A Novel Multi-Task Learning Model with PSAE Network for Simultaneous Estimation of Surface Quality and Tool Wear in Milling of Nickel-Based Superalloy Haynes 230.

For data-driven intelligent manufacturing, many important in-process parameters should be estimated simultaneously to control the machining precision of the parts. However, as two of the most important in-process parameters, there is a lack of multi-task learning (MTL) model for simultaneous estimation of surface roughness and tool wear. To address the problem, a new MTL model with shared layers and two task-specific layers was proposed. A novel parallel-stacked auto-encoder (PSAE) network based on stacked denoising auto-encoder (SDAE) and stacked contractive auto-encoder (SCAE) was designed as the shared layers to learn deep features from cutting force signals. To enhance the performance of the MTL model, the scaled exponential linear unit (SELU) was introduced as the activation function of SDAE. Moreover, a dynamic weight averaging (DWA) strategy was implemented to dynamically adjust the learning rate of different tasks. Then, the time-domain features were extracted from raw cutting signals and low-frequency reconstructed wavelet packet coefficients. Frequency-domain features were extracted from the power spectrum obtained by the Fourier transform. After that, all features were combined as the input vectors of the proposed MTL model. Finally, surface roughness and tool wear were simultaneously predicted by the trained MTL model. To verify the superiority and effectiveness of the proposed MTL model, nickel-based superalloy Haynes 230 was machined under different cutting parameter combinations and tool wear levels. Some other intelligent algorithms were also implemented to predict surface roughness and tool wear. The results showed that compared with the support vector regression (SVR), kernel extreme learning machine (KELM), MTL with SDAE (MTL_SDAE), MTL with SCAE (MTL_SCAE), and single-task learning with PSAE (STL_PSAE), the estimation accuracy of surface roughness was improved by 30.82%, 16.67%, 14.06%, 26.17%, and 16.67%, respectively. Meanwhile, the prediction accuracy of tool wear was improved by 46.74%, 39.57%, 41.51%, 38.68%, and 39.57%, respectively. For practical engineering application, the dimensional deviation and surface quality of the machined parts can be controlled through the established MTL model.

Bismuth Vacancy-Induced Efficient CO2 Photoreduction in BiOCl Directly from Natural Air: A Progressive Step toward Photosynthesis in Nature.

Photocatalytic CO2 conversion into carbonaceous fuels through artificial photosynthesis is beneficial to global warming mitigation and renewable resource generation. However, a high cost is always required by special CO2-capturing devices for efficient artificial photosynthesis. For achieving highly efficient photocatalytic CO2 reduction (PCR) directly from natural air, we report rose-like BiOCl that is rich in Bi vacancies (VBi) assembled by nanosheets with almost fully exposed active {001} facets. These rose-like BiOCl with VBi assemblies provide considerable adsorption and catalytic sites, which hoists the CO2 capture and reduction capabilities, and thus expedites the PCR to a superior value of 21.99 µmol·g-1·h-1 CO generation under a 300 W Xe lamp within 5 h from natural air. The novel design and construction of a photocatalyst in this work could break through the conventional PCR system requiring compression and purification for CO2, dramatically reduce expenses, and open up new possibilities for the practical application of artificial photosynthesis.

Effect of Cutting Fluid on Milled Surface Quality and Tool Life of Aluminum Alloy.

The machining process of aluminum alloy usually produces built-up edge and tool sticking problems due to their low hardness and large plastic deformation, which may further affect the machined surface quality and tool life. This paper aims to investigate the influence of different cutting fluids on the machined surface quality and tool life during the milling process of 7050 aluminum alloy. A novel cutting fluid (QC-2803) was considered in the study, which is synthesized by addition of alkyl alcohol amide and chlorinated polyolefin, and the traditional cutting fluid (CCF-10) was used as the control group. The physical and chemical properties of two cutting fluids were characterized. The milling process of 7050 aluminum alloy was carried out under two different cutting fluid conditions. The machined surface morphology, cutting force and tool wear morphology were observed during the process. Results show that the surface tension of the novel cutting fluid is significantly lower than that of the traditional cutting fluid, which makes it easier to produce a lubricating film between the aluminum alloy and tool, and further benefits the machined surface quality and tool life. As a result, the surface roughness and cutting force are reduced by ~20.0% and ~42.9%, respectively, and the tool life is increased by 25.6% in the case of the novel cutting fluid (QC-2803). The results in this paper revealed the important laws of cutting fluid with metal surface quality, cutting performance and tool wear, which helps to control the machined surface quality and tool life by the selection of cutting fluid during metal milling.

A Review on Manufacturing and Post-Processing Technology of Vascular Stents.

Percutaneous coronary intervention (PCI) with stent implantation is one of the most effective treatments for cardiovascular diseases (CVDs). However, there are still many complications after stent implantation. As a medical device with a complex structure and small size, the manufacture and post-processing technology greatly impact the mechanical and medical performances of stents. In this paper, the development history, material, manufacturing method, and post-processing technology of vascular stents are introduced. In particular, this paper focuses on the existing manufacturing technology and post-processing technology of vascular stents and the impact of these technologies on stent performance is described and discussed. Moreover, the future development of vascular stent manufacturing technology will be prospected and proposed.

Effect of Corrosive Medium and Surface Defect-Energy on Corrosion Behavior of Rolled ZK61M Alloy.

Magnesium alloys have been widely used as lightweight engineering structural materials, but their service performances are severely restricted by corrosion failure. In this paper, the influence of corrosive medium and surface defect energy on the corrosion behavior of rolled ZK61M alloy was investigated. The corrosion tests were conducted in different concentrations of sodium chloride solution for different durations, and the polarization curves and electrochemical impedance spectroscopy were reported. The surface morphology of rolled ZK61M alloy before and after corrosion tests were analyzed. The results showed that the corrosion tendency became stronger with the increase of the concentration of corrosive medium and the number of surface defects of ZK61M alloy. Moreover, the initial corrosion pattern was the pitting caused by micro galvanic corrosion at the surface defect, which gradually developed into uniform corrosion. Furthermore, the main damage occurred at the grain boundary, resulting in the destruction of grain bonding force and the removal of material along the rheological layer. The oxidation corrosion mechanism was mainly the anodic dissolution mechanism.

Multi-Objective Optimization of Bioresorbable Magnesium Alloy Stent by Kriging Surrogate Model.

PURPOSE: The study proposed a multi-objective optimization method based on Kriging surrogate model and finite element analysis to mitigate the redial recoil and foreshortening ratio of bioresorbable magnesium alloy stent, and investigate the impact of strut thickness on stent expansion behavior. METHODS: Finite element analysis have been carried out to compare the expansion behavior of stents with various strut thickness. Latin hypercube sampling (LHS) was adopted to generate train sample points in the design space, and the Kriging surrogate model was constructed between strut parameters and stent behavior. The genetic algorithm (GA) was employed to find the optimal solution in the global design space. RESULTS: Stents with thinner struts experience lower stress but suffer from severe radial recoil and foreshortening effects. The radial recoil is decreased by 66%, and foreshortening ratio is reduced by 60% for the optimized stent with U-bend width 90.7 [Formula: see text] and link width 77.9 [Formula: see text]. The errors between Kriging surrogate model and finite element simulation are 6% and 9% for the radial recoil and foreshortening ratio. CONCLUSION: Stent expansion behavior are highly dependent on design parameters, i.e. thickness, U-bend and link strut width. The purposed Multi-objective optimization approach based on Kriging surrogate model and finite element analysis is efficient in stent design optimization problem.

The Development of Design and Manufacture Techniques for Bioresorbable Coronary Artery Stents.

Coronary artery disease (CAD) is the leading killer of humans worldwide. Bioresorbable polymeric stents have attracted a great deal of interest because they can treat CAD without producing long-term complications. Bioresorbable polymeric stents (BMSs) have undergone a sustainable revolution in terms of material processing, mechanical performance, biodegradability and manufacture techniques. Biodegradable polymers and copolymers have been widely studied as potential material candidates for bioresorbable stents. It is a great challenge to find a reasonable balance between the mechanical properties and degradation behavior of bioresorbable polymeric stents. Surface modification and drug-coating methods are generally used to improve biocompatibility and drug loading performance, which are decisive factors for the safety and efficacy of bioresorbable stents. Traditional stent manufacture techniques include etching, micro-electro discharge machining, electroforming, die-casting and laser cutting. The rapid development of 3D printing has brought continuous innovation and the wide application of biodegradable materials, which provides a novel technique for the additive manufacture of bioresorbable stents. This review aims to describe the problems regarding and the achievements of biodegradable stents from their birth to the present and discuss potential difficulties and challenges in the future.

Development of 3D-Printed Sulfated Chitosan Modified Bioresorbable Stents for Coronary Artery Disease.

Bioresorbable polymeric stents have attracted great interest for coronary artery disease because they can provide mechanical support first and then disappear within a desired time period. The conventional manufacturing process is laser cutting, and generally they are fabricated from tubular prototypes produced by injection molding or melt extrusion. The aim of this study is to fabricate and characterize a novel bioresorbable polymeric stent for treatment of coronary artery disease. Polycaprolactone (PCL) is investigated as suitable material for biomedical stents. A rotary 3D printing method is developed to fabricate the polymeric stents. Surface modification of polymeric stent is performed by immobilization of 2-N, 6-O-sulfated chitosan (26SCS). Physical and chemical characterization results showed that the surface microstructure of 3D-pinted PCL stents can be influenced by 26SCS modification, but no significant difference was observed for their mechanical behavior. Biocompatibility assessment results indicated that PCL and S-PCL stents possess good compatibility with blood and cells, and 26SCS modification can enhance cell proliferation. These results suggest that 3D printed PCL stent can be a potential candidate for coronary artery disease by modification of sulfated chitosan (CS).