Design and Development of Techniques for Equipment Health Monitoring System

Machines in Industries are often subjected to enormous wear and tear, which if unnoticed, may lead to production delays and increased maintenance cost. Machines must be able to analyse and provide statistics about its health, so that preventive measures can be taken to avoid catastrophes in the industries. Thus, there is a need of automated fault detection and prediction of system’s condition. The concept of equipment health monitoring is a crucial step in the field of research and development in the manufacturing industries. This equipment makes it handy in situations where machines require continuous monitoring and is difficult for humans to provide such attention , especially in the case of unmanned vehicles. Prediction of the status of equipment by acquisition of data from industrial machinery is the critical step in building such a system. Health of machines can be estimated by the data collected by the sensors-temperature, accelerometer, etc integrated with an embedded computing system, like a Raspberry Pi. This IoT model consisting of embedded system with wireless connectivity collects real time data from the equipment/machinery used in industries. This data is used to analyse and predict the health of the equipment, examine the steady-state characteristics using Machine Learning technique, Hidden Markovian Model. The concept of the proposed IoT model is evaluated over a conveyor belt test rig under various conditions, like different loads placed on various locations of conveyor belt and the belt is made to run at different speeds and data is collected over all these conditions. Then, a data model is created using Hidden Markovian Model which is further used in predicting the state of the belt based on the sequential data, here it is the sensor data. Given a state of the belt, this model can predict whether the belt is in proper condition or not, and if human intervention is required. Thus, at any point of time, having this setup on the machinery which needs to be monitored can be used in predicting the faults and notifying the user in case of any faulty behaviour or malfunctioning of machines. This setup can be used for any machines which are subjected to any motion, vibration and thermal changes. This helps in creating a completely automated fault detection systems in the present Industries.

Download Full-text

Artificial vision system for object classification in real time using Raspberry Pi and a Web camera

Revista de Tecnologías de la Información y Comunicaciones ◽

10.35429/jitc.2021.13.5.20.25 ◽

2021 ◽

pp. 20-25

Author(s):

Tomás Serrano-Ramírez ◽

Ninfa del Carmen Lozano-Rincón ◽

Arturo Mandujano-Nava ◽

Yosafat Jetsemaní Sámano-Flores

Keyword(s):

Embedded System ◽

Real Time ◽

Vision System ◽

Low Cost ◽

Artificial Vision ◽

Maintenance Cost ◽

Raspberry Pi ◽

Smart Cameras ◽

Suggested Technique ◽

Web Camera

Computer vision systems are an essential part in industrial automation tasks such as: identification, selection, measurement, defect detection and quality control in parts and components. There are smart cameras used to perform tasks, however, their high acquisition and maintenance cost is restrictive. In this work, a novel low-cost artificial vision system is proposed for classifying objects in real time, using the Raspberry Pi 3B + embedded system, a Web camera and the Open CV artificial vision library. The suggested technique comprises the training of a supervised classification system of the Haar Cascade type, with image banks of the object to be recognized, subsequently generating a predictive model which is put to the test with real-time detection, as well as the calculation for the prediction error. This seeks to build a powerful vision system, affordable and also developed using free software.

Download Full-text

Prognostics and Health Monitoring of Electro-Hydraulic Systems

Volume 2: Mechatronics; Estimation and Identification; Uncertain Systems and Robustness; Path Planning and Motion Control; Tracking Control Systems; Multi-Agent and Networked Systems; Manufacturing; Intelligent Transportation and Vehicles; Sensors and Actuators; Diagnostics and Detection; Unmanned, Ground and Surface Robotics; Motion and Vibration Control Applications ◽

10.1115/dscc2017-5392 ◽

2017 ◽

Author(s):

Damoon Soudbakhsh ◽

Anuradha M. Annaswamy

Keyword(s):

Fault Detection ◽

Health Monitoring ◽

Industrial Applications ◽

Remaining Useful Life ◽

Maintenance Cost ◽

Hydraulic Systems ◽

Multiple Sources ◽

Redundant Actuators ◽

Component Failures ◽

Prognostics And Health Monitoring

Electro-Hydraulic Systems (EHS) are commonly used in many industrial applications. Prediction and timely fault detection of EHS can significantly reduce their maintenance cost, and eliminate the need for redundant actuators. Current practice to detect faults in the actuators can miss failures with combination of multiple sources. Missed faults can result in sudden, unforeseen failures. We propose a fault detection technique based on Multiple Regressor Adaptive Observers (MRAO). The results were evaluated using a two-stage servo-valve model. The proposed MRAO can be used for on-line fault detection. Therefore, we propose a health monitoring approach based on the trend of the identified parameters of the system. Using the history of identified parameters, normal tear and wear of the actuator can be distinguished from the component failures to more accurately estimate the remaining useful life of the actuator.

Download Full-text

Prediction of athlete movements using wearable sensors for sports person health monitoring application

Journal of Intelligent & Fuzzy Systems ◽

10.3233/jifs-219160 ◽

2021 ◽

pp. 1-12

Author(s):

Tian Gao ◽

Yantao Lou ◽

C.B. Sivaparthipan ◽

Mamoun Alazab

Keyword(s):

Neural Network ◽

Health Monitoring ◽

Learning Algorithm ◽

Wearable Sensors ◽

Data Gathering ◽

Sensor Data ◽

Wearable Sensor ◽

Time Data ◽

Deep Learning Algorithm ◽

Optical Motion

Improvement in the data gathering to track the practise environments of the sports performance. Among these, the Internet of Things (IoT) technology with smartphones is increasingly evolving to help people with their health problems. In the world of athletics, wearable devices can provide real-time data to track athletes’ heart rhythms and help athletic activities. The players’ pulse rates change at various positions as they play sport and track their heartbeat, allowing them to understand their fitness and improve a person’s health. Therefore, the study proposes a wearable sensor-based athletic movement prediction (WS-AMP) model. The model uses the deep learning algorithm to effectively classify motions usually extracted from the interactive motion panels and determine how feasible it is to perform wearable sensor data classification. On 523 athletes with nine athletic motions, data on optical motion capture have been obtained. The research performs the deep neural network model’s training and validation, incorporating the convolutional neural network. The experimental study performs the prediction analysis and comparison with existing machine learning models. The experimental above analysis of wearable sensor-based IoT health monitoring of Sport person movements prediction are Abnormal Conditions ratio is 86.65%, Spectrum analysis of heart rate ratio is 87.12%, the Error rate of body maintenance ratio is 83.51%, Mental acuity ratio is 87.10% and finally overall accuracy, and F1 score ratio is 93.80%.

Download Full-text

FPGA Based Embedded System Development for Rolling Bearings Fault Detection of Induction Motor

International Journal of Reconfigurable and Embedded Systems (IJRES) ◽

10.11591/ijres.v2.i3.pp127-134 ◽

2013 ◽

Vol 2 (3) ◽

pp. 127

Author(s):

Shashidhara SM ◽

Sangameswara P Raju

Keyword(s):

Fault Diagnosis ◽

Fault Detection ◽

Embedded System ◽

Induction Motor ◽

Fourier Transforms ◽

System Development ◽

Fault Analysis ◽

Maintenance Cost ◽

Bearing Fault ◽

Bearing Fault Diagnosis

Bearing fault diagnosis is crucial in condition monitoring of any rotating machine. Early fault detection in machines can save millions of dollars in maintenance cost. Different methods are used for fault analysis such as short time Fourier transforms (STFT), Wavelet analysis (WA), Model based analysis, cepstrum analysis etc. Recently, there have been outstanding technological developments related to digital systems, in both hardware and software. These innovations enable the development of new designing methodologies that aim to the ease the future modifications, upgrades and expansions of the system. This paper presents a study of rolling bearing fault diagnosis of induction motor based on reconfigurable logic. A case study using FPGA, its design, as well as its implementation and testing, are presented.

Download Full-text

The Industry Internet of Things (IIoT) as a Methodology for Autonomous Diagnostics in Aerospace Structural Health Monitoring

Aerospace ◽

10.3390/aerospace7050064 ◽

2020 ◽

Vol 7 (5) ◽

pp. 64

Author(s):

Sarah Malik ◽

Rakeen Rouf ◽

Krzysztof Mazur ◽

Antonios Kontsos

Keyword(s):

Structural Health Monitoring ◽

Internet Of Things ◽

Data Processing ◽

Real Time ◽

Health Monitoring ◽

Sensor Data ◽

Management Approach ◽

Time Data ◽

Data Quality Management ◽

Structural Health

Structural Health Monitoring (SHM), defined as the process that involves sensing, computing, and decision making to assess the integrity of infrastructure, has been plagued by data management challenges. The Industrial Internet of Things (IIoT), a subset of Internet of Things (IoT), provides a way to decisively address SHM’s big data problem and provide a framework for autonomous processing. The key focus of IIoT is operational efficiency and cost optimization. The purpose, therefore, of the IIoT approach in this investigation is to develop a framework that connects nondestructive evaluation sensor data with real-time processing algorithms on an IoT hardware/software system to provide diagnostic capabilities for efficient data processing related to SHM. Specifically, the proposed IIoT approach is comprised of three components: the Cloud, the Fog, and the Edge. The Cloud is used to store historical data as well as to perform demanding computations such as off-line machine learning. The Fog is the hardware that performs real-time diagnostics using information received both from sensing and the Cloud. The Edge is the bottom level hardware that records data at the sensor level. In this investigation, an application of this approach to evaluate the state of health of an aerospace grade composite material at laboratory conditions is presented. The key link that limits human intervention in data processing is the implemented database management approach which is the particular focus of this manuscript. Specifically, a NoSQL database is implemented to provide live data transfer from the Edge to both the Fog and Cloud. Through this database, the algorithms used are capable to execute filtering by classification at the Fog level, as live data is recorded. The processed data is automatically sent to the Cloud for further operations such as visualization. The system integration with three layers provides an opportunity to create a paradigm for intelligent real-time data quality management.

Download Full-text

Efficient Big Data-Based Storage and Processing Model in Internet of Things for Improving Accuracy Fault Detection in Industrial Processes

Security and Privacy Issues in Sensor Networks and IoT - Advances in Information Security, Privacy, and Ethics ◽

10.4018/978-1-7998-0373-7.ch009 ◽

2020 ◽

pp. 215-230 ◽

Cited By ~ 3

Author(s):

Mamoon Rashid ◽

Harjeet Singh ◽

Vishal Goyal ◽

Nazir Ahmad ◽

Neeraj Mogla

Keyword(s):

Big Data ◽

Internet Of Things ◽

Fault Detection ◽

Real Time ◽

Sensor Data ◽

Industrial Processes ◽

Time Data ◽

Real Time Data ◽

Hadoop Distributed File System ◽

Improving Accuracy

As the lot of data is getting generated and captured in Internet of Things (IoT)—based industrial devices which is real time and unstructured in nature. The IoT technology—based sensors are the effective solution for monitoring these industrial processes in an efficient way. However, the real—time data storage and its processing in IoT applications is still a big challenge. This chapter proposes a new big data pipeline solution for storing and processing IoT sensor data. The proposed big data processing platform uses Apache Flume for efficiently collecting and transferring large amounts of IoT data from Cloud—based server into Hadoop Distributed File System for storage of IoT—based sensor data. Apache Storm is to be used for processing this real—time data. Next, the authors propose the use of hybrid prediction model of Density-based spatial clustering of applications with noise (DBSCAN) to remove sensor data outliers and provide better accuracy fault detection in IoT Industrial processes by using Support Vector Machine (SVM) machine learning classification technique.

Download Full-text

Health Monitoring System using Raspberry Pi and IOT

Oriental journal of computer science and technology ◽

10.13005/ojcst12.01.03 ◽

2019 ◽

Vol 12 (1) ◽

pp. 08-13 ◽

Cited By ~ 2

Author(s):

E. N. GANESH

Keyword(s):

Monitoring System ◽

Health Monitoring ◽

Medical Information ◽

Patient Data ◽

Sensor Data ◽

Raspberry Pi ◽

The Internet ◽

Health Monitoring System ◽

The World ◽

Patient Health

Health Monitoring system using IOT describes the collection and interoperation of Patient data collected from the sensors from the hospitals through IOT Technology. The collected sensor data will support the doctor in the emergency situation for the betterment and improvement of Patient health. The hardware platform to implement the project consists of a sensor and Raspberry Pi 3 Model B equipped in a way to communicate with a doctor through the Internet and Smart Phone. This proposed idea will help doctors to know about the state of patient health and monitor anywhere in the world. In this proposed idea the sensors gather the medical information of the patient that includes patient’s heart rate, blood pressure, and pulse rate Then using the camera the patient is livelily monitored through the Raspberry kit and this information is sent to the Internet and stored in a medical server. The doctor and patient can monitor the patient data from any place of the world through the provided IP server address anytime. The emergency alert is sent to the patient if the sensor value is exceeded by the threshold data. Thus the patient's health parameters are watched lively and regular monitoring through the medical server to a doctor will help to make an effective diagnosis and almost accurate care can be given. The data collected through the IOT will help the patient to recover easily and also enhanced medical care can be given to the patients at a low cost.

Download Full-text