For the past three decades, computer-aided process planning (CAPP) has attracted a large amount of research interest. A huge volume of literature has been published on this subject. Today, CAPP research faces new challenges owing to the dynamic markets and business globalisation. Thus, there is an urgent need to ascertain the current status and identify future trends of CAPP. Covering articles published on the subjects of CAPP in the past 10 years or so, this article aims to provide an up-to-date review of the CAPP research works, a critical analysis of journals that publish CAPP research works, and an understanding of the future direction in the field. First, general information is provided on CAPP. The past reviews are summarised. Discussions about the recent CAPP research are presented in a number of categories, i.e. feature-based technologies, knowledge-based systems, artificial neural networks, genetic algorithms, fuzzy set theory and fuzzy logic, Petri nets, agent-based technology, Internet-based technology, STEP-compliant CAPP and other emerging technologies. Research on some specific aspects of CAPP is also provided. Discussions and analysis of the methods are then presented based on the data gathered from the Elsevier's Scopus abstract and citation database. The concepts of 'Subject Strength' of a journal and 'technology impact factor' are introduced and used for discussions based on the publication data. The former is used to gauge the level of focus of a journal on a particular research subject/domain, whereas the latter is used to assess the level of impact of a particular technology, in terms of citation counts. Finally, a discussion on the future development is presented.

Computer-aided process planning-A critical review of recent developments and future trends

In the market-place of the 21st century, there is no place for traditional ‘over-the-wall’ communications between design and manufacturing. In order to ‘design it right the very first time’, designers must ensure that their products are both functional and easy to manufacture. Software tools have had some successes in reducing the barriers between design and manufacturing. Manufacturability analysis systems are emerging as one such tool — enabling identification of potential manufacturing problems during the design phase and providing suggestions to designers on how to eliminate them. In this paper, we provide a survey of current state-of-the-art automated manufacturability analysis. We present the historical context in which this area has emerged and outline characteristics to compare and classify various systems. We describe the two dominant approaches to automated manufacturability analysis and overview representative systems based on their application domain. We describe support tools that enhance the effectiveness of manufacturability analysis systems. Finally, we attempt to expose some of the existing research challenges and future directions.

/pdf/automated-manufacturability-analysis-a-survey-37wshii46r.pdf

Automated manufacturability analysis: a survey

Automated machining feature recognition, a sub-discipline of solid modeling, has been an active research area for last three decades and is a critical component in digital manufacturing thread for detecting manufacturing information from computer aided design (CAD) models. In this paper, a novel framework using Deep 3D Convolutional Neural Networks (3D-CNNs) termed FeatureNet to learn machining features from CAD models of mechanical parts is presented. FeatureNet learns the distribution of complex manufacturing feature shapes across a large 3D model dataset and discovers distinguishing features that help in recognition process automatically. To train FeatureNet, a large-scale mechanical part datasets of 3D CAD models with labeled machining features is automatically constructed. The proposed framework can recognize manufacturing features from the low-level geometric data such as voxels with a very high accuracy. The developed framework can also recognize planar intersecting features in the 3D CAD models. Extensive numerical experiments show that FeatureNet enables significant improvements over the state-of-the-arts manufacturing feature detection techniques. The developed data-driven framework can easily be extended to identify a large variety of machining features leading to a sound foundation for real-time computer aided process planning (CAPP) systems.

FeatureNet: Machining feature recognition based on 3D Convolution Neural Network

In this study the machining of AISI 1030 steel (i.e. orthogonal cutting) uncoated, PVD- and CVD-coated cemented carbide insert with different feed rates of 0.25, 0.30, 0.35, 0.40 and 0.45mm/rev with the cutting speeds of 100, 200 and 300m/min by keeping depth of cuts constant (i.e. 2mm), without using cooling liquids has been accomplished. The surface roughness effects of coating method, coating material, cutting speed and feed rate on the workpiece have been investigated. Among the cutting tools-with 200mm/min cutting speed and 0.25mm/rev feed rate-the TiN coated with PVD method has provided [email protected], TiAlN coated with PVD method has provided [email protected], AlTiN coated with PVD method has provided [email protected] surface roughness values, respectively. While the uncoated cutting tool with the cutting speed of 100m/min and 0.25mm/rev feed rate has yielded the surface roughness value of [email protected] Afterwards, these experimental studies were executed on artificial neural networks (ANN). The training and test data of the ANNs have been prepared using experimental patterns for the surface roughness. In the input layer of the ANNs, the coating tools, feed rate (f) and cutting speed (V) values are used while at the output layer the surface roughness values are used. They are used to train and test multilayered, hierarchically connected and directed networks with varying numbers of the hidden layers using back-propagation scaled conjugate gradient (SCG) and Levenberg-Marquardt (LM) algorithms with the logistic sigmoid transfer function. The experimental values and ANN predictions are compared by statistical error analyzing methods. It is shown that the SCG model with nine neurons in the hidden layer has produced absolute fraction of variance (R^2) values about 0.99985 for the training data, and 0.99983 for the test data; root mean square error (RMSE) values are smaller than 0.00265; and mean error percentage (MEP) are about 1.13458 and 1.88698 for the training and test data, respectively. Therefore, the surface roughness value has been determined by the ANN with an acceptable accuracy.

The experimental investigation of the effects of uncoated, PVD- and CVD-coated cemented carbide inserts and cutting parameters on surface roughness in CNC turning and its prediction using artificial neural networks

A neural network approach for early cost estimation of packaging products

A new technique for performing form-feature recognition using the principles of neural networks is discussed. Neural nets require parallel input of data, which, in this case, are B-rep solid models of parts. An input format has been developed which includes face descriptions and face-face relationships. An algorithm for recognition using neural-net-based techniques has been developed, and a suitable net architecture, which is similar to the multilayer perceptron in function and which implements the algorithm, has been designed. The net architecture is described, and a few examples are presented which highlight the strengths and weaknesses of the recognition algorithm.

Automatic form-feature recognition using neural-network-based techniques on boundary representations of solid models

In this paper, we propose a new multiuser nonlinear optical cryptosystem using fractional-order vortex speckle (FOVS) patterns as security keys. In conventional optical cryptosystems, mostly random phase masks are used as the security keys which are prone to various attacks such as brute force attack. In the current study, the FOVSs are generated optically by the scattering of the fractional-order vortex beam, known for azimuthal phase and helical wavefronts, through a ground glass diffuser. FOVSs have a remarkable property that makes them almost impossible to replicate. In the input plane, the amplitude image is first phase encoded and then modulated with the FOVS phase mask to obtain the complex image. This complex image is further processed to obtain the encrypted image using the proposed method. Two private security keys are obtained through polar decomposition which enables the multi-user capability in the cryptosystem. The robustness of the proposed method is tested against existing attacks such as the contamination attack and known-plaintext attack. Numerical simulations confirm the validity and feasibility of the proposed method.

/pdf/multi-user-nonlinear-optical-cryptosystem-based-on-polar-3a3x40v7.pdf

Multi-User Nonlinear Optical Cryptosystem Based on Polar Decomposition and Fractional Vortex Speckle Patterns

3D Incoherent Imaging Using an Ensemble of Sparse Self-Rotating Beams

In this paper, we propose a new asymmetric cryptosystem for phase image encryption, using the physically unclonable functions (PUFs) as security keys. For encryption, the original amplitude image is first converted into a phase image and modulated with a PUF to obtain a complex image. This complex image is then illuminated with a plane wave, and the complex wavefront at a distance d is recorded. The real part of the complex wavefront is further processed to obtain the encrypted image and the imaginary part is kept as the private key. The polar decomposition approach is utilized to generate two more private security keys and to enable the multi-user capability in the cryptosystem. Numerical simulations confirm the feasibility of the proposed method. 

/pdf/an-asymmetric-optical-cryptosystem-using-physically-2fnzcnbz.pdf

An Asymmetric Optical Cryptosystem Using Physically Unclonable Functions in the Fresnel Domain

Extracting the grain size from the microscopic images is a rigorous task involving much human expertise and manual effort. While calculating the grain size, we will be utilizing a finite number of particles which may lead to an uncertainty in the measurement. To avoid this difficulty, we utilize a simple mathematical tool, the auto-correlation function, to determine the grain size. The random particle distribution and the finite width Gaussian histogram of particle size has motivated us to utilize the auto-correlation function, which has been extensively studied for finding the size of random optical patterns. The finite width of the correlation function provides the grain size, and the difference in correlation length along two mutually independent directions provides information about the asymmetry present in the particle distribution, i.e., the deviation from a spherical shape. The results may find applications in material, pharmaceutical, chemical, and biological studies where extracting the grain size is essential.

Shashikanth Prabhakar

Papers

Automatic form-feature recognition using neural-network-based techniques on boundary representations of solid models

Multi-User Nonlinear Optical Cryptosystem Based on Polar Decomposition and Fractional Vortex Speckle Patterns

3D Incoherent Imaging Using an Ensemble of Sparse Self-Rotating Beams

An Asymmetric Optical Cryptosystem Using Physically Unclonable Functions in the Fresnel Domain

Analysing the Grain size and asymmetry of the particle distribution using auto-correlation technique