Design of reproducible polarized and non-polarized edge filters using genetic algorithm

<p>A genetic algorithm (GA) was used in this study to develop a standard penetration test (SPT)-based design method for the axial capacity of driven piles. A total of 72 pile load tests was collected from literature and divided into two groups based on their measurements. The first group had the load-transfer distribution measurements for extracting both the unit side and tip resistances. These unit resistances were correlated by the GA with soil measurements and pile properties to develop the design method. The second group, where only the total capacity measurements were available, were used to validate the new design method and compare its performance with three existing SPT-based design methods. The new GA-derived design method considers nonlinear relationships with the effective stress and pile length and provides an unbiased prediction with a low coefficient of variation (COV) of 40.0 %, while the three existing methods overestimate the capacity by a factor of 1.62 to 1.65 with a high COV of 40.3 % to 52.8 %, which could result in an under design of pile foundations. This study shows that the GA was able to obtain complex relationships with great accuracy and the new design method can be applied to new cases reasonably well.</p>

<p>A genetic algorithm (GA) was used in this study to develop a standard penetration test (SPT)-based design method for the axial capacity of driven piles. A total of 72 pile load tests was collected from literature and divided into two groups based on their measurements. The first group had the load-transfer distribution measurements for extracting both the unit side and tip resistances. These unit resistances were correlated by the GA with soil measurements and pile properties to develop the design method. The second group, where only the total capacity measurements were available, were used to validate the new design method and compare its performance with three existing SPT-based design methods. The new GA-derived design method considers nonlinear relationships with the effective stress and pile length and provides an unbiased prediction with a low coefficient of variation (COV) of 40.0 %, while the three existing methods overestimate the capacity by a factor of 1.62 to 1.65 with a high COV of 40.3 % to 52.8 %, which could result in an under design of pile foundations. This study shows that the GA was able to obtain complex relationships with great accuracy and the new design method can be applied to new cases reasonably well.</p>

Using a genetic algorithm to develop a pile design method

This paper presents a method for the design of high throughput rate quadrantally symmetric 2-D filters. It employs cascaded high throughput rate 1-D filters in a parallel structure. These filters require fewer multipliers than a direct 2-D implementation. As well, the parallel structure of the designed filter using SVD lends itself easily to a pipelined, high throughput implementation. The 1-D filters achieve a high throughput rate using canonical signed digit coefficients which are obtained using a new genetic algorithm design method. This new design method employs a unique chromosome coding technique to overcome the limitations previously encountered in using genetic algorithms for such designs

An aerodynamic optimal design method for wind-lens turbine using the Genetic Algorithm has been developed.In the present method,the aerodynamic design for the wind-lens turbine rotor is based on an axisymmetnc viscous flow analysis and a two-dimensional blade element design.The present optimal design method is able to search for the optimal wind-lens and rotor blade shape simultaneously.This coupled design method of turbine rotor and wind-lens has achieved to generate high performance wind-lens turbines.Three-dimensional Reynolds averaged Navier-Stokes(RANS) simulation shows that the new wind-lens turbine designed by the genetic algorithm design method is superior to conventional one in the total performance.

Hybrid force-displacement-based design methods for self-centering wall structures

Development and validation of a hybrid aerodynamic design method for curved diffusers using genetic algorithm and ball-spine inverse design method

As the advantages of foldable or deployable structures are being discovered, research into origami engineering has attracted more focus from both artists and engineers. With the aid of modern computer techniques, some computational origami design methods have been developed. Most of these methods focus on the problem of origami crease pattern design — the problem of determining a crease pattern to realize a specified origami final shape, but don’t provide computational solutions to actually developing a shape that meets some design performance criteria. This paper presents a design method that includes the computational design of the finished shape as well as the crease pattern. The origami shape will be designed to satisfy geometric, functional, and foldability requirements. This design method is named computational evolutionary embryogeny for optimal origami design (CEEFOOD), which is an extension of the genetic algorithm (GA) and an original computational evolutionary embryogeny (CEE). Unlike existing origami crease pattern design methods that adopt deductive logic, CEEFOOD implements an abductive approach to progressively evolve an optimal design. This paper presents how CEEFOOD — as a member of the GA family — determines the genetic representation (genotype) of candidate solutions, the formulation of the objective function, and the design of evolutionary operators. This paper gives an origami design problem, which has requirements on the folded-state profile, position of center of mass, and number of creases. Several solutions derived by CEEFOOD are listed and compared to highlight the effectiveness of this abductive design method.

As the advantages of foldable or deployable structures are being discovered, research into origami engineering has attracted more focus from both artists and engineers. With the aid of modern computer techniques, some computational origami design methods have been developed. Most of these methods focus on the problem of origami crease pattern design—the problem of determining a crease pattern to realize a specified origami final shape, but do not provide computational solutions to actually developing a shape that meets some design performance criteria. This paper presents a design method that includes the computational design of the finished shape as well as the crease pattern. The origami shape will be designed to satisfy geometric, functional, and foldability requirements. This design method is named computational evolutionary embryogeny for optimal origami design (CEEFOOD), which is an extension of the genetic algorithm (GA) and an original CEE. Unlike existing origami crease pattern design methods that adopt deductive logic, CEEFOOD implements an abductive approach to progressively evolve an optimal design. This paper presents how CEEFOOD—as a member of the GA family—determines the genetic representation (genotype) of candidate solutions, the formulation of the objective function, and the design of evolutionary operators. This paper gives an origami design problem, which has requirements on the folded-state profile, position of center of mass, and number of creases. Several solutions derived by CEEFOOD are listed and compared to highlight the effectiveness of this abductive design method.

This paper describes the research of genetic algorithm (GA) based PID for autonomous underwater vehicle (AUV) motion control. A simulation of heading control application is considered using GA and improved GA based PID. The dynamic model of AUV is established. The design method of GA and improved GA based PID is introduced. The heading control design model is obtained by the AUV linearization model at given operating points which considering the ocean current disturb. The heading controller is designed according to the method of GA and improved GA based PID. The simulation results show that the controller is effective with good dynamic performances for AUV motion control.

An efficient genetic reinforcement learning algorithm for designing fuzzy controllers is proposed in this paper. The genetic algorithm (GA) adopted in this paper is based upon symbiotic evolution which, when applied to fuzzy controller design, complements the local mapping property of a fuzzy rule. Using this Symbiotic-Evolution-based Fuzzy Controller (SEFC) design method, the number of control trials, as well as consumed CPU time, are considerably reduced when compared to traditional GA-based fuzzy controller design methods and other types of genetic reinforcement learning schemes. Moreover, unlike traditional fuzzy controllers, which partition the input space into a grid, SEFC partitions the input space in a flexible way, thus creating fewer fuzzy rules. In SEFC, different types of fuzzy rules whose consequent parts are singletons, fuzzy sets, or linear equations (TSK-type fuzzy rules) are allowed. Further, the free parameters (e.g., centers and widths of membership functions) and fuzzy rules are all tuned automatically. For the TSK-type fuzzy rule especially, which put the proposed learning algorithm in use, only the significant input variables are selected to participate in the consequent of a rule. The proposed SEFC design method has been applied to different simulated control problems, including the cart-pole balancing system, a magnetic levitation system, and a water bath temperature control system. The proposed SEFC has been verified to be efficient and superior from these control problems, and from comparisons with some traditional GA-based fuzzy systems.

An efficient genetic reinforcement learning algorithm for designing fuzzy controllers is proposed. The genetic algorithm (GA) adopted is based upon symbiotic evolution which, when applied to fuzzy controller design, matches well with the local mapping property of a fuzzy rule. Using this symbiotic-evolution-based fuzzy controller (SE-FC) design method, the number of control trials as well as consumed CPU time are reduced considerably as compared to traditional GA-based fuzzy controller design methods and other types of genetic reinforcement learning schemes. The proposed SE-FC design method has been applied to the cart-pole balancing system. Efficiency and superiority of the proposed SE-FC have been verified from this problem and from comparisons with the traditional GA-based fuzzy systems.

This chapter focuses on recent development of direct probability-based designmethods, including the expanded reliability-based design (expanded RBD) method, reliabilitybased robust geotechnical design (RGD) method, and the new safety standards for flood defenses in the Netherlands which is the first ever national standard that adopts direct (or full) probability-based design methods. One major criticism to the simplified semi-probabilistic RBD format is displacement of sound engineering judgment and lack of flexibility for practitioners. Because the simplified semi-probabilistic RBD format adopts the same trial-and-error approach as traditional allowable stress design (ASD) methods and it is developed to circumvent the need for practitioners to perform probabilistic analysis, these compromises seem unavoidable. An alternative solution to this dilemma is to maintain the engineering judgment and flexibility similar to ASD methods, but at the expense of performing probabilistic analysis using direct probability-based designmethods. It is shown that, with the aid of commonly available computers and widely used computer software such as Microsoft Excel, performing Monte Carlo Simulation (MCS)-based probabilistic analysis and design are becoming more and more straightforward and convenient. MCS is already available in some commercial geotechnical software programs. MCS can be comprehended easily as a repetitive computer execution of traditional ASD design calculation, and the reliability analysis background required for performing MCS is substantially reduced. A gravity retaining wall design example is used in this chapter to illustrate theMCS-based design method in Excel.

Proper energy storage system design is important for performance improvements in solar power shared building communities. Existing studies have developed various design methods for sizing the distributed batteries and shared batteries. For sizing the distributed batteries, most of the design methods are based on single building energy mismatch, but they neglect the potentials of energy sharing in reducing battery capacity, thereby easily causing battery oversizing problem. For sizing the shared batteries, the existing design methods are based on a community aggregated energy mismatch, which may avoid battery oversizing but cause another severe problem, i.e. excessive electricity losses in the sharing process caused by the long-distance power transmissions. Therefore, this chapter proposes a hierarchical design method of distributed batteries in solar power shared building communities, with the purpose of reducing the battery capacity and minimizing the energy loss in the sharing process. The developed design method first considers all the distributed batteries as a virtual ‘shared’ battery and searches its optimal capacity using genetic algorithm. Taking the optimized capacity as a constraint, the developed method then optimizes the capacities of the distributed batteries for minimizing the energy loss using nonlinear programming. Case studies on a building community show that compared with an existing design method, the proposed design can significantly reduce the battery capacity and electricity loss in the sharing process, i.e. 36.6% capacity reduction and 55% electricity loss reduction. This chapter integrates the considerations of aggregated energy needs, local PV power sharing, advanced community control, and battery storage sharing, which will be useful to optimize three functions (energy efficiency, energy production and flexibility) in a positive energy district towards energy surplus and climate neutrality.

With the increasing demands of health care, the design of hospital buildings has become increasingly demanding and complicated. However, the traditional layout design method for hospital is labor intensive, time consuming and prone to errors. With the development of artificial intelligence (AI), the intelligent design method has become possible and is considered to be suitable for the layout design of hospital buildings. Two intelligent design processes based on healthcare systematic layout planning (HSLP) and generative adversarial network (GAN) are proposed in this paper, which aim to solve the generation problem of the plane functional layout of the operating departments (ODs) of general hospitals. The first design method that is more like a mathematical model with traditional optimization algorithm concerns the following two steps: developing the HSLP model based on the conventional systematic layout planning (SLP) theory, identifying the relationship and flows amongst various departments/units, and arriving at the preliminary plane layout design; establishing mathematical model to optimize the building layout by using the genetic algorithm (GA) to obtain the optimized scheme. The specific process of the second intelligent design based on more than 100 sets of collected OD drawings includes: labelling the corresponding functional layouts of each OD plan; building image-to-image translation with conditional adversarial network (pix2pix) for training OD plane layouts, which is one of the most representative GAN models. Finally, the functions and features of the results generated by the two methods are analyzed and compared from an architectural and algorithmic perspective. Comparison of the two design methods shows that the HSLP and GAN models can autonomously generate new OD plane functional layouts. The HSLP layouts have clear functional area adjacencies and optimization goals, but the layouts are relatively rigid and not specific enough. The GAN outputs are the most innovative layouts with strong applicability, but the dataset has strict constraints. The goal of this paper is to help release the heavy load of architects in the early design stage and present the effectiveness of these intelligent design methods in the field of medical architecture.