WO1999021017A1 - Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state - Google Patents
Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state Download PDFInfo
- Publication number
- WO1999021017A1 WO1999021017A1 PCT/US1998/022190 US9822190W WO9921017A1 WO 1999021017 A1 WO1999021017 A1 WO 1999021017A1 US 9822190 W US9822190 W US 9822190W WO 9921017 A1 WO9921017 A1 WO 9921017A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- measure
- values
- profile
- environment
- fault
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0751—Error or fault detection not based on redundancy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/0703—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation
- G06F11/0706—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment
- G06F11/0709—Error or fault processing not based on redundancy, i.e. by taking additional measures to deal with the error or fault not making use of redundancy in operation, in hardware, or in data representation the processing taking place on a specific hardware platform or in a specific software environment in a distributed system consisting of a plurality of standalone computer nodes, e.g. clusters, client-server systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/22—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing
- G06F11/2252—Detection or location of defective computer hardware by testing during standby operation or during idle time, e.g. start-up testing using fault dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/3006—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3055—Monitoring arrangements for monitoring the status of the computing system or of the computing system component, e.g. monitoring if the computing system is on, off, available, not available
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/32—Monitoring with visual or acoustical indication of the functioning of the machine
- G06F11/324—Display of status information
- G06F11/327—Alarm or error message display
Definitions
- the invention relates to fault detection and fault identification in a complex environment. More particularly, the invention relates to systems and methods for profiling "normal conditions" in a complex environment, for automatically updating the profiles of "normal conditions”, for automatically detecting faults based on the "normal conditions” profiles, and for identifying faults in environments which are measurable by multiple variables.
- a profile of normal behavior is generated by collecting data about a environment over time and normalizing the data. The data collected represents the state of the environment at different times whether or not a fault condition exists. It is implicitly assumed that, over time, the number of observations made at times when faults are present will be small relative to the number of observations made at times when no faults are present; and that the normalized value of the data sets will be a fair indicator of the state of the environment when no faults are present. New observations of the environment may then be compared to the profile to make a determination of whether a fault exists.
- IP Internet Protocol
- MIB I and MIB Il-Internet RFCs 1156 and 1158 the Simple Network Management Protocol
- RMON MIB-Internet RFC 1757 the Remote Monitoring Management Information Base
- Feather used custom, passive hardware monitors on the Computer Science Department ETHERNET network at Carnegie Mellon University to gather data over a seven month period. Raw data were collected for packet traffic, load, collisions, and packet lengths using a sampling interval of 60 seconds. In this work, profiles and thresholds were computed from the data using moving average techniques in which a profile, visualized as a plot of expected behavior over a 24 hour period, was computed for each variable that had been collected. Maxion and Feather used an exponentially weighted moving average to develop profiles. In this scheme, the profile value for each time point is a weighted average of the values of the same point on previous days, with the weights decreasing exponentially so that older points have the least weight.
- weights where a is the smoothing parameter which lies between 0 and 1, is: a, a(a-l), a(a-l)2. a(a-l) 3 , .... Using these techniques, a new profile is computed every 24 hours.
- Another object of the invention is to provide methods for determining the accuracy of profiles and indicators of normal conditions in complex environments.
- the systems and methods of the present invention are based on three unexpected discoveries about which the prior art teaches away: i.e. that in order to build an accurate profile of normal conditions in a environment, it is important to collect data only when no fault conditions exist; that there is a characteristic relationship between a measure of normal conditions and a measure of fault conditions; and that in volume processing environments, faults are more likely to be present when the environment is operating at low volume.
- the present invention was conceived in response to the recognition that the current techniques for alert generation that are based on automatically generating and updating profiles are inaccurate because they are based on averaging techniques that combine observations from situations in which there are faults with those from situations in which the environment is trouble free.
- Detection methods based on profiles built in this manner cannot be made sensitive because the profile is always biased and profile variance is relatively large. It has been discovered that a profile is much more accurate if data collected during a fault condition is eliminated from the population of data used to create the profile. Moreover, contrary to the assumption that high volume (in a volume environment such as a communications network) is a source of faults, it has been discovered that high volume is a symptom of a no fault condition. Therefore, in accord with the invention, profiles are built from data which is taken only during high volume conditions (or in the case of environments other than volume environments, only during conditions which are proven to be indicative of no fault).
- a profile is made of the environment using observations made during no fault conditions.
- a range of values for one or more "trusted" variables are identified as values indicative of a no fault condition.
- Data is also collected (only at times when the trusted variable(s) indicate(s) no fault) for other variables which may be indicative of a fault condition.
- Statistical profiles are established for each of these other variables. In a simple implementation, profiles are made by averaging observations and maintaining a mean value and standard deviation for each variable.
- the environment is continuously monitored and the normal profile(s), as well as the thresholds/ranges of the trusted variable(s), are preferably continuously updated during normal conditions, as indicated by the trusted variable(s).
- the trusted variable(s) When, during monitoring of the environment, the trusted variable(s) exhibit value(s) outside the normal range, a possible fault condition is indicated and the present values of the other variables are examined to determine whether or not any of these variables exhibit values outside the normal profiled thresholds/ranges. Depending on which of these variables exhibits an abnormal value, a diagnosis of the fault may be possible.
- a system is provided to detect faulty behavior of one or more devices in a communications network.
- the normal profile is built with data observations acquired during high processing volume, a condition discovered to be indicative of the absence of faults.
- One or more fault thresholds are derived from statistical profiles made from observations made during high volume conditions. It is readily recognized that, in this exemplary embodiment, low processing volume is not necessarily indicative of the presence of a fault. Thus, a fault alert is generated during lowered processing volume only when one of the normal profiled thresholds is exceeded.
- normal profiles are built for a variety of complex environments in which there are at least two different measurable variables, one being a priori indicative of normal conditions (the trusted variable) and the other(s) being statistically indicative of a fault (the fault variable(s)).
- the trusted variable may include a number of variables which are combined in different ways depending on the environment and the fault thresholds likewise may be each built from a number of related variables which are indicative of a particular fault.
- the trusted variable(s) is monitored for deviation from normal, the normal profile is preferably adaptively updated during normal conditions, and the fault thresholds are examined only when the trusted variable(s) deviates from the normal profile.
- one measure of environment status when one measure of environment status (the trusted variable) can be used to detect fault-free operation, it can also be used as a switch to filter sampled observations of one or more other measures of environment status. Observations that have passed through the filter can then be used to estimate the profile of normal behavior for one or more other measures of environment status.
- Another feature of the invention is that it includes a technique for determining the reliability of a trusted variable for identifying a specific state of a target variable such as a variable believed to be effective for fault detection.
- a target variable such as a variable believed to be effective for fault detection.
- the target variable When plotted against the values of the trusted variable, the target variable should reveal a pattern of very low variance over some range of the trusted variable. If a low variance region does not appear in the plots either the trusted variable is faulty or the proposed measure is insufficiently related to the target state (or its inverse).
- systems and methods of the invention are applicable to control and regulation of an apparatus in response to environmental changes.
- Figure 1 is a simplified flow chart of the generalized operation of the systems and methods of the invention
- Figure 2 is a simplified flow chart of the generalized operation of the systems and methods of the invention where several fault variables are profiled;
- Figure 3 is a simplified flow chart of the generalized operation of the systems and methods of the invention including adaptive profiling;
- Figure 4 is a schematic diagram of the relationship between trusted variables and fault variables and how environment profiles are updated
- Figure 5 is a schematic representation of the statistical variance of trusted variable(s) and fault detection variables
- Figure 6 is a simplified flow chart of the operation of the systems and methods of a first exemplary embodiment of the invention including adaptive profiling as applied in a communications network;
- FIGS. 7 and 8 are simplified flow charts of the operation of the systems and methods of a second embodiment of the invention as applied to controlling the rate of a pacemaker;
- Figure 9 is a simplified flow chart of the operation of the systems and methods of a third embodiment of the invention as applied to updating the profile of normal operating conditions in an internal combustion engine.
- FIG. 10 is a simplified block diagram of a hardware system for implementing the methods of the invention.
- Appendix A is a source code listing of an exemplary embodiment of the invention (18 pages).
- a profile is made of the environment using observations made during no fault conditions.
- a range of values for one or more "trusted" variables are identified as values indicative of a no fault condition.
- the trusted variable is a one- way indicator, only indicating the absence of a fault, but incapable, in and of itself, of indicating the presence of a fault.
- observations in the form of measurable data are collected only at times when the trusted variable indicates no fault.
- a profile is created for the environment which includes the bounds of the trusted variable and the bounds observed for other variables during times of no-fault conditions as indicated by the trusted variable.
- the trusted variable will be chosen based on a priori knowledge of the environment. For example, one may postulate that gas mileage is a trusted variable for determining whether an automobile has a faulty engine. The trusted variable may be self- evident or it may be learned from observation.
- one of the discoveries of this invention is that high volume in a communications network is an indicator that there are no faults in the network.
- low volume in the network does not necessarily indicate that there is a fault in the network.
- Low volume may be caused by other factors which are not faults. For example, certain times of day or times of year may normally yield low volume in the environment.
- a key aspect of the present invention is, however, that the profile of the environment be derived from observations made only when the trusted variable gives assurance that no fault exists. When this is done, the profile will contain "acceptable" values for different measurements of the environment. In other words, the profile will reflect what the environment looks like when we know that it is not faulty. Once the profile has been built in this way, the fault detection process can begin an iterative examination of the environment.
- a simplified model of the fault detection process is shown in Figure 1.
- the fault detection process starts at 10 and proceeds to examine the trusted variable at 12 for the last data observation. If it is determined at 12 that the trusted variable is within the bounds (or above or below the threshold, depending on the environment and the variable) indicative of no fault, the process returns to 10 and then to examine the trusted variable at 12 for the next instant in time. If it is determined at 12 that the trusted variable no longer indicates a fault-free environment, another variable (measure of the environment) is examined at 14 to determine whether its value is within the range set forth in the no-fault environment profile. If it is determined at 14 that the "fault variable" is within normal limits, the process returns to 10 to begin the testing again at the next instant in time.
- the fault detection process starts at 10 and proceeds to examine the trusted variable at 12 for the present instant in time as in the example described above with reference to Figure 1. If it is determined at 12 that the trusted variable no longer indicates a fault-free environment, multiple fault variables are examined at 14a, 14b, 14c, etc. to determine whether their values are within the ranges set forth in the no-fault environment profile. If it is determined at any one of 14a, 14b, 14c, etc. that a "fault variable" is outside the normal profile, an alert is generated at 16 and it is assumed that a fault has been detected.
- Figure 2 shows the fault variables 14a, 14b, 14c, etc. being examined in sequence.
- the generation of the alert at 16 may be fault-specific depending on which of the fault variables indicated the fault. Thereby, the system may be operated to provide not only a fault detection, but a fault diagnosis as well.
- the systems and methods of the invention preferably include the adaptive updating of the environment profile (i.e. profiles of the trouble free range of one or more fault detecting variables).
- the profiles of the fault detection variables are updated at 18.
- the operation of the system shown in Figure 3 is otherwise the same as described above with reference to Figure 1 and the same reference numerals are used to indicate the same steps in the system.
- Figure 4 shows another way of representing the system shown in Figure 3 and which indicates the relationship between the trusted variable(s) and the fault detection variables.
- the profiles 19 shown in Figure 4 are updated at 18 each time the trusted variable(s) are within the range 20 indicative of no fault in the environment.
- the fault variable(s) are examined at 14 and their values are compared to the profile 19 to determine whether they are within the no fault range 22 of the profile or whether they fall outside the profile as indicating a fault state 24.
- the system of the invention can also be operated to discover a trusted variable. More particularly, the invention includes a technique for determining the reliability of a trusted variable for identifying a specific state of a target variable such as a variable believed to be effective for fault detection. The technique includes a statistical sampling of the trusted variable and the target variable. When plotted against the values of the trusted variable, the target variable should reveal a pattern of very low variance over some range of the trusted variable.
- this low variance region of the observational pair indicates a state in which no faults are present in the environment. In other domains, such a region may indicate a specific state of the environment under observation. If a low variance region does not appear in the plots either the trusted variable is faulty or the proposed measure is insufficiently related to the target state (or its inverse).
- Figure 5 shows a characteristic graph in which a trusted variable is effective at identifying a specific state of a fault detection variable.
- this type of graph is typically found to indicate a no fault state of the SNMP variable when the trusted variable is packet traffic volume.
- plots of a potential trusted variable against each of the target variables will clearly display a pattern with a low variance region 30 on the target variable, e.g. a fault detection variable, when a trusted variable is effective. Such plots can be used to determine the reliability and indicative range of a potential trusted variable.
- Figure 6 illustrates a system to detect faulty behavior of one or more devices in a communications network.
- the normal profile is built with data observations acquired during high processing volume, a condition discovered to be indicative of the absence of faults.
- One or more fault thresholds are derived from statistical profiles made from observations made during high volume conditions. It is readily recognized that, in this exemplary embodiment, low processing volume is not necessarily indicative of the presence of a fault. Thus, a fault alert is generated during lowered processing volume only when one of the normal profiled thresholds is exceeded.
- a data pair consisting of an observation of processing volume and a status variable are read at the start of the process at 110.
- Processing volume is compared at 112 against a threshold which defines high volume. If the data point is a high volume point, it is passed to a system component that uses the observation to update a profile of normal behavior for the error rate at 118. If the data point is not a high volume point, the status variable is passed to a system component that determines at 114 whether it represents normal behavior as defined by the current behavioral profile. If the observation does not fall within the system defined thresholds for normal behavior, an alert is generated at 116.
- the threshold that defines high processing volume may be setup at system initialization or it may be defined adaptively as data is observed.
- a simple algorithm for updating processing volume adapts to reductions in device capacity by adjusting the maximum processing volume down if a data point in the highest 1/16 of the volume range is not seen in a given time duration. This reduces the definition of high volume slowly but rapidly adjusts upward if a high volume point is seen.
- the code listing below assumes the minimum value for processing volume is zero.
- a preferred embodiment of this implementation of the invention has been designed and tested for Internet Protocol (IP) layer fault detection in Simple Network Management Protocol (SNMP) compliant network devices (Internet RFC 1157).
- IP Internet Protocol
- SNMP Simple Network Management Protocol
- the SNMP standard requires that devices maintain statistics about their processing status and history as specified in the Management Information Bases I and ⁇ (MIB I and MIB II) (Internet RFC's 1156, and 1158) and the Remote Monitoring Management Information Base (RMON MIB) (Internet RFC 1757).
- MIB II variable ipInDelivers to measure processing volume.
- Other MIB II variables e.g. ipInHdrErrors, ipInDiscards, ipFragFails, ipInAddrErrors, were used to measure device behavior.
- a known mechanism was used to poll a target SNMP compliant network device and, optionally, transform raw data values.
- the polling mechanism queries the device to obtain values for the selected MIB II variable or variables, including ipInDelivers. It is important that the values for the behavioral variables are time synchronous, within a reasonable margin, with the value of ipInDelivers. For the SNMP embodiment, this was accomplished without difficulty by existing SNMP query mechanisms by querying the values of all required data together or immediately subsequent to one another. Although it is not necessary, data are normally read at regular time intervals.
- data may be transformed prior to input to the fault detection of the invention.
- ipErrors ipInHdrErrors + ipFragFails + ipInAddrErrors + ipInDiscards.
- rate variables from the raw input by dividing observed data by the time interval since the last observation.
- the source code listing in Appendix A gives an illustration of how the system operates. Processing begins when a data observation pair consisting of a measure of processing volume and a second measure of environment behavior, e.g. (ipInDeliversRate, ipErrorsRate), is input to the system.
- the system is composed of three functional modules, Update VolumeProfile, UpdateBehaviorProfile, and GenerateAlert, which read from and write to two data stores.
- the modules Update VolumeProfile and UpdateBehaviorProfile are used to update the system's model of normal device behavior as reflected in the selected measure of device behavior, e.g. ipErrorsRate.
- the module, GenerateAlert evaluates the input data observation and generates an output signal if warranted.
- VolumeProfile One data store, VolumeProfile, is used to store parameters that are needed to maintain a lower bound for identifying "high” processing volumes.
- BehaviorProfile stores parameters that are used to identify "normal” device behavior. Parameters in the data stores may be modified during system operation by the modules, Update VolumeProfile and UpdateBehaviorProfile.
- the input data is either passed through the system without executing any module, passed through the two modules, Update VolumeProfile and UpdateBehaviorProfile, or passed into the single module GenerateAlert.
- the path a data observation takes depends on whether it is identified as having a high processing volume and on whether it is classified as an observation with "normal" behavior.
- VolumeProfile contains at least two numbers: the minimum value observed for ProcessingRate, and the maximum value observed for ProcessingRate.
- VolumeProfile may optionally include n storage areas where n is a parameter determined by the storage capacity available. These storage areas record information about past observations of the behavioral variable. This information is used to repair BehaviorProfile when the definition of "high" volume as specified by the model derived by VolumeProfile changes. When the definition of "high" volume changes, observations which had previously been included in the Behavioral model are now disallowed. The Behavioral model is repaired when these observations are removed from the computation of the profile.
- each of these storage areas contains at least three numbers. Two numbers represent a unique range of processing volumes and the third number records the sum of values of the behavioral variables observed in the range represented by the other two numbers. Together the storage areas should cover the range of processing volume currently defined by the model as "high" volume. When the definition of "high" volume advances to a higher range (preferably, it never declines) then the lowest k storage areas should be dropped (or used to further subdivide the covered range) and the info stored there used to repair the behavioral model.
- the first step of the method used by the invention is to normalize data inputs with respect to processing volume to create a behavioral rate variable.
- Data inputs are normalized by dividing the behavioral measure by the processing volume measure.
- the behavioral variable e.g. ipErrorsRate is divided by ipInDeliversRate to create a measure of error rate per delivered packet.
- the normalized data observation is compared to the stored profile for the behavioral variable.
- the behavioral profile central value is the mean of the smoothed variable ipErrorsRate/ipInDeliversRate taken over a sample of selected values and the profile thresholds are integral multiples of the standard deviation taken over the same sample of observed data points for ipErrorsRate/ipInDeliversRate. If the data exceeds a threshold an alert signal is output by the system. Optionally the output signal may vary according to the threshold which was exceeded. For example, in a preferred IP/SNMP embodiment, multiples of the standard deviation of the normalized behavioral variable are used as thresholds.
- the signal output is the integer m such that,
- every observation of processing volume is input to update the processing volume profile.
- every data observation pair is passed to the candidate evaluation module to determine whether it should be used update the profile of normal behavior.
- Candidate evaluation is much like anomaly detection except that the processing volume profile is used as a base of comparison.
- the profile central value is computed as the mean of those data observations that pass the candidate evaluation.
- the systems and methods of the present invention can be applied in a number of different environments for fault detection and fault identification.
- the adaptive profiling aspects of the invention can also be applied in the monitoring and control of devices operating in changing environments.
- the principles of the invention can be used to control the operation of a heart pacemaker.
- various measures of metabolic demand such as respiration rate, the QT interval, venous oxygen saturation, venous blood temperature, and minute volume have been used to control the pacing rate.
- MIR metabolic indicated rate
- Pacemakers such as those described in United States Patent Number 5,487,753 include a microprocessor with read-only memory (ROM) and random access memory (RAM) that are used to store the patient profile and control software.
- the microprocessor receives inputs from sense circuits that implement some measure of metabolic demand such as minute volume, uses the minute volume reading and the mapping profile to determine a pacing rate and send appropriate pacing pulses.
- Minute volume has been a particularly useful measure of metabolic demand but there are difficulties mapping minute volume to the appropriate metabolic indicated rate (MIR) which is used to set the pacing interval.
- MIR metabolic indicated rate
- RRF rate response factor
- Some pacemakers allow the RRF to be adjusted by a physician based on an evaluation of the patient according to age and general health.
- the use of a single RRF is inadequate because the response factor should vary according to the patient's exercise level, with higher slope for low levels of exercise and a more gradual slope for higher levels of exercise at a point where the patient's anaerobic threshold (AT) has been exceeded.
- AT anaerobic threshold
- a metabolic rate responsive pacemaker would dynamically respond to a patient's level of activity using a measure of metabolic demand and an appropriate mapping to MIR derived on an individual basis.
- a profile for the mapping could be identified experimentally for each patient if the intrinsic heart rate was measurable or deterministically related actual heart rate.
- the actual heart rate of a patient will vary depending on a wide range of factors including stress, food or drink recently ingested, level of fatigue, etc. In patients who require pacemakers, actual heart rates are particularly unreliable indicators of intrinsic heart rate because of pacing irregularities.
- the systems and methods of the present invention also provide a method for profiling intrinsic heart rate so that the mapping from a measure of metabolic demand such as minute volume to the MIR determined pacing rate can be established empirically on an individual basis.
- a pacemaker can be made dynamically responsive to level of activity on an individual basis.
- the profile used to determine the MIR determined pacing rate can be updated continuously so that it is responsive to longer term changes in the patient's general health and age.
- the method uses a trusted variable to determine when sensed measurements of actual heart rate and measured metabolic demand should be incorporated in a statistical profile that will determine a patient's individual mapping of measured metabolic demand, e.g. minute volume, to MIR.
- the trusted variable is used to identify a subset of measured observations that can be known with a high degree of certainty to indicate normality.
- the invention utilizes a measure which will identify when a patient's actual heart rate is at a normal and stable pace for a given level of exercise.
- MIR corresponding to an intrinsic heart rate
- a measure of heart beat regularity taken over a recent window of beats, might be used as a trusted variable. For some patients who require pacemakers these measurements could be taken under test conditions in a physicians office with the pacemaker disengaged.
- Figure 7 shows a flow chart for updating of the metabolic_demand-to-MIR mapping profile used to set the pacing interval of a pacemaker.
- the pacemaker has been disabled at 200 for the purposes of building the mapping profile.
- a measure of regularity of the patient's heart rate is determined at 202 by evaluating the change in heart rate over the previous n sampled observations, and is used as the trusted variable.
- the trusted variable indicates when the measured heart rate corresponds to the intrinsic rate.
- the system accepts the measured observation for metabolic demand, e.g. minute volume, and the measured observation for heart rate and uses these to update the mapping profile at 206.
- the trusted variable could not be based on heart rate as this is controlled by the pacing device.
- a trusted variable would need to be identified that would accurately identify the states in which the patient's heart rate is correctly paced.
- Continuous updating of the mapping profile, as the patient goes about his normal activities with the pacemaker enabled, can be accomplished if a trusted variable is found to accurately detect situations in which the pacing device is set correctly at the intrinsic heart rate.
- Other potential trusted variables could include measures that can be used to identify the correct intrinsic heart rate such as the change in the QT interval, change in venous oxygen saturation, the patient's or physician's assessment, or some combination of these.
- Figure 8 shows how the MIR mapping profile computed in the manner of this invention is used to control a pacemaker device similar to that described in United States Patent Number 5,487,753. This includes means for evaluating sensed input and controlling the pacing pulse.
- the selected measure of MD in this case minute volume, is measured at 208. If the interval indicated in the mapping profile does not match the current pacing interval at 210 the pacing interval is adjusted at 212 to the correct interval as recorded in the mapping profile for the corresponding minute volume.
- the systems and methods of the invention may be applied in the environment of an internal combustion.
- detection of combustion irregularities such as misfires and partial combustion in a internal combustion engine can be indicative of many types of problems such as poor grade fuel, incorrect fuel/air mixture, faulty ignition means, or misaligned valves.
- Detection of misfires has been important in order to improve diagnosis of engine performance and to prevent damage to catalytic exhaust systems.
- the prior art has sought to identify engine misfires by sampling a measure of engine speed and comparing engine speed to an average speed considered over many cycles or by determining the angular velocity of the engine.
- the average of these samples is then compared to a fault threshold to determine whether the engine as a whole, or, in some methods, a particular cylinder, is experiencing a faulty combustion cycle.
- a fault threshold to determine whether the engine as a whole, or, in some methods, a particular cylinder, is experiencing a faulty combustion cycle.
- the prior art generally does not include a method for automating the setting of fault thresholds that are used to determine whether misfires have occurred. These are assumed to be predetermined and stored in ROM memory attached to a microprocessor device that carries out the sampling and analysis.
- U.S. Patent Number 5,505,079 describes a system and device for making a combustion diagnosis by measuring time intervals between angular variations in the crank shaft, determining a set of parameters that represent variation in instantaneous speed of the engine at the moment of combustion, and comparing these parameters with a fault threshold. In that system and device, the fault threshold is determined in advance by simulations under controlled settings.
- U.S. Patent Number 5,574,217 describes an alternative system in which separate fault thresholds are predetermined for combinations of engine speed, change in engine speed, and manifold pressure in order to avoid incorrect fault detection for transient states. That method also assumes that fault thresholds are predetermined.
- the present invention provides a means for automatically computing and continuously updating profiles of normal behavior for a measure of angular velocity and for automatically determining fault thresholds that may be dependent upon other indicators of the state of the engine such as engine speed, engine acceleration, manifold pressure or other appropriate measures.
- a trusted variable that indicates normal operation for each cylinder such as the Percent Power Contribution Parameter described in U.S. Patent Number 5,446,664
- sampled measurements for a combination of engine speed, change in engine speed, and manifold pressure can be collected only during cycles or normal operation and a profile of normal behavior can be constructed that takes each combination of these variables into account.
- One way to compose the three measures into a single fault variable would be to use a weighted average of the values of each variable.
- the fault threshold for the combined variables can be computed using the standard deviation of the combined variable as described in earlier discussions.
- the reliability of the proposed trusted variable such as Percent Power Contribution (PPC) can be determined by graphing the combined fault detection variable against the proposed trusted variable.
- Figure 9 shows a flow diagram that uses a linear combination of the engine speed, engine acceleration, and manifold pressure as the fault detection variable.
- the system starts at 302
- measurements are taken of engine speed, acceleration and manifold pressure, and the PPC is computed at 304. If it is determined at 306 that the PPC is in the normal range, the profile for engine speed, acceleration and manifold pressure is updated at 308. Otherwise, measurements continue at 304. In this way an accurate profile of normal conditions can be built according to the invention.
- Figure 10 shows the basic components of a system for implementing the methods of the invention.
- the system includes a monitor 400 for acquiring data about the environment. These data are usually supplied by one or more sensors 402.
- the acquired data are passed to a comparator 404 which compares the present value of data samples to the profile of normal behavior which is contained in a database 406. If the data is within the normal profile, an updater 408 updates the profile database 406. This, the updater 408 also receives the data from the monitor 400 and when directed by the comparator 404, uses the present data to update the profile database 406.
- comparator 404 determines that the data samples he outside the normal profile, it sends a signal to an alert generator 410 to generate a fault alert.
- other action may be taken in lieu of generating an alert.
- other comparators may examine the data to diagnose the condition of the environment.
- interval > 3600 ) ⁇ interval DEFAULT_TIME_INTERVA ; printf ( "Collection interval set to %d seconds. ⁇ n", DEFAULT_TIME_IN TERVAL ) ;
- ⁇ pp party_getEntry( dst, dstlen ) ; if ( PP )
- HighVolume UpdateVolumeThreshold ( volumelteration, interval, time limit, *vars->val . integer, &Volume, verbose ); > else ⁇ /* Remaining loops update profiles */ if ( ! HighVolume ) ⁇ if ( ! UpdateBehaviorProfile ( count - 1, behaviorlteration, &Volu me, *vars->val . integer, medians, median_frequency, ratesCopy, verbose ) ) ⁇
- ⁇ n%s is out of range .
- Dev: %f ⁇ n" vbuffer, local ->tm_hour , local->tm_min , local->tm_sec , object_stats [profile] . rate , object_stats [prof ile] .median, object_stats (prof ile] . std_dev ) ; fprintf ( stderr, buffer ) ;
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Computer Networks & Wireless Communication (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Pure & Applied Mathematics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
- Debugging And Monitoring (AREA)
- Computer And Data Communications (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
Description
Claims
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CA002309034A CA2309034C (en) | 1997-10-22 | 1998-10-21 | Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state |
AU11067/99A AU1106799A (en) | 1997-10-22 | 1998-10-21 | Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state |
EP98953788A EP1032841A4 (en) | 1997-10-22 | 1998-10-21 | Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state |
JP2000517283A JP2001521210A (en) | 1997-10-22 | 1998-10-21 | System and method for adaptive profiling, fault detection and alerting in a changing environment measurable by at least two different measures of state |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/956,227 | 1997-10-22 | ||
US08/956,227 US6073089A (en) | 1997-10-22 | 1997-10-22 | Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state |
Publications (1)
Publication Number | Publication Date |
---|---|
WO1999021017A1 true WO1999021017A1 (en) | 1999-04-29 |
Family
ID=25497955
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US1998/022190 WO1999021017A1 (en) | 1997-10-22 | 1998-10-21 | Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state |
Country Status (6)
Country | Link |
---|---|
US (1) | US6073089A (en) |
EP (1) | EP1032841A4 (en) |
JP (1) | JP2001521210A (en) |
AU (1) | AU1106799A (en) |
CA (1) | CA2309034C (en) |
WO (1) | WO1999021017A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007085504A2 (en) * | 2006-01-25 | 2007-08-02 | Siemens Aktiengesellschaft | Method for the detection of a fault during operation of a system comprising a certain number of data records |
EP2018018A3 (en) * | 2000-05-12 | 2009-04-08 | Niksun, Inc. | Security camera for a network |
US10110632B2 (en) | 2003-03-31 | 2018-10-23 | Intel Corporation | Methods and systems for managing security policies |
Families Citing this family (96)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6604118B2 (en) | 1998-07-31 | 2003-08-05 | Network Appliance, Inc. | File system image transfer |
US7444394B2 (en) * | 1997-02-03 | 2008-10-28 | Canon Kabushiki Kaisha | Network data base control device and method thereof |
US20020150050A1 (en) * | 1999-06-17 | 2002-10-17 | Nathanson Martin D. | Automotive telemetry protocol |
US20100030423A1 (en) * | 1999-06-17 | 2010-02-04 | Paxgrid Telemetric Systems, Inc. | Automotive telemetry protocol |
US6457130B2 (en) | 1998-03-03 | 2002-09-24 | Network Appliance, Inc. | File access control in a multi-protocol file server |
US6317844B1 (en) | 1998-03-10 | 2001-11-13 | Network Appliance, Inc. | File server storage arrangement |
US6343984B1 (en) * | 1998-11-30 | 2002-02-05 | Network Appliance, Inc. | Laminar flow duct cooling system |
US6947797B2 (en) * | 1999-04-02 | 2005-09-20 | General Electric Company | Method and system for diagnosing machine malfunctions |
US7685311B2 (en) * | 1999-05-03 | 2010-03-23 | Digital Envoy, Inc. | Geo-intelligent traffic reporter |
US6457015B1 (en) | 1999-05-07 | 2002-09-24 | Network Appliance, Inc. | Adaptive and generalized status monitor |
US6591377B1 (en) * | 1999-11-24 | 2003-07-08 | Unisys Corporation | Method for comparing system states at different points in time |
US6601014B1 (en) * | 1999-11-30 | 2003-07-29 | Cerebrus Solutions Ltd. | Dynamic deviation |
US6560544B1 (en) * | 2000-04-28 | 2003-05-06 | Ford Motor Company | Method for monitoring a mixture |
EP1352332A4 (en) * | 2000-06-21 | 2004-12-08 | Concord Communications Inc | Liveexception system |
US7177927B1 (en) * | 2000-08-22 | 2007-02-13 | At&T Corp. | Method for monitoring a network |
US6931545B1 (en) * | 2000-08-28 | 2005-08-16 | Contentguard Holdings, Inc. | Systems and methods for integrity certification and verification of content consumption environments |
US6968540B2 (en) * | 2000-10-25 | 2005-11-22 | Opnet Technologies Inc. | Software instrumentation method and apparatus |
JP4184613B2 (en) | 2001-01-10 | 2008-11-19 | 株式会社東芝 | Deterioration diagnosis method |
DE50107821D1 (en) * | 2001-01-12 | 2005-12-01 | Siemens Ag | Method and device for computer-aided monitoring of a telecommunications network |
US6799284B1 (en) | 2001-02-28 | 2004-09-28 | Network Appliance, Inc. | Reparity bitmap RAID failure recovery |
WO2002091117A2 (en) | 2001-05-04 | 2002-11-14 | Invensys Systems, Inc. | Process control loop analysis system |
US7313621B2 (en) * | 2001-05-15 | 2007-12-25 | Sony Corporation | Personalized interface with adaptive content presentation |
US20030023710A1 (en) * | 2001-05-24 | 2003-01-30 | Andrew Corlett | Network metric system |
US6708137B2 (en) * | 2001-07-16 | 2004-03-16 | Cable & Wireless Internet Services, Inc. | System and method for providing composite variance analysis for network operation |
AU2002329611A1 (en) * | 2001-07-20 | 2003-03-03 | Altaworks Corporation | System and method for adaptive threshold determination for performance metrics |
US7050936B2 (en) * | 2001-09-06 | 2006-05-23 | Comverse, Ltd. | Failure prediction apparatus and method |
US7219034B2 (en) | 2001-09-13 | 2007-05-15 | Opnet Technologies, Inc. | System and methods for display of time-series data distribution |
US7260741B2 (en) * | 2001-09-18 | 2007-08-21 | Cedar Point Communications, Inc. | Method and system to detect software faults |
US6976189B1 (en) | 2002-03-22 | 2005-12-13 | Network Appliance, Inc. | Persistent context-based behavior injection or testing of a computing system |
GB0208616D0 (en) | 2002-04-15 | 2002-05-22 | Neural Technologies Ltd | A system for identifying extreme behaviour in elements of a network |
US6883113B2 (en) * | 2002-04-18 | 2005-04-19 | Bae Systems Information And Electronic Systems Integration, Inc. | System and method for temporally isolating environmentally sensitive integrated circuit faults |
US7631225B2 (en) * | 2004-10-01 | 2009-12-08 | Cisco Technology, Inc. | Approach for characterizing the dynamic availability behavior of network elements |
US8180922B2 (en) * | 2003-11-14 | 2012-05-15 | Cisco Technology, Inc. | Load balancing mechanism using resource availability profiles |
US7620714B1 (en) | 2003-11-14 | 2009-11-17 | Cisco Technology, Inc. | Method and apparatus for measuring the availability of a network element or service |
US7974216B2 (en) | 2004-11-22 | 2011-07-05 | Cisco Technology, Inc. | Approach for determining the real time availability of a group of network elements |
KR100603585B1 (en) * | 2004-11-26 | 2006-07-24 | 삼성전자주식회사 | Apparatus and method of self-diagnostics for network |
CN101171529A (en) * | 2005-03-18 | 2008-04-30 | 探索无线公司 | Enhanced mobile location |
WO2006096922A1 (en) * | 2005-03-18 | 2006-09-21 | Seeker Wireless Pty Limited | Enhanced mobile location method and system |
US8700069B2 (en) * | 2005-04-08 | 2014-04-15 | Wavemarket, Inc. | Systems and methods for mobile terminal location determination using radio signal parameter measurements |
JP2007013289A (en) * | 2005-06-28 | 2007-01-18 | Fujitsu Ltd | Nut table automatic update system in interlocking with rpr establishment |
US7698113B2 (en) * | 2005-06-29 | 2010-04-13 | International Business Machines Corporation | Method to automatically detect and predict performance shortages of databases |
US7289863B2 (en) * | 2005-08-18 | 2007-10-30 | Brooks Automation, Inc. | System and method for electronic diagnostics of a process vacuum environment |
EP1941749A4 (en) | 2005-10-24 | 2012-04-18 | Wavemarket Inc D B A Location Labs | Mobile service maintenance management |
EP1952578A4 (en) * | 2005-11-04 | 2012-08-29 | Wavemarket Inc D B A Location Labs | Profile based communications service |
US7412356B1 (en) * | 2007-01-30 | 2008-08-12 | Lawrence Livermore National Security, Llc | Detection and quantification system for monitoring instruments |
US20100087194A1 (en) * | 2007-03-13 | 2010-04-08 | Macnaughtan Malcolm David | Enhanced zone determination |
WO2009036497A1 (en) * | 2007-09-17 | 2009-03-26 | Seeker Wireless Pty Limited | Systems and methods for triggering location based voice and/or data communications to or from mobile radio terminals |
US8737985B2 (en) * | 2007-11-26 | 2014-05-27 | Wavemarket, Inc. | Methods and systems for zone creation and adaption |
US8341444B2 (en) * | 2008-02-11 | 2012-12-25 | International Business Machines Corporation | Minimization of power consumption in server environment |
US20110034179A1 (en) * | 2008-04-07 | 2011-02-10 | Seeker Wireless Pty. Limited | Location of wireless mobile terminals |
US8140300B2 (en) * | 2008-05-15 | 2012-03-20 | Becton, Dickinson And Company | High throughput flow cytometer operation with data quality assessment and control |
US8213308B2 (en) | 2008-09-11 | 2012-07-03 | Juniper Networks, Inc. | Methods and apparatus for defining a flow control signal related to a transmit queue |
US8154996B2 (en) * | 2008-09-11 | 2012-04-10 | Juniper Networks, Inc. | Methods and apparatus for flow control associated with multi-staged queues |
US8325749B2 (en) | 2008-12-24 | 2012-12-04 | Juniper Networks, Inc. | Methods and apparatus for transmission of groups of cells via a switch fabric |
WO2010034060A1 (en) * | 2008-09-24 | 2010-04-01 | Iintegrate Systems Pty Ltd | Alert generation system and method |
US7954010B2 (en) * | 2008-12-12 | 2011-05-31 | At&T Intellectual Property I, L.P. | Methods and apparatus to detect an error condition in a communication network |
US8254255B2 (en) | 2008-12-29 | 2012-08-28 | Juniper Networks, Inc. | Flow-control in a switch fabric |
US8331362B2 (en) * | 2008-12-30 | 2012-12-11 | Juniper Networks, Inc. | Methods and apparatus for distributed dynamic network provisioning |
US8190769B1 (en) | 2008-12-30 | 2012-05-29 | Juniper Networks, Inc. | Methods and apparatus for provisioning at a network device in response to a virtual resource migration notification |
US8255496B2 (en) * | 2008-12-30 | 2012-08-28 | Juniper Networks, Inc. | Method and apparatus for determining a network topology during network provisioning |
US8054832B1 (en) | 2008-12-30 | 2011-11-08 | Juniper Networks, Inc. | Methods and apparatus for routing between virtual resources based on a routing location policy |
US8565118B2 (en) * | 2008-12-30 | 2013-10-22 | Juniper Networks, Inc. | Methods and apparatus for distributed dynamic network provisioning |
US8953603B2 (en) * | 2009-10-28 | 2015-02-10 | Juniper Networks, Inc. | Methods and apparatus related to a distributed switch fabric |
US8442048B2 (en) * | 2009-11-04 | 2013-05-14 | Juniper Networks, Inc. | Methods and apparatus for configuring a virtual network switch |
US9264321B2 (en) | 2009-12-23 | 2016-02-16 | Juniper Networks, Inc. | Methods and apparatus for tracking data flow based on flow state values |
JP5418250B2 (en) * | 2010-01-26 | 2014-02-19 | 富士通株式会社 | Abnormality detection apparatus, program, and abnormality detection method |
US8386849B2 (en) * | 2010-01-29 | 2013-02-26 | Honeywell International Inc. | Noisy monitor detection and intermittent fault isolation |
US8244236B2 (en) | 2010-04-29 | 2012-08-14 | Wavemarket, Inc. | System and method for aggregating and disseminating mobile device tag data |
US9602439B2 (en) | 2010-04-30 | 2017-03-21 | Juniper Networks, Inc. | Methods and apparatus for flow control associated with a switch fabric |
US9065773B2 (en) | 2010-06-22 | 2015-06-23 | Juniper Networks, Inc. | Methods and apparatus for virtual channel flow control associated with a switch fabric |
US8621305B2 (en) | 2010-07-08 | 2013-12-31 | Honeywell International Inc. | Methods systems and apparatus for determining whether built-in-test fault codes are indicative of an actual fault condition or a false alarm |
US8553710B1 (en) | 2010-08-18 | 2013-10-08 | Juniper Networks, Inc. | Fibre channel credit-based link flow control overlay onto fibre channel over ethernet |
US8683591B2 (en) | 2010-11-18 | 2014-03-25 | Nant Holdings Ip, Llc | Vector-based anomaly detection |
US9660940B2 (en) | 2010-12-01 | 2017-05-23 | Juniper Networks, Inc. | Methods and apparatus for flow control associated with a switch fabric |
US8504077B2 (en) | 2010-12-04 | 2013-08-06 | Wavemarket, Inc. | System and method for monitoring and disseminating mobile device location information |
US8891406B1 (en) | 2010-12-22 | 2014-11-18 | Juniper Networks, Inc. | Methods and apparatus for tunnel management within a data center |
US9032089B2 (en) | 2011-03-09 | 2015-05-12 | Juniper Networks, Inc. | Methods and apparatus for path selection within a network based on flow duration |
US10331510B2 (en) | 2011-05-23 | 2019-06-25 | Siemens Corporation | Simulation based fault diagnosis using extended heat flow models |
KR101586051B1 (en) * | 2011-05-31 | 2016-01-19 | 한국전자통신연구원 | Apparatus and method for providing vehicle data for testing product |
US8694835B2 (en) | 2011-09-21 | 2014-04-08 | International Business Machines Corporation | System health monitoring |
US8811183B1 (en) | 2011-10-04 | 2014-08-19 | Juniper Networks, Inc. | Methods and apparatus for multi-path flow control within a multi-stage switch fabric |
US8719196B2 (en) | 2011-12-19 | 2014-05-06 | Go Daddy Operating Company, LLC | Methods for monitoring computer resources using a first and second matrix, and a feature relationship tree |
US8600915B2 (en) | 2011-12-19 | 2013-12-03 | Go Daddy Operating Company, LLC | Systems for monitoring computer resources |
US8862727B2 (en) | 2012-05-14 | 2014-10-14 | International Business Machines Corporation | Problem determination and diagnosis in shared dynamic clouds |
US9817884B2 (en) | 2013-07-24 | 2017-11-14 | Dynatrace Llc | Method and system for real-time, false positive resistant, load independent and self-learning anomaly detection of measured transaction execution parameters like response times |
US9547834B2 (en) | 2014-01-08 | 2017-01-17 | Bank Of America Corporation | Transaction performance monitoring |
US10044556B2 (en) | 2015-06-23 | 2018-08-07 | International Business Machines Corporation | Identifying performance-degrading hardware components in computer storage systems |
CA3058076A1 (en) | 2016-07-01 | 2018-01-04 | Paxgrid Cdn Inc. | System for authenticating and authorizing access to and accounting for wireless access vehicular environment consumption by client devices |
US10279816B2 (en) * | 2017-03-07 | 2019-05-07 | GM Global Technology Operations LLC | Method and apparatus for monitoring an on-vehicle controller |
US10771369B2 (en) * | 2017-03-20 | 2020-09-08 | International Business Machines Corporation | Analyzing performance and capacity of a complex storage environment for predicting expected incident of resource exhaustion on a data path of interest by analyzing maximum values of resource usage over time |
US10489225B2 (en) | 2017-08-10 | 2019-11-26 | Bank Of America Corporation | Automatic resource dependency tracking and structure for maintenance of resource fault propagation |
US20190334759A1 (en) * | 2018-04-26 | 2019-10-31 | Microsoft Technology Licensing, Llc | Unsupervised anomaly detection for identifying anomalies in data |
JPWO2022138778A1 (en) * | 2020-12-24 | 2022-06-30 | ||
US11210155B1 (en) * | 2021-06-09 | 2021-12-28 | International Business Machines Corporation | Performance data analysis to reduce false alerts in a hybrid cloud environment |
US11803778B2 (en) | 2021-08-04 | 2023-10-31 | Watsco Ventures Llc | Actionable alerting and diagnostic system for water metering systems |
US11353840B1 (en) * | 2021-08-04 | 2022-06-07 | Watsco Ventures Llc | Actionable alerting and diagnostic system for electromechanical devices |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5113489A (en) * | 1989-01-27 | 1992-05-12 | International Business Machines Corporation | Online performance monitoring and fault diagnosis technique for direct current motors as used in printer mechanisms |
US5237518A (en) * | 1990-10-27 | 1993-08-17 | Vanderbilt University | Optimization method for adaptive sensor reading scheduling and delayed alarm evaluation in real-time diagnostic systems |
US5200126A (en) * | 1990-11-29 | 1993-04-06 | Eastman Kodak Company | Method and apparatus for monitoring the stability of the injection molding process by measurement of screw return time |
US5375126B1 (en) * | 1991-04-09 | 1999-06-22 | Hekimian Laboratories Inc | Integrated logical and physical fault diagnosis in data transmission systems |
CH687110A5 (en) * | 1991-09-10 | 1996-09-13 | Luwa Ag Zellweger | A method for creating a Stoerungsdiagnose on production machines and application of the method to textile machinery. |
US5309448A (en) * | 1992-01-03 | 1994-05-03 | International Business Machines Corporation | Methods and systems for alarm correlation and fault localization in communication networks |
FR2689934B1 (en) * | 1992-04-10 | 1994-06-17 | Siemens Automotive Sa | METHOD AND DEVICE FOR DETECTING THE COMBUSTION IRREGULARITIES OF AN ENGINE, PARTICULARLY MEDIUM AND HIGH SPEED, APPLICATION TO A CONTROL SYSTEM OF AN INJECTION ENGINE. |
GB9208704D0 (en) * | 1992-04-22 | 1992-06-10 | Foxboro Ltd | Improvements in and relating to sensor units |
US5446664A (en) * | 1992-10-07 | 1995-08-29 | Spx Corporation | Method and apparatus for diagnosing faulty cylinders in internal combustion engines |
US5452277A (en) * | 1993-12-30 | 1995-09-19 | International Business Machines Corporation | Adaptive system for optimizing disk drive power consumption |
US5487753A (en) * | 1995-03-16 | 1996-01-30 | Telectronics Pacing Systems, Inc. | Rate-responsive pacemaker with anaerobic threshold adaptation and method |
US5574217A (en) * | 1995-06-06 | 1996-11-12 | Chrysler Corporation | Engine misfire detection with compensation for normal acceleration of crankshaft |
-
1997
- 1997-10-22 US US08/956,227 patent/US6073089A/en not_active Expired - Lifetime
-
1998
- 1998-10-21 EP EP98953788A patent/EP1032841A4/en not_active Withdrawn
- 1998-10-21 AU AU11067/99A patent/AU1106799A/en not_active Abandoned
- 1998-10-21 CA CA002309034A patent/CA2309034C/en not_active Expired - Lifetime
- 1998-10-21 WO PCT/US1998/022190 patent/WO1999021017A1/en active Application Filing
- 1998-10-21 JP JP2000517283A patent/JP2001521210A/en active Pending
Non-Patent Citations (6)
Title |
---|
D. SNG: "Network Monitoring and Fault Detection on the University of Illinois at Urbana-Champaign Campus Computer Network", TECHNICAL REPORT, 1990 |
F. FEATHER: "Fault Detection in an Ethernet Network via Anomaly Detectors", PH.D. DISSERTATION, 1992 |
J. HANSEN, THE USE OF MULTI-DIMENSIONAL PARAMETRIC BEHAVIOR OF A CSMA/CD NETWORK FOR NETWORK DIAGNOSIS, 1992 |
R. MAXION; F. FEATHER: "A Case Study of Ethernet Anomalies in a Distributed File System Environment", IEEE TRANSACTIONS ON RELIABILITY, vol. 39, no. 4, 1990, pages 433 - 43 |
See also references of EP1032841A4 * |
SNG D. C.-H.: "NETWORK MONITORING AND FAULT DETECTION ON THE UNIVERSITY OF ILLINOIS AT URBANA-CHAMPAIGN CAMPUS COMPUTER NETWORK.", REPORT UIUCDCS-R-90-1595, XX, XX, 1 April 1990 (1990-04-01), XX, pages A + III - VIII + 01, XP002920291 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2018018A3 (en) * | 2000-05-12 | 2009-04-08 | Niksun, Inc. | Security camera for a network |
US8275875B2 (en) | 2000-05-12 | 2012-09-25 | Niksun, Inc. | Security camera for a network |
US10110632B2 (en) | 2003-03-31 | 2018-10-23 | Intel Corporation | Methods and systems for managing security policies |
WO2007085504A2 (en) * | 2006-01-25 | 2007-08-02 | Siemens Aktiengesellschaft | Method for the detection of a fault during operation of a system comprising a certain number of data records |
WO2007085504A3 (en) * | 2006-01-25 | 2007-10-25 | Siemens Ag | Method for the detection of a fault during operation of a system comprising a certain number of data records |
Also Published As
Publication number | Publication date |
---|---|
CA2309034A1 (en) | 1999-04-29 |
US6073089A (en) | 2000-06-06 |
JP2001521210A (en) | 2001-11-06 |
CA2309034C (en) | 2009-07-28 |
EP1032841A1 (en) | 2000-09-06 |
EP1032841A4 (en) | 2010-09-01 |
AU1106799A (en) | 1999-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA2309034C (en) | Systems and methods for adaptive profiling, fault detection, and alert generation in a changing environment which is measurable by at least two different measures of state | |
US6457143B1 (en) | System and method for automatic identification of bottlenecks in a network | |
US6973415B1 (en) | System and method for monitoring and modeling system performance | |
US7813298B2 (en) | Root cause problem detection in network traffic information | |
US7280988B2 (en) | Method and system for analyzing and predicting the performance of computer network using time series measurements | |
US7502844B2 (en) | Abnormality indicator of a desired group of resource elements | |
US7318178B2 (en) | Method and system for reducing false alarms in network fault management systems | |
US7725571B1 (en) | Method and apparatus for service analysis in service level management (SLM) | |
JP4965064B2 (en) | Self-learning method and system for anomaly detection | |
Long et al. | A study of the reliability of internet sites | |
CN108848515A (en) | A kind of internet of things service quality-monitoring platform and method based on big data | |
EP1998252A1 (en) | Method and apparatus for generating configuration rules for computing entities within a computing environment using association rule mining | |
EP0861545A1 (en) | Method of determining the topology of a network of objects | |
US7197428B1 (en) | Method for performance monitoring and modeling | |
CN104854577A (en) | Method and apparatus for detecting and analyzing noise and other events affecting communication system | |
CN117612687B (en) | Medical equipment monitoring and analyzing system based on artificial intelligence | |
EP3742700B1 (en) | Method, product, and system for maintaining an ensemble of hierarchical machine learning models for detection of security risks and breaches in a network | |
CN108809708A (en) | A kind of powerline network node failure detecting system | |
CN110224885A (en) | Alarm method, device, storage medium and the electronic equipment of monitoring of tools | |
CN113392893B (en) | Method, device, storage medium and computer program product for locating business fault | |
US7426502B2 (en) | Assessing health of a subsystem or service within a networked system | |
CN107590008A (en) | A kind of method and system that distributed type assemblies reliability is judged by weighted entropy | |
Nie et al. | Passive diagnosis for WSNs using data traces | |
Bovenzi et al. | A statistical anomaly-based algorithm for on-line fault detection in complex software critical systems | |
Allen et al. | On the self-similarity of synthetic traffic for the evaluation of intrusion detection systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AL AM AT AU AZ BA BB BG BR BY CA CH CN CU CZ DE DK EE ES FI GB GE GH GM HU ID IL IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MD MG MK MN MW MX NO NZ PL PT RO RU SD SE SG SI SK SL TJ TM TR TT UA UG UZ VN YU ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GH GM KE LS MW SD SZ UG ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE BF BJ CF CG CI CM GA GN GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
ENP | Entry into the national phase |
Ref document number: 2309034 Country of ref document: CA Ref country code: CA Ref document number: 2309034 Kind code of ref document: A Format of ref document f/p: F |
|
NENP | Non-entry into the national phase |
Ref country code: KR |
|
ENP | Entry into the national phase |
Ref country code: JP Ref document number: 2000 517283 Kind code of ref document: A Format of ref document f/p: F |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1998953788 Country of ref document: EP |
|
REG | Reference to national code |
Ref country code: DE Ref legal event code: 8642 |
|
WWP | Wipo information: published in national office |
Ref document number: 1998953788 Country of ref document: EP |