International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 12 | Dec 2024
p-ISSN: 2395-0072
www.irjet.net
Machine Learning-Based Anomaly Detection in Industrial Machine Using IoT Data Penjarla Jyothi Prasanna1, Kavali Deepthi Priya2, Pothu Aravind3, Dr. D. Sreenivasulu4 1B-Tech 4th year, Dept. of CSE(DS), Institute of Aeronautical Engineering
2 B-Tech 4th year, Dept. of CSE(DS), Institute of Aeronautical Engineering 3 B-Tech 4th year, Dept. of CSE(DS), Institute of Aeronautical Engineering
4Associate Professor, Dept. of CSE(DS), Institute of Aeronautical Engineering, Telangana, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Minimizing downtime and maximizing
may transition to a proactive maintenance paradigm that is data-driven, identifying anomalies in machine behavior early on to avert breakdowns. The difficulty, though, is in reliably identifying trends that point to possible breakdowns by processing and analyzing the massive amounts of IoT data. Techniques for machine learning have become effective tools for managing this complexity. By training models using previous sensor data, it is possible to automatically detect anomalous patterns, or anomalies, that presage equipment problems. This study looks into the use of different machine learning algorithms to identify abnormalities in industrial machinery, including Support Vector Machines (SVM), Random Forests (RF), Logistic Regression (LR), Decision Trees (DT), and Convolutional Neural Networks (CNN). By lowering the likelihood of unanticipated breakdowns and improving predictive maintenance capabilities, these models optimize machine reliability while minimizing operating expenses.
maintenance operations in industrial machinery depend on anomaly detection. This study investigates the application of machine learning methods to detect anomalies in sensor data generated by industrial machinery connected to the Internet of Things. Several models were utilized, such as Support Vector Machines, Random Forests, Decision Trees, Logistic Regression, and Convolutional Neural Networks, to identify anomalous patterns that may indicate malfunctions in the equipment. This method minimizes the possibility of unplanned machine faults and improves operating efficiency by enabling proactive maintenance through the use of realtime sensor data. Increasing the reliability of industrial machinery can be accomplished in a scalable and efficient way by combining machine learning with Internet of Things data.
Key Words: Sensor
data, Convolutional Neural Networks, Support Vector Machines, Logistic Regression, Decision Trees, Random Forests, Industrial machinery, IoT, Machine learning, Predictive maintenance, anomaly detection, and maintenance optimization.
2. LITERATURE SURVEY 2.1 An Overview on Anomaly Detection in Industrial Machinery
1.INTRODUCTION In modern industrial settings, the seamless operation of machinery is paramount to ensuring efficiency, productivity, and safety. However, the occurrence of anomalies or unexpected faults within industrial machinery can disrupt operations, leading to costly downtime, maintenance expenses, and potential safety hazards. Exploiting the potential of machine learning (ML) algorithms and Internet of Things (IoT) technologies for anomaly detection is becoming more popular as a means of reducing risks and improving the efficiency of industrial machines.
Industrial machine anomaly detection, which uses real-time sensor data to find unusual patterns that point to possible machine problems, has emerged as a crucial component of predictive maintenance. Outliers were formerly identified using threshold-based techniques, but as machine learning and the Internet of Things have advanced quickly, more complex algorithms have been devised to improve the scalability and accuracy of detection systems.
The emergence of the Internet of Things (IoT) has brought about a significant transformation in the industrial sector by allowing machines to be equipped with sensors that produce copious volumes of real-time data. More opportunities for increasing operational efficiency have been created by this flood of sensor data, especially in the field of predictive maintenance. Conventional maintenance approaches, which depend on planned or reactive methods, frequently result in unplanned equipment breakdowns or unnecessary downtime. Through the utilization of IoT data, enterprises
Traditional Methods: Early approaches to anomaly detection focused on statistical models, such as Shewhart control charts and threshold-based monitoring, to detect deviations from predefined norms. These methods, as discussed by Montgomery (2007), were widely used for quality control but were limited in detecting complex anomalies in multidimensional data.
© 2024, IRJET
|
Impact Factor value: 8.315
Key findings:
Machine Learning Integration: The importance of machine learning algorithms in anomaly identification has been
|
ISO 9001:2008 Certified Journal
|
Page 720