Zhexiang Zou

Electric linear or rotary actuators are the ultimate power-dense execution units in modern industrial and transportation systems, yet their dependability is directly governed by the health of the driving electric motor. To guarantee fail-safe operation of the electromechanical actuator chain, condition monitoring and fault diagnosis of the embedded motor have become indispensable. The motor fault diagnosis process can be comprehensively summarized into four key steps: signal acquisition, feature extraction, condition monitoring, and fault identification. Based on the data obtained by signal acquisition, machine learning methods can be effectively integrated into the latter three steps. Feature extraction techniques primarily revolve around autoencoders. In terms of condition monitoring technology, in-depth research has been conducted on image recognition, including the identification of two-dimensional and three-dimensional images. In terms of fault identification, various machine learning methods have been applied, such as convolutional neural networks, autoencoders, transfer learning, long short-term memory networks, and support vector machines. Finally, the potential application of the Large Language Model in motor fault diagnosis was explored.

In marine electric propulsion systems (MEPS) driven by variable-frequency drives, motor current signals often exhibit complex modulation components, ambiguous spectra, and severe noise interference, rendering it challenging to extract fault-related modulation components. To address this issue, we propose a zero-crossing tacholess order tracking method based on motor current signals. This method utilizes zero-crossing estimation of the instantaneous frequency to perform angular resampling of stator current signals and demodulates the envelope spectrum to extract fault characteristic spectra, enabling the diagnosis of mechanical faults in MEPS. Given the synchronization of the synchronous motor speed with the inverter fundamental frequency, this method estimates instantaneous frequencies in the time domain without requiring integration or time–frequency representation, which is simple and computationally efficient. Data validation on a small-scale marine electric propulsion test platform demonstrates that the proposed method exhibits good robustness under variable-speed conditions and effectively detects imbalance faults caused by propeller breakages and gear faults resulting from bevel gear tooth defects. Therefore, the proposed method can be applied to diagnose faults in downstream mechanical equipment driven by motors.

Gear failures are often linked to inadequate lubrication, inappropriate viscosity, and insufficient lubricant quantity, leading to significant gear damage. Insufficient lubrication alters the dynamic torque characteristics of gear systems, subtly changing motor current signal modulation. Industrial motors commonly employ closed-loop speed control systems, which inevitably introduce harmonic interference from electronic components and background noise. This interference results in a low signal-to-noise ratio, complicating the precise demodulation of minor current modulations and posing challenges to early fault diagnosis. This paper explores fundamental frequency fluctuations in motor currents under speed-sensorless vector control systems and their impact on current signal demodulation. It introduces a novel technique, Carrier-Reconstructed Modulation Signal Bispectrum (CR-MSB), which reconstructs the carrier to remove irrelevant components and utilizes phase alignment to reduce random noise, enabling precise extraction of nonlinear modulation features from current signals. To validate the proposed approach, a two-stage, helical industrial gearbox was tested under various operating conditions by altering the lubricant quantities and viscosities. The results revealed that under variable load conditions with subpar lubrication, the current sideband amplitudes exhibited the corresponding characteristics, allowing diagnosing the changes in lubrication condition. This verifies that CR-MSB based current signal analysis can be an effective tool for extracting monitoring information from motors with closed-loop control drives.

Maintaining exceptional product quality and boosting processing efficiency requires precise evaluation of various aspects of the turning process, including the cutting depth, feed rate, and size of the workpiece. This article presents a novel approach for observing the turning process state using modulation signal bispectrum (MSB) and motor current signals. A nonlinear model was established that clarifies the load torque oscillations during turning, which in turn affects the amplitude and phase modulation of the motor stator current. Random noise can be efficiently minimized using the MSB algorithm, allowing the extraction of the current-modulation characteristic sideband phase and amplitude from the collected current signal. This technique enables clear representation and enhanced monitoring of load torque changes throughout the turning process. The proposed method was validated via mathematical simulations and universal lathe tests, with the results indicating that the MSB phase and amplitude values effectively capture both dynamic and static torque alterations during the turning operation, making this approach a valuable tool for overseeing the turning process.