In step of cutting. The results can be summarized

In this paper, a
new intelligent adaptive methodology was proposed for the optimization of
cutting parameters in finish hard turning of AISI D2 using PSO as an
optimization technique and ANN and GP as modeling techniques. Since it
considerers the variations in machining process, which in this paper is
progressive tool wear, the methodology can be defined as an adaptive
optimization system. The core of the system is composed of three process partitions:
a genetic model for predicting the values of tool flank wear, a neural network
model for predicting the surface roughness and a PSO optimization unit to find
optimum cutting parameters in each step of cutting.

The results can
be summarized as follows:

We Will Write a Custom Essay Specifically
For You For Only $13.90/page!

order now

Surface roughness reduces with
the increase of cutting speed and decrease of feed. Tool flank wear also
adversely affect the surface quality. The feed has greater influence on surface
roughness followed by tool flank wear. The tool wear is influenced more by the
cutting speed as compared to feed rate. Tool wear rate is intensive in early
moments. By passing the time, this rate decreases. By considering both the tool
life and the surface roughness, a combination of optimum cutting parameters according
to defined performance index was obtained as v=67.5 m/min and f=0.425

Comparing the results of
experiments and results obtained by intelligent methods shows that genetic
programming and artificial neural networks have unique ability and precision in
modeling of machining characteristics. Models developed for surface roughness
and tool wear using intelligent technique are very useful for predicting new
experiments and can be used reliably in adaptive optimization system. Close
correlation between predicted and measured values was established previously. 

The adaptive optimization
technique presented in this paper can vary cutting conditions to operate at
maximum efficiency based on defined performance index that results in higher
material removal rate accompanying with lower cutting costs. The results of comparisons
made between proposed methodology and optimization with constant parameters shows
that the proposed method improved the sum of performance indexes by 40%
compared to machining with constant optimum cutting parameters.

Future work
could be directed to application of various intelligent models and optimization
techniques to machining process optimization, investigation of adaptive control
with optimization by implementation of various sensor systems to assess the
variation in cutting process, such as tool wear, and apply appropriate cutting
parameters accordingly, and performing adaptive optimization experiments with
different performance indexes and different constraints such as power,
temperature, vibration and other machining characteristics.