Towards the Automated Design of Phased Array Ultrasonic Transducers – Using Particle Swarms to find “Smart” Start Points Stephen Chen, York University Sarah Razzaqi, University of Queensland Vincent Lupien, Acoustic Ideas Inc.
June 26, 2007IEA/AIE 2007 Phased Array Ultrasonic Transducers A non-mechanical way to direct an energy beam Useful for Non-Destructive Evaluation
June 26, 2007IEA/AIE 2007 Continuum Probe Designer™ Product of Acoustic Ideas Inc. Automated design tool that creates an optimized probe for a given inspection task Removes “art” of design
June 26, 2007IEA/AIE 2007 Continuum Probe Designer™ Components Cost function generator uses exclusive patent- pending technology to design an optimized probe
June 26, 2007IEA/AIE 2007 Optimization Solver The optimized probe is developed for a given probe geometry Finding the best probe geometry is another optimization task In this paper, the probe designer is treated as a “cost function generator”
June 26, 2007IEA/AIE 2007 Optimization Objective Probe costs are directly related to the number of elements used in a design Existing instrumentation can only control 32 independent channels at a time
June 26, 2007IEA/AIE 2007 An Evolution Strategy for the Optimization Solver (CEC2006) Standard (1+λ)-ES with λ = 3 Performs significantly better than gradient descent (i.e. fmincon ) Note: fmincon takes about an hour and uses about 300 evaluations
June 26, 2007IEA/AIE 2007 Evolution Strategy vs. fmincon Tested on one expert selected and 29 random start points ES results are much better and more consistent ES results are still not good enough fmincon (1+λ)-ES
June 26, 2007IEA/AIE 2007 Independent Parallel Runs High standard deviation suggests that using multiple runs will lead to easy improvements Results are better, but still not good enough (1+λ)-ES Four parallel
June 26, 2007IEA/AIE 2007 “Smart” Start Points High correlation between ES solution and quality of random start point Use random search to find “smart” points Better results again Four parallel “Smart” start pts
June 26, 2007IEA/AIE 2007 Analyzing “Smart” Start Points Is perceived correlation significant? From 120 random start points, apply the (1+λ)-ES to the 30 worst and best 30 Worst30 Best30 Worst30 Best
June 26, 2007IEA/AIE 2007 “Smart” Start Points on the TSP Is correlation an obvious/trivial observation? Correlation does not exist on TSP 30 Worst30 Best30 Worst30 Best 1230%1128%11% 18%16%1.3%2.4%
June 26, 2007IEA/AIE 2007 Coarse Search does not Help on TSP Coarse search for better starting points does not improve the performance of two- opt on the TSP Four parallel “Smart” start pts 9.2%8.8% 1.1%1.4%
June 26, 2007IEA/AIE 2007 Improve Coarse Search Generate 50 random points Use best 4 to seed 4 PSOs Design PSOs to favour exploration over convergence
June 26, 2007IEA/AIE 2007 PSO vs. Random Search to find “Smart” Start Points PSO finds even better start points Improved “smart” start points lead to an even better performance Random search PSO
June 26, 2007IEA/AIE 2007 Exploiting Global Convexity Search space is globally convex Seek centre of search space by coordinating individual ESs with crossover PSO With Crossover
June 26, 2007IEA/AIE 2007 Current Work Exploring Coarse Search – Greedy Search Inspired by WoSP (CEC2005) Different from memetic algorithms (which apply greedy search to every search point) Useful for expensive evaluations Useful for non-globally convex search spaces
June 26, 2007IEA/AIE 2007 Rastrigin function Globally convex Average value of each “well” is directly related to the quality of the local optima
June 26, 2007IEA/AIE 2007 Schwefel function NOT globally convex Average value of each “well” should still be directly related to the quality of the local optima
June 26, 2007IEA/AIE 2007 Summary Achieved important level of performance on benchmark test suite for a difficult real-world problem Demonstrated potential of coarse search-greedy search combinations