Shuiguang Tong's research while affiliated with Zhejiang University and other places

In previous studies on re-entrant hybrid flow shops, the impact of dynamic events was often ignored despite being a common occurrence in practical production. To address this issue and simultaneously reduce energy consumption, a multi-objective evolutionary algorithm with variable neighborhood search (MOEA-VNS) has been proposed to optimize the green scheduling problem in a re-entrant hybrid flow shop with dynamic events (RHFS-GDS).The approach involves creating a green dynamic scheduling optimization model, which aims to minimize the makespan, total energy consumption, and stability of rescheduling solutions. A hybrid green scheduling decoding method is then employed to select machines for each operation and calculate fitness. Additionally, three neighborhood structures are designed to improve the population diversity and optimality of the MOEA-VNS algorithm. Two rescheduling strategies are also adopted to handle dynamic events that may occur during production. Experimental results demonstrate that these approaches are effective in solving the RHFS-GDS problem and can guide actual production. By incorporating dynamic events and rescheduling strategies into the optimization process, the proposed MOEA-VNS algorithm provides a comprehensive solution to the complex challenges faced by re-entrant hybrid flow shops in practical production environments.

A stochastic uncertain tribodynamic model is established for a spur gear pair for the first time. The stochastic uncertainty of pinion rotation speed propagated to lubrication performance is investigated. The probability density function of the minimum lubricant film thickness hmin evolves over time periodically at interval of an engagement process. Correspondence between abrupt increase in meshing force and amplification of hmin uncertainty is found. Robust and reliable lubrication performance can be achieved by suppressing the hmin uncertainty and decreasing the lubrication failure probability. This can be done by increasing lubricant viscosity, and decreasing input torque and uncertainty level of input rotation speed. This work lays a solid foundation for robust and reliability based optimization for tribodynamic gear system.

Gear drive is one of the most widely used transmission forms. Its vibration analysis plays an important role in design and operation. Considering the gear meshing resonance phenomenon (MRP), the paper analyzes the influences of rotating speed and load on meshing resonance intensity (MRI). Based on the gear meshing impact mechanism, meshing force variation during the engagement process were obtained. It was considered as meshing impacts exerted on the gear system. By comparing the maximum meshing force under different circumstances, it was found that rotating speeds and loads were positively related to meshing forces. The vibration signals with different load torques and rotating speeds obtained from the gear pair were analyzed. The experiment results showed that the intensity of meshing impact increased with the increases of both rotating speed and load. It was also observed that due to the MRP, the gear meshing frequency was modulated to the resonance frequency band as meshing impacts. Consequently, the resonance frequency band contained most of the energy of the meshing impact. An indicator called resonance energy ratio (RER) was defined to represent the proportion of resonance energy due to meshing impact. The simulation and experiment result show that the proposed RER indicator can well assess the intensity of the vibration. By comparing the RER values of 20 sets of gear vibration data, the influences of rotating speed and load on MRI were discussed. The result show that the proposed method is helpful to the vibration assessment and condition monitoring in different operational states.

The superheater in the boiler is the key of equipment connecting high-temperature steam to the turbine for power generation. At present, the problems of large variable fluctuations, strong timing coupling, and multi-power plant data utilization prevent the temperature, flow, and pressure prediction of the boiler superheater. In this paper, a method for predicting the parameters of boiler superheater based on a transfer learning model is proposed, which realizes the joint utilization of data from multiple power plants. The method first collects data from a waste incineration boiler power plant for pre-training the long short-term memory (LSTM)-transformer model, and then completes the transfer learning training on the new power plant. The proposed method has the advantages of high prediction accuracy, good robustness, and more reliable location prediction with drastic changes. The predictions on the test set are within ± 5% of the experimental value. Compared with the model not trained by the transfer learning, the proposed method achieves the lowest relative errors for all prediction intervals in the 3-15 min range. Compared to the linear regression (LR), support vector regression (SVR), and random forest (RF), the proposed method improves the average absolute percentage error (MAPE) by 30%, 13%, and 20%, respectively. Flatter loss sharpness value and better robust performance obtained from the transfer learning method is verified by an experimental verification. Finally, a digital system design for power plants with real-time data visualization monitoring, parameter prediction, and fault warning functions are implemented.

Gear drives are inherently subjected to time-variant loads, which always create an uncertainty and may degrade the vibration performance and system reliability. However, due to their complicated statistical properties, it is impractical to employ probability-based dynamic analysis methods. Additionally, most studies neglect the elastohydrodynamic lubrication behaviors between tooth surfaces under time-variant load conditions. A novel tribodynamic analysis method is proposed to evaluate system responses efficiently, in which the uncertain time-variant loads are described using interval processes. Firstly, a deterministic tribodynamic model coupling the system dynamics and elastohydrodynamic lubrication is established. To reduce the computational cost, the interval Karhunen-Loeve expansion is employed to simplify the interval processes using a small number of uncorrelated interval variables, while the Chebyshev subinterval decomposition is carried out to approximate actual responses using one-variable functions. The proposed method shares a comparable accuracy with the time-consuming Monte Carlo simulation and experiments. Parametric studies show that the uncertain time-variant loads significantly affect the uncertainty of vibration and induce a more hazardous lubricating condition. Additionally, the variation trend of uncertain tribodynamic responses is highly correlated with the rotating speed.

Variational mode decomposition (VMD) is a suitable tool for processing cavitation-induced vibration signals and is greatly affected by two parameters: the decomposed number K and penalty factor α under strong noise interference. To solve this issue, this study proposed self-tuning VMD (SVMD) for cavitation diagnostics in fluid machinery, with a special focus on low signal-to-noise ratio conditions. A two-stage progressive refinement of the coarsely located target penalty factor for SVMD was conducted to narrow down the search space for accelerated decomposition. A hybrid optimized sparrow search algorithm (HOSSA) was developed for optimal α fine-tuning in a refined space based on fault-type-guided objective functions. Based on the submodes obtained using exclusive penalty factors in each iteration, the cavitation-related characteristic frequencies (CCFs) were extracted for diagnostics. The power spectrum correlation coefficient between the SVMD reconstruction and original signals was employed as a stop criterion to determine whether to stop further decomposition. The proposed SVMD overcomes the blindness of setting the mode number K in advance and the drawback of sharing penalty factors for all submodes in fixed-parameter and parameter-optimized VMDs. Comparisons with other existing methods in simulation signal decomposition and in-lab experimental data demonstrated the advantages of the proposed method in accurately extracting CCFs with lower computational cost. SVMD especially enhances the denoising capability of the VMD-based method.