Tool Wear State Recognition with Deep Transfer Learning Based on Spindle Vibration for Milling Process

The wear of metal cutting tools will progressively rise as the cutting time goes on. Wearing heavily on the toolwill generate significant noise and vibration, negatively impacting the accuracy of the forming and the surfaceintegrity of the workpiece. Hence, during the cutting process, it is imperative to continually monitor the tool wearstate andpromptly replace anyheavilyworn tools toguarantee thequality of the cutting.The conventional tool wearmonitoring models, which are based on machine learning, are specifically built for the intended cutting conditions.However, these models require retraining when the cutting conditions undergo any changes. This method has noapplication value if the cutting conditions frequently change. This manuscript proposes a method for monitoringtool wear basedonunsuperviseddeep transfer learning. Due to the similarity of the tool wear process under varyingworking conditions, a tool wear recognitionmodel that can adapt to both current and previous working conditionshas been developed by utilizing cutting monitoring data from history. To extract and classify cutting vibrationsignals, the unsupervised deep transfer learning network comprises a one-dimensional (1D) convolutional neuralnetwork (CNN) with a multi-layer perceptron (MLP). To achieve distribution alignment of deep features throughthe maximum mean discrepancy algorithm, a domain adaptive layer is embedded in the penultimate layer of thenetwork. A platformformonitoring tool wear during endmilling has been constructed. The proposedmethod wasverified through the execution of a full life test of end milling under multiple working conditions with a Cr12MoVsteel workpiece. Our experiments demonstrate that the transfer learning model maintains a classification accuracyof over 80%. In comparisonwith the most advanced tool wearmonitoring methods, the presentedmodel guaranteessuperior performance in the target domains.

Sparsity-Enhanced Model-Based Method for Intelligent Fault Detection of Mechanical Transmission Chain in Electrical Vehicle

In today’s world,smart electric vehicles are deeply integrated with smart energy,smart transportation and smart cities.In electric vehicles(EVs),owing to the harsh working conditions,mechanical parts are prone to fatigue damages,which endanger the driving safety of EVs.The practice has proved that the identification of periodic impact characteristics(PICs)can effectively indicate mechanical faults.This paper proposes a novel model-based approach for intelligent fault diagnosis ofmechanical transmission train in EVs.The essential idea of this approach lies in the fusion of statistical information and model information froma dynamic process.In the algorithm,a novel fractal wavelet decomposition(FWD)is used to investigate the time-frequency representation of the input signal.Based on the sparsity of the PIC model in the Hilbert envelope spectrum,amethod for evaluating PIC energy ratio(PICER)is defined based on an over-complete Fourier dictionary.A compound indicator considering kurtosis and PICER of dynamic signal is designed.Using this index,evaluations of the impulsiveness of the cycle-stationary process can be enabled,thus avoiding serious interference from the sporadic impact during measurements.The robustness of the proposed approach to noise is demonstrated via numerical simulations,and an engineering application is employed to validate its effectiveness.