Search

Effective condition monitoring of motors is crucial in diverse electric powertrain systems, including applications in electric transportation and nuclear power plants. Vibration analysis, a key component of motor condition testing, aids in identifying equipment failures, assessing operational status, and guiding preventive maintenance. However, achieving high evaluation accuracy while minimizing the number of vibration sensors to reduce operational and maintenance costs poses a significant challenge. This article introduces a novel approach for vibration testing using a spatial–spectral-based inductive graph neural network. The proposed algorithm focuses on mining vibration sensor-based clusters to reveal spatial connectivity and spectral correlation patterns. It efficiently aggregates and extracts features from sensor graph signals near the target location, subsequently reconstructing vibration signals using convolutional networks to create a virtual sensor. To validate the effectiveness of the proposed method, experimental verification was conducted on a 21 kW interior permanent magnet synchronous motor testing rig equipped with Brüel and Kjær's vibration sensing equipment. The results demonstrate the algorithm's ability to enhance evaluation accuracy and reliability. This innovative approach not only contributes to the field of motor condition monitoring but also addresses the challenge of minimizing the number of vibration sensors, thereby reducing manual operation and maintenance costs associated with sensor networks.

The main challenges in designing the power reserve control (PRC) lie in the rapid estimation of the maximum available power ($P_\mathrm{avi}$) in real time and effective drift avoidance under the condition of fast-changing irradiation. Conventional PRC strategies utilize direct measurement or curve-fitting-based estimation to determine the $P_\mathrm{avi}$, which shows obvious limitations, such as extra hardware, implementation complexity, and slow estimation speed. Meanwhile, the drifted reserved power ($\Delta P$) may deteriorate the dynamic response performance, bring high dc-link overvoltage risk, and affect the system operation stability due to the voltage-step-$\Delta P$ regulation mechanism in conventional PRC methods. To address these issues, an improved PRC strategy with a fast $\Delta P$ transient mechanism is proposed with the rapid estimation of $P_\mathrm{avi}$ through just one pair of photovoltaic (PV) voltage and current sampling. Thus, the proposed algorithm is cost-effective, easy to implement, and compatible with existing PV systems since no additional hardware components are required. Moreover, the proposed PRC breaks through the inherent limitation of the voltage-step-$\Delta P$ mechanism, which can ensure the $\Delta P$ drift mitigation even under fast-changing weather conditions. Main experimental comparisons with other advanced PRC strategies were conducted to verify the advantages of the proposed algorithm in terms of rapid real-time available power estimation and drift avoidance.