• Smart Structures and Systems
• /
• v.18 no.1
• /
• pp.75-92
• /
• 2016

The design of a semi-active (SA) control system addressed to mitigate wind induced structural demand to high wind turbine towers is discussed herein. Actually, the remarkable growth in height of wind turbines in the last decades, for a higher production of electricity, makes this issue pressing than ever. The main objective is limiting bending moment demand by relaxing the base restraint, without increasing the top displacement, so reducing the incidence of harmful "p-delta" effects. A variable restraint at the base, able to modify in real time its mechanical properties according to the instantaneous response of the tower, is proposed. It is made of a smooth hinge with additional elastic stiffness and variable damping respectively given by springs and SA magnetorheological (MR) dampers installed in parallel. The idea has been physically realized at the Denmark Technical University where a 1/20 scale model of a real, one hundred meters tall wind turbine has been assumed as case study for shaking table tests. A special control algorithm has been purposely designed to drive MR dampers. Starting from the results of preliminary laboratory tests, a finite element model of such structure has been calibrated so as to develop several numerical simulations addressed to calibrate the controller, i.e., to achieve as much as possible different, even conflicting, structural goals. The results are definitely encouraging, since the best configuration of the controller leaded to about 80% of reduction of base stress, as well as to about 30% of reduction of top displacement in respect to the fixed base case.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.105-125
• /
• 2024

Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.