Evolutionary algorithms (EA) are a superset of genetic algorithms (GA). GA usually work with bits or small integer numbers.

There are some EA that can work directly with floating-point numbers, among them Differential Evolution (DE) [1] [2] [3].

The talk gives an introduction to continuous (floating point) problems using examples from electrical engineering and the optimization of waveforms for piezo-electric inkjet printers. With these printers the form of the jetted droplet (among other parameters like the liquid being jetted) depends on the waveform sent to the piezo crystal. The droplet shape is responsible for the quality of the drop and the print result.

The software uses the Python bindings PGAPy [5] for the package PGAPack. PGAPack is a genetic algorithm library originally developed at Argonne National Laboratories [4]. I maintain both open source packages for some years now. Over the years I’ve added various newer algorithms like Differential Evolution and strategies for multi-objective optimization using NGSA-II [6]. This makes PGAPack a comprehensive optimization toolbox for all sorts of evolutionary algorithms.

[1] Rainer Storn and Kenneth Price. Differential evolution – a simple and efficient adaptive scheme for global optimization over continuous spaces. Technical Report TR-95-012, International Computer Science Institute (ICSI), March 1995.

[2] Rainer Storn and Kenneth Price. Differential evolution – a simple and efficient heuristic for global optimization over continuous spaces. Journal of Global Optimization, 11(4):341–359, December 1997.

[3] Kenneth V. Price, Rainer M. Storn, and Jouni A. Lampinen. Differential Evolution: A Practical Approach to Global Optimization. Springer, Berlin, Heidelberg, 2005.

[4] PGAPack, a general-purpose, data-structure-neutral, parallel genetic algorithm library https://github.com/schlatterbeck/pgapack

[5] PGAPy: Python Wrapper for PGAPack Parallel Genetic Algorithm Library https://github.com/schlatterbeck/pgapy

[6] Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and T. Meyarivan. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2):182–197, April 2002.