Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Gearbox fault diagnosis based on Multi-Scale deep residual learning and stacked LSTM model(Elsevier B.V., 2021) Ravikumar, K.N.; Yadav, A.; Kumar, H.; Gangadharan, K.V.; Narasimhadhan, A.V.Fault diagnosis methods based on signal analysis techniques are widely used to diagnose faults in gear and bearing. This paper introduces a fault diagnosis model that includes a multi-scale deep residual learning with a stacked long short-term memory (MDRL-SLSTM) to address sequence data in a gearbox health prediction task in an internal combustion (IC) engine. In the MDRL-SLSTM network, CNN and residual learning is firstly utilized for local feature extraction and dimension reduction. The experiment is carried out on the gearbox of an IC engine setup, two datasets are used; one is from bearing and the other from 2nd driving gear of gearbox. To reduce the number of parameters, down-sampling is carried out on input data before giving to the architecture. The model achieved better diagnostic performance with vibration data of gearbox. Classification accuracy of 94.08% and 94.33% are attained on bearing datasets and 2nd driving gear of gearbox respectively. © 2021 Elsevier LtdItem Classification of gear faults in internal combustion (IC) engine gearbox using discrete wavelet transform features and K star algorithm(Elsevier B.V., 2022) Ravikumar, K.N.; Madhusudana, C.K.; Kumar, H.; Gangadharan, K.V.Vibration-based fault diagnosis is one of the widely used techniques for condition monitoring of the machines equipped with a gearbox. Severe operating conditions of gearbox result in gear tooth failure. To develop an effective fault diagnosis technique for the mechanical system, a machine learning approach is highly necessary and plays a vital role in the area of condition monitoring. This paper presents the vibration-based fault diagnosis of IC engine gearbox operating under actual running condition. An Eddy current dynamometer is used to apply the external load on the output shaft of the engine. Driving gear with healthy condition and progressive tooth defect conditions are considered for the analysis. The vibration signals of engine gearbox under various gear tooth conditions are measured. Discrete wavelet transform features are extracted from the vibration signals and more contributing features for classification are selected using decision tree algorithm. The Lazy based classifiers viz, k-nearest neighbour algorithm, K-star algorithm and locally weighted learning algorithm are used for classification. A comparative study of these classifiers is made using percentage of classification accuracy. The maximum classification accuracy of about 97.5% is achieved by the K-star algorithm. Based on the experimental results, K-star algorithm and discrete wavelet transform technique can be used for diagnosing the gear faults in IC engine gearbox using vibration signals. © 2021 Karabuk UniversityItem Fault diagnosis of antifriction bearing in internal combustion engine gearbox using data mining techniques(Springer, 2022) Ravikumar, K.N.; Aralikatti, S.S.; Kumar, H.; Kumar, G.N.; Gangadharan, K.V.Ball bearing failure are most common failure in rotating machinery, which can be catastrophic. Hence obtaining early failure warning along with precise fault detection technique is at most important. Early detection and timely intervention are the key in condition monitoring for long term endurance of machine components. The early research has used signal processing and spectral analysis extensively for fault detection however data mining with machine learning is most effective in fault diagnosis, the same is presented in this paper. The vibration signals are acquired for an output shaft antifriction bearing in a two-wheeler gearbox operated at various loading conditions with healthy and fault conditions. Data mining is employed for these acquired signals. Statistical, discrete wavelet and empirical mode decomposition are employed for feature extraction process and J48 decision tree for feature selection. Classification is carried out using K*, Random forest and support vector machine algorithm. The classifiers are trained and tested using tenfold cross validation method to diagnose the bearing fault. A comparative study of feature extraction and classifiers are done to evaluate the classification accuracy. The results obtained from K* classifier with wavelet feature yielded better accuracy than rest other classifiers with classification accuracy 92.5% for bearing fault diagnosis. © 2021, The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden.