It is always an important and challenging issue to achieve an effective fault diagnosis in rotating machinery in industries. In recent years, deep learning proved to be a high-accuracy and reliable method for data-based fault detection. However, the training of deep learning algorithms requires a large number of real data, which is generally expensive and time-consuming. To cope with this, we proposed a Resnet classifier with model-based data augmentation, which is applied for bearing fault detection. To this end, a dynamic model was first established to describe the bearing system by adjusting model parameters, such as speed, load, fault size, and the different fault types. Large amounts of data under various operation conditions can then be generated. The training dataset was constructed by the simulated data, which was then applied to train the Resnet classifier. In addition, in order to reduce the gap between the simulation data and the real data, the envelop signals were used instead of the original signals in the training process. Finally, the effectiveness of the proposed method was demonstrated by the real bearing experimental data. It is remarkable that the application of the proposed method can be further extended to other mechatronic systems with a deterministic dynamic model.

To explore the potential wear performance of commonly utilized hydraulic system polymer components, we investigated the effects of different working conditions on the frictional and wear behaviors of three polymer sealing materials in this study. Polytetrafluoroethylene (PTFE), nylon (PA), and polypropylene (PP) composites were prepared using copper (Cu) and glass fiber (GF) as fillers. The tribological and wear properties (wear rate, surface appearance, wear patterns) of the sealing composites were evaluated. The results showed consistent trends toward increasing average coefficient of friction as load and speed increased for PTFE. The incorporation of filler improved the wear resistance of the composites. The addition of Cu particles showed lower coefficient under higher load and sliding speed. PA with continuous glass fiber (CGF) sealing composites showed lower coefficient, less wear volume, and relatively smoother wear zone surfaces than PTFE-based composites or PP with short glass fiber (SGF). We propose that PA-CGF outperforms other materials in regards to fatigue and friction and wear even under extremely high silding speed,as well as sealing properties.

Die forging hydraulic presses, essential for metal forming in large-scale component manufacturing, often suffer from low energy utilization. Due to system complexity and load uncertainty, accurately characterizing the dynamic energy consumption during operation remains a significant challenge. Additionally, determining the optimal system configuration to minimize energy consumption in the forging process is difficult. To address these issues, this study proposes an electromechanical-hydraulic coupling model to dynamically quantify energy dissipation in key components of the hydraulic press during operation. The influence of motor speed, pump displacement, and overflow pressure settings on system energy consumption is analyzed, and an energy efficiency optimization strategy based on system parameter matching is developed. The accuracy of the proposed energy consumption model is validated through forging experiments on scaled-down aircraft connection components, with the steady-state error of each characteristic curve remaining within 5.5%. Furthermore, the optimized operating parameters result in a 18,753.3 J and 26,710.3 J reduction in motor and pump energy consumption, respectively, while overflow and throttling losses are reduced by 138,986.8 J and 30,357.1 J, leading to an overall system energy consumption reduction of 61.9% in a single operating cycle. Considering typical factory operation, this corresponds to an estimated annual energy saving of approximately 1400 kWh, demonstrating the practical significance of the proposed optimization strategy.