Deep Learning Based Data Fusion for Sensor Fault Diagnosis and Tolerance in Autonomous Vehicles

Environmental perception is one of the key technologies to realize autonomous vehicles.Autonomous vehicles are often equipped with multiple sensors to form a multi-source environmental perception system.Those sensors are very sensitive to light or background conditions,which will introduce a variety of global and local fault signals that bring great safety risks to autonomous driving system during long-term running.In this paper,a real-time data fusion network with fault diagnosis and fault tolerance mechanism is designed.By introducing prior features to realize the lightweight network,the features of the input data can be extracted in real time.A new sensor reliability evaluation method is proposed by calculating the global and local confidence of sensors.Through the temporal and spatial correlation between sensor data,the sensor redundancy is utilized to diagnose the local and global confidence level of sensor data in real time,eliminate the fault data,and ensure the accuracy and reliability of data fusion.Experiments show that the network achieves state-of-the-art results in speed and accuracy,and can accurately detect the loca-tion of the target when some sensors are out of focus or out of order.The fusion framework proposed in this paper is proved to be effective for intelligent vehicles in terms of real-time performance and reliability.     

Seismic fluid identification using a nonlinear elastic impedance inversion method based on a fast Markov chain Monte Carlo method

Elastic impedance inversion with high efficiency and high stability has become one of the main directions of seismic pre-stack inversion. The nonlinear elastic impedance inversion method based on a fast Markov chain Monte Carlo (MCMC) method is proposed in this paper, combining conventional MCMC method based on global optimization with a preconditioned conjugate gradient (PCG) algorithm based on local optimization, so this method does not depend strongly on the initial model. It converges to the global optimum quickly and efficiently on the condition that efficiency and stability of inversion are both taken into consideration at the same time. The test data verify the feasibility and robustness of the method, and based on this method, we extract the effective pore-fluid bulk modulus, which is applied to reservoir fluid identification and detection, and consequently, a better result has been achieved.     

改性丝瓜络对铜离子吸附的研究

在柠檬酸溶液中,以硫酸氢钠为催化剂,通过酯化反应制备了改性丝瓜络重金属离子吸附剂。研究了不同温度下其对Cu(Ⅱ)的静态吸附性能,测定了不同温度下的吸附曲线,并通过SEM及XRD对碱处理前后的丝瓜络进行了表征。结果表明,改性丝瓜络在不同温度下的吸附过程符合一级动力学模型;SEM分析表明碱处理后表面有明显的沟壑;XRD分析显示碱处理后丝瓜络结晶度降低了13.4%。     

Experimental Studies on Combustion Characteristics of Mixed Municipal Solid Waste

In our country, municipal solid wastes (MSW) are always burnt in their original forms and only a few pretreatments are taken. Therefore it is vital to study the combustion characteristics of mixed waste. In this paper, thermogravimetric analysis and a lab scale fluidized bed facility were used as experimental means. The data in two different experimental systems were introduced and compared. It took MSW 3-3.5 min to burn out in FB, but in thermogravimetric analyzer, the time is 20-25 min. It can be concluded that, in general, the behavior of a mixture of waste in TGA can be expressed by simple combination of individual components of the waste mixtures. Only minor deviations from the rule were observed. Yet, in Fluidized Bed, it was found that, for some mixtures, there was interference among the components during fluidized bed combustion.     

Molecular mechanisms for chemoprevention of colorectal cancer by natural dietary compounds

Colorectal cancer is one of the major causes of cancer-related mortality in both men and women worldwide. This review focuses on preventing the initiation and promotion of neoplastic growth in colorectal cancer, particularly with natural dietary compounds. Chemoprevention is defined as the use of natural dietary compounds and/or synthetic substances that can delay, prevent, or even reverse the development of adenomas, as well as the progression from adenoma to carcinoma. The molecular mechanisms of their chemopreventive action are associated with the modulation of signaling cascades, gene expressions involved in the regulation of cell proliferation, differentiation, and apoptosis and the suppression of chronic inflammation, metastasis, and angiogenesis. Here, we summarize the currently known targets and signaling pathways whereby natural dietary compounds interfere with the development of colorectal cancer, and thus providing evidence for these substances in colonic cancer chemopreventive action.     

Synergistic manipulation of micro-nanostructures and composition: anatase/rutile mixed-phase TiO2 hollow micro-nanospheres with hierarchical mesopores for photovoltaic and photocatalytic applications

The construction of nanocrystals with controllable composition and desirable micro-nanostructures is a well-known challenge. A combination of favorable composition and optimized micro-nanostructures can enhance the performance of a material significantly. Using TiO(2) as an example, we demonstrate here a facile approach to prepare anatase/rutile mixed-phase TiO(2) hollow micro-nanospheres with hierarchical mesopores. Our strategy relies on polymer-assisted assembly of ～ 5 nm nano-building blocks into three-dimensional hierarchical hollow micro-nanospheres in a mixed alcohol-water solution. This superior micro-nanostructure endows the sample with hierarchical mesopores and a high surface area of 106 m(2) g(-1). We also show that, due to the synergetic effects of the mixed-phase composition and the micro-nanostructures, the sample exhibited significantly improved photovoltaic performance and similar photocatalytic performance compared with the commercial Degussa P25. These results suggested that our sample has great potential for future photovoltaic and photocatalytic applications.     

Amazing ageing property and in situ comparative study of field emission from tungsten oxide nanowires

In this work, needle-shaping of tungsten oxide nanowires occurred during field emission characterization. Compared with nanowires with a flat apex, needle-shaped emitters showed a lower threshold field of 11.9 V μm(-1) for 1 mA cm(-2) and a higher emission current of 1120 μA at 16.2 V μm(-1). Most notably, the measured ageing current dramatically increased by more than four times until it slightly decreased, tending towards stability. In addition, the samples showed striking difference in their nonlinear Fowler-Nordheim plot before and after ageing tests. Selected area diffraction and transmission electron microscope characterizations were used to further study these amazing results.     

Integrate silver colloids with silicon nanowire arrays for surface-enhanced Raman scattering

A facile method to prepare uniform and reproducible surface-enhanced Raman scattering (SERS) substrates is presented. Quasi-spherical silver colloids prepared by microwave heating and wafer-scale uniform silicon nanowire (SiNW) arrays fabricated via wet chemical etching were united together as SERS substrates. The novel SERS substrates displayed stronger Raman enhancement than conventional silver colloids as well as outstanding uniformity and reproducibility in our experiments. In addition, it was found that the cross section of SiNW arrays possessed stronger enhancement activity than the front side. The enhancement effects of two adjacent SiNWs (as a simplification of SiNW arrays) were evaluated by the finite difference time domain (FDTD) method.