Search

Durability, or sometimes called lifetime of fuel cell stack, is the prime parameter of the polymer electrolyte exchange membrane fuel cell (PEMFC) electrical vehicles. Vehicle operations include some driving state which will affect the output behavior of fuel cell stack. Some key driving states are analyzed, and they have significant effects on the durability of PEMFC stacks. Released durability test protocols are reviewed and compared from based on these key driving states. These durability test protocols can be good references on evaluation of fuel cell stack and development of the fuel cell electrical vehicle (FCEV).

Fuel cell vehicle actual operation condition is relatively complex, fuel cell electric stack is under the major influence of operating conditions, because of dynamic road condition, thermal management is a particularly big design difficulty for the fuel cell passenger cars. It is important to ensure the fuel cell stack’s temperature is controlled within a reasonable range under the heavy load work, but it is easy to produce the low temperature in the process of condition switched and in low load, then to result the performance decrease of the fuel cell stack due to the working temperature low, this paper aiming at these problems, has carried on the real road vehicle testing data analysis, and make a optimization using a multidimensional fuzzy control method based on the original water pump control strategy, to improve the water pump control on the adaptability of different working conditions, through the actual road testing, on the premise of guarantee the stack’s temperature within a reasonable range, improve the average water temperature of the stack, to obtain the ideal effect, effectively improve the stacks performance in the different kinds of operating conditions for FCEV.

The proton exchange membrane fuel cell (PEMFC) is one of promising zero emission tools which are applied in the automobile. The PEMFC system is the integration which convert the chemical energy of hydrogen to the electricity and provide the driving force to the vehicle. The hydrogen recirculation loop is commonly used in the vehicle fuel cell system to get a higher fuel consumption efficiency. However, the block issues can happen in the hydrogen recirculation loop and the performance of fuel cell system decreases. The failure mode and mechanisms caused by block issues in hydrogen recirculation loop are shortly reviewed including the water management and nitrogen blanketing. These problems may cause the fuel starvation, carbon corrosion and fuel cell system performance decreasing. Regard to the response option, some counter measures are adapted including the hydrogen purge and hydrogen oscillation.

The vehicle fuel cell works with complex operating conditions. It is important to monitor the water content of the fuel cell to prevent the fuel cell from dry-out and flooding. However, few water content measurement techniques are suitable to be integrated in vehicles. Because the electrical test methods for resistance can be operated without modifying the fuel cell stack and water content in proton exchange membrane (PEM) has certain correlation with its resistance, the resistance-based water content measurement techniques have received extensive attentions. This article explained the basic concepts and resistance based online water content monitoring techniques in the fuel cell vehicle applications.

Online music recommender systems are becoming increasingly prevalent because of the popularity of digital music and music recommendation generally caters to users by discovering songs that match their preferences. However, these systems have to face a challenge: how to recommend new songs in a situation where prior knowledge is scarce. Some researches take auxiliary information into consideration in new recommendation approaches to deal with this problem. Nevertheless, they rarely pay attention to complex relationships among different feature spaces when they map those information to a latent space. To this end, this paper proposes an approach that uses non-linear transformation to integrate different auxiliary information into the songs latent representations. Unlike other studies which directly map auxiliary information to the feature space, the proposed music recommendation model (NeuTrans) maps different information features to low-dimensional vector representation by non-linear neural networks. Specifically, the NeuTrans separately employs matrix factorization and attribute network embedding to extract auxiliary information (historical interaction, network structure and attributes of songs). The feature space of different information is obtained by nonlinearly mapping the feature space of the songs. Experimental analysis on two real-world datasets shows that our framework outperforms the state-of-the- art approaches on Top-N music recommendation.

With the growing popularity of online social platforms, it has been universally recognized that incorporating social relations into recommender systems can usually alleviate the problem of data sparsity. However, social recommender systems based on explicit relations are not as successful as expected due to the noise and the social cold issue of explicit social links. The intuition of utilizing explicit relations is that users share similar preferences if they are friends in the social network. In fact, quite a lot of users who are distant from each other in the social network also have similar tastes. The user item network and the user social network can provide useful information that can complement each other, so that exploring the implicit friends using the heterogeneous network they formed would be more helpful. In this paper, we propose an approach IFSR to discover implicit friends over the heterogeneous network to improve the performance of social recommendation. To find out reliable implicit ties, we first model the system as a heterogeneous network upon which both the preferences and social information are coupled. Over the HIN, similarities between each pair of users can be quantified through network embedding based representation learning. To reduce the computational cost while preserving the information embedded in the original networks and uncover the latent information hiding in the HIN, several meaningful meta-paths over the HIN are designed to guide the process of random walks. Finally, the Top-K implicit friends are incorporated into a social bayesian ranking model to enhance the performance of item ranking. Experimental results on three datasets demonstrate IFSR outperforms the state-of-the-art methods and illustrate why the implicit friends are advantageous for social recommendation.

The recommendation systems have been widely employed due to the effectiveness on mitigating the information overload issue. At present, the recommendation systems have made great progress, but they are under the threat of shilling attack because of their open nature. Shilling attack is the way by which the attackers can manipulate the recommendation results and cause great harm to recommendation systems. Existing shilling attack detection models are mainly based on statistical measures to extract features like the rating deviation, which are generally susceptible to attack strategies. Once the attacker changes attack strategy, the detection model which is based on the statistical method may fail. Some researchers have identified that implicit features hidden in user-user interactions and user-item interactions can be utilized to solve the problem. Their research aims to learn potential relationship between users to update features. However, the research ignores the significance of learning features by employing label information. To solve this problem, in this paper, we propose a novel detection model, named BayesDetector, which takes not only the user-user and user-item interactions but also the label information into consideration in the process of learning user implicit features. Furthermore, to take full advantage of user labels, the Bayesian model is added to the feature learning. Experiments on two datasets, Amazon and Movielens, show that BayesDetector significantly outperforms the state-of-the-art methods.