The term of Intelligent Manufacturing Systems (IMSs) can be attributed to a tentative forecast of J. Hatvany and L. Nemes from 1978.  In another landmark paper of J. Hatvany in 1983, IMSs were outlined as the next generation of manufacturing systems that - utilizing the results of artificial intelligence (AI) research - were expectedto solve, within certain limits, unprecedented, unforeseen problems on the basis even of incomplete and imprecise information. Soft  computing  technologies,  like  ANNs,  fuzzy  systems,  GAs,  probabilistic  tech-niques,  their  combinations  and  their  hybrid  use  with  more  traditional  symbolic  approaches of AI are prospective tools for realizing systems with the required behaviour. Soft  computing  (SC)  is  a  branch,  in  which,  it  is  tried  to  build  intelligent  and  wiser machines.

Intelligence provides the power to derive the answer and not simply arrive to the answer. Purity of thinking, machine intelligence, freedom to work, dimensions, complexity and fuzziness handling capability increase, as we go higher and higher in the  hierarchy  The  final  aim  is  to  develop  a  computer  or  a machine which will work in a similar way as human being scan do, i.e. the wisdom of human beings can be replicated in computers in some artificial manner. Intuitive   consciousness/wisdom   is   also   one   of   the   important   area   in   the   soft computing, which is always cultivated by meditation. This is indeed, an extraordinary challenge   and   virtually   a   new   phenomenon,   to   include   consciousness   into   the computers. Soft  computing  is  an  emerging  collection  of  methodologies,  which  aim  to  exploit tolerance  for  imprecision,  uncertainty,  and  partial  truth  to  achieve  robustness, tractability    and    total    low    cost.    Soft    computing    methodologies    have    been advantageous in many applications.

In contrast to analytical methods, soft computing methodologies  mimic  consciousness  and  cognition  in  several  important  respects: they  can  learn  from  experience;  they  can  universalize  into  domains  where  direct experience  is  absent;  and,  through  parallel  computer  architectures  that  simulate biological  processes,  they  can  perform  mapping  from  inputs  to  the  outputs  faster than inherently serial analytical representations. The trade off, however, is a decrease in accuracy.  If  a  tendency  towards  imprecision  could  be  tolerated,  then  it should  be possible  to  extend  the  scope  of  the  applications  even  to  those  problems  where  the analytical and mathematical representations are readily available. The motivation for such  an  extension  is  the  expected  decrease  in  computational  load  and  consequent increase of computation speeds that permit more robust system.

Soft Computing differs from conventional (hard) computing in many ways.  For example, soft computing exploits tolerance of imprecision. Uncertainty, partial truth and human mind.  “In effect the role model of soft computing is human mind. “Soft-computing is  defined  as  a  collection  of  techniques  spanning  many  fields  that  fall  under various categories in computational intelligence. Soft computing has three main branches: fuzzy Systems,   evolutionary   computation,   artificial   neural   computing,   machine   learning   (ML), Probablistic  Reasoning  (PR),  belief  networks,  chaos  theory,  parts  of  learning  theory  and Wisdom based Expert System (WES), etc.