[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN110736968A - Radar abnormal state diagnosis method based on deep learning - Google Patents

Radar abnormal state diagnosis method based on deep learning Download PDF

Info

Publication number
CN110736968A
CN110736968A CN201910981582.9A CN201910981582A CN110736968A CN 110736968 A CN110736968 A CN 110736968A CN 201910981582 A CN201910981582 A CN 201910981582A CN 110736968 A CN110736968 A CN 110736968A
Authority
CN
China
Prior art keywords
model
value
faults
reconstruction
radar
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.)
Granted
Application number
CN201910981582.9A
Other languages
Chinese (zh)
Other versions
CN110736968B (en
Inventor
刘井泉
解光耀
曾聿赟
张昊宇
刘正藩
秦楚晴
杨辉
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.)
Shanghai Xiangtong Petrochemical Technology Co Ltd
Tsinghua University
Original Assignee
Shanghai Xiangtong Petrochemical Technology Co Ltd
Tsinghua University
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 Shanghai Xiangtong Petrochemical Technology Co Ltd, Tsinghua University filed Critical Shanghai Xiangtong Petrochemical Technology Co Ltd
Priority to CN201910981582.9A priority Critical patent/CN110736968B/en
Publication of CN110736968A publication Critical patent/CN110736968A/en
Application granted granted Critical
Publication of CN110736968B publication Critical patent/CN110736968B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
    • G01S7/02—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S13/00
    • G01S7/40—Means for monitoring or calibrating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

The invention discloses an radar abnormal state diagnosis method based on deep learning, which comprises the following steps of utilizing historical state data and alarm data of all subsystems of a meteorological radar system, taking the alarm data as labels, classifying faults, extracting characteristic parameters related to each faults by using a stepwise regression method, taking the characteristic parameter with the largest correlation coefficient in the characteristic parameters of each faults as a reconstruction parameter target of a reconstruction model, building the reconstruction model by using a long-and-short-term memory network LSTM model, utilizing the characteristic parameters except the characteristic parameter with the largest correlation coefficient to perform fitting reconstruction on the characteristic parameter with the largest correlation coefficient to obtain a reconstruction value, making probability-based quantization standards for the difference value between the reconstruction value and an actual measurement value of each faults, making time interval statistics for the quantization results of each faults, integrating the diagnosis results of different models to obtain real-time multiple fault diagnosis results, giving early warning, filtering and obtaining a final diagnosis result.

Description

Radar abnormal state diagnosis method based on deep learning
Technical Field
The invention belongs to the technical field of radar systems, and particularly relates to radar abnormal state diagnosis methods based on deep learning.
Background
The natural weather radar system in use at present is relatively complex electronic systems, including a transmitter subsystem, a receiver subsystem and a servo subsystem, and all electronic parameters of each subsystem are not physically connected, so that the electronic parameters reflected by faults are not physically connected, and the fault diagnosis and prediction of the natural weather radar system cannot be carried out by utilizing the traditional expert experience.
Disclosure of Invention
In view of the above-mentioned technical problems, the present invention is directed to providing methods for diagnosing abnormal states of radar based on deep learning.
In order to solve the technical problems, the invention adopts the following technical scheme:
A radar abnormal state diagnosis method based on deep learning, which is applied to a meteorological radar system comprising a transmitter subsystem, a receiver subsystem and a servo subsystem, and comprises the following steps:
the method comprises the steps of utilizing historical state data and alarm data of all subsystems of a meteorological radar system, using the alarm data as labels, classifying faults, and extracting characteristic parameters related to each types of faults by using a stepwise regression method;
taking the characteristic parameter with the maximum correlation coefficient in the characteristic parameters of each -type faults as a reconstruction parameter target of a reconstruction model, building the reconstruction model by using a long-time memory network (LSTM) model, and performing fitting reconstruction on the characteristic parameter with the maximum correlation coefficient by using the characteristic parameters except the characteristic parameter with the maximum correlation coefficient to obtain a reconstruction value;
making probability-based quantification standard for the difference value between the reconstructed value and the measured value of each types of faults;
and carrying out time interval statistics on the quantitative result of each type fault, integrating the diagnosis results of different models to obtain a plurality of real-time fault diagnosis results, giving early warning, filtering false alarms and obtaining a final diagnosis result.
Preferably, for each types of faults, the probability-based quantification criterion of the difference between the reconstructed value and the measured value further includes:
analyzing the distribution condition of the measured values, and if a plurality of running states exist, superposing the plurality of Gaussian distributions;
assuming that the predicted value and the measured value are independent, if the predicted value obeys Gaussian distribution, and assuming that the radar operating state is normal, the measured value should obey the Gaussian distribution, and the difference value between the two obeys N (0,2 sigma ^2) distribution;
and (3) performing grouping processing on the probability of the difference to obtain a final quantization result:
Figure BDA0002235359160000021
if the predicted value is equal to the measured value, η is equal to 1, and the more the predicted value deviates from the measured value, the closer η is to 0.
Preferably, for each types of faults, performing time interval statistics on the quantized result, filtering false alarms, and obtaining a final diagnosis result further includes:
setting a probability decision threshold ηo，η＜ηoA fault condition point is considered to occur;
and (5) performing time interval statistics by using m continuous time points, and determining that a fault occurs when the fault state point is greater than 0.3 m.
Preferably, the stepwise regression method is a forward-introduction method, and specifically, only independent variables with the largest variation of the dependent variable are added into the model firstly, then another independent variables are added in an attempt, whether the variation of the dependent variable which can be explained by the whole model is obviously increased is checked, and iteration is repeated until no independent variable meets the condition of adding the model.
Preferably, the stepwise regression method is a backward elimination method, and specifically comprises the steps of putting all variables into a model, then trying to eliminate independent variables from the model, checking whether variation of the whole model interpretation dependent variable has significant change, eliminating the variables which reduce the interpretation quantity to the minimum, and repeating iteration until no independent variable meets the elimination condition.
Preferably, the stepwise regression method is a two-way elimination method, and specifically, independent variables with the largest variation of the dependent variable are added into the model firstly, then another independent variables are added in an attempt, all the variables in the whole model are checked, if the dependent variable is increased significantly, the independent variable is retained, the variable with insignificant effect is eliminated, and iteration is repeated until optimal variable combinations are obtained finally.
Preferably, the process of building the reconstruction model by using the long-term memory network LSTM model is as follows:
forgetting gammafNonlinear activation of cells read a<t-1>And input data x of the current LSTM cell<t> values between 0 and 1 are output to each of the LSTM cell states c<t-1>Wherein 1 represents "completely retained", and 0 represents "completely discarded";
input ΓuFor the sigmoid layer, which is used to decide the values that need to be updated, the tanh layer is used to create new candidate value vectors
Figure BDA0002235359160000031
Updated vector c<t>Determined by both input and forget ;
output ΓoDetermining the output value, running sigmoid layer gamma to determine which part of LSTM cell state will be output, and outputting cell state c<t>Processing by tanh gives values between-1 and adds it to the output ΓoThe outputs of (a) are multiplied to finally output a part of the determined output.
The invention has the following beneficial effects: the method has the advantages that multiple faults are diagnosed aiming at faults of all subsystems of the natural weather radar, combination of multiple faults can be judged, possible faults can be predicted in advance, and false alarms can be filtered under the condition that the existing radar frequently gives an invalid alarm.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for diagnosing abnormal states of a radar based on deep learning according to an embodiment of the present invention;
FIG. 2 is a flowchart of the steps of diagnosing a subsystem of a radar transmitter in the method for diagnosing an abnormal radar state based on deep learning according to an embodiment of the present invention
FIG. 3 is a schematic diagram of a diagnostic operational state of a radar transmitter subsystem as a superposition of a plurality of Gaussian distributions;
FIG. 4 is a schematic flow chart of the LSTM algorithm for diagnosis of a radar transmitter subsystem;
FIG. 5 is a schematic diagram of a diagnostic LSTM structure of a radar transmitter subsystem.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all embodiments of the present invention.
The embodiment of the invention provides radar abnormal state diagnosis methods based on deep learning, which are applied to a meteorological radar system comprising a transmitter subsystem, a receiver subsystem and a servo subsystem and comprise the following steps:
the method comprises the steps of utilizing historical state data and alarm data of all subsystems of a meteorological radar system, using the alarm data as labels, classifying faults, and extracting characteristic parameters related to each types of faults by using a stepwise regression method;
taking the characteristic parameter with the maximum correlation coefficient in the characteristic parameters of each -type faults as a reconstruction parameter target of a reconstruction model, building the reconstruction model by using a long-time memory network (LSTM) model, and performing fitting reconstruction on the characteristic parameter with the maximum correlation coefficient by using the characteristic parameters except the characteristic parameter with the maximum correlation coefficient to obtain a reconstruction value;
making probability-based quantification standard for the difference value between the reconstructed value and the measured value of each types of faults;
and carrying out time interval statistics on the quantitative result of each type fault, integrating the diagnosis results of different models to obtain a plurality of real-time fault diagnosis results, giving early warning, filtering false alarms and obtaining a final diagnosis result.
Referring to fig. 1, which is a schematic flow chart corresponding to the radar abnormal state diagnosis method based on deep learning in the embodiment of the present invention, the method includes acquiring device state time series data of each subsystem of the meteorological radar system, performing type 1 fault feature parameter extraction, type 2 fault feature parameter extraction, to type N fault feature parameter extraction, then taking the feature parameter with the largest correlation coefficient in the feature parameters for each faults as a reconstruction parameter target of a reconstruction model, building the reconstruction model using a long-and-short memory network LSTM model, obtaining a reconstruction model 1, reconstructing models 2 to N, and performing a probability-based quantization standard on a difference value between a reconstruction value and an actual measurement value of each faults, to obtain a classified fault discrimination result, that is, a type 1 fault discrimination result, a type 2 fault discrimination result to a type N fault discrimination result, and further obtaining a device state overall recognition result of the whole meteorological radar system according to the various fault discrimination results.
The abnormal state diagnosis process is further illustrated in step by taking a radar transmitter subsystem as an example, so that those skilled in the art can better understand the implementation process of the method of the present invention.
Referring to fig. 2, a flow chart of steps of a method for fault diagnosis of a subsystem of a radar transmitter is shown, comprising the steps of:
s10, using the historical state data and alarm data of the radar transmitter subsystem, using the alarm data as labels, using stepwise regression method to extract n characteristic parameters related to the fault of the transmitter subsystem, considering that if the characteristic parameters are changed significantly, the health state of the transmitter is changed, because the characteristic parameters are the key information extracted from the state variables of the system, the key information can accurately represent the state of the system, if the operation state of the system is changed, the key information is directly reflected on the change of the state variables, and the characteristic parameters show the change more significantly.
The historical state data can comprise radar state data of all nationwide sites in the historical year, data points are collected every time intervals, each data point comprises a plurality of variable parameters, the alarm data comprises alarm time and alarm classification numbers, and in a specific application example, the characteristic parameters can comprise horizontal channel antenna peak power, transmitter peak power, transmission and antenna power ratio, horizontal channel antenna power zero setting, transmitter power zero setting, reflectivity expected value, short pulse system calibration constant, long pulse system calibration constant, speed expected value 4, speed measured value 4, KD calibration expected value, KD calibration measured value, horizontal channel power before filtering and horizontal channel power after filtering.
In S10, Forward selection, Backward elimination and Bidirectional elimination can be used as the stepwise regression, and a detailed implementation of the stepwise regression is described in below.
If the forward-run method is used, only independent arguments with the largest dependent variable variation are added to the model, then another independent variables are added in an attempt, whether the dependent variable variation which can be explained by the whole model is remarkably increased or not is checked (F-test, t-test and the like), and iteration is repeated until no independent variable meets the condition of adding the model.
If a backward elimination method is used, as opposed to the forward introduction method, where all variables are put into the model, then of the independent variables are tried to be eliminated from the model, the variation of the model interpretation dependent variables is checked to see if there is a significant variation, the variables with the least reduction in interpretation are eliminated, and iteration is repeated until no independent variable meets the elimination condition.
If the two-way elimination method is used, in order to combine the forward introduction method and the backward elimination method, independent variables with the largest variation of the independent variables are added into the model firstly, then additional independent variables are added in an attempt, all the variables in the whole model are checked, if the dependent variables are obviously increased, the independent variables are kept, the variables with the insignificant effects are eliminated, and iteration is repeated until optimal variable combinations are finally obtained.
S20, taking the characteristic parameter y ( is the peak power of the transmitter or the peak power of the horizontal channel antenna in general) with the maximum correlation coefficient in the characteristic parameters as the reconstruction parameter target of the reconstruction model, building the reconstruction model by using a Long and short Memory Network (LSTM) model, and fitting and reconstructing y by using n-1 characteristic parameters except the characteristic parameter y to obtain a reconstruction value
As shown in fig. 4 and 5, when the reconstruction model is constructed using the LSTM model, time-series state data X ═ X is input(1),…,X(m)Outputting a reconstructed parameter value Y ═ Y through a long-time memory network LSTM(1),…,Y(m)}. wherein the LSTM comprises forget :' Ff＝σ(Wf[a<t-1>，x<t>]+bf) Input (update ) Fu＝σ(Wu[a<t-1>，x<t>]+bu) (ii) a Updating the candidate value:
Figure BDA0002235359160000061
output gammao＝σ(Wo[a<t-1>，x<t>]+bo) (ii) a Updating the value:nonlinear activation: a is<t>＝Γo×tanhc<t>. The calculation process is as follows:
forgetting gammafNon-linear activation of cells read a<t-1>And input data x of the current LSTM cell<t>Outputting values between 0 and 1 to each LSTM ticketMeta state c<t+1>The numbers in (1). 1 means "complete retention" and 0 means "complete discard".
Input ΓuIt is sigmoid layers that decide what values to update then tanh layers are used to create new candidate vectors
Figure BDA0002235359160000063
Updated vector c<t>Determined by both the input and the forgetting .
Output ΓoThe output value is determined by first running sigmoid layers Γ to determine which portion of the LSTM cell state will be output<t>Processed by tanh (to obtain values between-1 and 1) and output ΓoWill eventually output only that portion of the determined output.
S30, to the reconstruction value
Figure BDA0002235359160000065
And the difference value of the measured value y is used as a probability-based quantification standard.
In a specific application example, S30 may further include step :
and i, analyzing the distribution of y, and if a plurality of operating states exist, superposing a plurality of Gaussian distributions. As shown in fig. 3, the distribution of the peak power of the transmitter is a superposition of two gaussian distributions, less than 300 obeying the (1) distribution and more than 300 obeying the (2) distribution.
And ii, assuming that the predicted value and the measured value are independent, if the predicted value is subjected to (1) distribution, and assuming that the radar operating state is normal, the measured value is also subjected to (1) distribution, and the difference value of the two is subjected to N (0,2 sigma ^2) distribution.
And iii, performing grouping treatment on the probability of the difference to obtain a final quantification result:if the predicted value is equal to the measured value, η is equal to 1, and the more the predicted value deviates from the measured value, the closer η is to 0.
And S40, carrying out time interval statistics on the quantized result, and filtering false alarms to obtain a final diagnosis result.
In a specific application example, S40 may further include step :
setting a probability decision threshold η0，η＜η0Deeming transmitter to be a fault condition point
And ii, taking m continuous time points as time interval statistics, and considering that a fault occurs when the fault state point is greater than 0.3 m.
Although or more embodiments of the present invention have been described in connection with the accompanying drawings, it will be understood by those of ordinary skill in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the following claims.

Claims (7)

  1. The method for diagnosing the abnormal state of the radar based on deep learning is characterized by being applied to a meteorological radar system comprising a transmitter subsystem, a receiver subsystem and a servo subsystem and comprising the following steps of:
    the method comprises the steps of utilizing historical state data and alarm data of all subsystems of a meteorological radar system, using the alarm data as labels, classifying faults, and extracting characteristic parameters related to each types of faults by using a stepwise regression method;
    taking the characteristic parameter with the maximum correlation coefficient in the characteristic parameters of each -type faults as a reconstruction parameter target of a reconstruction model, building the reconstruction model by using a long-time memory network (LSTM) model, and performing fitting reconstruction on the characteristic parameter with the maximum correlation coefficient by using the characteristic parameters except the characteristic parameter with the maximum correlation coefficient to obtain a reconstruction value;
    making probability-based quantification standard for the difference value between the reconstructed value and the measured value of each types of faults;
    and carrying out time interval statistics on the quantitative result of each type fault, integrating the diagnosis results of different models to obtain a plurality of real-time fault diagnosis results, giving early warning, filtering false alarms and obtaining a final diagnosis result.
  2. 2. The deep learning-based radar abnormal state diagnosis method of claim 1, wherein the probability-based quantization criterion for the difference between the reconstructed value and the measured value for each types of faults further steps comprise:
    analyzing the distribution condition of the measured values, and if a plurality of running states exist, superposing the plurality of Gaussian distributions;
    assuming that the predicted value and the measured value are independent, if the predicted value obeys Gaussian distribution, and assuming that the radar operating state is normal, the measured value should obey the Gaussian distribution, and the difference value between the two obeys N (0,2 sigma ^2) distribution;
    and (3) performing grouping processing on the probability of the difference to obtain a final quantization result:
    Figure FDA0002235359150000011
    if the predicted value is equal to the measured value, η is equal to 1, and the more the predicted value deviates from the measured value, the closer η is to 0.
  3. 3. The deep learning-based radar abnormal state diagnosis method as claimed in claim 1 or 2, wherein for each types of faults, time interval statistics is performed on the quantized result, false alarms are filtered out, and the step of obtaining a final diagnosis result further comprises:
    setting a probability decision threshold ηo，η＜η0A fault condition point is considered to occur;
    and (5) performing time interval statistics by using m continuous time points, and determining that a fault occurs when the fault state point is greater than 0.3 m.
  4. 4. The deep learning-based radar abnormal state diagnosis method as claimed in claim 1 or 2, wherein the stepwise regression method is a forward introduction method, and is characterized in that only independent variables with the largest interpretation dependent variable variation are added into the model firstly, then another independent variables are added in an attempt, whether the interpretation dependent variable variation of the whole model is increased remarkably or not is checked, and iteration is repeated until no independent variable meets the condition of adding the model.
  5. 5. The deep learning-based radar abnormal state diagnosis method as claimed in claim 1 or 2, wherein the stepwise regression method is a backward elimination method, and is characterized in that all variables are put into a model, independent variables are tried to be eliminated from the model, whether variation of an explanation dependent variable of the whole model has significant variation is checked, variables with minimum reduction of the explanation variable are eliminated, and iteration is repeated until no independent variable meets the elimination condition.
  6. 6. The method for diagnosing the abnormal state of the radar based on the deep learning of claim 1 or 2, wherein the stepwise regression method is a two-way elimination method, and is characterized in that independent arguments with the largest variation of the dependent variables are added into the model firstly, then additional arguments are added in an attempt, all the variables in the whole model are checked, if the dependent variables are increased remarkably, the independent variables are retained, the variables with the insignificant effects are eliminated, and iteration is repeated until optimal variable combinations are obtained finally.
  7. 7. The deep learning-based radar abnormal state diagnosis method as claimed in claim 1 or 2, wherein the process of building the reconstruction model by using the long-time memory network LSTM model comprises the following steps:
    forgetting gammafNonlinear activation of cells read a<t-1>And input data x of the current LSTM cell<t> values between 0 and 1 are output to each of the LSTM cell states c<t-1>Wherein 1 represents "completely retained", and 0 represents "completely discarded";
    input ΓuFor the sigmoid layer, which is used to decide the values that need to be updated, the tanh layer is used to create new candidate value vectors
    Figure FDA0002235359150000021
    Updated vector c<t>Determined by both input and forget ;
    output ΓoDetermining output value, operatingsigmoid layer Γ to determine which portion of the LSTM cell state will be output, cell state c<t>Processing by tanh gives values between-1 and adds it to the output ΓoThe outputs of (a) are multiplied to finally output a part of the determined output.
CN201910981582.9A 2019-10-16 2019-10-16 Radar abnormal state diagnosis method based on deep learning Active CN110736968B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910981582.9A CN110736968B (en) 2019-10-16 2019-10-16 Radar abnormal state diagnosis method based on deep learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910981582.9A CN110736968B (en) 2019-10-16 2019-10-16 Radar abnormal state diagnosis method based on deep learning

Publications (2)

Publication Number Publication Date
CN110736968A true CN110736968A (en) 2020-01-31
CN110736968B CN110736968B (en) 2021-10-08

Family

ID=69270085

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910981582.9A Active CN110736968B (en) 2019-10-16 2019-10-16 Radar abnormal state diagnosis method based on deep learning

Country Status (1)

Country Link
CN (1) CN110736968B (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112308391A (en) * 2020-10-22 2021-02-02 清华大学 Real-time monitoring and anomaly detection method for equipment state based on neural network
CN112325918A (en) * 2020-10-19 2021-02-05 中国电子科技集团公司第三十八研究所 State prediction processing system of standard instrument
CN112434930A (en) * 2020-11-20 2021-03-02 中国地质大学（武汉） Fault diagnosis method, system and equipment in drilling process
CN112461537A (en) * 2020-10-16 2021-03-09 浙江工业大学 Wind power gear box state monitoring method based on long-time neural network and automatic coding machine
CN113255965A (en) * 2021-04-26 2021-08-13 大连海事大学 Intelligent processing system for prognosis of degradation fault of radar transmitter
CN113419226A (en) * 2021-08-24 2021-09-21 四川锦美环保股份有限公司 Radar troubleshooting system
TWI771098B (en) * 2021-07-08 2022-07-11 國立陽明交通大學 Fault diagnosis system and method for state of radar system of roadside units
CN117648588A (en) * 2024-01-29 2024-03-05 和尘自仪(嘉兴)科技有限公司 Meteorological radar parameter anomaly identification method based on correlation network graph cluster analysis

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9075713B2 (en) * 2012-05-24 2015-07-07 Mitsubishi Electric Research Laboratories, Inc. Method for detecting anomalies in multivariate time series data
US9519049B1 (en) * 2014-09-30 2016-12-13 Raytheon Company Processing unknown radar emitters
CN107491792A (en) * 2017-08-29 2017-12-19 东北大学 Feature based maps the electric network fault sorting technique of transfer learning
CN107560844A (en) * 2017-07-25 2018-01-09 广东工业大学 A kind of fault diagnosis method and system of gearbox of wind turbine
CN108197648A (en) * 2017-12-28 2018-06-22 华中科技大学 A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on LSTM deep learning models
WO2018136915A1 (en) * 2017-01-23 2018-07-26 Nrg Systems, Inc. System and methods of novelty detection using non-parametric machine learning
CN108875913A (en) * 2018-05-30 2018-11-23 江苏大学 A kind of matsutake Fast nondestructive evaluation system and method based on convolutional neural networks
CN109856969A (en) * 2018-11-06 2019-06-07 皖西学院 A kind of failure prediction method and forecasting system based on BP neural network model
US20190179026A1 (en) * 2017-12-13 2019-06-13 Luminar Technologies, Inc. Adjusting area of focus of vehicle sensors by controlling spatial distributions of scan lines
CN109934337A (en) * 2019-03-14 2019-06-25 哈尔滨工业大学 A kind of detection method of the spacecraft telemetry exception based on integrated LSTM
CN110007355A (en) * 2019-04-15 2019-07-12 中国科学院电子学研究所 The detection method and device of a kind of convolution self-encoding encoder and interior of articles exception
CN110221302A (en) * 2019-05-24 2019-09-10 上海高智科技发展有限公司 Environmental detection device and its modification method, system, portable equipment and storage medium
CN110263846A (en) * 2019-06-18 2019-09-20 华北电力大学 The method for diagnosing faults for being excavated and being learnt based on fault data depth
CN110286361A (en) * 2019-07-08 2019-09-27 电子科技大学 Radar transmitter failure prediction method based on SNR degradation model and particle filter

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9075713B2 (en) * 2012-05-24 2015-07-07 Mitsubishi Electric Research Laboratories, Inc. Method for detecting anomalies in multivariate time series data
US9519049B1 (en) * 2014-09-30 2016-12-13 Raytheon Company Processing unknown radar emitters
WO2018136915A1 (en) * 2017-01-23 2018-07-26 Nrg Systems, Inc. System and methods of novelty detection using non-parametric machine learning
CN107560844A (en) * 2017-07-25 2018-01-09 广东工业大学 A kind of fault diagnosis method and system of gearbox of wind turbine
CN107491792A (en) * 2017-08-29 2017-12-19 东北大学 Feature based maps the electric network fault sorting technique of transfer learning
US20190179026A1 (en) * 2017-12-13 2019-06-13 Luminar Technologies, Inc. Adjusting area of focus of vehicle sensors by controlling spatial distributions of scan lines
CN108197648A (en) * 2017-12-28 2018-06-22 华中科技大学 A kind of Fault Diagnosis Method of Hydro-generating Unit and system based on LSTM deep learning models
CN108875913A (en) * 2018-05-30 2018-11-23 江苏大学 A kind of matsutake Fast nondestructive evaluation system and method based on convolutional neural networks
CN109856969A (en) * 2018-11-06 2019-06-07 皖西学院 A kind of failure prediction method and forecasting system based on BP neural network model
CN109934337A (en) * 2019-03-14 2019-06-25 哈尔滨工业大学 A kind of detection method of the spacecraft telemetry exception based on integrated LSTM
CN110007355A (en) * 2019-04-15 2019-07-12 中国科学院电子学研究所 The detection method and device of a kind of convolution self-encoding encoder and interior of articles exception
CN110221302A (en) * 2019-05-24 2019-09-10 上海高智科技发展有限公司 Environmental detection device and its modification method, system, portable equipment and storage medium
CN110263846A (en) * 2019-06-18 2019-09-20 华北电力大学 The method for diagnosing faults for being excavated and being learnt based on fault data depth
CN110286361A (en) * 2019-07-08 2019-09-27 电子科技大学 Radar transmitter failure prediction method based on SNR degradation model and particle filter

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
KYLE HUNDMAN 等: "Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding", 《PROCEEDINGS OF THE 24TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING》 *
YANGJING 等: "Long short-term memory neural network based fault detection and isolation for electro-mechanical actuators", 《NEUROCOMPUTING》 *
YUYUN ZENG 等: "A STATISTICAL MODEL FOR ACCESSING WALL THINNING RATE DUE TO FLOW ACCELERATED CORROSION BASED ON INSPECTION DATA IN NUCLEAR POWER PLANTS", 《PROCEEDINGS OF THE 2014 22ND INTERNATIONAL CONFERENCE ON NUCLEAR ENGINEERING》 *
王新颖 等: "深度学习神经网络在管道故障诊断中的应用研究", 《安全与环境工程》 *
解光耀 等: "PHM技术在核电厂的应用与展望", 《核动力工程》 *
郭彦杰: "基于循环神经网络的脉搏信号分析研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
陈畅 等: "基于LSTM网络预测的水轮机机组运行状态检测", 《山东大学学报(工学版)》 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112461537A (en) * 2020-10-16 2021-03-09 浙江工业大学 Wind power gear box state monitoring method based on long-time neural network and automatic coding machine
CN112325918A (en) * 2020-10-19 2021-02-05 中国电子科技集团公司第三十八研究所 State prediction processing system of standard instrument
CN112308391A (en) * 2020-10-22 2021-02-02 清华大学 Real-time monitoring and anomaly detection method for equipment state based on neural network
CN112434930A (en) * 2020-11-20 2021-03-02 中国地质大学（武汉） Fault diagnosis method, system and equipment in drilling process
CN112434930B (en) * 2020-11-20 2023-08-08 中国地质大学（武汉） Drilling process fault diagnosis method, system and equipment
CN113255965A (en) * 2021-04-26 2021-08-13 大连海事大学 Intelligent processing system for prognosis of degradation fault of radar transmitter
CN113255965B (en) * 2021-04-26 2024-09-13 大连海事大学 Intelligent radar transmitter degradation fault prognosis processing system
TWI771098B (en) * 2021-07-08 2022-07-11 國立陽明交通大學 Fault diagnosis system and method for state of radar system of roadside units
CN113419226A (en) * 2021-08-24 2021-09-21 四川锦美环保股份有限公司 Radar troubleshooting system
CN117648588A (en) * 2024-01-29 2024-03-05 和尘自仪(嘉兴)科技有限公司 Meteorological radar parameter anomaly identification method based on correlation network graph cluster analysis
CN117648588B (en) * 2024-01-29 2024-04-26 和尘自仪(嘉兴)科技有限公司 Meteorological radar parameter anomaly identification method based on correlation network graph cluster analysis

Also Published As

Publication number Publication date
CN110736968B (en) 2021-10-08

Similar Documents

Publication Publication Date Title
CN110736968B (en) Radar abnormal state diagnosis method based on deep learning
CN110348150B (en) Fault detection method based on correlation probability model
CN117421684B (en) Abnormal data monitoring and analyzing method based on data mining and neural network
CN113671917B (en) Detection method, system and equipment for abnormal state of multi-modal industrial process
CN112414694B (en) Equipment multistage abnormal state identification method and device based on multivariate state estimation technology
CN114023399A (en) Air particulate matter analysis early warning method and device based on artificial intelligence
CN113568774A (en) Real-time anomaly detection method for multi-dimensional time sequence data by using unsupervised deep neural network
CN115470850A (en) Water quality abnormal event recognition early warning method based on pipe network water quality time-space data
CN113598784B (en) Arrhythmia detection method and system
CN112488142A (en) Radar fault prediction method and device and storage medium
CN116684878B (en) 5G information transmission data safety monitoring system
CN113988210A (en) Method and device for restoring distorted data of structure monitoring sensor network and storage medium
CN117290726A (en) CAE-BiLSTM-based fault early warning method for mobile equipment
US11668857B2 (en) Device, method and computer program product for validating data provided by a rain sensor
CN115687322A (en) Water quality time series missing data completion method based on encoder-decoder and autoregressive generated countermeasure network
CN111353640A (en) Method for constructing wind speed prediction model by combination method
CN118282780B (en) New energy automobile vehicle-mounted network intrusion detection method, equipment and storage medium
CN117077870B (en) Water resource digital management method based on artificial intelligence
CN112365093A (en) GRU deep learning-based multi-feature factor red tide prediction model
CN117474529A (en) Intelligent operation and maintenance system for power grid
CN110764065B (en) Radar fault diagnosis method based on time sequence reconstruction
CN113919237B (en) Method for on-line working condition segmentation and fault diagnosis of fan equipment
CN116992295A (en) Reconstruction method and device for machine pump equipment monitoring missing data for machine learning
CN115878978A (en) Method for detecting abnormity of periodic characteristic signals of industrial mobile robot
CN115409262A (en) Railway data center key performance index trend prediction method and abnormity identification method

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
GR01 Patent grant
GR01 Patent grant