To suppress the disturbance caused by the parameter mismatch, this article proposes an adjustable model predictive control (AMPC) strategy for an interior permanent-magnet synchronous motor (IPMSM) drives. The key of the proposed method is that an improved model reference adaptive system (IMRAS) is applied to identify online parameters. The traditional proportional-integral (PI) controller in the adaptive law of IMRAS is replaced by a fuzzy logic controller, it can improve the identification accuracy and enhance the robustness of sudden variations in speed reference and load torque. Then, the identified parameters can be used in the AMPC to replace constant parameters. Compared with the traditional model predictive control, the AMPC strategy can effectively decrease motor system current distortion and torque ripple when parameter mismatch occurs. Moreover, the maximum torque per ampere control (MTPA) control strategy based on the formula solution is adopted. And the optimal MTPA operation points can be found automatically by online parameter identification to achieve the minimum amplitudes of the phase current. Finally, the validity and correctness of the proposed method are verified by experiments.

Artificial Intelligence (AI) is a key technological enabler for the transition of agricultural production and management from experience-driven to data-driven, continuously advancing modern agriculture toward smart agriculture. This evolution ultimately aims to achieve a precise agricultural production model characterized by low resource consumption, high safety, high quality, high yield, and stable, sustainable development. Although machine learning, deep learning, computer vision, Internet of Things, and other AI technologies have made significant progress in numerous agricultural production applications, most studies focus on singular agricultural scenarios or specific AI algorithm research, such as object detection, navigation, agricultural machinery maintenance, and food safety, resulting in relatively limited coverage. To comprehensively elucidate the applications of AI in agriculture and provide a valuable reference for practitioners and policymakers, this paper reviews relevant research by investigating the entire agricultural production process—including planting, management, and harvesting—covering application scenarios such as seed selection during the cultivation phase, pest and disease identification and intelligent management during the growth phase, and agricultural product grading during the harvest phase, as well as agricultural machinery and devices like fault diagnosis and predictive maintenance of agricultural equipment, agricultural robots, and the agricultural Internet of Things. It first analyzes the fundamental principles and potential advantages of typical AI technologies, followed by a systematic and in-depth review of the latest progress in applying these core technologies to smart agriculture. The challenges faced by existing technologies are also explored, such as the inherent limitations of AI models—including poor generalization capability, low interpretability, and insufficient real-time performance—as well as the complex agricultural operating environments that result in multi-source, heterogeneous, and low-quality, unevenly annotated data. Furthermore, future research directions are discussed, such as lightweight network models, transfer learning, embodied intelligent agricultural robots, multimodal perception technologies, and large language models for agriculture. The aim is to provide meaningful insights for both theoretical research and practical applications of AI technologies in agriculture.

Motor current signature analysis (MCSA) has been widely used for fault diagnosis of induction motors (IMs) because of its non-invasiveness and comparatively low cost. However, the spectral leakage of the fundamental supply frequency can obscure the fault characteristic component when IMs operating at no-load or low-load conditions. In this paper, a broken rotor bar (BRB) fault diagnosis approach based on the third-order energy operator (TOEO) demodulated current signals is presented. The TOEO approach performs effectively in reducing the negative impact of the fundamental supply frequency spectral leakage and enhancing the BRB fault features. Theoretical and experimental results show that the TOEO approach can excellently reveal the fault characteristic frequency, instead of the sideband frequencies. Besides, the results are compared with the Teager-Kaiser energy operator (TKEO). The capability of the presented approach has several advantages over the TKEO, especially when the IMs are fed by an inverter.

The parameter mismatch in model predictive control (MPC), especially in fault-tolerant control, will lead to degradation of output performance. This article presents a new robust predictive current control based on online d-q inductance identification for a five-phase permanent-magnet (PM) motor under open-circuit fault. First, the MPC of the five-phase motor under the fault-tolerant operation of A-phase open-circuit is built, and then, the parameter mismatch caused by the d-q-axis inductance and the stator resistance is analyzed and discussed. Afterward, the real-time d-q-axis inductance identified by a fault-tolerance model reference adaptive system is used to replace the original parameters in MPC. Moreover, the flux linkage parameter mismatch can be rejected by the incremental predictive model in the proposed method. Therefore, the proposed method can eliminate almost all parameter mismatches, thereby improving output performance and enhancing parameter robustness under open-circuit fault. Finally, the validity and effectiveness of the proposed method are verified by experiments.

This article proposes a multiscale convolutional residual neural network algorithm with attention mechanisms for early interturn short circuit (ITSC) fault diagnosis of five-phase permanent magnet synchronous motors (FPPMSMs). First, a multiscale convolutional neural network with channel attention is used to highlight the fault features. Second, a spatial attention residual module is developed to improve feature learning performance, which can alleviate the problem of disappearing gradients and further enhance the fault features in the feature map. Finally, a self-attention structure is adopted to reduce reliance on manually set parameters, capture the internal correlation of features, and improve the interpretability of the network model. Experiments on ITSC faults of FPPMSM are carried out. The experimental results and the comparison with the other four methods highlight the superiority of the proposed method.

Model predictive control (MPC) has been successfully extended into fault-tolerant operation for the five-phase permanent-magnet synchronous motor (PMSM) under an open-circuit fault. However, compared with the open-circuit fault, the influence of short-circuit fault is more serious. Therefore, this article proposes a new multivectors model predictive control (MV-MPC) with voltage error tracking for a five-phase PMSM under short-circuit faults, including single-phase short-circuit fault and interphase short-circuit fault. The key of this method is to directly add short-circuit compensatory currents to reference currents that benefited from the advantages of MPC. Due to the loss of the faulted phase, the shapes of ordinary sectors under faults become asymmetrical. Then, a multivectors selection method is presented by constructing the cost function with voltage error terms and determining optimal vectors based on the shortest distance principle and sine theorem. Compared with the existing methods, the total harmonic distortion of the current and torque ripple is reduced greatly under the proposed method. Finally, the effectiveness and superiority of the proposed method are validated by experiments.