A feature recognition system with interactive feature inspection and deletion capabilities

A recognition process of the features in a part model uses the knowledge of an application engineer. The knowledge is encoded as rules of the recognition procedure that are applied to the part model during the recognition process. Such a human interaction is difficult to control in extracting the moulding features because the features moulding of the application engineer may change from one engineer to the other and external conditions may change. Instead, we treat the result of the recognition process as a first approximation of the user's intention and let the user interactively modify the result. In this paper, we present a feature recognition system where the user can inspect the result of the recognition and delete the recognised features interactively.     

Mechanical Product Disassembly Sequence and Path Planning Based on Knowledge and Geometric Reasoning

A feature-based assembly model is proposed for disassembly sequence planning, and establishing a correct and practical disassembly path for the part in the product, based on geometric reasoning and knowledge. The fundamental assembly modelling strategy for a product is based on the mating features of its parts. An algorithm is introduced which uses the information provided by the mating features of parts in the product to find the candidate parts for disassembly and to carry out disassembly path planning. A complete and accurate interference checking approach is used to ensure no global collision while disassembling a part. In some cases, it cannot be implemented by geometric reasoning alone, so a set of criteria and heuristic rules based on knowledge, constraints, relationships among parts, and quantitative disassemblability assessment are used. It can also be carried out interactively by the user when necessary. The proposed method is integrated with the CAD model of the product. The user can visually disassemble the product while planning, so it is easier to carry out the disassembly planning and generate an optimal sequence.     

自动工艺设计系统

描述了自动工艺设计专家系统的研究与开发，该系统使用VISUAL PROLOG语言，基于知识进行计算机辅助工艺设计。在系统中采用零件特征与加工特性相结合的方法描述零件；分层和分类收集存主知识，知识基与推理分离，用户可以打开知识库根据要求修改知识；推理机制采用反向推理，进行合一算法自动生成工艺规程。     

Contact states recognition in robotic part mating based on support vector machines

In order to autonomously execute part mating, an intelligent robot should be able to carry out active compliant motion. Contact states recognition machine is a missing link for implementation of this kind of motion within an intelligent robotic assembly system. In this paper, we present an approach to design contact states recognition machines for various types of part mating problems. We have chosen generalized mating force as a basic feature measured from the process. Starting from force measurements, online recognition is carried out using class boundaries and transduction mappings obtained during offline training. The basis for the proposed offline training procedure is not experimental data but a mechanical model of the part mating process. This enables supervised training without requiring numerous experiments. Furthermore, this has allowed extraction of qualitative features from the analytical model of mating force. To provide good time localization and phase correctness, we have utilized discrete wavelet transform for feature extraction. The obtained patterns have been classified using support vector machines to obtain a recognition machine with good generalization properties. The proposed machine is elaborated and experimentally verified using case study of cylindrical part mating with chamfer crossing. We have used quasi-static model of insertion force as a starting point in the training process. Exploiting some characteristics of Daubechies wavelets, we have managed to extract features that are independent on characteristics of the concrete cylindrical part mating. Finally, the generated machine was evaluated using intensive real-world experiments. Herein we have shown that performance of the generated contact states recognition machine was excellent.     

基于制造特征的工艺知识管理技术研究

针对目前制造企业工艺设计知识管理方法不能有效支持工艺设计的问题,提出了一种基于制造特征的工艺知识管理技术.在该技术中,通过制造特征与工艺知识的关联,建立了基于制造特征的工艺知识表达模型,通过对制造特征的分类管理可以有效地管理工艺知识.在知识的重用过程中,通过对制造特征的检索,工艺知识以知识表达模型的方式,将设计该特征工艺所需的工艺知识传递给工艺设计人员,有助于工艺人员快速作出工艺决策.     

基于制造特征的工艺知识管理技术研究

针对目前制造企业工艺设计知识管理方法不能有效支持工艺设计的问题,提出了一种基于制造特征的工艺知识管理技术。在该技术中,通过制造特征与工艺知识的关联,建立了基于制造特征的工艺知识表达模型,通过对制造特征的分类管理可以有效地管理工艺知识。在知识的重用过程中,通过对制造特征的检索,工艺知识以知识表达模型的方式,将设计该特征工艺所需的工艺知识传递给工艺设计人员,有助于工艺人员快速作出工艺决策。     

基于STEP的特征造型系统

零件的特征建模是ＣＡＤ／ＣＡＰＰ／ＣＡＭ集成的关键，本文于ＳＴＥＰ的特征造型系统ＪＷ－ＣＡＤ。它以Ｐｒｏ／Ｅ系统作为支撑软件，并用ＳＴＥＰ标准作为零件信息达与数据交换机制。     

Macro-capp: A prototype capp system for an FMS

This paper deals with the role, advantages, problems and solution techniques for the implementation of dynamic Computer Aided Process Planning (CAPP) systems in a Felxible Manufacturing system (FMS). A large variety of part features for both rotational and prismatic parts are considered. A custom group technology coding technique is designed and implemented to describe part profile to system software concisely and comprehensively. The part profile code is assimilated by the system interactively. A prototype CAPP system was designed for a pseudo FMS containing multiple machining centres. The system described develops process plans that consider both alternative routes and methods to manufacture a part. Heuristic knowledge was implemented to choose between alternatives with flowtime minimization as the objective function. The system was tested and its outputs validated with respect to both prismatic and rotational parts.     

以上下文为中心的设计知识管理方法

为了提高设计知识重用的效率，提出了一种以上下文为中心的设计知识管理方法。设计上下文指设计知识被利用的环境，包括当前设计任务和当前设计者的属性。该方法的核心内容有两个方面，即协调-意图-行为三层设计过程建模以及模板和覆盖相结合的设计用户建模。协调层、意图层和行为层分别采用工作流、树形结构和层次自动机表示。在用户建模中，采用用户属性对模板进行分类和匹配，并且基于领域知识体系结构定义模板的内容。该方法利用上下文实现设计知识的主动推荐，可减少重要知识的遗漏和缩短查找时间，不需要对设计知识的内容进行形式化的描述和对知识的格式进行转换，通用性强，实现代价小。     

智能计算机辅助教学领域知识库的实现及应用

提出一种新颖有效的ICAI领域知识库的实现方法及其应用。通过制定一个知识点属性的通用存储结构，建立基于知识点的领域知识的树状层次结构和知识点间联系的支撑网络结构，即领域知识结构模型，将知识点形式化，结构化后纳入领域知识库，在此基础上实现了学习路线生成，动态学习进程控制，知识缺陷诊断，个性化学习等智计算机辅助教学特性。     

An approach for pattern recognition of hand activities based on EEG and Fuzzy neural network

Electroencephalography (EEG) is another interesting bio-electrical signal to differ from EMG (Electromyography). In order to pursue its application in the control of the multi-fingered robot hand or the prosthetic hand, the pattern recognition technology of the human hand activities based on EEG should be investigated as a very important and elementary research objective at first. After discussing our research strategy about EEG applied in the control of the robot hand, the recognition model named as Fuzzy Neural Network (FNN) is set up in this paper, and then its related algorithms, such as the fundamental knowledge produced, the learning samples set, the features extracted, and the patterns recognized with the artificial neural network (ANN), are deeply discussed for achieving the classification of some basic mental tasks. In addition, the experimental research has also been done using a two-channel system of measuring EEG signal, and the result shows the new recognition model using FNN can extract not only the effective spectral features of the hand movements and the other usual accompanying mental tasks, such as blinking eyes, watching red color and listening music, so as to achieve the fundamental knowledge production and the feature extraction, but also has the good capability of the pattern recognition about the human hand activities through the fuzzy setting of the learning samples and the training of its ANN.     

Software integration technologies in CIM

Two CASE-tools for Computer-Integrated Manufacturing are proposed: CIMVIEW, for high level, functional, top-down integration, company-specific analysis and modelling; and CIMGLUE, for low level, bottom-up integration, and interfacing of existing applications. In CIMVIEW the user interactively builds an SA/SD dataflow model of the functions of the company. The functional decomposition of ‘bubles’ is internally converted into Lisp representation. The contents of the dataflow ‘arrows’ is derived interactively from the actual customer files or scanned paper documents and converted into hierarchic Lisp lists. The result is a Lisp model of the company functions under investigation. This model can be utilized by Lisp-based tools for many purposes, including symbolic simulation, animation, metrics, data consistency and usage checks, and the automatic generation of the interface specifications, or the automatic generation of modified forms after simplification of the dataflows. CIMGLUE is a general tool to build representation conversion programs between almost any software packages, A and B. The conversion program is built interactively, utilizing examples of package A output and package B input. Both CIMGLUE and CIMVIEW tools are described at a general level for different implementations. A CIMVIEW-prototype has been implemented based on Common Lisp and Common Windows. In the STIF (semantically transparent interfacing) method, the probably variable definitions of the transferred items are isolated outside the interface as much as possible, instead of using cross-references inside the interface. This is done by embedding some elements of the definition language of application A into the definition language of application B. A method of semantically transparent interfacing, STIF, is also defined, and two cases in which it has been applied are briefly described.     

基于KF的特征识别技术研究

论述了基于UG的孔类零件模型的特征识别方法和实现技术.详细论述了孔类特征识别知识库的建立以及基于UG/KF的推理机制,最后给出了应用实例,为工程应用提供了有效的解决方案.特征识别是从零件的三维模型中获取相关几何信息,建立基于知识库的特征信息,用于后续的应用.     

Extraction of manufacturing information from design-by-feature solid model through feature recognition

Feature recognition is the key to the computer-aided design (CAD) and computer-aided manufacturing (CAM) integration to build a computer-integrated manufacturing system. There are two approaches to CAD feature recognition: platform-dependent and platform-independent. In the platform-independent approach, the part’s geometrical data are extracted from a neutral file such as DXF, IGES, or STEP. In contrast, the platform-dependent approach extracts the information of the design features directly from a design-by-feature solid model through the object-oriented model of a part. This paper explains a platform-dependent approach which is implemented to translate design features into manufacturing information. This approach begins with simplification using the suppression of fillets, and clustering non-intersecting design features is done. Then, the rule-based method is employed in order to recognize machining features. Finally, the needed manufacturing information such as tool accessing direction, dimensions, material removal regions, and geometrical and topological data is recognized. The application of the proposed system would be exhibited in generating machine path code for rapid prototyping and CNC machines and providing a database for computer-aided process planning. The proposed system was implemented on Autodesk Inventor and successfully tested for many complex 3D models.     

基于统计特征的点云模型匹配技术

为使匹配结果收敛于全局最优解,提出基于统计特征的点云模型匹配技术.通过调整自由模型与固定模型的一个或多个对应统计特征重合或一致来实现模型的匹配.基于统计特征的模型匹配分为完全匹配和部分匹配两种情况.完全匹配能够一次匹配成功;部分匹配需要进一步处理才能完成模型匹配:交互调整自由模型中未被约束的自由度,使得自由模型与固定模型达到视觉上的匹配,然后采用迭代最近点算法精确匹配.根据统计特征进行模型匹配,使匹配方案稳定、可靠,保证匹配结果收敛于全局最优解.     

面向铁路货车的设计知识管理系统研究与开发

针对铁路货车设计特点和研发需求,以支持铁路货车研发流程的知识驱动为目标,开展了面向铁路货车设计知识管理系统的研究,提出了基于本体和产生式规则的铁路货车知识混合表达方法、面向研发流程的设计知识关联模型,以及基于用户模型的设计知识重用等关键技术,解决了铁路货车设计知识组织、管理和使用的难点问题。在此基础上完成了面向铁路货车的设计知识管理系统的开发。     

面向铁路货车的设计知识管理系统研究与开发

针对铁路货车设计特点和研发需求,以支持铁路货车研发流程的知识驱动为目标,开展了面向铁路货车设计知识管理系统的研究,提出了基于本体和产生式规则的铁路货车知识混合表达方法、面向研发流程的设计知识关联模型,以及基于用户模型的设计知识重用等关键技术,解决了铁路货车设计知识组织、管理和使用的难点问题。在此基础上完成了面向铁路货车的设计知识管理系统的开发。     

Path planning of multi-patched freeform surfaces for laser scanning

In this paper, a new method for scanning a complex surface model with multiple patches is proposed. In scanning of freeform-shaped models, it is difficult to generate a measuring plan by human intuition due to the complexity of the part. The developed method calculates the number of scans, scan direction, and scan path for a stripe-type laser scanner. The user can designate the surface patches that need to be scanned. In generating the scan plan, surface information is first extracted from the CAD model automatically. Other information such as, design knowledge, functionality and machine parameters are provided interactively. Based on this information, the original surface model is sampled in the u, v parameter domain and the sampled points are grouped using the view angle of the laser scanner. The scan direction is determined by calculating the global mean vector of the sampled points that belong to a group. The range of the view angle can be varied to enhance the quality of captured point data. The optical scan paths for each scan direction are calculated by projecting the sampled points onto a 2D plane. The optical constraints are also verified to guarantee the generated scan plan.     

A system for the design and manufacture of feature-based parts through the Internet

The Internet has enabled the development of applications for supporting the design and manufacturing of industrial parts and products. Some actions have been performed by some research groups in different parts of the world aiming at conceiving product modeling systems based on the technology of features to allow information sharing, both for the activities related to product development and for manufacturing. This paper describes the implementation of the WebMachining system () developed in a context of e-Mfg and concurrent engineering, aimed at integrating CAD/CAPP/CAM for the remote manufacturing of feature-based cylindrical parts with symmetrical and asymmetrical features through the Internet, using an approach based on multi-agent systems. The information referring to the features is manipulated through a relational database management system. The graphic user interface (GUI) is implemented in Java and HTML. In this GUI, the user inputs the information on the design features that compose the part. Then these data are sent to the server. Since the part is cylindrical, the user models the part in two dimensions, and it can be visualized as three-dimensional through VRML. A database was implemented that stores the information on the product modeled by features, containing information associated with the form features, material features, tolerance features and technological features. These combined pieces of information allow the mapping of design features into machining features, which is fundamental for process planning. The database information is described in this article through the IDEF1X information model.