Patents by Inventor Pradyumna Sampath
Pradyumna Sampath has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11348598Abstract: Systems, methods, and devices for monitoring industrial equipment using audio are described herein. One system includes two computing devices. The first computing device can receive, from an audio sensor, audio sensed during operation of industrial equipment, extract a plurality of features from the audio, determine whether any portion of the audio is anomalous, and send, upon determining a portion of the audio is anomalous, the anomalous portion of the audio to the second, remotely located, computing device. The second computing device can provide the anomalous portion of the audio to a user to determine whether the anomalous portion of the audio corresponds to a fault occurring in the equipment, and receive, from the user upon determining the anomalous portion of the audio corresponds to a fault occurring in the equipment, input indicating the anomalous portion of the audio corresponds to the fault to learn fault patterns in the equipment.Type: GrantFiled: October 22, 2020Date of Patent: May 31, 2022Assignee: HONEYWELL INTERNATIONA, INC.Inventors: Ramprasad Yelchuru, Shreyan Chowdhury, Pradyumna Sampath
-
Patent number: 11222625Abstract: Systems and methods for training a control panel to recognize user defined and preprogrammed sound patterns are provided. Such systems and methods can include the control panel operating in a learning mode, receiving initial ambient audio from a region, and saving the initial ambient audio as an audio pattern in a memory device of the control panel. Such systems and methods can also include the control panel operating in an active mode, receiving subsequent ambient audio from the region, using an audio classification model to make an initial determination as to whether the subsequent ambient audio matches or is otherwise consistent with the audio pattern, determining whether the initial determination is correct, and when the control panel determines that the initial determination is incorrect, modifying or updating the audio classification model for improving the accuracy in detecting future consistency with the audio pattern.Type: GrantFiled: April 15, 2019Date of Patent: January 11, 2022Assignee: Ademco Inc.Inventors: Pradyumna Sampath, Ramprasad Yelchuru, Purnaprajna R. Mangsuli
-
Publication number: 20210043221Abstract: Systems, methods, and devices for monitoring industrial equipment using audio are described herein. One system includes two computing devices. The first computing device can receive, from an audio sensor, audio sensed during operation of industrial equipment, extract a plurality of features from the audio, determine whether any portion of the audio is anomalous, and send, upon determining a portion of the audio is anomalous, the anomalous portion of the audio to the second, remotely located, computing device. The second computing device can provide the anomalous portion of the audio to a user to determine whether the anomalous portion of the audio corresponds to a fault occurring in the equipment, and receive, from the user upon determining the anomalous portion of the audio corresponds to a fault occurring in the equipment, input indicating the anomalous portion of the audio corresponds to the fault to learn fault patterns in the equipment.Type: ApplicationFiled: October 22, 2020Publication date: February 11, 2021Inventors: Ramprasad Yelchuru, Shreyan Chowdhury, Pradyumna Sampath
-
Patent number: 10867622Abstract: Systems, methods, and devices for monitoring industrial equipment using audio are described herein. One system includes two computing devices. The first computing device can receive, from an audio sensor, audio sensed during operation of industrial equipment, extract a plurality of features from the audio, determine whether any portion of the audio is anomalous, and send, upon determining a portion of the audio is anomalous, the anomalous portion of the audio to the second, remotely located, computing device. The second computing device can provide the anomalous portion of the audio to a user to determine whether the anomalous portion of the audio corresponds to a fault occurring in the equipment, and receive, from the user upon determining the anomalous portion of the audio corresponds to a fault occurring in the equipment, input indicating the anomalous portion of the audio corresponds to the fault to learn fault patterns in the equipment.Type: GrantFiled: October 25, 2019Date of Patent: December 15, 2020Assignee: Honeywell International Inc.Inventors: Ramprasad Yelchuru, Shreyan Chowdhury, Pradyumna Sampath
-
Publication number: 20200327885Abstract: Systems and methods for training a control panel to recognize user defined and preprogrammed sound patterns are provided. Such systems and methods can include the control panel operating in a learning mode, receiving initial ambient audio from a region, and saving the initial ambient audio as an audio pattern in a memory device of the control panel. Such systems and methods can also include the control panel operating in an active mode, receiving subsequent ambient audio from the region, using an audio classification model to make an initial determination as to whether the subsequent ambient audio matches or is otherwise consistent with the audio pattern, determining whether the initial determination is correct, and when the control panel determines that the initial determination is incorrect, modifying or updating the audio classification model for improving the accuracy in detecting future consistency with the audio pattern.Type: ApplicationFiled: April 15, 2019Publication date: October 15, 2020Inventors: Pradyumna Sampath, Ramprasad Yelchuru, Purnaprajna R. Mangsuli
-
Publication number: 20200066298Abstract: Systems, methods, and devices for monitoring industrial equipment using audio are described herein. One system includes two computing devices. The first computing device can receive, from an audio sensor, audio sensed during operation of industrial equipment, extract a plurality of features from the audio, determine whether any portion of the audio is anomalous, and send, upon determining a portion of the audio is anomalous, the anomalous portion of the audio to the second, remotely located, computing device. The second computing device can provide the anomalous portion of the audio to a user to determine whether the anomalous portion of the audio corresponds to a fault occurring in the equipment, and receive, from the user upon determining the anomalous portion of the audio corresponds to a fault occurring in the equipment, input indicating the anomalous portion of the audio corresponds to the fault to learn fault patterns in the equipment.Type: ApplicationFiled: October 25, 2019Publication date: February 27, 2020Inventors: Ramprasad Yelchuru, Shreyan Chowdhury, Pradyumna Sampath
-
Patent number: 10475468Abstract: Systems, methods, and devices for monitoring industrial equipment using audio are described herein. One system includes two computing devices. The first computing device can receive, from an audio sensor, audio sensed during operation of industrial equipment, extract a plurality of features from the audio, determine whether any portion of the audio is anomalous, and send, upon determining a portion of the audio is anomalous, the anomalous portion of the audio to the second, remotely located, computing device. The second computing device can provide the anomalous portion of the audio to a user to determine whether the anomalous portion of the audio corresponds to a fault occurring in the equipment, and receive, from the user upon determining the anomalous portion of the audio corresponds to a fault occurring in the equipment, input indicating the anomalous portion of the audio corresponds to the fault to learn fault patterns in the equipment.Type: GrantFiled: July 12, 2018Date of Patent: November 12, 2019Assignee: Honeywell International Inc.Inventors: Ramprasad Yelchuru, Shreyan Chowdhury, Pradyumna Sampath