Richard Preen & Larry Bull UWE, Bristol. Introduction Evolutionary computing has been applied widely. Over 70 examples of “human competitive” performance.

Slides:



Advertisements
Similar presentations
Logical and Artificial Intelligence in Games Lecture 14
Advertisements

Bridging the Gap Between Statistics and Engineering Statistical calibration of CFD simulations in Urban street canyons with Experimental data Liora Malki-Epshtein.
Genetic Algorithms Genetic Programming Ata Kaban School of Computer Science University of Birmingham 2003.
GENETICA The problem-solving approach proposed here, largely based on the previous remarks, is implemented through the computer language GENETICA. GENETICA.
More MR Fingerprinting
 TOPIC; ENERGY SOURCE  SUBTOPIC; WIND ENERGY.
Team Notus TEAM NOTUS UNIVERSITY OF HOUSTON COLLEGE OF TECHNOLOGY SENIOR DESIGN 1 Horizontal Wind Turbine.
Biologically Inspired AI (mostly GAs). Some Examples of Biologically Inspired Computation Neural networks Evolutionary computation (e.g., genetic algorithms)
1 Sensor Networks and Networked Societies of Artifacts Jose Rolim University of Geneva.
Introduction to Genetic Algorithms Yonatan Shichel.
Evolutionary Design By: Dianna Fox and Dan Morris.
Artificial Intelligence Genetic Algorithms and Applications of Genetic Algorithms in Compilers Prasad A. Kulkarni.
Simulation Models as a Research Method Professor Alexander Settles.
Evolutionary Computation Application Peter Andras peter.andras/lectures.
Evolving Agents in a Hostile Environment Alex J. Berry.
By Misfer Almarri.  Have the main rotor shaft and electrical generator at the top of a tower, and must be pointed into the windrotor  Small turbines.
Wind Turbine By Misfer Almarri. Wind Turbine Efficiency Depends on the size of the turbine and the average wind speed How much power needed What type.
August 2012 New Generation of Wind Turbines We Turn Energy Consumers into Energy Producers.
Wind Energy LiChung Hung (Uly) What’s wind power?  Wind turbines convert the kinetic energy from the wind into mechanical energy which is then used.
Urban Wind Power. Why? Locations, where is no space for large turbines Energy savings o Preventing energy transporting losses from larger power plants.
Genetic Algorithms Overview Genetic Algorithms: a gentle introduction –What are GAs –How do they work/ Why? –Critical issues Use in Data Mining –GAs.
Energy to Educate Craig Hammond Stephanie Sheppard Kyle Tress Justin Valenti Presented to: OPP EDSGN 100 8/8/11.
Wind Modeling Studies by Dr. Xu at Tennessee State University
Jarred Morales and Cody Beckemeyer Advisior: Dr. Junkun Ma ET 483.
Genetic Algorithm.
Abstract Due to increased interest in the application of renewable energy, wind energy has been increased attention by researchers. Studies have been conducted.
How to use CFD (RANS or LES) models for urban parameterizations – and the problem of averages Alberto Martilli CIEMAT Madrid, Spain Martilli, Exeter, 3-4.
Flow Simulation of a Maple Seed
Numerical Investigation of Internal Wave-Vortex Interactions Tyler D. Blackhurst and J.C. Vanderhoff Department of Mechanical Engineering Brigham Young.
NCAS/APRIL Meeting on Urban Air Quality Modelling Dispersion modelling at Imperial College London Professor Helen ApSimon and Dr Roy Colvile Page 1/N ©
Cody Beckemeyer Advisors: Junkun Ma Cris Koutsougeras ET 494 Fall 2013.
Introduction people business vision and goals Product design aims features and benefits competitive comparison current status What we are looking for manufacturing.
More on coevolution and learning Jing Xiao April, 2008.
Wind God by John D. Rockefellar top lawl and Sieng for me swagLy.
APEX Institute of Technology &Management Mr. SAURAV KUMAR (EEE # ) Mr. GAURAV KUMAR (ECE # ) B.TECH. PROJECT PRESENTATION-2012 [1]
Wind Power and its Science As one of the powerful energy sources.
Fuzzy Genetic Algorithm
Coevolution Chapter 6, Essentials of Metaheuristics, 2013 Spring, 2014 Metaheuristics Byung-Hyun Ha R2R3.
‘Externalizing Abstract Mathematical Models’ Lisa Tweedie,Robert Spence, Huw Dawkes and Hua Su Department of Electrical Engineering, Imperial College Of.
By: Eric Cale and Derek Lewis. Rationale Question: How can we generate electricity using a “greener” method? Why? It provides CLEAN energy Climate change.
Horizontal Axis Wind Turbine Systems: Optimization Using Genetic Algorithms J. Y. Grandidier, Valorem, 180 Rue du Marechal Leclerc, F B ´ Begles,
Design of a Vertical-Axis Wind Turbine
Chapter 9 Genetic Algorithms Evolutionary computation Prototypical GA
Horizontal Axis Fan design. HAWTs Vs. VAWTs -HAWTs should be used since it is more effective in producing laminar flow and aerodynamics compared to VAWTs.
The German Comenius team presents:
Electricity Wind Power Solar Power Hydro Electric Conservation.
Innovative and Unconventional Approach Toward Analytical Cadastre – based on Genetic Algorithms Anna Shnaidman Mapping and Geo-Information Engineering.
Comparative Reproduction Schemes for Evolving Gathering Collectives A.E. Eiben, G.S. Nitschke, M.C. Schut Computational Intelligence Group Department of.
A comparative approach for gene network inference using time-series gene expression data Guillaume Bourque* and David Sankoff *Centre de Recherches Mathématiques,
And how they work Created by Austin Beidelman TeachersStudents.
Genetic Search Algorithms Matt Herbster. Why Another Search?  Designed in the 1950s, heavily implemented under John Holland (1970s)  Genetic search.
Renewable Energy: Wind Power Salvador Griñán Egea. 1º Bachillerato Science and Technology. This project is about the Renewable Energy focusing on Wind.
IP d.c. devices © Oxford University Press 2011 d.c. devices.
17.3 Darwin and Natural Selection: What Darwin knew  Darwin understood the fossil record and explained it by combining the two popular ideas of gradualism.
Robot Intelligence Technology Lab. Evolutionary Robotics Chapter 3. How to Evolve Robots Chi-Ho Lee.
Genetic Algorithm(GA)
Vertical Axis Wind Turbine Noise
Haploid-Diploid Evolutionary Algorithms
Selected Topics in CI I Genetic Programming Dr. Widodo Budiharto 2014.
VERTICAL AXIS TURBINE Most of the world's energy resources are from the sun's rays hitting earth. Some of that energy has been preserved as fossil energy,
VERTICAL AXIS WIND TURBINE
Wind Turbine
Vertical Axis Wind Turbine
Anatomy of Modern Wind Turbine & Wind farms
Haploid-Diploid Evolutionary Algorithms
Anatomy of Modern Wind Turbines-1
COMBINED DARRIEUS - SAVONIUS WIND TURBINE
CHAPTER I. of EVOLUTIONARY ROBOTICS Stefano Nolfi and Dario Floreano
Lecture 4. Niching and Speciation (1)
Coevolutionary Automated Software Correction
Presentation transcript:

Richard Preen & Larry Bull UWE, Bristol

Introduction Evolutionary computing has been applied widely. Over 70 examples of “human competitive” performance have been noted [Koza, 2010]. Most of this work has included simulation or models. When simulations are costly, surrogate models can be used. Data mining techniques are used to create approximations of the function space from sample points gathered from the simulator/model.

Embodied Evolution 1 Some hard problems are difficult to model or simulate in a useful way. Small amount of work using simulated evolutionary design directly on a task: Jet nozzle [Rechenberg, 1971] Mobile robotics [Nolfi, 1992] Electronic circuits [Thompson, 1998] Unconventional computing [Harding & Miller, 2004] Chemical systems [Theis et al., 2007]

Embodied Evolution 2 Explore use of surrogate models in conjunction with direct solution evaluation only for complex tasks. No best-guess simulator or model used. Combine with emerging rapid-fabrication (3D printing) technology. Potential for truly unexpected results in a wide range of domains. Many issues, of course: time, noise in evaluations, representations, kinds of surrogates, etc.

An Example: Wind Turbines

Wind Energy “In theory, small-scale wind energy has the potential to generate 41.3 TWh of electricity and save 17.8 MtCO2 in the UK annually” [Carbon Trust, 2008]. Wind flow is rarely constant and consistent, rather it is usually veering and turbulent, and the influences of nearby obstacles can significantly alter wind flow patterns. Vertical axis wind turbines (VAWT) represent a very effective approach to harnessing wind power in many situations – especially urban areas. In comparison to the more common horizontal axis wind turbine (HAWT), VAWT can also be easier to manufacture, may scale more easily, and are typically inherently light- weight with little or no noise pollution.

A Simple Representation Confined design space to a four-blade Savonius VAWT with alterations in blade shape (profile and twist) possible. Genome [5,8,2,4] defines offsets from central spindle.

Embodied Evolution of VAWT Turbines of 30mm 3 volume Population size 20 Tournament selection Tip speed used as fitness measure Direct evaluations for first three generations (60 fabs) MLP surrogate model of fitness MLP trained for 1000 epochs per generation Best and random individual fabricated per generation

Single VAWT

Single VAWT: Z-axis design

Beyond Modelling Evolutionary computing has previously been used to design both HAWT and VAWT via CFD models. Essentially impossible for turbine arrays where interactions are considered. Dabiri et al. have recently highlighted how the spacing constraints of HAWT arrays often do not apply for VAWT, and even that performance can be increased by exploitation of inter-turbine flow effects. View wind farm as an energy-capture ecosystem and coevolve heterogeneous, interacting VAWT.

Embodied Coevolution Two “species” of turbine. Two populations and surrogate models (L, R). Each evaluated with best individual from other population. Evolve alternately. Seed with 10 best from single VAWT experiments. Allow counter-rotation. All other features the same as before.

Paired VAWT

Example

Results Speciation seen – L and R physically different. Homogeneous pairing of either species not as effective as the heterogeneous case. Counter-rotation not seen in fittest solutions here. Approach potentially unaffected by array size increase. CFD modelling impossible.