A conditional classification recurrent RBM for improved series mid-term forecasting

In the context of human-robot and robot-robot interactions, the better cooperation can be achieved by predicting the other party’s subsequent actions based on the current action of the other party. The time duration for adjustment is not sufficient provided by short term forecasting models to robots. A longer duration can by achieved by mid-term forecasting. But the mid-term forecasting models introduce the previous errors into the follow-up forecasting and amplified gradually, eventually invalidating the forecasting. A new mid-term forecasting with error suppression based on restricted Boltzmann machine(RBM) is proposed in this paper. The proposed model can suppress the error amplification by replacing the previous inputs with their features, which are retrieved by a deep belief network(DBN). Furthermore, a new mechanism is proposed to decide whether the forecasting result is accepted or not. The model is evaluated with several datasets. The reported experiments demonstrate the superior performance of the proposed model compared to the state-of-the-art approaches.

     

Intrinsically patterned electrical systems: physical requirements and experimental demonstration

Microsystem Technologies - This paper introduces a method of replicating electrical circuits through a series of specific requirements as part of a design methodology referred to as Intrinsically...     

The fractal effect of irregularity of crack branching on the fracture toughness of brittle materials

Microstructural observations of brittle materials indicated that a variety of microdefect events can be responsible not only for inelastic behaviour, but also for macroscopic crack front irregularity. This irregularity produces an increase in the fracture toughness of the material. In this paper, this irregularity is analysed by fractal geometry in a very simple manner; a fractal model of crack branching is established. Both microscopic and macroscopic analytical results show that the toughness can be raised appreciably as a fractal geometric effect of the irregularity.

---

Résumé Des observations microscopiques sur des matériaux fragiles ont montré qu'une variété d'évènements à l'échelle du microdéfaut peuvent être responsables non seulement du comportement inélastique, mais aussi de l'irrégularité du front d'une fissure macroscopique. Cette irrégularité provoque un accroissement de la ténacité à la rupture du matériau. Dans cette étude, on analyse de manière très simple cette irrégularité par fractogéométrie (Mandelbrot) et on établit un modèle fractal relatif à une fissure qui se ramifie. Les résultats de l'analyse microscopique et macroscopique montrent qu'un effet fractogéométrique de l'irrégularité du front de fissure est d'accroitre de manière appréciable la ténacité.

     

CAD与CAPP集成研究回转体类零件特征识别

本文研究了回转体轴类,轴套类零件的特征识别。对这类零件常用的特征单元进行了定义,描述了这类零件的特征模型:介绍了它的识别方法和特征参数定义方法。     

Characterization of ultrafine La x Sr1−x MnO3 powder prepared by spray pyrolysis

The characterization of La _x Sr_1−x MnO₃ powders produced by spray pyrolysis using scanning electron microscopy (SEM) and transmission electron microscopy (TEM) observation, specific surface area (Brunauer-Emett-Teller), and particle size distribution measurements shows that the resultant large particles are loose agglomerates consisting of many small particles. However, the sintered tiny particles can form hard agglomerates, and the particle size increases remarkably. The structures of the powders before and after sintering were identified by x-ray diffraction (XRD). The study of the electrical property of the powder shows that the powder is a metallic conductor. In a reducing atmosphere, the powder can be decomposed. When the powder is cofired with yttria-stabilized zirconia 5% (YSZ) powder at 1200 °C for 5 h, no new phase is produced, and the powder remains a single provskite hexagonal-rhombohedral structure.     

FORMATION OF MANGANESE SILICIDE THIN FILMS BY SOLID PHASE REACTION

1. IntroductionThe transition metal silicides have attraeted much attention because of their potentialapplicatiOIl in very large scale integration (VLSI) de.ice[1]. Near-noble metal silicides canbe used as Schottky al1d ohn1ic col1tacts in silicon-based d…     

多元酚——甲醛树脂中游离酚,游离醛含量的测定

多元酚－－甲醛树脂是本院开发的热固粘接剂新产品，本文给出了这一产品技术指标中游离酚、游离醛含量的测定方法，并对方法进行了讨论。