Friction is an inherent nonlinear disturbance that can lead to creeping, jitter, and decreased tracking precision in an electro-hydraulic servo system. In this paper, the LuGre friction model is used to describe the dynamic and static characteristics of the friction force of a servo system comprehensively. Accurate identification of model parameters is key to implementing friction compensation. However, traditional genetic identification algorithms have the shortcomings of a premature solution, slow convergence, and poor accuracy. To address these shortcomings, this paper proposes an improved adaptive genetic identification algorithm. The proposed algorithm selects evolutionary processes adaptively according to the population concentration in the initial stage of population evolution. Moreover, it adjusts the crossover probability and the mutation probability to identify a local optimum accurately and converge to the global optimum rapidly. During the late stage of population evolution, the accuracy of the global optimal solution can be improved by reducing the search range of identification parameters. The simulation results show that the relative error of the model parameter values identified by the proposed algorithm is reduced to less than 1% and the convergence speed is faster. Compared with the existing traditional genetic algorithm and adaptive genetic algorithm, the overall performance of the proposed method is better. This study provides a feasible and highly accurate identification method for parameter identification of friction models used in electro-hydraulic servo systems.

The raw signals produced by internal gear pumps are susceptible to noises brought on by mechanical vibrations and the surrounding environment, and the sample count collected during the various operating periods is not distributed evenly. Accurately diagnosing faults in internal gear pumps is significantly complicated by these factors. In light of these issues, accelerated life testing was performed in order to collect signals from an internal gear pump during various operating periods. Based on the architecture of a convolutional auto-encoder network, preprocessing of the signals in the various operating periods was performed to suppress noise and enhance operating period-representing features. Thereafter, variational mode decomposition was utilized to decompose the preprocessed signal into multiple intrinsic mode functions, and the multi-scale permutation entropy value was extracted for each intrinsic mode function to form a feature set. The feature set was subsequently divided into a training set and a test set, with the training set being trained to utilize a particle swarm optimization–least squares support vector machine network. For pattern recognition, the test set samples were fed into the trained model. The results demonstrated a 99.2% diagnostic accuracy. Compared to other methods of fault diagnosis, the proposed method is more effective and accurate.

Mechanical equipment failure may cause massive economic and even life loss. Therefore, the diagnosis of the failures of machine parts in time is crucial. The rolling bearings are one of the most valuable parts, which have attracted the focus of fault diagnosis. Many successful rolling bearing fault diagnoses have been made based on machine learning and deep learning. However, most diagnosis methods still rely on complex signal processing and artificial features, bringing many costs to the deployment and migration of diagnostic models. This paper proposes an end-to-end continuous/discontinuous feature fusion method for rolling bearing fault diagnosis (C/D-FUSA). This method comprises long short-term memory (LSTM), convolutional neural networks (CNN) and attention mechanism, which automatically extracts the continuous and discontinuous features from vibration signals for fault diagnosis. We also propose a contextual-dependent attention module for the LSTM layers. We compare the method with the other simpler deep learning methods and state-of-the-art methods in rolling bearing fault data sets with different sample rates. The results show that our method is more accurate than the other methods with real-time inference. It is also easy to be deployed and trained in a new environment.

The internal gear pump is simple in structure, small in size and light in weight. It is an important basic component that supports the development of hydraulic system with low noise. However, its working environment is harsh and complex, and there are hidden risks related to reliability and exposure of acoustic characteristics over the long term. In order to meet the requirements of reliability and low noise, it is very necessary to make models with strong theoretical value and practical significant to accurately monitor health and predict the remaininglife of the internal gear pump. This paper proposed a multi-channel internal gear pump health status management model based on Robust-ResNet. Robust-ResNet is an optimized ResNet model based on a step factor $h$ in the Eulerian approach to enhance the robustness of the ResNet model. This model was a two-stage deep learning model that classified the current health status of internal gear pumps, and also predicted the remaining useful life (RUL) of internal gear pumps. The model was tested in an internal gear pump dataset collected by the authors. The model was also proven to be useful in the rolling bearing data from Case Western Reserve University (CWRU). The accuracy results of health status classification model were 99.96% and 99.94% in the two datasets. The accuracy of RUL prediction stage in the self-collected dataset was 99.53%. The results demonstrated that the proposed model achieved the best performance compared to other deep learning models and previous studies. The proposed method was also proven to have high inference speed; it could also achieve real-time monitoring of gear health management. This paper provides an extremely effective deep learning model for internal gear pump health management with great application value.

Unsupervised industrial anomaly detection learns from normal images and identifies defects unseen during training. In reconstruction-based detectors, the features used to represent normality and the residuals used to localize defects vary across images, yet these signals are commonly selected with fixed category-level rules. We propose MSPNet, a Mirrored Selection Policy Network that learns these choices from validation performance. Its feature selection policy chooses channels that characterize normal appearance, and its residual selection policy chooses residuals for localization. The policies share a reward based on image-level and pixel-level AUROC while acting on complementary stages of the reconstruction pipeline, so the pair is symmetric in structure while the stages it acts on are not. Their scores are combined by SA-Fuzzy, a compact Takagi–Sugeno layer whose inputs are symmetric under exchange of the two branches, and whose membership functions are symmetric in branch agreement but asymmetric in anomaly level, so that increasing and decreasing anomaly signals receive different responses. On MVTec-AD, VisA, MPDD and BTAD, MSPNet obtains Image-AUROC/Pixel-AUROC values of 99.6/99.1, 98.2/99.0, 97.1/98.6 and 96.6/98.1, respectively. The learned policies are most useful for images whose selections depart from category averages, and SA-Fuzzy improves over a raw-score combiner on the images where the two branches disagree. On the full set, the two combiners are indistinguishable. Most of that margin comes from the exchange-invariant parameterization of the layer inputs. The present resolution does not separate fuzzy inference itself from a parameter-matched alternative. The learnable asymmetric memberships do separate from their symmetric counterpart on the same subset. These results show that input-adaptive selection can improve reconstruction-based anomaly detection across changing image appearances.

Rapid prediction of cavity sound pressure spectra is essential for the acoustic design of high-speed vehicles. A spectral database is built from 20 flow conditions (4 Mach numbers × 5 angles of attack) and eight cavity measurement points, giving 160 condition–point combinations, each densely sampled at 1147 amplitude–frequency points over 6–7000 Hz. Four models—RF, XGBoost, LightGBM and SVM—are compared on two prediction tasks, flow-condition and spatial-position prediction, before and after Bayesian optimization. Optimization markedly improves in-distribution accuracy and reduces dominant-frequency amplitude errors under unseen conditions, but reverses the ranking: RF and LightGBM dominate at baseline, whereas XGBoost ranks first after tuning, attaining 0.76 dB in the flow-condition task and staying on a par with RF (0.09 dB apart) in the spatial-position task. Under unseen conditions the SVM degenerates to a constant output of 117.11 dB, essentially the training-target mean, owing to the locality of the RBF kernel—a structural limitation that tuning cannot remedy. The direction of the peak-amplitude bias is not uniform: systematic underestimation occurs in the spatial-position task, whereas after tuning XGBoost overestimates the peak at Ma = 1.5, the condition with the highest measured amplitude. No single model is optimal across all scenarios.