摘要:
A method for identifying a degraded fan measures acoustic data from an operating datacenter fan. A motor rotation frequency and a vane passing frequency are determined from the acoustic data. Amplitudes of the frequencies are determined from the acoustic data. If the amplitude of the motor rotation frequency is greater than the amplitude of the vane passing frequency, then it is determined that the fan is degraded.
摘要:
A cooling device includes a base having cells. A pipe is coupled to the base for each of the cells. The pipes include passages that carry fluid toward the cell and away from the cell. A magnetohydrodynamic pump system coupled to the pipe circulates an electrically conductive cooling fluid within the passages and the cell. An orifice may emits jets of fluid into the cells. A controller coupled to the cooling device may independently control flow rates in two or more cells of the cooling device. The controller may receive information from the temperature sensors on the base of the cooling device for use in controlling the flow rates in the cells.
摘要:
A method for inferring an altitude of a computing device, involving monitoring variable data associated with a plurality of variables measured within the computing device, inferring the altitude of the computing device using the measured plurality of variables in a multivariate correlation function, and controlling operation of the computing device based on the inferred altitude.
摘要:
A method and an apparatus for determining cooling fan speeds that should be avoided to prevent vibational resonance with system enclosures, given ambient conditions, and/or current geographic altitude. An exemplary method to determine one or more ranges of fan speed for one or more cooling fans in a chassis with one or more systems to avoid vibrational resonance in the chassis caused by the one or more cooling fans is provided. The method includes determining a range of operable fan speed for the one or more cooling fans that meets the cooling goal of the one or more systems in the chassis, wherein the one or more cooling fans are used to cool the chassis, and the one or more systems. The method also includes scanning fan speed for the one or more cooling fans over the determined range of operable fan speed, and collecting and analyzing read or write rates on a hard disk drive in the one or more systems over the determined range of operable fan speed. The method further includes determining one or more ranges of usable fan speed that avoid vibrational resonance in the chassis caused by the one or more cooling fans, based on the collected and analyzed read or write rates.
摘要:
A method for performing server monitoring via condition tracking and state identification of server components. In one embodiment, the method includes continuously monitoring a server, the server having a plurality of components, determining whether a component of the plurality of components has entered a maintenance state, and triggering a maintenance action for the component if it has entered the maintenance state.
摘要:
One embodiment of the present invention provides a system that facilitates accelerated Soft-Error Rate (SER) testing of circuitry. The system starts by collecting a radioactive gas from the atmosphere and concentrating the radioactive gas in a testing chamber. Once the desired amount of radioactive gas is present in the testing chamber, the system SER tests the circuitry in the testing chamber by bombarding the circuitry with particles emitted from the radioactive gas while running testing procedures.
摘要:
An improved system for monitoring non-coincident, non-stationary, process signals. The mean, variance, and length of a reference signal is defined by an automated system, followed by the identification of the leading and falling edges of a monitored signal and the length of the monitored signal. The monitored signal is compared to the reference signal, and the monitored signal is resampled in accordance with the reference signal. The reference signal is then correlated with the resampled monitored signal such that the reference signal and the resampled monitored signal are coincident in time with each other. The resampled monitored signal is then compared to the reference signal to determine whether the resampled monitored signal is within a set of predesignated operating conditions.
摘要:
A method and system for analyzing a source of data. The system and method involves initially training a system using a selected data signal, calculating at least two levels of sensitivity using a pattern recognition methodology, activating a first mode of alarm sensitivity to monitor the data source, activating a second mode of alarm sensitivity to monitor the data source and generating a first alarm signal upon the first mode of sensitivity detecting an alarm condition and a second alarm signal upon the second mode of sensitivity detecting an associated alarm condition. The first alarm condition and second alarm condition can be acted upon by an operator and/or analyzed by a specialist or computer program.
摘要:
A method and system for providing a tag gas identifier to a nuclear fuel rod and analyze escaped tag gas to identify a particular failed nuclear fuel rod. The method and system include disposing a unique tag gas composition into a plenum of a nuclear fuel rod, monitoring gamma ray activity, analyzing gamma ray signals to assess whether a nuclear fuel rod has failed and is emitting tag gas, activating a tag gas sampling and analysis system upon sensing tag gas emission from a failed nuclear rod and evaluating the escaped tag gas to identify the particular failed nuclear fuel rod.
摘要:
A system for controlling energy usage in a server having a processor, where the system includes a memory for storing energy cost information, and a controller for determining a transaction rate for the processor. The controller is also for determining a cumulative of energy expended by the server based on the determined transaction rate for each of a number of available power level states (P-states) for operation of the processor, and for selecting one of the available P-states for operation of the processor based on the determined cumulative energy expended and the stored energy cost information.