Alternative Water Level Controller using Artificial Intelligence for Industrial Drum Boiler.

This work is based onthe paper entitled 'Overcoming the shrinkandswell effect in
water level controlstrategy on industrial drum boiler' [1], The basic function of this
boiler is to produce steam. The steam will allow the turbine to function and therefore,
will generate electricity to users. This paper illustrates the optimisation of loadfollowing
scheme by applying 3-element controller scheme to regulate the drumboiler's
water level. The PID controller is, by far the most commonly used for controlling and
monitoring purposes in process plants. Nevertheless, the performance specifications ofa
PID controllercould be further improved.
This FinalYear Project entitled 'Alternative WaterLevel Controller usingArtificial
Intelligence (AI)forIndustrialDrum Boiler'. It applies neural network, neuro-fuzzy and
pre-processing to comparethe control performance ofthe steam pressureand water level
ofthe boiler model.
The objective of the project is to design and construct software by using Matlab,
which can simulate and enhance thecontroller ofwater level andsteam pressure indrum
boiler. The Artificial Intelligence approach makes it easier to conceptualize and
implement control systems. Theprocess is reduced to a setofvisualizable steps. Thisis
a very important point. Actually implementing a control system, even a simple control
system, is more difficult than it appears. Unexpected aberrations and physical
anomalies inevitably occur.
In reading about AI control applications in industry, one of the significant points
that stand out is: AIis usedbecause it shortens the time for engineering development.
AI enables engineers to configure systems quickly without extensive experimentation
andto make use of information from expert human operators who have beenperforming
the task manually.