CONTROL SYSTEM USING FUZZY-NEURAL · PDF fileCONTROL SYSTEM USING FUZZY-NEURAL NETWORK ......

DESIGNING A FAULT DIAGNOSIS SYSTEM IN A PID PROCESS CONTROL SYSTEM USING FUZZY-NEURAL NETWORK Harmony Nnenna Nwobodo (Dept of Computer Engineering, Enugu State University of Science and Technology, Enugu) and Hyacinth Chibueze Inyiama (Dept of Electronic and Computer Engineering, Nnamdi Azikiwe University, Awka)

Abstract- Detection and diagnosis of systems faults are very essential for

protection of process control systems against failures and permanent damage. In

recent years, monitoring and fault detection in control systems have moved from

traditional methods to artificial intelligence techniques The objective of this paper

is to design a Fault Diagnosis System (FDS) for a PID water control systems that

will monitor the system during its normal working condition so as to detect the

occurrences of failures, recognize the location, the time of such fault, defines the

fault and hence suggests its possible rectification procedures. A PID Fuzzy Neural

Network continuous water process control system that lets water be at a set level as

water flows in and out of the tank was considered. In this paper, the FDS was designed

using Fuzzy Logic technique. Using fuzzy Logic techniques to analyze this is well

suited to low cost implementation based on cheap sensors, low resolution analog

to digital converters, and 4-bit or 8-bit one chip microcontroller systems..

Moreover such systems can be easily upgraded by adding new rules to improve

performance or add new features. Also machine operators will have an idea of the

fault and the rectification procedure.

KEYWORDS: Diagnosis, Fault, rectification, detection, Fuzzy Logic, fuzzy rules, failures

International Journal of Advancements in Research & Technology, Volume 3, Issue 9, September -2014 ISSN 2278-7763

80

Copyright © 2014 SciResPub. IJOART

IJOART

(I) INTRODUCTION

Components, machines and processes fail in varying ways depending upon their

constituent materials, operating conditions, etc. Failure modes are typically

monitored by a sensor which is intended for failure analysis purpose, to capture

those failure symptoms that are characteristics of a particular failure mode.

Pislaru, Trandabat and Olariu [1] in their work on Neurofuzzy system for

industrial processes fault diagnosis featured a methodology to monitor and

diagnose machine faults in complex industrial processes. They developed the

diagnostic model capable of providing diagnosis for single and multiple faults

based on noisy data. In their work, they only showed the faults incurred and

ignored monitoring of the system while on operation, the type and time of fault

occurrence and also the possible rectification techniques.

Wu, Karray and Song (2003) in Water Level Control by Fuzzy Logic and

Neural Network designed an Intelligent controller for controlling water level

system by building a prototype of water level control system first with Fuzzy

Logic control and then with Neural Network. The performance of both were

noted and compared and it was found that the neural network showed a better

performance than that of fuzzy logic. Fuzzy Neural Networks implement the

process of fuzzy reasoning through a Neural Network structure so that they

behave as Fuzzy System with learning capabilities. In this paper, the design of

the Fault Diagnosis System was discussed and then implemented in PID

continuous process system for water level using Fuzzy Neural Network.


81


IJOART

II) DESIGN OF THE FAULT DIAGNOSIS SYSTEM

The main aim of the Fault diagnosis system is the monitoring of the process

control during its normal conditions so as to detect the occurrence of failures,

recognize the location and time of occurrence [3]. Typical failure modes may

include leaks, sensor failures, temperature, pressure, valve failure, etc which is

the characteristics of a process failure. Also as a variety of vibration induced

faults that are affecting mechanical and electro-mechanical process elements

may occur. In this research fuzzy diagnostic system (FDS) was used. The FDS

takes features of the process control as inputs and then outputs any indication

that a failure mode has occurred. Fig 1.1 shows the FDS.

Fig1.1The FDS of tank water level.

PROCESS UNDER CONTROL

Pre-processing and Feature extraction

Fuzzy Diagnostic System

ALARM

FAILURES & POSSIBLE RECTIFICATION TECHNIQUESS

FUZZY DIAGNOSTIC SYSTEM

Fuzzification

Defuzification

Fuzzy inference engine

Fuzzy rule base

Failure


82


IJOART

The fuzzification block converts the feature extraction to degree and type of

failure, the fuzzy rule base is constructed from symptoms that indicate a

potential failure mode (This is developed directly from user experience,

simulated models or experimental data).The inference engine determines the

degree of fulfillment for each rule corresponding to each failure mode while the

last stage defuzzifies the resulting output to indicate a failure and this triggers

an alarm and at the same time suggests a solution to the fault. Table 1 shows the

rule base for failure, the time of occurred fault and rectification techniques. This

is easily produced by the inference engine.

Time of

Occurrence

Observation

(Rule Base)

Fault

(Output)

Rectification Techniques

12.00pm If Water level is at

constant position Then

Outflow valve /inflow valve

is faulty

Verify which and

change the valve

1.00am If Outflow rate is below

the lower threshold level

then

The inflow valve is faulty Change the inflow valve

....etc ... etc ... etc ... etc

Table 1 The rule base for failure, the time of fault and rectification techniques.


83


IJOART

Fig 1.2 shows the Fuzzy Neural control system running on PC interfaced to the

process under control via an INTEL 8286 Bidirectional Buffer where the FDS

was implemented. When the signal line B is active, the buffer sends information

to the process under control via the output port latch. Similarly, when the signal

line A is active, the feedback signals from the process are input via the input

port latch to the bidirectional buffer and from thence to the PC. The process

under Fuzzy-neural control has a valve that controls the inflow of the liquid into

the tank and another one that controls the outflow from the tank. The heater

increases the temperature of the liquid while the stirrer is used to ensure that the

liquid is of uniform temperature. The control system tries to keep the liquid

level in the tank constant within the set-point for level. This is achieved by

fuzzy-neural control by adjusting the inflow rate and outflow rate dynamically

as appropriate. Four sensors were also used: 1) to sense the liquid level in the

tank and 2) to sense the outflow rate from the tank, 3) to sense the temperature

and 4) to sense the pressure of the system. The four sensor outputs are selected

one at a time via 4 X 1 analog multiplexer. The selected signal is first amplified

and then converted to digital pattern via an analog to digital converter. The

digitalized sensor output are latched by the input port latch and forwarded to the

fuzzy-neural control system via the bidirectional buffer.


84


IJOART

Outflow rate sensor

FUZZY-NEURAL

CONROL SYSTEM

RUNNING ON PC

Intel 8286 Bidirectional Buffer

Analog MU

X 1 out of 4 Analog Digital Converter

INPU

T

PORT

OU

TPUT PO

RT LATCH

Outflow

Rate

Level sensor interface

Valve

ON/OFF

VALVE

PROCESS UNDER FUZZY-NEURAL CONTROL

Stirrer

Temperature

Sensor

Pressure sensor interface

Heater

Heater

Amplification stage

Set point for level

V

mV

A B

Fig 1.2 Block diagram of FDS being implemented in a PID Process Control System Using Fuzzy-Neural Network

PROCESS UNDER FUZZY NEURAL CONTROL

Pre-processing and Feature extraction

Fuzzy Diagnostic System

ALARM

FAILURES & POSSIBLE RECTIFICATION TECHNIQUESS

Failures


85


IJOART

III THE INDUSTRIAL SCENARIO

It is always necessary to perform a real-time simulation of any control system

before the circuit is constructed, to ensure the workability of that system. In this

work Proteus software package [4] was used for the simulation. The real time

simulation of the control system used as a typical industrial scenario is activated

by clicking the play button. When this is done the liquid from the upper tank

flows to the lower tank. The valve at the water inlet of the upper tank is being

controlled based on the rate of the outflow from the lower tank. This is done to

make sure that the set-point of the process under control is maintained. The

heater heats the liquid while the stirrer ensures that a uniform liquid temperature

is maintained. Fig 1.3 shows the industrial scenario of the process control in

Proteus environment. The first three computer system interfaces shown display

the variables under control (liquid level/outflow rate, pressure and temperature)

while the fourth one displays the fault diagnosis features (type of fault, time of

occurrence and possible rectification methods).. It should be noted that when

Proteus software is used to implement a real-time simulation, not all the system

components are placed on the layout. Some are placed in the sub sheet for

example the controller and some are not visible but are there by default e.g.

reset circuit, bidirectional buffer, power, the interfaces, analog to digital

converter, the multiplexer etc; while some are taken care of by the control

program. In Proteus design, this is called “referencing”.


86


IJOART

rxd vcc

gnd

vcc

gnd

flow0

liq0

a0a1a2a3a4a5a6a7b0b1b2b3b4b5b6b7rxdga8ga9v1 v0

flow0liq0

ga7ga6ga5ga4ga3ga2ga1ga0c7c6c5c4c3c2c1c0

a6 a6

a5 a5

a4 a4

a3 a3

a2 a2

a1 a1

a7 a7

a0 a0

b7 b6 b5 b4 b3

b1

b0

b2

ga9

ga0

ga8ga7ga6ga5ga4ga3ga2ga1

ga0ga1ga2ga3ga4

ga5ga6

ga7ga8ga9

P2.0P2.1pretempP2.a

buzrxd1txd1

txd3

rxd3

txd3rxd3

P3.atxd2

tssrxd2

txd2

rxd2

txd1

rxd1

SUB?

CCT001

RXD

RTS

TXD

CTS

P2.0P2.1P2.2P2.3P2.4P2.5P2.6P2.7ga0ga1ga2ga3ga4ga5ga6ga7buzliq0

f low0v0

P0.0P0.1P0.2P0.3P0.4P0.5P0.6P0.7P1.0P1.1P1.2P1.3P1.4P1.5P1.6P1.7txdga8ga9v1

24.0

3

1

VOUT 2

43.0

3

1

VOUT 2

12345678

2019181716151413

910

1211

U2

LED-BARGRAPH-GRN

12345678

2019181716151413

910

1211

flow

0gnd

P2.0P2.1

?

?

pretempP2.a

buzrxd1txd1

buz

P2.0

P2.1

Level Sensor Over FlowRate Sensor

CollectorTank

ON/OFF ValveInterface

ValveControl

Process UnderNeuro Fuzzy

Control

Neuro fuzzy Controller Of Tank Water Level

Computer System Interface

Sound(Alarm) Sub System

SyStem Sub Circuit

RXD

RTS

TXD

CTS

36.0

3

1

VOUT 2

67.0

3

1

VOUT 2

pre

temp

P3.a txd3rxd3txd2

rxd2 tss

RXD

RTS

TXD

CTS

RXD

RTS

TXD

CTS

?

?

P2.a

P3.a

tp

tp

P3.a

Temp Sensor

Pressure Sensor

Figure 1.6 Real time simulation for a typical Fuzzy Neural controller of tank water level


87


IJOART

IV CONCLUSION

Error detection and isolation system has been implemented in a Fuzzy Neural

PID controller. The developed Fuzzy Neural Network features error detection

and presents detailed rectification steps. This is much better than the trial and

error method used in repair and maintenance of process control systems.


88


IJOART

(V) REFERENCES

1) Pislaru Marius, Trandabat Alexandru and Olariu Marius on Neurofuzzy

system for industrial processes fault diagnosis (2003)

2) Wu Daniel, Karray Fakhreddine and Song Inso, Water Level Control by

Fuzzy Logic and Neural Network ( 2003 )

3) An Introduction to Fault Detection to Fault Tolerance by Rolf Isermann

(Springer Science and Business Media, 2006).

4) LaMothe, Andre The Black Art of Video Game Console Design. (December

22, 2005). Sams. ISBN 0-672-32820-8.

5) www.datasheetarchive.com/microprocessor 8286-datasheet.html

.


89


IJOART

http://en.wikipedia.org/wiki/International_Standard_Book_Number

http://en.wikipedia.org/wiki/Special:BookSources/0-672-32820-8

CONTROL SYSTEM USING FUZZY-NEURAL · PDF fileCONTROL SYSTEM USING FUZZY-NEURAL NETWORK ......

Documents

Transcript of CONTROL SYSTEM USING FUZZY-NEURAL · PDF fileCONTROL SYSTEM USING FUZZY-NEURAL NETWORK ......