Engine gearbox fault diagnosis using machine learning approach

2018 ◽  
Vol 24 (3) ◽  
pp. 345-357 ◽  
Author(s):  
Kiran Vernekar ◽  
Hemantha Kumar ◽  
Gangadharan K.V.
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Fault Diagnosis ◽  
Decision Tree ◽  
Condition Monitoring ◽  
Experimental Result ◽  
Maintenance Cost ◽  
Learning Approach ◽  
Content Type ◽  
Machine Learning Approach

Purpose Bearings and gears are major components in any rotatory machines and, thus, gained interest for condition monitoring. The failure of such critical components may cause an increase in down time and maintenance cost. Condition monitoring using the machine learning approach is a conceivable solution for the problem raised during the operation of the machinery system. The paper aims to discuss these issues. Design/methodology/approach This paper aims engine gearbox fault diagnosis based on a decision tree and artificial neural network algorithm. Findings The experimental result (classification accuracy 85.55 percent) validates that the proposed approach is an effective method for engine gearbox fault diagnosis. Originality/value This paper attempts to diagnose the faults in engine gearbox based on the machine learning approach with the combination of statistical features of vibration signals, decision tree and multi-layer perceptron neural network techniques.

scholarly journals Application of FURIA for Finding the Faults in a Hydraulic Brake System Using a Vibration Analysis through a Machine Learning Approach

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
Alamelu Manghai T. M ◽  
Jegadeeshwaran R
Keyword(s):  
Machine Learning ◽  
Fault Diagnosis ◽  
Decision Tree ◽  
Continuous Monitoring ◽  
Selection Process ◽  
Brake System ◽  
Learning Approach ◽  
Vibration Signals ◽  
Hydraulic Brake ◽  
Machine Learning Approach

Vibration-based continuous monitoring system for fault diagnosis of automobile hydraulic brake system is presented in this study. This study uses a machine learning approach for the fault diagnosis study. A hydraulic brake system test rig was fabricated. The vibration signals were acquired from the brake system under different simulated fault conditions using a piezoelectric transducer. The histogram features were extracted from the acquired vibration signals. The feature selection process was carried out using a decision tree. The selected features were classified using fuzzy unordered rule induction algorithm ( FURIA ) and Repeated Incremental Pruning to Produce Error Reduction ( RIPPER ) algorithm. The classification results of both algorithms for fault diagnosis of a hydraulic brake system were presented. Compared to RIPPER and J48 decision tree, the FURIA performs better and produced 98.73 % as the classification accuracy.

scholarly journals Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Differential Equations ◽  
Numerical Experiments ◽  
Optimization Problem ◽  
Learning Approach ◽  
The Neural Network ◽  
Machine Learning Approach ◽  
Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

Machine learning approach for multi-perspective volcanic eruption recognition using thermal infrared images

2020 ◽  
Author(s):  
Claudia Corradino ◽  
Gaetana Ganci ◽  
Giuseppe Bilotta ◽  
Annalisa Cappello ◽  
Ciro Del Negro
Keyword(s):  
Machine Learning ◽  
Decision Tree ◽  
Real Time ◽  
Mount Etna ◽  
Learning Approach ◽  
Bag Of Words ◽  
Infrared Images ◽  
Machine Learning Approach ◽  
Thermal Infrared Images ◽  
Thermal Cameras

<p>Detect, locate and characterize eruptions in real-time is fundamental to monitor volcanic activity. Here we present an automatic system able to discover and identify the main types of eruptive activities by exploiting infrared images acquired by the thermal cameras installed around Mount Etna volcano. The system, which employs the machine learning approach, is based on a decision tree tool and a bag of words-based classifier. The decision tree provides information on the visibility level of the monitored area, while the bag of words-based classifiers detects the onset of the eruptive activity and recognize the eruption type among either explosion and/or lava flow or plume. Thus, applied to each image of all thermal cameras over Etna in real-time, the proposed system provides two outputs, namely the visibility level and the recognized activity status. By merging the outcomes coming from each thermal camera, the monitored phenomena can be fully described from different perspectives getting deeper information in real-time and in an automatic way.   </p>

Sign in / Sign up

Export Citation Format

Share Document