard deviation ratio (RSR) were used to analyse the efficacy of the results. NSE and PBIAS values obtained from GA were superior, with the recorded flow with NSE and PBIAS ranging between 0.63 and 0.69 and between 1.12 and 9.81, respectively, for five discharge locations. The value of RSR was approximately 0 indicating the sensibly exceptional performance of the model. The results obtained from SFLA were robust and superior to PSO. Our results showed the prospective use and blending of the hydrodynamic model with EA would aid the decision-makers in analysing the vulnerability in river watersheds.
暂无评论