CN116910499A - System state monitoring method and device, electronic equipment and readable storage medium - Google Patents
System state monitoring method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN116910499A CN116910499A CN202310879815.0A CN202310879815A CN116910499A CN 116910499 A CN116910499 A CN 116910499A CN 202310879815 A CN202310879815 A CN 202310879815A CN 116910499 A CN116910499 A CN 116910499A
- Authority
- CN
- China
- Prior art keywords
- state
- system state
- group
- data
- abnormal
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 114
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000002159 abnormal effect Effects 0.000 claims description 105
- 230000014759 maintenance of location Effects 0.000 claims description 51
- 238000012549 training Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012790 confirmation Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 2
- 238000012806 monitoring device Methods 0.000 abstract description 14
- 230000000694 effects Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 10
- 238000004891 communication Methods 0.000 description 7
- 238000012423 maintenance Methods 0.000 description 7
- 238000011156 evaluation Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000001816 cooling Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000010792 warming Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application discloses a system state monitoring method, which comprises the following steps: data acquisition is carried out on a target system to obtain system data; dividing the system data according to data types to obtain each system data group; for each system data group, identifying the system data group by using a classifier corresponding to the data type, and determining the group state of the system data group; generating a system state using each of the group states; and identifying the system state by using a system state library, and determining a system state monitoring result. By applying the technical scheme provided by the application, the simpler and accurate system state monitoring can be realized, and the normal operation of the system is ensured. The application also discloses a system state monitoring device, electronic equipment and a computer readable storage medium, and the system state monitoring device and the computer readable storage medium have the technical effects.
Description
Technical Field
The present application relates to the field of industrial systems, and in particular, to a system status monitoring method, a system status monitoring device, an electronic device, and a computer readable storage medium.
Background
Industrial system status monitoring is an important guarantee of normal operation of an industrial system, namely, whether the industrial system is in a normal operation state or not is determined by status monitoring of the industrial system. At present, the state monitoring of an industrial system is mostly realized by manually judging or setting alarm monitoring points, but the realization mode has the problem of inaccurate and incomplete monitoring; a multi-state evaluation method is also proposed in the related art, but the problems of high modeling difficulty and high model maintenance cost still exist due to the need of building a system model.
Therefore, how to realize more concise and accurate system state monitoring and ensure the normal operation of the system is a problem to be solved by those skilled in the art.
Disclosure of Invention
The application aims to provide a system state monitoring method which can realize more concise and accurate system state monitoring and ensure the normal operation of a system; another object of the present application is to provide a system status monitoring device, an electronic apparatus, and a computer readable storage medium, which all have the above advantages.
In a first aspect, the present application provides a system status monitoring method, including:
Data acquisition is carried out on a target system to obtain system data;
dividing the system data according to data types to obtain each system data group;
for each system data group, identifying the system data group by using a classifier corresponding to the data type, and determining the group state of the system data group;
generating a system state using each of the group states;
and identifying the system state by using a system state library, and determining a system state monitoring result.
Optionally, the identifying the system data set by using the classifier corresponding to the data type, to obtain a set state of the system data set, includes:
processing the system data set by using a classifier corresponding to the data type to obtain an initial recognition result of the system data set, wherein the initial recognition result comprises probability values of states of various target groups hit by the system data set;
screening all probability values, and reserving a preset number of probability values with the maximum values;
and comparing and analyzing each retention probability value according to a preset recognition rule, and determining the group state of the system data group.
Optionally, when the preset number value is 2, the comparing and analyzing each retention probability value according to a preset recognition rule, to determine a group state of the system data set includes:
When the maximum retention probability value is not lower than a first threshold value and the difference value between the maximum retention probability value and a second retention probability value is lower than a second threshold value, taking a target group state corresponding to the maximum retention probability value and a target group state corresponding to the second retention probability value as group states of the system data group;
when the maximum retention probability value is not lower than a first threshold value and the difference value between the maximum retention probability value and a second retention probability value is not lower than a second threshold value, taking a target group state corresponding to the maximum retention probability value as a group state of the system data group;
and when the maximum retention probability value is lower than a first threshold value, determining that the initial recognition result is an abnormal recognition result.
Optionally, when the initial recognition result is determined to be the abnormal recognition result, the method further includes:
acquiring a manual calibration result of the system data set;
performing optimization training on the classifier corresponding to the system data set by using the manual calibration result to obtain an optimized classifier;
and based on the optimized classifier, returning to the step of identifying the system data set by using the classifier corresponding to the data type and determining the set state of the system data set.
Optionally, the system state library comprises an abnormal system state library and a non-abnormal system state library; the system state is identified by using a system state library, and a system state monitoring result is determined, which comprises the following steps:
determining a best matching non-abnormal state in which the system state hits in the non-abnormal system state library, and determining a first number of the same set of states in the system state and the best matching non-abnormal state;
determining a best matching abnormal state in which the system state hits in the abnormal system state library, and determining a second number of states of the same group in the system state and the best matching abnormal state;
when the first quantity exceeds the second quantity and the first quantity is not lower than a third threshold value, determining that the system state monitoring result is that the system state is normal;
when the first number does not exceed the second number and the second number is not lower than the third threshold, determining that the system state monitoring result is abnormal;
and when the first quantity and the second quantity are both lower than the third threshold value, determining that the system state monitoring result is that the system state is to be confirmed.
Optionally, the system state monitoring method further includes:
outputting a manual confirmation prompt when the system state monitoring result is determined to be the system state to be confirmed;
and outputting an alarm prompt when the system state monitoring result is determined to be abnormal.
Optionally, the system state monitoring method further includes:
and updating the system state library according to the system state monitoring result.
In a second aspect, the present application also discloses a system status monitoring device, including:
the acquisition module is used for acquiring data of a target system and obtaining system data;
the dividing module is used for dividing the system data according to the data type to obtain each system data group;
the first identification module is used for identifying each system data group by utilizing a classifier corresponding to the data type, and determining the group state of the system data group;
a generating module for generating a system state using each of the group states;
and the second recognition module is used for recognizing the system state by using the system state library and determining a system state monitoring result.
In a third aspect, the present application also discloses an electronic device, including:
A memory for storing a computer program;
a processor for implementing the steps of any of the system state monitoring methods described above when executing the computer program.
In a fourth aspect, the present application also discloses a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of any of the system state monitoring methods described above.
The application provides a system state monitoring method, which comprises the following steps: data acquisition is carried out on a target system to obtain system data; dividing the system data according to data types to obtain each system data group; for each system data group, identifying the system data group by using a classifier corresponding to the data type, and determining the group state of the system data group; generating a system state using each of the group states; and identifying the system state by using a system state library, and determining a system state monitoring result.
By applying the technical scheme provided by the application, for the collected system data about the target system, firstly, data classification is carried out according to the data types, the system data of the same type are ensured to be divided into the same data group, and corresponding classifiers are trained in advance for different data types, so that the corresponding system data groups can be identified by the same class of classifiers to obtain the group state of each system data group, further, all the group states are combined into the system state, and the system state is identified by utilizing a pre-established system state library, so that the system state monitoring result about the target system can be obtained. Therefore, the system data is divided according to the data types and then processed, the relevance of the system data in each data group can be effectively ensured, the accuracy of the system monitoring result is further ensured, then the system state condition is reflected through the combination of the data classification results, the construction and maintenance of a system model are not needed, the realization flow is simpler and more convenient, and the technical scheme can realize simpler and more accurate system state monitoring and effectively ensure the normal operation of the system.
The system state monitoring device, the electronic device and the computer readable storage medium provided by the application have the technical effects as well, and the application is not repeated here.
Drawings
In order to more clearly illustrate the technical solutions in the prior art and the embodiments of the present application, the following will briefly describe the drawings that need to be used in the description of the prior art and the embodiments of the present application. Of course, the following drawings related to embodiments of the present application are only a part of embodiments of the present application, and it will be obvious to those skilled in the art that other drawings can be obtained from the provided drawings without any inventive effort, and the obtained other drawings also fall within the scope of the present application.
FIG. 1 is a schematic flow chart of a system state monitoring method according to the present application;
FIG. 2 is a flow chart of another system status monitoring method according to the present application;
FIG. 3 is a schematic diagram of a system state library according to the present application;
FIG. 4 is a diagram showing a training data format according to the present application;
FIG. 5 is a schematic diagram of a system status monitor according to the present application;
fig. 6 is a schematic structural diagram of an electronic device according to the present application.
Detailed Description
The core of the application is to provide a system state monitoring method which can realize more concise and accurate system state monitoring and ensure the normal operation of the system; another core of the present application is to provide a system status monitoring device, an electronic device, and a computer readable storage medium, which all have the above advantages.
In order to more clearly and completely describe the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides a system state monitoring method.
Referring to fig. 1, fig. 1 is a flowchart of a system status monitoring method according to the present application, where the system status monitoring method may include the following steps S101 to S105.
S101: and acquiring data of the target system to obtain system data.
The step aims at realizing the data acquisition function, namely, carrying out data acquisition on a target system to obtain data information generated in the operation process, namely, the system data. The target system is a system needing to monitor the system state, the system type does not influence the implementation of the technical scheme, and the target system is applicable to various electronic systems, industrial systems and the like; the data type of various data information generated by the system data set target system in the operation process is not unique, and the data information can be set by technicians according to actual requirements, for example, the data can include but not limited to voltage, current, temperature, pressure, flow, vibration and the like.
It will be appreciated that the data acquisition operation may be performed in response to a system status monitoring instruction (which may be initiated by a technician through the front end, or automatically in response to some trigger signal), i.e. the data acquisition operation in S101 is performed upon receipt of the system status monitoring instruction.
S102: and dividing the system data according to the data types to obtain each system data group.
The step aims at realizing a data dividing function, namely dividing system data according to data types to obtain a plurality of system data sets. As described above, the data types of the system data collected during the data collection process are not unique, and may include multiple types of system data, where the system data may be divided into multiple system data sets according to different data types, for example, all current data may be divided into the same system data set, all voltage data may be divided into the same system data set, all temperature data may be divided into the same system data set, and so on.
Furthermore, the association relationship between various data types can be analyzed, and the association relationship is tightly combined into the same system data set, for example, the voltage and current relationship in the target system is more tightly, and then the current data set and the voltage data set can be combined into the same system data set. In addition, for the case that a certain data type has strong correlation of data in a group and weak correlation of data outside the group, the system data group of the data type can be further divided, for example, the temperature data group can be further divided into a first temperature data group, a second temperature data group and the like, so that the correlation of the data in the group is effectively ensured, and the accuracy of a system monitoring result is further ensured.
S103: and for each system data group, identifying the system data group by using a classifier corresponding to the data type, and determining the group state of the system data group.
This step aims at realizing the group status recognition function. Specifically, for different data types, corresponding data classifiers may be trained in advance for performing state recognition on the system data of the data type, so that for each system data set, the corresponding classifier may be invoked to perform recognition processing on the system data set, thereby determining the set state of the system data set. For example, a current classifier corresponding to the current data set may be invoked to identify the current data set, determine a set state of the current data set, and a temperature classifier corresponding to the temperature data set may be invoked to identify the temperature data set, determine a set state of the temperature data set. The group state is a real working state of the system data set corresponding to the data type, and taking the temperature data set as an example, the corresponding group state may be a high-temperature state, a low-temperature state, a heating state, a cooling state and the like.
The classifier is obtained by training sample data of corresponding data types in advance, and can be directly called when in use. In addition, the specific type of the classifier does not influence the implementation of the technical scheme, the data classification function can be realized, in one possible implementation mode, the classifier can specifically adopt an XGBoost gradient lifting tree (an algorithm realized based on boosting is a common classifier), and the classifier has the advantages of excellent effect, simplicity in use, high speed and the like.
S104: system states are generated using the sets of states.
This step aims at realizing a system state generation function of combining the group states of all the system data groups into the system state of the target system, for example, the system state= (current data group state, voltage data group state, temperature data group state, pressure data group state) of the target system.
S105: and identifying the system state by using a system state library, and determining a system state monitoring result.
This step aims at realizing the system state recognition function. Specifically, a system state library may be created in advance, in which various normal system states and/or abnormal system states are stored, so that the system states may be identified by means of database matching, thereby determining a system state monitoring result of the target system, where the system state monitoring result includes a normal system state and an abnormal system state (or an abnormal system state and an abnormal system state).
It can be seen that, in the system state monitoring method provided by the embodiment of the present application, for the collected system data about the target system, data classification is performed according to the data types, so that the same type of system data is guaranteed to be divided into the same data group, and corresponding classifiers are pre-trained for different data types, thereby, the corresponding system data groups can be identified by using the same class of classifiers to obtain a group state of each system data group, further, all the group states are combined into a system state, and then the system state is identified by using a pre-created system state library, so as to obtain a system state monitoring result about the target system. Therefore, the system data is divided according to the data types and then processed, the relevance of the system data in each data group can be effectively ensured, the accuracy of the system monitoring result is further ensured, then the system state condition is reflected through the combination of the data classification results, the construction and maintenance of a system model are not needed, the realization flow is simpler and more convenient, and the technical scheme can realize simpler and more accurate system state monitoring and effectively ensure the normal operation of the system.
Based on the above embodiments:
in an embodiment of the present application, the identifying the system data set by using the classifier corresponding to the data type to obtain a set state of the system data set may include:
processing the system data set by using a classifier corresponding to the data type to obtain an initial recognition result of the system data set, wherein the initial recognition result comprises probability values of states of various target sets hit by the system data set;
screening all probability values, and reserving a preset number of probability values with the maximum values;
and comparing and analyzing each retention probability value according to a preset recognition rule, and determining the group state of the system data group.
The embodiment of the application provides a method for realizing group state identification of a system data group based on a classifier. As described above, the classifier is used for performing state recognition on the system data sets of the corresponding data types, and for each system data set, the system data set may be input into the classifier of the corresponding data type, and the output of the classifier is an initial recognition result, where the main content includes probability values of the system data set hitting various target set states, for example, when the data type is temperature, all the target set states that exist may include: the temperature data set is processed based on the temperature classifier, and then the output of the temperature data set is: the temperature data sets are respectively a probability value of a temperature rising state, a probability value of a temperature falling state, a probability value of a high temperature state and a probability value of a low temperature state. Further, all probability values are filtered, and only the preset number of probability values with the maximum value are reserved, and based on the above example, the initial recognition result about the temperature data set is assumed to be: if the probability value of the warming state is greater than the probability value of the high temperature state is greater than the probability value of the low temperature state is greater than the probability value of the cooling state, only the first two probability values (the preset number value is 2) can be reserved, namely the probability value of the warming state and the probability value of the high temperature state; of course, the specific value of the preset number is set by a technician according to the actual situation, which is not limited in the present application, and it should be noted that the preset number is less than the total number of the target group states. And finally, comparing and analyzing each retention probability value according to a preset recognition rule, and determining the group state of the current system data group.
In one embodiment of the present application, when the preset number value is 2, the comparing and analyzing each retention probability value according to the preset recognition rule to determine the group status of the system data group may include:
when the maximum retention probability value is not lower than the first threshold value and the difference value between the maximum retention probability value and the second retention probability value is lower than the second threshold value, taking the target group state corresponding to the maximum retention probability value and the target group state corresponding to the second retention probability value as the group state of the system data group;
when the maximum retention probability value is not lower than a first threshold value and the difference value between the maximum retention probability value and the second retention probability value is not lower than a second threshold value, taking the target group state corresponding to the maximum retention probability value as the group state of the system data group;
and when the maximum retention probability value is lower than the first threshold value, determining that the initial recognition result is an abnormal recognition result.
The embodiment of the application provides a specific form of preset recognition rule. In the embodiment of the application, taking the preset number value as 2 as an example, the preset recognition rule is developed and introduced. Firstly, when the preset number value is 2, two retention probability values are a maximum retention probability value and a second retention probability value; then, the two probability values are compared with a preset evaluation threshold (a first threshold and a second threshold) for analysis, so that whether the group state of the current system data group is credible or not can be determined according to the analysis result, and the group state of the current system data group can be determined when the credibility is determined.
Of course, the evaluation threshold values (the first threshold value and the second threshold value) are all evaluation values set by a technician according to actual conditions/combination history experience, and the specific evaluation values are not limited by the present application.
In one embodiment of the present application, when it is determined that the initial recognition result is an abnormal recognition result, the system state monitoring method may further include:
acquiring a manual calibration result of a system data set;
optimizing and training the classifier corresponding to the system data set by using the manual calibration result to obtain an optimized classifier;
based on the optimized classifier, returning to the step of identifying the system data set by using the classifier corresponding to the data type and determining the set state of the system data set.
The system state monitoring method provided by the embodiment of the application can further realize the classifier optimization function. Specifically, when the initial recognition result is determined to be an abnormal recognition result, the initial recognition result is not trusted, and a new state of the type of data is also indicated to be present, namely, a group state which cannot be recognized by the current classifier and is completely different from the existing target group state, at this time, the classifier needs to be optimized to obtain an optimized classifier so as to apply the recognition of the new group state. In the implementation process, a technician can manually calibrate the system data set to obtain a corresponding manual calibration result, then the manual calibration result is used as new training data to perform optimization training on the corresponding classifier, and the optimized classifier can be obtained, so that S102 can be returned to use the optimized classifier to perform group state recognition again.
In one embodiment of the application, the system state library may include an abnormal system state library and a non-abnormal system state library; the identifying the system state by using the system state library, and determining the system state monitoring result may include:
determining a best matching non-abnormal state of the system state hit in a non-abnormal system state library, and determining a first number of the same set of states in the system state and the best matching non-abnormal state;
determining a best-matching abnormal state hit by the system state in an abnormal system state library, and determining a second number of states of the same group in the system state and the best-matching abnormal state;
when the first quantity exceeds the second quantity and the first quantity is not lower than a third threshold value, determining that the system state monitoring result is that the system state is normal;
when the first quantity does not exceed the second quantity and the second quantity is not lower than a third threshold value, determining that the system state monitoring result is abnormal;
and when the first quantity and the second quantity are both lower than a third threshold value, determining that the system state monitoring result is the system state to be confirmed.
The embodiment of the application provides a method for realizing system state identification based on a system state library. Specifically, the system state library may include an abnormal system state library and a non-abnormal system state library, where the abnormal system state library includes a plurality of system states determined to be abnormal in the target system, and the non-abnormal system state library includes a plurality of system states determined to be normal in the target system, so that the system states that need to be identified currently can be processed by using the abnormal system state library and the non-abnormal system state library. In the implementation process, the target system state which is most matched with the current system state is respectively inquired in an abnormal system state library and a non-abnormal system state library, namely the most matched non-abnormal state in the non-abnormal system state library and the most matched abnormal state in the abnormal system state library; and then, respectively determining the quantity of the same group of states in the current system state and the two best matching states to obtain a first quantity and a second quantity, thereby realizing the determination of the system state monitoring result through numerical comparison.
For example, assuming that the system data of the target system is divided into 5 data types, the system state is composed of 5 group states, corresponding to each system state recorded in the abnormal system state library corresponding to the target system is composed of 5 group states, each system state recorded in the non-abnormal system state library is composed of 5 group states, on the basis that each group state in the system states can be sequentially matched when the most matched state in the library is inquired, when the number of identical group states in the 5 group states is the largest (for example, 3 group states are identical), the system state can be taken as the most matched state, and the most matched non-abnormal state and the most matched abnormal state can be obtained; accordingly, the number of the same group states is the first number/the second number.
In one embodiment of the present application, the system status monitoring method may further include:
outputting a manual confirmation prompt when the system state monitoring result is determined to be the system state to be confirmed;
and when the system state monitoring result is determined to be abnormal, outputting an alarm prompt.
The system state detection method provided by the embodiment of the application can further realize a result output function. Specifically, when the system state monitoring result is determined to be the system state to be confirmed, a manual confirmation prompt can be output to inform the technician that the current identification result is inaccurate and that the manual re-checking confirmation is needed; when the system state monitoring result is determined to be abnormal, an alarm prompt can be output to inform technicians that the target system is abnormal currently and maintenance processing needs to be performed timely. Of course, when the system state monitoring result is determined to be that the system state is normal, a monitoring passing prompt can be output to inform a technician that the current target system is in a normal running state.
In one embodiment of the present application, the system status monitoring method may further include: and updating the system state library according to the system state monitoring result.
The system state detection method provided by the embodiment of the application can further realize the database updating function, namely updating the system state library according to the system state monitoring result so as to further perfect and comprehensively integrate the system state library and provide assistance for the subsequent new round of system state monitoring. Specifically, when the system state library includes an abnormal system state library and a non-abnormal system state library, if the system state monitoring result is that the system state is normal, the system state monitoring can be added to the non-abnormal system state library, and the content in the non-abnormal system state library is subjected to duplication removal and correction processing; if the system state monitoring result is that the system state is abnormal, the system state monitoring can be added to an abnormal system state library, and duplicate removal and correction processing can be carried out on the content in the abnormal system state library.
Based on the above embodiments, another system state monitoring method is provided in the embodiments of the present application.
Referring to fig. 2, fig. 2 is a flow chart of another system state monitoring method provided by the present application, and the implementation flow of the system state monitoring method is as follows:
1. Data packet
In the monitored system, the system measuring points are divided into a plurality of groups according to different physical meanings (data types), such as current, voltage, temperature, vibration, flow, pressure and the like. If the current and the voltage have close association relation in the system, the current and the voltage can be divided into one class, and other physical quantities are similar; if the temperature in the system obviously has strong correlation in groups and weak correlation among groups, the temperature can be divided into a first temperature … … and a second temperature … …, and other physical quantities are similar.
2. Classifier training and application
Training a classifier: as many classifiers of different physical meanings as possible are trained by historical data (i.e. training data) provided with a system state label V and each group of state labels S, and the classifiers can be realized by adopting XGBoost gradient lifting trees.
Classifier application (group state identification): taking a certain system data set (set as S1 set) as an example, when the system data set outputs the result through the S1 classifier: state one S1 A And probability value R1 A State two S1 B And probability value R1 B … …, (arranged in descending order of probability values). Then:
(1) When R1 is A When the data set is smaller than a threshold value N1 (a first threshold value), the result obtained by the S1 classifier is not trusted, a new state appears, a label for calibrating the system data set is needed to be manually intervened, and the S1 classifier is retrained and optimized; -
(2) When R1 is A Greater than or equal to a threshold value N1, R1 A -R1 B When the threshold value is smaller than the threshold value N2 (the second threshold value), the result of the S1 classifier is considered to be S1 A And S1 B (of course, R1 can also be built in a similar manner A And R1 B 、R1 C The relation between the S1 classifier and the S1 classifier results in S1 A 、S1 B And S1 C )；
(3) When R1 is A Greater than or equal to a threshold value N1, R1 A -R1 B If the result is greater than the threshold N2, the result of the S1 classifier is considered to be S1 A 。
If the result of the S1 classifier has an abnormal state label, the result of the S1 classifier is considered to be the abnormal state label, and the normal state label is discarded (the purpose of this operation is to rather determine that the error report is not reported by the method).
3. System state generation and identification
First, the states of the respective groups are combined in a certain order to form a system state. Such as current set state A, voltage set state B, temperature set state C, vibration set state D, liquid level set state E, pressure set state F, flow set state G, can be combined to form a system state ABCDEFG, wherein A 1 B 1 C 1 D 1 E 1 F 1 G 1 Is a system state. It should be noted that the above-mentioned group state in 2 may exist in two or more ways, so that the combination representing one group state may form two system states, for example, the state of a certain group state current is A 1 And A 2 The system state is formed as A 1 B 1 C 1 D 1 E 1 F 1 G 1 And A 2 B 1 C 1 D 1 E 1 F 1 G 1 。
Further, the system state is classified into a normal system state, an abnormal system state, and to-be-confirmed. All system states of training data are classified according to normal and abnormal states and are respectively stored in a normal system state library and an abnormal system state library, as shown in fig. 3, fig. 3 is a schematic diagram of a system state library provided by the application, and the schematic diagram mainly comprises a normal system state library and an abnormal system state library. The manner in which the system states in the system state library are increased may include, but is not limited to:
(1) And the training data acquisition mode is the same as that of the training data, namely, a system state is established as a normal system state or an abnormal system state.
(2) If the result of a certain group(s) of physical quantities is not necessarily linked to a normal system state or an abnormal system state, the group states of the groups may be replaced with underlines, indicating that the group states of the groups are arbitrary, and that the normal system state and the abnormal system state obtained from the training data need to be corrected. For example, according to the experience of engineersThe voltage group status, the temperature group status and the normal (or abnormal) system status are not necessarily related, the system status A 1 B 1 C 1 D 1 E 1 F 1 G 1 Is modified as A 1 __D 1 E 1 F 1 G 1 。
(3) If the result of a certain group(s) of physical quantities is (are) constant in normal system state or abnormal system state, the other groups than those groups are replaced with underlines, meaning that when the group states of those groups are determined, the other group states may be arbitrary and the duplicate items in the normal system state and abnormal system state obtained by the training data need to be removed. For example, the presence of A in an abnormal System State 3 B 1 C 1 D 2 E 1 F 1 G 2 It is now empirically assumed by engineers that when the current set state is A 3 The vibration group state is D 2 The flow group state is G 2 When the system state is always abnormal, removing the abnormal system state A 3 B 1 C 1 D 2 E 1 F 1 G 2 Keep abnormal system state A 3 __ 1 D 2 __G 2 。
4. Monitoring result determination and system state self-maintenance
Setting a system state judgment threshold value N (a third threshold value) less than or equal to the number of system groups (based on the above example, the number of system groups is 7), wherein the system state formed by combining the results of the respective system data groups through the corresponding classifiers is V Real world Record the current system state V Real world The number of the same bits as the maximum number of the normal system states (in the normal system state library) is T, and the current system state V is recorded Real world The most identical number of bits in the abnormal system state (in the abnormal system state library) is F. It is noted that the group status is underlined in both the normal and abnormal system status, i.e., A 1 B 2 C 1 D 1 E 2 F 3 G 1 And A is a 1 __D 1 E 1 F 1 G 1 The number of identical digits of (2) is 5.Then there are:
(1) When T is more than F and T is more than or equal to N, the monitored system is considered to be in a normal system state;
(2) When T is less than or equal to F and F is more than or equal to N, the monitored system is considered to be in an abnormal system state;
(3) When T < N and F < N, the monitored system is considered to be confirmed.
Finally, when the system state of the monitored system is judged to be a normal system state, if T is smaller than the system grouping number, the system state is input into a normal system state library, and repeated contents in the normal system state library are corrected and removed; when the system state of the monitored system is judged to be an abnormal system state, triggering a system state alarm to remind an engineer of the abnormality to be processed, and if T is smaller than the number of system packets, recording the system state into an abnormal system state library, and correcting and removing repeated contents in the abnormal system state library; when the system state of the monitored system is judged to be confirmed, the system state is recorded into a class to be confirmed of a system state library, if the system state exists in the class to be confirmed, of course, the recording is not repeated, the system state in the class to be confirmed needs to be manually judged to be a normal system state or an abnormal system state by an engineer later, and then the system state is put into a corresponding library, and library state correction and removal work is carried out.
The following provides a practical application scenario:
taking a main water supply system of a power plant as an example, the system is composed of a series of equipment such as 3 main water supply pumps, 2 starting water supply pumps and the like, 109 measuring points can be recorded, and the system can be divided into 9 measuring points A1 of a main water supply pump current group, 6 measuring points A2 of a starting water supply pump current group, 2 measuring points B of a flow group, 1 measuring point C1 of a main water supply pump motor coil temperature+pump bearing temperature group, 24 measuring points D of a main water supply pump motor end vibration+pump end vibration group, 6 measuring points C2 of a main water supply pump inlet and outlet temperature group, 4 measuring points C3 of a starting water supply pump inlet and outlet temperature group, 3 measuring points E of a pressure difference group and 4 measuring points F of an environment group (environment variables such as generator power, factory building temperature, set cold water temperature and the like). The training data format is shown in fig. 4, and fig. 4 is a diagram showing a training data format provided by the present application, and the data is taken in a group of 5 minutes.
After the training data acquisition is completed, training the XGBoost multi-classifier by using each group of training data and the labels, and formulating the judging result of each group of states. The output results of multiple classifiers of each group only remain the first three classes in the case, when R1 A More than or equal to 40 percent and R1 A -R1 B When the number is more than or equal to 5%, the set of state results are S1 A The method comprises the steps of carrying out a first treatment on the surface of the When R1 is A More than or equal to 40 percent and R1 A -R1 B At < 5%, the set of status results is S1 A And S1 B 。
Further, the group status results are sequentially combined into a system status A1 A2B C1D C C3E F, and the system status is distinguished into a normal system status and an abnormal system status (the environment group is a non-necessary relationship group, underlined) according to the system status label and the engineer experience. At this time, the number of system packets is 9, and N is set to 6 or 7 (N is set to 6 when the system state label type is small, otherwise N is set to 7).
And then, the system state of the monitored system at a certain moment can be predicted to be in a normal system state or an abnormal system state by the system state monitoring method provided by the application, and when the abnormal system state occurs, an alarm is given in time to inform an engineer of analyzing the system state. In addition, in the actual use process, the system can also improve the accuracy of system state judgment by continuously and automatically maintaining system state classification.
It can be seen that, in the system state monitoring method provided by the embodiment of the present application, for the collected system data about the target system, data classification is performed according to the data types, so that the same type of system data is guaranteed to be divided into the same data group, and corresponding classifiers are pre-trained for different data types, thereby, the corresponding system data groups can be identified by using the same class of classifiers to obtain a group state of each system data group, further, all the group states are combined into a system state, and then the system state is identified by using a pre-created system state library, so as to obtain a system state monitoring result about the target system. Therefore, the system data is divided according to the data types and then processed, the relevance of the system data in each data group can be effectively ensured, the accuracy of the system monitoring result is further ensured, then the system state condition is reflected through the combination of the data classification results, the construction and maintenance of a system model are not needed, the realization flow is simpler and more convenient, and the technical scheme can realize simpler and more accurate system state monitoring and effectively ensure the normal operation of the system.
The embodiment of the application provides a system state monitoring device.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a system status monitoring device provided by the present application, where the system status monitoring device may include:
the acquisition module 1 is used for acquiring data of a target system to obtain system data;
the dividing module 2 is used for dividing the system data according to the data types to obtain each system data group;
the first identifying module 3 is configured to identify, for each system data set, the system data set by using a classifier corresponding to the data type, and determine a set state of the system data set;
a generation module 4 for generating a system state using the respective sets of states;
and the second recognition module 5 is used for recognizing the system state by using the system state library and determining a system state monitoring result.
It can be seen that, according to the system state monitoring device provided by the embodiment of the present application, for the collected system data about the target system, data classification is performed according to the data types, so that the same type of system data is guaranteed to be divided into the same data group, and corresponding classifiers are pre-trained for different data types, so that the corresponding system data groups can be identified by using the same class of classifiers to obtain a group state of each system data group, further, all the group states are combined into a system state, and then the system state is identified by using a pre-created system state library, so as to obtain a system state monitoring result about the target system. Therefore, the system data is divided according to the data types and then processed, the relevance of the system data in each data group can be effectively ensured, the accuracy of the system monitoring result is further ensured, then the system state condition is reflected through the combination of the data classification results, the construction and maintenance of a system model are not needed, the realization flow is simpler and more convenient, and the technical scheme can realize simpler and more accurate system state monitoring and effectively ensure the normal operation of the system.
In one embodiment of the present application, the first identification module 3 may include:
the processing unit is used for processing the system data set by utilizing a classifier corresponding to the data type to obtain an initial identification result of the system data set, wherein the initial identification result comprises probability values of states of various target sets hit by the system data set;
the screening unit is used for screening all probability values and reserving a preset number of probability values with the maximum value;
and the analysis unit is used for carrying out comparison analysis on each retention probability value according to a preset recognition rule and determining the group state of the system data group.
In an embodiment of the present application, when the preset number of values is 2, the analysis unit may be specifically configured to, when the maximum retention probability value is not lower than the first threshold value and the difference between the maximum retention probability value and the second retention probability value is lower than the second threshold value, take the target group state corresponding to the maximum retention probability value and the target group state corresponding to the second retention probability value as the group state of the system data group; when the maximum retention probability value is not lower than a first threshold value and the difference value between the maximum retention probability value and the second retention probability value is not lower than a second threshold value, taking the target group state corresponding to the maximum retention probability value as the group state of the system data group; and when the maximum retention probability value is lower than the first threshold value, determining that the initial recognition result is an abnormal recognition result.
In one embodiment of the present application, when the initial recognition result is determined to be an abnormal recognition result, the system state monitoring device may further include an optimization module, configured to obtain a manual calibration result of the system data set; optimizing and training the classifier corresponding to the system data set by using the manual calibration result to obtain an optimized classifier; based on the optimized classifier, returning to the step of identifying the system data set by using the classifier corresponding to the data type and determining the set state of the system data set.
In one embodiment of the application, the system state library may include an abnormal system state library and a non-abnormal system state library; the second identifying module 5 may be specifically configured to determine a best matching non-abnormal state that the system state hits in the non-abnormal system state library, and determine a first number of states in the same group as the best matching non-abnormal state; determining a best-matching abnormal state hit by the system state in an abnormal system state library, and determining a second number of states of the same group in the system state and the best-matching abnormal state; when the first quantity exceeds the second quantity and the first quantity is not lower than a third threshold value, determining that the system state monitoring result is that the system state is normal; when the first quantity does not exceed the second quantity and the second quantity is not lower than a third threshold value, determining that the system state monitoring result is abnormal; and when the first quantity and the second quantity are both lower than a third threshold value, determining that the system state monitoring result is the system state to be confirmed.
In one embodiment of the present application, the system status monitoring device may further include an output module, configured to output a manual confirmation prompt when it is determined that the system status monitoring result is that the system status is to be confirmed; and when the system state monitoring result is determined to be abnormal, outputting an alarm prompt.
In one embodiment of the present application, the system state monitoring device may further include an update module, configured to update the system state library according to the system state monitoring result.
For the description of the apparatus provided by the embodiment of the present application, refer to the above method embodiment, and the description of the present application is omitted here.
The embodiment of the application provides electronic equipment.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to the present application, where the electronic device may include:
a memory for storing a computer program;
a processor for implementing the steps of any of the system condition monitoring methods described above when executing a computer program.
As shown in fig. 6, which is a schematic diagram of a composition structure of an electronic device, the electronic device may include: a processor 10, a memory 11, a communication interface 12 and a communication bus 13. The processor 10, the memory 11 and the communication interface 12 all complete communication with each other through a communication bus 13.
In an embodiment of the present application, the processor 10 may be a central processing unit (Central Processing Unit, CPU), an asic, a dsp, a field programmable gate array, or other programmable logic device, etc.
The processor 10 may call a program stored in the memory 11, and in particular, the processor 10 may perform operations in an embodiment of a system status monitoring method.
The memory 11 is used for storing one or more programs, and the programs may include program codes including computer operation instructions, and in the embodiment of the present application, at least the programs for implementing the following functions are stored in the memory 11:
data acquisition is carried out on a target system to obtain system data;
dividing system data according to data types to obtain each system data group;
for each system data group, identifying the system data group by using a classifier corresponding to the data type, and determining the group state of the system data group;
generating a system state using each set of states;
and identifying the system state by using a system state library, and determining a system state monitoring result.
In one possible implementation, the memory 11 may include a storage program area and a storage data area, where the storage program area may store an operating system, and at least one application program required for functions, etc.; the storage data area may store data created during use.
In addition, the memory 11 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device or other volatile solid-state storage device.
The communication interface 12 may be an interface of a communication module for interfacing with other devices or systems.
Of course, it should be noted that the structure shown in fig. 6 is not limited to the electronic device in the embodiment of the present application, and the electronic device may include more or fewer components than those shown in fig. 6 or may be combined with some components in practical applications.
Embodiments of the present application provide a computer-readable storage medium.
The computer readable storage medium provided by the embodiment of the application stores a computer program, and when the computer program is executed by a processor, the steps of any one of the system state monitoring methods can be realized.
The computer readable storage medium may include: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
For the description of the computer-readable storage medium provided in the embodiment of the present application, refer to the above method embodiment, and the description of the present application is omitted here.
In the description, each embodiment is described in a progressive manner, and each embodiment is mainly described by the differences from other embodiments, so that the same similar parts among the embodiments are mutually referred. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative elements and steps are described above generally in terms of functionality in order to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software modules may be disposed in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The technical scheme provided by the application is described in detail. The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to facilitate an understanding of the method of the present application and its core ideas. It should be noted that it will be apparent to those skilled in the art that the present application may be modified and practiced without departing from the spirit of the present application.
Claims (10)
1. A system condition monitoring method, comprising:
data acquisition is carried out on a target system to obtain system data;
dividing the system data according to data types to obtain each system data group;
for each system data group, identifying the system data group by using a classifier corresponding to the data type, and determining the group state of the system data group;
generating a system state using each of the group states;
and identifying the system state by using a system state library, and determining a system state monitoring result.
2. The system state monitoring method according to claim 1, wherein the identifying the system data set by using the classifier corresponding to the data type, to obtain the set state of the system data set, includes:
Processing the system data set by using a classifier corresponding to the data type to obtain an initial recognition result of the system data set, wherein the initial recognition result comprises probability values of states of various target groups hit by the system data set;
screening all probability values, and reserving a preset number of probability values with the maximum values;
and comparing and analyzing each retention probability value according to a preset recognition rule, and determining the group state of the system data group.
3. The system state monitoring method according to claim 2, wherein when the preset number value is 2, the comparing and analyzing each retention probability value according to a preset recognition rule, and determining the group state of the system data group includes:
when the maximum retention probability value is not lower than a first threshold value and the difference value between the maximum retention probability value and a second retention probability value is lower than a second threshold value, taking a target group state corresponding to the maximum retention probability value and a target group state corresponding to the second retention probability value as group states of the system data group;
when the maximum retention probability value is not lower than a first threshold value and the difference value between the maximum retention probability value and a second retention probability value is not lower than a second threshold value, taking a target group state corresponding to the maximum retention probability value as a group state of the system data group;
And when the maximum retention probability value is lower than a first threshold value, determining that the initial recognition result is an abnormal recognition result.
4. The system state monitoring method according to claim 3, further comprising, when it is determined that the initial recognition result is the abnormality recognition result:
acquiring a manual calibration result of the system data set;
performing optimization training on the classifier corresponding to the system data set by using the manual calibration result to obtain an optimized classifier;
and based on the optimized classifier, returning to the step of identifying the system data set by using the classifier corresponding to the data type and determining the set state of the system data set.
5. The system state monitoring method of claim 2, wherein the system state library comprises an abnormal system state library and a non-abnormal system state library; the system state is identified by using a system state library, and a system state monitoring result is determined, which comprises the following steps:
determining a best matching non-abnormal state in which the system state hits in the non-abnormal system state library, and determining a first number of the same set of states in the system state and the best matching non-abnormal state;
Determining a best matching abnormal state in which the system state hits in the abnormal system state library, and determining a second number of states of the same group in the system state and the best matching abnormal state;
when the first quantity exceeds the second quantity and the first quantity is not lower than a third threshold value, determining that the system state monitoring result is that the system state is normal;
when the first number does not exceed the second number and the second number is not lower than the third threshold, determining that the system state monitoring result is abnormal;
and when the first quantity and the second quantity are both lower than the third threshold value, determining that the system state monitoring result is that the system state is to be confirmed.
6. The system condition monitoring method of claim 5, further comprising:
outputting a manual confirmation prompt when the system state monitoring result is determined to be the system state to be confirmed;
and outputting an alarm prompt when the system state monitoring result is determined to be abnormal.
7. The system condition monitoring method of claim 1, further comprising:
and updating the system state library according to the system state monitoring result.
8. A system condition monitoring apparatus, comprising:
the acquisition module is used for acquiring data of a target system and obtaining system data;
the dividing module is used for dividing the system data according to the data type to obtain each system data group;
the first identification module is used for identifying each system data group by utilizing a classifier corresponding to the data type, and determining the group state of the system data group;
a generating module for generating a system state using each of the group states;
and the second recognition module is used for recognizing the system state by using the system state library and determining a system state monitoring result.
9. An electronic device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the system condition monitoring method according to any one of claims 1 to 7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the system condition monitoring method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310879815.0A CN116910499A (en) | 2023-07-18 | 2023-07-18 | System state monitoring method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310879815.0A CN116910499A (en) | 2023-07-18 | 2023-07-18 | System state monitoring method and device, electronic equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116910499A true CN116910499A (en) | 2023-10-20 |
Family
ID=88354485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310879815.0A Pending CN116910499A (en) | 2023-07-18 | 2023-07-18 | System state monitoring method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116910499A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118134208A (en) * | 2024-05-06 | 2024-06-04 | 国网山东省电力公司滨州市沾化区供电公司 | Power transmission and transformation operation detection data processing method, system, terminal and storage medium |
-
2023
- 2023-07-18 CN CN202310879815.0A patent/CN116910499A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118134208A (en) * | 2024-05-06 | 2024-06-04 | 国网山东省电力公司滨州市沾化区供电公司 | Power transmission and transformation operation detection data processing method, system, terminal and storage medium |
| CN118134208B (en) * | 2024-05-06 | 2024-07-23 | 国网山东省电力公司滨州市沾化区供电公司 | Power transmission and transformation operation detection data processing method, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| US8868985B2 (en) | Supervised fault learning using rule-generated samples for machine condition monitoring | |
| CN109522221B (en) | Method and system for improving fuzzy test efficiency | |
| CN116910499A (en) | System state monitoring method and device, electronic equipment and readable storage medium | |
| CN112231134B (en) | Fault processing method and device for neural network processor, equipment and storage medium | |
| KR20190008515A (en) | Process Monitoring Device and Method using RTC method with improved SAX method | |
| KR20220068799A (en) | System for detecting error of automation equipment and method thereof | |
| CN116994641A (en) | Semiconductor aging test method and system thereof | |
| CN116956282A (en) | Abnormality detection system based on network asset memory time sequence multi-feature data | |
| CN111555899B (en) | Alarm rule configuration method, equipment state monitoring method, device and storage medium | |
| US20210080924A1 (en) | Diagnosis Method and Diagnosis System for a Processing Engineering Plant and Training Method | |
| CN116820821A (en) | Disk failure detection method, apparatus, electronic device and computer readable storage medium | |
| CN112181792A (en) | Method, system and related assembly for abnormal marking of time sequence data | |
| US20220405161A1 (en) | Data selection assist device and data selection assist method | |
| CN112526558B (en) | System operation condition identification and cutting method under partial data loss condition | |
| CN116399477A (en) | Diagnosis management and control method and device for battery module temperature sensor | |
| CN114677052A (en) | Natural gas load fluctuation asymmetry analysis method and system based on TARCH model | |
| CN114416467A (en) | Anomaly detection method and device | |
| CN109886119B (en) | Industrial control signal-based control function classification method and system | |
| CN113407520A (en) | Power network safety data cleaning system and method based on machine learning | |
| CN108959028B (en) | Method and device for analyzing life cycle of disk | |
| CN114237647B (en) | Single-chip microcomputer programming control system and single-chip microcomputer programming control method | |
| CN117055537B (en) | Motorcycle electric control system fault diagnosis method based on Internet of things | |
| JP7281394B2 (en) | Abnormal diagnosis device and program | |
| TWI700565B (en) | Parameter correction method and system thereof |
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 |