Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
6 results
Search Results
Item Fault diagnosis of single point cutting tool using spectrum, cepstrum and wavelet analysis(American Institute of Physics Inc. subs@aip.org, 2019) Aralikatti, S.S.; Ravikumar, K.N.; Kumar, H.Tool fault diagnosis is essential in modern machining process to commemorate automation and precise manufacturing with limited human intervention. Automation increases productivity and efficient job handling ability. Online tool condition monitoring enables the fault diagnosis of cutting tool. A sensor is employed to acquire the information of the tool condition. The sensor data will be in raw form, which need to be processed using signal processing technique to derive the useful information about the tool fault. In the present work, a single point cutting tool of carbide tip used to machine oil hardened nickel steel. Various tool conditions are considered namely healthy, extended overhang, worn flank and broken tool. Vibration signals corresponding to each tool conditions are acquired using accelerometer to monitor tool condition. The time domain signals are transformed to frequency domain by employing fast Fourier transform (FFT). Other signal processing techniques such as cepstrum analysis and wavelet analysis used to understand the ailment of tool. The study also addresses limitations of signal processing tools and the advantage of one over the other. © 2019 Author(s).Item Fault diagnosis of single-point cutting tool using vibration signal by rotation forest algorithm(Springer Nature, 2019) Aralikatti, S.S.; Ravikumar, K.N.; Kumar, H.In various machining operations, the tool condition monitoring (TCM) is highly necessary to avoid uncertain downtime in production. TCM provides continuously the condition of cutting tool by noticing various parameters such as temperature, acoustic emission and vibration. One of the best ways to monitor the condition of cutting tools for unmanned machining is by observing tool vibration signature. In the present work, vibration signals are acquired from the cutting tool. One healthy state and three faulty conditions of tools are considered for the study. The faulty tools considered in the current study are worn flank, broken tool and extended overhang. The vibration signals of these faulty tool conditions are used to train the machine learning algorithm. Statistical features are extracted from the vibration signal to feed as input to the J48 decision tree. The classifier algorithm used in the current study is rotation forest algorithm. The algorithm uses only significant features which are selected from a decision tree. The algorithm is validated with test dataset to recognize the faulty or healthy state of the tool. It was found that the algorithm could classify the tool condition with 95.00% classification accuracy. © 2019, Springer Nature Switzerland AG.Item Comparative study on tool fault diagnosis methods using vibration signals and cutting force signals by machine learning technique(Tech Science Press sale@techscience.com, 2020) Aralikatti, S.S.; Ravikumar, K.N.; Kumar, H.; Shivananda Nayaka, H.; Sugumaran, V.The state of cutting tool determines the quality of surface produced on the machined parts. A faulty tool produces poor surface, inaccurate geometry and non-economic production. Thus, it is necessary to monitor tool condition for a machining process to have superior quality and economic production. In the present study, fault classification of single point cutting tool for hard turning has been carried out by employing machine learning technique. Cutting force and vibration signals were acquired to monitor tool condition during machining. A set of four tooling conditions namely healthy, worn flank, broken insert and extended tool overhang have been considered for the study. The machine learning technique was applied to both vibration and cutting force signals. Discrete wavelet features of the signals have been extracted using discrete wavelet transformation (DWT). This transformation represents a large dataset into approximation coefficients which contain the most useful information of the dataset. Significant features, among features extracted, were selected using J48 decision tree technique. Classification of tool conditions was carried out using Naïve Bayes algorithm. A 10 fold cross validation was incorporated to test the validity of classifier. A comparison of performance of classifier was made between cutting force and vibration signal to choose the best signal acquisition method in classifying tool fault conditions using machine learning technique. © 2020 Tech Science Press. All rights reserved.Item 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.Item Tool vibration isolation in hard turning process with magnetorheological fluid damper(Elsevier Ltd, 2023) Aralikatti, S.S.; Kumar, H.Tool vibration in metal cutting significantly influences the surface finish and machining stability. Suppressing the tool vibration to enhance the finished product quality is the need of the hour. The current study proposes the augmentation of a Magnetorheological (MR) fluid damper to suppress tool vibration in hard tuning with easy installation without structural modification. The MR fluid damper changes its damping coefficient with the magnetic field to regulate variable cutting conditions. An optimal composition of MR fluid has been prepared in-house to be used in the damper. The in-house MR fluid is compared with commercial MR fluid. The comparison shows that in-house prepared MR fluid performs equally well compared to commercial fluid. The MR damper effectively damps high-amplitude vibration at aggressive cutting conditions. The L9 Taguchi design of the experiment opted to arrive at minimal machining parameters to evaluate the damper's performance in machining two workpiece materials, namely oil-hardened nickel steel (OHNS) and high carbon high chromium (HCHCR D2) die steel. The surface roughness and tool vibration are reduced with the damper. It is noted that in-house MR fluid performed equally well as commercial MR fluid. The tool wear study is also carried out to monitor the influence of external damping over tool life. The stability lobe diagram is obtained analytically with experimental validation to mark the stability limit of the machining condition. The stability boundary increases with the damper enabling aggressive cutting conditions. © 2023 The Society of Manufacturing EngineersItem Determining the optimal composition of magnetorheological fluid for a short-stroke magnetorheological damper(Springer, 2023) Aralikatti, S.S.; Puneet, N.P.; Kumar, H.The current study investigates the effect of viscosity of base oil and weight fraction of carbonyl iron particles on maximum yield stress and effective damping range of a short-stroke magnetorheological damper (stroke length of 2 mm) designed for tool vibration mitigation. It is difficult to find the exact composition of magnetorheological fluid (MRF) based on the design equations, as unidentified practical parameters influence their behaviour hence, optimization by experimental techniques is necessary. Optimal composition of MRF are identified by genetic algorithm through central composite design of experiment. A validation study is conducted to cross verify the optimum values delivered by the algorithm. The damper is fitted onto lathe machine with the optimal fluid composition to evaluate its performance in controlling the tool vibration. The damper has been designed for the specific speed, feed and depth of cut however, the design procedure for developing a damper for higher/other cutting conditions can be achieved by the design scheme mentioned in this article. The vibration level of tool reduced by 28.66% and the amplitude of cutting force reduced by 68.18% indicating reduction of chatter vibration with the damper. An improved surface finish has been observed from 4.8 to 1.6 μm. © 2023, Indian Academy of Sciences.