Feature-based System Research Articles

Developing a Feature-Based System for Automated Machining Feature Recognition (ISO 10303 AP 224) of Prismatic Components

Manufacturing is one of the main source of income for a developing country, like Malaysia. Start from the beginning of need in the market, a new concept of product is created. From the initial idea based on a need, this idea is hard to be understood if not presented in any form of drawing or prototype. So, computer-aided design (CAD) has the greatest role in helping to visualise the initial concept of a design with presenting the idea in a graphical view. However, this type of data cannot be used directly for the manufacturing process and normally intervention of human effort is needed to define all the manufacturing features from the component drawing again. This work is laborious if not assisted by computer technology. As a result, this paper aims to design a system and database which has the ability to extract geometrical features from drawings and identify all the manufacturing features which is useful for manufacturing process. This project takes a neutral drawing format, ISO 10303-203, as the input of the system. Then, a mechanism which consists of manufacturing feature extraction and feature recognition will be implemented and lastly, a new form of manufacturing feature-based data, ISO 10303-224 will be acquired for the subsequent manufacturing process.

An Integrated Reverse Modeling Approach Based on Reconstruction of Features and Constraints

Reverse engineering is an important tool to generate CAD models. This paper describes an integrated approach for modeling parts from point cloud to surfaces or solids based on features and constraints. The approach allows designers to integrate reverse engineering and feature-based CAD system in the reconstruction of parts. This approach has two advantages over current practice and the reconstructed models produced by this method are feature-based and constraints satisfaction, which provides a higher level description of part geometry rather than the tedious low-level editing of geometric descriptions as in reverse engineering. This method also facilitates modification and innovative design to the reconstructed parts, which would be extremely difficult or impossible to accomplish if current reverse engineering method is applied. In addition, it is a more convenient and practical way for designers. To illustrate the validation of this integrated modeling approach, a more complicated example is illustrated based on the approach.

Fuzzy Approach for Semantic Face Image Retrieval

Our aim is to realize semantic face image retrieval (FIR)\ by bridging the semantic-gap between low-level visual features of images and the high-level labels that describe facial features. This allows a user to retrieve face images based on a description of face features rather than an example image. We approach the semantic-gap problem by developing a fuzzy-based method of finding a mapping between the low-level features and the vocabulary that describes the semantics of the face features. The contribution of this paper is a new method of using fuzzy clustering and fuzzy inference methods to derive the degree of membership for each semantic label to a new image. Our experiments show that our approach has good results for annotating images, and provides a sound foundation for local face feature-based FIR systems. We have made available a demonstration system online. Further, our system is not domain specific and can be generalized and applied to other problems in the field of image retrieval.

A new history-independent modeling approach for feature-based design

The majority of current feature-based modeling systems employ model history to store feature creation operations and re-execute them sequentially after each modification, which is called history-based modeling. Due to the static feature creation order, history-based modeling causes some problems during the reevaluation of the model, such as the evaluated model does not correspond to its specification, the operation can only refer to the boundary entities created by the previous operations, high computation cost, etc. In this research work, a new history-independent modeling approach is proposed. For the “remove feature” operation, only boundary faces originating from the feature being removed, and the intersecting features are modified for updating the resulting BRep model. For the “modify feature” operation, the feature being modified is first removed from the product model and then re-added with the new specifications, thus its creation step in the model history is changed. As a result, some of the problems caused by the static feature creation order are solved. During the reevaluation, the computation time is dependent solely on the execution of the feature and its intersecting features being edited. The computational complexity of the boundary evaluation using the proposed method for three representative models has been analyzed based on Open CASCADE. A case model was studied in a proof-of-concept prototype system to demonstrate the proposed modeling approach.

Feature-based integration of conceptual and detailed mould design

The plastic production industry has been growing rapidly in recent years, and injection mould, which is especially widely used in 4C (computer, communication, consumer electronics, and car) products, is the most popular in moulding plastic. The diverse requirements of customers and pressures of just-in-time production are big challenges in the injection mould industry. The advantages, that keep products’ quality and increase work efficiency, will decide a company's competitive capabilities. Therefore, this study proposes a feature-based integration of the conceptual and detailed mould design process within the computer-aided design (CAD) tool. It adopts a feature-oriented method and the dedicated application programming interface (API) to implement the features integration function of the conceptual and detailed mould design. Based on intellectualised, customised, and standardised procedures, not only does this prevent probable engineering mistakes and generate consistent web reports, but also transmits the intact feature information from conceptual to detailed mould design, thus shortening detailed mould design processes. In the case studies of this paper, using the feature-based navigating system can result in time savings up to 56% and 59%. The results show significant time savings over traditional mould design processes.

Manufacturing feature-based cost management system: a case study in Brazil

Feature costing is a topic of recent discussion related to cost management systems (CMSs) aimed at understanding how product features influence production process costs. It raises as a key issue in mass customisation environments where a single product model can present hundreds of menu options. In this study, we explore the concept of feature costing beyond the use of activity-based costing (ABC). We propose a CMS based on features and common elements as costing objects instead of products. In our model, we use the unit of production effort method to organise the direct manufacturing costs, ABC method to address the indirect cost and the standard methods to compute raw materials costs. We illustrate the method in the production of bus seats in a Brazilian manufacturing company. This study gives different perspectives to the international academic community on the use of a different CMS used by many Brazilian companies.

3320 Feature-based Off-line Teaching System for Industrial Welding Robots to Assist Teaching Program Generation

The teaching operation requires huge amount of time and effort to prepare teaching programs. An objective of this study is to simplify the teaching operation for welding robots. The "welding feature" concept is utilized to develop a feature-based off-line teaching system. The old teaching programs generated in the past are distinguished by the "welding feature". When a new teaching program is generated, the most suitable teaching program is retrieved by the "welding feature" from the old teaching programs. Several suitable teaching programs are combined and modified to complete a new teaching program for new welding operation.

Design Meta-Intent Representation and Semantic Annotation

The parametric feature-based modeling systems can express design intent at high-level. But they usually lack representations for explaining why the feature is selected, what its design purpose and source are. This paper integrates the design intent object with design rationale and proposes an ontology-based representation framework for design meta-intent information. An approach to ontology instantiation for design intent objects and meta-intent properties by semantic annotating is presented. In order to improve the annotating efficiency the methods to automatically capture the design meta-intent information are also discussed. Based on above approaches the design meat-intent information can be naturally and effectively constructed during design process.

Preserving spatial information and overcoming variations in appearance for face recognition

Local feature-based approaches mainly aim to achieve robustness to variations in facial images by assuming that only some parts of the facial images may be affected. However, such approaches may lose spatial information. In this study, a compromise feature extraction scheme is studied which extracts local features while preserving spatial information. The proposed scheme exploits an ensemble of classifiers where each member is constructed using randomly selected design parameters including the size, number and location of sub-images for local feature extraction. Experiments conducted on FERET and ORL databases have shown that proposed scheme surpasses the local feature-based reference systems which focus on either local information or preserving spatial information.

STEP-Based Feature Modeller for STEP Compliant CNC

Feature-based modeling is one of key technologies to implement intelligent STEP compliant CNC, which can associate not only geometric and topological information, but also form features, tolerances, material properties and other information which may be used during the process planning and STEP-NC machining. This paper presents a machining feature-based modeler to build parts and exports them as the format of STEP AP224 file. The modeling system provides three main steps to construct a part: (1) selection of raw stock form stock library, (2) selection of predefined machining features according to ISO14649 to be subtracted from the part being designed, and (3) providing information to define the machining feature attributes such as feature size, position, orientation etc. This feature-based modeling system is implemented by using Microsoft C# and NX Open technology in UG NX6.0 environment.

Study on On-Machine Inspection Technology of Machining Center Based

With the development of digitalized manufacturing (DM), on-machine inspection (OMI) has become the key link of integrated quality system in DM. In DM, The detection and monitoring system chiefly dealing with kinds of parameters in machining process, taking on-line detection, analyzing the process quality information and carrying out corresponding quality assurance, so the quality of product may be assured and DM can be run in good condition. Therefore, the OMI technology of machining center based is researched. The framework of OMI and the hardware structure of special driving card for probe or tool (SDCPT) are described. Computer aided inspection planning (CAIP) is the integration bridge between CAD/CAM and computer aided inspection. A feature-based CAIP system for OMI is proposed to inspect the complicated mechanical parts efficiently during machining or after machining. The CAIP system is designed to produce an inspection process planning directly from CAD model. The prototype CAIP system includes the tolerance feature analysis, accessibility analysis, feature identification, measurement planning, and collision detection. The CAIP system can minimize the number of part setups and probe orientations and the inspection feature sequence.

New methodology in facial composite construction: from theory to practice

Existing commercial, computerised techniques for constructing facial composites generated from eyewitness memory are essentially electronic versions of the original, mechanical feature-based systems such as PhotoFIT and Identikit. The effectiveness of this feature-based approach is fundamentally limited by the witness's ability to recall and verbalise accurate descriptions of facial features from memory. Recent advances in facial composite methodology have led to software systems that do not rely on this process but instead exploit a cognitively less demanding process of recognition. We provide a technical overview of the EFIT-V system, currently being used by a number of police services in the UK.

Feature-Based Recognition of Control Chart Patterns: A Generalized Approach

Control chart patterns (CCPs) can be associated with certain assignable causes creating problems in the manufacturing processes and thus, the recognition of CCPs can accelerate the diagnostic search, for those causes. Researches in developing CCP recognition systems have traditionally been carried out using standardized or scaled process data to ensure the generalized applicability of such systems. Whereas standardization of data requires additional efforts for estimation of the mean and standard deviation of the underlying process, scaling of process data leads to loss of distinction between the normal and stratification patterns because a stratification pattern is essentially a normal pattern with unexpected low variability. In this paper, a new approach for generalization of feature-based CCP recognition system is proposed, in which the values of extracted shape features from the control chart plot of actual data become independent of the process mean and standard deviation. Based on a set of six shape features, eight most commonly observed CCPs including stratification pattern are recognized using heuristic and artificial neural network techniques and the relative performance of those approaches is extensively studied using synthetic pattern data.

An approach to feature-based three-dimensional modelling and similarity assessment of turned components

Feature-based modelling has been considered an indispensable tool for integrating design and manufacturing processes. In contrast to the common approach of simply attaching manufacturing information to existing geometric models, the present work proposes a new approach to extracting machining features from a feature-based solid modelling, based on an integrated geometric modelling system that supports both feature-based modelling and feature recognition. As a result, feature information is directly available to downstream activities, and feature extraction or recognition is no longer needed. The proposed feature-based modelling system provides a graphical environment for solid modelling in AutoCAD. This paper presents algorithms for feature-based modelling. The feature types are used as a basis for similarity assessment.

Latent Prosody Analysis for Robust Speaker Identification

Handsets that are not seen in the training phase (unseen handsets) are significant sources of performance degradation for speaker identification (SID) applications in the telecommunication environment. In this paper, a novel latent prosody analysis (LPA) approach to automatically extract the most discriminative prosodic cues for assisting in conventional spectral feature-based SID is proposed. The concept of the LPA approach is to transform the SID problem into a full-text document retrieval-like task via 1) prosodic contour tokenization, 2) latent prosody analysis, and 3) speaker retrieval. Experimental results of the phonetically balanced, read-speech, handset-TIMIT (HTIMIT) database demonstrated that the proposed method of fusing the LPA prosodic feature-based SID systems with maximum-likelihood a priori handset knowledge interpolation (ML-AKI) spectral feature-based SID outperformed both the pitch and energy Gaussian mixture model (Pitch-GMM) and the bigram of the prosodic state (Bigram) counterparts for both cases of counting all and only unseen handsets.

A STEP-NC Programming System for Prismatic Parts

To comply with STEP-NC (ISO 14649), a new paradigm for NC programming, many computer systems involved in NC manufacture are required to reshape in both functionality and structure. This paper reports a feature-based NC programming system for prismatic parts to be machined using STEP-NC machine tools. The proposed system consists of three functional modules, i.e. a feature-based modeler, a process planner and a part program generator. The modeler provides a graphical environment for the part model, which is created by adding manufacturing features on a 2.5 D sweep primitive shape. The process planner determines which operations are to be performed for the features, generates workingsteps and then produces a reasonable workplan. Finally both the geometrical and the process information are passed to the part program generator to form a complete ISO 14649-compliant file. The proposed system is demonstrated through the generation of the STEP-NC part program for an example part, and major issues such as the feature-operation mapping and the workingstep sequencing etc are also addressed in this paper.

Extracting relation information from text documents by exploring various types of knowledge

Extracting semantic relationships between entities from text documents is challenging in information extraction and important for deep information processing and management. This paper investigates the incorporation of diverse lexical, syntactic and semantic knowledge in feature-based relation extraction using support vector machines. Our study illustrates that the base phrase chunking information is very effective for relation extraction and contributes to most of the performance improvement from syntactic aspect while current commonly used features from full parsing give limited further enhancement. This suggests that most of useful information in full parse trees for relation extraction is shallow and can be captured by chunking. This indicates that a cheap and robust solution in relation extraction can be achieved without decreasing too much in performance. We also demonstrate how semantic information such as WordNet, can be used in feature-based relation extraction to further improve the performance. Evaluation on the ACE benchmark corpora shows that effective incorporation of diverse features enables our system outperform previously best-reported systems. It also shows that our feature-based system significantly outperforms tree kernel-based systems. This suggests that current tree kernels fail to effectively explore structured syntactic information in relation extraction.

Textual case-based reasoning for spam filtering: a comparison of feature-based and feature-free approaches

Spam filtering is a text classification task to which Case-Based Reasoning (CBR) has been successfully applied. We describe the ECUE system, which classifies emails using a feature-based form of textual CBR. Then, we describe an alternative way to compute the distances between cases in a feature-free fashion, using a distance measure based on text compression. This distance measure has the advantages of having no set-up costs and being resilient to concept drift. We report an empirical comparison, which shows the feature-free approach to be more accurate than the feature-based system. These results are fairly robust over different compression algorithms in that we find that the accuracy when using a Lempel-Ziv compressor (GZip) is approximately the same as when using a statistical compressor (PPM). We note, however, that the feature-free systems take much longer to classify emails than the feature-based system. Improvements in the classification time of both kinds of systems can be obtained by applying case base editing algorithms, which aim to remove noisy and redundant cases from a case base while maintaining, or even improving, generalisation accuracy. We report empirical results using the Competence-Based Editing (CBE) technique. We show that CBE removes more cases when we use the distance measure based on text compression (without significant changes in generalisation accuracy) than it does when we use the feature-based approach.

Feature-based design for process planning of machining processes with optimization using genetic algorithms

The development of a feature-based design environment that can be applied in the concept-to-manufacturing stages of the machining process is explained. It is broadly divided into four modules, namely, feature-based design (FBD) environment, virtual factory environment (VFE), operation-based feature mapping (OBFM) and optimization using genetic algorithms (GA). The feature-based design environment module is used for the design, modelling, synthesis, representation and validation of the components for machining application. It uses integrated features, which are predefined as feature templates in the feature library. While instancing these integrated features, they get/derive the information required for the design, modelling, process planning and manufacturing stages of the components as their attributes, from the user/knowledge base. After creating the component, integrated features present in it are validated with respect to its application, namely machining process. The VFE module defines the mathematical model of the factory in the computer, which provides the database for operations, machines, cutting tools, work pieces, etc. The knowledge base maps validated features of the component into operation sets in the first phase of the OBFM stage. Each operation in the operation sets can be carried out using different machines and cutting tools in the factory. All these possible choices are obtained in the second phase of OBFM. GA is used to find the optimal sequence of operations, machines and cutting tools for different criteria. Provisions are also available to generate NC codes for operations, which are to be carried out with NC or CNC machines, if selected. Thus, the optimal process plan for the selected criteria with respect to the given factory environment is found for the modelled component. The feature-based design system developed is built on existing CAD, programming and spread-sheet software tools, namely CATIA®, MS-Visual Basic® and MS-Excel®, which not only save developmental effort, but also make full use of the functionalities of these commercial softwares. This paper explains the developed system with a case study.

Sensitivity to spatial and temporal modulations of first-order and second-order motion

This study characterises the spatiotemporal “window of visibility” for first-order motion (luminance-modulated noise) and three varieties of second-order motion (contrast-modulated, polarity-modulated and spatial length-modulated noise). Direction-identification thresholds (minimum modulation depth producing 79.4% correct) were measured for each motion pattern (acuity permitting) over a five octave range of spatial and temporal frequencies (0.5–16 c/deg and 0.5–16 Hz respectively). Thresholds were converted into modulation sensitivity (1/threshold). For first-order motion patterns, sensitivity functions were generally bandpass. However, for second-order motion patterns, functions were predominantly lowpass in nature. In particular, the functions corresponding to contrast-modulated and polarity-modulated noise were virtually identical in terms of shape and sensitivity. However, sensitivity to modulations of spatial length was extremely poor and more lowpass, suggesting that additional strategies, perhaps a feature-based system, may be required for encoding motion of images of this type.