Search Results (9)

Electric bicycles in elevators pose serious safety hazards. Fires in the confined space make escape difficult, and recent accidents involving e-bike fires have caused casualties and property damage. To prevent e-bikes from entering elevators and improve public safety, this design employs the Nezha development board as the upper computer for visual detection. It uses deep learning algorithms to recognize hazards like e-bikes. The lower computer orchestrates elevator controls, including voice alarms, door locking, and emergency halt. The system comprises two parts: the upper computer uses the YOLOv11 model for target detection, trained on a custom e-bike image dataset. The lower computer features an elevator control circuit for coordination. The workflow covers target detection algorithm application, dataset creation, and system validation. The experiments show that the YOLOv11 demonstrates superior e-bike detection performance, achieving 96.0% detection accuracy and 92.61% mAP@0.5, outperforming YOLOv3 by 6.77% and YOLOv8 by 15.91% in mAP, significantly outperforming YOLOv3 and YOLOv8. The system accurately identifies e-bikes and triggers safety measures with good practical effectiveness, substantially enhancing elevator safety. Full article

Production using modular architecture can not only shorten the product development cycle and improve the efficiency of product development, but also facilitate the upgrading of a product’s main functions and the recycling of materials. However, mechatronic products are plagued by various problems, such as greater difficulty in development and longer product development cycles due to their large numbers of parts with intricate internal relationships. However, the existing modular design method still faces problems when dealing with the modular design of mechatronic products. The structure of mechanical and electrical products is very complex, which is not conducive to the establishment of a model, and complex structural models lead to low efficiency and poor accuracy of module identification. Therefore, we propose an integrated module division method for mechatronic products based on core part hierarchical clustering and non-core part association analysis. Firstly, the core part screening method is used to simplify the structural model of mechatronic products and reduce the difficulty of modeling. Then, based on the core parts, the corresponding product design structural matrix (DSM) model is established. Secondly, the hierarchical clustering algorithm is used to obtain the module division scheme of different levels of mechatronic products, and the optimal modular scheme is obtained through an evaluation of modularity and a rationality analysis of module structure. Finally, based on the analysis of the association strength between the non-core parts and the existing modules, the non-core parts are classified into the corresponding product modules, and the final modularization scheme is obtained. A case study demonstrates the feasibility of the proposed method through the modular design of an electric bicycle. Full article

Electric bicycles offer convenient short-distance travel, but improper battery charging poses a fire risk, especially indoors, potentially causing significant accidents, property damage, and even threats to life. Recognizing the charging state of electric bicycle batteries is crucial for safety. This paper proposes a novel method to identify the charging process of lithium batteries in electric bicycles. Methods that do not require physical alterations to the equipment are used to acquire users’ electricity consumption data, with current signals preprocessed and input into a combined model integrating convolutional neural networks (CNN) and bidirectional long short-term memory (BiLSTM) networks. The proposed model captures complex patterns and features in the charging data, effectively identifying the charging characteristics of lithium batteries. Validation using NASA’s lithium battery dataset and real experimental data shows that the combined model achieves recognition accuracy of 96% and 97% on training data and 93% and 94% on validation data. Further validation under multiple device loads and comparison with other models indicate that the proposed method is highly accurate, outperforming traditional CNN and LSTM models by 4–9%. This research enhances the safety and regulation of electric bicycle battery charging and provides a reliable method for non-intrusive load identification in smart monitoring systems, contributing to improved safety measures and energy management in residential environments. Full article

This paper proposes a new method for assessing the state of charge (SoC) and identifying the types of different lithium-ion cells used in the battery systems of light electric vehicles. A particular challenge in the development of this method was the SoC estimation time, as the method is intended for implementation in the control system of a bicycle charging station, where the state of charge must be determined immediately after the bicycle is plugged in in order to start the charging process as quickly as possible according to the appropriate charging algorithm. The method is based on the identification of the transfer function, i.e., the dynamic response of the battery voltage to the current pulse. In the learning phase of this method, a database of reference transfer functions and corresponding SoCs for a specific type of battery cell is created. The transfer functions are described by coefficients determined through the optimization procedure. The algorithm for estimating the unknown battery cell SoCs is based on the comparison of the measured voltage response with the responses of the reference transfer functions from the database created during the learning process to the same current signal. The comparison is made by calculating the integral of the square error (ISE) between the response of the specific reference transfer function and the measured voltage response of the battery cell. Each transfer function corresponds to a specific SoC and cell type. The specific SoC of the unknown battery is determined by quadratic interpolation of the SoC near the reference point with the smallest ISE for each battery type. The cell type detection algorithm is based on the fact that the integral squared error criterion near the actual SoC for the actual cell type changes less than the squared error criterion for any other battery cell type with the same SoC. An algorithm for estimating the SoC and cell type is described and tested on several different cell types. The relative error between the estimated SoC and the actual SoC was used as a measure of the accuracy of the algorithm, where the actual SoC was calculated using the Coulomb counting method. Full article

The rapid development of modern logistics and e-commerce highlights the importance of exploring various modes of transportation in the last-mile delivery (LMD) process. However, no comprehensive studies exist in the literature exploring all modes of LMD transportation, the changes in these transportation modes, and the commonalities between them. In this study, we address this gap by conducting a systematic review of 150 academic journal articles utilizing a combination of the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) content analysis and text mining analysis. Nine primary transportation methods (parcel lockers, autonomous drones, trucks, bicycles, crowd logistics, electric vehicles, tricycles, autonomous robots, and autonomous vehicles) are identified in this research. Additionally, we provide an analysis of the historical changes in these transportation modes in LMD. Using a bottom-up induction method, we identify the three major clusters of scholarly focus in the LMD literature: emphasis on value co-creation between consumers and logistics providers, practical delivery performance (path optimization or algorithms), and environmental friendliness. Further, we analyze the main themes under each cluster, leading to the identification of opportunities, challenges, and future research agendas. Our findings have implications for scholars, policymakers, and other stakeholders involved in LMD transportation modes. Full article

People are gradually coming around to the idea of living a low-carbon lifestyle and using green transportation, and given the severe urban traffic congestion, electric bicycle commuting has taken over as the preferred mode of short-distance transportation for many. Since batteries are used to power electric bicycles, there are no greenhouse gas emissions while they are in use, which is more in line with the requirement for sustainable development around the world. The public has been increasingly concerned about the safety issues brought on by electric bicycles as a result of the industry’s quick development and the rapid increase in the number of electric bicycles worldwide. The unsafe operation of the elevator and the safety of the building have been seriously compromised by the unauthorized admission of electric bicycles into the elevator. To meet the need for fast detection and identification of electric bicycles in elevators, we designed a modified YOLOv5-based identification approach in this study. We propose the use of the EIoU loss function to address the occlusion problem in electric bicycle recognition. By considering the interaction ratio and overlap loss of the target frames, we are able to enhance localization accuracy and reduce the missed detection rate of occluded targets. Additionally, we introduce the CBAM attention mechanism in both the backbone and head of YOLOv5 to improve the expressive power of feature maps. This allows the model to prioritize important regions of the target object, leading to improved detection accuracy. Furthermore, we utilize the CARAFE operator during upsampling instead of the nearest operator in the original model. This enables our model to recover details and side information more accurately, resulting in finer sampling results. The experimental results demonstrate that our improved model achieves an mAP of 86.35 percent, a recall of 81.8 percent, and an accuracy of 88.0 percent. When compared to the original model under the same conditions, our improved YOLOv5 model shows an average detection accuracy increase of 3.49 percent, a recall increase of 5.6 percent, and an accuracy increase of 3.5 percent. Tests in application scenarios demonstrate that after putting the model on the hardware platform Jeston TX2 NX, stable and effective identification of electric bicycles can be accomplished. Full article

Within the multiple urban–rural interactions that make up the territorial dynamics, this article addresses and identifies how mobility relations are produced between neighbouring municipalities that share services. The aim of this research is to carry out a diagnosis of the current mobility situation in an area of low population density in order to identify the needs and possible shortcomings in this area. The initial identification of weaknesses is essential in order to propose solutions for rural mobility. The methodology adopted is based on two distinct lines of work: (1) analysis of information in open data from public repositories using geographic information system tools (GIS), and (2) surveys of citizens living in the study area. The results allude to the fact that the most transcendental problem in the study area is the lack of a quality collective public transport service that meets minimum utility requirements for users, a fact that generates a transfer towards the use of private vehicles. No serious parking, noise, pollution or road safety problems are observed; however, similar dynamics to other rural areas with low demographic density are confirmed, such as the age of the mobile fleet and an aging population with accessibility problems. The presence of new modes of transport (electric bicycles, personal mobility vehicles, and even electric vehicles) is practically insignificant. Both teleworking and the new consumer habits associated with online shopping have not yet had a strong impact. Political decision making by public administrations is identified as a direct application of this research. Full article

The need for reducing the cost of and space in Electrically Assisted Bicycles (EABs) has led the research to the development of solutions able to sense the applied pedalling torque and to provide a suitable electrical assistance avoiding the installation of torque sensors. Among these approaches, this paper proposes a novel method for the estimation of the pedalling torque starting from an estimation of the motor load torque given by a Load Torque Observer (LTO) and evaluating the environmental disturbances that act on the vehicle longitudinal dynamics. Moreover, this work shows the robustness of this approach to rotor position estimation errors introduced when sensorless techniques are used to control the motor. Therefore, this method allows removing also position sensors leading to an additional cost and space reduction. After a mathematical description of the vehicle longitudinal dynamics, this work proposes a state observer capable of estimating the applied pedalling torque. The theory is validated by means of experimental results performed on a bicycle under different conditions and exploiting the Direct Flux Control (DFC) sensorless technique to obtain the rotor position information. Afterwards, the identification of the system parameters together with the tuning of the control system and of the LTO required for the validation of the proposed theory are thoroughly described. Finally, the capabilities of the state observer of estimating an applied pedalling torque and of recognizing the application of external disturbance torques to the motor is verified. Full article

Speed pedelecs, electric bicycles that can provide pedal assistance up to 45 km/h, have seen rapid uptake over the past ten years in Flanders, Belgium, yet perceptions around motivators and barriers have not been studied and understood in detail. This paper reports on the qualitative experiences of 100 participants from 10 Flemish companies who replaced their commuting vehicle by a speed pedelec for up to three weeks. Focus groups provided data in the identification of the motivators and the barriers towards speed pedelecs in comparison to those for bicycles and pedelecs classified in nine categories. The results from the focus groups show notable differences in motivators for using speed pedelecs compared to bicycles and pedelecs—the higher available speed and range within a given timeframe, which provides the possibility of better time management. The mental benefits and the competitive aspect of commuting with a speed pedelec were identified as new motivators. The purchase cost and the perception of safety as barriers remain, with reliability, flexibility, and planning identified as new barriers. Full article