Performance Analysis of IoT-Based Sensor, Big Data Processing, and Machine Learning Model for Real-Time Monitoring System in Automotive Manufacturing

Current technologies such as Internet of Things (IoT)-based sensors can be considered a solution to provide efficient monitoring of the manufacturing process. In this study, a real-time monitoring system that utilizes IoT-based sensors, big data processing, and a hybrid prediction model is proposed.
Authors: Muhammad Syafrudin, Ganjar Alfian, Norma Latif Fitriyani and Jongtae Rhee 
 
Journal: Sensors 2018, 18(9), 2946
 
Publisher: MDPI 
 
Abstract
 
With the increase in the amount of data captured during the manufacturing process, monitoring systems are becoming important factors in decision making for management. Current technologies such as Internet of Things (IoT)-based sensors can be considered a solution to provide efficient monitoring of the manufacturing process.
 
In this study, a real-time monitoring system that utilizes IoT-based sensors, big data processing, and a hybrid prediction model is proposed. Firstly, an IoT-based sensor that collects temperature, humidity, accelerometer, and gyroscope data was developed. The characteristics of IoT-generated sensor data from the manufacturing process are: real-time, large amounts, and unstructured type.
 
The proposed big data processing platform utilizes Apache Kafka as a message queue, Apache Storm as a real-time processing engine and MongoDB to store the sensor data from the manufacturing process. Secondly, for the proposed hybrid prediction model, Density-Based Spatial Clustering of Applications with Noise (DBSCAN)-based outlier detection and Random Forest classification were used to remove outlier sensor data and provide fault detection during the manufacturing process, respectively.
 
The proposed model was evaluated and tested at an automotive manufacturing assembly line in Korea. The results showed that IoT-based sensors and the proposed big data processing system are sufficiently efficient to monitor the manufacturing process. Furthermore, the proposed hybrid prediction model has better fault prediction accuracy than other models given the sensor data as input. The proposed system is expected to support management by improving decision-making and will help prevent unexpected losses caused by faults during the manufacturing process.

Photo: The real-case implementation of the proposed IoT-based sensor in an assembly line (credits: Muhammad Syafrudin, Ganjar Alfian, Norma Latif Fitriyani and Jongtae Rhee)

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
 
Read more

Comments

No comments to display.

Related posts

EU's Call for Proposals: RobotUnion acceleration program for European robotic startups and SMEs

The ideal project RobotUnion is looking for is disruptive and innovative, beyond the state of the art and with a degree of differentiation with its competitors. The ideal projects are also looking for additional investment for scaling their business globally.
Application Deadline in 2 months

Vietnamese Seafood export targets US$ 10 billion in turnover in 2019

The Vietnamese aquatic sector set a target of raising its export revenue to US$10 billion in 2019, according to the Viet Nam Association of Seafood Exporters and Producers (VASEP).

Australia Emerges as a Leading Innovator for Agriculture 4.0

Investors and researchers are looking to Australia to develop the agricultural and food technologies of the future.

Dubai’s RTA starts using robots in cleaning metro stations

Dubai’s Roads and Transport Authority (RTA) has embarked on using robots in cleaning metro stations as part of efforts to introduce new techniques driven by artificial intelligence technology.

India approves Phase-II of Grid Connected Rooftop Solar Programme for achieving cumulative capacity of 40,000 MW from Rooftop Solar Projects by the year 2022

The Cabinet Committee on Economic Affairs chaired by the Prime Minister, Shri Narendra Modi has given its approval for the Phase-II of Grid Connected Rooftop Solar Programme for achieving cumulative capacity of 40,000 MW from Rooftop Solar (RTS) Projects by the year 2022. The programme will be implemented with total central financial support of Rs.11,814 crore (1,663 million USD)

EU's Call for Proposals: eIdentification & eSignature

The Core Service Platform of eID will continue to provide support to Member States at technical and operational level. Such assistance will comprise technical support and advice, including the maintenance of the reference implementation, as well as supporting a broader uptake of eID. In addition to the support provided in previous WPs, the assistance will be extended also to the operation of the eIDAS interoperability nodes after the entry into force of the eID mutual recognition in September 2018, as well as to addressing implementation questions derived from this mutual recognition (such as identity matching issues). The support to the onboarding of new domains will be continued, with a special focus on the re-use of eID in mobile environments.
Application Deadline in 3 months

EU's Call for Proposals: Automated Translation

In 2019, the main objectives are to support the collection of language tools and resources for specific domains and for under-resourced languages as well as to stimulate the integration and take-up of CEF AT services.
Application Deadline in 3 months

Call for Proposals: Promoting leadership and economic opportunities for women across the clean energy sector in Southern and East Africa

This call is focused on promoting leadership and economic opportunities for women across the clean energy sector. We are seeking applications that propose innovative approaches to gender inclusion while also supporting core business objectives and growth. Projects will be evaluated based on concept innovation, development impact, business model and financial sustainability. Applications from women entrepreneurs and women-led organisations are strongly encouraged.
Application Deadline in a month

Call for Nominations: 2019 BBVA Foundation Frontiers of Knowledge Awards

Nominations are open for 2019 BBVA Foundation Frontiers of Knowledge Awards that recognize fundamental contributions in a broad array of areas of scientific knowledge, technology, humanities and artistic creation.
Application Deadline in 4 months