3. Go is an ancient Chinese game.
Fan Hui was defeated by AlphaGo
recently
3
4. What is Artificial neural network?
It resembles the human brain in the
following two ways: -
It acquires knowledge through learning.
It’s knowledge is stored within the
interconnection strengths known as weight.
4
5. Inputs , xn
Connection weight , wn
Sum = w1 x1 + ……+ wnxn
Simply summed, fed to f( )
to generate a result and
then output.
f
w1
w2
xn
x2
x1
wn
f(w1 x1 + ……+ wnxn)
ARTIFICIAL NEURON MODEL
6. ARTIFICIAL NEURAL NETWORK MODEL
output layer
connections
Input layer
Hidden layers
Neural network
Including
connections
(called weights)
between neuron
Compare
Actual
output
Desired
output
Input
output
Fig: Showing adjust of neural
network
Fig : Artificial neural network model
7. TYPES OF ANN
7
A two-layer feedforward artificial
neural network with 8 inputs, 2x8
hidden and 2 outputs
A single-layer feedforward artificial neural
network with 4 inputs, 6 hidden and 2
outputs. Given position state and direction
outputs wheel based control values.
12. HOSPITALS AND MEDICINE
Used as clinical decision support
systems
Have also been used to diagnose
several cancers.
Computer-aided interpretation of
medical images.
12
13. ADVANTAGES
It involves human like thinking.
They handle noisy or missing data.
They can work with large number of variables or
parameters.
They provide general solutions with good predictive
accuracy.
System has got property of continuous learning.
They deal with the non-linearity in the world in which
we live.
14. RELEVANCE OF ANN IN OUR PROJECT
Signal Conditioning Circuit voltage Vs pressure exhibits
nonlinearity.
Reason being component drifts.
The ANN estimates and compensates the nonlinearity of SCC.
Significant stability , High sensitivity & High linearity.
14
15. PRESSURE SENSING ELEMENTS
(A) a C-shaped Bourdon tube
(B) a helical Bourdon tube
(C) flat diaphragm
(D) a convoluted diaphragm
(E) a capsule
(F) a set of bellows
15
16. BELLOW AS A SENSING ELEMENT
16
It is simple
Rugged in construction
Capable of providing large force
Wide pressure range.
17. WORKING OF BELLOW
17
Displacement of Bellow
by applied pressure.
Fixed end of
ferromagnetic wired to
bellow end.
Change in Inductance
due to small
displacements.
18. PRESSURE TRANSDUCER
•It provides an electrical output proportional
to applied pressure.
•It combines the sensor element of a gauge
with a mechanical-to-electrical converter.
18
19. PREVIOUS ATTEMPTS AT PRESSURE TRANSDUCING
Pressure transducer with elastic capacitor as a transducing
element.
Intelligent differential pressure transmitter to maximize sensor
output.
Switched capacitive interference for capacitive pressure sensor
by Yamada.
Piezo-electric pressure transducer with silicon diaphragm as
sensor. 19
Continued
…
20. A dual diaphragm based wire transducer for
pneumatic pressure measurement.
Automatic bridge balancing method for
capacitive sensor.
Modified Maxwell-Wien bridge for
measurement of displacement based
inductance.
20
22. HYDRAULIC SYSTEMS
22
Utilized to monitor and
provide pressure
feedback to systems.
Allow the operator to fully
control the mechanical
devices.
Monitor the hydraulic
fluid level for preventive
maintenance.
23. FLUID & GAS SYSTEMS
To monitor the
requisite pressure
conditions
23
24. SIGNAL CONDITIONING
Manipulating of Analog Signal for
further processing.
It is among the basic processes in
control engineering.
Other basic processes include sensing
and processing of signal.
It includes processes like filtering,
amplifying, converting etc. 24
26. APPLICATIONS OF SIGNAL CONDITIONING
Data Acquisition.
Pre processing of Signals.
Devices that use SCC are signal filters,
instrument amplifiers, isolation
amplifiers, digital-to-analog
convertors, invertors, current to
voltage convertors, multiplexers etc.
26
27. O I S C C
•Op amp based inductive signal
conditioning circuit.
•It uses position sensor using differential
inductance measurement.
•It has achieved a linearity of 2.5%.(
proposed circuit). 27
29. LIMITATIONS OF OISCC
•The direct connection of inductance in
feed back path which provides derivative
action may damage it.
•Suffers from stray effects, ambient factors
which causes non linearity in result.
29
30. OUR PROPOSED TECHNIQUE AT A GLANCE
Change in inductance due to
bellow displacement
Signal conditioning using
OISCC
Compensation of errors by
ANN
Highly linear and Sensitive
output. 30
32. OVERVIEW OF OUR NEXT PRESENTATION
Detailed working of OISCC
Algorithm used in ANN
Output characteristics of our model.
Advantage of our model compared to other
techniques.
32
33. REFERENCES:
P. E. Thoma, R. Stewart, and J. Colla, “A low pressure capacitance type
pressure to electric transducing element,” IEEE Trans. Compon.,Hybrids
Manuf. Technol., vol. 3, no. 2, pp. 261–265, Jun. 1980.
S. Shimada and Y. Shimizu, “Intelligent differential pressure transmitter
with multiple sensor formed on a (110)-oriented circular silicon
diaphragm,” IEEE Trans. Ind. Electron.,vol. 38, no. 5, pp. 379–384, Oct.
1991.
J.-M. Wu, “Multilayer Potts perceptrons with Levenberg–Marquardt
learning,” IEEE Trans. Neural Netw., vol. 19, no. 12, pp. 2032–2043, Dec.
2008.
V. N. Kumar and S. Sankar, “Development of an ANN-based linearization
technique for the VCO thermistor circuit,” IEEE Sensors J., vol. 15, no. 2,
pp. 886–894,Feb. 2015.
S. C. Bera, R. Sarkar, and M. Bhowmick, “Study of a modified differential
33