KR20150137950A - Apparatus and method for system monitoring - Google Patents

Apparatus and method for system monitoring Download PDF

Info

Publication number
KR20150137950A
KR20150137950A KR1020140133525A KR20140133525A KR20150137950A KR 20150137950 A KR20150137950 A KR 20150137950A KR 1020140133525 A KR1020140133525 A KR 1020140133525A KR 20140133525 A KR20140133525 A KR 20140133525A KR 20150137950 A KR20150137950 A KR 20150137950A
Authority
KR
South Korea
Prior art keywords
state
data set
subsystems
time
indicator
Prior art date
Application number
KR1020140133525A
Other languages
Korean (ko)
Inventor
오규삼
김형찬
서범준
권순환
조상원
Original Assignee
삼성에스디에스 주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 삼성에스디에스 주식회사 filed Critical 삼성에스디에스 주식회사
Priority to PCT/KR2014/010250 priority Critical patent/WO2015182831A1/en
Priority to CN201510063712.2A priority patent/CN105278494A/en
Priority to US14/616,131 priority patent/US20150347213A1/en
Publication of KR20150137950A publication Critical patent/KR20150137950A/en

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F11/00Error detection; Error correction; Monitoring
    • G06F11/30Monitoring
    • G06F11/3089Monitoring arrangements determined by the means or processing involved in sensing the monitored data, e.g. interfaces, connectors, sensors, probes, agents
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10Services
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02PCLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • General Engineering & Computer Science (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

A system monitoring apparatus and method are disclosed. A system monitoring apparatus according to an exemplary embodiment includes a data collection unit configured to collect a first data set obtained in a monitored system and determined to indicate the status of the system and a second data set obtained in the system; And an output unit configured to calculate an index associated with the status of the system using the first data set and the second data set.

Figure P1020140133525

Description

[0001] APPARATUS AND METHOD FOR SYSTEM MONITORING [0002]

The disclosed embodiments relate to a system monitoring apparatus and method, and more particularly to a technique for diagnosing and indexing the state of a system.

With the development of information and communication technologies, there has been an increasing demand for services that place various types of sensors in buildings and control devices in buildings based on sensor values. The state of the system providing such service may be monitored based on sensor values. Typically, such system monitoring involves determining whether the system is healthy or defective.

However, existing system monitoring techniques are not useful for detecting potential defects in the system. In general, the conventional technique only informs the user of a situation in which a fault has already occurred, and sets a protective threshold for determining that such a situation has occurred with only a slight possibility that the system is not normal. In addition, for a system with a high degree of complexity, the above-mentioned dichotomous judgment is difficult to show satisfactory performance. Therefore, there is a need for an improved technique for monitoring the above system to diagnose the system state.

The disclosed embodiments provide a system monitoring apparatus and method.

According to an exemplary embodiment, a data collection unit is configured to collect a first data set obtained in a monitored system and determined to indicate the status of the system and a second data set obtained in the system; And a calculation unit configured to calculate an indicator associated with the state of the system using the first data set and the second data set.

The first set of data may be one determined to indicate that the state of the system at the first time is a steady state or a defective state.

The indicator may comprise a basic state index value associated with the state of the system at a second time point.

The indicator may include an operational state index value associated with a state of the system over a time period from a time preceding the second time point to a second time point.

Wherein the calculating unit may be configured to calculate the operational state index value from a plurality of time-based basic state index values, each of the plurality of time-based basic state index values being associated with a state of the system at a point in time within the time period .

The system may comprise a plurality of subsystems, and the indicator may comprise a substatus index value associated with a status of one of the plurality of subsystems at the second time point.

Wherein the calculating unit may be configured to calculate the lower status indicator value from the plurality of subsystem-based basic status indicator values, wherein each of the plurality of the basic status indicator values for each of the plurality of subsystems comprises: Can be associated with one state.

The lower status indicator value may be a minimum value among the plurality of basic status indicator values for each subsystem.

The system monitoring apparatus may further include an interface unit configured to display the indicator on a user interface.

The system may include a plurality of subsystems, and the calculating unit may be further configured to calculate an index for each of the plurality of subsystems, wherein the interface unit is further configured to calculate, , Wherein each of the plurality of indicators for each subsystem may be associated with a status of a corresponding one of the plurality of subsystems.

The interface may also be configured to present at least one of the plurality of subsystems in an emphasized format.

Wherein the calculating unit may be further configured to calculate a degree of similarity between the first data set and the second data set, and the system monitoring apparatus is further configured to determine, based on the threshold and the similarity associated with the first data set, And a determination unit configured to determine whether the set indicates an abnormal symptom state of the system, the normal state, or the defect state.

The calculating unit may be further configured to calculate the index from the similarity.

Wherein the first data set may comprise a plurality of first sensor values measured through a plurality of sensors installed in association with the system and the second data set comprises a plurality of second sensors Value. ≪ / RTI >

The calculating unit may be further configured to calculate the contribution of each of the plurality of sensors to the similarity if it is determined that the second data set represents the defect state or the abnormal symptom state.

The determination unit may be further configured to select one of the plurality of sensors as a sensor to be inspected based on the calculated contribution.

The similarity may indicate a distance between the first data set and the second data set according to a predetermined distance metric.

The second data set may be determined to indicate the steady state if the distance is less than the threshold and the first data set is determined to represent the steady state and the distance is less than the threshold and the first data The second data set may be determined to indicate the fault state if the set is determined to represent the fault condition and the second data set may be determined to indicate the abnormal symptom condition if the distance is greater than the threshold value have.

The calculating unit may be further configured to calculate a basic state index value associated with a state of the system at a second time point from the distance, and the basic state index value is determined when the first data set indicates the normal state And the basic state index value may be calculated based on an increasing function for the distance when it is determined that the first data set represents the fault state.

According to another exemplary embodiment, there is provided a system monitoring method implemented by a computing device, the method comprising: collecting a first data set obtained in a monitored system and determined to indicate the status of the system and a second data set obtained in the system step; And calculating an indicator associated with the status of the system using the first data set and the second data set.

The first set of data may be one determined to indicate that the state of the system at the first time is a steady state or a defective state.

The indicator may comprise a basic state index value associated with the state of the system at a second time point.

The indicator may include an operational state index value associated with a state of the system over a time period from a time preceding the second time point to a second time point.

Wherein the calculating step may include calculating the operational state index value from a plurality of time-based basic state index values, wherein each of the plurality of time-based basic state indexes is calculated based on the time- Lt; / RTI >

The system may comprise a plurality of subsystems, and the indicator may comprise a substatus index value associated with a status of one of the plurality of subsystems at the second time point.

Wherein the calculating step may include calculating the lower status indicator value from the basic status indicator value for each of the plurality of subsystems, wherein each of the plurality of basic status indicator values for each of the plurality of subsystems includes the plurality RTI ID = 0.0 > of, < / RTI >

The lower status indicator value may be a minimum value among the plurality of basic status indicator values for each subsystem.

The system monitoring method may further include the step of presenting the indicator to the user interface.

The system may include a plurality of subsystems, the method comprising: calculating an indicator for each of the plurality of subsystems; And presenting at least some of the plurality of subsystem-specific indicators in the user interface in response to receiving user input, wherein each of the plurality of subsystem-specific indicators is associated with a corresponding one of the plurality of subsystems Lt; RTI ID = 0.0 > and / or < / RTI >

And displaying at least one of the plurality of subsystems in an emphasized format.

The system monitoring method comprising: calculating a degree of similarity between the first data set and the second data set; And determining based on the threshold and the similarity associated with the first data set whether the second data set represents an anomalous state of the system, the steady state, or the fault state.

The system monitoring method may further include calculating the indicator from the similarity.

Wherein the first data set may comprise a plurality of first sensor values measured through a plurality of sensors installed in association with the system and the second data set comprises a plurality of second sensors Value. ≪ / RTI >

The system monitoring method may further include calculating the contribution of each of the plurality of sensors to the similarity when it is determined that the second data set represents the defect state or the abnormal symptom state.

The system monitoring method may further include selecting one of the plurality of sensors as a sensor to be inspected based on the calculated contribution.

The similarity may indicate a distance between the first data set and the second data set according to a predetermined distance metric.

The second data set may be determined to indicate the steady state if the distance is less than the threshold and the first data set is determined to represent the steady state and the distance is less than the threshold and the first data The second data set may be determined to indicate the fault state if the set is determined to represent the fault condition and the second data set may be determined to indicate the abnormal symptom condition if the distance is greater than the threshold value have.

The system monitoring method may further comprise calculating a basic state index value associated with a state of the system at a second time point from the distance and wherein the basic state index value indicates that the first data set is in the steady state And the basic state index value can be calculated based on an increasing function for the distance when it is determined that the first data set represents the fault state have.

According to yet another exemplary embodiment, there is provided a method of monitoring a system, comprising a basic state indicator value associated with a point-in-time condition of a monitored system and including an operating state indicator value associated with a time- A status indicator configured to obtain a system status indicator further comprising at least one of a status indicator value; And an interface unit configured to display the system status indicator in a user interface.

The basic state index value may indicate a state of the system at a specific point in time and the operation state index value may indicate a state of the system over a time period from a point preceding the point in time to the point in time, The lower status indicator value may indicate the status of the particular subsystem at the particular point in time.

Wherein the calculating unit may be configured to obtain the operational state index value using a plurality of time-based basic state indexes, and each of the plurality of time-based basic state indexes may include a state of the system at a point within the time period Lt; / RTI >

The calculating unit may be configured to obtain the lower state index value using a plurality of subsystem-specific basic state index values, and the system may include a plurality of subsystems, System, and each of the plurality of subsystem-specific basic status indicator values may be associated with a status of one of the plurality of subsystems at the specific time.

The lower status indicator value may be a minimum value among the plurality of basic status indicator values for each subsystem.

The system may include a plurality of subsystems, the plurality of subsystems may include the particular subsystem, and the calculating unit may be further configured to obtain a plurality of subsystem-specific system state indicators, Each of the plurality of subsystem-specific system status indicators may be associated with a status of a corresponding one of the plurality of subsystems, and the interface unit may also display at least some of the plurality of subsystem-specific system status indicators on the user interface .

The interface may also be configured to present at least one of the plurality of subsystems in a highlighted format on the user interface.

According to yet another exemplary embodiment, there is provided a method of monitoring a system, comprising a basic state indicator value associated with a point-in-time condition of a monitored system and including an operating state indicator value associated with a time- Obtaining a system status indicator that further includes at least one of a lower status indicator value; And presenting the system state indicator to a user interface.

The basic state index value may indicate a state of the system at a specific point in time and the operation state index value may indicate a state of the system over a time period from a point preceding the point in time to the point in time, The lower status indicator value may indicate the status of the particular subsystem at the particular point in time.

Wherein the acquiring may include acquiring the operational state index value using a plurality of time-based basic state indexes, and each of the plurality of time-based basic state indexes may include a time- May be associated with the state of the system.

The acquiring may comprise acquiring the substatus index value using a plurality of subsystem-specific basic status indicator values, the system may comprise a plurality of subsystems, May comprise the particular subsystem and each of the plurality of subsystem-specific basic status indicator values may be associated with a status of one of the plurality of subsystems at the particular time.

The lower status indicator value may be a minimum value among the plurality of basic status indicator values for each subsystem.

The system may include a plurality of subsystems, the plurality of subsystems may include the particular subsystem, and the system monitoring method further comprises obtaining a plurality of subsystem-specific system status indicators And wherein each of the plurality of subsystem-specific system status indicators may be associated with a status of a corresponding one of the plurality of subsystems, and wherein the system monitoring method is adapted to detect at least some of the plurality of subsystem- To the user interface.

The system monitoring method may further include presenting at least one of the plurality of subsystems to the user interface in an emphasized format.

According to an exemplary embodiment, a computer readable storage medium having stored thereon a computer program for executing any one of the methods is provided.

According to certain embodiments, techniques are provided that not only can determine that the monitored system is healthy or defective, but can also determine that a potential defect or anomalous indication has occurred in the system.

According to some embodiments, even though the data indicative of the fault condition of the monitored system and the fault occurrence situation associated therewith are not defined (e.g., by an expert with detailed knowledge of the system) The state of the system can be determined as an abnormal symptom state only by the data indicating that the monitoring target system can be operated economically and conveniently.

According to some embodiments, the status of the monitored system can be efficiently presented, and anomalous indications of the system or elements that cause defects can be easily recognized.

1 illustrates an operating environment in which a system monitoring device according to an exemplary embodiment is deployed,
Figure 2 illustrates a graphical representation of a system state indicator in accordance with an illustrative embodiment;
Figure 3 illustrates a user interface according to an exemplary embodiment;
4 is a diagram for explaining a similarity degree calculation and system state determination according to an exemplary embodiment;
Figure 5 illustrates a user interface according to an exemplary embodiment;
6 is a diagram illustrating a system monitoring process according to an exemplary embodiment;
FIG. 7 illustrates a system monitoring process according to an exemplary embodiment;
Figures 8-10 each illustrate graphical representations representing different system status indicators in accordance with an exemplary embodiment;

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The following detailed description is provided to provide a comprehensive understanding of the methods, apparatus, and / or systems described herein. However, this is merely an example and the present invention is not limited thereto.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. The following terms are defined in consideration of the functions of the present invention, and may be changed according to the intention or custom of the user, the operator, and the like. Therefore, the definition should be based on the contents throughout this specification. The terms used in the detailed description are intended only to describe embodiments of the invention and should in no way be limiting. Unless specifically stated otherwise, the singular forms of the expressions include plural forms of meanings. In this description, the expressions "comprising" or "comprising" are intended to indicate certain features, numbers, steps, operations, elements, parts or combinations thereof, Should not be construed to preclude the presence or possibility of other features, numbers, steps, operations, elements, portions or combinations thereof.

Figure 1 illustrates an operating environment in which a system monitoring device according to an exemplary embodiment is deployed.

The exemplary operating environment 100 includes a system monitoring device 110, at least one monitored system 120, a database 140, and a user device 160.

The monitored system 120 is configured to provide a service (e.g., an intelligent management / control solution) to a building, a device installed in such a building, or other type of facility. The monitored system 120 may include various sensors (e.g., temperature sensors, humidity sensors, airflow sensors, etc.) disposed in such facilities. In addition, the monitored system 120 may further include an actuator for driving the sensors, a controller for controlling the facility, and the like. The monitored system 120 may provide data to the system monitoring device 110 that includes sensor values measured by the sensors.

The system monitoring device 110 is configured to collect data sets from the monitored system 120 and the database 140 and to monitor the monitored system 120 based on the collected data sets. Each data set may include sensor values measured through a plurality of sensors. In some embodiments, the system monitoring device 110 may be implemented or included within a computing device. Such a computing device may include one or more processors and a computer-readable storage medium accessible by the processor. The computer-readable storage medium may be internal or external to the processor, and may be coupled to the processor by any of a variety of well-known means. Computer-readable storage media may store computer-executable instructions. The processor may execute instructions stored on the computer readable storage medium. Such an instruction may cause the computing device, when executed by the processor, to perform operations in accordance with the illustrative embodiment.

The system monitoring device 110 may determine the status of the monitored system 120 from the newly acquired data set in the monitored system 120. In some embodiments, the system monitoring device 110 may determine that the newly acquired data set represents a state of the monitored system 120 at a particular point in time, which state may be any of the following.

- steady state: the monitored system 120 is healthy

- Defect Status: The monitored system 120 is faulty

- Abnormal Indication Status: The monitored system 120 exhibits an abnormal indication

For the sake of convenience, hereinafter, a data set indicating a normal state of the system such as the monitoring target system 120, a data set indicating a defective state of the system, and a data set indicating an abnormal symptom state of the system are referred to as "normal data" Quot; data "and" abnormality symptom data ". In addition, the above determination performed by the system monitoring apparatus 110 may also be referred to as "system state determination ".

The system monitoring device 110 may use the data set determined to represent the status of the monitored system 120 at the preceding time (e.g., the data set previously determined to be normal data or defective data) , Defect data, or abnormality symptom data. If the new data set is determined to be a normal data set or defect data, then the data set can also be used for determination regarding the subsequent data set.

The database 140 may maintain the data set determined to be normal data or fault data with the system state represented by the data set. For example, if a data set is normal data or defect data as determined by the system monitoring device 110 as described above, the data set may be stored in the database 140. As another example, if a user of the system monitoring device 110 directly determines that a data set is normal data (or, in some cases, defect data), the data set may also be stored in the database 140. This data set may be required for an initial system state determination of the system monitoring device 110. Further, after determining that the data set that has been determined (and presented to the user) as abnormal symptom data through system state determination of the system monitoring apparatus 110 is normal data or defect data, the data set is stored in the system monitoring apparatus 110 May be stored in the database 140 for subsequent system status determination. Therefore, even if the defect status of the system is not clearly defined in advance, the status of the monitored system 120 can be efficiently determined. This technique may allow a user to diagnose the status of the monitored system 120 and / or to operate the monitored system 120, even if the user is not specific to the monitored system 120 but has some knowledge.

In addition, the system monitoring device 110 may determine a system state indicator (not shown) associated with the state of the monitored system 120 based on the newly acquired data set and the previously determined data set as normal data or fault data in the monitored system 120 Can be calculated. The calculated indicator can be represented in the user interface provided to the user device 160. [ The user can effectively recognize the state of the monitored system 120 by utilizing such a system state index. For example, the system monitoring device 110 may provide a graphical user interface, including the graphical representation 200 shown in FIG. 2, to a user device 160, such as a display device. The graphical representation 200 of FIG. 2 visually exposes exemplary system state indicators. The graphical representation 200 may include a graphical representation of at least one of the indicator values described below (e.g., graphical representations 210, 220, 230).

Default State Indicator Value

The system state indicator may include an indicator value, which may also be referred to as a "basic state indicator value ". The basic state index values may be associated with the state of the monitored system 120 at a particular point in time. For example, the default state indicator value may be set to a value within a suitable range (e.g., 0 to 100%) to indicate the current state of the monitored system 120. For example, a basic state index value of 10% and a basic state index value of 90% may indicate that the monitoring target system 120 is not operating properly and that the monitoring target system 120 is operating normally, respectively . Accordingly, the user can easily diagnose the state of the monitoring target system 120 and check whether the monitoring target system 120 has a failure in a manner that is needed when necessary.

Operational State Indicator Value

The system status indicator may further include other indicator values, which may also be referred to as "operational status indicator values. &Quot; The operational state index values may be associated with the state of the monitored system 120 over a specific time period. As noted above, while the default state indicator values may indicate the state of the monitored system 120 at the current time, the operational state indicator values may be monitored over a specific time period (e.g., from the previous time to the current time) May be set to indicate the state of the system 120. For example, the operational state index value may be calculated from the basic state index values (i.e., associated with the state of the monitored system 120 at each point within the time period) . In view of this, if the status of the monitored system 120 has changed at some point but the change is due to normal operation (eg, when the boiler is operating in the building as the winter approaches) The operational state index value will be useful for the user to recognize that the monitored system 120 is operating normally.

Indicator values associated with the state of the parent system containing the subsystems

In some embodiments, the operating environment 100 may include a plurality of monitored systems 120, and the plurality of monitored systems 120 may be a plurality of subsystems included in the parent system. For example, the upper system corresponds to the building in which the sensors are located and each monitored system 120 is connected to a different device (e.g., an air conditioner, cooling tower, generator, boiler or heating heat exchanger) . Furthermore, a plurality of monitoring target systems 120 may be classified into a plurality of upper level systems, and a plurality of upper level systems may constitute a single highest level system. As such, the top level system can be represented by multiple layers. For example, referring to FIG. 3, it will be appreciated that the top level system may be represented, for example, in four layers (from the highest layer "layer 1" to the lowest layer "layer 4"). In this example, the entire system may include three subsystems on "layer 2" as a layer 1-system. Also, one of these three tier two-systems may include three subsystems on "tier three ". Similarly, one of these three tier 3-systems may include three tier 4-systems.

The system monitoring device 110 may perform the aforementioned operations for each of the plurality of monitored systems 120. [ In addition, the system monitoring device 110 may provide a bottom-up approach for monitoring an upper system including a plurality of monitored systems 120.

For example, the system monitoring apparatus 110 may calculate the following values as system status indicators of an upper system. First, the basic state index value of the upper system can be calculated from the basic state index values of each of the plurality of monitoring target systems 120. [ In addition, the system monitoring apparatus 110 may calculate an operation state index value of the upper system from the basic state index values of the upper system calculated at specific monitoring points within the specific time period. Further, the system monitoring device 110 may generate index values associated with the status of one of the subsystems (i.e., the plurality of monitored systems 120). This index value may be referred to as a "lower status index value ". For example, the substatus index value may be computed from the subsystem-specific basic status index values computed for each subsystem (i. E., Each associated with one of the subsystems at a particular time point). This sub-state indicator value allows the user to conveniently monitor not only the parent system but also a specific subsystem at once, when the user is presented with the basic state indicator value and the operation state indicator value of the parent system. For example, the system monitoring device 110 may calculate a minimum value among the basic status indicator values of the subsystems as a lower status indicator value. In this sense, this sub-state index value can also be referred to specifically as the "minimum state index value" of the parent system. If the parent system includes a significant number of subsystems, it may be difficult for the user to detect that the underlying state index values of the parent system may have caused a fault in any subsystem. For example, if 99 out of 100 monitored systems 120 have a basic status indicator value of 1, and one of them has a default status indicator value of 0, the average (99%) of the 100 basic status indicator values And can be presented to the user as a basic state index value of the parent system. Therefore, the minimum state index value (0%) of the parent system can allow the user to recognize the need for detailed fault checking.

The system monitoring device 110 may then provide a user interface to the user device 160 that includes the graphical representation 200 of FIG. As shown in FIG. 2, the graphical representation 200 may include a graphical representation 210, each representing a basic state index value, an operational state index value, and a lower state index value (e.g., a minimum state index value) (220) and a graphical representation (230). According to some embodiments, the system monitoring device 110 may initially represent the system state index of the parent system in the user interface and receive a particular user input (e.g., a mouse click to select the graphical representation 200) The system state indicators of the subsystems can be exposed on the user interface.

Accordingly, even if the user does not have sufficient expertise in the monitoring target system 120, the user can easily check the status of the monitoring target system 120, the status of the monitored target system 120 State and state of each subsystem of the monitoring target system 120 can be efficiently grasped if the subsystem of the monitoring target system 120 exists. As examples for illustration, each of Figures 8-10 shows a graphical representation representing different system status indicators according to an exemplary embodiment.

As an example, the graphical representation 800 of FIG. 8 includes graphical representations 810, 820, 830. FIG. The graphical representations 810, 820 and 830 respectively represent a basic state index value, an operating state index value, and a minimum state index value of the monitored system 120. Referring to FIG. 8, it can be seen that the operating state index value and the minimum state index value are not significantly different from the basic state index value. Accordingly, the user can quickly recognize that a change in the operation of the monitoring target system 120 or a defect of a specific subsystem of the monitoring target system 120 is not a suspicious situation.

As another example, the graphical representation 900 of FIG. 9 includes graphical representations 910, 920, 930. The basic state index values represented by the graphical representation 910 are not very high, and the operational state index values represented by the graphical representation 920 also have low values. Accordingly, the user can determine that there is a high possibility that factors such as a change in the operation of the monitoring target system 120 or an aging of the monitoring target system 120 have occurred. In addition, the graphical representation 930, which represents a minimum state index value near zero, can intuitively remind the user that such a possibility as well as an indication that a particular subsystem of the monitored system 120 may have failed .

As another example, the graphical representation 1000 of FIG. 10 includes graphical representations 1010, 1020, and 1030. Graphical representation 1010 and graphical representation 1020 represent similar basic state index values and operational state index values, respectively, while graphical representation 1030 represents a significantly lower minimum state index value. Accordingly, it can be predicted that there is a high possibility that a specific subsystem of the monitoring target system 120 is defective although the monitoring target system 120 operates as a whole and does not undergo significant change in operation.

3 illustrates a user interface according to an exemplary embodiment.

The exemplary user interface 300 may be provided to the user device 160 from the system monitoring device 110, either by user input or by default. 3, the user interface 300 includes graphical representations 311, 321, 322, 323, and 331 of indicator values generated by the system monitoring apparatus 110 for the above-mentioned four-tier top level system , 332, 333, 341, 342, 343). The graphical representation 311 of the system state index of the top level system of tier 1 may represent the basic state index value, the operational state index value, and the minimum state index value of the top-level system in the same manner as the graphical representation 200 of FIG. Similarly, each of the graphical representations 321, 322, and 323 may represent a corresponding one of the three tier two-system indicators, and each of the graphical representations 331, 332, - Each of the graphical representations 341, 342, and 343 may represent a corresponding one of the three tier-four systems. The graphical representation 370, the graphical representation 380, and the graphical representation 390, respectively, may represent a relationship between a system of an upper layer and sub-systems of the system. 3, the graphical representations 341, 342, and 343 are displayed on the basis of the basic state index values in the other graphical representations 311, 321, 322, 323, 331, 332, The same value as the state index value can be expressed.

An exemplary implementation of the system monitoring device 110 is described in further detail below. Referring again to FIG. 1, the system monitoring apparatus 110 may include a data collecting unit 112, a calculating unit 114, a determining unit 116, and an interface unit 118. Each component of the system monitoring device 110 may be implemented by hardware (e.g., processor, memory, network interface, display interface, input / output interface, etc.) of the computing device.

The data collection unit 112 may receive a data set that includes sensor values obtained by the monitored system 120 at a particular point in time. If N sensor values are obtained, this data set can be represented by an N-dimensional data point X = (x 1 , x 2 , ..., x N ). For convenience, this data set may also be referred to below as "Data Set X ".

The data collecting unit 112 collects a plurality of data sets previously determined to indicate a normal state of the monitoring target system 120 or a defect state of the monitoring target system 120 after being acquired by the monitoring target system 120. [ (Each data set including N sensor values) from the database 140. These data sets may be represented by N-dimensional data points Y i = (y i1 , y i2 , ..., y iN ), respectively. For convenience, each of these data sets may also be referred to below as "data set Y i ".

The calculation unit 114 may calculate a data set (hereinafter also referred to as "data set Y") most similar to the data set X among the data sets collected from the database 140. For this, the calculating unit 114 may calculate the degree of similarity between each of the data sets collected from the database 140 and the data set X. [ This similarity may represent the distance between two data sets according to a predetermined distance metric. For example, the similarity may be given as an Euclidean distance. In this case, the degree of similarity between the data set X and the data set Y is given by the following equation.

Figure pat00001

For a specific example, assume that two sets of data Y 1 and Y 2 are collected from database 140 and represented as two data points 410 and 420, respectively, in FIG. 4. If a two-dimensional data point 401 represents a data set X, the data set Y 1 will be calculated as a data set Y that is more similar to the data set X. Alternatively, if the two-dimensional data point 402 represents a data set X, the data set Y 2 will be calculated as a data set Y that is more similar to the data set X. As another example, if a two-dimensional data point 403 represents a data set X, the data set Y 1 will be calculated as a data set Y that is more similar to the data set X.

Furthermore, the calculating unit 114 may calculate an index associated with the state of the monitoring target system 120 from the calculated similarity. In some embodiments, the calculation unit 114 may calculate a basic state index value from the distance r between the data set X and the data set Y as follows.

If it is determined that data set Y represents a steady state of the monitored system 120, the calculation unit 114 may calculate a basic state index value based on a decrease function for the distance r. For example, the basic state index value can be given as 1 / (1 + r). As another example, the basic state index value may be given by the following equation.

Figure pat00002

Here, assuming that P data sets Y i are collected from the database 140, max d is the maximum value among the P elements y 1d , y 2d , ..., y Pd , and min d is the maximum value among the elements It is the minimum value.

If the data set Y is determined to indicate a fault condition of the monitored system 120, the calculation unit 114 may calculate a basic state index value based on an increasing function of the distance r. For example, the basic state index value may be given as 1 - {1 / (1 + r)}. As another example, the basic state index value may be given by the following equation.

Figure pat00003

As described above, the basic state index value can be calculated so that the closer the data set X is to normal data, the closer to 1 and closer to the defect data, the closer to 0. Therefore, the basic state index value may indicate that the state of the monitoring target system 120 is likely to be good when the data set Y is determined to be normal data. In addition, the basic state index value may indicate that the state of the monitoring target system 120 is likely to be poor when the data set Y is determined to be defective data.

For the sake of concrete example, it is assumed in FIG. 4 that data points 410 and 420 represent normal data and defect data, respectively. If the data point 401 or the data point 403 represents a data set X, the basic state index value of the monitored system 120 may be computed based on a reduction function for the distance r. Alternatively, if the data point 402 represents a data set X, the basic state index value of the monitored system 120 may be computed based on an increasing function on the distance r.

According to some embodiments, data set Y may be clustered data. Whether the data set (for example, the data set Y) stored in the database 140 is normal data or defective data when the database 140 is constructed using the clustering technique is determined by a ratio of normal data to combined data, And a preset threshold value. Furthermore, the basic state index value calculated as above can be adjusted according to the above ratio. For example, if the ratio of the normal data to the combined data in the data set Y is 8: 2 and the value calculated according to Equation 2 is 0.9, finally the basic state index value is 0.9 * 0.8 = 0.72 (i.e., 72%) Can be calculated.

The determining unit 116 may determine whether the data set X represents an abnormal symptom state, a steady state, or a defective state of the monitored system 120, based on the threshold associated with the data set Y and the calculated similarity. For example, when the degree of similarity indicates the distance r between the data set X and the data set Y as described above, the determination unit 116 can determine the state of the monitored system 120 as follows.

If the distance r is less than the threshold and the data set Y is determined to be normal data, then the data set X is determined to represent the steady state of the monitored system 120.

If the distance r is less than the threshold and the data set Y is determined to be defective data, then the data set X is determined to indicate the defective state of the monitored system 120.

If the distance r is greater than the threshold, then the data set X is determined to indicate the anomalous state of the monitored system 120.

4 is a threshold R 1 associated with data set Y 1 (normal data) represented by data point 410, and the radius of circle 422 in FIG. 4 is Assume a threshold R 2 associated with data set Y 2 (defect data) represented by data point 420. For example, if the data point 401 represents a data set X, because the distance between the data sets X and the data set Y 1 is less than R 1 data set X may be represent the determination that the monitored system 120 is normal . As another example, data point 402 is the case of representing the data set X, because the distance between the data sets X and the data set Y 2 is smaller than R 2 the data set X will denote the monitoring target system 120, that the fault is determined . As yet another example, data point 403, the data set in the case, the data set X and a set of data Y is larger than the R 1 the distance between the first representing data sets X X will show the monitoring target system 120, the abnormality ≪ / RTI >

In view of the above, when the data set X is included in the valid range of the data set Y, it can be determined that the data set X represents the state represented by the data set Y as it is. Otherwise, the data set X may be determined to represent an abnormal symptom state. As a result, the threshold associated with data set Y may also be referred to as the effective range of data set Y. [ This validity range may be established using various statistical methods (e.g., by applying an n-fold cross validation technique based on the history of the defects of the monitored system 120). The greater the effective range, the higher the possibility that the state of the monitoring target system 120 is erroneously judged as a defective state or a normal state. On the other hand, the smaller the effective range, the more frequently the state of the monitoring target system 120 may be determined to be in an abnormal symptom state. As an example, a suitable effective range may be given by the following equation.

Figure pat00004

In addition, when it is determined that the data set X represents a defect status or abnormality symptom state of the monitored system 120, the calculating unit 114 may calculate the similarity between the data set X and the data set Y, Can be calculated. The determining unit 116 may then select at least one of the sensors in the monitored system 120 (e.g., the sensor with the highest contribution) as the subject sensor based on the calculated contribution.

On the other hand, as mentioned above, the basic state index value may not sufficiently represent a gradual change in the state of the monitored system 120 while indicating the state of the monitored system 120 at a particular point in time. For example, it may be difficult for a user to recognize incremental changes such as aging of devices in a building solely based on basic state index values. In view of this, the calculating unit 114 may additionally calculate the operating state index value as follows.

The calculation unit 114 repeats the calculation of the similarity and the calculation of the basic state index values for each of a plurality of time points within a specific monitoring time period (for example, a time period of the length of u) Value can be obtained. Then, the calculating unit 114 may calculate the operating state index value from the acquired basic state index values.

For example, the calculation unit 114 may calculate a weighted average of the plurality of basic point of view basic state index values as the operation state index value. Further, the calculating unit 114 may give a specific weight to the weighted average if two or more of the following conditions are satisfied.

Assume that the P data sets Y i constructed in the database 140 are within a certain range in the N dimension. If the occurrence frequency of the event that the data set X goes out of the range over time in the monitoring time interval exceeds a certain value (for example, P a%), it is not a temporary defect in the monitored system 120 There is a high possibility that the operation of the monitoring target system 120 has been changed or aged. Where a may be chosen to minimize RSS (Residual Sum of Squares) using an n-fold cross validation technique.

- the number of days in which the occurrence frequency of events in which the data set X is out of the range mentioned above exceeds a certain value (for example, b% b) over time in the monitoring period (for example, u is 14 days) If the number is smaller than u (e.g., 9 days) that is smaller than u, it is likely that the operation of the monitored system 120 has undergone a change or deterioration. Here, u, v, and b may be selected to minimize RSS using an n-fold cross validation technique.

- If the number of days in which the data set X that is statistically unlikely to occur over time in the monitoring period (for example, u is 14 days) has occurred even once, It is highly likely that the operation of the monitoring target system 120 has been changed or deteriorated. Where u and w may be selected to minimize RSS using an n-fold cross validation technique.

If two or more of the above conditions are satisfied, the operational state indicator value may be calculated as a weighted average of the basic state indicator values at a plurality of time points, with a weight p (where 0 <p <1). Here, p can be chosen to minimize RSS using an n-fold cross validation technique. For example, if the above weighted average is 0.9 and p is 0.5 and two or more of the above conditions are satisfied, then the final operating state indicator value can be calculated as 0.9 * 0.5 = 0.45 (i.e., 45%).

Meanwhile, as mentioned above, the operating environment 100 may include a plurality of monitored systems 120, and each monitored system 120 may be a subsystem included in the parent system. In this case, the calculating unit 114 may calculate the similarity and calculate the basic state index values for each of the plurality of subsystems (i.e., the plurality of monitored systems 120) The state index value can be obtained. Further, the calculating unit 114 may calculate an indicator associated with the state of the host system (hereinafter also referred to as "higher indicator"). For example, the calculation unit 114 may calculate a basic state index value of an upper system (e.g., a normal average or a weighted average of basic state index values for each subsystem) from the acquired basic state index values for each subsystem.

Furthermore, the higher indicator may further include at least one of an operating state indicator value and a lower state indicator value (e.g., a minimum state indicator value) of the host system. For example, the calculating unit 114 may calculate the operation state index value of the parent system similar to the operation of calculating the operation state index value of the monitored system 120. [ The calculating unit 114 may calculate the lower state index value as a minimum value among the plurality of basic state indexes for each subsystem. On the other hand, the determination unit 116 may select at least one subsystem to be checked (e.g., a subsystem having a substatus index value as a basic status index value).

The interface unit 118 may provide a user interface to the user device 160. Hereinafter, the operation of the interface unit 118 will be described with reference to FIG.

For example, the interface unit 118 may provide a graphical user interface 500 that includes a graphical representation 510 of an indicator associated with the status of a parent system (e.g., a building control system named " To the same user device 160.

The interface unit 118 may also receive user input (e.g., mouse clicks). The interface unit 118 receives user input for detailed monitoring and, in response to receipt of such user input, communicates with the subsystems (e.g., the "air conditioner 1" device and the "cooling tower" device, (E.g., a basic state index value) associated with each or all of the states of all or a portion of the graphical user interface 500. For example, when the interface 118 receives a user input for selecting a graphical representation 510 in the graphical user interface 500, the interface 118 may provide a graphical representation 520 and / or a graphical representation 525 And visually exposed to the graphical user interface 500. The graphical representation 520 and the graphical representation 525 may each represent a basic state index value of the "air conditioner 1" device and a basic state index value of the "cooling tower" device. Furthermore, the interface unit 118 may represent at least one of the plurality of subsystems (e.g., an "air conditioner 1" device having a minimum state index value as a basic state index value) in a format highlighted in the graphical user interface 500. 5, the connecting line 545 of the graphical representation 510 and the graphical representation 525 may be thicker than the connecting line 540 of the graphical representation 510 and the graphical representation 520, , The graphical representation 525 may be larger in size and / or the thickness of the border than the graphical representation 520. [

Similarly, the interface unit 118 may represent the sensor value of each of the sensors included in each subsystem in the graphical user interface 500. For example, the interface unit 118 may represent such sensor values in the graphical user interface 500 by expressing the indicators associated with the status of the subsystem in the graphical user interface 500 (graphical representations 530, 532 , 533, 535, 537, 539). In addition, the interface unit 118 may represent the above-mentioned inspection object sensor (for example, the air supply temperature sensor and the mixed temperature sensor of the "air conditioner 1" apparatus) in a format emphasized in the user interface. For example, as shown in FIG. 5, the connection lines 553 and 555 may be thicker than the connection lines 550, 552, 557, and 559, and the graphical representations 533 and 535 may be graphical representations 530, 532, 537, and 539, the thickness of the rim can be remarkable.

6 illustrates a system monitoring process according to an exemplary embodiment. For example, an exemplary process 600 may be performed by the system monitoring device 110.

After the start operation, the process 600 proceeds to operation S605. In operation S605, data determined as normal data or defect data is collected. For example, as can be seen in the following table, whether the data for the in-building devices is normal data or defective data can be determined by time period. Referring to the table below, it can be seen that the building contains various devices (e.g., devices referred to as "air conditioner 1", "air conditioner 6", "heating heat exchanger 1", etc.).

Figure pat00005

Such normal data or defect data may be stored in a database such as the database 140. For example, the database may maintain a data set (also referred to as an "existing data set") associated with a device referred to as " air conditioner 3 ". For example, existing data sets may include data sets presented in the following table. Referring to the table below, it can be seen that seven sensors are installed in the "air conditioner 3" device, and each existing data set contains seven sensor values measured through seven sensors at a particular point in time.

Figure pat00006

Sensor values of existing data sets may be normalized per sensor. For example, if the mean and standard deviation of the ambient temperature sensor values of the existing data sets are s and t, respectively, the ambient temperature sensor value of the data set presented in Table 2 above can be normalized to (-1.94485 - s) / t have. The normalized sensor value may be limited to a specific interval (e.g., -1.0 to 1.0). In addition, the upper section may be divided into a plurality of sub-sections, and a representative value (e.g., a median value or an average value of the sensor values in the sub-section) may be given to each sub-section.

In operation S610, a new data set (hereinafter also referred to as the "current data set") to be used to determine the current state of the "air conditioner 3" device is collected from the "air conditioner 3" device. For example, the current data set may be given as the data set presented in the following table.

Figure pat00007

The sensor values of the current data set can be normalized per sensor. For example, the ambient temperature sensor value of the data set presented in Table 3 above can be normalized to (-12.9682-s) / t.

In operation S615, the similarity between each of the existing data sets and the current data set is calculated. As noted above, the similarity may be Euclidean distance between two data points. As another example, the similarity may be a Manhattan distance between two data points. Through this calculation of similarity, an existing data set that is most similar to the current data set among the existing data sets can be determined. For convenience of explanation, it is assumed that the existing data set presented in Table 2 is the closest to the current data set presented in Table 3.

In operation S620, it is determined whether the similarity between the current data set and the existing data set most similar to the most similar existing data set effective range is large. If the similarity is greater than or equal to the effective range, it is determined that the current data set represents the abnormality symptom state of the "air conditioner 3" device (S625). Further, the history of such a determination may be recorded (e.g., in a database), and the user may be notified of the anomalous state of the anomaly. If the above degree of similarity is smaller than the effective range, it is determined whether the most similar existing data set is defective data (S630). If it is determined that the most similar existing data set is defective data, it is determined that the current data set represents the defective state of the "air conditioner 3" device (S635). The history of such a determination can be recorded (e. G., In a database) and the user can be notified of the defect status. Subsequently, the process 600 continues to operation S645. If it is determined in operation S630 that the most similar existing data set is normal data, the process 600 proceeds to operation S645.

On the other hand, if it is determined that the current data set represents an abnormality symptom state of the "air conditioner 3" device, a sensor that has the greatest influence on such determination can be identified. For this, the contribution of each sensor to the similarity between the most similar existing data set and the current data set can be calculated (S640). The contribution of the Kth sensor among the N sensors can be given by the following equation.

Figure pat00008

Subsequently, the process 600 continues to operation S645.

In operation S645, an indicator associated with the state of the "air conditioner 3" device is calculated. Such an indicator may include a basic status indicator value that is calculated as described above, and may additionally include an operational status indicator value. On the other hand, operations (S610) to (S645) may be repeated for each in-building apparatus, and an index related to the state of the building, which is an upper system, can be calculated. Such an indicator may include a basic status indicator value calculated as described above, and may additionally include an operational status indicator value and / or a minimum status indicator value.

7 illustrates a system monitoring process according to an exemplary embodiment. For example, an exemplary process 700 may be performed by the system monitoring device 110.

After the start operation, the process 700 proceeds to operation S710. In operation S710, a system state indicator (e.g., each subsystem of the monitored system 120 and / or the monitored system 120) associated with the state of the monitored system is obtained. Such a system state indicator includes a basic state indicator value associated with the state of the point of view of the system. In addition, the system state indicator may include an operating state indicator value associated with a time-varying state of the system, a substatus state value associated with a particular state of a particular subsystem of the system, if any, And may further include all of the substatus index values.

According to some embodiments, the system monitoring device 110 (the computing portion 114) may obtain such system state indicators through the same or similar operations as those previously mentioned. For example, when a monitored system includes a plurality of subsystems, a plurality of subsystem-specific system state indicators (each associated with a status of a corresponding one of the subsystems of the monitored system 120) A higher indicator (i. E., A system state indicator of the monitored system 120) may be obtained.

Specifically, the basic state index value may indicate the state the monitored system has at a particular point in time. For example, the calculating unit 114 may obtain the basic state index value for each viewpoint. In addition, the operational state index value may indicate the state of the system over a period of time from the preceding point to the specific point in time. For example, the calculating unit 114 may obtain an operational state index value by using a plurality of viewpoint basic state index values. The basic state index value at each point in time may include a state of the system at a point in time, . Furthermore, the lower state index value may indicate the state of a particular subsystem at a particular point in time. For example, when the monitored system includes a plurality of subsystems (including the specific subsystem mentioned above), the calculating unit 114 may obtain the sub-state index values using the basic state index values for each of the plurality of subsystems The basic state index value for each subsystem may indicate the state of the corresponding one of the plurality of subsystems at the above specific time point. The lower state index value may be a minimum state index value that is a minimum value among the plurality of basic state index values for each subsystem.

In operation S720, the obtained system state index is represented in the user interface. According to some embodiments, the interface 118 of the system monitoring device 110 may be implemented as a graphical representation, such as the graphical representations 200, 800, 900, 1000 shown in Figures 2 and 8-10, May be visually exposed on the user interface. In addition, when the monitored system includes a plurality of subsystems, the interface unit 118 may be configured to display indicators of at least some of the systems and subsystems similar to the user interfaces 300, 500 shown in FIGS. 3 and 5 Can be expressed in a user interface in a tree structure. In particular, as shown in FIG. 5, the interface unit 118 may present in the user interface at least one of the subsystems of the system (e.g., a particular subsystem from which the minimum state indicator value of the system originates) in a highlighted format . For example, in FIG. 5, graphical representations 525, 533, 535 may appear prominently in size and / or border thickness, and connecting lines 545, 553, 555 may be thicker and / . This user interface allows the user to easily recognize the status of the monitored system and to enable effective verification of subsystems that may have been defective.

Then, if another system state indicator is obtained, the process 700 repeats the operations (S710, S720) described above for the new system state indicator.

On the other hand, exemplary embodiments may include a computer-readable storage medium including a program for performing the procedures described herein on a computer. Such computer-readable storage media may include program instructions, local data files, local data structures, etc., alone or in combination. The computer-readable storage medium may be those specially designed and constructed for the present invention. Examples of computer-readable storage media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floppy disks, and ROMs, And hardware devices specifically configured to store and execute the same program instructions. Examples of program instructions may include machine language code such as those generated by a compiler, as well as high-level language code that may be executed by a computer using an interpreter or the like.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, . Therefore, the scope of the present invention should not be limited to the above-described embodiments, but should be determined by equivalents to the appended claims, as well as the appended claims.

110: System monitoring device
112: Data collecting unit
114:
116:
118:
120: Systems to be monitored
140: Database
160: User device

Claims (53)

A data collection unit configured to collect a first data set obtained in the monitored system and determined to indicate the status of the system and a second data set obtained in the system; And
And an output unit configured to calculate an index associated with the status of the system using the first data set and the second data set
System monitoring device.
The method according to claim 1,
Wherein the first data set is determined to indicate that the state of the system at a first time is a steady state or a fault state.
The method according to claim 1,
Wherein the indicator comprises a basic state index value associated with a state of the system at a second point in time.
The method of claim 3,
Wherein the indicator comprises an operational state indicator value associated with a state of the system over a time period from a time preceding the second time point to a second time point.
The method of claim 4,
Wherein the calculating unit is configured to calculate the operational state index value from a plurality of time-based basic state index values, each of the plurality of time-based basic state index values being associated with a state of the system at a time point within the time period, Monitoring device.
The method of claim 3,
Wherein the system comprises a plurality of subsystems, and wherein the indicator comprises a substatus index value associated with a status of one of the plurality of subsystems at the second time point.
The method of claim 6,
Wherein the calculating unit is configured to calculate the lower state index value from a plurality of subsystem-based base state index values, and each of the plurality of base system-specific base state index values is configured to calculate one of the plurality of subsystems at the second time point System monitoring device.
The method of claim 6,
Wherein the lower status indicator value is a minimum value among the plurality of subsystem-specific basic status indicator values.
The method according to claim 1,
Further comprising an interface configured to present the indicator to a user interface.
The method of claim 9,
Wherein the system further comprises a plurality of subsystems and wherein the calculating unit is further configured to calculate an index for each of the plurality of subsystems in response to receiving the user input, Wherein each of the plurality of subsystem-specific indicators is associated with a status of a corresponding one of the plurality of subsystems.
The method of claim 10,
Wherein the interface is further configured to render at least one of the plurality of subsystems in a highlighted format.
The method of claim 2,
Wherein the calculating unit is further configured to calculate a degree of similarity between the first data set and the second data set,
Wherein the system monitoring device is configured to determine, based on the threshold associated with the first data set and the similarity, whether the second data set represents an anomalous state of the system, the steady state, or the defective state Further comprising a system monitoring device.
The method of claim 12,
And wherein the calculating unit is further configured to calculate the indicator from the similarity.
The method of claim 12,
Wherein the first data set includes a plurality of first sensor values measured through a plurality of sensors installed in association with the system and the second data set includes a plurality of second sensor values measured through the plurality of sensors System monitoring device.
15. The method of claim 14,
Wherein the calculating unit is further configured to calculate a contribution of each of the plurality of sensors to the similarity if it is determined that the second set of data represents the defect state or the abnormal symptom state.
16. The method of claim 15,
Wherein the determination unit is further configured to select one of the plurality of sensors as a sensor to be inspected based on the calculated contribution.
The method of claim 12,
Wherein the similarity indicates a distance between the first data set and the second data set according to a predetermined distance metric.
18. The method of claim 17,
The second data set is determined to represent the steady state if the distance is less than the threshold and the first data set is determined to represent the steady state and the distance is less than the threshold and the first data set The second data set is determined to indicate the fault state when it is determined that the fault condition is indicated, and the second data set is determined to indicate the abnormality symptom condition if the distance is greater than the threshold value.
18. The method of claim 17,
Wherein the calculating unit is further configured to calculate a basic state index value associated with a state of the system at a second time point from the distance, wherein the basic state index value is calculated based on the distance Wherein the basic state index value is calculated based on an increasing function for the distance when it is determined that the first data set represents the fault state.
A system monitoring method implemented by a computing device,
Collecting a first data set obtained in the monitored system and determined to indicate the status of the system and a second data set obtained in the system; And
Using the first data set and the second data set to calculate an indicator associated with the state of the system
How to monitor the system.
The method of claim 20,
Wherein the first data set is determined to indicate that the state of the system at a first time is a steady state or a fault state.
The method of claim 20,
Wherein the indicator comprises a basic state index value associated with the state of the system at a second point in time.
23. The method of claim 22,
Wherein the indicator comprises an operational state indicator value associated with a state of the system over a time period from a time preceding the second time point to a second time point.
24. The method of claim 23,
Wherein the calculating step includes calculating the operating state index value from a plurality of viewpoint-based basic state index values, wherein each of the plurality of viewpoint-based basic state index values indicates a state of the system at a point within the time period Wherein the system monitoring method comprises:
23. The method of claim 22,
Wherein the system comprises a plurality of subsystems, and wherein the indicator comprises a substatus index value associated with a status of one of the plurality of subsystems at the second time point.
26. The method of claim 25,
Wherein the calculating step includes calculating the lower state index value from a plurality of basic system state index values for each subsystem, wherein each of the plurality of base state index values for each of the plurality of subsystems includes a plurality of sub- A method of monitoring a system, the method being associated with a state of one of the systems.
26. The method of claim 25,
Wherein the lower status indicator value is a minimum one of the plurality of basic status indicator values for each of the plurality of subsystems.
The method of claim 20,
And presenting the indicator to a user interface.
29. The method of claim 28,
The system includes a plurality of subsystems,
Calculating an index for each of the plurality of subsystems; And
Further comprising presenting at least a portion of the plurality of subsystem-specific indicators in the user interface in response to receiving user input, wherein each of the plurality of subsystem-specific indicators is associated with a corresponding one of the plurality of subsystems The method comprising:
29. The method of claim 29,
Further comprising presenting at least one of the plurality of subsystems in an emphasized format.
23. The method of claim 21,
Calculating a degree of similarity between the first data set and the second data set; And
Further comprising determining based on the threshold and the similarity associated with the first data set whether the second data set represents an anomalous state of the system, the steady state, or the fault state.
32. The method of claim 31,
And calculating said indicator from said degree of similarity.
32. The method of claim 31,
Wherein the first data set includes a plurality of first sensor values measured through a plurality of sensors installed in association with the system and the second data set includes a plurality of second sensor values measured through the plurality of sensors And a method for monitoring the system.
34. The method of claim 33,
Further comprising calculating the contribution of each of the plurality of sensors to the similarity if it is determined that the second set of data represents the defect state or the abnormal symptom state.
35. The method of claim 34,
And selecting one of the plurality of sensors as a sensor to be inspected based on the calculated contribution.
32. The method of claim 31,
Wherein the similarity indicates a distance between the first data set and the second data set according to a predetermined distance metric.
37. The method of claim 36,
The second data set is determined to represent the steady state if the distance is less than the threshold and the first data set is determined to represent the steady state and the distance is less than the threshold and the first data set The second data set is determined to indicate the fault state when it is determined to indicate the fault condition and the second data set is determined to indicate the abnormal symptom condition if the distance is greater than the threshold value.
37. The method of claim 36,
Further comprising calculating from the distance a basic state index value associated with a state of the system at a second time point, wherein the basic state index value is calculated based on the distance to the first state when the first data set is determined to represent the steady state Wherein the basic state index value is calculated based on an increasing function for the distance when it is determined that the first data set represents the fault state.
Further comprising at least one of an operating state indicator value associated with a time period state of the system and a bottom state indicator value associated with a point-in-time state of a particular subsystem of the system, A calculating unit configured to obtain a system state index including; And
And an interface unit configured to display the system status indicator in a user interface.
42. The method of claim 39,
Wherein the basic state index value indicates a state of the system at a specific point in time, the operational state index value indicates a state of the system over a time period from a point preceding the specific point in time to the point in time, Value indicates the status of the particular subsystem at the particular time.
42. The method of claim 39,
Wherein the calculating unit is configured to obtain the operational state index value using a plurality of time-based basic state index values, and each of the plurality of time-based basic state index values is associated with a state of the system at a time point within the time period , System monitoring device.
42. The method of claim 39,
Wherein the calculating unit is configured to obtain the substatus indicator value using a plurality of subsystem-specific basic status indicator values, the system comprising a plurality of subsystems, the plurality of subsystems comprising the specific subsystem Wherein each of the plurality of subsystem-specific basic status indicator values is associated with a status of one of the plurality of subsystems at the specific time.
43. The method of claim 42,
Wherein the lower status indicator value is a minimum value among the plurality of subsystem-specific basic status indicator values.
42. The method of claim 39,
Wherein the system comprises a plurality of subsystems, wherein the plurality of subsystems comprises the specific subsystem, and wherein the calculator is further configured to obtain a plurality of subsystem-specific system status indicators, wherein the plurality of subsystem- Wherein each of the status indicators is associated with a status of a corresponding one of the plurality of subsystems, and wherein the interface is further configured to present at least a portion of the plurality of subsystem-specific system status indicators to the user interface.
45. The method of claim 44,
Wherein the interface is further configured to render at least one of the plurality of subsystems in a highlighted format on the user interface.
Further comprising at least one of an operating state indicator value associated with a time period state of the system and a bottom state indicator value associated with a point-in-time state of a particular subsystem of the system, Obtaining a system state indicator including; And
And presenting the system state indicator to a user interface.
47. The method of claim 46,
Wherein the basic state index value indicates a state of the system at a specific point in time, the operational state index value indicates a state of the system over a time period from a point preceding the specific point in time to the point in time, Value represents the status of the particular subsystem at the particular point in time.
47. The method of claim 46,
Wherein the acquiring includes acquiring the operational state index value using a plurality of time-based basic state index values, wherein each of the plurality of time- The method comprising:
47. The method of claim 46,
Wherein the acquiring includes obtaining the substatus indicator value using a plurality of subsystem-specific basic status indicator values, the system comprising a plurality of subsystems, Wherein each of the plurality of subsystem-specific basic status indicator values is associated with a status of one of the plurality of subsystems at the specific time.
55. The method of claim 49,
Wherein the lower status indicator value is a minimum one of the plurality of basic status indicator values for each of the plurality of subsystems.
47. The method of claim 46,
Wherein the system comprises a plurality of subsystems, wherein the plurality of subsystems comprises the specific subsystem, and wherein the system monitoring method further comprises obtaining a plurality of subsystem-specific system status indicators, Wherein each of the subsystem-specific system status indicators is associated with a status of a corresponding one of the plurality of subsystems, and wherein the system monitoring method comprises: representing at least a portion of the plurality of subsystem-specific system status indicators in the user interface &Lt; / RTI &gt;
54. The method of claim 51,
And presenting at least one of the plurality of subsystems in a highlighted format to the user interface.
A computer-readable storage medium having computer-executable instructions for performing the method recited in any one of claims 20 to 38 and 46 to 52 when executed by a processor.
KR1020140133525A 2014-05-30 2014-10-02 Apparatus and method for system monitoring KR20150137950A (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/KR2014/010250 WO2015182831A1 (en) 2014-05-30 2014-10-29 Apparatus and method for monitoring system
CN201510063712.2A CN105278494A (en) 2014-05-30 2015-02-06 System monitoring apparatus and method
US14/616,131 US20150347213A1 (en) 2014-05-30 2015-02-06 Apparatus and method for system monitoring

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR20140066494 2014-05-30
KR1020140066494 2014-05-30

Publications (1)

Publication Number Publication Date
KR20150137950A true KR20150137950A (en) 2015-12-09

Family

ID=54873815

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020140133525A KR20150137950A (en) 2014-05-30 2014-10-02 Apparatus and method for system monitoring

Country Status (2)

Country Link
KR (1) KR20150137950A (en)
CN (1) CN105278494A (en)

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6834256B2 (en) * 2002-08-30 2004-12-21 General Electric Company Method and system for determining motor reliability
US8731724B2 (en) * 2009-06-22 2014-05-20 Johnson Controls Technology Company Automated fault detection and diagnostics in a building management system
JP5284433B2 (en) * 2011-09-14 2013-09-11 株式会社東芝 Process monitoring / diagnosis / support equipment

Also Published As

Publication number Publication date
CN105278494A (en) 2016-01-27

Similar Documents

Publication Publication Date Title
KR102011620B1 (en) Importance determination device of abnormal data and importance determination method of abnormal data
JP6394726B2 (en) Operation management apparatus, operation management method, and program
US20160033946A1 (en) Building management system analysis
US20160378583A1 (en) Management computer and method for evaluating performance threshold value
US20090216393A1 (en) Data-driven anomaly detection to anticipate flight deck effects
RU2601669C2 (en) Turbojet engine measuring circuit monitoring system
CN108268689B (en) Method for diagnosing and evaluating state of heating element and application thereof
JP6521096B2 (en) Display method, display device, and program
JP6304767B2 (en) SENSOR MONITORING DEVICE, SENSOR MONITORING METHOD, AND SENSOR MONITORING PROGRAM
CN103502951B (en) Operation management system, operation management method and program thereof
JP6482743B1 (en) Risk assessment device, risk assessment system, risk assessment method, and risk assessment program
US20180234746A1 (en) Maintenance device, presentation system, and program
JP2016128973A (en) Sign diagnosis system and sign diagnosis method
CN112199258A (en) Method and device for monitoring magnetic disk, electronic equipment and medium
US20190265088A1 (en) System analysis method, system analysis apparatus, and program
JP5771317B1 (en) Abnormality diagnosis apparatus and abnormality diagnosis method
US20190369165A1 (en) Management device, management method, and non-transitory storage medium
JP6574533B2 (en) Risk assessment device, risk assessment system, risk assessment method, and risk assessment program
JP5918661B2 (en) Equipment diagnostic device and setting change reminding method
JP6875199B2 (en) Equipment diagnostic system
KR20150137950A (en) Apparatus and method for system monitoring
US20150347213A1 (en) Apparatus and method for system monitoring
JP7347953B2 (en) Equipment early warning monitoring device and equipment early warning monitoring method
JP5771318B1 (en) Abnormality diagnosis apparatus and abnormality diagnosis method
JP7170564B2 (en) Motor deterioration trend monitoring system

Legal Events

Date Code Title Description
WITN Withdrawal due to no request for examination