Method and apparatus for detecting heat sink faults

• US 7,346,468 B2
• Filed: 08/08/2006
• Issued: 03/18/2008
• Est. Priority Date: 08/08/2006
• Status: Expired due to Fees

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: International Business Machines Corporation
• Inventors: Scollard, Michael Leo, Stankevich, Victor A., McMillan, Henry Gaines, Purrington, Challis Llewellyn, Bashor, Paul Douglas
• Primary Examiner(s): Bui; Bryan
• Application Number:
  US11/463,058
• Publication Number:
  US 20080040067A1
• Time in Patent Office: 588 Days
• Field of Search: 702/130, 702/132, 702/136, 702/185, 702/85, 702/99, 236/91.D, 236/91.F, 700/299, 700/300
• US Class Current: 702/136
• CPC Class Codes: G06F 11/24 Marginal checking or other specified testing methods not covered by G06F11/26, e.g. race tests

Abstract

Detecting, predicting, and diagnosing faults in a cooling system. According to one embodiment, a heat sink is in thermal contact with a heat-generating electronic component. When a temperature differential between the electronic component and the heat sink exceeds a set point, a fault signal is generated. The set point may be empirically or theoretically determined. The set point may be a static set point, or it may be a dynamic set point determined according to real-time operational parameters of the system. The system may be implemented with predictive failure analysis (PFA) to provide a more reliable, efficient, inexpensive, and robust computer system.

Claims

1. A method comprising:

sensing a source temperature of a heat-generating electronic component in an electronic system;

sensing a sink temperature of a heat sink in thermal communication with the heat-generating electronic component;

determining an actual temperature differential between the source temperature and the sink temperature; and

outputting a fault signal in response to the actual temperature differential exceeding a set point indicative of a heat sink fault.

2. The method of claim 1, further comprising selecting the set point as a function of real-time values of one or more system parameters.

3. The method of claim 1, further comprising:

recording the source temperature at a first time;

computing a time interval between the first time and a second time wherein the sink temperature is substantially equal to the source temperature at the first time; and

selecting the set point as a function of the time interval.

4. The method of claim 1, further comprising:

detecting one or both of an air flow rate and a fan speed; and

selecting the set point as a function of one or both of the air flow rate and the fan speed.

5. The method of claim 1, further comprising:

detecting an inlet air temperature upstream from the heat sink; and

computing the set point as a function of the inlet air temperature.

6. The method of claim 1, wherein the heat-generating electronic component comprises a CPU.

7. The method of claim 1, further comprising calibrating one or more temperature sensors for sensing one or both of the source temperature and the sink temperature prior to powering on the electronic system.

8. A device, comprising:

a source temperature sensor in direct thermal communication with a heat-generating electronic component of the electronic system;

a sink temperature sensor in direct thermal communication with a heat sink of an electronic system, wherein the heat sink is in thermal communication with the heat-generating electronic component;

a processor in electronic communication with the sink temperature sensor and the source temperature sensor, the processor configured for computing a set point indicative of a heat sink fault as a function of one or more operational parameters of the electronic system, computing an actual temperature differential as a function of the sink temperature and the source temperature, and for outputting a fault signal in response to the actual temperature differential exceeding the set point.

9. The device of claim 8, wherein the computer is configured for recording the source temperature at a first time, computing a time interval between the first time and a second time wherein the sink temperature is substantially equal to the source temperature at the first time, and selecting the set point as a function of at least the time interval.

10. The device of claim 8, wherein the one or more operational parameters are selected from air flow rate, fan speed, inlet air temperature, and combinations thereof.

11. The device of claim 8, wherein the heat-generating electronic component comprises a CPU.

12. A machine-accessible medium containing instructions, which when executed by a machine, cause the machine to perform operations, comprising:

instructions for sensing a source temperature of a heat-generating electronic component in an electronic system;

instructions for sensing a sink temperature of a heat sink in thermal communication with the heat-generating electronic component;

instructions for determining an actual temperature differential between the source temperature and the sink temperature; and

instructions for outputting a fault signal in response to the actual temperature differential exceeding a set point indicative of a heat sink fault.

13. The machine-accessible medium of claim 12, further comprising:

instructions for selecting the set point as a function of real-time values of at least one of the one or more system parameters;

instructions for recording the source temperature at a first time;

instructions for computing a time interval between the first time and a second time wherein the sink temperature is substantially equal to the source temperature at the first time; and

instructions for selecting the set point as a function of the time interval.

14. The machine-accessible medium of claim 12, wherein the operations further comprise:

instructions for detecting one or both of an air flow rate and a fan speed; and

instructions for selecting the set point as a function of one or both of the air flow rate and the fan speed.

15. The machine-accessible medium of claim 12, wherein the operations further comprise:

instructions for detecting an inlet air temperature upstream from the heat sink; and

instructions for computing the set point as a function of the inlet air temperature.

16. The machine-accessible medium of claim 12, wherein the set point is a function of one or more of an air flow rate, a fan speed, and an inlet air temperature.

17. The machine-accessible medium of claim 12, wherein the heat-generating electronic component comprises a CPU.