Políticas

130

The real time simulation of the control system used as a typical industrial scenario is achieved by clicking the play button. When this is done the liquid from the upper tank flows to the lower tank. The valve to 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. The alarm sub system sounds at indication of any fault. One of the four computer system interfaces displays the possible rectification methods of the fault and the time evolution of such faults while the other three, displays show the various readings of the outflow rate/liquid level, the pressure and temperature. 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 e.g. controller; some are not visible but are there by default e.g. reset circuit, crystal microcontroller, power, etc;

while some are taken care of by the control program. In Proteus design, this is called ―referencing.

131

called fuzzification). The neural network then takes the fuzzified input and output scales to derive a model which is converted back to the original input and output scales (defuzzification). Then the output of the

―defuzified‖ fuzzy system became input to the process under control as shown in the block diagram in Figure 3.1. The Fuzzy Neural controller of tank water level shown in Figure 4.12a has four layers. The first layer represents the input variables for liquid level, temperature and pressure respectively, the second represents their membership sets, the third layer represents the fuzzy rules and the fourth layer represents the defuzified output for the three variables under consideration. The rule layer produces seventy-five rules altogether, twenty-five rules from each of the variables and gives three outputs at a time for each of the three variables that satisfies the condition at a particular instance.

The design specification is in two stages. The first stage has the personal computer (PC) where all the software controlling the system is installed.

The PC has limited ports which are used for other computer peripheral and communication devices. Out of these ports, one is then used for the bidirectional buffer which interfaced the process control system and the PC. This helps to eliminate the use of two ports for input and output from the PC. When line A is active (Figure 4.11a), line B becomes inactive, and then feedback signal from the process via input latch moves to the bidirectional buffer and goes to the PC. The feedback signals from the

132

process sensors pass through a set of stages before reaching the bidirectional buffer. After amplification of the signal, the multiplexer selects one out of the four variables at a time and sends it to Analog Digital Converter which digitizes the signal and then passes it to the buffer through the input latch. When line B is active, the buffer sends information to the process under control via the output latch to the process through the actuators.

The second stage as shown in figure 4.11b shows the process under fuzzy neural control, which shows a tank containing the liquid that is to be at a set level as water flows in and out of the tank, the heater heats up the Figure 4.11a: Design specification for Fuzzy Neural control of tank water level (First stage)

NEURO CONROL SYSTEM

RUNNING ON PC

PRINTER PORT Intel 8286 Bidirectional Buffer

Analog MUX 1 out of 4Do D1 Analog Digital Converter INPUT PORT L ATCH OUTPUT PORT LATCH

Amplification stage

V

A

B

133

liquid and the stirrer continually stirs it to ensure a uniform temperature.

The three actuators shown are the interfaces to the process under control, and they are the heater control interface, the valve control interface and the power control interface. Four transducers which sense the variables (liquid level, temperature, pressure and outflow rate) were used to convert each respective signal to electrical signal which is sent to the multiplexer where one is selected at a time and from the ADC through the input port latch back to the PC. When Figures 4.11a and 4.11b are combined, figure 4.12b, the model diagram results.

Outflow rate sensor

Outflow Rate Sensor Interface Level sensor interface

Valve Control interface

ON/OFF VALVE Interface PROCESS UNDER NEURAL

CONTROL NETWORK

Stirrer

Level sensor Temperature

Sensor interface

Pressure sensor interface

Heater Control interface

Heater Set point

for level

mV

Figure 4.11b: Design specification for Fuzzy Neural control of tank water level (Second stage)

134

Figure 4.12b shows the block diagram of the Intelligent Process Control System Using Fuzzy-Neural Network. Here, the Fuzzy Neural control system running on PC interfaced to the process under control via an INTEL 8286 Bidirectional Buffer. Just like in the neural controller, when the signal line B is active, the buffer sends information to the process

Vo

HC ^Vop

Figure 4.12a: Fuzzy Neural control of tank water level Vo HC Vop

HL T P

1^ST Layer (input layer)

2^nd Layer (membership function layer)

3^rd Layer (rule base layer)

4^th Layer (output layer)

135

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-out-of-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.

136

Figure 4.12b: Block diagram of The Intelligent Process Control System Using Fuzzy-Neural Network

Outflow rate sensor FUZZY-NEURAL

CONROL SYSTEM

RUNNING ON PC

PRINTER PORT Intel 8286 Bidirectional Buffer

Analog MUX 1 out of 4Do D1 Analog Digital Converter INPUT PORT L ATCH OUTPUT PORT LATCH

Outflow Rate Sensor Interface Level sensor interface

Valve Control interface

ON/OFF VALVE Interface

PROCESS UNDER FUZZY-NEURAL CONTROL

Stirrer

Level sensor Temperature

Sensor interface

Pressure sensor interface

Heater Control interface

Heater

Amplification stage

Set point for level V

mV A

B

137