Detection of abnormal situations in mobile systems not only provides predictions about risky situations but also has the potential to increase energy efficiency. In this study, two real-world drives of a battery electric vehicle and unsupervised hybrid anomaly detection approaches were developed. The anomaly detection performances of hybrid models created with the combination of Long Short-Term Memory (LSTM)-Autoencoder, the Local Outlier Factor (LOF), and the Mahalanobis distance were evaluated with the silhouette score, Davies–Bouldin index, and Calinski–Harabasz index, and the potential energy recovery rates were also determined. Two driving datasets were evaluated in terms of chaotic aspects using the Lyapunov exponent, Kolmogorov–Sinai entropy, and fractal dimension metrics. The developed hybrid models are superior to the sub-methods in anomaly detection. Hybrid Model-2 had 2.92% more successful results in anomaly detection compared to Hybrid Model-1. In terms of potential energy saving, Hybrid Model-1 provided 31.26% superiority, while Hybrid Model-2 provided 31.48%. It was also observed that there is a close relationship between anomaly and chaoticity. In the literature where cyber security and visual sources dominate in anomaly detection, a strategy was developed that provides energy efficiency-based anomaly detection and chaotic analysis from data obtained without additional sensor data.

Fatma Nur Büyük, Efe Savran, Fatih Karpat. Journal of Dental Implant Research 2022;41:50-63. https://doi.org/10.54527/jdir.2022.41.3.50

Increasing energy need brings people one step closer to energy saving and alternative sources. The search for reliable and sustainable resources also contributes greatly to technological progress. Thanks to advanced technology, energy use becomes more efficient. However, the concept of sustainability emerges in the field of energy as in other sectors. It is expected that electric vehicles, which have started to increase in interest in recent years, will make a positive contribution to issues such as environmental protection and sustainable energy. In addition, production centers for electric vehicles should also be sustainable and sensitive to carbon emissions. In this study, energy and carbon loss assessment was carried out in an electric bus manufacturing factory. With the help of linear regression analysis, the data of the last 3 years were evaluated. Moreover, as a result of internal audits, energy loss points were determined. As a result of this study, sustainability, carbon loss, and energy management issues in an electric vehicle production factory were evaluated and guiding qualities for today's and future technology companies were revealed.

In this study, the Bald Eagle Search Algorithm performed hydrogen consumption and battery cycle optimization of a fuel cell electric vehicle. To save time and cost, the digital vehicle model created in Matlab/Simulink and validated with real-world driving data is the main platform of the optimization study. The digital vehicle model was run with the minimum and maximum battery charge states determined by the Bald Eagle Search Algorithm, and hydrogen consumption and battery cycle values were obtained. By using the algorithm and digital vehicle model together, hydrogen consumption was minimized and range was increased. It was aimed to extend the life of the parts by considering the battery cycle. At the same time, the number of battery packs was included in the optimization and its effect on consumption was investigated. According to the study results, the total hydrogen consumption of the fuel cell electric vehicle decreased by 57.8% in the hybrid driving condition, 23.3% with two battery packs, and 36.27% with three battery packs in the constant speed driving condition.

The purpose of this study was to develop a fuzzy logic controller (FLC)-based energy management strategy for battery electric vehicles that enables them to reduce their energy consumption and carbon emission levels without sacrificing their performance. An electric vehicle model was developed in MATLAB/Simulink using a virtual battery and validated with real-world driving tests to save time and money. An in-depth investigation is conducted on both virtual and real vehicles to confirm the effectiveness of the proposed energy management strategy. This study shows that by using FLC-based energy management, an energy consumption advantage of 9.16% can be achieved while maintaining acceptable performance levels in real-world driving conditions. This advantage results in significant reductions annually: 1044.09 tons of CO₂ emissions, USD 164,770.65 in savings for electric bus lines, and 5079 battery cycles. For European passenger electric vehicles, this corresponds to 405,657.6 tons of CO₂ emissions reduced, USD 64,017,840 saved, and 5.071 battery cycles per vehicle. This strategy not only enhances energy efficiency but also contributes to long-term sustainability in public transportation systems, particularly for electric bus fleets, which play a critical role in urban mobility.