Competent Genetic Algorithms Research Articles

Development of sensor placement optimization tool and application to large-span cable-stayed bridge

Structural health monitoring (SHM) is essential for engineers to effectively evaluate structural performance. The accelerometers and strain gauges are commonly used for monitoring and testing structural performance. Placing both types of sensors is the key step for SHM and structural testing. This paper presents the development and application of the sensor placement optimization methods, which have been integrated and implemented in a versatile software tool for maximizing the sensor coverage capacity for structural performance assessment. The sensor placement solutions are optimized using a parallel optimization framework based on the competent genetic algorithm, leading to a number of features that enrich the application flexibility. The developed methods and software tool provide a generic approach for multi-type sensor placement. The integrated tool has been applied to the Indian River Inlet Bridge a large-span cable-stayed bridge to demonstrate and validate the effectiveness of the proposed solution methods for facilitating real world SHM practice.

Competent genetic algorithms for weighing matrices

In this paper, we demonstrate that the search for weighing matrices constructed from two circulants can be viewed as a minimization problem together with two competent genetic algorithms to locate optima of an objective function. The motivation to deal with the messy genetic algorithm (mGA) is given from the pioneering results of Goldberg, regarding the ability of the mGA to put tight genes together in a solution which points directly to structural patterns in weighing matrices. In order to take into advantage certain properties of two ternary sequences with zero autocorrelation we use an adaptation of the fast messy GA (fmGA) where we combine mGA with advanced techniques, such as thresholding and tie-breaking. This transformation of the weighing matrices problem to an instance of a combinatorial optimization problem seems to be promising, since we resolved two open cases for weighing matrices as these are listed in the second edition of the Handbook of Combinatorial Designs.

Efficient model building in competent genetic algorithms using DSM clustering

Detecting multivariate interactions between the variables of a problem is a challenge in traditional genetic algorithms (GAs). This issue has been addressed in the literature as the linkage learning problem. It is widely acknowledged that the success of GA in solving any problem depends on the proper detection of multivariate interactions in the problem. Different approaches have thus been proposed to detect and represent such interactions. Estimation of distribution algorithms (EDAs) are amongst these approaches that have been successfully applied to a wide range of hard optimization problems. They build a model of the problem to detect multivariate interactions, but the model building process is often computationally intensive. In this paper, we propose a new clustering algorithm that turns pair-wise interactions in a dependency structure matrix (DSM) into an interaction model efficiently. The model building process is carried out before the evolutionary algorithm to save computational burden. The accurate interaction model obtained in this way is then used to perform an effective recombination of building blocks (BBs) in the GA. We applied the proposed approach to solve exemplar hard optimization problems with different types of linkages to show the effectiveness and efficiency of the proposed approach. Theoretical analysis and experiments showed that the building of an accurate model requires O(nlog (n)) number of fitness evaluations. The comparison of the proposed approach with some existing algorithms revealed that the efficiency of the model building process is enhanced significantly.

Pressure-Dependent Leak Detection Model and Its Application to a District Water System

Cost-effective reduction of water loss is a compelling but challenging task for water utilities. This paper presents a model-based optimization method for leakage detection of water distribution systems. Leakage hotspots are assumed to exist at the model nodes identified. Leakage is represented as pressure-dependent demand simulated as emitter flows at selected model nodes. The leakage detection method is formulated to optimize the leakage node locations and their associated emitter coefficients such that the differences between the model predicted and the field observed values for pressure and flow are minimized. The optimization problem is solved by using a competent genetic algorithm. The leakage detection method is developed as an add-on feature of the optimization-based model calibration tool. This enables engineers to undertake leakage hotspot optimization as an independent task or combine the task with hydraulic model calibration, subject to suitably varied field data. Two case studies are discusse...

Design Process Sequencing With Competent Genetic Algorithms

In product design, it is critical to perform project activities in an appropriate sequence. Otherwise, essential information will not be available when it is needed, and activities that depend on it will proceed using assumptions instead. Later, when the real information is finally available, comparing it with the assumptions made often precipitates a cascade of rework, and thus cost and schedule overruns for the project. Information flow models have been used to sequence the engineering design process to minimize feedback and iteration, i.e., to maximize the availability of real information where assumptions might otherwise be made instead. In this paper, we apply Genetic Algorithms (GAs) to an information flow model to find an optimized sequence for a set of design activities. The optimality of a solution depends on the objective of rearrangement. In an activity sequencing context, objectives vary: reducing iteration/feedback, increasing concurrency, reducing development lead-time and cost, or some combination of these. We adopt a matrix-based representation scheme, the design structure matrix (DSM), for the information flow models. Our tests indicate that certain DSM characteristics (e.g., size, sparseness, and sequencing objective) cause serious problems for simple Genetic Algorithm (SGA) designs. To cope with the SGA deficiency, we investigate the use of a competent GA: the ordering messy GA (OmeGA). Tests confirm the superiority of the OmeGA over a SGA for hard DSM problems. Extensions enhancing the efficiency of both a SGA and the OmeGA, in particular, niching and hybridization with a local search method, are also investigated.

Military antenna design using simple and competent genetic algorithms

Over the past decade, the Air Force Research Laboratory (AFRL) Antenna Technology Branch at Hanscom AFB has employed the simple genetic algorithm (SGA) as an optimization tool for a wide variety of antenna applications. Over roughly the same period, researchers at the Illinois Genetic Algorithm Laboratory (IlliGAL) at the University of Illinois at Urbana Champaign have developed GA design theory and advanced GA techniques called competent genetic algorithms—GAs that solve hard problems quickly, reliably, and accurately. Recently, under the guidance and direction of the Air Force Office of Scientific Research (AFOSR), the two laboratories have formed a collaboration, the common goal of which is to apply simple, competent, and hybrid GA techniques to challenging antenna problems. This paper is composed of two parts. The first part of this paper summarizes previous research conducted by AFRL at Hanscom for which SGAs were implemented to obtain acceptable solutions to several antenna problems. This research covers diverse areas of interest, including array pattern synthesis, antenna test-bed design, gain enhancement, electrically small single bent wire elements, and wideband antenna elements. The second part of this paper starts by briefly reviewing the design theory and design principles necessary for the invention and implementation of fast, scalable genetic algorithms. A particular procedure, the hierarchical Bayesian optimization algorithm (hBOA) is then briefly outlined, and the remainder of the paper describes collaborative efforts of AFRL and IlliGAL to solve more difficult antenna problems. In particular, recent results of using hBOA to optimize a novel, wideband overlapped subarray system to achieve −35 dB sidelobes over a 20% bandwidth. The problem was sufficiently difficult that acceptable solutions were not obtained using SGAs. The case study demonstrates the utility of using more advanced GA techniques to obtain acceptable solution quality as problem difficulty increases.

Application of Tabu‐BOA to acquire multimodal and multiobjective solutions for electric equipment configuration problems in a power plant

AbstractThis paper applies the Bayesian Optimization Algorithm with Tabu Search (Tabu‐BOA) to electric equipment configuration problems in a power plant. Tabu‐BOA is a hybrid evolutionary computation algorithm with competent genetic algorithms and meta‐heuristics. The configuration problems we consider have complex combinatorial properties, and therefore are hard to formulate and solve via conventional mathematical programming techniques. Using the proposed method, we have solved the following problems (in order of increasing complexity): (1) cost minimization of electric equipment configuration and the corresponding cabling, (2) plus choice of the power plant operation patterns, (3) plus parallel operation of multiple transformers, (4) plus change of the supply voltages (high voltage or low voltage) to the electric power load, and (5) with addition of another objective, that is, both minimization of the cost and maximization of the surplus power supply. © 2005 Wiley Periodicals, Inc. Electr Eng Jpn, 152(3): 8–20, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/eej.20150

Solving optimum TDMA broadcast scheduling in mobile ad hoc networks: a competent permutation genetic algorithm approach

A competent permutation encoded genetic algorithm (GA) is proposed for solving the optimum time division multiple access (TDMA) broadcast scheduling problem in mobile ad hoc networks. The problem is widely known as non-deterministic polynomial (NP) complete and diverse heuristic algorithms were reported to solve this problem recently. In this study, the GA approach is developed to cooperate with a deterministic greedy-like algorithm to obtain the optimum schedules. The main feature of the proposed GA approach lies in employing a permutation encoding strategy and thus obviates the invalid solutions encountered by the conventional binary encoding scheme. Consequently, the problem search space is reduced to a great extent and the GA becomes more efficient in searching the optimum solutions. A variety of simulation scenarios were conducted to examine the evolutionary behaviour and the scheduling performance of the proposed GA approach. Simulation results suggest that the proposed GA approach exhibits superior search capability in obtaining lower frame length whilst maintaining higher slot utilisation compared with other recently proposed methods.

Multi‐objective inversion of surface waves and receiver functions by competent genetic algorithm applied to the crustal structure of the Paraná Basin, SE Brazil

Surface wave dispersion and receiver functions are sensitive to different, but dependent, seismic properties. Their joint inversion is multi‐objective and can provide tight constraints on layer‐interfaces and S‐velocities. We used one of the competent genetic algorithms, Bayesian optimization algorithm, as the multi‐objective inversion technique. Multi‐objective criterion of receiver functions and surface wave dispersion can better constrain solutions than each separate objective. We applied this new method to data from three stations in the Paraná Basin, Brazil, and found S‐velocity structure well‐constrained down to 150 km depth. The inverted S‐velocities in the lower crust are less than 3.8 km/s and are lower than in the surrounding foldbelts. Some indication of high velocities (Vs > 4 km/s) in the 5–7 km lowermost crust is given by a Moho transition zone. This may suggest that possible underplating was not widespread in the Paraná basin.

Book Review: The Design of Innovation: Lessons from and for Competent Genetic Algorithms

Book Review: The Design of Innovation: Lessons from and for Competent Genetic Algorithms

Scalability problems of simple genetic algorithms.

Scalable evolutionary computation has become an intensively studied research topic in recent years. The issue of scalability is predominant in any field of algorithmic design, but it became particularly relevant for the design of competent genetic algorithms once the scalability problems of simple genetic algorithms were understood. Here we present some of the work that has aided in getting a clear insight in the scalability problems of simple genetic algorithms. Particularly, we discuss the important issue of building block mixing. We show how the need for mixing places a boundary in the GA parameter space that, together with the boundary from the schema theorem, delimits the region where the GA converges reliably to the optimum in problems of bounded difficulty. This region shrinks rapidly with increasing problem size unless the building blocks are tightly linked in the problem coding structure. In addition, we look at how straightforward extensions of the simple genetic algorithm-namely elitism, niching, and restricted mating are not significantly improving the scalability problems.