To tackle the issue of limited sample data in small sample fault diagnosis for rolling bearings using deep learning, we propose a fault diagnosis method that integrates a KANs-CNN network. Initially, the raw vibration signals are converted into two-dimensional time-frequency images via a continuous wavelet transform. Next, Using CNN combined with KANs for feature extraction, the nonlinear activation of KANs helps extract deep and complex features from the data. After the output of CNN-KANs, an FAN network module is added. The FAN module can employ various feature aggregation strategies, such as weighted averaging, max pooling, addition aggregation, etc., to combine information from multiple feature levels. To further tackle the small sample issue, data generation is performed on the original data through diffusion networks under conditions of fewer samples for bearings and tools, thereby increasing the sample size of the dataset and enhancing fault diagnosis accuracy. Experimental results demonstrate that, under small sample conditions, this method achieves higher accuracy compared to other approaches.

An enhanced fault diagnosis approach for rolling bearings with composite faults using an optimized Squeeze and Excitation ResNet (SE-ResNet) model is proposed. This method integrates grid search (GS), support vector regression (SVR), ensemble empirical mode decomposition (EEMD), and low-rank multimodal fusion (LMF) to effectively handle the signals of acoustic–vibration fusion. By combining these techniques, the aim is to improve the accuracy and reliability of rolling bearing fault diagnosis. Firstly, improved EEMD combined with GS-SVR and a window function is used for rolling bearing vibration signal decomposition. Singular value methods are used to filter and reconstruct the results. Secondly, Markov transition fields (MTFs) are used to encode vibration signals into 2D images. LMF is used for the fusion of vibration and sound signals. An improved Squeeze and Excitation ResNet50 network is proposed for feature identification and classification of rolling bearing composite fault data. Finally, the method undergoes rigorous testing and evaluation using rolling bearing data. The experimental outcomes demonstrate that, in comparison to traditional neural networks, the enhanced SE-ResNet, integrated with GS-SVR-EEMD and LMF, attains superior diagnostic accuracy. Additionally, the proposed approach can be effectively utilized for diagnosing rolling bearing composite faults.

In response to the challenges of bearing fault diagnosis under small sample sizes and variable operating conditions, this paper proposes a novel method based on the two-dimensional analysis of vibration acceleration signals and a Multi-Task Conditional Generative Adversarial Network (MTC-GAN). This method first constructs two-dimensional images of vibration signals by leveraging the physical properties of the bearing acceleration signals and employs Local Binary Patterns (LBP) to extract subtle texture features from these images, thereby generating fault feature signatures with high discriminative power across different operating conditions. Subsequently, MTC-GAN is utilized for data augmentation, and the trained discriminator is used to perform fault classification tasks, improving classification accuracy under conditions with small sample sizes. Experimental results demonstrate that the proposed method achieves excellent fault diagnosis accuracy and robustness under both small sample sizes and varying operating conditions. Compared to traditional methods, this approach exhibits higher efficiency and reliability in handling complex operating conditions and data scarcity.

Aiming at the problem of insufficient accuracy in identifying the wear state of milling cutters with single-modal signals during milling, a method for identifying the wear state of milling cutters combining multi-modal information with deep learning is proposed. Firstly, the time-domain and frequency-domain features of the multimodal signal are extracted. The variational mode decomposition (VMD) method optimized by the multi-objective genetic algorithm is adopted to extract the energy features of each component as time-frequency features. Subsequently, the multi-domain features are fused to construct the feature matrix, and the Pearson correlation coefficient is used for feature dimensionality reduction. The ResNet-CBAM-BiGRU network (RC-BiGRU) model and the data augmentation strategy of physical constraints are introduced. The results show that the proposed model achieved an accuracy rate of 96.5% when using the enhanced fusion signal. It outperforms the following benchmark models: the proposed model that only uses force signals (91.1% accuracy), the 1D Convolutional Neural Network (1DCNN) model that does not use the enhanced fusion signal (88.9% accuracy), and the proposed model that only uses the unenhanced fusion signal (94.3% accuracy). This study confirms that the proposed RC-BiGRU fusion model and the data enhancement strategy have significant advantages in tool wear prediction, providing new ideas for predictive maintenance and fault diagnosis of tools.

The control system of parallel robots has problems such as low code reusability and insufficient scalability. To address the issues that the existing parallel robot code is not easy for subsequent secondary development and cannot meet the operational requirements of the propellant grain grasping process, this paper studies the key technologies of the parallel robot control system. It uses a Programmable Logic Controller (PLC) to directly control the motion logic of the robot, replacing the control method of traditional motion controllers, and utilizes the Ethernet for Control Automation Technology (EtherCAT) bus for communication to achieve control interaction with the robot’s servo motors. In the automated production line, this parallel robot eliminates the interaction between the motion controller and the PLC. Moreover, by reserving digital and analog interfaces, it effectively improves the secondary development capability of the parallel robot. Through propellant grain grasping experiments, it is verified that the robot moves stably with a grasping success rate of over 99.8%, These results demonstrate that the proposed PLC-based control system not only meets the stringent requirements of high-speed propellant handling but also provides a more open, scalable, and cost-effective architecture compared to traditional motion controller-based solutions. This work thereby offers a valuable reference and a practical framework for the development of next-generation industrial robotic systems that prioritize flexibility and ease of secondary development.