Many compartments are prone to pose safety hazards such as loose fasteners or object intrusion due to their confined space, making manual inspection challenging. To address the challenges of complex inspection environments, diverse target categories, and variable scales in confined compartments, this paper proposes a novel GMS-YOLO network, based on the improved YOLOv8 framework. In addition to the lightweight design, this network accurately detects targets by leveraging more precise high-level and low-level feature representations obtained from GhostHGNetv2, which enhances feature-extraction capabilities. To handle the issue of complex environments, the backbone employs GhostHGNetv2 to capture more accurate high-level and low-level feature representations, facilitating better distinction between background and targets. In addition, this network significantly reduces both network parameter size and computational complexity. To address the issue of varying target scales, the first layer of the feature fusion module introduces Multi-Scale Convolutional Attention (MSCA) to capture multi-scale contextual information and guide the feature fusion process. A new lightweight detection head, Shared Convolutional Detection Head (SCDH), is designed to enable the model to achieve higher accuracy while being lighter. To evaluate the performance of this algorithm, a dataset for object detection in this scenario was constructed. The experiment results indicate that compared to the original model, the parameter number of the improved model decreased by 37.8%, the GFLOPs decreased by 27.7%, and the average accuracy increased from 82.7% to 85.0%. This validates the accuracy and applicability of the proposed GMS-YOLO network.

Parallel interleaved multilevel inverters (PIMIs) hold substantial potential for high-power applications, but their inherent circulating current issue leads to increased current stress and reduced system efficiency. This article focuses on phase circulating current (PCC) suppression in PIMIs. First, a PCC prediction model is proposed, considering a one-control-cycle delay when applying the asymmetric regular sampling (ARS) rule. By employing this model, appropriate redundant vectors are selected to achieve an approximately 50% reduction in PCC. Then, another PCC prediction model is developed, incorporating a two-control-cycles delay. Utilizing this model, an ARS-based variable switching frequency pulsewidth modulation (VSFPWM) is proposed to precisely control the peak value of PCC, and a method for determining the boundary of the switching frequency is suggested. The proposed VSFPWM explores the capability of the pulsewidth modulation (PWM) algorithm to effectively control PCC under low-switching frequency and low-carrier ratio conditions by using two degrees of freedom: vector selection and switching frequency. Finally, the effectiveness of the proposed strategy is validated by experiment with a 36-MVA inverter.

Finite Control Set Model Predictive Control (FCS-MPC) has the ability to achieve multi-objective optimization, but there are still many challenges. The key to realizing multi-objective optimization in FCS-MPC lies in the design of the cost function. However, the different dimensions of penalty terms in the cost function often lead to difficulties in designing weighting coefficients. Incorrect weighting coefficients may result in truncation errors in calculations of DSPs and FPGAs, thereby affecting the algorithm’s control performance. Therefore, this article focuses on a system driving an induction motor with a three-level Neutral Point Clamped (NPC) inverter, and selects stator current and switching frequency as penalty terms in the cost function. An improved method is proposed to unify the dimensions of both penalty terms in the cost function. By unifying the dimensions of the penalty terms, a simple design of weighting coefficients can be achieved. Subsequently, to balance the inverter’s switching frequency and the dynamic response performance of the motor, a composite cost function is further proposed. Finally, the rationality of the proposed method is validated through simulation and experimental platforms.

The lithium battery energy storage system (LBESS) can provide short-term high power and long-term high energy for electromagnetic launch system through high-rate discharge. However, the high-rate discharge LBESS has the problems of output voltage drop and current low-frequency fluctuation in the high-voltage and high-power launch process. This article introduces an energy storage system topology with N+1-level dynamic chopping converter, which can realize dynamic compensation of output voltage. To promote the rapidity of output voltage compensation, an improved active disturbance rejection control method by designing the variable gain (VG) control law with initial small gain is proposed to suppress the initial peak of total disturbance observation, thus improving the response speed of VG-ADRC controller. In order to decrease the dc current fluctuation, a nonlinear extended state observer with a muti-cascade notch filter is designed to attenuate the low-frequency components in total disturbance observation, the reference current is adjusted in real-time, thereby greatly suppressing the fluctuation amplitude of output current. Moreover, the frequency analysis shows that the proposed method does not introduce the negative phase into the loop transfer function and affect the stability of the original system. Finally, a 10 MW peak power pulsed discharge experimental platform was built to verify the effectiveness and practicability of the proposed strategies.

In parallel interleaved multilevel inverter (PIMI) applications, the objectives of suppressing the phase circulating current (PCC) and the zero-sequence circulating current (ZSCC) under conventional SVPWM are often conflicting. This makes it challenging for conventional modulation strategies to achieve their coordinated mitigation. To address this issue, this paper proposes an improved asymmetric regular sampling variable-switching-frequency PWM (ARS-VSFPWM) strategy incorporating a cost function model. First, to overcome the failure of symmetric regular sampling (SRS) under low-switching-frequency conditions, a predictive model for PCC and ZSCC is established based on ARS while accounting for control delay. Then, cost-function-based online optimization of vector selection achieves qualitative coordinated suppression of both circulating currents. Furthermore, variable switching frequency introduces an additional degree of freedom, dynamically adjusting the switching frequency per control cycle to quantitatively constrain peak circulating currents to predefined thresholds. Finally, results from 36-MW simulations and experiments validate the effectiveness and superiority over conventional methods.