Search Results

Recently, application of a Multi-axis road simulator has been studied to improve reproducibility of vehicle running, however the system is complicated and expensive due to the large number of vibration axis. Therefore, it is necessary to clarify the evaluation object and balance the evaluation accuracy with the test efficiency appropriately. In this study, we have developed a method for efficient fatigue reliability evaluation of an off-road motorcycle with the road simulator. We focused on the simulation of a jump section of a track because it had been clarified that the fatigue damage in the jump section accounts for the most of the fatigue damage to the vehicle in one lap on the track.

Among others, off-road motorcycles are subject to changes in road surface conditions depending on weather conditions, and the influence of riding operation on their behavior is significant. Therefore, for consistent evaluation of handling stability, it is effective to quantitatively understand the amount of riding operation and vehicle behavior through data measurement. However, when riding off-road motorcycles, the impact on the vehicle is large, and there are problems with the impact resistance of the measurement equipment. There is also a high risk of damage to sensors due to entrapment of mud or stones, etc. Therefore, when using high-precision sensors, it is necessary to proceed with careful operational verification. In particular, since off-road motorcycles are designed to be lightweight, measurement equipment for them must be lightweight as well and compact enough to avoid possible large impact on the vehicle's dynamic characteristics.

Machine learning is used for the research and development of ITS services and the rider assistance for on-road motorcycle racing. Meanwhile, rider assistance systems for off-road motorcycles have yet to be developed, partly due to the complexity of the measurement conditions, as described in the previous paper. This research aims to create a reliable AI which is capable of classifying typical jump behaviors in off-road riding by machine learning to create a rider assistance system for off-road motorcycles. Motorcycle manufacturers and certain research institutes use motion sensors to collect data, but the data is obtained from a limited number of vehicles and riders. The creation of a rider assistance system requires a large amount of validation data. Furthermore, it is desirable to achieve the target with data that can be measured in mass-produced vehicles, which will make it possible to collect data even from general users.