Seminar Topics & Project Ideas On Computer Science Electronics Electrical Mechanical Engineering Civil MBA Medicine Nursing Science Physics Mathematics Chemistry ppt pdf doc presentation downloads and Abstract

Full Version: NEURO-FUZZY MODELING OF SUPERHEATING SYSTEM OF A STEAM POWER PLANT
You're currently viewing a stripped down version of our content. View the full version with proper formatting.
NEURO-FUZZY MODELING OF SUPERHEATING SYSTEM OF A STEAM POWER PLANT


[attachment=23574]

What is this?



We are going to model the super heating system of a 325MW thermal power plant using Neuro-fuzzy algorithm.
Nine neuro-fuzzy models for seven subsystems of the superheatig systems
The first and second super heaters are MIMO systems, they are modeled as two parallel MISO models with same inputs
Models have 8~11 inputs and one output.


By Using?


Mathematically proven that Least squere error (LSE) method is best suited for linear systems
For non linear systems, additional to above, number data driven (I/O data based) methods as well.
The unknown system can be modeled by means of linguistic variables
Recurrent neuro-fuzzy N/Ws are used which are connected in series or parallel
The common N/W is identified as Adaptive Neuro-Fuzzy Inference Systems (ANFIS)


SECOND LEFT-HAND DE-SUPER HEATING MODELING:


The inputs of the de super heater are the steam temperature before spraying water Tb (inlet temperature), the spraying water mass rate V and the steam mass rate f.
The output is the steam temperature after spraying water Ta (outlet temperature).