This paper deals with the constraint-based design, optimum design and reconfiguration strategy of a 3-RPS parallel manipulator. Some design conditions related to the base and moving-platform design parameters and the three degree of-freedom operation modes are derived. A 3-RPS parallel manipulator with two types of operation modes is generated by following those conditions. Due to its potential advantages, this manipulator is used as an ankle rehabilitation device which can cover the ankle joint motion. To derive the optimum parameters, kinematic optimization is conducted by initially parametrizing the orientation workspace and it turns out that its orientation workspace is not symmetrical. The singularity loci are traced in its orientation workspace. A performance index, named Maximum Inscribed Circle Diameter (MICD) is presented to assess the maximum tilt of the moving-platform for any azimuth angle. The distributions of MICD are plotted in the design space for different moving-platform heights. The optimum region with regard to MICD is obtained. It is noteworthy that the evolution of MICD as a function of movingplatform height in both operation modes is the opposite. Therefore, a reconfiguration strategy is proposed to ensure the moving-platform working above the minimum required orientation for any moving-platform height.
Faulty compressors must be detected in advance to speed up the quality control process of the compressor's performance. Machine learning models have recently been used as fault classification models to distinguish between normal and abnormal compressors, facilitating more sophisticated fault detection methods than those in the past. However, very few studies have been conducted on accurate and efficient feature selection, despite its high importance. Therefore, this study proposes a new hybrid method that combines the merits of existing feature methods, filter and wrapper methods, to obtain a stable, accurate, and efficient fault classification model. For this, three types of filtering methods with different characteristics, such as chi-square, extra tree classifier, and correlation matrix, are used to derive the high-ranked features and then create a powerful feature set consisting of their union sets. Subsequently, using the wrapper method, one combination of features with the highest classification accuracy was selected among all the combinations of features in the union feature set. Using two experimental examples and one numerical example with different types and numbers of data, the robustness and accuracy of the proposed method were verified through comparison with the existing filter methods by combining three classification models: support vector machine, K-nearest neighbor, and multi-layer perceptron.
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.