International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 02 | Feb-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 832
Asset Management in Manufacturing Industries Using Big Data
Analytical Architecture
Dr.T.R.Saravanan
1
, R.S.Vaibhave
2
1
Assistant Professor, Department of Computer Science and Engineering, JEPPIAAR SRR Engineering College,
Padur, Chennai -603103.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - The asset management is for managing
company's details by storing and sorting them. The
company which wants to have a good place in market can
make use of these ideas of storing data and further
analyzing them. The storage is about details of the workers,
machine and their functionalities, stock market details
which require huge storage and therefore big data concept
is employed. Handling with the data includes Hadoop, data
mining technologies which are essential for this
architecture. The structured, semi-structured and
unstructured data has to be managed. The major purpose is
to make use of the unused data of the company. The unused
data are just the ones which have low necessity for the
company but maybe of some use to the employee such as the
machine details and the instructions of operating them. The
employee can also get access to their own salary details by
having authentication. By giving more features for the user
the company can be more organized and easy for the
employee at the same time. Here the data scientist plays an
important role for visualizing the data which are to be given
to the employee. The clustering and classification
algorithms are used for sorted storage. The prediction
process is carried after the report of all the data has been
collected. Resultant graph is being generated so that it is
easy for the authorities to analyze the growth and their
position in market.
Key Words: authentication, big data, classification,
clustering, Hadoop, market
1. INTRODUCTION
A huge amount of data for operating and maintaining is
required and the asset of the company serves this purpose.
Nowadays, every industry uses asset management
functions for storing large amount of data. But they arenǯt
using the best of it. Some companies donǯt even process
the stored or existing data. This results in the degradation
of the companyǯs performance and its efficiency. The
Information and Communication Technologies have
become dynamic and the industries should develop their
standards by using these technologies efficiently [1]. Many
applications and systems which are governed by these
ICTǯs are implemented in some industrial areas. Though
they make use of them, these technologies do not yield a
complete overview about the system. Here the users and
the data scientists are the major part of the system,
primarily when it comes under the tree of big data. The big
data objective is to process and handle data which is of
high velocity, volume, variety and veracity [2]. In the view
of Information and Communication Technology, Big Data
is the best technology to be used in industries [3]. The data
scientist must be an expert in solving the problems which
arises during the understanding of data, preparing the
data, modelling the data, evaluating the data and
deploying it efficiently. Managing the assets in an efficient
way with many facilities is the major goal. This includes
maintaining the company's standards and also making the
company more organized. The asset management system
provides an easy way for storing the company's data and
managing it. The architecture paves way for more accurate
grouping of data and storing them in ordered way. The
Hadoop distributed file system is used so that any type of
data regarding the company can be handled. The data may
be text, images and other formats also. The system overall
generates a prediction report for the growth of the
company.
The upcoming part of the paper is arranged in the
following manner. In section 2, this paper reviews about
how the uploading of data and pre-processing is carried
out. In section 3, the classification and clustering of the
data is discussed. In section 4, the analysis and the
prediction of the growth is explained. In section 5, the
aspects of the user interface is presented. Section 6 depicts
the overall structure of the system by explaining the
architectural design. The section 7, describes the tools
involved to achieve the successive environment. The
following section consists of the future work to be carried
out. Finally the section 8 summarizes the outcomes. These
all operates in a single system and provides efficient
management through big data technology.
2. FILE UPLOAD AND PREPROCESSING
File uploading is the chief process which is carried out in
every big data projects in order to work with it. Here in this
system, the data stored up to date is to be considered for
processing. Data gathering is the major step taken to
perform stock market analysis. In the Manufacturing
industrial sector, monitoring of various assets usually the
sensors are used to keep the machineries in an optimal
state and to reduce the maintenance downtime. This
converts the physical machinery property into an electrical
signal. Then the manipulation is performed using the filters
to reduce the noise generated. And these are sent to a
database where liable information can be obtained. This is
also a part of asset of the company.