The integration of artificial intelligence (AI) and machine learning (ML) technologies is rapidly transforming the design, operation, and optimization of electric motorcycles. This review analyzes research published between 2015 and 2024, focusing on how ML algorithms enhance performance, energy efficiency, diagnostics, and charging strategies across four key domains: electric motors, energy storage, charging systems, and electronic components. The review highlights state-of-the-art solutions such as torque and range prediction using LSTM/GRU models, predictive maintenance via CNNs and autoencoders, energy flow control in hybrid battery–supercapacitor systems using reinforcement learning, and federated learning for privacy-preserving embedded applications. Comparative insights reveal quantifiable performance gains over traditional methods, while integrated frameworks are proposed for linking ML diagnostics, Vehicle-to-Grid (V2G) functionalities, and renewable energy integration. The paper concludes with targeted recommendations for future research, including lightweight edge-deployable models, Explainable AI for safety-critical applications, and the fusion of intelligent charging with eco-design principles, aiming to enable intelligent, sustainable, and high-performance electric motorcycle systems.

The dynamic loads acting on passengers during road accidents depend not only on the vehicle structure, but also on the properties of the applied passenger and driver protection system. Two-point seat belts are the most frequently used personal protection system for adult passengers in bus vehicles. The paper investigates the thread of dynamic loads acting on the body of a 50 percentile dummy placed in an armchair equipped with two-point seat belts. In order to solve this problem, tests recorded with the Phantom v310 camera were used, the object of which was the Hybrid II 50th dummy, and the recording of the tests was carried out for three different collision speeds. The article presents the results of the crash tests obtained with the use of the TEMA Automotive program. Crash test analysis showing the displacement of the head and upper torso of the dummy located in the limited space between the bus-type seats indicates that standard seat belts do not provide sufficient protection. The article indicates the basis for further research and improvement of the personal protection system of passengers transported in minibuses and buses.

The purpose of this publication is to present the construction and adaptation of the test stand intended for motorcycle simulation research. The stand is designed to study the impact of motorcycle vibrations that act on the body of the driver and passenger. Motorcycles belong to one of the types of transport that directly affects users. Excessive vibrations transmitted to the body of the driver and passenger can make driving uncomfortable and even dangerous. The vibrations of motorcycles depend mainly on the technical condition of the vehicle, the structure of the vehicle, and the construction of the engine. The stand was built on the basis of a hydraulic power supply unit, distributor, and electrohydraulic pulsators. The purpose of the construction of the stand is to examine a given group of motorcycles to learn and eliminate vibrations that occur in various areas of motorcycles and affect the comfort, health, and safety of motorcycle travelers. Test studies of the presented stand are presented in this article. The preliminary results of the simulation tests determined the possibility of testing individual elements and motorcycles on the laboratory stand.

The article presents the results of research on the relationship between the technical condition of motorcycle shock absorbers determined on the diagnostic line and their damping characteristics. The basic division of shock absorber tests was characterized, which includes tests of shock absorbers installed in the motorcycle and disassembled, carried out on a test stand made of MTS components. The results of two sets of shock absorbers tested using the EUSAMA and THETA methods, as well as tested on a stand for testing shock absorbers removed from a motorcycle, are discussed. Based on the obtained results, the best method of diagnosing shock absorbers was indicated.

The aim of this study was to develop and preliminarily validate an accelerometer-based method for objectively assessing the fidelity of laboratory-replicated motorcycle road vibrations and supporting the operator’s decision to terminate or continue the replication process. Reliable reproduction of real-world road inputs is necessary for repeatable investigations of vehicle dynamics and safety-relevant loads. Vertical front- and rear-axle accelerations recorded on different road surfaces were used as targets for a two-channel electrohydraulic test rig. The method combines percentage errors in response minima and maxima, retention of the best result obtained, time- and frequency-domain signal-fidelity assessment, and machine-learning prediction of the next trial. The retained responses exhibited high lag-compensated correlation and high in-band coherence. The extremum-based criterion detected local degradation that RMS error did not consistently reveal. A random-forest regressor produced a lower forecast error than a persistence baseline; however, the limited number of independent sequences does not support autonomous stopping. The proposed method provides a transparent, verifiable operator-support layer for sensor-based motorcycle testing. It may improve the repeatability and credibility of laboratory assessments of vehicle response to real-world road inputs, but validation over repeated sessions is required before automation.