Pak. J. Biotechnol. Vol. 15 (special issue-I) 2018
IMPROVED GENETIC ALGORITHM FOR ENHANCING THE COMFORTNESS OF A PASSENGER CAR
By Dhananjeyan S., Rajalakshmi K., Nandhini J., Ramya R., Sophiya P.,
This paper mainly focusing the significance of effective and most powerful optimization technique Real coded Genetic Algorithm (RGA) for vehicle system over Binary coded Genetic Algorithm (BGA). Normal Fuzzy Logic Controller (FLC) can act intelligently to improve the comfort of passengers inside a car. For multi input controllers, the choice of scaling factors of the FLC requires more effort and knowledge where most of the FLC designers struggle. In this paper the FLC scaling factors have been identified with two different but similar optimization techniques – BGA and RGA. For the optimization, the RMS value of car Body Acceleration (BA) is taken as the Performance Index (PI). The simulation work has done in MATLAB/SIMULINK environment by considering the dual bump as the road disturbance input. The effectiveness of the RGA tuned FLC (RGAFLC) is proved in comparison with the BGA tuned FLC (BGAFLC) for the passenger car.
A SURVEY OF EXTANT SURVEILLANCE SYSTEMS USINGBIOMETRIC TRACKING
By Vasanth Subramanian, Sunil Dev Choudhary B. and Lalithamani N.,
Recently there has been a tremendous increase in the interest of the security of people and due to the ubiquitous presence of surveillance cameras and other similar systems, Automated surveillance systems have garnered widespread interest from the scientific community. Concomitantly, several advancements in the domain of biometrics have contributed to its pervasiveness in unrestricted environments. Although current systems are remarkable, they are far from impeccable and are limited by several conditions. In short, there is still vast scope for major improvements in our extant systems. In this survey, we strive to provide a comprehensive review of the present literature and to propose a better model that would aim to solve the present limitations.
A REVIEW ON BIOMETRIC CRYPTOSYSTEM USING FUZZY VAULT
By V. Sujitha and D. Chitra
Biometric framework helps to gather statistics from individual and it’s used to particularly find out the person with the physical-behavioral mechanism of the biometric qualities. The most challenge of biometric method is to provide the guarantee for storage space of the biometric templates without compromising the security and privacy. Biometric cryptosystem method is very helpful to secure traits from unauthorized access. The fuzzy vault is a famous and better biometric cryptography method to ensure the templates and its secret key in biometric frameworks. This paper reviews the various research work did in biometric cryptosystem using fuzzy vault.
FEATURE DIMINUTION BY HYBRID ALGORITHM FOR IMPROVING THE SUCCESS RATE FOR IVF TREATMENT
By Durairaj M1 and N. Ramasamy2
Infertility is the most common problem faced by today’s generation. The factors like environment, genetic or personal characteristics are responsible for these problems. Different infertility treatments like IVF, IUI etc are used to treat those infertile people. But the cost and emotions beyond each and every cycle of IVF treatment is very high and also the success rate differs from person to person. So, there is a need to find a system which would predict the outcome of IVF to motivate the people both in psychologically and financially. Many Data Mining techniques are applied to predict the outcome of the IVF treatment. Reducing the unwanted features which affects the quality of result is one of the significant tasks in Data Mining. This paper proposes a hybrid algorithm which combines the core features of Ant Colony Optimization Algorithm and Relative Reduct Theory for Feature Reduction. In this work, the proposed Algorithm is compared with the existing related algorithms. It is evident from the results that the proposed algorithm achieved its target of reducing the features to minimum numbers without compromising the core knowledge of the system to estimate the success rate.
SURVEY ON NONOBSTRUCTIVE AND CONTINUOUS USER AUTHENTICATION ON MOBILE DEVICES
By N.Lalithamani, Raam Balaji D and SVPKH Satya Dev
The use of mobile devices in our day to day life has increased drastically in the last ten years. Much of it can be contributed to the breakthrough in the field of communication. Since they contain most of our personal information, the constant worry of security and privacy has increased. In order to tackle this problem, non-obstructive and continuous user authentication has been proposed. This paper deals with the methods that have been proposed till now and the challenges that are yet to be overcome in this field.
HUMAN RE-IDENTIFICATION USING COLOUR AND TEXTURE FEATURES
By R. Newlin Shebiah, S. Arivazhagan
Human Re-Identification turns out to be the most fascinating and perplexing tasks in the domain of smart video surveillance in recent time. Re-Identification is crucial in establishing reliable tagging of person across multiple cameras or even within the same camera to re-establish detached or lost tracks. The challenge in Person Re-Identification lies due to the visual and spatio-temporal uncertainty in the appearance of the person’s across multiple cameras. Here, a viewpoint invariant human re-identification framework with colour and texture features is proposed. The descriptor encodes the visual features of the human from the chromatic content described by colour statistical features, Local Binary histogram and Histogram of Gradients derived from wavelet transformed input image. Similarity measure is found by the Euclidean distance measured between the extracted feature descriptors from the non-overlapping cameras. From the experimental results it is observed that the proposed system significantly out performs state-of-the-art algorithms on the VIPeR Human Re-identification dataset.
TEXT BASED SENTIMENT ANALYSIS OF PRODUCT REVIEWS
By A Razia Sulthana, A Arokiaraj Jovith and L Sairamesh
With advent of web 2.0 people started sharing their opinions in social network. The social media helps in communicating with public and provides a clear platform to share the views about the product. This has led to different ways of analyzing the user reviews. Sentiment analysis is one of the wide spread area which helps in identifying the same. We proposed a sentiment classifier which recognizes the opinion word based on linguistic analysis. This analysis is done before the preprocessing stage so as to filter outliers and extract only the necessary words. In against the existing approach, the time consumed in this method is considerably reduced as the reviews are analyzed in the initial stage. This method analyzes the sentiment of the reviews posted by customers in online portals by taking the bigrams into account. The relationship between bigrams is identified to know the wavelength of the user’s intention. The prioritized bigrams are chosen for every review such that it qualifies the root word and the root word itself. To inculcate we have implemented a different theoretical model. The data set we have taken for our experiment is a collection of 25,000 reviews from Cornell. The model was experimented with different training sets where the accuracy and precision measures shows a marginal increase. The results of our approach can be used for predicting the results in future as per the market specifications and future models. The accuracy, precision and recall were the metrics that were used to identify the quality of our methodology. Thus the study on bigrams in reviews yields an added value in sentiment analysis.
BLIND HYBRID WATERMARKING FOR SECURITY OF MEDICAL IMAGES
By K. Swaraja
In the proposed work a sightless robust and secure watermarking for image is planned by utilizing discrete wavelet transform (DWT) and Schur transform. In this proposal by exploiting DWT on the part of RONI (region of non interest) of the medical image, dissimilar sub bands of frequency of wavelets are obtained. Schur transform is employed on the LH sub band of the RONI, to attain dissimilar singular matrices. Of these chosen blocks ensemble of features with related values is recognized from the singular value matrix which lie at the left part. These pairs of values are adapted utilizing a threshold to insert the watermark. To attain the quality of image besides the robustness of medical image as well as content of watermark, suitable threshold is selected. Two watermarks, an image type and a text type which have been employed for the identification of original medical 2D data. The text watermark corresponds to the electronic record of the patient (EPR) for identification and the other watermark which is taken as image presents authentication. As a result of the amalgamation of DWT and Schur transform, this proposal offers improved visibility of watermarked image along with recovered content of watermark. With the projected scheme, watermark bits are extorted effectively even after withstanding a variety of attacks. Performance assessment of projected scheme with accessible schemes illustrates that the robustness is improved in the anticipated scheme against dissimilar kinds of attacks.
A SURVEY ON PEAK VALUE FREQUENCY OF VALVES FOR FETAL DEVELOPMENT
By S. Vinod, D. Hemalatha, A. Sushanthi, J. Nandhini,
Electrochemical coupling of fetal heart can be evaluated noninvasively using Doppler ultrasound and fetal electrocardiography .FNN which is a sort of neural system technique, was utilized to remove blood clots from which patient preoperative data is obtained and efficient model is proposed using Robotically actuated delivery sheath techniques.(RADS)This information can be used for early diagnosis of fetal diseases and assessment main factor of evaluating fetal circulation which provide information on the fetal wellbeing during pregnancy and fetal distress due to insufficient oxygen supply for fetus these conditions threaten the life of the fetus while early detection reduces prenatal morbidity and mortality.
EFFICIENT LSA FLOODING PROCESS TO OPTIMIZE OSPF ROUTING
By P. Anu and S.Vimala
In this paper, the Open Shortest Path First (OSPF) Routing algorithm is improvised in terms of congestion, packet delivery ratio and throughput by having the concept of cluster head to reduce the extra overhead that occurs due to LSA flooding.
DETECTION OF FAULTS IN OVERHEAD LINES USING DISCRETE WAVELET TRANSFORM
By Avagaddi Prasad1 and J. Belwin Edward2
Fault detection is a primary concern in isolation of faults. The present protective relaying systems used for fault detection are not precisely functioning which may lead to entire system shut down. The necessity to improve performance of present protective schemes used in power systems is rapidly increasing due to the drastic changes in power system working environment. This work shows a strategy for fault detection in overhead systems using discrete wavelet transform by overcoming the problems faced in conventional methods. This strategy utilizes just fault current estimations toward one side of the overhead line to detect the faults. The sufficiency of proposed technique is analyzed under a different fault conditions using technical computing tool. The results obtained are encouraging and also it is found out that the accuracy in proposed fault detection methodology has increased considerably.
DESIGN MODELING AND FABRICATION OF HUMAN-HUMANOID ROBOT COMMUNICATION
By Manoharan P. A.1, John Maria Vivian2 , Naveen Winson2 , Solomon Azariah2,Gnana Kousalya2
Humanoid robotics is an emerging technology, lot of research work is done, its advanced research and development is being continued to incorporate multiple tasks in the robust environment of robotics system. Human Machine Interface (HMI)is a challenging task, which depends upon the critical applications required. Study, design and development of a novel Human face recognition and Speech synthesis essential for the humanoid robot, is carried out in this research project. Voice synthesis and recognition, voice to text conversion is interfaced to the database. Important feature of facial recognition is carried out, using principal component analysis (PCA) algorithm called, Eigen-faces. Prototype model of a humanoid design was simulated, fabricated and tested for the real-time application to interact with the students and faculties. Humanoid Robot (HR) model was validated for its functional capability and enhanced processing speed. HR is capable addressing oral communication of the personnel; HRHMI, through teleconferencing or video conferencing (VC) at remote terminal.
Pak. J. Biotechnol. Vol. 15 (special issue-II) 2018
SPECIAL ISSUE ICRAME 17
DESIGN AND DEVELOPMENT OF AN AUTOMATIC HEAD LAMP LEVELING SYSTEMS FOR AUTOMOBILES
By K. Ranjithkumar1, P. Ganeshan1, P. Raju, B. Prabu2, V. Mohanavel3, S. Dinesha1, S. Hariharan1, S. Jayasuriya1, G. Amarnath1
A head lamp is usually attached to the front of a vehicle such as a car, with the purpose of illuminating the road ahead during periods of low visibility, such as night or precipitation. Headlight to be used in informal discussion interchangeably, headlamp is the correct technical term for the day to-day device itself, while headlight properly refers to the beam of light produced and distributed by the device. A headlamp can also be mounted on a bicycle with a battery or small electrical generator, and most other vehicles from trains to airplanes tend to have their own headlamps. A head lamp auto-leveling system can be used inexpensively and for a long term by reducing the unpleasant feeling in the driver. An implementation of the head-lamp leveling system includes head lamps whose axis is tilted horizontally/vertically with respect to a vehicle turning movement
SYNCHRONIZER LIFE ENHANCEMENT USING CARBON FIBRE COMPOSITES
By K. Chandramohan, P. V. Arunraj, A. Haymik Raja,
The synchronizer in a domestic tractor is observed to be having a lifetime of 2-3 efficient years with the current material used for synchronizer being Brass. In this work with discuss about how to enhance the existence time of synchronizer by replacing Brass with Carbon – Carbon composite (C-C) material. The pattern of the carbon fiber chosen is Woven Roving Mat (WRM) which is blended with Epoxy resin with two layers of 0.5 mm thickness as a laminate. The WRM cloth is rolled over by the Epoxy resin with the help of a roller and then both are kept inside the bottom portion of the die arrangement. As design has the central guiding, the die can be inserted easily and straight into the bottom portion and the top portion is pressed inside the bottom portion. The composite friction material die is designed with AISI H13 steel and manufactured. A pressure of 400 kg/cm2 is applied to an area of 7.02 cm2; therefore, a force of 2800 kg is required, hence a 5 Ton hydraulic press is used. The result is observed that the carbon – carbon composite shows enhanced strength and endurance properties than the brass. By the results obtained we infer that brass can be replaced by carbon –carbon composite to increase the lifetime of synchronizer.
AIR COMPRESSOR FAULT DIAGNOSIS THROUGH STATISTICAL FEATURE EXTRACTION AND RANDOM COMMITTEE CLASSIFIER
By S. Aravinth1 and V. Sugumaran2
Reciprocating air compressor is important equipment in industrial sector of both manufacturing and nonmanufacturing division. Failures of such significant components lead to severe economic losses and machine downtime. Several miscellaneous reasons may affect the operating system of such complex arrangement if regular monitoring is not done. This present article comprises of on-line condition monitoring diagnostics of compressor, where five major faults are taken into compressor system one at a time. Vibration signals for every fault condition is acquired and processed through signal condition circuitry arrangements with DAQ system and suitable software medium. Signals from each condition were given as an input to machine learning approach where statistical features were extracted in initial screening process. Most contributing features were alone selected out of feature selection process. These selected features were processed in Random Committee classifier to measure the accuracy of correctly classified signals from taken set of signals.
INVESTIGATION OF PERFORMANCE AND EMISSION CHARACTERISTICS OF DI DIESEL ENGINE FUELLED WITH MAHUA ETHYL ESTERS
By Radha Krishna Gopidesi *1, Premkartikkumar SR2, Naveen Kumar Chinthala3, Narendra Kumar S4
The utilization of diesel engine is continuously increasing due to higher fuel to power ratio and efficient. But, it causes increasing the emissions and the fossil petroleum products are also diminishing rapidly. Thus, it is essential to substitute the diesel fuel with non-edible vegetable oils and animal fat oils. In the present investigation diesel was replaced by Mahua Oil Ethyl Esters (MOEE) with a variety of compositions (M10, M20, M30, and M40) to analyse the performance and the emission characteristics of the diesel engine. In the present experimental work, the engine was made to run on constant speed at varied load conditions. Based on the performance analysis of present investigation M30 gave enhanced results, compared to the pure diesel and the other blends. Therefore, M30 was taken as an optimized blend. For that blend, the air preheating and supercharging was used. The air pre- heating at 60ºC of M30 showed the improvement of mechanical efficiency and brake thermal efficiency when compared with the diesel and all other blends of MOEE. Since, the blends of MOEE have more oxygen content it reduces the emissions of HC, CO, and Smoke compared to pure diesel.
MISFIRE DETECTION IN I.C. ENGINE USING MACHINE LEARNING APPROACH
By Sumedh Mulay1, V. Sugumaran1 and S. Babu Devasenapati2
Misfire is one of the major problem associated with the engine as it leads to power loss along with exhaust of air-pollutants like HC, CO, and NOx. Maintenance and condition monitoring of an IC engine is a very crucial activity which requires restriction of emission to the least possible levels. For misfire detection, vibration signals from engine cylinder were obtained using the piezoelectric accelerometer. As engine misfire gives specific vibration signal pattern with respect to the cylinder where misfire took place. Further, 12 statistical features like Standard Error, Sample Variance, Skewness etc. were extracted from obtained signals. Out of these, only useful features were identified using the J48 decision tree algorithm. Classification via Regression, IBk were used as classifiers for classification of these selected features. This paper deals with the comparative study of these classifiers and ensembling these classifiers using Vote classifier and from that, the better algorithm for misfire detection system is suggested.
COMPARATIVE MECHANICAL CHARACTERIZATION OF SPJ (SISAL-PALM-JUTE)KPC(KENAF-PALM-COIR) -JPJ (JUTE-PALM-JUTE) HYBRID FIBER REINFORCED COMPOSITES
By R. Thamilarasan1*, K. Purushothaman2
Development of natural composites were in use over a long time. Researchers are working to provide green materials due to emission and scarcity issues. This article deals the mechanical characteristics of Sisal-Palmyara-Jute (SPJ), Kenaf-Palmyra-Coir (KPC) and Jute-Palm fruit -Jute (JPJ) fibers at different orientation is prepared with polymer resin. Natural fibers are collected from local farmers and extracted by stem explosion method and are cleaned, treated as per our requirement. Specimens were prepared with ASTM Standards and are tested to evaluate tensile strength, Flexural strength and Impact strength. Woven mat technique and Hand lay-up technique is followed at room temperature to mould the specimen. The weight fractions of fibers are equal 50:50% for all the fibers used in the experimental analysis. The result shows the energy absorbed by the jute-palm-jute composite is more than the other for equal weight fractions.
MECHANICAL CHARACTERIZATION OF SISAL-PALM-JUTE AND KENAF-PALM-COIR HYBRID FIBER REINFORCED COMPOSITES
By R. Thamilarasan1*, K. Purushothaman2, B. Murugesh3, P. Ramshankar4, P. Ganeshan4, K. Raja6
Development of natural composites were in use over a long time. Researchers are working to provide green materials due to emission and scarcity issues. This article deals the mechanical characteristics of Sisal-PalmyaraJute(SPJ) and Kenaf-Palmyara-Coir (KPC). Fibers at different orientation is prepared with polymer resin. Natural fibers are collected from local farmers and extracted by stem explosion method and are cleaned, treated as per our requirement. Specimens were prepared with ASTM Standards and are tested to evaluate tensile strength, Flexural strength and Impact strength. Hand lay-up technique is followed at room temperature to mould the specimen. The weight fractions of fibers are equal 50:50% for all the fibers used in the experimental analysis. The result shows the energy absorbed by the composite SPJ is more than the other for equal weight fractions.
MECHANICAL CHARACTERIZATION OF PALMFRUIT (HYBRID) FIBRE REINFORCED COMPOSITE
By R. Thamilarasan1*, K. Purushothaman2,
This paper describes the research work carried out with natural composites of Jute-Palm fruit-jute (J-P-J) and Sisal-Sisal-Sisal (S-S-S) fibers at different orientation are prepared with polymer resin. Natural fibers are collected from local farmers and extracted to our required size also cleaned, treated as per our requirement. Specimens were prepared with ASTM Standards and are tested to evaluate tensile strength, Flexural strength and Impact strength. Woven mat technique and Hand lay-up technique is followed at room temperature to mould the specimen. The weight fractions of fibers are equal 50:50% for all the fibers used in the experimental analysis. Flexural, tensile and Impact properties of hybrid composites were analyzed. The result shows the energy absorbed by the jute-palm-jute composite is more than the other for equal weight fractions.
STUDY ON THE MECHANICAL PROPERTIES OF THE NATURAL FIBRE REINFORCED POLYMER COMPOSITE MATERIALS
By P. Ramshankar1*, K. Raja2, P. Ganeshan3, P. Raju3, V.S. Karthigayan4, M. Lavanya3, K.K. Pavithraa3, H. Rajaraja Sozhan3, M. Mohanambal3
The studying of mechanical properties of fibre and its reduced cost of treating and several other property variations can achieve the requirement of alternatives in fibre utilization. These chemically treated natural fibers are possessing improved properties than untreated fibers. They are having better results in impact strength, toughness and fatigue limit. The main objective of this review is defining about the research of natural fibre and developing the natural fibre in its reinforced polymer composites.
A STUDY ON MECHANICAL PROPERTY OF CEMENT WITH PARTIAL REPLACING SECONDARY CEMENTITIOUS MATERIALS
By P. Vasanthi1, A. Sujaatha2, A. Bhaskar3, Lavish Gaur4
In recent years, a lot of interest has been developed among the civil engineering community regarding Secondary Cementitious Materials (SCM) in concrete. The ingredients that have to Moreover since ground granulated blast furnace slag (GGBS), Fly ash and Silica fume (Bhanja, et al., 2005) industrial by products and the quality of the end products may depend heavily on the quality of these byproducts. By considering the above threat a study was carried out in M40 grade of concrete with the fractional substitute of cement by GGBS, fly ash and silica fume with different percentages. our work presents a detailed study on its strength parameters like Compressive strength, split tensile strength and flexural strength for period of 7 days, 14 days and 28 days respectively. From this process, it reveals that the increase in fractional substitute of cement by SCMs increased the compressive, split tensile strength and flexural strength with the Partial replacement of OPC by GGBS 20 % + SF 10% gives the better result than the normal type of concrete.
INVESTIGATION ON MICROSTRUCTURE AND MICRO HARDNESS OF FRICTION STIR WELDED DISSIMILAR ALUMINUM ALLOY PLATES
By G. Swaminathan1, S. Sathiyamurthy2, P. Naveenchandran3
Assembly of two different grades of aluminum plates is need in many light weight vehicles structures like military, aerospace, ship building and automobile applications. This paper deals with joining of AA7075-T651 with AA6063-T6 aluminum alloys by friction stir welding (FSW) process using cylindrical straight and taper at Tool revolving speed, tool axial force and welding transverse speed of 1000,1100,1200rpm, 4, 5, 6 KN and 30,45,60 mm/min. The effect welding process parameters on weld appearance and hardness were examined experimentally. The microstructures were observed at various regions and analyzed by means of optical microscope. From this investigation were established that the use of taper cylindrical pin profile of tool provides to better flow of materials between both alloys and the formation of flaw free weld zone. The growth in Micro-Hardness is attributed to the development of fine grains and intermetallic in the weld zone, and in addition, the reduced size of weaker regions, such as TMAZ and HAZ regions, results in good metallurgical properties.
OPTIMIZATION OF CYCLE TIME OF PALLETIZATION USING ABB ROBOT THROUGH SIMULATED ANNEALING ALGORITHM AND TRANSLATIONAL APPROACH
By Ameet Singh1, V. Sugumaran2, G. Balamuruga Mohan Raj3
The paper is related to pick and place robotic system (IRB - 1600). The main objective is to minimize the optimum cycle time of the robotic system. To achieve the following objective simulated annealing algorithm (SA) is carried out. Industrial constraint regarding the functioning of real industrial robotic system has been taken in concern during the research practice. Numerical results show that the different algorithm perform optimally for the tested instances in a reasonable computational time. Complete installation and cycle time of the system has been reduced and optimized with proper design and simulation using offline programming.
STUDY OF EROSION CORROSION BEHAVIOUR OF MAGNESIUM AND ITS ALLOYS
By S. Jayabharathy1, P. Mathiazhagan2
Erosion Corrosion is the degradation of material by means of combined effect of mechanical flow and chemical reactions with the surrounding environment. Light weighting of automobiles has been a critical issue in the transportation industries. Magnesium alloy seems to be the best promising next generation’s material and as a substitute to aluminium alloy and steel that are being used in automotive, aerospace industries. In this study ,Magnesium,AZ31 and AZ91 were used to investigate the erosion corrosion rate and corrosion rate in 3.5% wt NaCl .The experiments involved the measurement of weight loss .Experimental setup was used to carry out the erosion corrosion test. Immersion test was conducted to determine the corrosion rate. Results include erosion corrosion analysis, comparative analysis of erosion corrosion and corrosion rate. Further SEM analysis was done to study the microstructure behaviour of the samples. It was found that the corrosion rate increases as time of exposure increases. It was also inferred that the erosion corrosion rate is higher than corrosion rate due to moving fluid under the same environmental condition.
AN EXPERIMENTAL STUDY ON TERNARY BLEND BASED STEEL FIBRE REINFORCED GEO POLYMER CONCRETE
By M. Jothilingam1, Pratheeba Paul2,
Cement is the second most consumed product and as per the year 2010 status the quantity assessed was 3.3 billion tons at global level. Cement industry accounts for 5% to 8% of world’s carbon dioxide emissions. It is also well-known fact that cement production consumes large amount of natural resources such as limestone, chalk, clay, etc. which are extracted from the quarry by blasting. On the other hand, Thermal Power Plants generates huge quantities of Fly ash while utilizing the coal for their process. As assessed by Central Electricity Authority, the total quantity of Fly Ash generated during 2015-2016 in India was 83.64 million MT. As per the Report of Indian Minerals year book 2014 issued by Ministry of Mines, Government of India, around 10 million tons of Blast Furnace slag is generated in India from iron & steel industry. Substantial quantity of this fly ash and GGBFS are used for landfills only. Both fly ash and GGBFS exhibits Cementitious as well as pozzolana characteristics. So, fly ash and GGBFS can be effectively utilized for production of concrete. One of the current research trends in Civil Engineering is to find an alternate material for Cement concrete. Geo Polymer Concrete is one such alternate for Cement Concrete. But, steam/ heat curing is required for producing Geo Polymer Concrete which makes it difficult for using the same for in situ applications. This project aims at finding the viable solutions for producing cast-in-situ geopolymer concrete without compromising on mechanical and durability properties of geopolymer concrete by using locally available industrial wastes such as Fly Ash & GGBS. The compression and flexural strength along with durability properties of Geopolymer concrete were investigated in this work. This study consisted of casting cubes and prisms and curing was done at ambient temperature to suit the cast-in-situ conditions. The specimens were tested for 7 & 28 days strength. Durability studies were carried out after the age of 28 days. It can be concluded that Geopolymer concrete can be produced cast-in-situ without any special curing requirement such as steam/ heat curing, and without compromising on mechanical and durability properties
FABRICATION AND TESTING OF 13 LAYER GLASS FIBER LAMINATES FOR APPLICATION IN ELECTRICAL JUNCTION BOXES AND ENCLOSURES
By D.K. Mohan kumar, A. Mathivanan, G.Manikandan, S.D. Kumar
Aim of our work is to investigate the experimental values of tensile, flexural, impact, compression flame rating test and thermal expansion test GFRP Composites Embedded with 13 layers of Glass fiber orientation as laminates. The laminates are prepared with orientation of (900 450 900 450300 450 900 450 300 900 450 900 450) under Rule of mixture. Basically Metal, wood and alloys are used as electrical enclosures, junction boxes and battery Housings, Alloys are used to improve heat dissipation, insulation and weight reduction, however we incorporate the idea of replacing the metal ones with glass fiber sheet laminates. The result shows the significant improvement of flexural strength, tensile strength, less weight and no fire extinguish in the composite manufacturing laminates, from the obtained results it is found that Glass fiber reinforced laminates replace the existing electrical junction boxes.
DESIGN AND FABRICATION OF UP DE-SALINATOR KIT OPTIMIZATION OF PROCESS PARAMETERS FOR GAS METAL ARC WELDING OF DISSIMILAR AA7075 AND AA6063 ALUMINIUM ALLOYS USING ARTIFICIAL NEURAL NETWORKS (ANN)
By G. Swaminathan1, A. Mathivanan2, S.D. Kumar1, C. Uthirapathy1
The present investigations deal with the effect and optimization of gas metal arc welding parameters on the mechanical properties in welding of dissimilar AA7075 and AA6063 Aluminum alloys. The process parameters used are current, voltage and gas flow rate and Taguchi experimental design method were followed. Tensile strength and Impact strength have been found for the optimum welding parameters. Further an Artificial Neural Network model was developed for the analysis and simulation of the correlation between process parameters and mechanical properties. The input for the model is current, voltage and gas flow rate and the output for the model is Tensile and Impact strength. The combined influence of current, voltage and gas flow rate on the mechanical properties of the joint was simulated. The model can calculate tensile strength and impact strength as functions of process parameters. Lastly a comparison was made between the measured and calculated value and it was found that the calculated results were in agreement with the measured data.
DESIGN AND FABRICATION OF UP DE-SALINATOR KIT
By P. Ganeshan1*, P. Raju1, A. John Martin2, D.S. Nethran1, S. Raja1, S. Kavin1, N. Naveneeth Raj1, M.R. Manikandan1, K. Raja3
Water, is an endless requirement of the living thing all around the universe. But now it is reaching a level of scarcity in all regions which had rich water sources before. This not achieved naturally but we humans in order to find solutions on living with luxury lead a test with environment by destroying the forest, over utilization of ground water sources, improving the level of chemicals in the available ground water with use of chemical fertilizers and with several forms of destructive techniques. Thus we humans who started this should find a solution to end up the arising situation. Which not only have brought solution to the available problems but also acts as a solution for the problems which are going to arise further.
PERFORMANCE ANALYSIS OF 2-METHYLTETRAHYDROFURAN BLENDED ON BIODIESEL ENGINE
By P. Ganeshan1*, V. Ragavan1, P. Raju1, S. Karthigayan2, M. Nimalan1, V. Mathan Raj1, S. Naveen Prakash1, K. Praveen Kumar1, P. Rajkumar1
Biodiesel nowadays is emerging as an alternative fuel which is a good replacement to the petroleum diesel. Biodiesel is mainly derived from fats and oils by different methods such as dilution, pyrolysis, micro emulsification and transesterification but these days most commercial method used for bio-diesel production is 2methyltetrahydrofuran transesterification. Biodiesel was prepared using transesterification process by optimizing the production parameters such as alcohol to oil molar ratio, catalyst concentration etc. Engine design also plays an important role as if it is improved it reduces fuel consumption and give better performance parameters. In this thesis the main emphasis has been laid on optimum production of biodiesel from neem oil and then using the biodiesel blends with diesel studying the comparative exhaust emission characteristics and engine performance. A four stroke single cylinder compression ignition engine was used to measure performance and emission parameters. Biodiesel (fire point and calorific value) added to the diesel (fire point and calorific value) at Three different volume concentrations i.e. 10, 20, &30 of Biodiesel and to blend the Biodiesel with 2-Methyltetrahydrofuraneto study the emission levels.
DESIGN AND FABRICATION OF ALTERNATIVE COOLING SYSTEM FOR CONVENTIONAL PURPOSE
By N. Yogaraj1, P. Ganeshan1*, P. Raju1, P.A. Nigal Ashik1, B. Boobalan 1, K. Arumugam 1, D. Dinesh Kumar 1, V. Logeshwaran 1, K. Raja
The main purpose of this alternate cooling system is to circulate cooling air to the surrounding that means it will act as an air cooling system. Instead of using water, ice cubes are used here. The exhaust fan plays a main purpose of the exhaust fan is to suck the air from the closed area (polystyrene container) and supply to surrounding. The polystyrene box is nothing but the thermocol container and it is shaped into required dimensions for fitting the exhaust fan at the center of the box. The sufficient ice cubes are kept inside the box. Once the ice bars are filled into the closed container the vapour arises, after completing all the setting process the exhaust fan is switched to ON position, so that it exhausts the vapour to the surrounding. The cooling capacity is measured with the help of digital thermometer and the temperature is to be noted for every 2 hours so that the verification of the cooling capacity is to be done.
COMPUTATIONAL FLUID DYNAMICS ANALYSIS OF FINNED TUBE DEHUMIDIFIER FOR SOLAR HUMIDIFICATION DEHUMIDIFCATION DESALINATION PLANT
By B. Monarch1, V. Tejasvi1, C. Chiranjeevi1*, T. Srinivas2 and R. Shankar2
Desalination by air Humidification Dehumidification (HDH) is one of the upcoming technologies of converting brackish water into freshwater. It works by evaporating the brackish water and humidifying air passing over it, leaving the salts behind. The humidified air is then passed through the condensers to recover the water it carries by condensation of water vapour. This condensed water is free from salts and can be directly used or can be further treated for use. The use of a compact finned tube heat exchanger for the purpose of the 2nd dehumidifier in a two stage HDH process is carried out by using computational fluid dynamics (CFD) analysis. The boundary condition for the computational work is obtained from experimental setup in a pilot plant. As CFD models can take up very large computational power for solving fin structures, the model is solved by modelling the fins side of the dehumidifier as a porous medium. The water yield obtained from condensation, thermal characteristics of the fluid model are obtained is compared with experimental results. The yield of water obtained is 3848 ml/hour for the first set of experimental observations.
TYRE PRESSURE MONITORING SYSTEM USING STATISTICAL ANALYSIS AND ROTATION FOREST ALGORITHM
By Anoop P.S. and V. Sugumaran
Tyre pressure monitoring systems (TPMS) are dedicated vehicle systems, which is to calculate the vehicle tyre pressure at any condition. Direct tyre pressure monitoring systems use normal pressure sensors to measure the pressure which is fitted within the tyre. These systems are accurate and they need batteries and wireless sensors. An indirect TPMS uses the sensor data from the wheel speed sensor of the anti-lock breaking system and compares them to determine a pressure difference. This paper suggests a new and reliable vehicle tyre pressure supervise hardware using rotation forest algorithm. Vertical wheel hub vibrations are extracted using an accelerometer. The statistical features are acquired from the accelerometer data and the features are classified using rotation forest algorithm. A reasonably good percentage (93.33%) of classification accuracy was attained from the experiment.
ARTIFICIAL LIMB MOVEMENT SYSTEM USING K-STAR ALGORITHM - A DISCRETE WAVELET TRANSFORMATION APPROACH
By V.V. Ramalingam*1, S. Mohan2, V. Sugumaran3, B. Rebecca jeyavadhanam4
Machine learning is one of the promising areas which contributes to human rehabilitation and this statement can be substantiated by the number of researches conducted in this field. In this study, we attempt to direct an artificial limb system with the help of Electroencephalogram (EEG) signals. EEG signals are created as a result of brain activities when humans intend to perform any action. Hence, capturing this signal and using them to control the artificial limb will be as close to how a human will control their normal hand. Four separate “classes of EEG signals were recorded from” 27 healthy subjects while they were instructed to perform various hand movements such as Finger open (Fopen), Finger close (Fclose), Wrist counterclockwise (WCCW) and Wrist clockwise (WCW). The recorded EEG signals were further classified with classification algorithm to identify the desired movement. Feature extraction, feature selection and feature classification are the three important phases of machine learning which needs to be focused on. The aim of this study is to mine Discrete Wavelet features from EEG signals, classify them with K-Star algorithm, and propose the best features that can be used to regulate the artificial limb.
LIFETIME MAXIMIZATION OF WIRELESS SENSOR NETWORKS IN A WIND TURBINE
By Indhu R1*, Sankaran R A2, Sugumaran V3
Wind turbines are installed in remote places and operated continuously which demands continuous condition monitoring systems for effective utilization. The condition monitoring of wind turbine is using machine learning approach is an established area. While the initial cost of the wind turbines are higher, the additional cost introduced by the condition monitoring system makes the situation worse. The fault diagnosis technique is employed using wireless sensor networks (WSN) wherein one sensor node is attached to every wind turbine in which the fault diagnosis is done. A sink node receives the signals from all the wind turbines and all the operations are carried out in the sink node. A major issue in WSN is that the battery of the sensor nodes will reduce gradually with time, as the location of the sensor nodes are very far from the sink node in many wind turbine plants. The effective operation of the WSN based fault diagnosis system is greatly dependent on number of wind turbines per base station of the wireless sensor network. In the present work, the machine learning technique is used for the extracted vibration signals from the wind turbine bearing. The wind turbine plant is equipped with the wireless sensor network and found that when the base station is in the middle of the wind turbine plant, three wind turbines has to be kept for one base station. The simulation is done using Matlab©.
ANALYSIS AND MODELLING OF SUPPORT VECTOR MECHANISM FOR THE BIOMASS GASIFICATION PROCESS
By T. Sathish*1, M.D.Vijayakumar2, P. Periyasamy3
Biomass gasification process is one of the major process of producing combustible gases like Carbon monoxide (CO), Hydrogen (H2) and traces of Methane and non-useful products like tar and dust are used in hot air generators, dryers, boilers, ovens, industries and in many other applications. So in order to improve the accuracy and efficiency of biomass gasification a precise modelling technique based on artificial intelligence is proposed in this paper. Support Vector Mechanism (SVM) is the proposed method used to increase the efficiency of the biomass gasification and to predict the biomass gasification by back propagation algorithm.
EXERGY ANALYSIS OF SOLAR PHOTO VOLTAIC THERMAL HYBRID HEAT PUMP WORKING WITH CIRCULAR AND TRIANGULAR EVAPORATOR TUBE CONFIGURATIONS
By N. Gunasekar1, M. Mohanraj2, G. Sathish Sharma3, R. Prakash3*
In order to evaluate the performance of a solar photovoltaic thermal hybrid heat pump working with circular and triangular tube evaporator configurations, exergy analysis is performed in this study. The experiments were carried out under the meteorological conditions of Coimbatore city (latitude of 10.98oN and longitude of 76.96oE) in India. Exergy destruction and exergy efficiency of each components of the system were calculated with reference to four ambient conditions such as solar intensity, ambient temperature, ambient relative humidity and ambient wind velocity. The exergy performance parameters of the heat pump were simulated using artificial neural networks to have accurate exergy performance comparison. The results indicated that maximum exergy destruction for both the configurations occurred in PV-T evaporator. The exergy destruction in circular tube configuration is 2-7% higher than triangular tube configuration. It was also found out that exergy efficiency of the system using triangular tube configuration is 1.2-3.8% higher than circular tube configuration.
EFFECT OF SAMPLING FREQUENCY AND SAMPLE LENGTH ON FAULT DIAGNOSIS OF WIND TURBINE BLADE
By More Vasudha, Panditrao Harshal, A. Joshuva*, V Sugumaran*
The purpose of this research is to determine the effect of sampling frequency and sample length on fault diagnosis of the wind turbine blade in order to optimise the cost as high sampling frequency leads to high cost. This study uses machine-learning approach followed by feature extraction and feature selection with J48 decision tree algorithm. In this take a look at, statistical features had been extracted from vibration signals with various sampling frequency and corresponding sample duration. With extracted features, function choice and category turned into achieved. With the help of J48 decision tree algorithm the optimal sampling size is obtained at sampling frequency of 4000Hz, which gives the classifier accuracy as 72.66%. The obtained results can be used with low cost accelerometer i. e. MEMS based accelerometer.
ANALYZING VERTICAL VIBRATIONS OF AUTOMOBILE WHEEL HUB TO MONITOR TYRE PRESSURE USING STATISTICAL FEATURES AND SUPPORT VECTOR MACHINE ALGORITHM
By Anoop P S1, V Sugumaran1 and Hemanth Mithun Praveen1
One of the main safety measures used in automobiles are Tyre pressure monitoring systems (TPMS). These are intelligent devices fabricate to supervise the tyre pressure in automobile. The current technology use barometric sensors or vehicle speed sensors to measure the pressure directly. They mainly depend on batteries and different types of remote sensors which would increase the installation cost and complication maintenance. This paper suggests a novel technique adopting machine learning and fault diagnosis to supervise the vehicle tyre pressure indirectly. Vertical vibrations from a wheel hub are acquired using a three axis mems accelerometer sensor. After feature extraction and feature selection the selected features are classified using support vector machine algorithm. A good classification accuracy of 90% was gained.
OPTIMIZATION OF CYCLE TIME OF PALLETIZATION USING ABB ROBOT THROUGH PARTICLE SWARM OPTIMIZATION ALGORITHM AND TRANSLATIONAL APPROACH 4:13 AM 3/29/2018
By Ameet Singh1, V. Sugumaran1,* , G. Balamuruga Mohan Raj2
This paper presents an efficient and reliable evolutionary-based approach to solve palletization problem. The proposed approach employs particle swarm optimization (PSO) algorithm for minimization of cycle time of palletizing robot i.e. IRB-1600. The operator of algorithm are reviewed, focusing on how each affects search behaviour in the problem space. This paper first analyzes the impact of the parameters i.e. population size and maximum run on the performance of the particle swarm optimizer. Numerical results show that the different algorithm perform optimally for the tested instances in a reasonable computational time. The proposed approach results have been compared to those that reported in the literature recently. The results are promising and show the effectiveness and robustness of the proposed approach.
ESTIMATION OF REMAINING LIFE OF BEARINGS USING ROTATION FOREST AND RANDOM COMMITTEE CLASSIFICATION MODELS – A STATISTICAL LEARNING APPROACH
By R. SATISHKUMAR1, V. SUGUMARAN2
Bearings are considered to be one of the critical elements in all rotating machineries. Bearings are in general used to reduce or minimize the friction in the rotating parts. Strengthening the predictive maintenance of bearings helps to improve the performance of the machines. Hence, bearing prognosis gains its importance in the recent times. This paper emphasis on estimation of remaining life of bearings using classification models through condition monitoring techniques. Vibration signals acquired from the experiments were used to assess the current state of the bearings while in operation. Statistical features were extracted from the signals and the best contributing features were selected for building a classification model with Random forest, Rotation forest and Random committee classifiers. The effectiveness of the classification model built by Random forest, Rotation forest and Random committee classifiers were analysed and compared through a statistical machine learning approach.