Derivation of Pareto Front with Genetic Algorithm and Neural Network

This paper presents a new multi-objective optimization method, which is inspired from the idea of non-dominated sorting genetic algorithm (NSGA) and genetic quantum algorithm (GQA). The GQA has been tested on well known test beds in single objective optimization and compared with the genetic algorithm (GA) in the lead author’s previous work [22]. This paper aims to apply the idea of GQA to multi-objective optimization (MOO). The developed method is called non-dominated sorting genetic quantum algorithm (NSGQA). The developed method is tested with benchmark problems collected from literature, which have characteristics representing various aspects of a MOO problem. Test results show that NSGQA has better performance on most benchmark problems than currently popular MOO methods such as the NSGA. The integration of GQA with MOO, and the systematic comparison with other MOO methods on benchmark problems, should be of general interest to researchers on MOO and to practitioners using MOO methods in design.

Multi-objective optimization of the shell in autonomous intelligent argo profiling float

In the last twenty years genetic algorithms (GAs) were applied in a plethora of fields such as: control, system identification, robotics, planning and scheduling, image processing, and pattern and speech recognition (Back et al., 1997). In robotics the problems of trajectory planning, collision avoidance and manipulator structure design considering a single criteria has been solved using several techniques (Alander, 2003). Most engineering applications require the optimization of several criteria simultaneously. Often the problems are complex, include discrete and continuous variables and there is no prior knowledge about the search space. These kind of problems are very more complex, since they consider multiple design criteria simultaneously within the optimization procedure. This is known as a multi-criteria (or multiobjective) optimization, that has been addressed successfully through GAs (Deb, 2001). The overall aim of multi-criteria evolutionary algorithms is to achieve a set of non-dominated optimal solutions known as Pareto front. At the end of the optimization procedure, instead of a single optimal (or near optimal) solution, the decision maker can select a solution from the Pareto front. Some of the key issues in multi-criteria GAs are: i) the number of objectives, ii) to obtain a Pareto front as wide as possible and iii) to achieve a Pareto front uniformly spread. Indeed, multi-objective techniques using GAs have been increasing in relevance as a research area. In 1989, Goldberg suggested the use of a GA to solve multi-objective problems and since then other researchers have been developing new methods, such as the multi-objective genetic algorithm (MOGA) (Fonseca & Fleming, 1995), the non-dominated sorted genetic algorithm (NSGA) (Deb, 2001), and the niched Pareto genetic algorithm (NPGA) (Horn et al., 1994), among several other variants (Coello, 1998). In this work the trajectory planning problem considers: i) robots with 2 and 3 degrees of freedom (dof ), ii) the inclusion of obstacles in the workspace and iii) up to five criteria that are used to qualify the evolving trajectory, namely the: joint traveling distance, joint velocity, end effector / Cartesian distance, end effector / Cartesian velocity and energy involved. These criteria are used to minimize the joint 27

In order to improve the efficiency and accuracy of the prediction of expressway traffic flow, this paper, based on the characteristics of the data of the expressway traffic flow, focuses on an optimized method of prediction with the application of the neural network with genetic algorithm. Applying genetic algorithm, optimizing BP neural network structure and establishing a new mixed model, this algorithm speed up the slow convergence velocity of traditional BP neural network prediction and increases the possibility to escape local minima. This algorithm based on the optimized genetic neural network predicts the actual data of the expressway traffic flow, the result of which shows that the application of the optimized method of prediction with the genetic neural network algorithm is effective and that it improves the rate and the accuracy of the prediction of the expressway traffic flow.

In a nuclear industry area, high temperature treatment of materials is a factor which requires special attention. Assessment needs to be conducted on the properties of the materials used, including the strength of the materials. The measurement of material properties under thermal processes may reflect residual stresses. The use of Genetic Algorithm (GA) to determine the optimal residual stress is one way to determine the strength of a material. In residual stress modeling with several parameters, it is sometimes difficult to solve for the optimal value through analytical or numerical calculations. Here, GA is an efficient algorithm which can generate the optimal values, both minima and maxima. The purposes of this research are to obtain the optimization of variable in residual stress models using GA and to predict the center of residual stress distribution, using fuzzy neural network (FNN) while the artificial neural network (ANN) used for modeling. In this work a single-material 316/316L stainless steel bar is modeled. The minimal residual stresses of the material at high temperatures were obtained with GA and analytical calculations. At a temperature of 650 0 C, t he GA optimal residual stress estimation converged at – 711.3689 MPa at adistance of 0.002934 mm from center point, whereas the analytical calculation result at that temperature and position is -975.556 MPa . At a temperature of 850 0 C, the GA result was -969.868 MPa at 0.002757 mm from the center point, while with analytical result was -1061.13 MPa. The difference in residual stress between GA and analytical results at a temperature of 650 0 C is about 27 %, while at 850 0 C it is 8.67 %. The distribution of residual stress showed a grouping concentrated around a coordinate of (-76; 76) MPa. The residuals stress model is a degree-two polynomial with coefficients of 50.33, -76.54, and -55.2, respectively, with a standard deviation of 7.874 . Received: 09 October 2014 ; Revised: 21 April 2015; Accepted: 16 June 2015

This paper investigates UAV conceptual design using optimization methods. The conceptual design of a Medium Altitude Long Endurance (MALE) UAV is formulated as two different optimization problems. The optimization problems use a single objective and dual objective functions. For the single objective case, endurance maximization of the UAV is taken as the objective function with aspect ratio and wing loading as design variables. Wing weight, stall speed, maximum speed and rate of climb are taken as constraints. In the dual objective case, minimizing weight is removed from the constraint set and added as the second objective and four more design variables namely taper ratio, thickness to chord ratio, loiter velocity and loiter altitude are added. In the single objective case, both conventional optimization algorithm and genetic algorithm are used to solve the problem and identical results are obtained. A newly developed multi-objective evolutionary algorithm named NSGA-II (non-dominated sorting genetic algorithm) is used to capture the full Pareto front for the dual objective problem. For the dual objective case, numerical results show that several useful Pareto optimal designs exist for the conceptual design of UAV. These Pareto points are thoroughly analyzed for use in detailed design.

A new control technique for growth optimization of plant in hydroponics is proposed. In the method, physiological processes of the plant to environmental factors are firstly identified by using a neural network, and then optimal values of the environmental factors are determined through the prediction of the identified model by using a genetic algorithm. Here, we divided the growth process into 4 stages and tried to obtain optimal 4-step values of the nutrient concentration of the hydroponic solution which maximize the ratio of total leaf length to stem diameter (TLL/SD), which is a good indicator for plant growth, using this method. For the identification, multi-input (nutrient concentration and light intensity) and single-output (TLL/SD)-system was considered. This control technique permitted one to successfully identify the complex system and quickly search the optimal 4-step concentrations. The optimal values obtained here was effective for the actual growth control.

Gene selection from microarray gene expression datasets and clustering of samples into different groups are important data mining tasks for disease identification. Selection of more interpretable genes from the gene expression dataset is an essential data-preprocessing task, which helps to study on cancer diseases. Gene selection during sample clustering is inherently a difficult task as there is no obvious criterion to guide the search. Simultaneous gene selection and sample clustering is a two-way data analysis technique which has recently gained attention in research area. The traditional clustering techniques are unable to handle noisy data properly. So, effective clustering algorithms are more desirable which can deal with the relevant and noise free data. Therefore, target genes selection before sample clustering is essential and of course effective if both the tasks are done simultaneously. In this chapter, optimal gene subset is selected and sample clustering is performed simultaneously using Multi-Objective Genetic Algorithm (MOGA). Different versions of MOGA are employed to choose the optimal gene subset, where natural number of optimal clusters of samples is automatically obtained at the end of the process. Non-dominated sorting genetic algorithm (NSGA), Strength pareto evolutionary algorithm (SPEA) and its modified version SPEA2 are applied for the purpose. The methods use nonlinear hybrid uniform cellular automata for generating initial population, tournament selection strategy, two-point crossover operation, and a suitable jumping gene mutation mechanism to maintain diversity in the population. It uses mutual correlation coefficient; internal and external cluster validation indices as objective functions to find out the non-dominated solutions. To measure the cluster validation indices, clustering algorithm is applied on data subset associated to chromosomes in the population to find out different clusters. After the convergence of genetic algorithm, the best solution from the non-dominated solutions is identified that provides the important genes and categorizes the samples into clusters. The experimental results express the correctness of the proposed simultaneous gene selection and sample categorization method. The goodness of optimality of the clusters obtained using different genetic algorithms is expressed by comparing various cluster validation indices.

A genetic algorithm was used to search for optimal future land use and transportation plans for a pair of high-growth cities. Hundreds of thousands of plans were considered. Constraints were imposed to insure adequate housing for future residents. Objectives included the minimization of traffic congestion, the minimization of costs, and the minimization of change from the status quo. The genetic algorithm provided planners and decision-makers with a rich set of optimal plans known as the Pareto set. An interactive computer tool was developed to assist decision-makers in scanning the information in the Pareto set as they “shop” for a plan.

This paper aimed to establish a nonlinear relationship between laser cladding process parameters and the crack density of a high-hardness, nickel-based laser cladding layer, and to control the cracking of the cladding layer via an intelligent algorithm. By using three main process parameters (overlap rate, powder feed rate, and scanning speed), an orthogonal experiment was designed, and the experimental results were used as training and testing datasets for a neural network. A neural network prediction model between the laser cladding process parameters and coating crack density was established, and a genetic algorithm was used to optimize the prediction results. To improve their prediction accuracy, genetic algorithms were used to optimize the weights and thresholds of the neural networks. In addition, the performance of the neural network was tested. The results show that the order of influence on the coating crack sensitivity was as follows: overlap rate > powder feed rate > scanning speed. The relative error between the predicted value and the experimental value of the three-group test genetic algorithm-optimized neural network model was less than 9.8%. The genetic algorithm optimized the predicted results, and the technological parameters that resulted in the smallest crack density were as follows: powder feed rate of 15.0726 g/min, overlap rate of 49.797%, scanning speed of 5.9275 mm/s, crack density of 0.001272 mm/mm2. Therefore, the amount of crack generation was controlled by the optimization of the neural network and genetic algorithm process.

In this paper, an improved neural network enterprise credit rating model, which is grounded on a genetic algorithm, is suggested. With the characteristics of self-adaptiveness and self-learning, the genetic algorithm is utilized to adjust and enhance the thresholds and weights of the neural network connections. The potential problems of the backpropagation (BP) neural network with slothful speed of convergence and the possibility of falling into the local minimum point are solved to a convinced degree using the genetic algorithm in combination. The hybrid technique of the genetic BP neural network is applied to a credit rating system. Using commercial banks’ datasets, our experimental evaluations suggest that, using a combination of the BP neural network and the genetic algorithm, the proposed model has high accuracy in enterprise credit rating and has good application value. Moreover, the proposed model is approximately 15.9% more accurate than the classical BP neural network approach.

This paper proposes a multi-objective structure for the optimization of an engine control unit mapping. In this way, first an integrated engine-vehicle model is developed. The objective functions for the optimization problem can be defined from this model. After describing the structure of the optimization problem, two different multi-objective genetic algorithms, namely distance-based Pareto genetic algorithm and non-dominated sorting genetic algorithm (together with entropy-based multi-objective genetic algorithm), are proposed and implemented. The results demonstrate the superiority of this computerized structure to the manual mapping methods and also more generality of the multi-objective methods compared to single-objective ones.

A new recognition method of vehicle license plates based on neural network is presented in this paper. For the Back Propagation (BP) neural network often trap into the local minimum in the training process, a Genetic Neural Network (GNN), GABP was constructed by combining the Genetic Algorithm(GA)with BP neural network. The training of the GABP neural network was finished in two steps. The GA was firstly used to make a thorough searching in the global space for the weights and thresholds of the neural network, which can ensure they fall into the neighborhood of global optimal solution. Then, in order to improve the convergence precision, the gradient method was used to finely train the network and find the global optimum or second-best solution with good performance. On the other side, feature extraction is also important for improving the recognition rate of the network. So both the structure features and the statistic features are used in this paper, which include mesh feature, direction line element feature and Zernike moments feature. Experimental results show that the proposed method can save the time of training network and achieve a highly recognition rate.

Stochastic multi-objective optimization approaches in a real-world oil field waterflood management

Based on safety assessment factors determined by operation characteristics of a certain tailing ,genetic BP neural network evaluation model is established. To overcome such problems of BP neural network as slow convergence ,poor generalization ability and easy to fall into local minimum value,this paper proposes to use genetic algorithm to optimize threshold value,weights and structure of neural network. Thus,by taking advantage of extensive mapping ability of neural network and global search ability of genetic algorithm,neural network and genetic algorithm will have complementary advantages and the learning speed of network will be accelerated. The application of the described method shows optimized fitting precision,improved accuracy and efficiency ,and enhanced generalization ability of BP neural network. In conclusion,this model can effectively reflect and accurately evaluate non-linear relations between security levels and evaluation factors in tailing.