Search

Nowadays, the commercial potential of live e-commerce is being continuously explored, and machine vision algorithms are gradually attracting the attention of marketers and researchers. During live streaming, the visuals can be effectively captured by algorithms, thereby providing additional data support. This paper aims to consider the diversity of live streaming devices and proposes an extremely lightweight and high-precision model to meet different requirements in live streaming scenarios. Building upon yolov5s, we incorporate the MobileNetV3 module and the CA attention mechanism to optimize the model. Furthermore, we construct a multi-object dataset specific to live streaming scenarios, including anchor facial expressions and commodities. A series of experiments have demonstrated that our model realized a 0.4% improvement in accuracy compared to the original model, while reducing its weight to 10.52%.

The vehicle-road collaborative intelligence approach has become an industry consensus. It can efficiently tackle the technical hurdles and reduce the performance requirements and costs of on-board perception and computing devices. There is a need for in-depth quantitative studies to optimize the allocation of vehicle-road intelligent capabilities for collaborative intelligence. However, current research tends to focus more on qualitative analysis, and there is little research on the redistribution of vehicle and roadside intelligent capabilities. In this paper, we present a model for distributing perception and computing capabilities between vehicle-side and roadside, ensuring to meet the needs of various autonomous driving levels. Meanwhile, the collaborative intelligence approach will also introduce the costs of intelligent infrastructure deployment, energy, and maintenance. Different roads have varying scene characteristics and usage intensities. It is necessary to conduct a cost-effectiveness analysis of the intelligent deployment of different road types. A vehicle-road cost allocation model is developed based on the lifecycle traveled distance of vehicles and the lifecycle traffic flow of various roads to evaluate the function-cost effectiveness. Our study presents several vehicle-road intelligent schemes that meet the needs of various autonomous driving levels and selects Beijing for case analysis. The results indicate that primary intelligent infrastructure can reduce the lifecycle cost of the vehicle-side intelligent scheme for intermediate autonomous driving from ¥65,301 to ¥37,703, and advanced intelligent infrastructure can reduce the lifecycle cost for advanced autonomous driving from ¥126,938 to ¥42,180. Considering the distributed cost of vehicle-side and roadside, urban roads in Beijing have higher function-cost effectiveness compared to highways, especially urban expressways, which are expected to generate 43.3 times the vehicle-function-cost benefits after the advanced intelligent upgrades. The corresponding research findings can serve as a reference for city managers to make decisions on intelligent road deployment.

Developing electric vehicle (EV) energy storage technology is a strategic position from which the automotive industry can achieve low-carbon growth, thereby promoting the green transformation of the energy industry in China. This paper will reveal the opportunities, challenges, and strategies in relation to developing EV energy storage. First, this paper clarifies the strategic value and potential of developing EV energy storage under the carbon neutrality goal. Second, this paper demonstrates strategic opportunities and challenges during the development. Third, this paper proposes methods for creating a good market environment and business models. Finally, this paper suggests that relevant policies and regulations should be formulated and charts the course of technology development. The results show that EV energy storage technology has potential in terms of technology, the scale of development, and the user economy. The proposal of the carbon neutrality goal, the increasing market share of EVs, lower-cost and higher-efficiency batteries, etc., have all further accelerated the development of EV energy storage. The EV energy storage field should focus on developing battery technology, make advancements toward delivering longer cycle lives and improving the safety and availability of battery materials, and ramp up the R&D efforts with respect to developing vehicle-to-grid (V2G) management technologies. Simultaneously, it is necessary to create a business ecosystem centered on V2G operating platforms, constituting a process to which various players can contribute and achieve mutually beneficial results. It is also essential to formulate top-level strategic plans across industries and organizations, develop an electricity-trading mechanism as soon as possible, and promote the implementation of technical standards related to EV energy storage.

Temporal knowledge graphs (KGs) have recently attracted increasing attention. The temporal KG forecasting task, which plays a crucial role in such applications as event prediction, predicts future links based on historical facts. However, current studies pay scant attention to the following two aspects. First, the interpretability of current models is manifested in providing reasoning paths, which is an essential property of path-based models. However, the comparison of reasoning paths in these models is operated in a black-box fashion. Moreover, contemporary models utilize separate networks to evaluate paths at different hops. Although the network for each hop has the same architecture, each network achieves different parameters for better performance. Different parameters cause identical semantics to have different scores, so models cannot measure identical semantics at different hops equally. Inspired by the observation that reasoning based on multi-hop paths is akin to answering questions step by step, this paper designs an Interpretable Multi-Hop Reasoning (IMR) framework based on consistent basic models for temporal KG forecasting. IMR transforms reasoning based on path searching into stepwise question answering. In addition, IMR develops three indicators according to the characteristics of temporal KGs and reasoning paths: the question matching degree, answer completion level, and path confidence. IMR can uniformly integrate paths of different hops according to the same criteria; IMR can provide the reasoning paths similarly to other interpretable models and further explain the basis for path comparison. We instantiate the framework based on common embedding models such as TransE, RotatE, and ComplEx. While being more explainable, these instantiated models achieve state-of-the-art performance against previous models on four baseline datasets.

Technical route decision making of intelligent driving has always been the focus of attention of automotive enterprises and even the industry. Firstly, this study combs the main technical routes of intelligent driving at different levels from three dimensions: development strategy, intelligence allocation and sensor combination. Then, the methodology of technical component combination is designed to disassemble different technical routes into corresponding technical component combinations. Finally, an improved evaluation model of total cost of ownership of intelligent driving is developed and the total cost of ownership of intelligent driving system under different technical routes is compared. For the development strategy, even if the function superposition can follow some research and development achievements of low-level intelligent driving, scenario-driven is still the option with lower cost and better sustainability. For intelligence allocation, collaborative intelligence can effectively reduce the cost of the vehicle compared with single-vehicle intelligence by up to 46%, but the cost reduction depends on the original on-board hardware. For sensor combination, the multi-source fusion always has the cost advantage compared with vision-only, but the advantage is more obvious in the medium-level and high-level stage of single-vehicle intelligence.

There is a need for in-depth studies of autonomous vehicle safety that evaluate the effectiveness of safety functions and different “atomic” technology combinations for vehicles and roads. In this paper, we provide a crash avoidance effectiveness evaluation model for autonomous vehicles enabled with different sensor combinations based on multiple variables of 14 different “atomic” sensing technologies on the vehicle side and road side, 52 safety functions, and 14 accident types. Meanwhile, a cost-sharing model is developed based on the traveled distance during the life cycle of vehicles and based on the traffic flow over the life cycle of roads to evaluate the unit cost per km of different “atomic” technology combinations. The results clearly show that the cost increases with the addition of “atomic” sensing technologies on the vehicle side, while an increase in crash avoidance effectiveness decreases. It is necessary to switch to V2X and to introduce roadside “atomic” technology combinations to realize better safety effectiveness at a lower cost for vehicles. In addition, a map that covers the safety effectiveness and cost per kilometer of all “atomic” technology combinations is calculated for decision-makers to select combinations under the preconditions of cost and safety.

The Measurement-While-Drilling (MWD) system, composed of a tri-axial magnetometer and a tri-axial accelerometer, is widely used in the Horizontal Directional Drilling machine in coal mines. This system can provide attitude information of each measuring point in the borehole, which will eventually allow the trajectory of the borehole to be drawn. The attitude information, however, showed a low-level accuracy, due to the sensor’s imperfection and mounting errors. The accuracy worsened when low-cost sensors were employed, as they had higher random noise. Therefore, an exploration of ways to eliminate the sensor imperfection and mounting tolerance as well as to suppress the noise is needed. In this paper, a feasible calibration approach was designed to address these issues. This new approach combined three foundational calibration algorithms, including the ellipsoidal fitting method, the planar fitting method, and the inner product invariance method. The traditional ellipsoidal fitting method and planar fitting method were optimized by using the recursive least square criterion and omitting the steps of sample data acquisition, respectively. In addition, the noise suppression method was involved in our approach to improve the calibration accuracy. The numerical simulation results showed that the number of sampling points decreased significantly, but the accuracy of the azimuthal angle and the pitch angle fully met the engineering requirements. The experimental results showed that the pitch angle error was reduced by less than 0.5°, and the azimuth error was also reduced by less than 2.5°. It should be noted that this new approach could be implemented without the help of other expensive auxiliary equipment.

There are big differences between the driving behaviors of intelligent connected vehicles (ICVs) and traditional human-driven vehicles (HVs). ICVs will be mixed with HVs on roads for a long time in the future. Different intelligent functions and different driving styles will affect the condition of traffic flow, thereby changing traffic efficiency and emissions. In this paper, we focus on China’s expressways and secondary motorways, and the impacts of the ‘single-lane automatic driving system’ (SLADS) on traffic delay, road capacity and carbon dioxide (CO2) emissions were studied under different ICV penetration rates. Driving styles were regarded as important factors for scenario analysis. We found that with higher volume input, SLADS has an optimizing effect on traffic efficiency and CO2 emissions generally, which will be more significant as the ICV penetration rate increases. Additionally, enhancing the aggressiveness of driving behavior appropriately is an effective way to amplify the benefits of SLADS.

Developing new energy vehicles (NEVs) is essential for China’s automotive industry to achieve carbon peak and carbon neutrality goals. The development of a NEV platform is an effective means for automotive companies to balance the development cost, development time, and product performance of NEVs. However, there is no clear solution to choosing new energy vehicle platform development strategies and models for automotive companies. This paper mainly studies the significance of NEV platform development, the classification and characteristics of NEV platforms, and the development strategies and trends of NEV platforms for automotive companies. The study results found that choosing a new dedicated electric platform (NDEP) is inevitable for the latest automotive companies, such as TESLA Motors. An adapted electric platform (AEP) is a temporary solution that meets the dual credits policy. It lacks competitiveness and has been gradually eliminated for the traditional automotive companies. The new dedicated electric platform is a long-term development solution when comprehensively considering the market, technology, and policy. The compatible platform (CP) is a transitional solution when considering the development trend of automotive powertrain, the market size of NEVs, and the platform technology of NEVs. Besides, joint development and shared use is the primary development model for the automotive enterprise in the future. Finally, companies should increase their research and development efforts on NEV architecture platforms to maximize platform-based development’s scale effect and application value. The research can provide strategic guidance for automotive companies to develop NEV platforms.

Battery operating data of electric vehicles is becoming increasingly quantified and complicated. A data analysis platform is necessary to excavate high-value battery status information for more efficient battery management. This paper proposes a Flask framework and Pyecharts-based lithium-ion data analysis and visualization platform. The design processes including the front-end and back-end frameworks, data preprocessing, data visualization, and data storage are elaborated. In the proposed data platform, a case study of battery state of charge estimation using different machine learning methods is demonstrated, and most of the estimation errors are less than 2.0%, highlighting the effectiveness of the platform.

Wireless power transfer (WPT) is becoming popular increasingly in stationary electric vehicle (EV) charging. Various coil structures were proposed to improve the coupling characteristics, and polarized couplers have been proven to have better performance. Considering the varying spatial scales of transmitting and receiving, coils will alter the mutual inductance, further affecting the output power and transmission efficiency; therefore, it is crucial to calculate the mutual inductance of polarized couplers with variable offset for WPT system design. However, given the complex structure and the various excitation conditions of polarized couplers, the solving process based on the finite element model is time-consuming and resource intensive, therefore it is necessary to develop analytical models of mutual inductance for polarized couplers under misalignment. In this paper, the analytical models of the two commonly used polarized couplers with a Double-D polarized coil (DDP) or a Bipolar polarized coil (BP) on both sides under misalignment along any direction under different excitation conditions are proposed based on dual Fourier transformation. The mutual inductance characteristics of the two polarized couplers under misalignment can be investigated based on the proposed analytical models and finite element models, respectively. The results show that the mutual inductance of BP-BP coupler with in-phase current excitation mode is greater and more stable, and the method based on the analytical model is timesaving. Finally, the prototype of the WPT system with the two polarized couplers has been built, and experiments have also been carried out to verify the accuracy of the analytical models.

With the rapid development of new energy vehicles (NEVs) industry in China, the reusing of retired power batteries is becoming increasingly urgent. In this paper, the critical issues for power batteries reusing in China are systematically studied. First, the strategic value of power batteries reusing, and the main modes of battery reusing are analyzed. Second, the economic benefit models of power batteries echelon utilization and recycling are constructed. Finally, the economic benefits of lithium iron phosphate (LIP) battery and ternary lithium (TL) battery under different reusing modes are analyzed based on the economic benefit models. The results show that when the industrial chain is fully coordinated, LIP battery echelon utilization is profitable based on a reasonable scenario scheme. However, the multi-level echelon utilization is only practical under an ideal scenario, and more attention should be paid to the first level echelon utilization. Besides, the performance matching of different types of batteries has a great impact on the echelon utilization income. Thus, considering the huge potentials of China’s energy storage market, the design of automobile power batteries in the future should give due consideration to the performance requirements of energy storage batteries. Moreover, the TL battery could only be recycled directly, while the LIP has the feasibility of echelon utilization at present. At the same time, it will strengthen the cost advantage of the LIP battery, which deserves special attention.

With the phasing down of subsidies, China has launched the new energy vehicle (NEV) credit regulation to continuously promote the penetration of electric vehicles. The two policies will coexist through 2020 and definitely pose a dramatic impact on the development of the Chinese and even the global electric vehicle market. However, few studies have systematically investigated the relationship between the two policies as well as the synergistic impacts during the overlap period. This paper interprets the rationales of China’s subsidy policy and NEV credit regulation and establishes a bottom-up model to estimate the synergistic impacts of the two policies on the technological trends of battery electric vehicles (BEVs) from the perspective of credit cost-effectiveness. The results suggest that the subsidy policy still maintains strong support for the development of electric vehicles in China. For small BEVs whose driving ranges are higher than 300 km, subsidies even account for 40⁻50% of the manufacturing cost. In addition, we conclude that the two policies will complement each other in the transitional period and small BEVs are preferred by both policies. Under the NEV credit regulation, 350 km will consistently be the optimal driving range, which will definitely limit the development of other ranges. With the addition of the subsidy, the limitation will be amended in the short run. However, the effect of the subsidy is decreasing and is going to be canceled after 2020, so the focus should be on the optimization of the NEV credit regulation.

The explosion of the vehicle market in China has caused a series of problems, like energy security, climate change, air pollution, etc. The deployment of electric vehicles (EVs) is considered an effective solution to address these problems. Thus, both the state and local governments in China have launched some policies and incentives to accelerate the development of EVs and the EV industry. Do EVs can effectively solve these problems in short term, viewed from the fleet point? Based on China’s most up-to-date deployment plan for EVs, this paper analyzes the energy consumption and greenhouse gas (GHG) emissions caused by China’s road transport sector in three different scenarios. The results indicate that, based on current planning, the energy consumption and GHG emissions of the whole fleet will peak in 2025 and 2027, at the level of around 403 mtoe (million tons of oil equivalent) and 1763 mt CO2 eq. (million tons of CO2 equivalent), respectively. The introduction of EVs will significantly reduce the reliance on fossil fuel in the long term, with increasing ownership, while, in the short term, the fuel economy regulation will still play a more important role. Policy makers should continually pay attention to this. Meanwhile, commercial vehicles, especially heavy-duty trucks will account for a bigger and bigger proportion in the energy consumption and GHG emissions of the whole fleet. Thus, to some extent the focus should shift from passenger vehicles to commercial vehicles. More measures could be implemented.

Energy efficiency is one of the key factors affecting energy consumption and greenhouse gas (GHG) emissions. By focusing on China’s transport sector, this study comprehensively reviews and compares the energy efficiency performance of passenger vehicles, light-duty commercial vehicles, commercial road transport, commercial water transport, aviation transport and railway transport, and identifies the opportunities for further energy efficiency improvements. It is found that railway transport exhibited the greatest improvement in energy efficiency during the past decade, which was mainly driven by progress in its electrification. Passenger vehicles have also experienced considerable energy efficiency improvements, which can be mainly attributed to the establishment of mandatory fuel consumption standards. In contrast, commercial road transport has shown the least improvement, due to insufficient policy implementations. Based on the analysis, it is recommended that, as China’s present policy framework to improve energy efficiency in the transport sector is generally effective, it should be consistently maintained and successively improved. Electrification represents a major opportunity for improvement of energy efficiency in the transport sector. Such potential should be fully tapped for all transport modes. Greater effort should be put into improving the energy efficiency of commercial road transport. The policy instruments utilized to improve the energy efficiency of heavy-duty vehicles should be as intensive and effective as the policy instruments for passenger vehicles.

Despite the rich nutritional content of okara, the majority remains underutilized and discarded as food waste. In this study, solid-state fermentation of okara with food-grade fungi was performed to extract and solubilize any remnant nutrients locked within the lignocellulosic matrix to produce a nutrient-rich okara fermentate. Fermented okara media (FOM) was used as the sole nutrient source for growing marine diatom, Phaeodactylum tricornutum. Results have shown a two-fold increase in biomass production when grown on FOM (0.52 g L−1) as compared with conventional Guillard’s F/2 media (0.25 g L−1). Furthermore, cellular fucoxanthin content was enhanced significantly by two-fold to reach a final concentration of 15.3 mg g−1 compared to 7.3 mg g−1. Additionally, a significantly higher amount of polyunsaturated fatty acid (PUFA) was produced, particularly eicosapentaenoic acid (EPA) which yield has increased by nearly three-fold. Metabolomics analysis of intracellular contents in fermented okara culture revealed a significantly enhanced accumulation of nitrogenous metabolites, alongside the decrease in sugar metabolites as compared to F/2 culture, thus indicating metabolic flux towards pathways involved in cellular growth. This study demonstrated an innovative and low-cost strategy of using fermented okara as a nutritious substrate for achieving a sustainable media replacement for high density algal growth with a simultaneous enhancement of production in highly valued nutraceuticals, including fucoxanthin and EPA.