The vibration signal of a pump is often used for analysis in the study of hydraulic-pump fault diagnosis methods. In this study, for the analysis, sound signals were used, which can be used to acquire data in a non-contact manner to expand the use scenarios of hydraulic-pump fault-diagnosis methods. First, the original data are denoised using complete ensemble empirical mode decomposition with adaptive noise and the minimum redundancy maximum relevance algorithm. Second, the noise-reduced data are plotted as mean spectrogram bar graphs, and the datasets are divided. Third, the training set graphs are input into the ResNet-50 network to train the base model for fault diagnosis. Fourth, all the layers of the base model are frozen, except for the fully connected and softmax layers, and the support set graphs are used to train the base model through transfer learning. Finally, a fault diagnosis model is obtained. The model is tested using data from two test pumps, resulting in accuracies of 86.1% and 90.8% and providing evidence for the effectiveness of the proposed method for diagnosing faults in hydraulic plunger pumps.

The hydrostatic bearing slipper pair of the hydraulic pump has a unique adaptive friction characteristic, which has a better friction reduction and anti-wear ability than the general sliding friction pair, and also has a certain recovery effect on the performance degradation caused by the early wear of the slipper. This paper attempts to reveal the friction adaptive mechanism. Based on the fractal theory, two fractal parameters of fractal dimension and scale coefficient are used to characterize the surface morphology of the slipper mathematically, and the adaptive friction mechanism model is established by combining the friction coefficient equation. The effects of different fractal parameters on the friction coefficient and other performance parameters of slipper pairs are obtained by means of the numerical analysis method. The wear test was carried out by replacing specimens at different intervals to observe the worn surface morphology and the degradation process of the slipper to verify the correctness of the theoretical results. The results show that the friction performance and load-bearing capabilities of the slipper can be recovered to a certain extent within a short period when early wear occurs, and its surface performance shows the variation characteristics of deterioration-repair-re-deterioration-re-repair.

Unsupervised domain adaptation technology has been proven to effectively tackle the fault diagnosis issue of hydraulic pump across different working conditions, which utilizes a large amount of labeled data under one operating condition to achieve fault diagnosis of unlabeled data under another new operating condition. However, a current challenge of this method is the difficulty in acquiring sufficient labeled data of the source domain in practical engineering and overcoming the significant distribution differences to extract transferable features. In this paper, a novel fault transfer diagnosis approach for hydraulic pump, named DS-IDANN, is proposed by integrating dynamic simulation and an improved domain adversarial neural network. The proposed DS-IDANN method mainly includes two steps. To begin with, the simulated system of hydraulic pump is built to obtain the simulation data under different health status by deriving the relationship between impact force and fault deformation. Then, a semi-supervised domain adversarial graph convolutional network is constructed to realize the fault transfer diagnosis from the simulation data to measured data by introducing a maximum entropy and improving the structure of the traditional domain adversarial neural network. Finally, one case study conducted on a plunger pump is implemented to demonstrate the effectiveness and practicability of our developed method, and the result indicates that the accuracy of fault diagnosis is higher than other existing approaches.

Due to the scarcity of labeled samples, the practical engineering application of deep learning-based hydraulic pump fault diagnosis methods is extremely challenging. This study proposes a semi-supervised learning method based on data augmented consistency regularization (DACR) to address the issue of lack of labeled data in diagnostic models. It utilizes augmented data obtained from the improved symplectic geometry modal decomposition method as additional perturbations, expanding the feature space of limited labeled samples under different operating conditions of the pump. A high-confidence label prediction process is formulated through a threshold determination strategy to estimate the potential label distribution of unlabeled samples. Consistent regularization loss is introduced in labeled and unlabeled data, respectively, to regularize model training, reducing the sensitivity of the classifier to additional perturbations. The supervised loss term ensures that the predictions of the augmented labeled samples are consistent with the true labels. Meanwhile, the unsupervised loss term can be used to minimize the difference between the distributions of unlabeled samples for different augmented versions. Finally, the proposed method is combined with Kolmogorov–Arnold Network (KAN). Comparative experiments based on data from two models of hydraulic pumps verify the superior recognition performance of this method under low label rate.

Aiming at the problem that soft robots are challenging to take into account both flexibility and bearing capacity, Using the software Pneu-Net driver as the deformation mode, magnetorheological fluid material phase transformation to achieve variable stiffness, A pneumatic modular soft joint structure with dynamically adjustable deformation and stiffness in all directions is proposed. In this paper, mathematical models of deformation and variable stiffness are established. The correspondence between gas pressure and deformation and applied current and joint stiffness is obtained. The finite element analysis method was used to simulate the deformation characteristics and variable stiffness characteristics of modular joints based on the Yeoh model. Finally, the theoretical and simulation results are verified by deformation and variable stiffness tests. It is proved that the modular joint has good rigid-flexible coupling characteristics.