Professional Documents
Culture Documents
Application of Genetic Algorithms in Knitting Tech
Application of Genetic Algorithms in Knitting Tech
net/publication/236645932
CITATIONS READS
16 165
2 authors, including:
Mirela Blaga
Gheorghe Asachi Technical University of Iasi
62 PUBLICATIONS 149 CITATIONS
SEE PROFILE
Some of the authors of this publication are also working on these related projects:
TexMatrix - Matrix of knowledge for innovation and competitiveness in textile enterprises View project
All content following this page was uploaded by Mirela Blaga on 26 January 2018.
To cite this article: M. Blaga & M. Draghici (2005): Application of genetic algorithms in knitting technology, Journal of The
Textile Institute, 96:3, 175-178
This article may be used for research, teaching, and private study purposes. Any substantial or systematic
reproduction, redistribution, reselling, loan, sub-licensing, systematic supply, or distribution in any form to
anyone is expressly forbidden.
The publisher does not give any warranty express or implied or make any representation that the contents
will be complete or accurate or up to date. The accuracy of any instructions, formulae, and drug doses
should be independently verified with primary sources. The publisher shall not be liable for any loss, actions,
claims, proceedings, demand, or costs or damages whatsoever or howsoever caused arising directly or
indirectly in connection with or arising out of the use of this material.
Application of genetic algorithms in knitting
technology
doi:10.1533/joti.2004.0064
M. Blaga and M. Draghici
‘Gh. Asachi’ Technical University, Faculty of Textiles and Leather, Iasi, Romania
Abstract: The paper presents an original software, Knitting Machine Simulator (KMS), developed
to design and to optimize a knitting machine’s cam profiles. The program applies a genetic algorithm
over a real-time knitting machine simulation in order to test the generated cam profiles.
Downloaded by [Universitatea Tehnica Gheorghe Asachi] at 08:13 16 January 2013
Key words: Genetic algorithm, knitting, cams, software, optimization. DirectX, KMS.
© The Textile Institute 0159 175 JOTI 2004 Vol. 96 No. 3 pp. 175–178
M. Blaga and M. Draghici
and Blaga, 2004): the height (h), the bottom length (L),
and the top length of the cam (l). The difference between
the top and bottom length will determine its angle (α).
When shaping the cam, the algorithm will not change its
profile beyond these dimensions. In order to obtain the
profile optimization, the program generates an individual
population, named ‘chromosomes’.
Each chromosome will contain dates referring to the
profile of a cam, using genes. The number of genes is the
same for all individuals of the same population. To describe
a cam profile using genes, dividing the height of the cam
with the number of genes in the chromosome is used, a
value describing the length of the cam at the height of the
gene being attributed to each cam. An example of a gene
information generated cam can be seen in Fig. 2.
Downloaded by [Universitatea Tehnica Gheorghe Asachi] at 08:13 16 January 2013
The software offers the facilities detailed in the following Figure 3 The calculated forces at the impact between the needle
sections. butt and the cam
Legend: Dark force: the force that raises the needle; Light force:
Generation of an initial population the shear force.
The first cam is generated starting from the user-specified
characteristics and will have a linear profile. The others impact between the cam and the needle butt, and the
will be obtained by applying the mutation operator upon optimization of the average and dispersion ensures the
the linear profile cam. A cam will be generated until the search for a cam with a profile as uniform as possible and
number of chromosomes specified by the user is reached. with the least variations of the shear force.
Figure 4 Cam with wrong profile. Figure 5 Cam with better profile.
This way, the program can be restored from the last step.
If the final position is not finalized, the program returns
to the generation before last. To start a new search, the
‘Genetic algorithm’ window is used. Here the test name
is inserted, the file-path location, the number of genes,
and the number of chromosomes of the current test, as
well as dates regarding the cam to be generated: base
length, top length, height and width of the cam.
The ‘Select Machine/Simulation’ window (Fig. 7) sets
different machine configurations, such as the number of
needle beds, the needle number on which the test will
take place, the angle between the needle beds, the distance
between them, the knockover depth, the knitting speed Figure 8 ‘KMS Cams Generator’ in the cam setting stage.
and the knitting cycles during which the test of the cam advantage of the method is that data are obtained in real
will happen. time, from the simulation, not pre-calculated values, so
The user may setup the following characteristics: an interval of initial impact points on the cam can be
obtained that the program will consider when modeling
– the time evolution method, which can be a constant or
the profile of the cam. The utilization of KMS software
a variable between frames;
in knitting machine cam design ensures a reduction of
– the constant time duration established in the ‘Time’
the time for the design process of about 25%, which will
field
involve lower costs for this phase.
The ‘Cams Generator Module’ has also a routine that The ‘Knitting Machine Simulator – Cams Generator
allows the visualization of obtained marks by the Module’ (KMS) represents an original tool for the
chromosomes of a population and the visualization and generating and optimization of cam profiles for knitting
printing of a 2-dimensional image of the cam profile, named machines.
‘KMS–Mesh Profile Viewer’. Figure 8 represents the KMS
Cams Generator in the cam-setting stage. REFERENCES
Downloaded by [Universitatea Tehnica Gheorghe Asachi] at 08:13 16 January 2013