Caterpillar Inc.

Christopher Ha

Yang Liu

Shawn Nainan Mathew

Qi Wang

Julian Andres Norato

Badrinarayan Parthasarathy Athreya

Sungmoon Jung

Nolan S Finch

David J McIntyre

Praveen Halepatali

David Longanbach

Yihong Yang

Chau Le

Torsten Van Wassenhove

Christopher M Burkard

Diana E Huerta

Fiona J O'Laughlin

Taylor Jensen

Saniye Gizem Aydin

Arthur W Scheck

Sanghyun Shin

The system receives an input indicating a device and an indication of an issue associated with the device and a natural language input describing a troubleshooting procedure performed to resolve the issue. Based on the input indicating the device, and the indication of the issue associated with the device, the system maps the natural language input into a predetermined troubleshooting procedure associated with the device. The system receives an input indicating a result among the multiple results associated with the predetermined troubleshooting procedure. Based on the result of the predetermined troubleshooting procedure, the system determines a troubleshooting procedure to perform. The troubleshooting procedure includes a repair step associated with the issue or a testing step associated with the issue and is different from the troubleshooting procedure performed to resolve the issue. The system suggests the troubleshooting procedure to an operator associated with the device.

Resolving an issue experienced by a particular device using natural language input

A method for dynamically creating and validating a predictive analytics model to transform data into actionable insights the method comprising: identifying an event, selectively tagging, based on analytics expertise, at least one time series data area (data area), where the identified event occurred, comparing data area where the identified event is tagged with the data area where the identified event is not tagged, building, based on analytics expertise, the predictive analytics model embodying the classification generated by selective tagging, displaying the visual indicia generated by executing the predictive analytics model, and validating the predictive model based on a feedback from at least one domain expert.

Collaborative system and method for validating equipment failure models in an analytics crowdsourcing environment

A method for loading a payload carrier of a machine includes receiving, from a camera on the machine, a two-dimensional image of an interior of the payload carrier as material is loaded into the payload carrier. The method further includes filtering the image to identify a contour of the loaded material and determining an area of the contour. The method further includes controlling a display device indicate the determined area.

Optimizing loading of a payload carrier of a machine

A method for loading a payload carrier of a machine includes receiving, from a camera on the machine, a two-dimensional image of an interior of the payload carrier as material is loaded into the payload carrier. The method further includes sectioning the two-dimensional image into a plurality of regions, and determining, for individual of the regions, whether the region includes a representative of fill material. The method may also include determining a fill volume based on the regions having fill and those not having fill.

Determining payload carrier volume using a neural network

A method for tracking workers at a worksite is disclosed. The method includes acquiring a video of the worksite and detecting a movement of objects in the video. Each object is represented by a plurality of pixels. The method includes identifying an item associated with at least one object by clustering a set of pixels of the plurality of pixels based on a color of the set of pixels. Next, the method includes determining the item as a hard hat based on at least a shape of the set of pixels, and identifying the object as a specific worker based on the color of the set of pixels. The method also includes generating a movement data associated with the specific worker based on a tracking of the hard hat.

Method and system for tracking workers at worksites

A system for determining a welding sequence is disclosed. The system may have a welding sequence generator configured to create an initial population of welding sequences based on a user-generated constraint. The system may also have a welding simulator configured to simulate welding for at least one welding sequence in the initial population of welding sequences to model distortion for the at least one welding sequence. The welding sequence generator may be further configured to receive the distortion for the at least one welding sequence in the initial population from the welding simulator, determine whether a merit value derived from at least the distortion for the at least one welding sequence satisfies one or more predetermined criteria, output the at least one welding sequence as a potential welding sequence if the merit value satisfies the predetermined criteria.

Method and system for determining welding sequences

A wear estimation system for a component of a machine includes a geolocation unit, a non-transitory computer-readable medium bearing a component wear estimate program, a controller, and an interface device. The geolocation unit is configured to generate a location signal indicative of a location of the machine. The controller is in operable communication with the geolocation unit to receive the location signal therefrom and is configured to execute the component wear estimate program. The interface device is configured to display a graphical user interface of the component wear estimate program. The component wear estimate program is configured to determine an estimated part life for the component based upon an environmental characteristic of the location; to track an actual usage amount for the component; and to indicate, through the graphical user interface, when the usage amount of the component exceeds a threshold percentage of the estimated part life.

System and method for estimating part wear based on environment

Growing community of inventors

Champaign, IL, United States of America

Christopher Ha