Neural network tomography: Network replication from output surface geometry

The geometry design and machining of blades for axial-flow fans are important issues because the twisted profile and flowfield of blades are complicated. The rapid design of a blade that performs well and satisfies machining requirements is one of the goals in designing fluid machinery blades. In this study, an integrated approach combining computational fluid dynamics (CFD), an artificial neural network, an optimization method and a machining method is proposed to design a three-dimensional blade for an axial-flow fan. From the machining point of view, the three-dimensional surface geometry of a fan blade can be defined as the swept surface of the tool path created by using the generated machining method. By taking advantage of its powerful learning capability, a back-propagation artificial neural network is used to set up the flowfield models and to forecast the flow performance of the axial-flow fan. The desired optimal blade geometry is obtained by using a complex optimization method.

Download Full-text

Neural-network calibration of a multiple-line laser-camera range sensor for 3D surface-geometry measurement

10.1117/12.817411 ◽

2008 ◽

Author(s):

Chris Yu-Liang Liu ◽

Jonathan Kofman

Keyword(s):

Neural Network ◽

Surface Geometry ◽

Range Sensor ◽

Multiple Line ◽

3D Surface ◽

Geometry Measurement

Download Full-text

A Study of Vision-Based Measurement of Weld Joint Shape Incorporating the Neural Network

Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture ◽

10.1243/pime_proc_1994_208_060_02 ◽

1994 ◽

Vol 208 (1) ◽

pp. 61-69 ◽

Cited By ~ 2

Author(s):

K-Y Bae ◽

S-J Na

Keyword(s):

Neural Network ◽

Three Dimensional ◽

Ccd Camera ◽

Image Plane ◽

Welding Distortion ◽

Surface Geometry ◽

Visual Sensing ◽

Laser Stripe ◽

The Neural Network ◽

A Charge

Visual sensing of the surface geometry is often necessary to inspect and evaluate the quality of welded joints as well as to sense the transient distortion of a structure during welding for the feedback of its current geometry. This investigation presents a simple and non-contact digitization method of the vision-based system for measuring the three-dimensional surface geometry of the object distorted by welding. Its basic principles are based on the equation derived from the geometric optics, for which the illumination of the laser beam was controlled in the form of the projected plane. This method utilized a 10 mW He-Ne laser for the structured light and a charge coupled device (CCD) camera as the vision sensor. When the laser stripe is projected on to the weldment, a minute deviation from the perfect plane existing on the specimen surface causes a distortion of the stripe. The shape and amount of the weldment distortion can be then calculated by analysing the distorted laser stripe. In this study, a neural network was proposed and implemented for recognizing the laser stripe features from the image plane. A calibration scheme of corresponding an image to the world position was also adopted for determining the sectional features of the welding distortion. The feasibility of determining the welding distortion by the proposed vision-based system was demonstrated through the experiments with various types of specimen.

Download Full-text

Stable learning for neural network tomography by using back projection type image

2014 IEEE 7th International Workshop on Computational Intelligence and Applications (IWCIA) ◽

10.1109/iwcia.2014.6988102 ◽

2014 ◽

Author(s):

Masaru Teranishi

Keyword(s):

Neural Network ◽

Network Tomography ◽

Back Projection ◽

Stable Learning

Download Full-text

Improved neural network tomography by initial learning with coarse reconstructed image

Neurocomputing ◽

10.1016/j.neucom.2015.03.103 ◽

2016 ◽

Vol 172 ◽

pp. 399-404

Author(s):

Masaru Teranishi

Keyword(s):

Neural Network ◽

Reconstructed Image ◽

Network Tomography ◽

Initial Learning

Download Full-text

Hybrid Position/Force Control in Robotised Machining

Solid State Phenomena ◽

10.4028/www.scientific.net/ssp.210.192 ◽

2013 ◽

Vol 210 ◽

pp. 192-199 ◽

Cited By ~ 7

Author(s):

Piotr Gierlak

Keyword(s):

Neural Network ◽

Force Control ◽

Robotic Manipulator ◽

Machining Process ◽

Surface Geometry ◽

Machining Processes ◽

Machined Surface ◽

Robot Trajectory ◽

Force Control System ◽

Accuracy And Repeatability

The article presents an application of the neural hybrid position/force control of the robotic manipulator. Realisation of many machining processes requires an application of the hybrid position/force control in order to perform the desired robot trajectory, which results from the machined surface geometry, and the desired tool downforce. The application of the robotic manipulator for realisation of the machining process enables to elimination of human handwork and ensures greater accuracy and repeatability of products. In the article is presented mainly the application of the hybrid position/force control system, in which a multilayer neural network is applied in order to manipulator nonlinearities compensation.

Download Full-text