Data supplement for a soft sensor using a new generative model based on a variational autoencoder and Wasserstein GAN

In industrial process control, measuring some variables is difficult for environmental or cost reasons. This necessitates employing a soft sensor to predict these variables by using the collected data from easily measured variables. The prediction accuracy and computational speed in the modeling procedure of soft sensors could be improved with adequate training samples. However, the rough environment of some industrial fields makes it difficult to acquire enough samples for soft sensor modeling. Generative adversarial networks (GANs) and the variational autoencoder (VAE) are two prominent methods that have been employed for learning generative models. In the current work, the VA-WGAN combining VAE with Wasserstein generative adversarial networks (WGAN) as a generative model is established to produce new samples for soft sensors by using the decoder of VAE as the generator in WGAN. An actual industrial soft sensor with insufficient data is used to verify the data generation capability of the proposed model. According to the experimental results, the samples obtained with the proposed model more closely resemble the true samples compared with the other four common generative models. Moreover, the insufficiency of the training data and the prediction precision of soft sensors could be improved via these constructed samples.     

Using semantic web technologies to access soft AEC data

Building related data tends to be generated, used and retained in a domain-specific manner. The lack of interoperability between data domains in the architecture, engineering and construction (AEC) industry inhibits the cross-domain use of data at an enterprise level. Semantic web technologies provide a possible solution to some of the noted interoperability issues. Traditional methods of information capture fail to take into account the wealth of soft information available throughout a building. Several sources of information are not included in performance assessment frameworks, including social media, occupant communication, mobile communication devices, occupancy patterns, human resource allocations and financial information.The paper suggests that improved data interoperability can aid the integration of untapped silos of information into existing structured performance measurement frameworks, leading to greater awareness of stakeholder concerns and building performance. An initial study of how building-related data can be published following semantic web principles and integrated with other ‘soft-data’ sources in a cross-domain manner is presented. The paper goes on to illustrate how data sources from outside the building operation domain can be used to supplement existing sources. Future work will include the creation of a semantic web based performance framework platform for building performance optimisation.     

控制系统的腐蚀与防护

分析了影响集散控制系统腐蚀的环境因素,并提出以电子元器件为核心的控制系统的防腐蚀措施.     

基于曲波变换的彩色图像零水印研究

提出了一种基于曲波变换的彩色图像零水印构造和检测算法。利用原图像进行USFFT算法的曲波变换（Curvelet Transform）和离散余弦变换（DCT）得到的系数进行二值化处理,构造具有一定鲁棒性的水印,解决了水印嵌入时鲁棒性与隐蔽性之间的矛盾,更好地保护了原图像信息。该算法通过抗攻击测试和识别测试,证明其具有性能稳定、可行性高的特点。     

手掌静脉识别系统的研究与设计

手掌静脉识别技术是静脉识别领域的新兴课题,原理相当简单,但具体实现有很多的挑战,包括如何设计一个能获得手掌静脉图像的采集实验装置和能够进行精确识别的算法等;对手掌静脉识别系统进行了初步的分析与研究,在研究的基础上为手掌静脉识别系统提供了一些硬件解决方案,包括如何选取CCD摄像机、怎样设计光源系统等,设计了手掌静脉采集实验装置,完成了手掌静脉识别系统的整体搭建,并采集到了较清晰的手掌静脉图像。     

并行采集系统触发晃动实时校正技术研究

在并行实时采集系统,大量的采用了并行时间交替采样和数据分相存储技术,但采样数据的并行存储将引起触发抖动问题,严重降低了整个系统的性能。在分析触发抖动原因的基础上,提出了采用时间内插计数法,通过实时放大并测量触发信号和并行采样时钟的时间间隔,对触发晃动进行校正,从而达到降低触发抖动,提高波形显示稳定性的目的,并结合工程应用,在采用8路拼合的2GSPS实时采样数字存储示波器中实现了对触发晃动的校正,最后给出了该功能的性能测试结果。     

A framework for modeling,animating, and morphing textured implicit models

This paper presents a framework for modeling, animating, and morphing textured implicit models. Our hierarchical skeletal implicit surface model incorporates key-frame animation and procedural solid texturing in a unified and coherent way. Our system enables the designer to create complex special effects by synchronizing shape, animation, and texture transformations.     

Tuning the viscosity of halogen free bulk heterojunction inks for inkjet printed organic solar cells

For the solution processing of organic photovoltaics on an industrial scale, the exclusion of halogenated solvents is a necessity. However, the limited solubility of most semiconducting polymer/fullerene blends in non-halogenated solvents results in ink formulations with low viscosities which poses limitations to the use of roll-to-roll compatible deposition processes, such as inkjet printing. We propose to add polystyrene as a rheological modifier to increase the viscosity of bulk heterojunction (BHJ) non-halogenated inks. The printing and performance of P3HT/PCBM photoactive layer inks are characterized as a function of polystyrene concentration and three different molecular weights. Addition of 1 wt% polystyrene provided a near two-fold gain in viscosity, with the largest viscosity gains coming from the polymer with the highest molecular weight. However, this coincided with greater viscoelastic behavior, which reduced the jetting performance of the inks. Differences in solvent compatibility of the polystyrene/P3HT/PCBM ternary blend resulted in phase separation upon layer drying, whereby polystyrene segregated to the layer-air interface to form an isolated domain or network like topology. Nevertheless, a 1.7-fold increase in dynamic viscosity was obtained for devices with printed BHJ layers containing polystyrene at the expense of a 20% reduction in OPV performance. The improved viscosity and good printing behavior achieved with small additions of polystyrene demonstrates its potential to overcome the limited viscosity resulting from typical non-halogenated ink formulations for semiconducting polymers. These results offer a step forward to the industrialization of inkjet printing as an effective deposition technique for functional layers of organic electronics.     

基于Matlab-GUI数控机床热误差补偿的仿真系统

为了使数控机床加工精度得以提高,对数控机床热误差补偿系统进行研究。在建立基于BP神经网络数控机床热误差补偿模型的同时,运用Matlab-GUI工具设计了具有通用性交互式数控机床热误差补偿的仿真系统,该系统可使热误差补偿更具有实时性、在线高效性和补偿系统操作可视化。     

Evolutionary-Programming-Based Kalman Filter for Discrete-Time Nonlinear Uncertain Systems

Some observations and improvements on the conventional Kalman filtering scheme to function properly are presented. The improvements can be achieved using the minimal principle evolutionary programming (EP) technique. A new linearization methodology is presented to obtain the exact linear models of a class of discrete-time nonlinear time-invariant systems at operating states of interest, so that the conventional Kalman filter can work for the nonlinear stochastic systems. Furthermore, a Kalman innovation filtering algorithm and such an algorithm based on the evolutionary programming optimal-search technique are proposed in this paper for discrete-time time-invariant nonlinear stochastic systems with unknown-but-bounded plant uncertainties and noise uncertainties to find a practically implementable “best” Kalman filter. The worst-case realization of the discrete-time nonlinear stochastic uncertain systems represented by the interval form with respect to the implemented “best” nominal filter is also found in this paper for demonstrating the effectiveness of the proposed filtering scheme.