A Framework for Self-Realizing Process Models for Additive Manufacturing

2011 ◽  
Author(s):  
Sungshik Yim ◽  
David W. Rosen
Keyword(s):  
Neural Network ◽  
Additive Manufacturing ◽  
Process Planning ◽  
Process Model ◽  
Selective Laser Sintering ◽  
Process Models ◽  
Clustering Methods ◽  
In Series ◽  
Design Requirements ◽  
Planning Problems

This research discusses a framework for automating process model realization for additive manufacturing. The models map relationships from design requirements to process variables and can be utilized for future process planning. A repository is employed to collect data and contains previous process plans and corresponding design requirements. The framework organizes data through a statistical clustering method and builds regression models using a multi-layer neural network. Hierarchical and k-means clustering methods are employed in series to manage the data. A two layer neural network and augmented training algorithm are employed to build process models. The framework has been tested with Stereolithography and Selective Laser Sintering process planning problems to demonstrate its usefulness.

Toward Metamodels for Composable and Reusable Additive Manufacturing Process Models

2014 ◽  
Vol 136 (6) ◽  
Author(s):  
Paul Witherell ◽  
Shaw Feng ◽  
Timothy W. Simpson ◽  
David B. Saint John ◽  
Pan Michaleris ◽  
...  
Keyword(s):  
Additive Manufacturing ◽  
Metal Powder ◽  
Manufacturing Process ◽  
Process Model ◽  
Model Development ◽  
Process Models ◽  
Powder Bed Fusion ◽  
Powder Bed ◽  
Future Work ◽  
Am Processes

In this paper, we advocate for a more harmonized approach to model development for additive manufacturing (AM) processes, through classification and metamodeling that will support AM process model composability, reusability, and integration. We review several types of AM process models and use the direct metal powder bed fusion AM process to provide illustrative examples of the proposed classification and metamodel approach. We describe how a coordinated approach can be used to extend modeling capabilities by promoting model composability. As part of future work, a framework is envisioned to realize a more coherent strategy for model development and deployment.

scholarly journals Neural network adaptive real-time optimizing control of industrial processes

2017 ◽  
Vol 19 ◽  
pp. 129
Author(s):  
Normah Abdullah ◽  
Muhammad Anas Mohd Razali ◽  
Mohammed Hamood Othman Ahmed ◽  
Mohd Zaki Nuawi ◽  
Mohd Marzuki Mustafa ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Process Model ◽  
Chemical Engineering ◽  
Coefficient Of Determination ◽  
Engineering Research ◽  
In Series ◽  
Artificial Neural Network Ann ◽  
Optimizing Control

<p>Real-time optimization (RTO) has attracted considerable interest among researchers and industries for being able to optimise the plant economics such as product efficiency, product quality and process safety in the wake of increasing global competitions. The success of RTO depends much on the quality of model being used in the optimisation. The present study was carried out to explore the use of artificial neural network (ANN) to improve the quality of the model being used in the modified two step (MTS) technique. The MTS is a real-time optimising control algorithm of the modifier adaptation scheme which is used to determine the optimum steady-state control set-points. The proposed new version of MTS technique will be using process model based on ANN. A laboratory scale process of a two continuous stirred tank heat exchanger in series (2CSTHEs) is used as a case study. The multilayer feed forward ANN architecture 4-10-6 with linear function was used to model the 2CSTHEs and then integrates into the MTS technique, the resulted algorithm will be known as Iterative Neural Network Modified Two Step (INNMTS) technique. Simulation studies were conducted to test the performance of the INNMTS technique on the 2CSTHEs process. The results show that the overall value for the coefficient of determination(R<sup>2</sup>)is equal to one, which indicates adequacy of the model proposed for the prediction of the behavior of 2CSTHEs system. When NN model of 2CSTHEs is applied to the INNMTS technique, the model-plant mismatch is greatly reduced to almost zero, which indicates by significant reduction in the number of iterations to 5which requires by INNMTS compared to 16 iterations by the MTS technique to converge to optimal real solution.</p><p>Chemical Engineering Research Bulletin 19(2017) 129-138</p>

scholarly journals Integrated component-support topology optimization for additive manufacturing with post-machining

2019 ◽  
Vol 25 (2) ◽  
pp. 255-265 ◽  
Author(s):  
Matthijs Langelaar
Keyword(s):  
Topology Optimization ◽  
Additive Manufacturing ◽  
High Performance ◽  
Process Model ◽  
Process Models ◽  
Content Type ◽  
Wide Range ◽  
Support Layout ◽  
Overhang Angle ◽  
Subtractive Machining

PurposeThe purpose of this paper is to communicate a method to perform simultaneous topology optimization of component and support structures considering typical metal additive manufacturing (AM) restrictions and post-print machining requirements.Design/methodology/approachAn integrated topology optimization is proposed using two density fields: one describing the design and another defining the support layout. Using a simplified AM process model, critical overhang angle restrictions are imposed on the design. Through additional load cases and constraints, sufficient stiffness against subtractive machining loads is enforced. In addition, a way to handle non-design regions in an AM setting is introduced.FindingsThe proposed approach is found to be effective in producing printable optimized geometries with adequate stiffness against machining loads. It is shown that post-machining requirements can affect optimal support structure layout.Research limitations/implicationsThis study uses a simplified AM process model based on geometrical characteristics. A challenge remains to integrate more detailed physical AM process models to have direct control of stress, distortion and overheating.Practical implicationsThe presented method can accelerate and enhance the design of high performance parts for AM. The consideration of post-print aspects is expected to reduce the need for design adjustments after optimization.Originality/valueThe developed method is the first to combine AM printability and machining loads in a single topology optimization process. The formulation is general and can be applied to a wide range of performance and manufacturability requirements.

Case-Based Retrieval Approach of Supporting Process Planning in Layer-Based Additive Manufacturing

2007 ◽  
Author(s):  
Sungshik Yim ◽  
David Rosen
Keyword(s):  
Additive Manufacturing ◽  
Process Planning ◽  
Description Logic ◽  
Retrieval Method ◽  
Storage And Retrieval ◽  
Process Plans ◽  
Requirements Process ◽  
Design And Manufacturing ◽  
Design Requirements ◽  
Case Based

The process planning task for a given design problem in additive manufacturing can be greatly enhanced by referencing previously developed process plans. In this research, a case-based retrieval method, called the DFM (Design For Manufacturing) framework, that retrieves previously formulated process plans is proposed to support process planning. To support the DFM Framework, we have developed an information model (ontology) of manufacturing process knowledge in the domain of additive manufacturing processes, including design requirements, process plans, and rules that map requirements to plans. Description Logic (DL) is identified as an appropriate mathematical formalism to encode the ontology and realize the computational mapping between the design and manufacturing domains. Storage and retrieval algorithms are presented that, first, structure the repository of previous DFM problems and, second, enable DFM problems to be retrieved.

IN-PROCESS MODEL GENERATION FOR THE PROCESS PLANNING OF A PRISMATIC PART

2003 ◽  
Vol 02 (02) ◽  
pp. 147-162 ◽  
Author(s):  
SANG C. PARK ◽  
GOPALAN MUKUNDAN ◽  
SHUXIN GU ◽  
GUSTAV J. OLLING
Keyword(s):  
Process Planning ◽  
Process Model ◽  
Process Models ◽  
Geometric Algorithms ◽  
Planning Stage ◽  
Geometric Problems ◽  
Polygonal Chain ◽  
3D Geometry ◽  
Initial Process ◽  
Generation Problem

It is very essential to have 3D geometry of In-Process Models (IPMs) for the integration of various activities related to process planning. The accuracy of IPMs is not critical at the initial process planning stage but it becomes very important for the detailed process planning stage since inaccurate IPMs may result in costly mistakes. This paper proposes a procedure to generate accurate IPMs for the detailed process planning of a prismatic part. We transform the IPM generation problem into well-known 2D geometric problems, and use 2D geometric algorithms (2D curve offset, Voronoi diagram and polygonal chain intersection) instead of generalized 3D algorithms. Since highly optimized solutions are available for these 2D geometric problems, the proposed procedure achieves the efficiency and robustness by simply combining proven 2D geometric algorithms.

scholarly journals Trace Clustering: A Preprocessing Method to Improve the Performance of Process Discovery

2021 ◽  
Vol 10 (09) ◽  
pp. 116-121
Author(s):  
Huiling LI ◽  
Shuaipeng ZHANG ◽  
Xuan SU
Keyword(s):  
Process Model ◽  
Process Mining ◽  
Process Models ◽  
Clustering Methods ◽  
Clustering Method ◽  
Model Quality ◽  
Process Discovery ◽  
Event Logs ◽  
Clustering Model ◽  
Preprocessing Method

The information system collects a large number of business process event logs, and process discovery aims to discover process models from the event logs. Many process discovery methods have been proposed, but most of them still have problems when processing event logs, such as low mining efficiency and poor process model quality. The trace clustering method allows to decompose original log to effectively solve these problems. There are many existing trace clustering methods, such as clustering based on vector space approaches, context-aware trace clustering, model-based sequence clustering, etc. The clustering effects obtained by different trace clustering methods are often different. Therefore, this paper proposes a preprocessing method to improve the performance of process discovery, called as trace clustering. Firstly, the event log is decomposed into a set of sub-logs by trace clustering method, Secondly, the sub-logs generate process models respectively by the process mining method. The experimental analysis on the datasets shows that the method proposed not only effectively improves the time performance of process discovery, but also improves the quality of the process model.

scholarly journals Quantifying Discretization Errors in Electrophoretically-Guided Micro Additive Manufacturing

Micromachines ◽  
2018 ◽  
Vol 9 (9) ◽  
pp. 447 ◽  
Author(s):  
David Pritchet ◽  
Newell Moser ◽  
Kornel Ehmann ◽  
Jian Cao ◽  
Jiaxing Huang
Keyword(s):  
Additive Manufacturing ◽  
Process Model ◽  
Microelectrode Array ◽  
Colloidal Particles ◽  
Pulse Width Modulation ◽  
Mean Square Displacement ◽  
Time Discretization ◽  
Process Models ◽  
Particle Trajectories ◽  
Discretization Errors

This paper presents process models for a new micro additive manufacturing process termed Electrophoretically-guided Micro Additive Manufacturing (EPμAM). In EPμAM, a planar microelectrode array generates the electric potential distributions which cause colloidal particles to agglomerate and deposit in desired regions. The discrete microelectrode array nature and the used pulse width modulation (PWM) technique for microelectrode actuation create unavoidable process errors—space and time discretization errors—that distort particle trajectories. To combat this, we developed finite element method (FEM) models to study trajectory deviations due to these errors. Mean square displacement (MSD) analysis of the computed particle trajectories is used to compare these deviations for several electrode geometries. The two top-performing electrode geometries evaluated by MSD were additionally investigated through separate case studies via geometry variation and MSD recomputation. Furthermore, separate time-discretization error simulations are also studied where electrode actuating waveforms were simulated. The mechanical impulse of the electromechanical force, generated from these waveforms is used as the basis for comparison. The obtained results show a moderate MSDs variability and significant differences in the computed mechanical impulses for the actuating waveforms. The observed limitations of the developed process model and of the error comparison technique are briefly discussed and future steps are recommended.

Politikvermittlung an der Schnittstelle von Unterhaltung und Information : Political communication at the interface of entertainment and information

SPIEL ◽  
2019 ◽  
Vol 4 (1) ◽  
pp. 121-145
Author(s):  
Larissa Leonhard ◽  
Anne Bartsch ◽  
Frank M. Schneider
Keyword(s):  
Information Processing ◽  
Political Participation ◽  
Knowledge Acquisition ◽  
Political Communication ◽  
Information Seeking ◽  
Process Model ◽  
Political Information ◽  
Process Models ◽  
Dual Process ◽  
Dual Process Model

This article presents an extended dual-process model of entertainment effects on political information processing and engagement. We suggest that entertainment consumption can either be driven by hedonic, escapist motivations that are associated with a superficial mode of information processing, or by eudaimonic, truth-seeking motivations that prompt more elaborate forms of information processing. This framework offers substantial extensions to existing dual-process models of entertainment by conceptualizing the effects of entertainment on active and reflective forms of information seeking, knowledge acquisition and political participation.

A Novel Automatic Modulation Classification Method Using Attention Mechanism and Hybrid Parallel Neural Network

2021 ◽  
Vol 11 (3) ◽  
pp. 1327
Author(s):  
Rui Zhang ◽  
Zhendong Yin ◽  
Zhilu Wu ◽  
Siyang Zhou
Keyword(s):  
Neural Network ◽  
Communication Systems ◽  
Parallel Structure ◽  
Modulation Classification ◽  
Automatic Modulation Classification ◽  
Spatial Features ◽  
Temporal Features ◽  
Different Types ◽  
In Series ◽  
Parallel Network

Automatic Modulation Classification (AMC) is of paramount importance in wireless communication systems. Existing methods usually adopt a single category of neural network or stack different categories of networks in series, and rarely extract different types of features simultaneously in a proper way. When it comes to the output layer, softmax function is applied for classification to expand the inter-class distance. In this paper, we propose a hybrid parallel network for the AMC problem. Our proposed method designs a hybrid parallel structure which utilizes Convolution Neural Network (CNN) and Gate Rate Unit (GRU) to extract spatial features and temporal features respectively. Instead of superposing these two categories of features directly, three different attention mechanisms are applied to assign weights for different types of features. Finally, a cosine similarity metric named Additive Margin softmax function, which can expand the inter-class distance and compress the intra-class distance simultaneously, is adopted for output. Simulation results demonstrate that the proposed method can achieve remarkable performance on an open access dataset.

scholarly journals LVD-NMPC: A learning-based vision dynamics approach to nonlinear model predictive control for autonomous vehicles

2021 ◽  
Vol 18 (3) ◽  
pp. 172988142110195
Author(s):  
Sorin Grigorescu ◽  
Cosmin Ginerica ◽  
Mihai Zaha ◽  
Gigel Macesanu ◽  
Bogdan Trasnea
Keyword(s):  
Neural Network ◽  
Model Predictive Control ◽  
Predictive Control ◽  
Nonlinear Model ◽  
Autonomous Vehicles ◽  
Process Model ◽  
Network Performance ◽  
Vision System ◽  
Nonlinear Model Predictive Control ◽  
Scaled Model

In this article, we introduce a learning-based vision dynamics approach to nonlinear model predictive control (NMPC) for autonomous vehicles, coined learning-based vision dynamics (LVD) NMPC. LVD-NMPC uses an a-priori process model and a learned vision dynamics model used to calculate the dynamics of the driving scene, the controlled system’s desired state trajectory, and the weighting gains of the quadratic cost function optimized by a constrained predictive controller. The vision system is defined as a deep neural network designed to estimate the dynamics of the image scene. The input is based on historic sequences of sensory observations and vehicle states, integrated by an augmented memory component. Deep Q-learning is used to train the deep network, which once trained can also be used to calculate the desired trajectory of the vehicle. We evaluate LVD-NMPC against a baseline dynamic window approach (DWA) path planning executed using standard NMPC and against the PilotNet neural network. Performance is measured in our simulation environment GridSim, on a real-world 1:8 scaled model car as well as on a real size autonomous test vehicle and the nuScenes computer vision dataset.

Sign in / Sign up

Export Citation Format

Share Document