Intelligent Control of Consolidation and Solidification Processes

Intelligent processing of materials (IPM) deals with the integration of process models and in situ sensors into an intelligent process controller to achieve desired material properties. IPM-based control systems recently have been developed for both consolidation and solidification processes. This article explores the application of models based on the finite- element method (FEM) to develop process actuation systems, to design process schedules and component shape, and to develop a control model with which to control the process. The results in this article were presented at the AeroMat ’93 Advanced Aerospace Materials/Processes Conference and Exposition, Anaheim, CA, 7–10 June 1993     

Thermal Monitoring of Self-Checking Systems

With the increasing power density in integrated systems resulting from scaling down, the occurrence of field failures due to overheating has considerably increased. Faulty operation can be prevented by on-line temperature monitoring. This paper deals with questions of on-line temperature monitoring in safety-critical systems. First the possible temperature sensors are reviewed and basic principles of self-checking systems including such sensors are detailed, then a new temperature sensor cell with extremely good parameters designed especially for DfTT applications is presented. The basic questions of integrating thermal sensors into self-checking systems are also discussed.     

光纤智能复合材料

对光纤型智能复合材料的工作原理，性能特点和应用前景作了介绍，并讨论了制造成型的技术问题。     

Echolocation — From range to outline segments

A ring of ultrasonic sensors mounted on a mobile robot is used to map a room. The sensors are modelled with an arc model: the object causing the reflection lies on an arc with radius equal to the range and arc angle equal to twice the beam angle. By fusing sensing with motion, a surface is displayed as a sequence of arcs. In this paper, the algorithm for obtaining outline segments from the arcs is presented.     

Target differentiation with simple infrared sensors using statistical pattern recognition techniques

This study compares the performances of various statistical pattern recognition techniques for the differentiation of commonly encountered features in indoor environments, possibly with different surface properties, using simple infrared (IR) sensors. The intensity measurements obtained from such sensors are highly dependent on the location, geometry, and surface properties of the reflecting feature in a way that cannot be represented by a simple analytical relationship, therefore complicating the differentiation process. We construct feature vectors based on the parameters of angular IR intensity scans from different targets to determine their geometry and/or surface type. Mixture of normals classifier with three components correctly differentiates three types of geometries with different surface properties, resulting in the best performance (100%) in geometry differentiation. Parametric differentiation correctly identifies six different surface types of the same planar geometry, resulting in the best surface differentiation rate (100%). However, this rate is not maintained with the inclusion of more surfaces. The results indicate that the geometrical properties of the targets are more distinctive than their surface properties, and surface recognition is the limiting factor in differentiation. The results demonstrate that simple IR sensors, when coupled with appropriate processing and recognition techniques, can be used to extract substantially more information than such devices are commonly employed for.     

Modeling Microwave Vacuum Drying Kinetics and Moisture Diffusivity of Carrot Slices

Carrot slices of 3.5 mm thickness were dried in a laboratory microwave vacuum dryer at five different microwave power density levels of 2, 4.66, 7.33, 10, and 12.66 W/g and at three vacuum chamber pressure levels of 6.66, 19.98, and 33.3 kPa to 4-6% d.b. moisture content. Inside the dryer the sample holding plate was rotated with the speed of 4 rpm for uniform microwaves application. The drying rates were increased with the increase in microwave power density at all pressure levels and the Page model was found to be the most suitable model to predict the drying behavior of carrot slices at all process conditions. The Page model drying rate constant (k, min^-1) showed high correlation with microwave power density at constant pressure by a power law equation and showed a logarithmic relationship with the microwave power density and pressure. Similar to the drying rate constant, the average moisture diffusivity at constant pressure was found to be function of microwave power density by power law equation as well as was also dependent on the power density and pressure by a logarithmic relationship.     

锅炉除渣机转速报警器的设计

针对贵州茅台酒厂股份有限公司锅炉除渣机经常卡死,导致煤渣不能及时从锅炉燃烧室排出,从而影响正常作业的问题,设计出以微控制器为核心的锅炉除渣机转速报警器。     

异类传感器实时信息融合的STMHM算法

异类传感器实时信息融合由于两类设备的数据率不同和数据误差的限制,一直未得到有效解决,提出一种空时二维多假设模型(STMHM)算法来解决该问题。设计的融合数据模型,将异类传感器的测量数据映射在二维直角坐标系下;按照新的融合数据模型分别构建两类传感器的目标量测空间和融合空间;设计量测空间时间初始化方法和目标实体空间的滤波算法;通过仿真验证表明:该算法能够实现异类传感器的信息融合,初次融合成功的确认时间在3～5个主动传感器扫描周期。     

基于国产卫星多光谱影像的河流水体浊度遥感联合反演研究

基于集合建模思想,在水体光谱特征分析与敏感波段选择基础上,集成多种遥感反演模型优势,构建了河流水体浊度多光谱遥感联合反演模型(Combined Model-BP,CM-BP)。选择汉江中下游典型河段为研究区,利用2012—2013年原位观测数据,以具有较高时间分辨率和空间分辨率的国产卫星数据作为多光谱遥感数据源,测试评估了CM-BP浊度遥感反演模型适用性,并与传统波段组合模型进行精度比较,基于反演结果分析了研究区浊度时空分布特征。结果表明:基于集合建模思想构建的CM-BP模型的反演精度、适应性及稳定性均高于波段组合模型;从光谱分辨率、时空分辨率等角度考虑,环境与灾害监测预报小卫星星座系统、高分一号卫星、资源三号等国产卫星多光谱遥感数据是河流水体水质反演优选数据源;国产卫星遥感数据可以满足河流水体水质高精度、实时性与大尺度等遥感反演需要,为河流水环境监测研究提供数据基础。     

ASRNet: Adversarial Segmentation and Registration Networks for Multispectral Fundus Images

Multispectral imaging (MSI) technique is often used to capture images of the fundus by illuminating it with different wavelengths of light. However, these images are taken at different points in time such that eyeball movements can cause misalignment between consecutive images. The multispectral image sequence reveals important information in the form of retinal and choroidal blood vessel maps, which can help ophthalmologists to analyze the morphology of these blood vessels in detail. This in turn can lead to a high diagnostic accuracy of several diseases. In this paper, we propose a novel semi-supervised end-to-end deep learning framework called “Adversarial Segmentation and Registration Nets” (ASRNet) for the simultaneous estimation of the blood vessel segmentation and the registration of multispectral images via an adversarial learning process. ASRNet consists of two subnetworks: (i) A segmentation module S that fulfills the blood vessel segmentation task, and (ii) A registration module R that estimates the spatial correspondence of an image pair. Based on the segmention-driven registration network, we train the segmentation network using a semi-supervised adversarial learning strategy. Our experimental results show that the proposed ASRNet can achieve state-of-the-art accuracy in segmentation and registration tasks performed with real MSI datasets.