CN114596458A - Method and system for detecting state of dewatering device - Google Patents

Method and system for detecting state of dewatering device Download PDF

Info

Publication number
CN114596458A
CN114596458A CN202011415064.XA CN202011415064A CN114596458A CN 114596458 A CN114596458 A CN 114596458A CN 202011415064 A CN202011415064 A CN 202011415064A CN 114596458 A CN114596458 A CN 114596458A
Authority
CN
China
Prior art keywords
data
working condition
acquiring
data segment
segments
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
Application number
CN202011415064.XA
Other languages
Chinese (zh)
Inventor
熊伟
彭波
胡昌权
宋伟
秦伟
张波
谭健
刘辉
梁兵
谭红
苟俊轶
万戈
蒋昊
黄静才
张艳玲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Petrochina Co Ltd
Original Assignee
Petrochina Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Petrochina Co Ltd filed Critical Petrochina Co Ltd
Priority to CN202011415064.XA priority Critical patent/CN114596458A/en
Publication of CN114596458A publication Critical patent/CN114596458A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The embodiment of the application discloses a method and a system for detecting the state of a dehydration device, wherein the method comprises the following steps: initializing and segmenting existing data, and acquiring segmented data segments; acquiring a fused data segment based on the segmented data segment; acquiring a working condition type based on the fused data segment; and detecting the state of the dewatering device based on the working condition type. The embodiment of the application can improve the state detection precision of the dewatering device and effectively prevent safety risks.

Description

Method and system for detecting state of dewatering device
Technical Field
The embodiment of the application relates to the technical field of safety risk detection, in particular to a method and a system for detecting the state of a dehydration device.
Background
The dehydration device is a key device on a gas field water conveying pipeline, safety risks can be prevented by detecting the state of the dehydration device, and the state of the dehydration device is detected by using data, so that the dehydration device is widely concerned.
In the related art, a prediction model is established for the state of the dehydration device by using existing data, and then the model is directly used for detecting the state of the dehydration device. However, since the state of the dehydration apparatus is complicated during the operation and cannot be roughly described by using the same model, the detection accuracy of the related art is not high.
Disclosure of Invention
The embodiment of the application provides a method and a system for detecting the state of a dehydration device, which are used for detecting the state of the dehydration device and further preventing safety risks.
In one aspect, an embodiment of the present application provides a method for detecting a state of a dehydration apparatus, where the method includes: initializing and segmenting existing data, and acquiring segmented data segments; acquiring a fused data segment based on the segmented data segment; acquiring a working condition type based on the fused data segment; and detecting the state of the dewatering device based on the working condition type.
In a possible implementation manner, the initializing and segmenting the existing data, and acquiring the segmented data segment includes: carrying out standardization processing on the existing data to obtain a processed data characteristic vector; carrying out mean value filtering on the processed data characteristic vector to obtain filtered data; and carrying out data segmentation on the filtered data to obtain segmented data segments.
In a possible implementation manner, the obtaining a fused data segment based on the segmented data segment includes: obtaining a loss function of each data segment based on the segmented data segments; and fusing the data segments based on the loss function of each data segment to obtain fused data segments.
In a possible implementation manner, the obtaining a type of a working condition based on the fused data segment includes: acquiring the distance between the fused data fragments; clustering the fused data segments based on the distance between the fused data segments to obtain clustered data segments; and acquiring the working condition type based on the clustered data segments.
In a possible implementation manner, the detecting the state of the dehydration device based on the operating condition type includes: establishing a state prediction model of each working condition type based on the working condition types; acquiring central data of each working condition type; inputting a new data segment, wherein the new data segment is acquired through a dehydration device; acquiring a state prediction model of the new data segment based on the new data segment, the central data of each working condition type and the state prediction model of each working condition type; and detecting the state of the dehydration device based on the state prediction model of the new data segment.
In another aspect, an embodiment of the present application provides a system for detecting a state of a dehydration apparatus, where the system includes: the initialization module is used for initializing and segmenting the existing data and acquiring segmented data segments; the fusion module is used for acquiring fused data fragments based on the segmented data fragments; the clustering module is used for acquiring the working condition type based on the fused data segments; and the prediction module is used for detecting the state of the dehydration device based on the working condition type.
In a possible implementation manner, the initialization module is configured to perform normalization processing on existing data, and obtain a processed data feature vector; carrying out mean value filtering on the processed data characteristic vector to obtain filtered data; and carrying out data segmentation on the filtered data to obtain segmented data segments.
In a possible implementation manner, the fusion module is configured to obtain a loss function of each data segment based on the segmented data segments; and fusing the data segments based on the loss function of each data segment to obtain fused data segments.
In a possible implementation manner, the clustering module is configured to obtain a distance between the fused data segments; clustering the fused data segments based on the distance between the fused data segments to obtain clustered data segments; and acquiring the working condition type based on the clustered data segments.
In a possible implementation manner, the prediction module is configured to establish a state prediction model of each operating condition type based on the operating condition type; acquiring central data of each working condition type; inputting a new data segment, wherein the new data segment is acquired through a dehydration device; acquiring a state prediction model of the new data segment based on the new data segment, the central data of each working condition type and the state prediction model of each working condition type; and detecting the state of the dehydration device based on the state prediction model of the new data segment.
The present embodiments also provide a computer-readable storage medium having at least one program instruction or code stored therein, where the program instruction or code is loaded and executed by a processor to make a computer implement the state detection method of the dehydration device.
The technical scheme provided by the embodiment of the application at least comprises the following beneficial effects: 1. the data segmentation technology is used, and on the basis, the working condition type is obtained by using a fusion and clustering method, so that the condition is not required to be specified after the data are clustered, and the working condition of the data can be determined by calculation in a self-adaptive manner. 2. Models are respectively established according to different working conditions, after new data are obtained, the used models are determined according to the similarity degree between the new data and classified data, so that the state of the dehydration device is determined, and the problems that the working state of the dehydration device is complex and the detection precision is inaccurate are solved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of a method for detecting a state of a dehydration engine according to an embodiment of the present application;
fig. 2 is a schematic diagram of a state detection system of a dehydration engine according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of a method for detecting a state of a dewatering device according to an embodiment of the present application is shown, the method including the following steps:
step 101, initializing and segmenting existing data, and acquiring segmented data segments.
In one possible implementation method, the existing data is initially segmented, and the obtaining of the segmented data segment includes, but is not limited to, the following sub-steps:
1011. and carrying out standardization processing on the existing data to obtain the processed data characteristic vector.
Wherein the existing data is already obtained data, alternatively the existing data may be obtained by a sensor installed in the dewatering device. Optionally, based on the existing data, a vector composed of features of the existing data, that is, an existing data feature vector, is obtained. Further optionally, the existing data feature vector is processed according to the following formula, and the processed data feature vector is obtained by calculation:
Figure BDA0002818715180000041
wherein x isoldFor existing data feature vectors, xnewMu is the mean value of the existing data vector and sigma is the standard deviation of the existing data vector. Wherein, the standard deviation is the arithmetic square root of the arithmetic mean (i.e. variance) of the squared deviation, and represents the discrete degree of a data set, and the standard deviation is calculated according to the existing data vector.
1012. And performing mean filtering on the processed data characteristic vectors to obtain filtered data.
Optionally, the processed data feature vector may be subjected to mean filtering processing by using a sliding window, so as to obtain filtered data.
1013. And carrying out data segmentation on the filtered data to obtain segmented data fragments.
Optionally, a bottom-up data segmentation method is adopted for the filtered data, and the filtered data is segmented into a plurality of small segments until the number of the first segments is obtained, so that segmented data segments are obtained. Further optionally, the first number of segments is set based on experience.
And 102, acquiring the fused data segment based on the segmented data segment.
In one possible implementation method, based on the segmented data segment, the obtaining of the fused data segment includes, but is not limited to, the following sub-steps:
1021. and acquiring a loss function of each data segment based on the segmented data segments.
Optionally, for the segmented data segments, the loss function of each data segment is calculated according to the following formula:
Figure BDA0002818715180000042
wherein the cost represents a loss function for each data segment, the costQRepresenting the corresponding matrix reconstruction error for each data segment,
Figure BDA0002818715180000043
representing the Hotelling statistical loss for each data segment. Further optionally, the matrix reconstruction error cost corresponding to each data segment is determined according to the following formulaQ：
Figure BDA0002818715180000044
Figure BDA0002818715180000045
Wherein I represents a unit vector, Ui,pAnd representing a characteristic vector matrix obtained by taking each segmented data segment as a multivariate time sequence segment and reducing the dimension of an autocovariance matrix of the multivariate time sequence segment. Illustratively, the dimensionality reduction method may be Principal Component Analysis (PCA). Si(ai，bi) Representing each of the divided data segments, i.e. each of the divided multivariate time series, ai，biA represents the divided multivariate time seriesiPoint to point biAnd (4) points.
Alternatively, each data is determined according to the following formulaHotelling statistical loss cost of fragmentsT 2：
Figure BDA0002818715180000051
Wherein S isi(ai，bi) Representing each of the divided data segments, i.e. each of the divided multivariate time series, ai，biA represents the divided multivariate time seriesiPoint to point biAnd (4) points. Is determined according to the following formula
Figure BDA0002818715180000058
Figure BDA0002818715180000053
Wherein x iskRepresenting the data vectors acquired at the kth time point in each of the segmented multivariate time series,
Figure BDA0002818715180000054
representing the division of each dimension of the matrix by the eigenvalues.
1022. And fusing the data segments based on the loss function of each data segment to obtain fused data segments.
Optionally, fusing the data segments based on the loss function of each data segment, and obtaining the fused data segment includes but is not limited to:
1022-1, searching the data segment with the minimum loss function based on the loss function of each data segment as a first data segment;
1022-2, comparing the loss functions of the left and right segments of the data segment based on the data segment with the minimum loss function, and taking the data segment with the small loss function as a second data segment;
1022-3, fusing the first data fragment and the second data fragment to obtain a fused partial data fragment and an unfused residual data fragment;
1022-4, repeating the steps 1022-1 to 1022-3 for the fused partial data segment and the unfused residual data segment until the fused partial data segment and the unfused residual data segment are fused to the second segment number, so as to obtain the fused data segment. Further optionally, the second segment number represents a total number of final fused data segments, based on an empirical setting.
And 103, acquiring the working condition type based on the fused data fragments.
In one possible implementation method, based on the fused data segment, the obtaining of the operation type includes, but is not limited to, the following sub-steps:
1031. and acquiring the distance between the fused data fragments.
Optionally, the distance d (X) between the fused data segments is obtained according to the following formulan,Yn)：
Figure BDA0002818715180000055
Wherein, Xn、YnRespectively representing two fused data segments. Further alternatively, it is calculated according to the following formula
Figure BDA0002818715180000056
Figure BDA0002818715180000057
Wherein the content of the first and second substances,
Figure BDA0002818715180000061
each represents Xn、YnCharacteristic value of two fused data segments, thetai,jRepresents XnOf the ith main direction and YnIs included between the jth main directions.
Optionally, other suitable distance measurement methods may also be selected according to different data segment characteristics, which is not limited in this embodiment of the present application.
1032. And clustering the fused data segments based on the distance between the fused data segments to obtain the clustered data segments.
And taking the fused data segments as a multivariate time sequence, and optionally clustering the fused data segments by using a density clustering method aiming at the multivariate time sequence.
Illustratively, Based on the distance between the fused data segments, the fused data segments are clustered using a Noise-Based Spatial Clustering of Applications with Noise (DBSCAN), resulting in clustered data segments.
1033. And acquiring the working condition type based on the clustered data segments.
And taking each clustered data segment as a working condition type to obtain different working condition types.
And 104, detecting the state of the dehydration device based on the working condition type.
In one implementation, based on the type of operating condition, detecting the state of the dehydration engine includes, but is not limited to, the following sub-steps:
1041. and establishing a state prediction model of each working condition type based on the working condition types.
Alternatively, different state prediction models may be established for different operating condition types. In one example, the state prediction model is a hidden markov model, which can predict the feature values at the next time according to the feature values at the previous time.
Optionally, according to actual needs, the state prediction model may also be a fault diagnosis model or other prediction models, such as various prediction diagnosis models based on a neural network or other machine learning methods, and the like, which is not limited in this embodiment of the present application.
1042. And acquiring central data of each working condition type.
In one example, obtaining central data for each operating condition type includes: in the same working condition, cubic spline dynamic time programming (CDTW) is carried out on the same characteristic in different time periods, and central data of each working condition type is obtained.
Optionally, this example includes, but is not limited to, the following sub-steps:
1042-1 in the same working condition, according to the time sequence, taking the data segments corresponding to the first two time segments as the first data segment and the second data segment respectively;
1042-2 obtaining a two-dimensional coordinate path by using a Dynamic Time Warping (DTW) algorithm on the same feature of the first data segment and the second data segment;
1042-3 averaging the two-dimensional coordinate paths, setting a new sequence, taking the obtained two-dimensional coordinate path average as a sequence index, and taking the average of the values corresponding to the sequence index as a sequence value to obtain the new sequence;
1042-4 interpolating the new sequence by using a cubic spline curve, and sampling from 0 by adding 1 every time, wherein the number of sampling points is consistent with the number of indexes to obtain new sampling data points;
1042-5 taking the new sampled data point as the first data segment, taking the data segments corresponding to other time segments in the same working condition as the second data segment, using the same method to do CDTW operation and repeating the operation until only one unary sequence is obtained, and using the same method to do CDTW operation for each feature until only one multivariate time sequence is obtained, called central data, and each working condition corresponds to one such central data.
For example, for two sequences of the same feature: x ═ 2,0,1,1,2,4,2,1,2,0], y ═ 1,1,2,4,2,1,2,0], and DTW operations are performed on the two sequences to obtain a two-dimensional coordinate path: [(0,0),(1,0),(2,0),(3,1),(4,2),(5,3),(6,4),(7,5),(8,6),(9,7)]. Wherein the two-dimensional coordinate path starts from (0, 0). Averaging the two-dimensional coordinate path to obtain: [0,0.5,1,2,3,4,5,6,7,8], taking the two-dimensional coordinate path average value as a sequence index, wherein the average value of the values corresponding to the sequence index is: [1.5,0.5,1,1,2,4,2,1,2,0]. The new sequence is interpolated by using a cubic spline curve, sampling is carried out in a mode of adding 1 from 0, the number of sampling points is consistent with the number of indexes, namely sampling values corresponding to [0,1,2,3,4,5,6,7,8 and 9] to obtain new sampling data points, the new sampling data points are taken as first data segments, data segments corresponding to other time segments in the same working condition are taken as second data segments, the CDTW operation is carried out by using the same method and is continuously repeated until only one unary sequence is obtained, for each feature, the CDTW operation is carried out by using the same method until only one multivariate time sequence is obtained, and the central data of a certain working condition is obtained by using the method.
Optionally, the central data of each operating condition type may also be obtained by using a mean value multivariate sequence method, which is not limited in this application embodiment.
1043. And inputting a new data segment, and acquiring the new data segment through a dehydration device.
1044. And acquiring a state prediction model of the new data segment based on the new data segment, the central data of each working condition type and the state prediction model of each working condition type.
Optionally, the distance between the new data segment and the central data of each working condition type is obtained according to the manner of obtaining the distance between the fused data segments, wherein the length of the new data segment is the average of the lengths of all the central data segments; classifying the new data segment based on the distance between the new data segment and the central data of each working condition type, acquiring the working condition to which the new data segment belongs, and selecting the state prediction model of the working condition as the state prediction model of the new data segment.
1045. And detecting the state of the dehydration device based on the state prediction model of the new data segment.
Optionally, the new data segment is predicted based on the state prediction model of the new data segment, the predicted state of the new data segment is determined, and the predicted state of the new data segment is used as the state detection result of the dehydration device.
The embodiment of the application uses the PCA data segmentation technology, and on the basis, the density-based clustering method is used for obtaining the working condition type, so that the condition that the data need not to be specified after clustering is ensured, and the working condition of the data can be determined by calculation in a self-adaptive manner. The embodiment of the application also establishes the state prediction models respectively aiming at different working conditions, after new data is obtained, the similarity degree between the new data and classified data is calculated, and then the used prediction model is determined, so that the state of the dehydration device is determined, and the problems of complex working state and inaccurate detection precision of the dehydration device are solved.
Referring to fig. 2, a schematic diagram of a state detection system 20 of a dewatering device according to an embodiment of the present application is shown, the system includes the following modules:
the initialization module 201 is configured to initialize and segment existing data, and obtain a segmented data segment. Optionally, the initialization module 201 is used for, but not limited to: carrying out standardization processing on the existing data to obtain a processed data characteristic vector; carrying out mean filtering on the processed data characteristic vector to obtain filtered data; and carrying out data segmentation on the filtered data to obtain segmented data fragments.
And the fusion module 202 is configured to obtain a fused data segment based on the segmented data segment. Optionally, the fusion module 202 is used for, but not limited to: obtaining a loss function of each data fragment based on the segmented data fragments; and fusing the data segments based on the loss function of each data segment to obtain fused data segments.
And the clustering module 203 is used for acquiring the working condition type based on the fused data segments. Optionally, clustering module 203 is used for, but not limited to: acquiring the distance between the fused data segments; clustering the fused data segments based on the distance between the fused data segments to obtain clustered data segments; and acquiring the working condition type based on the clustered data segments.
The prediction module 204 is configured to detect a state of the dehydration engine based on the type of operating condition. Optionally, the prediction module 204 is used for, but not limited to: establishing a state prediction model of each working condition type based on the working condition type; acquiring central data of each working condition type; inputting a new data segment, and acquiring the new data segment through a dehydration device; acquiring a state prediction model of the new data segment based on the new data segment, the central data of each working condition type and the state prediction model of each working condition type; and detecting the state of the dehydration device based on the state prediction model of the new data segment.
It should be understood that, when the system provided in fig. 2 is used to implement its functions, it is only illustrated by the above-mentioned division of the functional modules, and in practical applications, the above-mentioned function distribution may be performed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to perform all or part of the functions described above. In addition, the system and method embodiments provided by the above embodiments belong to the same concept, and specific implementation processes thereof are described in the method embodiments for details, which are not described herein again.
In an exemplary embodiment, there is also provided a computer-readable storage medium having at least one program code stored therein, the at least one program code being loaded and executed by a processor to cause a computer to implement any one of the above-described state detection methods of a dehydration engine.
Alternatively, the computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a Compact Disc Read-Only Memory (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, there is also provided a computer program or a computer program product having at least one computer instruction stored therein, the at least one computer instruction being loaded and executed by a processor to cause a computer to implement the state detection method of any one of the above-mentioned dehydration apparatuses.
In the several embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. For example, the system embodiments described above are merely illustrative, and for example, the division of the module is merely a logical division, and the actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may also be an electrical, mechanical or other form of connection.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present application.
In addition, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
It should also be understood that, in the embodiments of the present application, the size of the serial number of each process does not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
The term "at least one" in this application means one or more, and the term "plurality" in this application means two or more, for example, a plurality of data means two or more data.
It is to be understood that the terminology used in the description of the various described examples herein is for the purpose of describing particular examples only and is not intended to be limiting. As used in the description of the various described examples and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The above description is only exemplary of the present application and is not intended to limit the present application, and any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims (10)

1. A method of detecting a state of a dehydration engine, said method comprising:
initializing and segmenting existing data, and acquiring segmented data segments;
acquiring a fused data segment based on the segmented data segment;
acquiring a working condition type based on the fused data segment;
and detecting the state of the dewatering device based on the working condition type.
2. The method of claim 1, wherein the initializing segmentation of the existing data and obtaining the segmented data segments comprises:
carrying out standardization processing on the existing data to obtain a processed data characteristic vector;
carrying out mean value filtering on the processed data characteristic vector to obtain filtered data;
and carrying out data segmentation on the filtered data to obtain segmented data segments.
3. The method of claim 1, wherein obtaining the fused data segment based on the segmented data segment comprises:
obtaining a loss function of each data segment based on the segmented data segments;
and fusing the data segments based on the loss function of each data segment to obtain fused data segments.
4. The method according to claim 1, wherein obtaining the type of the operating condition based on the fused data segment comprises:
acquiring the distance between the fused data fragments;
clustering the fused data segments based on the distance between the fused data segments to obtain clustered data segments;
and acquiring the working condition type based on the clustered data segments.
5. The method according to any of claims 1-4, wherein said detecting a state of a dewatering device based on said type of operating condition comprises:
establishing a state prediction model of each working condition type based on the working condition types;
acquiring central data of each working condition type;
inputting a new data segment, wherein the new data segment is acquired through a dehydration device;
acquiring a state prediction model of the new data segment based on the new data segment, the central data of each working condition type and the state prediction model of each working condition type;
and detecting the state of the dehydration device based on the state prediction model of the new data segment.
6. A system for detecting the condition of a dehydration engine, said system comprising:
the initialization module is used for initializing and segmenting the existing data and acquiring segmented data segments;
the fusion module is used for acquiring fused data fragments based on the segmented data fragments;
the clustering module is used for acquiring the working condition type based on the fused data segments;
and the prediction module is used for detecting the state of the dehydration device based on the working condition type.
7. The system of claim 6, wherein the initialization module is configured to perform normalization processing on the existing data to obtain a processed data feature vector; carrying out mean value filtering on the processed data characteristic vector to obtain filtered data; and carrying out data segmentation on the filtered data to obtain segmented data segments.
8. The system according to claim 6, wherein the fusion module is configured to obtain a loss function for each data segment based on the segmented data segments; and fusing the data segments based on the loss function of each data segment to obtain fused data segments.
9. The system of claim 6, wherein the clustering module is configured to obtain a distance between the fused data segments; clustering the fused data segments based on the distance between the fused data segments to obtain clustered data segments; and acquiring the working condition type based on the clustered data segments.
10. The system of any one of claims 6-9, wherein the prediction module is configured to establish a state prediction model for each operating condition type based on the operating condition type; acquiring central data of each working condition type; inputting a new data segment, wherein the new data segment is acquired through a dehydration device; acquiring a state prediction model of the new data segment based on the new data segment, the central data of each working condition type and the state prediction model of each working condition type; and detecting the state of the dehydration device based on the state prediction model of the new data segment.
CN202011415064.XA 2020-12-04 2020-12-04 Method and system for detecting state of dewatering device Pending CN114596458A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011415064.XA CN114596458A (en) 2020-12-04 2020-12-04 Method and system for detecting state of dewatering device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011415064.XA CN114596458A (en) 2020-12-04 2020-12-04 Method and system for detecting state of dewatering device

Publications (1)

Publication Number Publication Date
CN114596458A true CN114596458A (en) 2022-06-07

Family

ID=81802346

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011415064.XA Pending CN114596458A (en) 2020-12-04 2020-12-04 Method and system for detecting state of dewatering device

Country Status (1)

Country Link
CN (1) CN114596458A (en)

Similar Documents

Publication Publication Date Title
EP1960853B1 (en) Evaluating anomaly for one-class classifiers in machine condition monitoring
KR100247969B1 (en) Apparatus and method for massive pattern matching
CN116126945B (en) Sensor running state analysis method and system based on data analysis
US7716152B2 (en) Use of sequential nearest neighbor clustering for instance selection in machine condition monitoring
CN106021826A (en) Method for predicting complete residual life of aero-engine under variable working conditions based on working condition identification and similarity matching
JP7320885B2 (en) Systems, methods and media for manufacturing processes
CN111190804A (en) Multi-level deep learning log fault detection method for cloud native system
CN110570544A (en) method, device, equipment and storage medium for identifying faults of aircraft fuel system
CN113438114B (en) Method, device, equipment and storage medium for monitoring running state of Internet system
CN111612037A (en) Abnormal user detection method, device, medium and electronic equipment
CN115221516B (en) Malicious application program identification method and device, storage medium and electronic equipment
CN113807418A (en) Injection molding machine energy consumption abnormity detection method and system based on Gaussian mixture model
CN114861788A (en) Load abnormity detection method and system based on DBSCAN clustering
CN116304909A (en) Abnormality detection model training method, fault scene positioning method and device
CN114662602A (en) Outlier detection method and device, electronic equipment and storage medium
CN114020811A (en) Data anomaly detection method and device and electronic equipment
CN113255752A (en) Solid material consistency sorting method based on feature clustering
CN112422546A (en) Network anomaly detection method based on variable neighborhood algorithm and fuzzy clustering
US11048730B2 (en) Data clustering apparatus and method based on range query using CF tree
CN114596458A (en) Method and system for detecting state of dewatering device
WO2023231374A1 (en) Semi-supervised fault detection and analysis method and apparatus for mechanical device, terminal, and medium
CN115329082A (en) Log sequence anomaly detection method based on deep hybrid neural network
CN114021118A (en) Multi-element behavior detection method, system and medium based on super-fusion server system
CN112906751A (en) Method for identifying abnormal value through unsupervised learning
Djukova Discrete (Logic) Recognition Procedures: Principles of Construction, Complexity of Realization, and Basic Models

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