Enzymes are important and effective biological catalyst proteins participating in almost all active cell processes. Identification of multi-functional enzymes is essential in understanding the function of enzymes. Machine learning methods perform better in protein structure and function prediction than traditional biological wet experiments. Thus, in this study, we explore an efficient and effective machine learning method to categorize enzymes according to their function. Multi-functional enzymes are predicted with a special machine learning strategy, namely, multi-label classifier. Sequence features are extracted from a position-specific scoring matrix with autocross-covariance transformation. Experiment results show that the proposed method obtains an accuracy rate of 94.1% in classifying six main functional classes through five cross-validation tests and outperforms state-of-the-art methods. In addition, 91.25% accuracy is achieved in multi-functional enzyme prediction, which is often ignored in other enzyme function prediction studies. The online prediction server and datasets can be accessed from the link http://server.malab.cn/MEC/.

Modeling complex fluid flow using machine learning is increasingly recognized as a valuable approach for revealing multiphase fluid phenomena. Bubble dynamics represent a classical two-phase flow problem that plays a crucial role in various engineering domains. In this paper, physics-informed neural networks (PINNs) are applied to facilitate incompressible two-phase bubble motion modeling by integrating governing equations and interface evolution equations. The loss function of PINNs consists of multiple loss terms, including initial and boundary conditions constraints, partial differential equations residuals, and volume fraction constraints. The performance of PINNs is influenced by the competing effects of these loss terms. Therefore, we introduce a heuristic adaptive weights approach to automatically adjust loss weights for each training point, avoiding manual tuning and improving the accuracy of PINNs. We investigate typical bubble motion cases, specifically focusing on bubble rising and breakup, to showcase the capabilities of the proposed method. We explore the impact of weights and present the results in comparison to the baselines. Through the bubble breakup case, we illustrate that our model shows superior performance even with more complex scenarios. Then we further discuss the generalization and robustness of our model, showing their indispensability over traditional solvers in gas–liquid two-phase systems. Specifically, we accelerate computation speed in transfer learning without the need to modify the original model. We also show that our method effectively solves ill-posed problems, such as those without initial data or with incomplete or noisy boundary conditions.

An integrated analysis method for a rocket-augmented turbine-based combined cycle (TBCC) engine is proposed based on the trajectory optimization method of the Gauss pseudospectral. The efficiency and energy of the vehicles with and without the rocket are analyzed. Introducing an appropriate rocket to assist the TBCC-powered vehicle will reduce the total energy consumption of drag, and increase the vehicle efficiency in the transonic and the mode transition. It results in an increase in the total efficiency despite a reduction in engine efficiency. Therefore, introducing a rocket as the auxiliary power is not only a practical solution to enable flight over a wide-speed range when the TBCC is incapable but also probably an economical scheme when the the TBCC meets the requirements of thrust. When the vehicle drag is low, the rocket works for a short time and its optimal relative thrust is small. Thus, the TBCC combined with a booster rocket will be a more simple and suitable scheme. When the vehicle drag is high, the operating time of the rocket is long and the optimal relative thrust is large. The specific impulse has a significant impact on the flight time and the total fuel consumption. Accordingly, the combination form for the rocket-based combined cycle (RBCC) engines and the turbine will be more appropriate to obtain higher economic performance.

Combustion test diagnosis has always been one of the most important technologies for the development of aerospace engineering. The traditional methods of measurement have been unable to meet the requirements of accurate capture of the flow field in the development process of the aeroengine combustor. Therefore, the development of high-precision measurement and diagnostic techniques to meet the needs of the aeroengine combustor design is imperative. Laser diagnostics techniques developed quickly in the past several years. They are used to measure the parameters of the combustion flow field such as velocity, temperature, and components concentration with high space and time resolution and brought no disturbance. Planar laser-induced fluorescence, coherent anti-Stokes Raman scattering, tunable diode laser absorption spectroscopy, and Raman scattering were introduced systemically in this paper. After analysis of their own advantages and disadvantages, the authors considered validated Raman scattering system and Tunable Diode Laser Absorption Tomography are more suitable for research activities on aeroengine combustion systems.