Fuzzy Learning Force for Robotized Sewing
A fuzzy model reference adaptive controller for regulating the fabric’s tensional forces applied by a robot during
the sewing task is developed. The adaptive fuzzy logic controller closes the loop outside the internal scara robot controller.
The robot guides a piece of fabric in a conventional industrial sewing machine while its controller maintains a desired
constant tensional force applied to the fabric during the sewing process. In each loop, the proposed controller calculates the
appropriate robot end-effector displacement. A force sensor mounted on the wrist of the robot manipulator measures the
actual force applied to the fabric, and the formulated force error is used in order to adapt the controllers’ parameters. The
performance of the controller is investigated experimentally and the results show the effectiveness of the FMRL approach
and its wide range of applications.
The robotics group of the department of the
Mechanical Engineering and Aeronautics has been
working the last years on the robotic handling of fabrics.
The robotic sewing is one of the tasks that consist the
group’s research. In this framework, a feedforward neural
network (FNN) controller [5], able to guide a wide range
of fabric types, was implemented. The target of the
controller was to apply a desired constant tensional force
to the fabric during the whole sewing process. In order to
investigate further this area, the implementation of a
FMRL controller was decided. Also, the fact that no
work using fuzzy adaptive control has been found in the
robotics handling of fabrics area consisted an additional
motive to use this method. vs enterprises
The robotic sewing system is piece of fabric is gripped by a robot manipulator holding
the right edge while the opposite left edge of the fabric is
moving with unknown velocity by the feed dog
mechanism of the sewing machine. During the sewing
process the fabric should be kept taut so as to prevent the
buckling and ensure qualitative stitches. The desired
tensional forces for each fabric are depended on the fabric
type and properties [1].https://www.vssewingmachine.in/
The aim of the presented approach is to develop
a flexible controller that could be able to guide a wide
range of fabric types without knowing the properties or
the model of each fabric. The target of the proposed
controller is to apply a desired constant tensional force to
the fabric in the begging and during the sewing process,
independently of the sewing machine velocity. The force
sensor mounted on the wrist of the robot manipulator is
used to measure the force applied to the fabric which is
the only feedback signal in the outer control loop relative
to the internal controller of the robot. The tensile stiffness
coefficient of the fabric is non-linear and changes by
decreasing the nominal length as the sewing proceeds