A small-spot deformation camouflage design algorithm based on background texture matching

In order to solve the problem of poor fusion between the spots of deformation camouflage and the background,a small-spot deformation camouflage design algorithm based on background texture matching is proposed in this research.The combination of spots and textures improved the fusion of the spot pattern and the background.An adversarial autoencoder convolutional network was designed to extract background texture features.The image adversarial loss was added and the reconstruction loss was improved to improve the clarity of the generated texture pattern and the generalization ability of the model.The digital camouflage was formed by obtaining the mean value of the square area and replacing the main color.At the same time,the spots in the square area with a side length of 2 s were subjected to simple linear iterative clustering to form irregular small-spot camouflage.A dataset with a scale of 1050 was established in the experiment.The training results of three different loss functions were investigated.The results showed that the proposed loss function could enhance the generalization of the model and improve the quality of the generated texture image.A variety of digital camouflages with main colors and irregular small-spot camouflage were generated,and their efficiency was tested.On the one hand,intuitive evaluation was given by personnel observing the camouflage pattern embedded in the background and its contour map calculated by the canny operator.On the other hand,objective comparison result was formed by calculating the 4 evaluation indexes between the camouflage pattern and the background.Both results showed that the generated pattern had a high degree of fusion with the background.This model could balance the relationship between the spot size,the number of main colors and the actual effect according to actual needs.

Landscape Features and Design Elements of Earth-sheltered Buildings

Categories of earth-sheltered buildings were summarized, and it was proposed that landscape features of earth-sheltered buildings were demonstrated mainly as "ecological, landscape-like and systematic". Landscape elements such as entrance, road, water and greening were believed as major means of showing landscape features of earth-sheltered buildings. Entrance landscape design of such buildings was analyzed from the perspectives of plane-type, slope-type and step-type forms. Road design for these buildings should respect natural terrains so as to connect spaces and organize traffic routes reasonably. Waterscape design should take both landscape effects and loading capacity of roof into consideration so as to meet water-loving psychology of the public, virtual and real approaches should be combined to create waterscapes. Greening design of earth-sheltered buildings was explored from the perspectives of roof greening and vertical greening to improve the green coverage rate and show favorable ecological effects.

Top-down assembly design using assembly features

The primary task of top-down assembly design is to define a product抯 detailed physical description satisfying its functional requirements identified during the functional design phase. The implementation of this design process requires two things, that is, product functional representation and a general assembly model. Product functions are not only the formulation of a customer抯 needs, but also the input data of assembly design. A general assembly model is to support the evolving process of the elaboration of a product structure. The assembly feature of extended concept is taken as a functional carrier, which is a generic relation among assembly-modeled entities. The model of assembly features describes the link between product functions and form features of parts. On the basis of this link, the propagation of design modifications is discussed so as to preserve the functionality and the coherence of the assembly model. The formal model of assembly design process describes the top-down process of creating an assembly model. This formal model is represented by the combination of assembly feature operations, the assembly model and the evaluation process. A design case study is conducted to verify the applicability of the presented approaches.

基于BP神经网络的TBM刀盘关键位置应变重构

为解决恶劣工况下全断面硬岩隧道掘进机(tunnel boring machine,TBM)关键主承力结构应变监测难、监测不准的难题,提出了一种基于BP神经网络和有限元分析的TBM刀盘关键位置应变重构方法.首先,通过静、动力学有限元分析确定了TBM刀盘关键位置,并提取了刀盘典型易损特征子结构.其次,基于有限元技术和实验设计(design of experiments,DOE)方法,分别进行了标准件和特征子结构多载荷下静力学有限元分析,并构建了载荷-应变数据库.最后,运用BP神经网络建立了标准样件和刀盘特征子结构的应变重构模型,并进行了标准样件的实验验证.结果表明,重构应变的平均误差为10%,验证了方法的可行性,为TBM刀盘复杂结构的应变重构提供了一种可行的方法.

A FORMAL REPRESENTATION FOR FEATURE-BASED DESIGN

从三个方面研究了基于特征设计的形式化描述方法：基于特征设计的基本定义、设计过程模型及设计算法。文中给出了特征分类、特征操作、特征模型验证和特征映射策略及其形式化描述方式，建立了兼顾并行工程和顺序工程设计方式的基于特征设计过程形式化描述模型，提出了基于特征的设计算法，为解决基于特征设计系统开发和运行缺乏统一方法学这一课题作了有益的尝试。

Optimal Design of Bicycle Frame Parameters Considering Biomechanics

With the development of technology and the change of market demands,the trend in middle and high grade bicycle manufacturing is developed toward small-volume,multi-species,and customer-oriented production.Therefore,human element should be fully considered in design so that the bicycle has the best cycling performance for the specific rider.Currently,customized design is difficult to achieve since feature parameters of the rider are not included in the design.The design of bicycle frame is the most important in bicycle design.The relative positions among the saddle,handlebar and central axis are defined as the bicycle three-pivot,they are the main parameters in bicycle frame design.In conventional bicycle design,frame parameters are merely relevant to bicycle types.On the basis of the principles of biomechanics and ergonomics knowledge,this paper presents a design method for bicycle three-pivot considering feature parameters of the rider by dynamic simulation.Firstly,a dynamic model of rider-bicycle system is built for a special rider,and a serial of simulation experiments is designed by uniform test method.Then,a mathematical model is built between the three-pivot position and the square of lower limb muscle stress by using simulation and regression analysis of the rider-bicycle system.The optimal three-pivot position parameters are obtained by setting the minimal of the square of the lower limb muscle stress as the objective.Therefore,the optimal parameters are gained for the specific rider.Finally,various results are gained for different riders based on the same design process.The function between feature parameters of the rider and the optimum three-pivot position parameters is built by regression.Bicycle design considering biomechanics can be divided into three main steps：calculating the three-pivot position,designing the geometrical structure of the bicycle frame and analyzing frame strength,and selecting appropriate parts and assembling the bicycle.Bicycle design considering biomechanics changes the conventional bicycle design and realizes customized design by considering human element in the design process.

Collaborative Design in PDM / 3D CAD Integrated Environment

Some key issues in supporting collaborative design in product data management（PDM ） system and 3D computer aided design（CAD） system integrated environment are analyzed. The general architecture of the integrated environment is divided into five tiers and employs the transparently integrated mode, with the mode, function calling and information exchanging among independent PDM and CAD processes are carried out via message translation /parse approach. Product layout feature（PLF ） model definition is presented, PLF model is used to represent design intention at the preliminary design phase. The collaborative design methodology employing the PLF model in PDM/3D CAD integrated environment is analyzed. The design methodology can speed up the design process, reduce the investment and improve the product quality.

PERFORMANCE-BASED INTELLIGENT RESOURCE DESCRIPTION MODEL FOR INTERNET-BASED PRODUCT DESIGN

Issues on intelligent resource description and multiple intelligent resources integration for lntemet based collaborative design are analyzed. A performance-based intelligent resource description model for lnternet-based product design is proposed, which can help to create, store, manipulate and exchange intelligent resource description information for applications, tools and systems in Interact-based product design. A method to integrate multiple intelligent resources to fulfill a complex product design and analysis via lntemet is also proposed. A real project for improving the bearing system design of a turbo-expander with many intelligent resources in prominent universities is presented as a case study.

Blank Panel Design of Integral Wing Skin Panels Based on Feature Mapping Methods

A blank panel design algorithm based on feature mapping methods for integral wing skin panels with supercritical airfoil surface is presented.The model of a wing panel is decomposed into features,and features of the panel are decomposed into information of location,direction,dimension and Boolean types.Features are mapped into the plane through optimal surface development algorithm.The plane panel is modeled by rebuilding the mapped features.Blanks of shot-peen forming panels are designed to identify the effectiveness of the methods.

Research on Variable Structure Parametric Design System of Ceramic Tile Mould Based on Modular

To solve the existing problems during the ceramic mold enterprises product design and development process, the variable structure parametric design system based on modular of ceramic mold has been developed. The system uses the object-oriented technology and top-down design concept as a guide, establishes a ceramic mold parametric design process, divides the process of ceramic mold design into modules of different levels and creates a component model library based on the functional analysis. Expanding modular thinking to parts structure design level is an effective solution to the difficulty of changing the structure during the product design process. Examples show that the system can achieve a ceramic mold product design, improve design efficiency.

Linker Library:基于几何特征的骨架跃迁片段库

骨架跃迁是目前应用最广泛的药物设计策略之一,但是现有骨架跃迁方法产生的化合物大多为已报道的先导化合物的衍生物或类似物,化学结构缺乏新颖性。针对现有骨架跃迁方法的局限性,提出了一种保持药效团与骨架之间的相对距离和角度不变的骨架跃迁策略,构建一个包含骨架几何特征的linker片段库:Linker Library。该片段库可以根据骨架中心到连接点之间距离和角度,推荐结构新颖且可保持官能团相对位置的片段,有助于指导化合物的骨架跃迁并加速药物发现进程。

MRMR Based Feature Vector Design for Efficient Citrus Disease Detection

In recent times,the images and videos have emerged as one of the most important information source depicting the real time scenarios.Digital images nowadays serve as input for many applications and replacing the manual methods due to their capabilities of 3D scene representation in 2D plane.The capabilities of digital images along with utilization of machine learning methodologies are showing promising accuracies in many applications of prediction and pattern recognition.One of the application fields pertains to detection of diseases occurring in the plants,which are destroying the widespread fields.Traditionally the disease detection process was done by a domain expert using manual examination and laboratory tests.This is a tedious and time consuming process and does not suffice the accuracy levels.This creates a room for the research in developing automation based methods where the images captured through sensors and cameras will be used for detection of disease and control its spreading.The digital images captured from the field’s forms the dataset which trains the machine learning models to predict the nature of the disease.The accuracy of these models is greatly affected by the amount of noise and ailments present in the input images,appropriate segmentation methodology,feature vector development and the choice of machine learning algorithm.To ensure the high rated performance of the designed system the research is moving in a direction to fine tune each and every stage separately considering their dependencies on subsequent stages.Therefore the most optimum solution can be obtained by considering the image processing methodologies for improving the quality of image and then applying statistical methods for feature extraction and selection.The training vector thus developed is capable of presenting the relationship between the feature values and the target class.In this article,a highly accurate system model for detecting the diseases occurring in citrus fruits using a hybrid feature development approach is proposed.The overall improvement in terms of accuracy is measured and depicted.

Fuzzy Methodology for Taxonomy and Knowledge Base Design

This paper summarizes the research results dealing with washer and nut taxonomy and knowledge base design, making the use of fuzzy methodology. In particular, the theory of fuzzy membership functions, similarity matrices, and the operation of fuzzy inference play important roles.A realistic set of 25 washers and nuts are employed to conduct extensive experiments and simulations.The investigation includes a complete demonstration of engineering design. The results obtained from this feasibility study are very encouraging indeed because they represent the lower bound with respect to performance, namely correctrecognition rate, of what fuzzy methodology can do. This lower bound shows high recognition rate even with noisy input patterns, robustness in terms of noise tolerance, and simplicity in hardware implementation. Possible future works are suggested in the conclusion.

Compact Car-Body Surface Design with T-spline Surface

Creating proper B-spline surface models is a very challenging task for designers in car-body surface design.Due to the tensor-product structure of B-spline surface,some undesirable issues of the redundant control points addition,incomplete surface definition and the difficulty of trimming boundary alteration frequently occur,when designing the car-body surface with B-spline surfaces in local-feature-lines construction,full-boundary-merging and visual surface trimming.A more efficient approach is proposed to design the car-body surface by replacing B-spline surface with classical T-spline surface.With the local refinability and multilateral definition offered by Tspline surface,those designing issues related with B-spline surface can be overcomed.Finally,modeling examples of the door,hood and rear-window are given to demonstrate the advantage of T-spline surface over B-spline surface in car-body surface design.

Research on a New Coding System for Vibrating Feeder Design

The sUdeway design is the key in the design of the disc vibrating feeder. However, no reliable theoretical guidance has come into existence, which greatly restricted the application of CAD（ Computer-aided design）. In order to feed the application of CAD technology, we must make improvements to the existing coding method. Based on the similarity principle of Group Technology and existing coding system, a new coding method applicable to slide- way design is brought forward. The existing coding system could get optimized by means of analysing and studying the influence imposed by the parts＇ shape and posture features. More detailed information about the parts could be supplied by the new coding system, which makes the design simpler, more convenient and more accurate with the subjoin of the initial and targeted codes.

A FEATURE－BASED PRODUCT MODELLING SYSTEM ON PC （CASE STUDY OF PARTS DESIGN FOR PRESS MACHINE）

This article reports on the design and implementation of feature modelling system for the CAPP of rotational symmetric components. The work deals with design by features, feature parts database design, and parts information modelling techniques realized in Personal Computer. The modular software provides utilities such as interactive component synthesis, dimensioning, tolerancing and graphical display.

机械加工MBD毛坯模型的特征识别设计方法

为了解决基于模型的定义(MBD)环境下机械加工毛坯辅助设计问题,采用特征识别技术辅助创建三维毛坯模型.首先分析了机械加工工艺设计环节MBD毛坯模型的组成要素与模型要求,并建立零件模型的属性面邻接图;根据零件模型上加工特征的特点划分简单特征、体积特征和表面特征;通过属性面邻接子图的模式从特征集合中识别出简单特征与体积特征,并利用补特征法与半空间法抑制这2种特征;最后,根据工艺员输入的表面加工余量创建抑制表面特征的实体.在整个毛坯设计推理过程中研究了三维制造标注的维护方法,最终达到辅助工艺员快速设计MBD毛坯模型的目的.

基于B－rep表示的机械零件工作图尺寸标注的智能化

基于实体造型和特征造型技术，对机械零件工作图尺寸标注智能化进行了系统的研究．建立了尺寸标注综合模型，论述了尺寸标注冗余性判断基本原理，将神经网络、特征识别和尺寸键技术相结合，确定零件的尺寸标注方案；采用了基于范例推理（ＣＢＲ）的方法完成了零件标注尺寸的自动市置，最后通过ＡｕｔｏＣＡＤ输出零件工作图．

基于BP神经网络的产品生命周期评价敏感性分析

为支持产品方案设计阶段设计信息反馈指导方案优化,提出基于BP神经网络的设计方案敏感性分析方法。建立了绿色信息模型,从方案设计中提取与环境影响相关的绿色信息;建立了神经网络敏感性分析模型,将各个生命周期阶段的绿色信息作为敏感性分析的输入参数,将对应的生命周期评价结果作为输出参数;训练BP神经网络模型使相对误差达到预期精度;分别提取该BP网络输入层与隐含层、隐含层与输出层各单元之间的连接权值,使用Tchaban算法计算得到绿色信息对生命周期评价结果的敏感性系数,即影响贡献值。以牵引电机为例,验证了所提敏感性分析方法,确定了主要设计变量对评价结果的影响趋势,从而对设计方案的变更提出了改进方向。