KR101724444B1 - Apparatus and method for diagnosing object being diagnosed - Google Patents

Apparatus and method for diagnosing object being diagnosed Download PDF

Info

Publication number
KR101724444B1
KR101724444B1 KR1020160010504A KR20160010504A KR101724444B1 KR 101724444 B1 KR101724444 B1 KR 101724444B1 KR 1020160010504 A KR1020160010504 A KR 1020160010504A KR 20160010504 A KR20160010504 A KR 20160010504A KR 101724444 B1 KR101724444 B1 KR 101724444B1
Authority
KR
South Korea
Prior art keywords
mahalanobis distance
data
dimension
calculating
reference data
Prior art date
Application number
KR1020160010504A
Other languages
Korean (ko)
Inventor
이인
한성호
Original Assignee
삼성중공업(주)
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 삼성중공업(주) filed Critical 삼성중공업(주)
Priority to KR1020160010504A priority Critical patent/KR101724444B1/en
Application granted granted Critical
Publication of KR101724444B1 publication Critical patent/KR101724444B1/en

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M99/00—Subject matter not provided for in other groups of this subclass
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M1/00—Testing static or dynamic balance of machines or structures
    • G01M1/14—Determining imbalance
    • G01M1/16—Determining imbalance by oscillating or rotating the body to be tested
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions

Landscapes

  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)

Abstract

The present invention relates to an apparatus and a method of diagnosing an object to be diagnosed. According to one embodiment of the present invention, the apparatus for diagnosing an object to be diagnosed comprises: a dimension unit determining a dimension of data to calculate a Mahalanobis distance in accordance with a number of base data used as a base to diagnose an object to be diagnosed; a Mahalanobis distance calculation unit calculating the Mahalanobis distance regarding data of the determined dimension among input data collected from the object to be diagnosed; and a status determination unit determining a state of the object to be diagnosed in accordance with the calculated Mahalanobis distance.

Description

[0001] APPARATUS AND METHOD FOR DIAGNOSING OBJECT BEING DIAGNOSED [0002]

The present invention relates to an apparatus and a method for diagnosing pineal body.

The Mahalanobis distance, which refers to the distance between the two points represented by the multivariate correlations, is the multidimensional spatial distance used for cluster analysis. It is the distance between the two points, as well as the standard deviation and correlation coefficient Are considered together.

The Mahalanobis distance can be used to detect the status of the device and determine whether the device is operating normally or abnormally. In order to diagnose the device using the Mahalanobis distance, prior information about the device to be diagnosed is required.

Such prior information is used as reference data for diagnosing the apparatus. In order to calculate the Mahalanobis distance of the n-dimensional input data collected from the apparatus, the inverse matrix of the covariance matrix should be obtained based on the n-dimensional reference data From at least n reference data, at least n 2 reference data are required.

Therefore, as the dimension of the data increases in the calculation of the Mahalanobis distance, the number of reference data required in advance increases sharply. In this case, the time required to acquire the reference data for diagnosing the apparatus becomes longer, It is difficult to increase the level of the device more than a predetermined level, thereby limiting the reliability of the diagnosis of the device.

The embodiment of the present invention is an apparatus for diagnosing a device using a Mahalanobis distance by calculating the Mahalanobis distance by adjusting the number of dimensions of data even if the reference data is not sufficiently secured, And a method thereof.

The embodiments of the present invention adaptively determine the number of dimensions of data used for calculation of the Mahalanobis distance according to the number of reference data secured for device diagnosis, And an object of the present invention is to provide a pediatric group diagnostic apparatus and method capable of improving the reliability of diagnosis.

The apparatus for diagnosing a pituitary organ according to an embodiment of the present invention includes a dimension determining unit for determining a dimension of data for calculating a marathon novice distance according to the number of reference data used as a criterion for diagnosing a pitavirus group; A Mahalanobis distance calculating unit for calculating the Mahalanobis distance with respect to the data of the determined dimension among the input data collected from the pit assembly; And a state determination unit for determining the state of the pincers in accordance with the Mahalanobis distance calculated.

The pivotal unit may include a rotating body that rotates about an axis.

The dimension determining unit may determine a maximum natural number less than or equal to the square root of the number of reference data as the dimension of the data for calculating the Mahalanobis distance when two or more reference data are provided.

Wherein the Mahalanobis distance calculating unit selects a component of the determined dimension according to a predetermined priority among a plurality of different components constituting the reference data and the input data, Calculate the mean and covariance, and calculate the Mahalanobis distance for the selected component in the input data based on the calculated mean and covariance.

Wherein the state determining unit determines the state of the pincers if the calculated Mahalanobis distance is less than or equal to a preset allowable value, and when the calculated Mahalanobis distance is greater than the allowable value, The state of the group can be determined as an abnormal state.

The dimension determination unit may update the dimension of the data for calculating the Mahalanobis distance when the reference data is added.

According to an embodiment of the present invention, there is provided a method for diagnosing a pimple group, comprising: determining a dimension of data for calculating a Mahalanobis distance according to a number of reference data used as a criterion for diagnosing a pimple group; Calculating the Mahalanobis distance for the data of the determined dimension among the input data collected from the pivotal entity; And determining the state of the pincers in accordance with the Mahalanobis distance calculated.

According to the embodiment of the present invention, the delay of the device diagnosis can be minimized by calculating the Mahalanobis distance by adjusting the number of dimensions of the data even if the reference data is not sufficiently secured when the device is diagnosed using the Mahalanobis distance .

According to the embodiment of the present invention, the number of dimensions of data used in the calculation of the Mahalanobis distance is adaptively determined according to the number of reference data secured for device diagnosis, The reliability of the diagnosis can be improved.

1 is an exemplary block diagram of a pediatric unit diagnostic apparatus according to an embodiment of the present invention.
2 to 6 are exemplary diagrams for explaining a process of determining the dimension of data for calculating the Mahalanobis distance according to the number of reference data in an embodiment of the present invention.
7 is an exemplary flowchart of a pidavirus diagnostic method in accordance with an embodiment of the present invention.
FIG. 8 is an exemplary flowchart illustrating a process of determining a dimension of data according to the number of reference data in an embodiment of the present invention.
9 is an exemplary flowchart illustrating a process of calculating a Mahalanobis distance according to an embodiment of the present invention.
10 is an exemplary flowchart for explaining a process of determining the state of a pit group according to Mahalanobis distance according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings attached hereto.

FIG. 1 is an exemplary block diagram of a pinched-body diagnostic apparatus 10 according to an embodiment of the present invention.

Referring to FIG. 1, the pacemaker diagnostic apparatus 10 may include a dimension determining unit 121, a Mahalanobis distance calculating unit 122, and a state determining unit 123. The dimension determining unit 121, the mahalanobis distance calculating unit 122 and the status determining unit 123 may be configured as a processing unit 120 for processing data. For example, the processing unit 120 may include a processor , A CPU, a controller, and the like.

The processing unit 120 can process the data according to the executed program by loading and executing a program stored in the storage unit 130 that is prepared in advance to diagnose the pid entities 100. The storage unit 130 may be a storage device capable of storing a large amount of data such as an HDD and an SSD, but is not limited thereto and may be a storage device capable of reading a small amount of data such as RAM, ROM, cache, .

The pincidal unit diagnostic apparatus 10 can process data collected from the pincers 100 as a diagnostic target to diagnose whether the pincers 100 are operating normally or abnormally.

According to an embodiment of the present invention, the pintle 100 may include a rotating body rotating about an axis. That is, the diagnosis apparatus 10 can be used to diagnose the rotating body.

For example, the pedometer unit diagnostic apparatus 10 can determine whether a device that is rotating, such as a motor or a pump, is operating normally or abnormally. However, the pedometer unit diagnostic apparatus 10 may be used for diagnosing the operation of various various driving apparatuses other than the rotating body, and the pintle 100 is not limited to the rotating body.

The pincidal unit diagnostic apparatus 10 may include an input unit 110. The input unit 110 receives the data collected from the body 100 and transmits the data to the processing unit 120. According to an exemplary embodiment, the input unit 110 may be an input device such as a keyboard, a mouse, and a touchpad, but may be a communication device that receives data from the pintle 100 according to an embodiment.

For example, the input unit 110 may receive data on the operation of the pincers 100 from a sensor mounted on the pincers 100 or around the pincers 100 by wire or wirelessly.

Data relating to the pincers 100 to which the input unit 110 is input may indicate a physical quantity measured due to the operation of the pincers 100. For example, May be included.

The pincidal unit diagnostic apparatus 10 may include an output unit 140. The output unit 140 is a device for outputting data generated by the processing unit 120 and may include a display device such as an LCD, a PDP or the like for visually displaying data on a screen. However, the output unit 140 may include a voice output device such as a speaker, or a communication device that transmits data to a user's terminal by wire or wireless.

The dimension determining unit 121 may determine the dimension of the data for calculating the Mahalanobis distance according to the number of reference data used as a criterion for diagnosing the pincushion group 100. [ The Mahalanobis distance calculator 122 may calculate the Mahalanobis distance for the data of the determined dimension among the input data collected from the body 100. The state determination unit 123 may determine the state of the body 100 based on the calculated Mahalanobis distance.

2 to 6 are exemplary diagrams for explaining a process of determining the dimension of data for calculating the Mahalanobis distance according to the number of reference data in an embodiment of the present invention.

The dimension determining unit 121 can determine the dimension of the data used to calculate the Mahalanobis distance according to the number of reference data about the pincushion group 100. [ The reference data may be collected before diagnosis is performed and stored in the storage unit 130. However, the reference data may be further secured during diagnosis and stored in the storage unit 130. [

According to an embodiment of the present invention, when more than two reference data are provided, the dimension determining unit 121 may divide a maximum natural number smaller than or equal to the square root of the number of reference data by the data for calculating the Mahalanobis distance As shown in FIG.

Referring to FIG. 2, the pincidal unit diagnostic apparatus 10 has only one reference data. In this case, the parenchyma diagnostic apparatus 10 can not calculate the Mahalanobis distance, The diagnosis can be held until it is secured.

Referring to FIG. 3, the pedometer unit diagnostic apparatus 10 obtains two reference data S 1 and S 2. In this case, the dimension determining unit 121 determines a maximum And the number of dimensions of the data for calculating the Mahalanobis distance can be determined.

3, the number of dimensions of the data used for calculating the Mahalanobis distance is determined to be 1, and the Mahalanobis distance calculator 122 calculates the number of dimensions of the n-dimensional The Mahalanobis distance is calculated for the one-dimensional data a 1 among the components.

Referring to FIG. 4, the pedometer unit diagnostic apparatus 10 obtains three reference data S 1 , S 2 , and S 3. In this case, the dimension determining unit 121 obtains three reference data It can be determined as the number of dimensions of the data for calculating Mahalanobis distance by obtaining 1 as the maximum natural number less than or equal to the square root.

4, the Mahalanobis distance calculator 122 calculates the Mahalanobis distance only for the one-dimensional data a 1 among the n-dimensional components constituting the input data x .

Referring to FIG. 5, the pivotal member diagnostic apparatus 10 has four reference data S 1 , S 2 , S 3 , and S 4 . In this case, the dimension determining unit 121 obtains the square root of 4, which is the number of the reference data, and obtains 2 as the largest natural number smaller than or equal to the reference natural number. Therefore, the number of dimensions of the data for calculating the Mahalanobis distance is determined to be 2 .

Accordingly, in FIG. 5, the Mahalanobis distance calculator 122 calculates the two-dimensional data a 1 ( n) among the n-dimensional components constituting the input data x And Mahalanobis distance for a2.

6, when the m pieces of reference data S 1 to S m are provided, the dimension determining unit 121 determines the dimension of the reference data, which is the largest natural number less than or equal to the square root of the number m of the reference data i can be determined as the dimension of the data for calculating the Mahalanobis distance.

Therefore, even if the nodal input data x is collected from the nodal organization 100 by collecting n different data from the pivotal group 100, the Mahalanobis distance can be calculated only for a 1 to a i .

According to one embodiment of the present invention, the Mahalanobis distance calculator 122 calculates the distance between the reference data S 1 to S m and a plurality of different components a 1 to a n constituting the input data x, The components a 1 to a i of the determined dimension i can be selected according to the above-described method.

In Figs. 3 to 5, a 1 is selected first among the n components a 1 to a n , and then a 2 is selected, but the priority for the n components can be set differently. The priorities can be variously set according to the embodiments in order to affect the reliability in the device diagnosis using the Mahalanobis distance.

Then, the Mahalanobis distance calculator 122 calculates an average and a covariance for the selected components a 1 to a i among the reference data S 1 to S m , and calculates an average and a covariance based on the calculated average and covariance, The Mahalanobis distance for the selected components a 1 to a i can be calculated.

The Mahalanobis distance is the ratio of covariance to the degree to which certain data are away from the population mean in a multivariate normal distribution, which can be calculated by the following equation:

Figure 112016009353281-pat00001

Where D 2 is the Mahalanobis distance, x is the input data, m is the mean value, and C is the covariance.

The Mahalanobis distance calculator 122 calculates an average m and a covariance C for the selected components a 1 to a i in the n-dimensional reference data S 1 to S m , and calculates an average m and a covariance C , It is possible to calculate the Mahalanobis distance D 2 for the selected components a 1 to a i from the n-dimensional input data x.

The state determination unit 123 determines the state of the body 100 based on the calculated Mahalanobis distance.

According to one embodiment of the present invention, the state determination unit 123 compares the calculated Mahalanovis distance with a predetermined allowable value, and when the Mahalanovis distance is less than or equal to the allowable value, State to a normal state, and when the Mahalanobis distance is larger than the allowable value, the state of the pincers 100 may be determined to be abnormal.

In addition, according to an embodiment of the present invention, when the reference data is added during the diagnosis of the pincushion group 100, the dimension determining unit 121 updates the dimension of the data for calculating the Mahalanobis distance .

As described above, the reference data S 1 to S m can be further secured during the diagnosis of the pile group 100. In this case, the dimension determination unit 121 may perform the above-described dimension determination process again Once done, you can update the dimension i of the data to calculate the Mahalanobis distance.

As a result, each time the reference data is additionally provided to the pivot diagnosis unit 10, the dimension i of the data may increase, and the embodiment of the present invention may increase the dimension i of the data gradually It is possible to continuously improve the reliability of device diagnosis using the Ranobis distance.

7 is an exemplary flow diagram of a pimple group diagnostic method 20 in accordance with an embodiment of the present invention.

The pincidal unit diagnosis method 20 may be performed by the pinched unit diagnostic apparatus 10 according to the embodiment of the present invention described above.

Referring to FIG. 7, the paired-organ diagnosis method 20 includes the steps of: calculating the Mahalanobis distance based on the number of reference data S 1 to S m used as a criterion for diagnosing the pidavirus group 100; step (S210) for determining a dimension i, step (S220) for calculating the Taj la nobiseu distance to the data a 1 to a i of the determined dimension i wherein from the input data x is collected from the Pidgin group 100, and And determining the state of the pintle 100 according to the calculated Mahalanobis distance (S230).

8 is an exemplary flowchart for explaining a process S210 of determining dimension i of data according to the number m of reference data in an embodiment of the present invention.

Referring to FIG. 8, the step S210 of determining the dimension i of the data is performed when two or more reference data S 1 to S m are provided (YES in S211) And determining the maximum natural number as the dimension i of the data for calculating the Mahalanobis distance (S213).

If the number m of the reference data is one smaller than two, the Mahalanobis distance can not be calculated. Therefore, the diagnosis method 20 can suspend the diagnosis until the reference data is further secured.

FIG. 9 is an exemplary flowchart illustrating a process of calculating Mahalanobis distance (S220) according to an embodiment of the present invention.

Referring to FIG. 9, the step S220 of calculating the Mahalanobis distance includes a step of calculating the Mahalanobis distance using the determined dimension i (i) according to a predetermined priority among a plurality of different components a 1 to a n constituting the reference data and the input data, selecting components a 1 to a i as much as (S221), the reference data S 1 to the selected component in S m a 1 to step (S222), and the calculated mean for calculating the mean and covariance of the a i And calculating a Mahalanobis distance for the selected components a 1 to a i among the input data x based on the covariance (S 223).

FIG. 10 is an exemplary flowchart for explaining a process (S230) of determining the state of a papilla group 100 according to Mahalanobis distance according to an embodiment of the present invention.

Referring to FIG. 10, the step S230 of determining the state of the pincushion 100 according to the Mahalanobis distance is performed when the calculated Mahalanobis distance is smaller than or equal to a preset allowable value (NO in S231) (S232) of determining the state of the pincers (100) as a normal state, and when the calculated Mahalanobis distance is larger than the allowable value (YES in S231), the state of the pincers (100) (Step S233).

According to an embodiment of the present invention, the input data x may be collected from the pile group 100 and continuously input to the pile diagnostic unit 10, x, the Mahalanobis distance is calculated to continuously diagnose the operation of the pincers.

Referring again to FIG. 7, when the reference data is added (YES in S240), the pedometer group diagnostic method 20 repeats the process of determining the dimension i of the data for calculating the Mahalanobis distance (S210) It is possible to update and increase the dimension i of the data.

The pincide-group diagnostic method 20 may be stored in a computer-readable recording medium that is manufactured as a program for execution on a computer. The computer-readable recording medium includes all kinds of storage devices in which data that can be read by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage, and the like. In addition, the pid gang diagnosis method 20 may be embodied as a computer program stored in a medium for execution in combination with the computer.

While the present invention has been described with reference to the exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments. Those skilled in the art will appreciate that various modifications may be made to the embodiments described above. The scope of the present invention is defined only by the interpretation of the appended claims.

10: Pidgin group diagnostic device
100: Pidgin group
110: input unit
120:
121: Dimension determination section
122: Mahalanobis distance calculation unit
123:
130:
140:

Claims (7)

A dimension determining unit that determines a dimension of data for calculating the Mahalanobis distance according to the number of reference data used as a criterion for diagnosing a pidazine group;
A Mahalanobis distance calculating unit for calculating the Mahalanobis distance with respect to the data of the determined dimension among the input data collected from the pit assembly; And
A state determining unit for determining the state of the pincers in accordance with the Mahalanobis distance calculated;
Wherein the pediatric unit diagnostic apparatus comprises: The method according to claim 1,
Wherein the pivotal assembly includes a rotating body rotating about an axis. The method according to claim 1,
Wherein the dimension determination unit comprises:
And determines a maximum natural number smaller than or equal to the square root of the number of reference data as the dimension of data for calculating the Mahalanobis distance, when the reference data is provided more than once. The method according to claim 1,
The Mahalanobis distance calculation unit comprises:
Selecting components of the determined dimension according to a predetermined priority among a plurality of different components constituting the reference data and the input data,
Calculates an average and a covariance of the selected components from the reference data,
And calculates the Mahalanobis distance for the selected component from the input data based on the calculated mean and covariance. The method according to claim 1,
Wherein the status determination unit comprises:
If the calculated Mahalanobis distance is less than or equal to a predetermined allowable value,
And determines the state of the pincers as an abnormal state when the calculated Mahalanobis distance is larger than the allowable value. The method according to claim 1,
Wherein the dimension determination unit comprises:
And updating the dimension of the data for calculating the Mahalanobis distance when the reference data is added. Determining the dimension of the data for calculating the Mahalanobis distance according to the number of reference data used as a criterion for diagnosing the pidazine group;
Calculating the Mahalanobis distance for the data of the determined dimension among the input data collected from the pivotal entity; And
Determining the state of the pincers in accordance with the Mahalanobis distance calculated;
The method comprising the steps of:
KR1020160010504A 2016-01-28 2016-01-28 Apparatus and method for diagnosing object being diagnosed KR101724444B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020160010504A KR101724444B1 (en) 2016-01-28 2016-01-28 Apparatus and method for diagnosing object being diagnosed

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020160010504A KR101724444B1 (en) 2016-01-28 2016-01-28 Apparatus and method for diagnosing object being diagnosed

Publications (1)

Publication Number Publication Date
KR101724444B1 true KR101724444B1 (en) 2017-04-07

Family

ID=58583304

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020160010504A KR101724444B1 (en) 2016-01-28 2016-01-28 Apparatus and method for diagnosing object being diagnosed

Country Status (1)

Country Link
KR (1) KR101724444B1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110108486A (en) * 2018-01-31 2019-08-09 阿里巴巴集团控股有限公司 Bearing fault prediction technique, equipment and system
CN111649886A (en) * 2019-03-04 2020-09-11 三菱重工业株式会社 Abnormality detection device, rotating machine, abnormality detection method, and program
KR20210114463A (en) * 2019-03-28 2021-09-23 미츠비시 파워 가부시키가이샤 Plant monitoring device, plant monitoring method, and program

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000259222A (en) * 1999-03-04 2000-09-22 Hitachi Ltd Device monitoring and preventive maintenance system
JP2009288100A (en) * 2008-05-29 2009-12-10 Mitsubishi Heavy Ind Ltd Soundness diagnosis method and program, and soundness diagnosis apparatus of windmill
JP2011113220A (en) * 2009-11-25 2011-06-09 Mitsubishi Heavy Ind Ltd Component deterioration prediction system for rail traveling vehicle
JP2013113775A (en) * 2011-11-30 2013-06-10 Mitsubishi Electric Corp Elevator abnormality diagnostic device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000259222A (en) * 1999-03-04 2000-09-22 Hitachi Ltd Device monitoring and preventive maintenance system
JP2009288100A (en) * 2008-05-29 2009-12-10 Mitsubishi Heavy Ind Ltd Soundness diagnosis method and program, and soundness diagnosis apparatus of windmill
JP2011113220A (en) * 2009-11-25 2011-06-09 Mitsubishi Heavy Ind Ltd Component deterioration prediction system for rail traveling vehicle
JP2013113775A (en) * 2011-11-30 2013-06-10 Mitsubishi Electric Corp Elevator abnormality diagnostic device

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110108486A (en) * 2018-01-31 2019-08-09 阿里巴巴集团控股有限公司 Bearing fault prediction technique, equipment and system
CN110108486B (en) * 2018-01-31 2022-07-05 阿里巴巴集团控股有限公司 Bearing fault prediction method, device and system
CN111649886A (en) * 2019-03-04 2020-09-11 三菱重工业株式会社 Abnormality detection device, rotating machine, abnormality detection method, and program
CN111649886B (en) * 2019-03-04 2022-05-10 三菱重工业株式会社 Abnormality detection device, rotating machine, abnormality detection method, and computer-readable storage medium
KR20210114463A (en) * 2019-03-28 2021-09-23 미츠비시 파워 가부시키가이샤 Plant monitoring device, plant monitoring method, and program
KR102603020B1 (en) 2019-03-28 2023-11-15 미츠비시 파워 가부시키가이샤 Plant monitoring devices, plant monitoring methods, and programs

Similar Documents

Publication Publication Date Title
KR101724444B1 (en) Apparatus and method for diagnosing object being diagnosed
US8131973B2 (en) Priority determination when dumping files
JP2014514080A5 (en)
US20100311023A1 (en) Systems amd methods for evaluating neurobehavioural performance from reaction time tests
CN112132265B (en) Model training method, cup-disk ratio determining method, device, equipment and storage medium
JP2015116319A (en) Diagnosis support device, diagnosis support method, and diagnosis support program
JP5432287B2 (en) Image system with report function and operation method
JP6208227B2 (en) System and method for generating a biomarker signature
EP3567600B1 (en) Improving a runtime environment for imaging applications on a medical device
US20230095492A1 (en) Methods and systems using fractional rank precision and mean average precision as test-retest reliability measures
CN105874460B (en) Identify method, readable medium and the equipment of at least one base of target sequence
US20160132637A1 (en) Noise model to detect copy number alterations
CN117591408A (en) Software testing method, device and storage medium
KR20170090088A (en) Apparatus and method for diagnosing object being diagnosed
KR102433411B1 (en) Ssvep classification method and bci system using cognitive load
JP6203313B2 (en) Feature selection device, feature selection method, and program
WO2021036305A1 (en) Data processing method, apparatus, device, and storage medium
US9277891B2 (en) Image diagnosis assistance apparatus, processing method thereof, and storage medium
KR102629555B1 (en) Method and apparatus for determining copy number variation profile using read depth correction in whole genome sequencing
TWI683223B (en) Method and device for filtering data
JP2004126857A (en) Default data estimating device and method and default data estimating program and recording medium with its program recorded thereon
US20220308975A1 (en) Evaluating new feature(s) for client device(s) based on performance measure(s)
US20210383905A1 (en) Medical information processing apparatus, medical information processing system, medical information processing method, and storage medium
CN117373665A (en) Digital health management method based on big data and related device
JP2022124540A (en) Model update device and model update method

Legal Events

Date Code Title Description
GRNT Written decision to grant