Professional Documents
Culture Documents
Unit 3 Smart Sensors Toj78grf9l
Unit 3 Smart Sensors Toj78grf9l
Smart Sensors
Primary Mechanical Sensors
Sensors in Mechatronics System
Sensors
Sensors
Sensors
Sensors
Classification of Sensors
Selection of Sensors
Need of Signal Conditioning
Data Transmission
Smart Sensors
Smart Sensors
• The sensor and computer are housed directly at the site of the
measurement.
• In this case we see that the feedback signal is delivered to the valve
via the standard 4–20 mA current transmission.
• In this case the smart sensor sends feedback information to the valve
via the serial bus.
Smart Sensors
Intelligent Sensor
WWW
Intelligent Sensor
What is intelligence
Intelligent Sensor
Problems with conventional sensors
Intelligent Sensor
Problems with conventional sensors
Intelligent Sensor
Compensation
Intelligent Sensor
Capabilities of Intelligent sensors
Integration
Intelligent Sensor
Applications of Intelligent sensors
Intelligent Sensor
Example of Intelligent sensors
Intelligent Sensor
Example of Intelligent sensors
Fuzzy Logic
An Approach for nonlinear mapping of one set of variables into
another set of variables.
In the next step, a fuzzy logic is applied to the input fuzzy variables
and a resulting set of output variables is generated.
Each fuzzy variable should obtain a value between zero and one,
which describes a degree of association of the analog input
(temperature) within the given fuzzy variable.
The fuzzy logic consists of the same basic: ∧—AND, ∨—OR, and
NOT operators:
In the first step, fuzzy variables obtained from rule evaluations are
used to modify the membership function employing the formula-
µK∗ (z) = min {µK (z), zK}
For example, if the output fuzzy variables are 0, 0.2, 0.7, 0.0, then the
modified membership functions have shapes shown by the thick line
in Figure.
Defuzzification process
Neural Networks
A biological neuron is a complicated structure, which receives trains of
pulses on hundreds of Excitatory and inhibitory inputs. Those incoming
pulses are summed with different weights (averaged) during the time
period of latent summation.
If the summed value is higher than a threshold, then the neuron itself is
generating a pulse, which is sent to neighbouring neurons.
Because incoming pulses are summed with time, the neuron generates a
pulse train with a higher frequency for higher positive excitation.
In other words, if the value of the summed weighted inputs is higher, the
neuron generates pulses more frequently.
At the same time, each neuron is characterized by the non-excitability for a
certain time after the firing pulse. This so-called refractory period can be more
accurately described as a phenomenon where after excitation the threshold
value increases to a very high value and then decreases gradually with a
certain time constant.
The refractory period sets soft upper limits on the frequency of the output
pulse train.
In the biological neuron, information is sent in the form of frequency
modulated pulse trains.
Neural Networks
Feedforward neural networks allow only one-directional signal
flow.
Furthermore, most feedforward neural networks are organized in
layers.
The three-layer feedforward neural network consists of input
nodes, two hidden layers and an output layer.
A single neuron is capable of separating input patterns into two
categories, and this separation is linear.
For example for patterns shown in figure, the separation line is
crossing x1 and x2 axes at x10 and x20.
This separation can be achieved with a neuron having the
following weights: w1= 1/x10, w2=1/x20 and w3= -1.
In general for n dimensions, the weights are
Neural Networks
For Detailed Information refer Page No. 946 to 949 of Topic 32.2 and
Topic 32.3 from Mechatronics Handbook
Neural Networks
One neuron can divide only linearly separated patterns. To select just one
region in n-dimensional input space, more than n+1 neurons should be
used.
If more input clusters are to be selected, then the number of neurons in the
input (hidden) layer should be properly multiplied.
If the number of neurons in the input (hidden) layer is not limited, then all
classification problems can be solved using the three-layer network.
An example of such a neural network, classifying three clusters in the two-
dimensional space, is shown in Figure.
Neurons in the first hidden layer create the separation lines between input
clusters.
Neurons in the second hidden layer perform the AND operation.
Output neurons perform the OR operation for each category.
The linear separation property of neurons makes some problems especially
difficult for neural networks, such as exclusive OR, parity computation for
several bits, or to separate patterns laying on two neighbouring spirals.
The feedforward neural network is also used for nonlinear transformation
(mapping) of a multidimensional input variable into another
multidimensional variable in the output.
Neural Networks
• Since biometrics can better solve the problems of access control, fraud
and theft, more and more organizations are considering biometrics a
solution to their security problems.
• The two conductor plates form a basic capacitor. The surface of the
finger acts as a third capacitor plate, separated by the insulating layers
in the cell structure and, in the case of the fingerprint valleys, a pocket
of air.
Fingerprint Scanner
• Varying the distance between the capacitor plates (by moving the
finger closer or farther away from the conducting plates) changes
the total capacitance (ability to store charge) of the capacitor.
Because of this quality, the capacitor in a cell under a ridge will
have a greater capacitance than the capacitor in a cell under a valley.
• To scan the finger, the processor first closes the reset switch for each
cell, which shorts each amplifier's input and output to "balance" the
integrator circuit.
• When the switch is opened again, and the processor applies a fixed
charge to the integrator circuit, the capacitors charge up.
• By reading every cell in the sensor array, the processor can put
together an overall picture of the fingerprint, similar to the image
captured by an optical scanner.
• This makes the system harder to trick. Additionally, since they use
a semiconductor chip rather than a CCD unit, capacitive scanners
tend to be more compact that optical devices.
Retina Scanner
• Developed in the 1980s, retinal scanning is one of the most well-
known biometric technologies, but it is also one of the least
deployed.
The two wavelengths are chosen for the reason that deoxygenated
haemoglobin has a higher absorption at around 660nm and at 910nm
oxygenated haemoglobin has the higher absorption.