Tolga Kurtoglu from Los Gatos, CA, age 47

Us Patents

System And Method For Computer Numerical Control (Cnc) Tool Without Undercut Features Operations Planning With The Aid Of A Digital Computer
view source
US Patent:

20200183356, Jun 11, 2020
Filed:

Feb 14, 2020
Appl. No.:

16/791733
Inventors:

- Sandviken, SE
Christian Fritz - Menlo Park CA, US
Gregory Burton - Mountain View CA, US
Tolga Kurtoglu - San Jose CA, US
International Classification:

G05B 19/4097
G05B 19/4093
Abstract:

A Web-based system and method creates one or more qualitatively distinct process plans for machining a part. The surfaces of the part are modeled and parameters for a plurality of CNC machining tools are obtained, including the orientations along which the tool cuts away raw material. A maximal set of translations for each tool is also obtained, where each translation includes a collision-free orientation of the tool and a maximal machinable volume of material removable from the part in that orientation. A search engine navigates through a hierarchically-structured search space that starts at an initial state and transitions to successive states based on actions that satisfy a cost constraint function. Each state and each action includes a tool, orientation of the tool, and a maximal machinable volume. The search ends when a goal condition is satisfied. The actions constitute the process plan.

System And Method For Detecting Anomaly Of A Machine Tool
view source
US Patent:

20190094108, Mar 28, 2019
Filed:

Nov 26, 2018
Appl. No.:

16/200014
Inventors:

- Palo Alto CA, US
Rajinderjeet Singh Minhas - Mountain View CA, US
Arvind Rangarajan - Santa Clara CA, US
Tolga Kurtoglu - San Jose CA, US
Johan de Kleer - Los Altos CA, US
International Classification:

G01M 13/00
G05B 19/4065
B23Q 17/09
G05B 23/02
Abstract:

A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

Planning Of Computer Numerical Control (Cnc) Machining Operations With The Aid Of A Digital Computer
view source
US Patent:

20170220028, Aug 3, 2017
Filed:

Jan 29, 2016
Appl. No.:

15/011312
Inventors:

- Palo Alto CA, US
Christian Fritz - Mento Park CA, US
Gregory Burton - Mountain View CA, US
Tolga Kurtoglu - San Jose CA, US
International Classification:

G05B 19/4097
Abstract:

A Web-based system and method creates one or more qualitatively distinct process plans for machining a part. The surfaces of the part are modeled and parameters for a plurality of CNC machining tools are obtained, including the orientations along which the tool cuts away raw material. A maximal set of translations for each tool is also obtained, where each translation includes a collision-free orientation of the tool and a maximal machinable volume of material removable from the part in that orientation. A search engine navigates through a hierarchically-structured search space that starts at an initial state and transitions to successive states based on actions that satisfy a cost constraint function. Each state and each action includes a tool, orientation of the tool, and a maximal machinable volume. The search ends when a goal condition is satisfied. The actions constitute the process plan.

Computer-Implemented Method And System For Machine Tool Damage Assessment, Prediction, And Planning In Manufacturing Shop Floor
view source
US Patent:

20160091393, Mar 31, 2016
Filed:

Sep 26, 2014
Appl. No.:

14/499060
Inventors:

- Palo Alto CA, US
Rajinderjeet Singh Minhas - Mountain View CA, US
Arvind Rangarajan - Santa Clara CA, US
Tolga Kurtoglu - San Jose CA, US
Johan de Kleer - Los Altos CA, US
International Classification:

G01M 13/00
B23Q 17/09
Abstract:

A self-aware machine platform is implemented through analyzing operational data of machining tools to achieve machine tool damage assessment, prediction and planning in manufacturing shop floor. Machining processes are first identified by matching similar processes through an ICP algorithm. Machining processes are further clustered by Hotelling's T-squared statistics. Degradation of the machining tool is detected through a trend of the operational data within a cluster of machining processes by a monotonicity test, and the remaining useful life of the machining tool is predicted through a particle filter by extrapolating the trend under a first-order Markov process. In addition, process anomalies across machines are detected through a combination of outlier detection methods including SOMs, multivariate regression, and robust Mahalanobis distance. Warnings and recommendations are flexibly provided to manufacturing shop floor based on policy choice.

Automated Metrology And Model Correction For Three Dimensional (3D) Printability
view source
US Patent:

20150269282, Sep 24, 2015
Filed:

Mar 18, 2014
Appl. No.:

14/217854
Inventors:

- Palo Alto CA, US
Walter Kim - San Francisco CA, US
Arvind Rangarajan - Santa Clara CA, US
Tolga Kurtoglu - San Jose CA, US
Assignee:

Palo Alto Research Center Incorporated - Palo Alto CA
International Classification:

G06F 17/50
G06T 19/20
G06T 17/10
Abstract:

A system and a method automate metrology, measurement, and model correction of a three dimensional (3D) model for 3D printability. Slices of the 3D model are received or generated. The slices represent 2D solids of the 3D model to be printed in corresponding print layers. Medial axis transforms of the slices are calculated. The medial axis transforms represent the slices in terms of corresponding medial axes. A local feature size at any point along a boundary of the slices is determined as the shortest distance from the point to a corresponding medial axis.

System For Visualizing A Three Dimensional (3D) Model As Printed From A 3D Printer
view source
US Patent:

20150269289, Sep 24, 2015
Filed:

Mar 18, 2014
Appl. No.:

14/217811
Inventors:

- Palo Alto CA, US
Tolga Kurtoglu - San Jose CA, US
Saigopal Nelaturi - Palo Alto CA, US
Arvind Rangarajan - Santa Clara CA, US
Assignee:

Palo Alto Research Center Incorporated - Palo Alto CA
International Classification:

G06F 17/50
G06T 17/00
Abstract:

A system and a method visualize three dimensional (3D) printability of a 3D model. A 3D printing process of the 3D model is simulated to generate a layered 3D model describing the 3D model as printed. A visual rendering of the layered 3D model is generated, and the visual rendering of the layered 3D model is displayed on a display device.

Automated Design And Manufacturing Feedback For Three Dimensional (3D) Printability
view source
US Patent:

20150269290, Sep 24, 2015
Filed:

Mar 18, 2014
Appl. No.:

14/217891
Inventors:

- Palo Alto CA, US
Walter Kim - San Francisco CA, US
Arvind Rangarajan - Santa Clara CA, US
Tolga Kurtoglu - San Jose CA, US
Assignee:

Palo Alto Research Center Incorporated - Palo Alto CA
International Classification:

G06F 17/50
G06T 17/10
Abstract:

A system and a method assess the three dimensional (3D) printability of a 3D model. Slices of the 3D model are received or generated. The slices represent two dimensional (2D) solids of the 3D model to be printed in corresponding print layers. Further, printing of the slices is simulated to identify corresponding printable slices.

Automated Augmented Model Extension For Robust System Design
view source
US Patent:

20150051890, Feb 19, 2015
Filed:

Aug 15, 2013
Appl. No.:

13/967503
Inventors:

- Palo Alto CA, US
Daniel G. Bobrow - Palo Alto CA, US
Tolga Kurtoglu - San Jose CA, US
Johan de Kleer - Los Altos CA, US
Assignee:

Palo Alto Research Center Incorporated - Palo Alto CA
International Classification:

G06F 17/50
US Classification:

703 6
Abstract:

A method is provided for automatically generating an augmented model of a cyber-physical component. Cyber-physical components are built from or depend upon the synergy computational and physical components. The method includes: reading an input model () into a processor (), the input model describing a nominal mode of operation for a physical component modeled by the input model; parsing with the processor the input model to generate a parse thereof; analyzing with the processor the parse of the input model; and automatically writing with the processor an augmented model () for the physical component from the input model based on the analysis, the augmented model describing the nominal mode of operation for the modeled physical component and at least one alternate mode of operation for the modeled physical component which is different from the nominal mode of operation. The augmented component models can be used to provide analyses of the behavior of faulted systems, including diagnosis, reliability, resiliency to faults and maintainability.