Image Segmentation and Geometric Feature Based Approach for Fast Video Summarization of Surveillance Videos

Process planning is the function that converts an engineering design into a manufacturing plan. One of the problems in feature-based process planning is the sequencing of features. Features must be given an order for removal. This order, or sequence, is partially dependent on the geometric relationships between the features. If the geometric relationships between features are such that they dictate a particular sequence, the features are said to have an interaction. Identifying these interactions is an important first step in creating the process plan. An approach to solve this problem using constructive solid geometry operations and the Episodal Associative Memory (EAM) is demonstrated. The EAM is an associative memory that integrates dynamic memory organization and neural computing techniques. The geometric feature relationships can be represented by a pattern. This pattern captures very qualitative information about the geometric positions fo the features. The EAM can organize these patterns into groups of similar geometric relationships. A method for dealing with exceptions, and for retrieving and storing general machining problems associated with interacting features will be described. The system implemented is shown to correctly sequence several types of feature interactions.

Download Full-text

Development of a Blade Parametric Modeling Methodology for Design and Analysis of Computer Experiments

Volume 2B: Turbomachinery ◽

10.1115/gt2015-43109 ◽

2015 ◽

Author(s):

Zafer Leylek ◽

A. J. Neely

Keyword(s):

Physical Space ◽

Computer Experiments ◽

Parametric Modeling ◽

Rotor Blades ◽

Geometric Feature ◽

Physical Parameters ◽

Base Line ◽

Turbine Stator ◽

Modeling Methodology ◽

Feature Based

This paper will present an enhanced parametric modeling technique for gas turbine stator and rotor blades. The enhanced blade parametric modeling system has been developed as part of a wider research program into global surrogate modeling of compressor and turbine aerodynamic performance using Design and Analysis of Computer Experiments (DACE) based techniques. The proposed method is based on a hybrid of geometric feature and Non-uniform Rational B-Spline (NURBS) based techniques. A base-line geometry is defined using the physical parameters and represented using NURBS curves and surfaces. A number of constraints are then imposed on the parametric model to ensure that DACE techniques can be effectively utilized. This is accomplished by mapping the geometric feature based parameters from the physical space to an alternative parametric space so that all feasible and numerically stable blade configurations can be represented using a unit hyper-cube. This method ensures a one-to-one mapping between the parametric sub-space and the geometric feature based system. The mapping is geometrically and numerically stable and does not produce ill-conditioned and unrealistic blade geometries. The development of the blade parametric modeling process allows the application of the complete suit of DACE tools and techniques. The method is valid for all axial blade profiles which include compressor and turbine stator and rotor blades.

Download Full-text