A System for Controlling and Monitoring IoT Applications

Lima, Zebenzuy; García-Vázquez, Hugo; Rodriguez, Raúl D.; Khemchandani, Sunil L.; Dualibe, Fortunato; Pino, J. del

doi:10.3390/asi1030026

Cited by 6 publications

(5 citation statements)

References 6 publications

(5 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, the IoT-based sensor device developed in this study is based on Raspberry Pi which is small-size, low-cost, and powerful single-board computer device. Previous studies have shown significant advantages of utilizing Raspberry Pi such as for controlling and monitoring IoT system [ 83 ], estimating the roll angle of a vehicle using embedded neural network in real-time [ 84 ], hosting and serving the user interface of eHealth care system [ 59 ], and monitoring the temperature of lava lake using near infrared thermal camera [ 85 ]. Therefore, the proposed IoT-based sensor device developed in this study could be applied to monitor the manufacturing process in real-time.…”

Section: Resultsmentioning

confidence: 99%

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

Syafrudin

Alfian

Fitriyani

et al. 2018

Sensors

262

103

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

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

Syafrudin

Alfian

Fitriyani

et al. 2018

Sensors

262

103

View full text Add to dashboard Cite

show abstract

“…The following in Figure 6 is a design form of the existing microcontroller or hardware firmware and an explanation of the program syntax flow with pseudocode as shown in Algorithm 1. The microcomputer module is a mini computer connecting the microprocessor and main memory as an inputoutput interface [29]. This study uses a Raspberry Pi Model 4 microcomputer; this computer board is installed with a Linux-based operating system and is used as a core processing device that serves as an IoT Broker and Apache web service.…”

Section: The Electrical Hardware Designsmentioning

confidence: 99%

Neobots: an open-source platform for a low-cost neonatal incubator with internet of things approach

Aryanto,

Maneetham,

Triandini

2024

IJ-AI

View full text Add to dashboard Cite

<div align="center">A baby incubator implements the internet of things (IoT) with an architectural design combining several scientific fields, such as networks, software, and hardware. Furthermore, this research develops an open-source platform called Neobots, including open-source program code to create a baby incubator. Then an overview of the system includes sending sensor data to the IoT Broker with the message queuing telemetry transport (MQTT) protocol and automatically storing data in the database. The results of the comparison value on each temperature sensor with a temperature sensor at the midpoint with an error of less than 0.7°C. Then testing the fuzzy between the Neobots program and the simulation in MATLAB got an error rate of 0-28.27%. In addition, in less than 10 minutes, the system response can adjust the temperature conditions to a setpoint value of 34°C from 29°C, and the average error value is 0.35°C during 1 hour of the Fuzzy implementation on the incubator. Then transfer data from the incubator to the database in a room without noise and full noise to get results for lost data less than 16.41% and 42.14%, delay rates between 0-6 seconds and 0-7 seconds with testing for 1 hour at every 1 second.</div>

show abstract

“…Raspberry Pi and other single-board computers are low-cost development devices for testing and education [11]. Raspberry Pi operates on the Raspbian Operating System (OS) that is based on Debian (Linux) [12]. Operating on the Raspbian OS enables Raspberry Pi to have access to multiple packages and programs such as the Python programming language that is widely used in machine learning and deployment development.…”

Section: Raspberry Pi Fig3 Layout Of Raspberry Pimentioning

confidence: 99%

Development of web-based interface for dry-low emission gas turbine using raspberry Pi

2023

Sustainable Processes and Clean Energy Transition

View full text Add to dashboard Cite

Abstract. In recent years, Dry-Low Emission (DLE) mode has been popular in gas turbine applications which can reduce emission production while maintaining high performance by operating the combustion at a low firing temperature. However, this type of combustor is prone to experience trips due to lean blowout occurrences and combustion instability. Dynamic simulation is needed to investigate the system's behavior in mitigating the tripping problem. Therefore, this paper proposed a simulator of the DLE gas turbine using Raspberry Pi, which can be accessed through the local server. Rowen's model is modified to represent the DLE gas turbine system, and its physical model is developed using open-source software, namely Scilab/XCos. The model is then attached to a web-based interface developed using Python and HTML programming language. The deployment of the web-based interface enables the gas turbine model to be accessed remotely without caring about the device's location by connecting the mobile to the same Wi-Fi router. This simulator will help improve the technical know-how of DLE gas turbine operation and can be embedded in the plant control system as a predictive maintenance tool.

show abstract

A System for Controlling and Monitoring IoT Applications

Cited by 6 publications

References 6 publications

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

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

Neobots: an open-source platform for a low-cost neonatal incubator with internet of things approach

Development of web-based interface for dry-low emission gas turbine using raspberry Pi

Contact Info

Product

Resources

About