Early detection of overheating devices

• US 9,250,667 B2
• Filed: 10/01/2013
• Issued: 02/02/2016
• Est. Priority Date: 04/16/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Liwa, Francisco D
• Primary Examiner(s): Williams, Hezron E
• Assistant Examiner(s): Shabman, Mark A
• Application Number:
  US14/042,967
• Publication Number:
  US 20140032944A1
• Time in Patent Office: 854 Days
• Field of Search: 73/233.4
• US Class Current: 1/1
• CPC Class Codes: G01N 33/0004 Gaseous mixtures, e.g. polluted air
• CPC Class Codes: G01N 33/0034 comprising neural networks or related mathematical techniques
• CPC Class Codes: G06F 1/206 comprising thermal management

Abstract

A method is provided that monitors the odor within the physical enclosure of a computing device that includes one or more components. The method includes determining whether the odor within the physical enclosure is indicative of an overheating component that is overheating within the physical enclosure of the computing device. Determining whether the odor within the physical enclosure may include an artificial neural network (“ANN”) to determine whether the odor is indicative of an overheating component. The method includes initiating an overheating protocol in response to determining that the odor within the physical enclosure is indicative of an overheating component. The method may, for example, alert the user and/or applications that a component is overheating.

Claims

1. A method comprising:

monitoring, using a sensor with a sensing material, an odor within a physical enclosure of a computing device comprising one or more components, the sensor comprising a metal oxide semiconductor field effect transistor (“

MOSFET”

), the MOSFET acting as a transducer that represents the odor as an electrical signal, wherein the sensing material comprises a gate of the MOSFET and odor molecules interact with gate material of the MOSFET to alter a threshold voltage of the MOSFET;

determining, using an artificial neural network, that the odor within the physical enclosure is indicative of an overheating component that is overheating within the physical enclosure of the computing device, wherein the artificial neural network determines that the odor is indicative of an overheating component by comparing an alteration in the sensing material with a reference database comprising a plurality of reference alterations caused by the overheating component, each reference alteration comprising an electrical signal that corresponds with an odor, wherein determining that the odor within the physical enclosure is indicative of the overheating component comprises determining that the alteration corresponds to one or more of the reference alterations in the reference database; and

initiating an overheating protocol in response to determining that the odor within the physical enclosure is indicative of the overheating component.

2. The method of claim 1, wherein monitoring the odor within the physical enclosure of the computing device comprises collecting one or more samples of odor molecules from within the physical enclosure of the computing device.

3. The method of claim 1, wherein odor molecules of the odor reversibly alter the sensing material for detecting the odor molecules.

4. The method of claim 1, further comprising adding an alteration that occurred in the sensing material to the reference database in response to determining that the odor within the physical enclosure is indicative of the overheating component.

5. The method of claim 4, further comprising receiving one or more additional entries to the reference database from one or more separate computing devices.

6. The method of claim 1, wherein the overheating protocol comprises shutting down the computing device.

7. The method of claim 1, wherein the overheating protocol comprises creating a log entry comprising data generated in connection with the overheating component.