Nano-coating has been a hot issue in recent years. It has good volume effect and surface effect, and can effectively improve the mechanical properties, corrosion resistance and wear resistance of the coatings. It is important to improve the wear resistance of the material surface. The successful preparation of nano-coatings directly affects the application of nano-coatings. Firstly, the preparation methods of conventional surface coatings such as chemical vapor deposition and physical vapor deposition, as well as the newly developed surface coating preparation methods such as sol-gel method, laser cladding and thermal spraying are reviewed in detail. The preparation principle, advantages and disadvantages and the application of each preparation method in nano-coating are analyzed and summarized. Secondly, the types of nano-coating materials are summarized and analyzed by inorganic/inorganic nanomaterial coatings and organic/inorganic nanomaterial coatings, and their research progress is summarized. Finally, the wear-resistant mechanism of nano-coatings is revealed from three aspects: grain refinement, phase transformation toughening mechanism and nano-effects. The application prospects of nano-coatings and the development potential combined with 3D technology are prospected.

No abstract

No abstract

Although several data-driven soft sensors are available, online reliable prediction of the Mooney viscosity in industrial rubber mixing processes is still a challenging task. A robust semi-supervised soft sensor, called ensemble deep correntropy kernel regression (EDCKR), is proposed. It integrates the ensemble strategy, deep brief network (DBN), and correntropy kernel regression (CKR) into a unified soft sensing framework. The multilevel DBN-based unsupervised learning stage extracts useful information from all secondary variables. Sequentially, a supervised CKR model is built to explore the relationship between the extracted features and the Mooney viscosity values. Without cumbersome preprocessing steps, the negative effects of outliers are reduced using the CKR-based robust nonlinear estimator. With the help of ensemble strategy, more reliable prediction results are further obtained. An industrial case validates the practicality and reliability of EDCKR.