CN112912807A - Abnormal diagnosis device - Google Patents
Abnormal diagnosis device Download PDFInfo
- Publication number
- CN112912807A CN112912807A CN201980067454.1A CN201980067454A CN112912807A CN 112912807 A CN112912807 A CN 112912807A CN 201980067454 A CN201980067454 A CN 201980067454A CN 112912807 A CN112912807 A CN 112912807A
- Authority
- CN
- China
- Prior art keywords
- abnormality
- data
- degree
- reference point
- operation data
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 17
- 230000002159 abnormal effect Effects 0.000 title description 16
- 230000005856 abnormality Effects 0.000 claims abstract description 116
- 238000004364 calculation method Methods 0.000 claims abstract description 29
- 238000005259 measurement Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 description 12
- 238000012360 testing method Methods 0.000 description 7
- 238000007796 conventional method Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000005484 gravity Effects 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000002547 anomalous effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 229910003460 diamond Inorganic materials 0.000 description 1
- 239000010432 diamond Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
在此前的异常诊断装置中，即使在数据没有大幅变化的情况下也存在用于确定异常原因的异常贡献度大幅变化的情况。异常诊断装置具备数据分类部，该数据分类部具有：类别计算部，其将从诊断对象所具备的多个传感器输出的运行数据分类为多个类别；基准点计算部，其计算多个类别的基准点；以及异常度计算部，其将基准点与当前的运行数据进行比较，计算当前的运行数据的异常度，基准点是多个类别中的2个以上的类别的加权平均。
In the conventional abnormality diagnosing apparatus, even when the data does not change greatly, the abnormality contribution degree for specifying the cause of the abnormality may change greatly. The abnormality diagnosis apparatus includes a data classification unit including: a class calculation unit that classifies operation data output from a plurality of sensors included in a diagnosis target into a plurality of classes; and a reference point calculation unit that calculates the data of the plurality of classes a reference point; and an abnormality degree calculation unit that compares the reference point with the current operating data, and calculates the abnormality degree of the current operating data, where the reference point is a weighted average of two or more categories among the plurality of categories.
Description
Technical Field
The present invention relates to an abnormality diagnosis device for a plant or apparatus.
Background
A power generation plant or a related device is provided with a plurality of sensors such as a thermometer, a pressure gauge, and a flow meter for the purpose of monitoring and control. In recent years, sensors such as acceleration sensors are also installed in infrastructure equipment such as bridges and roads, and the state of the equipment is monitored.
Such sensor data is characterized by the existence of a plurality of related sensor data, which are multidimensional time series data measured at a certain time period. Various methods have been proposed as a state monitoring method using such multidimensional time-series data.
For example, patent document 1 discloses a plant abnormality diagnosis apparatus as a technique using an adaptive resonance theory, the apparatus including: the plant abnormality diagnosis apparatus includes an abnormality degree calculation unit that obtains an abnormality degree of the entire plant to be diagnosed, based on a difference in spatial distance between data belonging to a category determined by using normal data by an adaptive resonance theory and a plurality of measurement data from various sensors provided in the plant to be diagnosed.
Here, the Adaptive Resonance Theory (ART) is a method of classifying multidimensional data into a plurality of categories according to the degree of similarity, and is described in, for example, non-patent document 1. By clustering and dividing multidimensional data into categories using ART, abnormalities can be detected.
Documents of the prior art
Patent document
Patent document 1: international publication No. 2018/052568
Non-patent document
Non-patent document 1: G.A.Carpenter and S.Grossberg, "ART 2: Self-organization No. fstable organization codes for analog input patterns", Applied Optics, Vol26, No.23,1987
Disclosure of Invention
Problems to be solved by the invention
In patent document 1, as shown in fig. 1, an abnormality of a device is detected based on operation data (diagnostic data) that deviates from a normal category that is classified into normal operation data (learning data). In order to determine the degree of abnormality and which signal has a large deviation, the degree of abnormality and the degree of contribution of abnormality are calculated based on the difference between the data at the time of normal operation and the current measurement data.
Here, the degree of abnormality and the degree of contribution to abnormality in patent document 1 will be described with reference to the drawings.
As shown in fig. 2, when an abnormality is detected, the distance from the current data k to the center of gravity of the nearest normal category (category 3 in the example of fig. 2) is defined as the degree of abnormality. The degree of abnormality indicates the degree of abnormality of the data.
As shown in fig. 3, a value obtained by decomposing the abnormality degree vector into components of the respective measurement values (x 1 and x2 in the example of fig. 3) is defined as the abnormality contribution degree. The degree of anomalous contribution indicates which signal deviates more from normal.
However, when the abnormality degree and the abnormality contribution degree described in patent document 1 are used, the abnormality contribution degree may be greatly changed although the measurement data in the abnormality does not greatly change. This example will be described with reference to fig. 4.
Fig. 4 shows a situation where new data m is measured in the vicinity after the data k shown in fig. 2 and 3 is in an abnormal state. The normal class closest to the data k is class 3, but the normal class closest to the data m becomes class 1. As a result, the value of the degree of abnormality of the two data does not change greatly, but the degree of contribution of abnormality changes greatly. That is, the degree of abnormal contribution of x2 is large in data k, while the degree of abnormal contribution of data x1 is large in data m.
As described above, in the method described in patent document 1, although the measurement data itself does not change greatly, the degree of abnormal contribution changes greatly, and the cause of the abnormality may not be estimated based on the degree of abnormal contribution.
Means for solving the problems
In order to solve the above problem, an abnormality diagnostic device according to the present invention includes: the abnormality diagnosis device includes a data classification unit having: a category calculation unit that classifies operation data output from a plurality of sensors included in a diagnostic object into a plurality of categories; a reference point calculation unit that calculates a plurality of types of reference points; and an abnormality degree calculation unit that compares a reference point, which is a weighted average of 2 or more categories among the plurality of categories, with the current operation data and calculates the abnormality degree of the current operation data.
Effects of the invention
The present invention, having the above configuration, does not cause a large change in the degree of contribution of an abnormality to nearby measurement data, and can improve the accuracy of estimating the cause of the abnormality.
Drawings
Fig. 1 shows a conventional method of classifying data.
Fig. 2 shows an example of calculating the degree of abnormality by a conventional method.
Fig. 3 shows an example of calculating the degree of abnormal contribution by a conventional method.
Fig. 4 shows a problem in calculating the abnormal contribution degree by a conventional method.
Fig. 5 shows the structure of an embodiment of the present invention.
Fig. 6 shows an example of the operation data stored in the operation data database.
Fig. 7 shows an example of the configuration of the data sorting unit according to the embodiment of the present invention.
Fig. 8 shows a method for calculating the degree of abnormality according to the present invention.
Fig. 9 shows an example of a trend graph of the classified categories.
Fig. 10 shows an example of a trend graph of the degree of abnormality and the degree of contribution of abnormality.
Fig. 11 shows test data.
Fig. 12 shows an example of calculating the degree of abnormality by a conventional method using test data.
Fig. 13 shows an example of calculating the degree of abnormal contribution by a conventional method using test data.
Fig. 14 shows an example of calculating the degree of abnormality by the method of the present invention using test data.
Fig. 15 shows an example of calculating the degree of abnormal contribution by the method of the present invention using test data.
Detailed Description
Hereinafter, embodiments of the present invention will be described with reference to the drawings. The following are merely examples, and do not limit the invention itself to the specific details described below.
Fig. 5 shows a structure of an embodiment of the present invention. The present embodiment is an example in which the diagnostic apparatus of the present invention is used for abnormality diagnosis of a plant, and includes a plant 10, an operation data database 20, a data classification unit 30, a classification result database 40, and a display operation unit 50. Hereinafter, the outline of each component will be described. The target of the abnormality diagnosis is not limited to the plant, and may be applied to other apparatuses.
The plant 10 is provided with sensors for controlling and monitoring the plant. Examples of the sensor include, but are not limited to, a flow meter, a thermometer, and a pressure gauge.
The operation data database 20 stores the operation data of the plant measured by the sensors of the plant 10, for example, as time-series data every 1 minute. Among the stored operation data, the operation data designated as the normal data by the display operation unit 50 is extracted as the learning data and sent to the data classification unit 30. In addition, after the data measured in real time in the plant 10 is temporarily stored in the operation data database 20, the data is transmitted to the data classification unit 30 as diagnostic data at a fixed cycle.
The data classification unit 30 classifies multidimensional operating data into a plurality of categories using an ART-based clustering algorithm (hereinafter referred to as "improved ART").
ART will be described here. In the ART, input data is classified into a plurality of categories (clusters), and each input data is assigned a category number after classification. The category is an aggregation of data having similarity, and input data assigned the same category number indicates high similarity.
In the learning phase, operation data (learning data) in which the apparatus is in a normal state is input to the ART. The ART classifies the operational data (learning data) into a plurality of categories according to the similarity of the data, and thus specifies a category (normal category) generated when the operational data is normal.
In the diagnosis stage, operational data to be diagnosed (diagnostic data) is input to the ART that learned the normal data. As a result, data having a high degree of similarity to the learning data is classified into the same category as the learning phase. However, when the tendency of data changes, such as when some abnormality occurs in the device, the data is classified into a category (new category) different from the learning data.
The data classification device 30 using the improved ART of the present embodiment outputs the classification number, the abnormality degree, and the abnormality contribution degree of each measurement data, which are obtained by classifying the input multidimensional data, as the data classification result.
The classification result database 40 manages the class number, the degree of abnormality, and the degree of contribution of abnormality output from the data classification unit 30. Further, weight coefficients serving as selection criteria for each category and gravity center data of data classified into each category are stored.
The display operation unit 50 sets conditions of the learning data and the diagnostic data. It is determined whether the operation data measured by the sensors of the plant 10 is the learning data or the diagnostic data based on the condition. The display operation unit 50 displays a trend graph of the category number, the degree of abnormality, and the degree of contribution to abnormality. The display operation unit 50 may be configured such that the display unit is separated from the operation unit.
Next, the method of diagnosing an abnormality according to the present embodiment will be described in detail with reference to fig. 6 to 10.
The plant 10 is composed of equipment, and piping, valves, and the like for connecting the equipment. Sensors such as a flow meter, a thermometer, and a pressure gauge are provided in the equipment and the piping to monitor and control the state of the plant. In these sensors, for example, if a thermometer, a label such as "TIC 001" is attached. The tag is an ID of each sensor, and each sensor is identified by the ID.
The operation data database 20 records data measured by the sensors of the plant 10 as time-series data. Fig. 6 shows an example of the operation data. As shown in fig. 6, as the operation data for each time measured by the sensors provided in the plant 10, the time at which the operation data was measured is recorded in the "time" column, and the values measured by the sensors specified by the IDs such as "FIC 001" and "PIC 001" are recorded in the other columns. This time interval can be arbitrarily specified, but is set to 1 minute in the present embodiment.
The data classification section 30 classifies the operation data using the improved ART. Fig. 7 shows a detailed configuration of the data sorting unit 30. The data classification unit 30 is composed of a category calculation unit 31, a reference value calculation unit 32, an abnormality degree calculation unit 33, and an abnormality contribution degree calculation unit 34.
The category calculation unit 31 classifies the operation data into categories according to the similarity of the operation data. The class into which the operation data (learning data) is classified in the learning stage is set as a normal class. The detailed algorithms classified into categories are described in non-patent document 1 and patent document 1, and therefore, the description thereof is omitted here.
The reference point calculating unit 32 calculates a reference point for calculating the degree of abnormality. The degree of abnormality is calculated based on deviation information between the reference point and the current operation data (diagnostic data).
Use of FIG. 8The method of calculating the degree of abnormality of the present invention will be explained. In the present embodiment, the weighted average g of the barycenter of the normal class is calculated by equation (1)aAs a reference point.
[ numerical formula 1]
Here, gi is the gravity center vector (coordinate) of the normal class j, di (k)Is from giDistance to the current measurement data k. f (x) is a monotonous decreasing function of x, and in the present embodiment, a sigmoid (sigmoid) function of expression (2) is used as an example.
[ numerical formula 2]
According to the formula (2), with the distance di (k)Become larger, f (d)i (k)) And becomes smaller. I.e. the weighted average gaThe coefficient of (d) becomes larger in the normal class close to the measurement data m and smaller in the class far away. In particular, the sigmoid function used in equation (2) is a function whose value gradually approaches zero as x becomes larger, and thus the distance di (k)The large class of coefficients is near zero and does not affect the calculation of the reference point.
That is, the reference point obtained in expression (1) is an average value of the barycentric coordinates of each class that are close to the barycenter of the class of the measurement data.
The abnormality degree calculation unit 33 calculates the abnormality degree of the current measurement data k based on the coordinates of the reference point calculated by the reference point calculation unit 32 and the coordinates of the current measurement data k. The degree of abnormality is defined by the distance between the two, and the vector d of the degree of abnormality in equation (3)a (k)Is the degree of abnormality.
[ numerical formula 3]
The abnormality contribution degree calculation unit 34 calculates the abnormality degree vector d obtained by the abnormality degree calculation unit 33a (k)Is set as xiThe degree of abnormal contribution R of the parameter i is obtained by the following formula (4)i。
[ numerical formula 4]
The classification result database 40 stores the class number, the degree of abnormality, and the degree of contribution to abnormality of each data obtained by the data classification unit 30.
The display operation unit 50 displays the data stored in the classification result database 40 and the operation data stored in the operation data database 20. Fig. 9 shows a trend graph of the classified categories. It is known that the category changes and the state of the plant changes with the time. In the example of fig. 9, the categories 1 to 3 are normal categories, and the category 4 is a new category.
Fig. 10 shows a display example of the abnormality degree and the abnormality contribution degree at the same time as fig. 9. The degree of abnormality is shown by the black line. Since the abnormality contribution degree is obtained by the equation (4), the sum of the abnormality contribution degrees of the parameters becomes the abnormality degree. The example shown in this figure is an example with 2 parameters, parameter x1Degree of abnormal contribution R1And parameter x2Degree of abnormal contribution R2The sum of (a) and (b) is the degree of abnormality. As is clear from a comparison between fig. 9 and fig. 10, the degree of abnormality increases from the time when the category becomes the new category, i.e., category 4.
Next, results of comparing the existing algorithm with the algorithm shown in the present embodiment using test data will be described with reference to fig. 11 to 15.
Fig. 11 shows test data in two dimensions. There are 50 points of learning data, which are classified into 9 categories as a result of classification by ART. The points illustrated by diamond represent the centroids of the classes. There are 31 points of diagnostic data, and data is input in the order from left to right at the time of diagnosis.
Fig. 12 and 13 show results of determining the degree of abnormality and the degree of contribution of abnormality by a conventional algorithm. In the degree of abnormality shown in fig. 12, points that do not change smoothly are at the time of 7 minutes and 21 minutes, but there is no discontinuity, and even in the existing algorithm, there is no big problem in the calculation of the degree of abnormality. On the other hand, in the abnormal contribution degree shown in fig. 13, the abnormal contribution degree of the center of gravity of the closest normal category at the time of 7 minutes discontinuously changes. If the degree of contribution of an abnormality changes so discontinuously due to a change in the nearest normal category, an erroneous determination may occur in which the cause of the abnormality is estimated using the data.
Next, fig. 14 and 15 show the results of the calculation of the degree of abnormality and the degree of contribution to abnormality by the algorithm of the present invention. The tendency of the degree of abnormality is not so changed as compared with the case of using the existing algorithm, but there is no discontinuous change in the graph of the degree of contribution of abnormality.
As described above, by using the abnormality diagnostic device of the present invention, it is possible to eliminate a phenomenon in which the degree of contribution of an abnormality greatly changes despite the approach of measurement data. That is, the accuracy in estimating the cause of an abnormality using the degree of contribution to the abnormality is improved.
In the present embodiment, an example using ART is shown as the data clustering technique, but other clustering techniques may be used. In addition, although the sigmoid function is used as f (x), other functions such as 1/x may be used.
Description of reference numerals
10: complete equipment
20: operational data database
30: data classification unit
31: category calculation unit
32: reference value calculation unit
33: abnormality degree calculation unit
34: abnormal contribution degree calculating part
40: database of classification results
50: a display unit.
Claims (10)
1. An abnormality diagnosis device characterized in that,
the abnormality diagnosis device is provided with a data classification unit,
the data classification unit includes:
a category calculation unit that classifies operation data output from a plurality of sensors included in a diagnostic object into a plurality of categories;
a reference point calculation unit that calculates the reference points of the plurality of categories; and
an abnormality degree calculation unit that compares the reference point with current operation data to calculate an abnormality degree of the current operation data,
the reference point is a weighted average of 2 or more of the plurality of categories.
2. The abnormality diagnostic device according to claim 1,
the abnormality degree calculation unit calculates the abnormality degree of the current operation data based on information on a deviation between the reference point and the current operation data.
3. The abnormality diagnostic device according to claim 1 or 2,
the abnormality degree calculation unit calculates the abnormality degree of the current operation data based on a difference in distance between the reference point and the current operation data.
4. The abnormality diagnostic device according to any one of claims 1 to 3,
the operation data is multidimensional data composed of measurement data respectively output from the plurality of sensors.
5. The abnormality diagnostic device according to claim 4,
the abnormality diagnostic device includes an abnormality contribution degree calculation unit that calculates a component of the abnormality degree in an axial direction of each of the plurality of measurement data as an abnormality contribution degree.
6. The abnormality diagnostic device according to any one of claims 1 to 5,
the abnormality diagnosis device includes an operation data database that outputs operation data, which is obtained when the diagnosis target is normal, among the input operation data, to the data classification unit as learning data,
the category calculation unit classifies a category into which the learning data is classified as a normal category,
the reference point is a weighted average of more than 2 of the normal classes.
7. The abnormality diagnostic device according to any one of claims 1 to 6,
defining a coefficient of a weighted average based on a distance from the current operating data to the reference point.
8. The abnormality diagnostic device according to claim 7,
the larger the distance from the current operation data to the reference point, the smaller the coefficient of the weighted average becomes.
9. The abnormality diagnostic device according to any one of claims 1 to 8,
the abnormality diagnosis device includes a display operation unit that displays the classification result output from the data classification unit.
10. The abnormality diagnostic device according to claim 9,
the classification result includes the number of the class classified by the class calculating section and the degree of abnormality.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2019-045371 | 2019-03-13 | ||
| JP2019045371A JP7233258B2 (en) | 2019-03-13 | 2019-03-13 | Abnormal diagnosis device |
| PCT/JP2019/043475 WO2020183781A1 (en) | 2019-03-13 | 2019-11-06 | Abnormality diagnosis device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112912807A true CN112912807A (en) | 2021-06-04 |
Family
ID=72427429
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201980067454.1A Pending CN112912807A (en) | 2019-03-13 | 2019-11-06 | Abnormal diagnosis device |
Country Status (3)
| Country | Link |
|---|---|
| JP (1) | JP7233258B2 (en) |
| CN (1) | CN112912807A (en) |
| WO (1) | WO2020183781A1 (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI768606B (en) * | 2020-12-18 | 2022-06-21 | 日月光半導體製造股份有限公司 | System and method for monitoring sensor |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070027788A1 (en) * | 2005-07-26 | 2007-02-01 | Cfph, Llc. | System and method for displaying and/or analyzing a limit order book |
| JP2013008111A (en) * | 2011-06-22 | 2013-01-10 | Hitachi Engineering & Services Co Ltd | Abnormality sign diagnostic device and abnormality sign diagnostic method |
| CN107506463A (en) * | 2017-08-30 | 2017-12-22 | 宁波城市职业技术学院 | A kind of data classification and processing method and equipment |
| WO2018051568A1 (en) * | 2016-09-15 | 2018-03-22 | 株式会社日立製作所 | Plant abnormality diagnosis device and plant abnormality diagnosis system |
| US20180275631A1 (en) * | 2017-03-22 | 2018-09-27 | Omron Corporation | Control system, control device, and control method |
| WO2019003703A1 (en) * | 2017-06-28 | 2019-01-03 | 株式会社日立製作所 | Diagnostic device and diagnostic method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05322642A (en) * | 1992-05-22 | 1993-12-07 | Hitachi Ltd | Abnormality diagnosis system for rotating machine |
-
2019
- 2019-03-13 JP JP2019045371A patent/JP7233258B2/en active Active
- 2019-11-06 CN CN201980067454.1A patent/CN112912807A/en active Pending
- 2019-11-06 WO PCT/JP2019/043475 patent/WO2020183781A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070027788A1 (en) * | 2005-07-26 | 2007-02-01 | Cfph, Llc. | System and method for displaying and/or analyzing a limit order book |
| JP2013008111A (en) * | 2011-06-22 | 2013-01-10 | Hitachi Engineering & Services Co Ltd | Abnormality sign diagnostic device and abnormality sign diagnostic method |
| WO2018051568A1 (en) * | 2016-09-15 | 2018-03-22 | 株式会社日立製作所 | Plant abnormality diagnosis device and plant abnormality diagnosis system |
| US20180275631A1 (en) * | 2017-03-22 | 2018-09-27 | Omron Corporation | Control system, control device, and control method |
| CN108628263A (en) * | 2017-03-22 | 2018-10-09 | 欧姆龙株式会社 | Control system, control device, computer readable storage medium and control method |
| WO2019003703A1 (en) * | 2017-06-28 | 2019-01-03 | 株式会社日立製作所 | Diagnostic device and diagnostic method |
| CN107506463A (en) * | 2017-08-30 | 2017-12-22 | 宁波城市职业技术学院 | A kind of data classification and processing method and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| JP7233258B2 (en) | 2023-03-06 |
| WO2020183781A1 (en) | 2020-09-17 |
| JP2020149259A (en) | 2020-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10809153B2 (en) | Detecting apparatus, detection method, and program | |
| EP2905665B1 (en) | Information processing apparatus, diagnosis method, and program | |
| CN105320727B (en) | Method for detecting anomalies in real-time sequences | |
| CA2433941C (en) | Adaptive modeling of changed states in predictive condition monitoring | |
| WO2014115615A1 (en) | Method for diagnosing abnormality, and apparatus for same | |
| CN110515351A (en) | Anomaly detector | |
| US20020128731A1 (en) | Global state change indicator for empirical modeling in condition based monitoring | |
| CN109641602A (en) | Abnormality detecting apparatus, method for detecting abnormality and non-transitory computer-readable medium | |
| CN107710089B (en) | Plant equipment diagnosis device and plant equipment diagnosis method | |
| US10976731B2 (en) | Abnormality diagnostic system | |
| US20180052726A1 (en) | Information processing device, information processing method, and recording medium | |
| JP6674033B2 (en) | Plant abnormality diagnosis device and plant abnormality diagnosis system | |
| JP7239354B2 (en) | data classifier | |
| JP2022035686A (en) | Diagnostic device and parameter adjustment method | |
| JP2018151821A (en) | Abnormality diagnosis system of facility apparatus | |
| KR20200010671A (en) | System and method for fault diagnosis of equipment based on machine learning | |
| CN115698881A (en) | Device for determining cause of abnormal modulation, method for determining cause of abnormal modulation, and program for determining cause of abnormal modulation | |
| CN112912807A (en) | Abnormal diagnosis device | |
| CN118551330B (en) | Cryogenic hydrogen storage tank fault diagnosis system based on machine learning | |
| JP2019113970A (en) | State diagnostic method of process and state diagnostic device of process | |
| JP6686947B2 (en) | Blast furnace state determination device and blast furnace operating method | |
| JP6953812B2 (en) | Anomaly detection device and anomaly detection system | |
| KR20230075826A (en) | Deep-learning based fault detection apparatus and method for motor | |
| WO2019092997A1 (en) | Data classification device | |
| JP2020177542A (en) | State change detection device and state change detection program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210604 |
|
| WD01 | Invention patent application deemed withdrawn after publication |