To find multimodal solutions for the optimal design of an interior permanent magnet synchronous motor (IPMSM) for fuel cell electric vehicles, an autotuning elliptical niching genetic algorithm is proposed. With conventional autotuning niching genetic algorithms, some peaks are difficult to find because of a circular niche region. The proposed algorithm solves this problem by introducing an elliptical niche. The superior performance of the proposed algorithm is verified using test functions, and it is applied to the optimal design of an IPMSM for fuel cell electric vehicles. INDEX TERMS Autotuning niching genetic algorithm (ANGA), fuel cell electric vehicle (FCEV), interior permanent magnet synchronous motor (IPMSM), multimodal, niche, pattern search method (PSM).

In this paper, the Novel Immune Algorithm (NIA) is proposed for an optimal design of electrical machines. By coupling the conventional Immune Algorithm and Steepest Descent Method, the NIA can perform fast and exact convergence to both global solutions and local solutions. Specifically, the concept of an antibody radius is newly introduced to improve the ability to navigate full areas effectively and to find new peaks by excluding already searched areas. The validity of the NIA is confirmed by mathematical test functions with complex objective function regions. The NIA is applied to an optimal design of an interior permanent magnet synchronous motor for fuel cell electric vehicles and to derive an optimum design with diminished torque ripple.

The dicentric chromosome assay is the “gold standard” in biodosimetry for estimating radiation exposure. However, large-scale deployment is limited due to its time-consuming nature and requirement for expert reviewers. Therefore, a recently developed automated system was evaluated for dicentric chromosome assay. A previously constructed deep learning-based automatic dose-estimation system (DLADES) was used to construct dose curves and calculate estimated doses. Blood samples from two donors were exposed to cobalt-60 gamma rays (0–4 Gy, at 0.8 Gy/min). DLADES efficiently identified monocentric and dicentric chromosomes but showed impaired recognition of complete cells with 46 chromosomes. We estimated the chromosome number of each “Accepted” sample in DLADES and sorted similar-quality images by removing outliers using the 1.5IQR method. We confirmed that 11 of the 12 data points followed the Poisson distribution. Blind samples were prepared for each dose to verify the accuracy of the estimated dose generated by the curve. The estimated dose was calculated using Merkle’s method. The actual dose for each sample was within the 95% confidence limits of the estimated dose. Sorting similar-quality images using chromosome numbers is crucial for automated dicentric chromosome assay. We successfully constructed a dose-response curve and determined the estimated dose using DLADES.

No abstract

No abstract