To enhance sensor fault detection in bearingless permanent magnet synchronous motors, this paper proposes a multi-signal fusion fault diagnosis method that integrates the Gramian angular field (GAF) transformation, a parallel convolutional neural network (pCNN), and a bidirectional long short-term memory (BiLSTM) network. First, sensor data are transformed into two-dimensional (2D) images using the GAF method. These images are then processed by the pCNN to extract fault feature vectors. Finally, the BiLSTM network captures transient temporal features embedded in the fault characteristics, enabling accurate fault classification. Experimental results demonstrate that the proposed method not only ensures precise fault identification but also significantly outperforms other machine-learning-based fault diagnosis approaches in terms of classification performance, thereby confirming its feasibility and reliability.

The unique structure of bearingless motors requires extra displacement sensors to monitor rotor movement, unlike conventional synchronous motors. However, this requirement inevitably escalates the cost and size of the motor. To address these issues, this paper proposes a novel approach: a bearingless synchronous reluctance motor (BSRM) without displacement sensors, utilizing the whale optimization algorithm–Elman neural network (WOA-ENN). The paper firstly introduces the suspension mechanism and mathematical model of the BSRM, upon which a function containing rotor position information is constructed. Subsequently, a sensorless method based on Elman neural network (ENN) is proposed, optimized using the whale optimization algorithm (WOA). Finally, the feasibility and reliability of the proposed approach are validated through simulations and experiments.

Traditional shaft-sealed centrifugal pumps exhibit problems, such as liquid leakage and reduced efficiency, due to mechanical seal failures. To address the issue, the bearingless direct-drive centrifugal pump system (BDDCPS) has been designed with bearingless motor technology. This may cause a new issue of rotor eccentricity displacement, which can lead to a reduction in pump performance. Compared to a stable state, the changes in characteristics, such as flow rate, head, and pressure, during the transient start-up process are more severe, increasing the likelihood of system failure and requiring greater attention. In order to ensure safety and reliable operation during the transient start-up process, this paper investigates the working principle of the BDDCPS and analyzes transient start-up characteristics with three different start-up methods. The external characteristics, pressure field distribution, velocity field distribution, and hydraulic losses analysis of the pump are determined for comparative analysis. Finally, it is found that the linear acceleration start-up method is the most suitable and efficient for the BDDCPS.

Traditional centrifugal pumps have limitations such as bearing wear and mechanical seal failures resulting from high-speed operations, which lead to a notable reduction in system efficiency. To overcome these limitations, centrifugal pumps driven by bearingless motors are employed. However, the absence of shaft constraints in such setups causes the impeller rotor to experience offset and tilting, thereby affecting pump performance and potentially causing system malfunctions. Thus, the bearingless direct-drive centrifugal pump (BDDCP) characteristics under extreme operating conditions need to be quantitatively analyzed. This study obtained a suitable turbulence model through experiments and subsequently designed three extreme operating conditions: different flow rates, impeller offset positions, and impeller tilt angles. The velocity field, external characteristics, and radial water excitation force were comprehensively analyzed. The results showed that flow changes greatly impact the BDDCP performance, while tilt angle changes slightly impact the BDDCP performance. These results can serve as a reference for subsequent research on BDDCP under extreme operating conditions.

Rotor suspension characteristics of magnetically levitated centrifugal pump under passive control is investigated by numerical simulation. Numerical models of the studied system are built, including a bearingless permanent magnetic slice motor (BPMSM) and a centrifugal pump. The authenticity of the numerical model is validated by comparing both simulated radially restoring electromagnetic force and fluid-induced axial force with theoretical values. Then, the performance of passive control of the simulated BPMSM is revealed, including axial restoring electromagnetic force and restoring torque exerted on the deviated rotor. It is found that the axial force induced by water suction in the pump impeller is crucial to affect the passive levitation stability of the rotor. Different modification schemes are studied to reduce fluid-induced axial force on the pump impeller so as to alleviate the requirement on the axial restoring force of BPMSM. It is found that balance hole and back blades can significantly diminish the axial force while twisted impeller blades can slightly increase the axial force. Finally, an improved impeller with balance hole and back blades is proposed for the centrifugal pump. Then, the net axial force and titling torque exerted by fluid and gravity on the assembled impeller and rotor are predicted and the two values are loaded on the rotor of the numerical model of BPMSM. The simulation results demonstrate that the current design of BPMSM can provide with enough restoring axial force and torque when initial position of the rotor is located at both centre and extreme positions.