Tool condition monitoring (TCM) is crucial in the machining process to confirm product quality as well as process efficiency and minimize downtime. Traditional methods for TCM, while effective to a degree, often fall short in real-time adaptability and predictive accuracy. This research work aims to advance the state-of-the-art methods in predictive maintenance for TCM and improve tool performance and reliability during the milling process. The present work investigates the application of Deep Learning (DL) and Reinforcement Learning (RL) techniques to monitor tool conditions in milling operations. DL models, including Long Short-Term Memory (LSTM) networks, Feed Forward Neural Networks (FFNN), and RL models, including Q-learning and SARSA, are employed to classify tool conditions from the vibration sensor. The performance of the selected DL and RL algorithms is evaluated through performance metrics like confusion matrix, recall, precision, F1 score, and Receiver Operating Characteristics (ROC) curves. The results revealed that RL based on SARSA outperformed other algorithms. The overall classification accuracies for LSTM, FFNN, Q-learning, and SARSA were 94.85%, 98.16%, 98.50%, and 98.66%, respectively. In regard to predicting tool conditions accurately and thereby enhancing overall process efficiency, SARSA showed the best performance, followed by Q-learning, FFNN, and LSTM. This work contributes to the advancement of TCM systems, highlighting the potential of DL and RL techniques to revolutionize manufacturing processes in the era of Industry 5.0.

This paper deals with finding the optimum parameters of a damped dynamic vibration absorber (DVA) to control chatter in metal cutting systems. The performance of conventional damped DVA is compared with the proposed skyhook damper in which the damper of the absorber system is connected between the absorber mass and an inertial reference in the sky, referred to as a skyhook damper. The damped DVA is optimized by reducing the magnitude in the positive side and increasing it in the negative side of the real part of the frequency response function of the main system. The optimum frequency ratio and the damping ratio of the damped DVA for the undamped and damped main system are obtained using analytical solutions and a numerical optimisation technique, viz genetic algorithm, respectively. The performance of the proposed skyhook damper is marginally better than the conventional type of damped DVA in controlling the vibration of the main system. This is verified by analyzing both the proposed and conventional models using finite element method-based commercial software ANSYS.

Linear spring mass systems placed on a moving belt have been subjected to numerous investigations. Dynamical characteristics like amplitude and frequency of oscillations and bifurcations have been well studied along with different control mechanisms for this model. But the corresponding nonlinear system has not received comparable attention. This paper presents an analytical investigation of the behavior of a Duffing oscillator placed on a belt moving with constant velocity and excited by dry friction. A negative gradient friction model is considered to account for the initial decrease and the subsequent increase in the frictional forces with increasing relative velocity. Approximate analytical expressions are obtained for the amplitudes and base frequencies of friction-induced stick–slip and pure-slip phases of oscillations. For the pure-slip phase, an expression for the equilibrium point is obtained, and averaging procedure is used to arrive at approximate analytical expressions of the periodic amplitude of oscillations around this fixed-point. For stick–slip oscillations, analytical expressions for amplitude are arrived at by using perturbation analysis for the finite time interval of the stick phase, which is linked to the subsequent slip phase through conditions of continuity and periodicity. These analytical results are validated by numerical studies and are shown to be in good agreement with them. It is shown that the pure-slip oscillation phase and the critical velocity of the belt remain unaffected by the nonlinear term. It is also shown that the amplitude of the stick–slip phase varies inversely with nonlinearity. The effect of different system parameters on the vibration amplitude is also studied.

In this paper, an experimental and numerical investigation of thermoelectric generator for energy harvesting performance of screw compressors has been studied. The sources of heat recovery from compressors are recognized and a heat exchanger to mount the Thermoelectric Generator (TEG) module assembly is designed to adapt for implementation in this work. Computational fluid dynamics (CFD) is used to find out the temperature distribution in the heat exchanger and experimental work is carried out to validate CFD results. The heat exchangers, consisting of five TEG modules, temperature profile and voltage value have been studied numerically and experimentally. The parametric study has been studied to understand the influence of various system parameters on energy harvesting performance TEG based heat exchanger. An average of 1.6 V is generated by each TEG module and heat exchanger consists of five TEG and an average of 8 V is generated continuously by the heat exchanger. Also, it is proved that the usages of steel foam with 90 % porosity in heat exchanger improves the heat transfer rate and maximize the output from 8 V to 24 V in heat exchanger.