The protective properties of coating systems usually depend on their base layer, since its characteristics and chemical composition are greatly responsible for prevention of corrosion development. Moreover, a good primer as a base coating has to provide good adhesion between the coating system and the substrate material, as well as good cohesion, i.e., coating strength. The described experiment aimed to determine the influence of input parameters (anticorrosive pigment content, conditioning time, dry film thickness) on the adhesion properties of the coating. The optimization of input parameters was achieved by the pull-off test in order to determine their maximum values. For the purpose of imitating aggressive atmosphere of service conditions, the experiment was run in a salt spray chamber, in which samples were cyclically sprayed with 5% sodium chloride (NaCl) solution for 120 h. The obtained mathematical model makes it possible to define the optimal values of the input variables for the defined values of the required property, i.e., the adhesion properties of the applied primer for certain exploitative conditions.
Classification algorithm based on the support vector method (SVM) was used in this paper to classify welded joints in two categories, one being good (+1) and the other bad (−1) welded joints. The main aim was to classify welded joints by using recorded sound signals obtained within the MAG welding process, to apply appropriate preprocessing methods (filtering, processing) and then to analyze them by the SVM. This paper proves that machine learning, in this specific case of the support vector methods (SVM) with appropriate input conditions, can be efficiently applied in assessment, i.e. in classification of welded joints, as in this case, in two categories. The basic mathematical structure of the machine learning algorithm is presented by means of the support vector method.
Metal inert gas (MIG) welding is one of the processes most commonly used for joining metals, especially for joining aluminum and its alloys. The application of a pulsed current in an electric arc allows better controllability of the molten droplets and the arc transition, which subsequently leads to welds with characteristic flaky joints of better quality. In this paper, the optimization of parameters for welding aluminum alloys using the synchropulse welding process is investigated. By observing the input variables that have the greatest influence on the change in appearance of the welding current characteristics (delta wire feed from 0.1 to 6.0 m/min, frequency F from 0.5 to 3 Hz, duty cycle from 10% to 90%), it is possible to perform an optimization to achieve the desired output values. The output variables of the experiments are defined as insufficient/excessive throat thickness (mm), depth of penetration (mm), and weld width (mm); and for the desired quality of the welded joint the most acceptable range of its values is selected, the numerical optimization implementation. The experiment has shown that the delta wire feed has the greatest effect on the observed properties, while the influence of frequency F and duty cycle is somewhat smaller, but the factors responsible for the observed output properties are still significant. From all this, it is possible to select specific values of these input variables to define the best possible observed properties and to determine the characteristics of the defined mathematical models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.