Application of BP Artificial Neural Network in Preparation of Ni–W Graded Coatings

The internal stress difference between soft-ductile aluminum alloy substrate and hard-brittle Ni–W alloy coating will cause stress concentration, thus leading to the problem of poor bonding force. Herein, this work prepared the Ni–W graded coating on aluminum alloy matrix by the pulse electrodeposition method in order to solve the mechanical mismatch problem between substrate and coatings. More importantly, a backward propagation (BP) neural network was applied to efficiently optimize the pulse electrodeposition process of Ni–W graded coating. The SEM, EDS, XRD, Vickers hardness tester and Weighing scales are used to analyze the micromorphology, chemical element, phase composition, and micro hardness as well as oxidation weight increase, respectively. The results show that the optimal process conditions with BP neural network are as follows: the bath temperature is 30 °C, current density is 15 mA/cm2 and duty cycle is 0.3. The predicted value of the model agrees well with the experimental value curve, the relative error is minor. The maximum error is less than 3%, and the correlation coefficient is 0.9996. The Ni–W graded coating prepared by BP neural network shows good bonding with the substrate which has flat and smooth interface. The thickness of the coating is about 136 μm, which slows down the oxidation of the substrate and plays an effective role in protecting the substrate.

Process Characteristics of Water-based Self-curing Coatings for Sand Casting

The rheological and gas evolution characteristics of water-based self-curing coatings for sand casting were analyzed and the influence of coating-thickness and graded coating on self-curing rate of coatings was studied. It can be seen from the test results that: the new water-based self-curing coating has both the characteristics of thixotropic fluid and pseudoplastic fluid, which has moderate thixotropy rate and high brushing index, good brushability and excellent comprehensive balance of flow-levelling and anti-flowability. It can meet the rheological requirements of various coating methods. The self-curing speed of water-based self-curing coating increases in an approximately linear manner with the decrease of its thickness. Thick coating should be best to paint at one time in the premise of ensuring its surface quality. Although the gas evolution volume of the new water-based self-curing coating is approximately equal to that of ordinary water-based baking coatings, but the gas evolution speed of self-curing coatings is almost half as that of the latter, which provides good conditions for preventing gas hole defect of casting.

Self-lubricating triboactive (Cr,Al)N+Mo:S coatings for fluid-free applications

Within this study, self-lubricating and triboactive (Cr,Al)N+Mo:S coatings were developed and investigated for the deposition on components in a low-temperature physical vapor deposition (PVD) hybrid process. Therefore, direct current magnetron sputtering (dcMS) and high power pulse magnetron sputtering (HPPMS) PVD were combined by using an industrial coating machine. Hereby, it was possible to deposit dense and smooth triboactive, self-lubricating nitride coatings with different chemical compositions and architectures on 16MnCr5E samples. Two coating architectures, a matrix monolayer and a graded coating structure, were developed to evaluate the effect on the tribological behavior. The morphology and coating thickness were analyzed by means of scanning electron microscopy (SEM). Furthermore, the indentation hardness and modulus of indentation as well as the compound adhesion between substrate materials and coating were analyzed. Tribological analyses of (Cr,Al)N+Mo:S-coated and uncoated samples were conducted under fluid-free friction regime at room temperature T = (20 ± 3) °C, a velocity v = 0.1 m/s and a distance s = 1000 m by varying the Hertzian contact pressure from 400 MPa ≤ pH ≤ 1300 MPa against steel counterparts, 100Cr6, in a pin-on-disk (PoD) tribometer. The graded coating architecture of (Cr,Al)N+Mo:S enabled a significant wear and friction reduction. Furthermore, Raman analyses prove the formation of solid lubrication tribofilm containing MoS2, MoO3 MoO2 and MoxOy at the toplayer of a graded (Cr,Al)N+Mo:S coating, which are responsible for the improved tribological behavior.

Thermal fracture of functionally graded thermal barrier coatings with pre-existing edge cracks and multiple internal cracks imitating a curved interface

This work is devoted to the problem of thermal fracture of a functionally graded coating on a homogeneous substrate (FGC/H) with an emphasis on the analysis of a special system of cracks that simulates a curved interface. The FGC/H structure contains the pre-existing crack system in the FGC, both edge cracks (which are often seen in FGC/H structures) and internal cracks. The stress intensity factors are calculated. (Generally, both Mode I and Mode II are nonzero.) Then, using the appropriate fracture criterion for mixed-mode fracture conditions, the crack propagation direction (so-called fracture angles) and critical loads, when this propagation is initiated, are determined. The application of fracture criteria requires knowledge of the fracture toughness near the crack tips. Thus, it is assumed that the fracture toughness of an FGC, as well as other material properties, continuously varies through the thickness of the coating. For multiple cracks, it is also important to know the weakest crack that starts to propagate first, and the initial direction of this growth. Therefore, the main attention is paid to the evaluation of the fracture angles for the cracks for different parameters of the FGC/H structure. Both cases of a homogeneous semi-infinite medium with a system of cracks imitating a curved interface and FGC/H structures with identical crack systems are studied.