Multi-target tracking, a high-level vision job in computer vision, is crucial to understanding autonomous driving surroundings. Numerous top-notch multi-object tracking algorithms have evolved in recent years as a result of deep learning’s outstanding performance in the field of visual object tracking. There have been a number of evaluations on individual sub-problems, but none that cover the challenges, datasets, and algorithms associated with visual multi-object tracking in autonomous driving scenarios. In this research, we present an exhaustive study of algorithms in the field of visual multi-object tracking over the last ten years, based on a systematic review approach. The algorithm is broken down into three groups based on its structure: methods for tracking by detection (TBD), joint detection and tracking (JDT), and Transformer-based tracking. The research reveals that the TBD algorithm has a straightforward structure, however the correlation between its individual sub-modules is not very strong. To track multiple objects, the JDT technique combines multi-module joint learning with a deep network framework. Transformer-based algorithms have been explored over the past two years, and they have benefits in numerous assessment indicators, as well as tremendous research potential in the area of multi-object tracking. Theoretical support for algorithmic research in adjacent disciplines is provided by this paper. Additionally, the approach we discuss, which uses merely monocular cameras rather than sophisticated sensor fusion, is anticipated to pave the way for the quick creation of safe and affordable autonomous driving systems.
10 February 2023 in Journal of Thermal Science and Engineering Applications
With the continuous development of internal combustion engine technology, the thermal efficiency of traditional energy vehicles has been difficult to improve, and the heat loss caused by high-temperature exhaust emissions is an important reason for the low thermal efficiency. To utilize the exhaust heat, the aim is to develop various spiral tube heat exchanger designs, namely, constant curvature heat exchanger with baffle and variable curvature heat exchanger. The design has been evaluated by referring to the performance evaluation coefficient (PEC); furthermore, the convection coefficient h has been taken into consideration as well. The idea is to perform numerical studies via computational fluid dynamics package and evaluate the performance of the spiral tube heat exchanger designs. PEC is the relationship between the heat exchange intensity of the heat exchanger and the flow resistance of the working fluid. The results show that the PEC evaluation index of the heat exchanger is the best when the spiral diameter of the heat exchange tube is 120 mm, and with the increase of the tube diameter and pitch, the overall performance of the heat exchanger decreases. The research on heat transfer enhancement of heat exchangers was carried out, and various spiral tube heat exchangers were designed based on the structure of spiral heat exchange tubes. The variable curvature heat exchanger has better overall performance than the baffle constant curvature heat exchanger. Compared to the single-variable curvature and the double-variable curvature, the maximum PEC difference of them does not exceed 0.01, and the double-variable curvature is more sufficient in volume utilization, and it can save about 13% volume. Considering the use requirements of the actual vehicle waste heat recovery system, the double-variable curvature spiral tube heat exchanger is more suitable for practical engineering applications than the single-variable curvature spiral tube heat exchanger.
Activated biochar (ABC) was prepared from typical plant/animal biochar (pig bone biochar/corn stalk biochar) by optimizing the gas production characteristics of anaerobic fermentation. The effects of the physical and chemical properties (specific surface area, surface functional group and conductivity) of ABC on the gas production characteristics of anaerobic fermentation were investigated. The results showed that the effect of pig-bone activated biochar (PABC) on anaerobic fermentation gas production characteristics was better than that of corn-stalk activated biochar (CABC). The peak period of gas production or methane production was up to 4 days earlier than that of the control group, and the cumulative methane production was up to 68% higher; this can shorten the fermentation period for up to 7 days, and the effect of stabilizing pH is better. In addition, the surface functional groups are not the dominant factors affecting the gas production characteristics, but the effects of conductivity and specific surface area cannot be neglected. For most experimental groups, when the specific surface area of PABC is more than 90 m2/g and the specific surface area of CABC is more than 100 m2/g. Methane production increases with the specific surface area increases and the controllable range of CBAC is relatively wider than that of PBAC. When the conductivity of CABC is more than 650 μS/cm and the conductivity of PABC is more than 1000 μS/cm, the conductivity has a positive correlation with methane production.
While Battery Electric Vehicles (BEVs) offer environmental benefits by reducing carbon emissions during use, their range remains limited compared to conventionally fuelled vehicles. This paper focuses on identifying factors that directly influence BEV range and explores strategies to mitigate range anxiety among potential users. Specifically, it reviews the impact of battery cell characteristics and vehicle lightweighting. Using the WLTP Class 3B drive cycle, energy consumption and Depth of Discharge (DoD) were evaluated across various battery capacities. Multiple Lithium-Ion battery models were simulated to analyse discharge behaviour, while vehicle mass composition was examined to assess the effectiveness of lightweighting in extending driving range. A lower initial State of Charge (SoC) and a standard discharge rate were used to estimate the remaining range, highlighting an approximate gain of up to 6 km at lower DoD levels. This work aims to accurately demonstrate how battery technology and structural weight impact energy consumption and usable range in BEVs. Current modelling approaches often overlook the relationship between driver discomfort and battery performance metrics. The main contribution is to address the gap by integrating Li-ion discharge modelling with vehicle dynamics to estimate range and compare cell characteristics. The ultimate goal is to support cost-effective strategies for increasing BEV usability, aligning them more closely with conventional vehicle expectations and enhancing journey flexibility.
6 January 2022 in Computational Intelligence and Neuroscience
This paper deals with adaptive nonlinear identification and trajectory tracking problem for model free nonlinear systems via parametric neural network (PNN). Firstly, a more effective PNN identifier is developed to obtain the unknown system dynamics, where a parameter error driven updating law is synthesized to ensure good identification performance in terms of accuracy and rapidity. Then, an adaptive tracking controller consisting of a feedback control term to compensate the identified nonlinearity and a sliding model control term to deal with the modeling error is established. The Lyapunov approach is synthesized to ensure the convergence characteristics of the overall closed-loop system composed of the PNN identifier and the adaptive tracking controller. Simulation results for an AFS/DYC system are presented to confirm the validity of the proposed approach.
The magnitude of pollution generated by public transport is significant and poses a major obstacle to the advancement of the Paris Climate Agreement. Therefore, it is crucial to adopt clean energy sources to drive bus vehicle, with fuel cells being an eco-friendlier option. Merely examining the fuel cell stack in isolation does not provide a viable solution to the problem. It is imperative to study the complete system, encompassing the Proton Exchange Membrane Fuel Cell (PEMFC) integrated with the load, specifically in the context of public transports. The aim of this paper is to design a control system model for a Proton Exchange Membrane Fuel Cell (PEMFC) within MATLAB Simulink environment. The model is designed to simulate the operating state of PEMFC under the conditions of urban road vehicle loads, which can reach up to 60kW. The key feature of PEMFC control system comprises the gas supply system and temperature regulator. For gas supply system, a PID control method is employed to regulate the anode pressure and maintain an acceptable pressure difference with the Cathode. For temperature regulator, water is used as a coolant to maintain the temperature level within the reactor. The fuel cell temperature is then kept within an acceptable range through feedback linearization control, further enhancing the stability of the system. The gas supply system and temperature regulator is incorporated into a system coordinator, which ensure stability of power output, capable of providing for up to 60kW.