The output voltage of inverters is influenced by nonlinear factors such as dead time and voltage drops, injecting low-order harmonics. This results in fifth and seventh harmonic distortions in the stator current, causing periodic torque ripples and significantly affecting the control precision of Permanent Magnet Synchronous Motors (PMSMs). To address this issue, this paper proposes a control strategy named quasi-proportional-resonant sliding mode control (QPR-SMC). Initially, sliding mode control is employed as the current controller to enhance disturbance rejection capability and provide a rapid dynamic response. Subsequently, a quasi-proportional-resonant controller is introduced to extract the sixth harmonic component from the current, which is then used as a compensation term for the sliding mode control surface. Finally, the current tracking error and the compensation term are combined as inputs to the sliding mode control law, forming a current error-proportional resonant-sliding mode control surface. This approach enhances the harmonic suppression capability of the system. The results demonstrate that the proposed method effectively reduces the fifth and seventh harmonic components in the three-phase current and mitigates motor jitter by suppressing the sixth harmonic in the d–q coordinate system.

Intelligent scheduling of knitting workshops is the key to realizing knitting intelligent manufacturing. In view of the uncertainty of the workshop environment, it is difficult for existing scheduling algorithms to flexibly adjust scheduling strategies. This paper proposes a scheduling algorithm architecture based on deep reinforcement learning (DRL). First, the scheduling problem of knitting intelligent workshops is represented by a disjunctive graph, and a mathematical model is established. Then, a multi-proximal strategy (multi-PPO) optimization training algorithm is designed to obtain the optimal strategy, and the job selection strategy and machine selection strategy are trained at the same time. Finally, a knitting intelligent workshop scheduling experimental platform is built, and the algorithm proposed in this paper is compared with common heuristic rules and metaheuristic algorithms for experimental testing. The results show that the algorithm proposed in this paper is superior to heuristic rules in solving the knitting workshop scheduling problem, and can achieve the accuracy of the metaheuristic algorithm. In addition, the response speed of the algorithm in this paper is excellent, which meets the production scheduling needs of knitting intelligent workshops and has a good guiding significance for promoting knitting intelligent manufacturing.

To address the issue of mechanical resonance frequency detection in dual-inertia servo systems, this paper proposes an online identification method for mechanical resonance frequency using a low-pass filter and cascaded second-order generalized integrator—frequency-locked loop (LPF-CSOGI-FLL). Initially, the cascaded second-order generalized integrator—frequency-locked loop (CSOGI-FLL) is employed to eliminate the interference of direct current (DC) bias in resonance frequency identification. From a dual-stage structural perspective, the first second-order generalized integrator (SOGI-FLL) acts as a band-pass pre-filter to extract the mechanical resonance signal from the signal to be tested. The second SOGI-FLL generates a signal with equal amplitude and frequency to the mechanical resonance and obtains the frequency of the resonance signal through the frequency-locked loop. Subsequently, a low-pass filter (LPF) is applied to the frequency feedback loop of the second-stage SOGI-FLL, effectively reducing the oscillation of the estimated frequency. Finally, combining the CSOGI-FLL with an LPF forms a novel structure, namely, LPF-CSOGI-FLL. The results demonstrate that the proposed method significantly improves the detection accuracy of mechanical resonance frequency under various conditions. Compared to traditional offline techniques, this method overcomes the impact of resonance frequency drift and enhances system stability.

To improve the synchronization accuracy of dual motors under external disturbances, this paper proposes a cross-coupling control strategy based on an improved global fast terminal sliding mode control (GFTSMC) and disturbance observer (DOB). In practical applications, dual-motor systems are often affected by external disturbances, leading to synchronization errors between the motors, which in turn affect the system’s stability and accuracy. First, for single-motor control, this paper uses the improved GFTSMC method to design a speed loop, enhancing the tracking accuracy and dynamic response of the individual motor by optimizing the sliding surface. Then, the improved GFTSMC is combined with a cross-coupling strategy to effectively solve the synchronization problem of dual motors. The cross-coupling strategy coordinates the operation of the two motors, reducing the speed deviation between them, thus improving synchronization accuracy and enhancing the system’s disturbance rejection capability. Moreover, the DOB is used to precisely estimate the frictional torque, and compensating for these disturbances improves the system’s robustness and stability. The results show that the proposed control method significantly improves the speed synchronization of the dual motors and exhibits excellent dynamic performance, effectively coping with complex external disturbances.

In order to improve the accuracy and detection effect of fabric defect detection, a fabric defect detection method based on local similarity comparison is proposed in this paper. This method first takes each pixel in the image as the central pixel, selects a specific window as the region size, and then uses the similarity between the central region and the surrounding neighborhood to find the neighborhood most similar to the central region to complete the estimation of the central pixel. Finally, the target image is obtained by the principle of background difference, so as to detect fabric defects. The results show that this method is superior to the traditional detection method, which can not only detect the defect image under the complex background, but also have good detection results for the fabric defect image under the influence of different organization and lighting factors. The detection accuracy rate under factory conditions can reach 98.45%, which has a high applicability and detection rate, and also demonstrates certain anti-interference performance.

To mitigate the challenges of false positives and undetected small-scale defects in fabric inspection, this study proposes an advanced fabric defect detection system that leverages an optimized YOLOv9 algorithm. First, redundant computations are reduced by introducing DualConv to replace standard convolution. Second, the LSKA attention mechanism is incorporated to increase the weight of important features, thereby enhancing the accuracy of small target detection and improving the generalization ability. Additionally, the focal modulation network is employed to replace the fast spatial pyramid module, mitigating the loss of detailed information caused by the feature pooling operation. Furthermore, the conventional feature pyramid network is replaced with bidirectional feature pyramid network, which is utilized for efficient feature fusion, thereby enhancing multiscale feature representation and improving detection accuracy. Finally, the bounding box loss function is optimized by introducing the shape-IoU loss function, which facilitates more rapid model convergence and significantly improves detection accuracy. Experiments conducted on a fabric defect dataset demonstrate that the proposed algorithm yields a 6.7% increase in mAP@0.5 and a 14.7% improvement in mAP@0.5–0.95, while simultaneously reducing the model’s total parameters by 17.8% and computational FLOPs by 14.4%, compared with those of the original algorithm. The improved YOLOv9 model significantly enhances the precision and accuracy of defect detection while maintaining inference speed (55.8 FPS) that meets industrial requirements.