PowerPoint Presentation

Guided By, VIDHYA.G.KAIMAL AsstProf:T.K.M.I.T Presented By, DANY ABEL RAJDELBIN SABUSHEBIN THOMASSREENATH.SVINEETH.V.LPROSTHETIC HAND USING ARTIFICIAL NEURAL NETWORK

ABSTRACTThe scientific researches in the field of rehabilitation engineering are increasingly providing mechanisms in order to help people with disability to perform simple tasks of day-to-day.

Several studies have been carried out highlighting the advantages of using muscle signal in order to control rehabilitation devices, such as experimental prostheses.

This project use of forearm surface electromyography (sEMG) signals for classification of several movements of the arm using just three pairs of surface electrodes located in strategic places.

Electromyography (EMG) is the control interface for modern, upper limb prosthetics.

Signal classification by Artificial Neural Network.

Cost effective

INTRODUCTIONThe development of systems managed by myoelectric signals with the intention to reproduce the human arm movement is far from perfect, which makes it the target of many investigations

Control of prosthesis based on the intention of the user .

Amputees are able to generate standardized myoelectric signals.

The proposed system uses only 3 pairs of electrodes .

More precise than conventional limb prosthetic

BACKGROUND INFORMATION Current Prosthetic Hand using TechnologyBCI TECHNOLOGYThe mind-to-movement system that allows a quadriplegic man to control a computer using only his thoughts is a scientific milestone. It was reached, in large part, through the brain gate system.

The Brain Gate System is based on Cyber kinetics platform technology to sense, transmit, analyze and apply the language of neurons.

The principle of operation behind the Brain Gate System is that with intact brain function, brain signals are generated even though they are not sent to the arms, hands and legs.

MYO ELECTRIC HANDMyo electric uses a battery and electronic motors to function.

Once it is attached, the prosthetic uses electronic sensors to detect minute muscle nerve, and EMG activity.

It then translates this muscle activity (as triggered by the user) into information that its electric motors use to control the artificial limbs movements.

The end result is that the artificial limb moves much like a natural limb, according the mental stimulus of the user.

The user can even control the strength and speed of the limbs movements and grip by varying his or her muscle intensity.

LITERATURE SURVEYClassification of Surface Electromyographic Signal for Prosthesis Control Application

2010 IEEE EMBS Conference on Biomedical Engineering & Sciences (IECBES 2010 KualaLumpurMalaysia, Siti A. Ahmadi, Asnor J. Ishak, Sawal Ali

This describes the classification stage of an electro myographic (EMG) control system for prosthetic hand application.

Moving ApEn was used as main method to extract features from the two channels of surface EMG signal at the forearm of the upper limb.

PROPOSED DESIGN

BLOCK DIAGARAM OF WORKING FLOW

SignalAcquisition USB interface

SensorPIC microcontroller

PC

MATLABanalysiscontrolling

Motor drive

CIRCUITS

Usb connectionMOTORPIC 16F87A POWER SOURCE EMG SENSOR POWEREMG SENSOR

PROTOTYPE 1MATERIAL USED SILICONE

Similar to human Wrist ShapeNot enough strongMore flexiblePoor holding power

DESIGNING THE HAND

PROTOTYPE 2 MATERIAL USEDTHERMOPLASTICS AND POLYSTYRENEPoor Design

Less Gripping

Poor Finger Movements

Not Flexible

PROTOTYPE 3

Less weightEasy to carryEasy movementsCan hold objectsElastic Band for Automatic closingUpgradable

MATERIALS USEDTHERMOPLASTICS WOOD ETC.

FEASIBILITY OF THE TOPICThe costs of commercially available myoelectric hands are very high, ranging in price from 3-4 lacs.We were able to develop a prototype hand with similar functionally to the more sophisticated myoelectric hands on the market.It roughly costs up to fifty thousand rupees . A new technology is devised for manufacturing the Prosthetic hand while making it easily affordable.

PLATFORM OF THE TOPICHARDWAREMicrocontrollerEMG sensor EMG electrode and padsServo motorPVC pipeNylon string

SOFTWAREMATLABMPLABPROTEUS

FUTURE ENHANCEMENTIndividual MotorsPowerful microprocessorsProportional Speed ControlFour Wrist OptionsSoft finger padsInnovative palm designDurable construction

Project planWork doneSelection of the Materials.Designing the prosthetic.Shipment of the Hardware parts. Prepared the initializing and training codes for the working.Completed the source code for motor drive.Developed the prototype

WORKING DEMO

CONCLUSIONThe proposed system uses only 3 pair of electrodes for the signal acquisition process.

The signal processing comprises of initialization, training and testing.

Artificial Neural Network is configured with three hidden layers

The no: of values for input sector is equal to the no: of output sector.

Particular data sets of EMG from amputees are loaded for the processing.