For certain combinations of cutter spinning speeds and cutting depths in milling operations, self-excited vibrations or chatter of the milling tool are generated. The chatter deteriorates the surface finish of the workpiece and reduces the useful working life of the tool. In the past, extensive work has been reported on chatter detections based on the tool deflection and sound generated during the milling process, which is costly due to the additional sensor and circuitry required. On the other hand, the manual intervention is necessary to interpret the result. In the present research, online chatter detection based on the current signal applied to the ball screw drive (of the CNC machine) has been proposed and evaluated. There is no additional sensor required. Dynamic equations of the process are improved to simulate vibration behaviors of the milling tool during chatter conditions. The sequence of applied control signals for a particular feed rate is decided based on known physical and control parameters of the ball screw drive. The sequence of the applied control signal to the ball screw drive for a particular feed rate can be easily calculated. Hence, costly experimental data are eliminated. Long short-term memory neural networks are trained to detect the chatter based on the simulated sequence of control currents. The trained networks are then used to detect chatter, which shows 98% of accuracy in experiments.

An adaptive hybrid controller is proposed for reducing the unbalanced vibration response of a flexible rotor/active magnetic bearing system. It is observed that conventional adaptive feedforward controller (AFFC) normally used in the active noise control is very sensitive in performance for changes in rotor spin frequencies. Although frequency updating is a part of its architecture, a small practical variation in the rotor spin frequency can reduce its effectiveness drastically. A smart combination of adaptive notch filter and Goertzel filter is proposed for the frequency estimation. During changes of the rotor spin frequency, fundamental harmonics of the flexible rotor are excited. By using hybrid controllers that combine feedback control and AFFC, the amplitude of these fundamental harmonics is reduced significantly. By applying the multi-harmonic hybrid control, the multiple harmonics generated due to coupling misalignment are compensated efficiently. Fourier transform of the control signal is further used to detect the presence of the coupling misalignment.

It is confirmed experimentally that in case of a rotor with crack, multiple harmonics are generated when the rotor revolves at a particular frequency. Only few modeling techniques successfully predict this particular behavior of the cracked rotor. It is observed in this research that modeling cracked rotors using conventional finite element methods cannot predict this particular behavior successfully. A nonlinear dynamic model of the flexible rotor with ball bearings is developed using discrete mass spring damper elements combined with an existing model of the crack to truly predict this confirmed experimental behavior. Certain crack detection techniques based on the steady-state response work well on this basic concept of the multiharmonics generation due to nonlinearities caused by cracks in the rotor. The presence of ball bearings, rotor-coupling misalignment, rotor-stator rub, and rotor bow can also cause significant nonlinearities in the overall system. These additional nonlinearities render these crack detection techniques to lose their effectiveness. Our work justifies through simulations that the Jeffcott rotors are the over simplified version of real-life rotor-bearing systems. Hence, these crack detection techniques cannot be efficiently applied for condition monitoring of real-life rotor-bearing systems. The proposed model also helps to understand that the presence of flexible bearing supports affects the dynamics of the system considerably and negatively affects the effectiveness of these crack detection techniques.