A Fault Detection Method for Electric Vehicle Battery System Based on Bayesian Optimization SVDD Considering a Few Faulty Samples

Accurate and reliable fault detection is essential for the safe operation of electric vehicles.Support vector data description(SVDD)has been widely used in the field of fault detection.However,constructing the hypersphere boundary only describes the distribution of unlabeled samples,while the distribution of faulty samples cannot be effectively described and easilymisses detecting faulty data due to the imbalance of sample distribution.Meanwhile,selecting parameters is critical to the detection performance,and empirical parameterization is generally timeconsuming and laborious and may not result in finding the optimal parameters.Therefore,this paper proposes a semi-supervised data-driven method based on which the SVDD algorithm is improved and achieves excellent fault detection performance.By incorporating faulty samples into the underlying SVDD model,training deals better with the problem of missing detection of faulty samples caused by the imbalance in the distribution of abnormal samples,and the hypersphere boundary ismodified to classify the samplesmore accurately.The Bayesian Optimization NSVDD(BO-NSVDD)model was constructed to quickly and accurately optimize hyperparameter combinations.In the experiments,electric vehicle operation data with four common fault types are used to evaluate the performance with other five models,and the results show that the BO-NSVDD model presents superior detection performance for each type of fault data,especially in the imperceptible early and minor faults,which has seen very obvious advantages.Finally,the strong robustness of the proposed method is verified by adding different intensities of noise in the dataset.

Microstructure and mechanical properties of Al-10Si alloy modified with Al-5Ti

The microstructure, fracture morphology and mechanical properties of Al-10 Si alloy modified with Al-5 Ti were analyzed and tested by optical microscopy, scanning electron microscopy, and universal electronic testing machine. Compared with unmodified Al-10 Si alloy, the area fraction of α-Al phase in Al-10 Si alloy modified at 740 °C increased first and then decreased with the increase of added amounts of Al-5 Ti, and reached the maximum when the added amount of Al-5 Ti was 0.5 wt.%. When the modification temperature increased from 700 to 740 °C with Al-5 Ti being fixed at 0.5 wt.%, α-Al dendrites were refined obviously and the area fraction remarkably increased. Compared with unmodified Al-10 Si alloy, the ultimate tensile strength and elongation of the alloy modified at 740 °C with 0.5 wt.% Al-5 Ti increased by 9% and 49%, respectively. The fracture surface of modified alloy predominantly exhibited ductile fracture.

Explosive Synchronization in Complex Dynamical Networks Coupled with Chaotic Systems

Explosive synchronization (ES), as one kind of abrupt dynamical transitions in nonlinearly coupled systems, has become a hot spot of modern complex networks. At present, many results of ES are based on the networked Kuramoto oscillators and little attention has been paid to the influence of chaotic dynamics on synchronization transitions. Here, the unified chaotic systems (Lorenz, Lü and Chen) and R?ssler systems are studied to report evidence of an explosive synchronization of chaotic systems with different topological network structures. The results show that ES is clearly observed in coupled Lorenz systems. However, the continuous transitions take place in the coupled Chen and Lü systems, even though a big shock exits during the synchronization process. In addition, the coupled R?ssler systems will keep synchronous once the entire network is completely synchronized, although the coupling strength is reduced. Finally, we give some explanations from the dynamical features of the unified chaotic systems and the periodic orbit of the R?ssler systems.

Effects of annealing at 800 and 1000℃ on phase precipitates and hardness of Al_(7)Cr_(20)Fe_(x)Ni_(73)−x alloys

The effects of Fe content on the microstructure,phase constituents and microhardness of the as-cast,800℃or 1000℃-annealed Al_(7)Cr_(20)Fe_(x)Ni_(73)−x(x=13−66)alloys were investigated.Not all these alloys are composed of the single FCC phase.The BCC and B2 phases are found.It is confirmed that the BCC phase in the Al7Cr20Fe66Ni7 alloy is transformed from the FCC phase at about 900℃ during cooling.While in the 800℃-annealed Al7Cr20Fe60Ni13 alloy,the FCC phase is stable and the hardness decreases.After annealing at 1000℃,for the precipitation of the B2 particles,the Al content in the FCC phase decreases,which results in decreasing of the alloy hardness.Moreover,after annealing at 800℃,a small amount of Al-rich B2 particles precipitate at the phase boundary and some nanocrystal BCC phase precipitates in the FCC matrix,which increases the hardness of the Al_(7)Cr_(20)Fe_(x)Ni_(73)−x(x=41−49)alloys.These results will help to the composition design and processing design of the Al−Cr−Fe−Ni based high-entropy alloys.

一种用于DC-DC变换器的指数型斜坡补偿电路

本文设计了一种指数型斜坡补偿电路,适用于峰值电流模式降压型DC-DC变换器,该电路利用固定的斜坡补偿斜率与指数型反斜坡补偿斜率的效果叠加得到补偿斜率随占空比连续变化的指数型补偿斜率,能够在低占空比时提供较小的斜坡补偿斜率,减小斜坡补偿对变换器带载能力的限制,在高占空比时提供足够的补偿斜率防止电路产生次谐波震荡。电路采用0.35μm BCD工艺,利用Hspice进行仿真,在变换器输入3.3V,占空比66%的条件下,反斜坡补偿电压斜率在导通时间达到设定值后开始呈现指数变化,证明了所设计电路的正确性。

Analysis of the performance of optical frequency comb based on recirculating frequency shifter influenced by an Er-doped fiber amplifier

The factors that influence the generation of a high-quality optical frequency comb(OFC)based on a recirculating frequency shifter(RFS)due to the maximum output power and noise figure of Er-doped fiber amplifier(EDFA)are studied theoretically and experimentally.Based on the theoretical analysis,numerical simulations and experiments under different EDFA parameters have been carried out.The results show that the performance of the OFC based on a RFS can be improved effectively by optimizing the maximum output power and the noise figure of the EDFA.