Using a modified genetic algorithm to find feasible regions of a desirability function

The multi‐response optimization (MRO) problem in response surface methodology is quite common in applications. Most of the MRO techniques such as the desirability function method by Derringer and Suich are utilized to find one or several optimal solutions. However, in fact, practitioners usually prefer to identify all of the near‐optimal solutions, or all feasible regions, because some feasible regions may be more desirable than others based on practical considerations. In this paper, with benefits from the stochastic property of a genetic algorithm (GA), we present an innovative procedure using a modified GA (MGA), a computational efficient GA with a local directional search incorporated into the GA process, to approximately generate all feasible regions for the desirability function without the limitation of the number of factors in the design space. The procedure is illustrated through a case study. The MGA is also compared with other commonly used methods for determining the set of feasible regions. Using Monte Carlo simulations with two benchmark functions and a case study, it is shown that the MGA can more efficiently determine the set of feasible regions than the GA, grid methods, and the Nelder–Mead simplex algorithm. Copyright © 2011 John Wiley & Sons, Ltd.     

Maximum weight matching and genetic algorithm for fixed-shape facility layout problem

To achieve efficient facility design, the problem of finding an initial slicing tree of a complete graph may influence the layout solutions in many ways. We introduce a maximum weight-matching algorithm to generate the slicing tree, which is used as an initial solution. This initial solution produces modifications to generate alternative layouts for further selection. The system employs a genetic algorithm (GA) as the search engine with a relationship weight function to obtain good solutions. The model is proposed to solve a fixed-shape layout problem. The research has made contributions to two areas. First, it defines a quality function for the clustering technique to generate an initial slicing tree. Second, it designs a process for generating layout alternatives that can take predetermined location constraints and weights based on relationships among facilities into consideration. We compare our initial slicing tree GA with other approaches in the literature. In addition, computational results to demonstrate the performance characteristics of our algorithm are also evaluated.     

Soft computing approach for reliability optimization: State-of-the-art survey

In the broadest sense, reliability is a measure of performance of systems. As systems have grown more complex, the consequences of their unreliable behavior have become severe in terms of cost, effort, lives, etc., and the interest in assessing system reliability and the need for improving the reliability of products and systems have become very important. Most solution methods for reliability optimization assume that systems have redundancy components in series and/or parallel systems and alternative designs are available. Reliability optimization problems concentrate on optimal allocation of redundancy components and optimal selection of alternative designs to meet system requirement. In the past two decades, numerous reliability optimization techniques have been proposed. Generally, these techniques can be classified as linear programming, dynamic programming, integer programming, geometric programming, heuristic method, Lagrangean multiplier method and so on. A Genetic Algorithm (GA), as a soft computing approach, is a powerful tool for solving various reliability optimization problems. In this paper, we briefly survey GA-based approach for various reliability optimization problems, such as reliability optimization of redundant system, reliability optimization with alternative design, reliability optimization with time-dependent reliability, reliability optimization with interval coefficients, bicriteria reliability optimization, and reliability optimization with fuzzy goals. We also introduce the hybrid approaches for combining GA with fuzzy logic, neural network and other conventional search techniques. Finally, we have some experiments with an example of various reliability optimization problems using hybrid GA approach.     

THE OPTIMUM SPEED OF VISUAL INSPECTION USING A RANDOM SEARCH STRATEGY

Choosing a standard speed for visual inspection is difficult using standard work measurement techniques. This paper uses a different approach, taking a model of human functioning in inspection and deriving an optimum speed of working so as to balance the cost of time against the cost of errors. Random search is used as the model and both self-paced and externally-paced conditions are derived for multiple fault types. Optimization using a Golden Section search is used to provide optimum inspection speed.     

A hybrid optimisation model for pallet loading

This study adopts a hybrid approach that integrates the genetic algorithm (GA) and fuzzy logic in order to assist in the generation of an optimal pallet loading plan. The proposed model enables the maximisation of profits for freight forwarders through the most efficient use of space and weight in pallet loading. The model uses fuzzy controllers to determine the numbers and size of cargo units on a pallet as well as the mutation rate in the GA approach within the optimisation process and enables the capture of tacit knowledge vested in industry practitioners. The pragmatic use of the model is illustrated using a freight-forwarding scenario that demonstrates the inherent limitations of the standard GA method, followed by the application of the proposed fuzzy GA model. To further demonstrate the benefits of the hybrid model, simulated annealing and Tabu search are used to benchmark the results achieved using various approaches; the proposed hybrid model is demonstrated to exceed these other approaches in overall performance. The application of the proposed hybrid approach across a range of scenarios is also discussed.     

Optimization of injection moulding conditions with user-definable objective functions based on a genetic algorithm

This paper applies a Genetic Algorithm (GA) method to optimize injection moulding conditions, such as melt temperature, mould temperature and injection time. A GA is very suitable for moulding conditions optimization where complex patterns of local minima are possible. Existing work in the literature has limited versatility because the optimization algorithm is hard-wired with specific objective function. However, for most of the practical applications, the appropriateness of optimization objective functions depends on each specific moulding problem. The paper develops a multi-objective GA optimization strategy, where the objective functions may be defined by the designers, including using different criteria and/or weights. For parts with general quality requirements, an objective function is also recommended with some quality measuring criteria, which are either more accurately represented or cover more moulding defects than those from existing simulation-based optimization approaches. The paper also elaborates on the effective GA attributes suited to moulding conditions optimization, such as population size, crossover rate and mutation rate. A case study demonstrates the effectiveness of the proposed approach and algorithm. The optimization results are compared with those from an exhaustive search method to determine the algorithm's accuracy in finding global optimum. It is found to be favourable.     

The A-Design approach to managing automated design synthesis

This paper presents an approach to managing the complexities of design synthesis techniques. Often computational approaches model design as a search process or as an optimization problem. The nature of such techniques, however, does not allow the user to interact with the search process once it has begun. Furthermore, traditional computational search lacks the ability to learn from experience. While computational search techniques have the ability to search many design alternatives quickly, the human engineer can often arrive at a more elegant and robust solution by applying heuristics learned from past experiences. The method introduced here improves the capabilities of design synthesis methods by allowing for user input and by making decisions based on previous experience. In studying past candidate designs the process learns to be more effective in searching for solutions. Results show how such a technique improves the quality of designs and efficiency of an existing search process.     

Simulated annealing based parallel genetic algorithm for facility layout problem

The facility layout problem (FLP), a typical combinational optimisation problem, is addressed in this paper by implementing parallel simulated annealing (SA) and genetic algorithms (GAs) based on a coarse-grained model to derive solutions for solving the static FLP with rectangle shape areas. Based on the consideration of minimising the material flow factor cost (MFFC), shape ratio factor (SRF) and area utilisation factor (AUF), a total layout cost (TLC) function is derived by conducting a weighted summation of MFFC, SRF and AUF. The evolution operations (including crossover, mutation, and selection) of GA provide a population-based global search in the space of possible solutions, and the SA algorithm can lead to an efficient local search near the optimal solution. By combing the characteristics of GA and SA, better solutions will be obtained. Moreover, the parallel implementation of simulated annealing based genetic algorithm (SAGA) enables a quick search for the optimal solution. The proposed method is tested by performing a case study simulation and the results confirm its feasibility and superiority to other approaches for solving FLP.     

Parameter optimisation using genetic algorithm for support vector machine-based price-forecasting model in National electricity market

The parameter selection is very important for successful modelling of input-output relationship in a function approximation model. In this study, support vector machine (SVM) has been used as a function approximation tool for a price series and genetic algorithm (GA) has been utilised for optimisation of the parameters of the SVM model. Instead of using single time series, separate time series for each trading interval has been employed to model each day-s price profile, and SVM parameters of these separate series have been optimised using GA. The developed model has been applied to two large power systems from National electricity market (NEM) of Australia. The forecasting performance of the proposed model has been compared with a heuristic technique, a linear regression model and the other reported works in the literature. Effect of price volatility on the performance of the models has also been analysed. Testing results show that the proposed GA-SVM model has better forecasting ability than the other forecasting techniques.     

Performance of genetic algorithms in search for water splitting perovskites

We examine the performance of genetic algorithms (GAs) in uncovering solar water light splitters over a space of almost 19,000 perovskite materials. The entire search space was previously calculated using density functional theory to determine solutions that fulfill constraints on stability, band gap, and band edge position. Here, we test over 2500 unique GA implementations in finding these solutions to determine whether GA can avoid the need for brute force search, and thereby enable larger chemical spaces to be screened within a given computational budget. We find that the best GAs tested offer almost a 6 times efficiency gain over random search, and are comparable to the performance of a search based on informed chemical rules. In addition, the GA is almost 10 times as efficient as random search in finding half the solutions within the search space. By employing chemical rules, the performance of the GA can be further improved to approximately 12–17 better than random search. We discuss the effect of population size, selection function, crossover function, mutation rate, fitness function, and elitism on the final result, finding that selection function and elitism are especially important to GA performance. In addition, we determine that parameters that perform well in finding solar water splitters can also be applied to discovering transparent photocorrosion shields. Our results indicate that coupling GAs to high-throughput density functional calculations presents a promising method to rapidly search large chemical spaces for technological materials.     

Optimum speed of visual inspection using a systematic search strategy

In an earlier paper, the authors presented models of human functioning in visual inspection and derived optimal working speeds to balance the cost of time and the cost of errors. Both self-paced and externally paced models assumed a random search strategy. It was noted that choosing a standard speed for visual inspection is difficult with standard work measurement techniques and that the data required for the suggested search model are easily measurable. The purpose of this paper is to complement the earlier work by deriving similar models employing a systematic search strategy. The two models can be considered as bounds on actual performance; thus the current paper complements the previous one by establishing an upper bound rather than a lower bound on performance in search tasks. Comparisons between the two strategies are presented.     

Cell formation problem with consideration of both intracellular and intercellular movements

The cellular manufacturing system (CMS) is a well-known strategy which enhances production efficiency while simultaneously cutting down the system-wide operation cost. Most of the researchers have been focused on developing different approaches in order to identify machine-cells and part-families more efficiently. In recent years, researchers have also focused their studies more scrupulously by collectively considering CMS with production volume, operation sequence, alternative routing or even more. However, very few of them have tried to investigate both the allocation sequence of machines within the cells (intra-cell layout) and the sequence of the formed cells (inter-cell layout). Solving this problem is indeed very important in reducing the total intracellular and intercellular part movements which is especially significant with large production volume.

In this paper, a two-phase approach has been proposed to tackle the cell formation problem (CFP) with consideration of both intra-cell and inter-cell part movements. In the first phase, a mathematical model with multi-objective function is formed to obtain the machine cells and part families. Afterwards, in the second phase, another mathematical model with single-objective function is presented which optimizes the total intra-cell and inter-cell part movements. In other words, the scope of problem has been identified as a CFP together with the background objective of intra-cell and inter-cell layout problems (IAECLP). The primary assumption for IAECLP is that only linear layouts will be considered for both intra-cell and inter-cell. In other words, the machine within cells and the formed cells are arranged linearly. This paper studies formation of two mathematical models and used the part-machine incidence matrix with component operational sequence.

The IAECLP is considered as a quadratic assignment problem (QAP). Since QAP and CFP are NP-hard, genetic algorithm (GA) has been employed as solving algorithm. GA is a widespread accepted heuristic search technique that has proven superior performances in complex optimization problems and further it is a popular and well-known methodology. The proposed algorithms for CFP and IAECLP have been implemented in JAVA programming language.     

A Fast Filling Algorithm for Image Restoration Based on Contour Parity

Filling techniques are often used in the restoration of images. Yet the existing filling technique approaches either have high computational costs or present problems such as filling holes redundantly. This paper proposes a novel algorithm for filling holes and regions of the images. The proposed algorithm combines the advantages of both the parity-check filling approach and the region-growing inpainting technique. Pairing points of the region’s boundary are used to search and to fill the region. The scanning range of the filling method is within the target regions. The proposed method does not require additional working memory or assistant colors, and it can correctly fill any complex contours. Experimental results show that, compared to other approaches, the proposed algorithm fills regions faster and with lower computational cost.     

Optimal design of the inspection buffer for an unreliable process

Placing an inspection buffer immediately after an unreliable process subject to failure protects the process customers from receiving non-conforming products. Such protection is achieved by screening the buffer contents whenever a shift in the process is detected. Previous studies have suggested that, if properly designed, such buffers can reduce overall costs. In this paper we make two types of contributions to the study of inspection buffers. First, we refine the model proposed by Klastorin et al. (1993), by incorporating a more efficient way of sampling, a more realistic objective function and more accurate cost expressions. Second, we provide analytical results to assist in the calculation of the economically optimal buffer size. Specifically, these include conditions for determining whether an inspection buffer is at all justified and a theorem for bounding the search for the optimal buffer size. The performance of the search bound and the sensitivity of the model are examined computationally.     

OPTIMIZATION OF COMPOSITE LAMINATES WITH CUTOUTS USING GENETIC ALGORITHM,VARIABLE METRIC AND COMPLEX SEARCH METHODS

Optimization of composite laminates with cutouts is a complex problem, involving non-differentiable objective function and constraints. Choice of the optimization method is generally based on the nature and complexity of the objective function, constraints and how easily and/or accurately the first derivatives can be found. Many researchers have attempted and applied different classical optimization techniques for non-convex optimization problems. This paper clearly brings out the advantages of a non-traditional optimization method-Genetic algorithm (GA) over conventional techniques, the limitations of conventional techniques and GA's ability to approach the global optimum in an n-dimensional search space, for composite laminates.     

Multiattribute Bayesian Acceptance Sampling Plans for Screening and Scrapping Rejected Lots

A general model for multiattribute Bayesian acceptance sampling plans is developed which incorporates the multiattribute utility function of a decision maker in its design. The model accommodates various dispositions of rejected lots such as screening and scrapping. The disposition of rejected lots is shown to have a substantial impact on the solution approach used and on the ease of incorporation of multiattribute utility functions in terms of their measurement complexity, functional form, and parameter estimation. For example, if all attributes are screenable upon rejection, and the prior distributions of lot quality on each attribute are independent, then an optimal multiattribute sampling plan can be obtained simply by solving for an optimal single sampling plan on each attribute independently. A discrete search algorithm, based on pattern search, is also developed and shown to be very effective in obtaining an optimal multiattribute inspection plan when such separability cannot be accomplished.     

A guided search genetic algorithm using mined rules for optimal affective product design

Affective design is an important aspect of new product development, especially for consumer products, to achieve a competitive edge in the marketplace. It can help companies to develop new products that can better satisfy the emotional needs of customers. However, product designers usually encounter difficulties in determining the optimal settings of the design attributes for affective design. In this article, a novel guided search genetic algorithm (GA) approach is proposed to determine the optimal design attribute settings for affective design. The optimization model formulated based on the proposed approach applied constraints and guided search operators, which were formulated based on mined rules, to guide the GA search and to achieve desirable solutions. A case study on the affective design of mobile phones was conducted to illustrate the proposed approach and validate its effectiveness. Validation tests were conducted, and the results show that the guided search GA approach outperforms the GA approach without the guided search strategy in terms of GA convergence and computational time. In addition, the guided search optimization model is capable of improving GA to generate good solutions for affective design.     

Hybrid simplex search and particle swarm optimization for the global optimization of multimodal functions

This article proposes the hybrid Nelder–Mead (NM)–Particle Swarm Optimization (PSO) algorithm based on the NM simplex search method and PSO for the optimization of multimodal functions. The hybrid NM–PSO algorithm is very easy to implement, in practice, since it does not require gradient computation. This hybrid procedure performed the exploration with PSO and the exploitation with the NM simplex search method. In a suite of 17 multi-optima test functions taken from the literature, the computational results via various experimental studies showed that the hybrid NM–PSO approach is superior to the two original search techniques (i.e. NM and PSO) in terms of solution quality and convergence rate. In addition, the presented algorithm is also compared with eight other published methods, such as hybrid genetic algorithm (GA), continuous GA, simulated annealing (SA), and tabu search (TS) by means of a smaller set of test functions. On the whole, the new algorithm is demonstrated to be extremely effective and efficient at locating best-practice optimal solutions for multimodal functions.     

Nonhierarchical multi‐model fusion using spatial random processes

New model fusion techniques based on spatial‐random‐process modeling are developed in this work for combining multi‐fidelity data from simulations and experiments. Existing works in multi‐fidelity modeling generally assume a hierarchical structure in which the levels of fidelity of the simulation models can be clearly ranked. In contrast, we consider the nonhierarchical situation in which one wishes to incorporate multiple models whose levels of fidelity are unknown or cannot be differentiated (e.g., if the fidelity of the models changes over the input domain). We propose three new nonhierarchical multi‐model fusion approaches with different assumptions or structures regarding the relationships between the simulation models and physical observations. One approach models the true response as a weighted sum of the multiple simulation models and a single discrepancy function. The other two approaches model the true response as the sum of one simulation model and a corresponding discrepancy function, and differ in their assumptions regarding the statistical behavior of the discrepancy functions, such as independence with the true response or a common spatial correlation function. The proposed approaches are compared via numerical examples and a real engineering application. Furthermore, the effectiveness and relative merits of the different approaches are discussed. Copyright © 2015 John Wiley & Sons, Ltd.