Tire mode shape categorization using Zernike annular moment and machine learning classification.

This research proposes a framework for categorizing the radial tire mode shapes using machine learning (ML) based classification and feature recognition algorithms, advancing the development of a digital twin for tire performance analysis. Tire mode shape categorization is required to identify modal features in a specific frequency range to maximize driving performance and secure safety. However, the mode categorization work requires a lot of manual effort to interpret modes. Therefore, this study suggests an ML-based classification tool to replace the conventional categorization process with two primary objectives: (1) create a database by categorizing the tire mode shapes based on the identified features and (2) develop an ML-based surrogate model to classify the tire mode shapes without manual effort. The feature map of the tire mode shape is built with the Zernike annular moment descriptor (ZAMD). The mode shapes are categorized using the correlation value derived by the modal assurance criteria (MAC) with all ZAMD values for each tire mode shape and subsequently creating the appropriate labels. The decision tree, random forests, and XGBoost, the representative supervised-learning algorithms for classification, are implemented for surrogate model development. The best-performed classifier can categorize the mode shapes without any manual effort with a high accuracy of 99.5%.

A data-driven approach to the "Everesting" cycling challenge.

The "Everesting" challenge is a cycling activity in which a cyclist repeats a hill until accumulating an elevation gain equal to the elevation of Mount Everest in a single ride. The challenge experienced a surge in interest during the COVID-19 pandemic and the cancelation of cycling races around the world that prompted cyclists to pursue alternative, individual activities. The time to complete the Everesting challenge depends on the fitness and talent of the cyclist, but also on the length and gradient of the hill, among other parameters. Hence, preparing an Everesting attempt requires understanding the relationship between the Everesting parameters and the time to complete the challenge. We use web-scraping to compile a database of publicly available Everesting attempts, and we quantify and rank the parameters that determine the time to complete the challenge. We also use unsupervised machine learning algorithms to segment cyclists into distinct groups according to their characteristics and performance. We conclude that the power per unit body mass of the cyclist and the tradeoff between the gradient of the hill and the distance are the most important considerations when attempting the Everesting challenge. As such, elite cyclists best select a hill with gradient > 12%, whereas amateur and recreational cyclists best select a hill with gradient < 10% to minimize the time to complete the Everesting challenge.