Considerable development has been done by some authors of this paper towards development of
manufacturing process units energized by Human Powered Flywheel Motor (HPFM) as an energy source.
This machine system comprises three sub systems namely (i) HPFM (ii) Torsionally Flexible Clutch (TFC)
(iii) A Process Unit. Process unit so far tried are mostly rural based such as brick making machine (both
rectangular and keyed cross sectioned), Low head water lifting, Wood turning, Wood strips cutting, etc
HPFM comprises pedalling system similar to bicycle, a speed rising gear pair and a flywheel big enough
such that a young lad of 21-25 years, 165cm height, slim structure can pump energy around 30,000 N-m in
minutes time. Once such an energy is stored peddling is stopped and a special type of TFC is engaged
which very efficiently brings about momentum and energy transfer from flywheel to a process unit. Process
unit utilization time upon clutch engagement is 5 to 15 seconds depending on the application. In other word
process units needing power of order of 3 hp to 10 hp can be powered by such a machine concept.
Experimental data base model is formulated for Human Powered Flywheel Motor Energized Brick Making
Machine (HPFMEBMM).
The focus of the present paper is on development of an optimum Artificial Neural Network (ANN) model
which will predict the experimental evidences accurately and precisely. The optimisation is acknowledged
though variation of various parameters of ANN topology like training algorithm, learning algorithm, size
of hidden layer, number of hidden layers, etc while training the network and accepting the best value of
that parameter. The paper also discusses the effects and results of variation of various parameters on
prediction of network.
Topology Optimization of Gears from Two Wheeler Gear Set Using Parametric StudyIOSRJMCE
: Gears are used to transmit motion from on shaft to another and it has wide variety of applications. One of the applications of gear is in automobile gear box. Gears generally fail when the working stress exceeds the maximum permissible stress. These stresses are proportional to the amount of power transmitted by the gears. This project intends to identify the magnitude of the stresses for a given configuration of a two wheeler gears transmitting power while trying to find ways for reducing weight of the gear. The philosophy for driving this work is the lightness of the gear for a given purpose while keeping intact its functionality thus reducing the material cost of the gear. Ease of incorporating the new feature for weight reduction over the existing process of manufacturing and the magnitude of volume of weight reduced could be considered as the key parameters for assessment for this work.
The formula cars need high tire grip on racing challenge by reducing rolling displacement at corner or
double change lands. In this case study, the paper clarifies some issues related to suspension system with
inerter to reduce displacement and rolling angle under impact from road disturbance on Formula SAE
Car. We propose some new designs, which have an advance for suspension system by improving dynamics.
We optimize design of model based on the minimization of cost functions for roll dynamics, by reducing the
displacement transfer and the energy consumed by the inerter. Base on a passive suspension model that we
carried out quarter-car and half-car model for different parameters which show the benefit of the inerter.
The important advantage of the proposed solution is its integration a new mechanism, the inerter, this
system can increase advance in development and have effects on the vehicle dynamics in stability vehicle.
Topology Optimization of Gears from Two Wheeler Gear Set Using Parametric StudyIOSRJMCE
: Gears are used to transmit motion from on shaft to another and it has wide variety of applications. One of the applications of gear is in automobile gear box. Gears generally fail when the working stress exceeds the maximum permissible stress. These stresses are proportional to the amount of power transmitted by the gears. This project intends to identify the magnitude of the stresses for a given configuration of a two wheeler gears transmitting power while trying to find ways for reducing weight of the gear. The philosophy for driving this work is the lightness of the gear for a given purpose while keeping intact its functionality thus reducing the material cost of the gear. Ease of incorporating the new feature for weight reduction over the existing process of manufacturing and the magnitude of volume of weight reduced could be considered as the key parameters for assessment for this work.
The formula cars need high tire grip on racing challenge by reducing rolling displacement at corner or
double change lands. In this case study, the paper clarifies some issues related to suspension system with
inerter to reduce displacement and rolling angle under impact from road disturbance on Formula SAE
Car. We propose some new designs, which have an advance for suspension system by improving dynamics.
We optimize design of model based on the minimization of cost functions for roll dynamics, by reducing the
displacement transfer and the energy consumed by the inerter. Base on a passive suspension model that we
carried out quarter-car and half-car model for different parameters which show the benefit of the inerter.
The important advantage of the proposed solution is its integration a new mechanism, the inerter, this
system can increase advance in development and have effects on the vehicle dynamics in stability vehicle.
Finite Element Analysis and Design Optimization of Connecting RodIJERA Editor
The objective of this study is to improve the design of connecting rod of single cylinder four stroke Otto cycle
engine by shape optimization. The main objective of this study is weight reduction of connecting rod and
improving its performance without affecting its functionality. Finite element analysis is one of the most
important tools of CAD/CAM CAE. For this study ANSYS analysis software is used for modeling, analysis and
shape design optimization. Initially, according to design considerations maximum loads were calculated for
various maximum operating loading conditions. Calculated loads used as a loading condition in various load
steps of FEM analysis. Stresses generated across all the locations of connecting rod evaluated using ANSYS
Workbench. For optimization ANSYS Shape optimization module is used and extracted the required shape of
connecting rod. Final CAD model of optimized connecting rod is prepared in Design Modeler. Static structural
analysis of modified design is performed and the results compared with baseline design. After result are
validated with the help of Modified Goodman’s Diagram. From the shape optimization we could able to achieve
14.73% weight reduction in existing connecting rod. Since the optimized design is having sufficient life, the
design is much improved as compared to the existing design
EXTRACTION OF NUMERICAL MODEL THROUGH OPTIMIZATION OF ANN MODEL FOR MANUALLY ...IAEME Publication
Considerable research work is carried in development of process units energized by Human Powered Flywheel Motor (HPFM). The process units tried so far are mostly rural based [12] such as wood turning, wood strip cutting, electricity generation, low head water lifting, etc. The HPFM
comprises of three subsystems namely (i) HPFM, (ii) Torsionally flexible clutch and (iii) A Process Unit.
The flow through the turbine components is associated with energy losses and hence energy
output from turbine is always less than the input energy. The global performance of turbine is
characterized by its overall efficiency. The casing has spiral shape and hence has swirling flow and
flow is subjected to frictional and vortex losses. The passage in stay ring and distributor has solid
vanes and flow passes through the ducts between the vanes is subjected mostly frictional losses.
Since runner is the most important component of mixed flow turbine and its design i.e. the blade
profile, number of blades plays vital role in overall performance of turbine at all operating regimes.
In the present work the numerical simulation of hydraulic Francis turbine is carried out by using
ANSYS software. The losses in each part of turbine are computed at different operating conditions
by changing the solidity of existing runner. The numerical results for efficiency of existing runner
are validated with experimental values. This study can be used efficiently as a reliable tool for
the practical design and performance analysis of Francis hydraulic turbines.
Finite Element Analysis and Design Optimization of Connecting RodIJERA Editor
The objective of this study is to improve the design of connecting rod of single cylinder four stroke Otto cycle
engine by shape optimization. The main objective of this study is weight reduction of connecting rod and
improving its performance without affecting its functionality. Finite element analysis is one of the most
important tools of CAD/CAM CAE. For this study ANSYS analysis software is used for modeling, analysis and
shape design optimization. Initially, according to design considerations maximum loads were calculated for
various maximum operating loading conditions. Calculated loads used as a loading condition in various load
steps of FEM analysis. Stresses generated across all the locations of connecting rod evaluated using ANSYS
Workbench. For optimization ANSYS Shape optimization module is used and extracted the required shape of
connecting rod. Final CAD model of optimized connecting rod is prepared in Design Modeler. Static structural
analysis of modified design is performed and the results compared with baseline design. After result are
validated with the help of Modified Goodman’s Diagram. From the shape optimization we could able to achieve
14.73% weight reduction in existing connecting rod. Since the optimized design is having sufficient life, the
design is much improved as compared to the existing design
Similar to OPTIMIZATION OF ARTIFICIAL NEURAL NETWORK MODEL FOR IMPROVEMENT OF ARTIFICIAL INTELLIGENCE OF MANUALLY DRIVEN BRICK MAKING MACHINE POWERED BY HPFM
EXTRACTION OF NUMERICAL MODEL THROUGH OPTIMIZATION OF ANN MODEL FOR MANUALLY ...IAEME Publication
Considerable research work is carried in development of process units energized by Human Powered Flywheel Motor (HPFM). The process units tried so far are mostly rural based [12] such as wood turning, wood strip cutting, electricity generation, low head water lifting, etc. The HPFM
comprises of three subsystems namely (i) HPFM, (ii) Torsionally flexible clutch and (iii) A Process Unit.
The flow through the turbine components is associated with energy losses and hence energy
output from turbine is always less than the input energy. The global performance of turbine is
characterized by its overall efficiency. The casing has spiral shape and hence has swirling flow and
flow is subjected to frictional and vortex losses. The passage in stay ring and distributor has solid
vanes and flow passes through the ducts between the vanes is subjected mostly frictional losses.
Since runner is the most important component of mixed flow turbine and its design i.e. the blade
profile, number of blades plays vital role in overall performance of turbine at all operating regimes.
In the present work the numerical simulation of hydraulic Francis turbine is carried out by using
ANSYS software. The losses in each part of turbine are computed at different operating conditions
by changing the solidity of existing runner. The numerical results for efficiency of existing runner
are validated with experimental values. This study can be used efficiently as a reliable tool for
the practical design and performance analysis of Francis hydraulic turbines.
Analytical Model of Cage Induction Machine Dedicated to the Study of the Inne...IJECEIAES
This paper presents a new analytical model for inner bearing raceway defect. The model is based on the presentation of different machine inductances as Fourier series without any kind of reference frame transformation. The proposed approach shows that this model is able to give important features on the state of the motor. Simulation based on spectral analysis of stator current signal using Fast Fourier Transform (FFT) and experimental results are given to shed light on the usefulness of the proposed model.
Optimization of Closure Law of Guide Vanes for an Operational Hydropower Plan...Dr. Amarjeet Singh
This paper addresses the optimization of twostage closure law of guide vanes in an operational
hydropower plant of Nepal. The mathematical model
has been established in commercial software Bentley
Hammer, whose correctness has been validated by
comparing the results with the data of experimental
load rejection test. The validated mathematical model
has been employed to find the parameters of optimum
closure pattern, which minimizes the non-linear
objective function of maximum water pressure and
maximum rotational speed of turbine.
Computational Estimation of Flow through the C-D Supersonic Nozzle and Impuls...IJMTST Journal
In this paper, CFD analysis of flow within, Convergent – Divergent rectangular super sonic nozzle and super sonic impulse turbine with partial admission have been performed. The analysis has been performed according to shape of a super sonic nozzle and length of axial clearance and the objective is to investigate the effect of nozzle-rotor interaction on turbine’s performance. It is found that nozzle-rotor interaction losses are largely dependent on axial clearance, which affects the flow within nozzle and the extent of flow expansion. Therefore selecting appropriate length of axial clearance can decrease nozzle-rotor interaction losses. The work is carried in two stages:1) Modeling and analysis of flow for rectangular convergent divergent super sonic nozzle. 2) Prediction of optimal axial gap between the nozzle and rotor blades by allowing the above nozzle flow. In the present work, using a finite volume commercial code, ANSYS FLUENT 14.5, carries out flow through the convergent divergent nozzle study. The nozzle geometry is modeled and grid is generated using ANSYS14.5 Software. Computational results are in good agreement with the experimental ones.
International Journal of Engineering Research and Applications (IJERA) is a team of researchers not publication services or private publications running the journals for monetary benefits, we are association of scientists and academia who focus only on supporting authors who want to publish their work. The articles published in our journal can be accessed online, all the articles will be archived for real time access.
Our journal system primarily aims to bring out the research talent and the works done by sciaentists, academia, engineers, practitioners, scholars, post graduate students of engineering and science. This journal aims to cover the scientific research in a broader sense and not publishing a niche area of research facilitating researchers from various verticals to publish their papers. It is also aimed to provide a platform for the researchers to publish in a shorter of time, enabling them to continue further All articles published are freely available to scientific researchers in the Government agencies,educators and the general public. We are taking serious efforts to promote our journal across the globe in various ways, we are sure that our journal will act as a scientific platform for all researchers to publish their works online.
The need for high pump performance and efficiency continue to encourage the study of flow between two parallel co-rotating discs in multiple discs pump or turbine. Therefore, this study entails the design, construction and CFD simulation of a 3D Tesla pump model axisymmetric swirling flow in order to enhance the understanding of Tesla pump for future development.
Method of solution entails designing and construction of a small prototype tesla pump and then using the design geometry and parameters to design and perform numerical simulation. The results of the numerical simulation were then analyzed.
The result obtained indicates static pressure to have minimum value of -4.7791Pa at the outlet and 13.777Pa at the pump inlet and with velocity magnitude having minimum velocity of 0.00m/s and maximum velocity of 4.12m/s. The strength of the velocity was seen to be very high at the pump outlet. The analysis radial velocity showed minimum value of -0.508m/s and maximum value of 3.981m/s with the radial velocity vector being concentrated at the discs periphery and outlet.
Model simulation results exhibited smooth pressure and velocity profiles. With the 3D simulation all flow variables are able to be predicted.
The need for high pump performance and efficiency continue to encourage the study of flow between two parallel co-rotating discs in multiple discs pump or turbine. Therefore, this study entails the design, construction and CFD simulation of a 3D Tesla pump model axisymmetric swirling flow in order to enhance the understanding of Tesla pump for future development.
Method of solution entails designing and construction of a small prototype tesla pump and then using the design geometry and parameters to design and perform numerical simulation. The results of the numerical simulation were then analyzed.
The result obtained indicates static pressure to have minimum value of -4.7791Pa at the outlet and 13.777Pa at the pump inlet and with velocity magnitude having minimum velocity of 0.00m/s and maximum velocity of 4.12m/s. The strength of the velocity was seen to be very high at the pump outlet. The analysis radial velocity showed minimum value of -0.508m/s and maximum value of 3.981m/s with the radial velocity vector being concentrated at the discs periphery and outlet.
Model simulation results exhibited smooth pressure and velocity profiles. With the 3D simulation all flow variables are able to be predicted.
Similar to OPTIMIZATION OF ARTIFICIAL NEURAL NETWORK MODEL FOR IMPROVEMENT OF ARTIFICIAL INTELLIGENCE OF MANUALLY DRIVEN BRICK MAKING MACHINE POWERED BY HPFM (20)
About
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Technical Specifications
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
Key Features
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface
• Compatible with MAFI CCR system
• Copatiable with IDM8000 CCR
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
Application
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Student information management system project report ii.pdfKamal Acharya
Our project explains about the student management. This project mainly explains the various actions related to student details. This project shows some ease in adding, editing and deleting the student details. It also provides a less time consuming process for viewing, adding, editing and deleting the marks of the students.
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...Amil Baba Dawood bangali
Contact with Dawood Bhai Just call on +92322-6382012 and we'll help you. We'll solve all your problems within 12 to 24 hours and with 101% guarantee and with astrology systematic. If you want to take any personal or professional advice then also you can call us on +92322-6382012 , ONLINE LOVE PROBLEM & Other all types of Daily Life Problem's.Then CALL or WHATSAPP us on +92322-6382012 and Get all these problems solutions here by Amil Baba DAWOOD BANGALI
#vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore#blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #blackmagicforlove #blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #Amilbabainuk #amilbabainspain #amilbabaindubai #Amilbabainnorway #amilbabainkrachi #amilbabainlahore #amilbabaingujranwalan #amilbabainislamabad
Vaccine management system project report documentation..pdfKamal Acharya
The Division of Vaccine and Immunization is facing increasing difficulty monitoring vaccines and other commodities distribution once they have been distributed from the national stores. With the introduction of new vaccines, more challenges have been anticipated with this additions posing serious threat to the already over strained vaccine supply chain system in Kenya.
Explore the innovative world of trenchless pipe repair with our comprehensive guide, "The Benefits and Techniques of Trenchless Pipe Repair." This document delves into the modern methods of repairing underground pipes without the need for extensive excavation, highlighting the numerous advantages and the latest techniques used in the industry.
Learn about the cost savings, reduced environmental impact, and minimal disruption associated with trenchless technology. Discover detailed explanations of popular techniques such as pipe bursting, cured-in-place pipe (CIPP) lining, and directional drilling. Understand how these methods can be applied to various types of infrastructure, from residential plumbing to large-scale municipal systems.
Ideal for homeowners, contractors, engineers, and anyone interested in modern plumbing solutions, this guide provides valuable insights into why trenchless pipe repair is becoming the preferred choice for pipe rehabilitation. Stay informed about the latest advancements and best practices in the field.
Water scarcity is the lack of fresh water resources to meet the standard water demand. There are two type of water scarcity. One is physical. The other is economic water scarcity.
Final project report on grocery store management system..pdfKamal Acharya
In today’s fast-changing business environment, it’s extremely important to be able to respond to client needs in the most effective and timely manner. If your customers wish to see your business online and have instant access to your products or services.
Online Grocery Store is an e-commerce website, which retails various grocery products. This project allows viewing various products available enables registered users to purchase desired products instantly using Paytm, UPI payment processor (Instant Pay) and also can place order by using Cash on Delivery (Pay Later) option. This project provides an easy access to Administrators and Managers to view orders placed using Pay Later and Instant Pay options.
In order to develop an e-commerce website, a number of Technologies must be studied and understood. These include multi-tiered architecture, server and client-side scripting techniques, implementation technologies, programming language (such as PHP, HTML, CSS, JavaScript) and MySQL relational databases. This is a project with the objective to develop a basic website where a consumer is provided with a shopping cart website and also to know about the technologies used to develop such a website.
This document will discuss each of the underlying technologies to create and implement an e- commerce website.
Democratizing Fuzzing at Scale by Abhishek Aryaabh.arya
Presented at NUS: Fuzzing and Software Security Summer School 2024
This keynote talks about the democratization of fuzzing at scale, highlighting the collaboration between open source communities, academia, and industry to advance the field of fuzzing. It delves into the history of fuzzing, the development of scalable fuzzing platforms, and the empowerment of community-driven research. The talk will further discuss recent advancements leveraging AI/ML and offer insights into the future evolution of the fuzzing landscape.
Overview of the fundamental roles in Hydropower generation and the components involved in wider Electrical Engineering.
This paper presents the design and construction of hydroelectric dams from the hydrologist’s survey of the valley before construction, all aspects and involved disciplines, fluid dynamics, structural engineering, generation and mains frequency regulation to the very transmission of power through the network in the United Kingdom.
Author: Robbie Edward Sayers
Collaborators and co editors: Charlie Sims and Connor Healey.
(C) 2024 Robbie E. Sayers
Automobile Management System Project Report.pdfKamal Acharya
The proposed project is developed to manage the automobile in the automobile dealer company. The main module in this project is login, automobile management, customer management, sales, complaints and reports. The first module is the login. The automobile showroom owner should login to the project for usage. The username and password are verified and if it is correct, next form opens. If the username and password are not correct, it shows the error message.
When a customer search for a automobile, if the automobile is available, they will be taken to a page that shows the details of the automobile including automobile name, automobile ID, quantity, price etc. “Automobile Management System” is useful for maintaining automobiles, customers effectively and hence helps for establishing good relation between customer and automobile organization. It contains various customized modules for effectively maintaining automobiles and stock information accurately and safely.
When the automobile is sold to the customer, stock will be reduced automatically. When a new purchase is made, stock will be increased automatically. While selecting automobiles for sale, the proposed software will automatically check for total number of available stock of that particular item, if the total stock of that particular item is less than 5, software will notify the user to purchase the particular item.
Also when the user tries to sale items which are not in stock, the system will prompt the user that the stock is not enough. Customers of this system can search for a automobile; can purchase a automobile easily by selecting fast. On the other hand the stock of automobiles can be maintained perfectly by the automobile shop manager overcoming the drawbacks of existing system.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
Top 10 Oil and Gas Projects in Saudi Arabia 2024.pdf
OPTIMIZATION OF ARTIFICIAL NEURAL NETWORK MODEL FOR IMPROVEMENT OF ARTIFICIAL INTELLIGENCE OF MANUALLY DRIVEN BRICK MAKING MACHINE POWERED BY HPFM
1. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
DOI : 10.5121/ijccms.2013.2304 39
OPTIMIZATION OF ARTIFICIAL NEURAL NETWORK
MODEL FOR IMPROVEMENT OF ARTIFICIAL
INTELLIGENCE OF MANUALLY DRIVEN BRICK
MAKING MACHINE POWERED BY HPFM
P. A. Chandak1
and J. P. Modak2
1
Department of Mechanical Engineering, DMIETR, Wardha (MH), India
2
Professor Emeritus, Dean (R&D), PCE, Nagpur(MH), India
ABSTRACT
Considerable development has been done by some authors of this paper towards development of
manufacturing process units energized by Human Powered Flywheel Motor (HPFM) as an energy source.
This machine system comprises three sub systems namely (i) HPFM (ii) Torsionally Flexible Clutch (TFC)
(iii) A Process Unit. Process unit so far tried are mostly rural based such as brick making machine (both
rectangular and keyed cross sectioned), Low head water lifting, Wood turning, Wood strips cutting, etc
HPFM comprises pedalling system similar to bicycle, a speed rising gear pair and a flywheel big enough
such that a young lad of 21-25 years, 165cm height, slim structure can pump energy around 30,000 N-m in
minutes time. Once such an energy is stored peddling is stopped and a special type of TFC is engaged
which very efficiently brings about momentum and energy transfer from flywheel to a process unit. Process
unit utilization time upon clutch engagement is 5 to 15 seconds depending on the application. In other word
process units needing power of order of 3 hp to 10 hp can be powered by such a machine concept.
Experimental data base model is formulated for Human Powered Flywheel Motor Energized Brick Making
Machine (HPFMEBMM).
The focus of the present paper is on development of an optimum Artificial Neural Network (ANN) model
which will predict the experimental evidences accurately and precisely. The optimisation is acknowledged
though variation of various parameters of ANN topology like training algorithm, learning algorithm, size
of hidden layer, number of hidden layers, etc while training the network and accepting the best value of
that parameter. The paper also discusses the effects and results of variation of various parameters on
prediction of network.
KEYWORDS
ANN, Matlab, Manually driven brick making machine. Simulation.
1. REVIEW OF THE BRICK MAKING MACHINE AND ITS PROCESS UNIT
1.1 Working of manually driven Brick making machine
A manually driven Auger-type brick making [1][3] machine developed by Dr. J. P. Modak is as
shown in figure. The operator drives the flywheel (17) though chain (25) and a pair of gears (19,
20). The chain drive is utilized for first stage transmission because the drive is required to be
irreversible. This is achieved with the conventional bicycle drive with a free wheel (21). When
the flywheel attains sufficient speed, the single jaw clutch (13, 15) is engaged. The clutch drives
the auger screw through a pair of gears (9, 10). The mix fed through hopper (3). A cone (2)
connects the drum (30) to the die (1). The cone eliminates the rotary motion of the mix before it
2. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
40
enters the die. The extracted column is collected in a detachable mould (4). It is lined on the
inside by Perspex to provide least resistance to motion of the column. The column is subsequently
demoulded by placing it upside down on the platform. The mould is moved horizontally, leaving
the column on the platform. About one or two hours after the column is laid on the platform, it
becomes stiff enough to be cut by a cutter to form bricks of standard size.
1.DIE, 2.CONE, 3.HOPPER, 4.AL MOULD, 5.MOULDING STAND, 6.CONVEYOR SCREW, 7.CONVEYER SHAFT,
8.HOPPER, 9. GEAR, 10.PINION, 11.PINION SHAFT, 12.BEARING, MOVABLE HALF CLUTCH, 14.CLUTCH LEVER,
15.FIXED HALF CLUTCH, 16.FLYWHEEL SHAFT, 17.FLYWHEEL, 18, BEARING FOR FLYWHEEL, 19.PINION II, 20.GEAR
II, 21.FREWHELL, 22.INTERMEDIATE SHAFT, 23.BEARING FOR INTERMEDIATE SHAFT, 24.CRANK GEAR, 25.PINION
FOLLOWER CHAIN, 26.DRIVER SEAT, 27.HANDLE, 28.BRACKET, 29.FRAME, 30.CONVEYOR DRUM.
Figure 1. Manually driven Brick Making Machine
The following process variables were involved in the process of experimentation. [1]
Table 1. Process variables and their dimensions
Sr No. Description of variables
Type of
variable
Symbol Dimension
1 Weight of lime Independent WL ML-1T-2
2 Weight of sand Independent Ws ML-1T-2
3 Weight of flyash Independent Wf ML-1T-2
4 Weight of water Independent Ww ML-1T-2
5 Outside diameter of screw Independent D1 L
6 Inside diameter of screw Independent D2 L
7 Pitch of Screw Independent P L
8 Larger Diameter of Cone Independent D1 L
9 Smaller Diameter of Cone Independent D3 L
10 Length of cone Independent LC L
11 Length of die Independent LD L
12 Moment of Inertia of flywheel Independent I ML2
13 Angular velocity of flywheel Independent W T-1
3. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
41
14 Acceleration of due to gravity Independent G LT-2
15 Gear ratio Independent G -
16 Length of square side of die Independent S L
17 Strength of brick Dependent Sb ML-1T-2
18 Length of Extruded Brick Column Dependent Lb L
19 Time of Extrusion Dependent Te T
20
Maximum length of Extruded Brick
Column
Dependent Lbm L
21 Critical Pressure of Extrusion Dependent Pc ML-1T-2
22 Instantaneous Torque on the angular shaft Dependent T ML-1T-2
1.2. Experimental setup
The experimental setup [1] basically consists of a manually driven brick making machine with
following facilities
Facility to change die, cone, auger, screw, blades and gears
Facility to mount the torque meter and to record process torque during extrusion process.
Facility to mount technogerators to record speeds of flywheel and auger screw.
1.3. Procedure of Experimentation
Initially the machine parameters were set as per the plan of experimentation. A homogeneous mix
of lime-flyash-sand, in requisite proportion by weight, was prepared by adding suitable amount of
water. The mix was soaked for 48 hours and was kept ready for use. To assure thorough mixing,
die and cone machine were removed. Sufficient mix was fed into the hopper.
The flywheel was speeded up to 400 rpm and the clutch was engaged. The mix passes out of the
barrel and is collected in the collector. The total prepared mix was circulated by using the
procedure described above three to four times to assure thorough mixing. Now die and cone were
bolted to machine. The mix was fed into the hopper. The flywheel was speeded up to 400 rpm
and the clutch was engaged. The extruded brick column was collected in a detachable mould. The
brick column was replaced in the hopper. This procedure was repeated five to ten times until an
uncracked column of uniform length was obtained. Now the experimental set up was ready to
record the observations.
1.4. Experimental observations and Empirical Model [11]
The experimental observations were recorded in tabulated form. As the variables involved were
high in number dimensionless pi terms were evaluated. And an empirical model was generated to
predict the experimental findings. The model was as follows.
Lb / D1 = 0.0043 (LD/D1) -1.8091
*(D12/IgWf) 0.139
*(G) 0.2766
*(√ D1/g. W) 1.27
*(Lc/D1)-1.977
*(P/ D1)1.3075
*(D2 / D1)0.8313
2. IDENTIFICATION OF PROBLEM AND SELECTED APPROACH
The plots are drawn to see the prediction of experimental evidences by the traditional empirical
model. The figures 2 to 8 evaluate and compare the results.
4. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
42
Figure 2: Graph of comparison between experimental observations and equation based prediction for
LD/D1 Vs Lb/D1
Figure 3: Graph of comparison between experimental observations and equation based prediction for
D12
/Ig)Wf Vs Lb / D1
Figure 4: Graph of comparison between experimental observations and equation based prediction for G Vs
Lb/D1
5. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
43
Figure 5: Graph of comparison between experimental observations nd equation based prediction for √
(D1/g). W Vs Lb/D1
Figure 6: Graph of comparison between experimental observations and equation based prediction for Lc/
D1 Vs Lb/D1
Figure 7: Graph of comparison between experimental observations and equation based prediction for P/ D1
Vs Lb/D1
6. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
44
Figure 8: Graph of comparison between experimental observations and equation based prediction for
D2/D1 Vs Lb/D1
Figures 2 to 8 clearly shows that the equation is not able to draw a continuous path through the
experimental findings. As the previous equation derived stand no more to predict the desired
experimental findings, it is forced to go for such a model which will be more reliable and
realistic. The percentage error is of the order of 200 to 300%. In view of the fact that independent
variables involved are high in numbers, it becomes a very tedious and inaccurate work to build an
accurate mathematical model. ANN i.e. Artificial Neural Network has shown its strength in the
field of learning and prediction of the desired results when the input variables are high in numbers
[7]. Since the equation is not predicting the observed data correctly we cannot rely on the same
for predicting the output for the unseen data. On the contrary, ANN model can give more reliable
model for the same.
3. MODIFICATION IN EXISTING DATABASE
The experimental evidences developed during experimentation were very little in number. As a
result experimental database was found to be insufficient for training and validation of the model
generated though ANN simulation.
In order to develop ANN model, the existing database was modified and improved in magnitude
by manoeuvring plots on the basis of present experimental evidences. The intermediate positions
in the plot are positioned and noted [6]. This database generated is as follows.
Table 2. Modified Data
Sr.
No.
Independent Variables Dependent
Variables
LD/D1 D12/Ig.Wf G √(D1/g).W Lc/
D1
P/
D1
D2 / D1 Lb / D1
1 0.2 3.7 4.5 9.19 0.5 0.24 0.4 1.174
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
240 0.5 2.102 4.5 9.19 0.5 0.24 0.4 0.854
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
550 0.5 3.7 2.867 9.19 0.5 0.24 0.4 1.455
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
710 0.5 3.7 4.5 2.841 0.5 0.24 0.4 0.203
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
912 0.5 3.7 4.5 9.19 0.4391 0.24 0.4 0.995
↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓ ↓
1555 0.5 3.7 4.5 9.19 0.5 0.24 0.39795 1.157
7. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
45
4. FORMULATION AND IMPLEMENTATION OF SEQUENTIAL MODELLING
EVALUATION
Modelling a system through ANN simulation involves use of ANN parameters appropriately. A
topology is nothing but the complete architecture of network formed through the use of ANN
parameters [9]. The ANN parameters should be varied systematically in an attempt to identify
best topology for a specified problem. The number of layers was restricted to two as the variables
involved were high in number. A table for evaluation of modelling technique is formed as below
[5]. The shaded column indicates the variation of that particular parameter and shaded row shows
the slandered value of that parameter.
Table 3. Table of sequential modelling evaluation
Program
Number
Hidden
layer
Size
Type of
Training
Function
Performance
Function
Types of transfer
function Type of
Learning
AlgorithmLayer1 Layer2
P1 20 trainlm mse logsig purelin learngd
P2 100 trainlm mse logsig purelin learngd
P3 200 trainlm mse logsig purelin learngd
P4 100 trainb mse logsig purelin learngd
P5 100 trainbfg mse logsig purelin learngd
P6 100 trainbr mse logsig purelin learngd
P7 100 trainc mse logsig purelin learngd
P8 100 trainlm mae logsig purelin learngd
P9 100 trainlm sse logsig purelin learngd
P10 100 trainlm sse tansig purelin learngd
P11 100 trainlm sse logsig purelin learngd
P12 100 trainlm sse logsig hardlim learngd
P13 100 trainlm sse logsig tansig learngd
P14 100 trainlm sse tansig logsig learngd
P15 100 trainlm sse tansig satlin learngd
P16 100 trainlm sse logsig satlin learngd
P17 100 trainlm sse logsig poslin learngd
P18 100 trainlm sse logsig tansig learncon
P19 100 trainlm sse logsig tansig learngd
P20 100 trainlm sse logsig tansig learnh
P21 100 trainlm sse logsig tansig learnk
The ANN parameters like hidden layer size, Training algorithm, performance function, transfer
functions of layers, learning Algorithm are decided to vary in order to see its effect over the
predication of model. Every parameter posses its diversified standard values out of which some
are chosen and their effects are observed after and during training. The table 3 shows the program
8. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
46
number and respected value of each parameter. For each case of a program one parameter is
varied and other parameters were allocated some constant standard value.
The training for all programs are carried and results were plotted to see the outcome. The training
with so many parameters gives fantastic diversified results which are presented in graphical form
as follows.
5. GRAPHICAL REPRESENTATION OF RESULTS AFTER TRAINING
Figure 9: Neural response with 20 Neurons
Figure 10: Percentage error with 20 neurons
Figure 11: Neural response with 100 Neurons
9. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
47
Figure 12: Percentage error with 100 Neurons
Figure 13: Neural response with 200 Neurons
Figure 14: Percentage error with 200 Neurons
Figure 15: Neural response with training Function “trainb”
10. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
48
Figure 16: Percentage error with training Function “trainb”
Figure 17: Neural response with training Function “trainbfg”
Figure 18: Percentage error with training Function “trainbfg”
Figure 19: Neural response with training Function “trainbr”
11. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
49
Figure 20: Percentage error with training Function “trainbr”
Figure 21: Neural response with training Function “trainc”
Figure 22: Percentage error with training Function trainc”
Figure 23: Neural response with performance Function “mae”
12. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
50
Figure 24: Percentage error with performance Function “mae”
Figure 25: Neural response with performance Function “sse”
Figure 26: Percentage error with performance Function “sse”
Figure 27: Neural response with layer transfer Function “tansig, purelin”
13. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
51
Figure 28: Percentage error with layer transfer Function “tansig, purelin”
Figure 29: Neural response with layer transfer Function “logsig, purelin”
Figure 30: Percentage error with layer transfer Function “logsig, purelin”
Figure 31: Neural response with layer transfer Function “logsig, hardlim”
14. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
52
Figure 32: Percentage error with layer transfer Function “logsig, hardlim”
Figure 33: Neural response with layer transfer Function “logsig, tansig”
Figure 34: Percentage error with layer transfer Function “logsig, tansig”
Figure 35: Neural response with layer transfer Function “tansig, logsig”
15. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
53
Figure 36: Percentage error with layer transfer Function “tansig, logsig”
Figure 37: Neural response with layer transfer Function “tansig, satlin”
Figure 38: Percentage error with layer transfer Function “tansig, satlin”
Figure 39: Neural response with layer transfer Function “tansig, purlin”
16. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
54
Figure 40: Percentage error with layer transfer Function “tansig, purlin”
Figure 41: Neural response with layer transfer Function “logsig, poslin”
Figure 42: Percentage error with transfer Function “logsig, poslin”
Figure 43: Neural response with Learn Function “learncon”
17. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
55
Figure 44: Percentage error with Learn Function “learncon”
Figure 45: Neural response with Learn Function “learngd”
Figure 46: Percentage error with Learn Function “learngd”
Figure 47: Neural response with Learn Function “learnh”
18. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
56
Figure 48: Percentage error with Learn Function “learnh”
Figure 49: Neural response with Learn Function “learnk”
Figure 50: Percentage error with Learn Function “learnk”
6. DISCUSSION OF RESULTS AFTER TRAINING
6.1 Effect of variation of number of neuron in hidden layer
Figure 8 to 10 shows that increase of number of neuron gives better prediction.
But as the number goes to 200 it takes very large time to train the network
Hence Layer size is limited to 100.
6.2 Effect of variation training styles
Figure 10 to 14 gives the results when training styles are changed.
The results are too bad with “trainb” & “trainc”
As a result it can be concluded that training styles affect the performance of network to
great extent.
19. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
57
It is been observed that back propagation training functions are better for fitting function
and the performance seems superior with “trainlm”
6.3 Effect of variation of Performance Function
Figure 14 to 16 displays the results with change of performance function
The change of performance function has shown little effect on prediction
Performance function “sse” has shown better results.
6.4 Effect of variation transfer function to hidden layer
Figure 16 to 24 shows the outcome when transfer function to hidden layers was changed.
There are too many transfer functions to use and network has two hidden layers. Hence
various combinations of these transfer functions were use to see the effect on
performance.
It is been observed that the outer most layer with linear transfer function “purelin” gives
better results
The combination of “logsig, tansig” transfer functions is found best for this case whereas
“with “tansig, logsig” is worst.
6.5 Effect of variation of Learning Function
Figure 24 to 28 put on view the results with variation of learning function.
It clearly shows the is very mild effect of variation learning function on performance of
network
Out of those learning functions “learncon” & “traingd” were very closed
“learngd” is selected amongst them.
7. CONCLUSION
The ANN simulation carried for HPFM operated Brick Making M/C gives satisfactory
results
The simulation is carried out is much exhaustive
It includes almost all ANN parameters to see its effect on network performance
The error in neural prediction much smaller and of the average of 5-10 %
8. FUTURE SCOPE
Prediction of ANN model may be compared with the available empirical model.
The best ANN model may be further used to develop another mathematical model.
The ANN model could be validated through unseen data.
This mathematical model then could be utilized to develop a physical controller.
20. International Journal of Chaos, Control, Modelling and Simulation (IJCCMS) Vol.2, No.3, September 2013
58
REFERENCES
[1] Modak J. P. and Askhedkar R. D. “Hypothesis for the extrusion of lime flash sand brick using a
manually driven Brick making machine”, Bulding Research and Information U.K., V22,NI, Pp 47-
54, 1994
[2] Modak J. P. and Bapat A. R. “Manually driven flywheel motor operates wood turning machine”,
Contepory Ergonomics, Proc. Ergonomics Society annual convension13-16April, Edinburg,
Scotland, Pp 352-357, 1993.
[3] Sohoni V. V., Aware H. V. and Modak J. P. “ Manual Manufacture of Keyed Bricks”, Building
Research and Information UK, Vol 25, N6, 1997, 354-364.
[4] Modak J. P.”Design and Development of Manually Energized Process Machines having
Relevance to Village/Agriculture and other productive operations, Application of manually
energized flywheel motor for cutting of wood strip”, Human Power, send for Publications.
[5] H. Schenck Junior “Theory of Engineering Experimentation”, MC Graw Hill, New York.
[6] P. A. Chandak, “Modelling of manually driven brick making machine by use of ANN”, M. Tech.
Thesis, PCE, Nagpur
[7]. S. N. Shvanandam, “Introduction to Neural Network using Matlab 6.0”, McGraw Hill publisher.
[8] Stamtios V. Kartaplopoulos , Understanding Neural Networks and Fuzzy Logics, IEEE Press
[9] Neural Network Toolbox TM
7 User’s Guide R2010a, , Mathworks.com.
[10] Rudra Prtap, “Getting Started with Matlab7,” Oxford, First Indian Edition 2006.
[11] A. R. Bapat, “Experimental Optimization of a manually driven flywheel motor”, M.E. Thesis,
VNIT, Nagpur.
[12] A. R. Bapat, Experimentation of Generalized experimental model for a manually driven flywheel
motor”, PhD Thesis, VNIT, Nagpur.
Authors
Pawan A. Chandak, Asstt Professor, Mechanical Engg, DMIETR, Wardha (MH), India
,Specilization: Artificial Neural Networks, Design and Fabrication, Vibration based
predictive Maintenance.