CN113255965A - Intelligent processing system for prognosis of degradation fault of radar transmitter - Google Patents
Intelligent processing system for prognosis of degradation fault of radar transmitter Download PDFInfo
- Publication number
- CN113255965A CN113255965A CN202110455925.5A CN202110455925A CN113255965A CN 113255965 A CN113255965 A CN 113255965A CN 202110455925 A CN202110455925 A CN 202110455925A CN 113255965 A CN113255965 A CN 113255965A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- degradation
- unit
- time step
- 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
Links
- 230000015556 catabolic process Effects 0.000 title claims abstract description 80
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 80
- 238000012545 processing Methods 0.000 title claims abstract description 45
- 238000004393 prognosis Methods 0.000 title claims abstract description 33
- 238000003672 processing method Methods 0.000 claims abstract description 5
- 238000002790 cross-validation Methods 0.000 claims description 15
- 230000010354 integration Effects 0.000 claims description 8
- 238000000034 method Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 5
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 10
- 238000007689 inspection Methods 0.000 description 8
- 241001123248 Arma Species 0.000 description 3
- 125000004122 cyclic group Chemical group 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Educational Administration (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses an intelligent processing system and a processing method for prognosis of a radar transmitter degradation fault. The data acquisition unit acquires working sample data of the radar transmitter, the sample data is subjected to denoising processing, prediction processing and fault discrimination processing of the data processing unit to obtain time step numbers of the degradation fault data, and the fault output and alarm unit inquires the time step numbers of the degradation fault data to obtain time step number information of the degradation fault data and display a fault early warning line. By using the technical scheme provided by the application, the prognosis of the degradation fault of the radar transmitter can be realized under the conditions that the monitoring historical data is less, the data does not reach the fault threshold value, the fault samples are few, even no fault samples exist and the like.
Description
Technical Field
The invention relates to the technical field of data processing and information processing, in particular to an intelligent processing system and a processing method for prognosis of a degradation fault of a radar transmitter.
Background
The marine radar equipment is often in a long-time working state, and although a core part transmitter of the marine radar equipment meets the requirement on the service life of a device when leaving a factory, the transmitter is easy to be degraded prematurely under the adverse conditions of complex marine environment, frequent use and the like. However, after the transmitter is degraded and failed, the transmitter is maintained, and the actual requirements cannot be met, so that the prognosis of the degradation and failure of the radar transmitter is very important. With the increasing complexity of the marine radar system, the difficulty of predicting the degradation fault of the radar transmitter is also increasing, for example: on the one hand, some monitoring characteristics of the radar transmitter are within the normal operating range, but the actual radar transmitter is close to its service life; on the other hand, the existing intelligent degradation fault prediction method needs a large number of fault samples as prior conditions, and the radar fault samples are difficult to obtain. Therefore, monitoring the characteristics of each monitoring point by only professionals is not only inefficient but also difficult to predict degradation failures.
Disclosure of Invention
The invention provides an intelligent processing system and a processing method for prognosis of a radar transmitter degradation fault, which aim to overcome the technical problem.
In order to achieve the above object, the invention according to claim 1 is:
an intelligent processing system for prognosis of degradation fault of a radar transmitter is characterized in that: comprises a data acquisition unit, a data processing unit and a fault output and alarm unit,
the data acquisition unit comprises sensor units arranged at a radar transmitter switch power supply module, a pulse modulation circuit, a control protection circuit, a power amplifier and a fan system; the sensor unit collects sample data of the radar transmitter in a working state according to different time interval sampling modes and transmits the sample data to the data processing unit;
the data processing unit comprises a sensor data denoising unit, a dynamic updating difference integration moving average autoregressive data prediction unit, a multivariate Gaussian distribution fault prediction unit and a cross validation set unit; the sensor data denoising unit denoises sample data, the dynamic updating difference integration sliding mean autoregressive data prediction unit predicts the denoised data to obtain time step data, the multi-Gaussian distribution fault prediction unit performs fault discrimination processing on the time step data to obtain time step numbers of degradation fault data, the time step numbers of the degradation fault data are transmitted to a degradation fault prognosis result output unit, and the cross validation set unit provides a self-adaptive threshold value for the multi-Gaussian distribution fault prediction unit to predict the optimal degradation fault data time step numbers;
the failure output and alarm unit comprises a degradation failure prognosis result output unit and a failure data step alarm unit, wherein the degradation failure prognosis result output unit outputs degradation failure data time step numbers; and the fault output and alarm unit inquires the time step number of the degraded fault data to obtain the time step label information of the degraded fault data and displays a fault early warning line.
Further, the degradation fault data time step number is at least one.
Similarly, the technical scheme 2 of the invention is as follows:
an intelligent processing method for prognosis of degradation fault of a radar transmitter is characterized by comprising the following steps:
step 1, data acquisition, namely acquiring sample data of a radar transmitter in a working state in a sampling mode at different time intervals by sensors arranged at a radar transmitter switching power supply module, a pulse modulation circuit, a control protection circuit, a power amplifier and a fan system, and transmitting the sample data to a sensor data denoising unit through data transmission;
step 2, the sensor data denoising unit performs wavelet algorithm on the sample data to perform denoising processing;
step 3, a dynamic updating difference integration moving average autoregressive data prediction unit predicts the data after de-noising processing to obtain time step data;
step 4, the multivariate Gaussian distribution fault prediction unit and the cross validation set unit perform fault discrimination processing on the time step data to obtain time steps of the degradation fault data;
step 5, outputting the degradation fault data time step number and displaying the number position information by a degradation fault prognosis result output unit;
and 6, the fault output and alarm unit inquires the time step number of the degradation fault data to obtain the time step label information of the degradation fault data and displays a fault early warning line.
Further, the step 4 of performing fault discrimination processing on the time step data by the multivariate gaussian distribution fault prediction unit to obtain the time step number of the degraded fault data specifically includes:
4.1, constructing a multivariate Gaussian model by using the sample data subjected to denoising processing by the sensor data denoising unit;
step 4.2, providing a self-adaptive threshold value for the optimal multi-element Gaussian model by the cross validation set;
4.3, calculating a multivariate Gaussian distribution probability value of the time step data by using the multivariate Gaussian distribution model;
and 4.4, comparing the multivariate Gaussian distribution probability value with a self-adaptive threshold to obtain a time step of the degradation fault data.
Further, there is at least one time step number of the degradation fault data obtained in step 5.
Further, in step 6, the number of the first time step of the degradation fault is inquired to obtain the label information of the first time step of the degradation fault data, and a fault early warning line is displayed.
Has the advantages that: the radar transmitter degradation fault prognosis intelligent algorithm adopted by the invention carries out high-precision prediction on data monitored by the sensor, realizes radar transmitter degradation fault prognosis under the condition that few fault samples (even no fault samples) and monitoring data do not exceed a fault threshold value, and is beneficial to system management, health state prediction and use power evaluation of equipment. The invention utilizes various data information of the sensor acquisition system, monitors, predicts and manages the state of the system by means of various inference algorithms and intelligent models, estimates the self health condition of the system and can effectively predict before the system generates degradation failure.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a block diagram of the present invention;
FIG. 2 is a flow chart of a method of use of the present invention;
fig. 3 is a flow chart for establishing an ARIMA model.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below 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. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an embodiment 1 of the present invention provides a technical solution: an intelligent processing system for prognosis of degradation fault of a radar transmitter specifically comprises the following components:
an intelligent processing system for prognosis of degradation fault of a radar transmitter is characterized in that: comprises a data acquisition unit, a data processing unit and a fault output and alarm unit,
the data acquisition unit comprises sensor units arranged at a radar transmitter switch power supply module, a pulse modulation circuit, a control protection circuit, a power amplifier and a fan system; the sensor unit collects sample data of the radar transmitter in a working state according to different time interval sampling modes and transmits the sample data to the data processing unit;
the data processing unit comprises a sensor data denoising unit, a dynamic updating difference integration moving average autoregressive data prediction unit, a multivariate Gaussian distribution fault prediction unit and a cross validation set unit; the sensor data denoising unit denoises sample data, the dynamic updating difference integration sliding mean autoregressive data prediction unit predicts the denoised data to obtain time step data, the multi-Gaussian distribution fault prediction unit performs fault discrimination processing on the time step data to obtain time step numbers of the degradation fault data, the time step numbers of the degradation fault data are transmitted to a degradation fault prognosis result output unit, and the cross validation set unit provides data support for the multi-Gaussian distribution fault prediction unit to predict the optimal time step numbers of the degradation fault data through automatically obtaining a threshold value;
the failure output and alarm unit comprises a degradation failure prognosis result output unit and a failure data step alarm unit, wherein the degradation failure prognosis result output unit outputs degradation failure data time step numbers; and the fault output and alarm unit inquires the time step number of the degraded fault data to obtain the time step label information of the degraded fault data and displays a fault early warning line.
In the specific embodiment 1, the degradation failure data time step number is at least one.
In the same way, the invention provides an embodiment 2 of intelligent treatment method for prognosis of radar transmitter degradation fault
Referring to fig. 2, the specific steps are as follows:
step 1, data acquisition, namely acquiring sample data of a radar transmitter in a working state in a sampling mode at different time intervals by sensors arranged at a radar transmitter switching power supply module, a pulse modulation circuit, a control protection circuit, a power amplifier and a fan system, and transmitting the sample data to a sensor data denoising unit through data transmission;
step 2, sensor data denoising, namely denoising sample data acquired by a sensor, specifically, performing wavelet denoising on the sample data acquired by each sensor input by a data acquisition unit, wherein specific wavelet parameters are as follows: the threshold function is a soft threshold function and a heuristic threshold is selected for the threshold, the number of wavelet decomposition layers is 1, the wavelet basis is Daubechies (db4), the working data of the denoised radar transmitter are obtained, and the data can be used for predicting the subsequent working time step data of the transmitter on one hand and can be used as the input data constructed by a multivariate Gaussian distribution model on the other hand;
and 3, Dynamically updating the data subjected to denoising processing by a differential Integrated Moving Average Autoregressive data prediction unit to obtain time step data, wherein particularly, a Dynamically Updated differential Integrated Moving Average Autoregressive algorithm (DU-ARIMA) is an improvement of the differential Integrated Moving Average Autoregressive algorithm (ARIMA), and the core algorithm of the dynamic Integrated Moving Average Autoregressive algorithm is still ARIMA.
As shown in fig. 3, the establishing ARIMA model includes the following steps: acquiring an original observation value sequence, carrying out stability inspection on the original observation value sequence, carrying out white noise inspection on the original observation value sequence if the original observation value sequence is stable, and carrying out differential operation on the original observation value sequence if the original observation value sequence is not stable until the stability inspection is passed; and performing white noise inspection on the stationarity passing through the stationarity inspection, acquiring a final observed value sequence if the stationarity passes through the white noise inspection, and fitting the observed value sequence to the ARMA model until the ARMA model passes through the white noise inspection if the stationarity passes through the white noise inspection, thereby obtaining the final observed value sequence.
The ARIMA algorithm is used for analyzing and predicting observed value sequence data, and an ARIMA (p, d, q) model can be expressed as:
wherein p represents the order of the autoregressive model, d represents the difference order, q represents the order of the moving average model, i represents the cyclic variable, and XtRepresents the sequence value corresponding to the current time point t, phi i represents an autoregressive coefficient, theta i represents a moving regression coefficient, and L represents a delay operator.
DU-ARIMA means that the real value of the last time step can be accessed for algorithm updating before the next predicted value is predicted, so that the prediction effect of the DU-ARIMA on data is better than that of the ARIMA. The ARIMA model is essentially a combination of differential operations and a Moving Average autoregressive algorithm (ARMA), and can be expressed as ARIMA (p, d, q), where p represents the order of the autoregressive model, d represents the differential order, and q represents the order of the Moving Average model. The optimal parameters of the ARIMA (p, d, q) model can be automatically obtained by the AIC information criterion. Specifically, the evaluation of the accuracy of the prediction result of the data by the DU-ARIMA algorithm can be expressed by Root Mean Square Error (RMSE) as:
wherein, h (x) in the formulai) To predict value, yiFor true values, m represents the total number of samples in the sequence and i is the loop variable. The smaller the RMSE value, the better the DU-ARIMA prediction. The prediction data obtained by the DU-ARIMA algorithm is time step data and can be used as test sample data of a multivariate Gaussian distribution model;
step 4, a multivariate Gaussian distribution fault prediction unit and a cross validation set unit perform fault discrimination processing on time step data to obtain time steps of the degraded fault data, multivariate Gaussian distribution comprises correlation information among all characteristic variables, the whole modeling process considers the correlation among all the characteristic variables and does not need a large amount of sample data, and the specific steps are as follows:
step 4.1, constructing a multivariate Gaussian model by using the sample data subjected to denoising processing by the sensor data denoising unit, and performing multivariate characteristic variable set
If each characteristic variable obeys Gaussian distribution, it can be recorded as formula
The multivariate Gaussian distribution model can be expressed as
The expectation of the multivariate Gaussian distribution is
Variance of multivariate Gaussian distribution of
P is a multivariate Gaussian distribution probability value, x represents a sample set, m represents the number of samples, n represents the number of characteristics, mu represents expectation, sigma represents the discrete degree, i represents a cyclic variable, and the multivariate characteristic variable set is sample data and time step data after denoising processing by a sensor data denoising unit;
step 4.2, a cross validation set is set, the cross validation set provides a self-adaptive threshold epsilon for predicting the optimal multivariate Gaussian model, specifically, the selection of the self-adaptive threshold parameter epsilon in the step 4 can be determined by setting data of the cross validation set, different self-adaptive threshold parameters epsilon can cause different multivariate Gaussian distribution models, and the obtained optimal model parameter value F1Also different, optimal model parameter values F1The calculation formula method is F1＝2PR/(P+R),F1∈[0,1]Wherein P is ntp/(ntp+nfp) For accuracy, R ═ ntp/(ntp+nfn) For recall, ntpNumber of samples representing that the actual value is a fault and the predicted value is also a fault, nfpNumber of samples, n, indicating that the actual value is normal and the predicted value is faultyfnIndicating the number of samples for which the actual value is faulty and the predicted value is normal. F1The closer the value is to 1The better the prediction effect of the bright model is;
4.3, calculating a multivariate Gaussian distribution probability value P of the time step data by utilizing a multivariate Gaussian distribution model expression;
and 4.4, comparing the multivariate Gaussian distribution probability value P with the self-adaptive threshold parameter epsilon to obtain time step of the degraded fault data, wherein the time step of the degraded fault data is the degraded fault time step data when the multivariate Gaussian distribution probability value P is larger than or equal to the self-adaptive threshold parameter epsilon, and the time step data of the degraded fault-free data is the degraded fault time step data when the multivariate Gaussian distribution probability value P is smaller than the self-adaptive threshold parameter epsilon.
Step 5, prognosis of the degradation fault, namely outputting the time step number of the degradation fault data, specifically, obtaining the time step data of the degradation fault data by a prognosis result output unit of the degradation fault, outputting the time step number of the degradation fault data and displaying the number position information;
and 6, the fault output and alarm unit inquires the time step number of the degradation fault data to obtain the time step label information of the degradation fault data and displays a fault early warning line.
In the specific example 2, the preferable scheme of the step 5 is as follows: the time step number of the degradation fault data obtained in the step 5 is at least one.
In the specific embodiment 2, in step 6, the first time step number of the degradation fault is queried to obtain the first time step label information of the degradation fault data, and a fault early warning line is displayed.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. An intelligent processing system for prognosis of degradation fault of a radar transmitter is characterized in that: comprises a data acquisition unit, a data processing unit and a fault output and alarm unit,
the data acquisition unit comprises sensor units arranged at a radar transmitter switch power supply module, a pulse modulation circuit, a control protection circuit, a power amplifier and a fan system; the sensor unit collects sample data of the radar transmitter in a working state according to different time interval sampling modes and transmits the sample data to the data processing unit;
the data processing unit comprises a sensor data denoising unit, a dynamic updating difference integration moving average autoregressive data prediction unit, a multivariate Gaussian distribution fault prediction unit and a cross validation set unit; the sensor data denoising unit denoises sample data, the dynamic updating difference integration sliding mean autoregressive data prediction unit predicts the denoised data to obtain time step data, the multi-Gaussian distribution fault prediction unit performs fault discrimination processing on the time step data to obtain time step numbers of degradation fault data, the time step numbers of the degradation fault data are transmitted to a degradation fault prognosis result output unit, and the cross validation set unit provides a self-adaptive threshold value for the multi-Gaussian distribution fault prediction unit to predict the optimal degradation fault data time step numbers;
the failure output and alarm unit comprises a degradation failure prognosis result output unit and a failure data step alarm unit, wherein the degradation failure prognosis result output unit outputs degradation failure data time step numbers; and the fault output and alarm unit inquires the time step number of the degraded fault data to obtain the time step label information of the degraded fault data and displays a fault early warning line.
2. The intelligent processing system for radar transmitter degradation fault prognosis as claimed in claim 1, wherein: the degradation fault data time step number is at least one.
3. A processing method using the radar transmitter degradation failure prognosis intelligent processing system according to claim 1, characterized by:
step 1, data acquisition, namely acquiring sample data of a radar transmitter in a working state in a sampling mode at different time intervals by sensors arranged at a radar transmitter switching power supply module, a pulse modulation circuit, a control protection circuit, a power amplifier and a fan system, and transmitting the sample data to a sensor data denoising unit through data transmission;
step 2, the sensor data denoising unit performs wavelet algorithm on the sample data to perform denoising processing;
step 3, a dynamic updating difference integration moving average autoregressive data prediction unit predicts the data after de-noising processing to obtain time step data;
step 4, the multivariate Gaussian distribution fault prediction unit and the cross validation set unit perform fault discrimination processing on the time step data to obtain time steps of the degradation fault data;
step 5, outputting the degradation fault data time step number and displaying the number position information by a degradation fault prognosis result output unit;
and 6, the fault output and alarm unit inquires the time step number of the degradation fault data to obtain the time step label information of the degradation fault data and displays a fault early warning line.
4. The use method of the intelligent processing system for the prognosis of the radar transmitter degradation fault, according to claim 3, wherein the step 4 of performing the fault discrimination processing on the time step data by the multivariate Gaussian distribution fault prediction unit and the cross validation set unit to obtain the degradation fault data comprises the following specific steps:
4.1, constructing a multivariate Gaussian model by using the sample data subjected to denoising processing by the sensor data denoising unit;
step 4.2, providing a self-adaptive threshold value for the optimal multi-element Gaussian model by the cross validation set;
4.3, calculating a multivariate Gaussian distribution probability value of the time step data by using the multivariate Gaussian distribution model;
and 4.4, comparing the multivariate Gaussian distribution probability value with a self-adaptive threshold to obtain a time step of the degradation fault data.
5. The use method of the radar transmitter degradation failure prognosis intelligent processing system as claimed in claim 4, wherein: the time step number of the degradation fault data obtained in the step 5 is at least one.
6. The use method of the radar transmitter degradation failure prognosis intelligent processing system according to claim 5, wherein: and 6, inquiring the first time step number of the degradation fault to obtain the first time step label information of the degradation fault data and displaying a fault early warning line.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110455925.5A CN113255965B (en) | 2021-04-26 | 2021-04-26 | Intelligent radar transmitter degradation fault prognosis processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110455925.5A CN113255965B (en) | 2021-04-26 | 2021-04-26 | Intelligent radar transmitter degradation fault prognosis processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113255965A true CN113255965A (en) | 2021-08-13 |
| CN113255965B CN113255965B (en) | 2024-09-13 |
Family
ID=77221944
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110455925.5A Active CN113255965B (en) | 2021-04-26 | 2021-04-26 | Intelligent radar transmitter degradation fault prognosis processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113255965B (en) |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030014692A1 (en) * | 2001-03-08 | 2003-01-16 | California Institute Of Technology | Exception analysis for multimissions |
| CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
| CN103645249A (en) * | 2013-11-27 | 2014-03-19 | 国网黑龙江省电力有限公司 | Online fault detection method for reduced set-based downsampling unbalance SVM (Support Vector Machine) transformer |
| CN104820146A (en) * | 2015-04-24 | 2015-08-05 | 中国电力科学研究院 | Transformer fault prediction method based on monitoring data of dissolved gas in oil of transformer |
| US20170016430A1 (en) * | 2015-07-17 | 2017-01-19 | General Electric Company | Systems and methods for improved wind power generation |
| CN106680012A (en) * | 2017-01-25 | 2017-05-17 | 浙江大学 | Fault detection method and fault diagnosis method for the non-stationary process of large coal-fired generator set |
| CN107085750A (en) * | 2017-03-10 | 2017-08-22 | 广东工业大学 | A kind of mixing dynamic fault Forecasting Methodology based on ARMA and ANN |
| CN107247230A (en) * | 2017-07-03 | 2017-10-13 | 浙江大学 | A kind of electric rotating machine state monitoring method based on SVMs and data-driven |
| CN108805202A (en) * | 2018-06-11 | 2018-11-13 | 上海新增鼎数据科技有限公司 | A kind of machine learning method and its application for electrolytic cell fault pre-alarming |
| CN108802525A (en) * | 2018-06-06 | 2018-11-13 | 浙江宇天科技股份有限公司 | Equipment fault intelligent Forecasting based on small sample |
| CN110333493A (en) * | 2019-07-19 | 2019-10-15 | 舒毅 | A kind of weather radar transmitter failure detection system and method |
| CN110736968A (en) * | 2019-10-16 | 2020-01-31 | 清华大学 | Radar abnormal state diagnosis method based on deep learning |
| US20200184373A1 (en) * | 2017-08-30 | 2020-06-11 | Siemens Aktiengesellschaft | Recurrent Gaussian Mixture Model For Sensor State Estimation In Condition Monitoring |
| US20200241514A1 (en) * | 2019-01-28 | 2020-07-30 | Exxonmobil Research And Engineering Company | Method and systems for fault detection and identification |
| CN111651312A (en) * | 2020-07-28 | 2020-09-11 | 南京宏声科技有限公司 | Three-level bidirectional early warning method and system for equipment fault based on edge calculation |
| CN112036480A (en) * | 2020-08-29 | 2020-12-04 | 大连海事大学 | Ship refrigeration system fault diagnosis method and device and storage medium |
| CN112214911A (en) * | 2020-10-31 | 2021-01-12 | 中国电子科技集团公司第十四研究所 | Power supply health state prediction method |
-
2021
- 2021-04-26 CN CN202110455925.5A patent/CN113255965B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030014692A1 (en) * | 2001-03-08 | 2003-01-16 | California Institute Of Technology | Exception analysis for multimissions |
| CN102208028A (en) * | 2011-05-31 | 2011-10-05 | 北京航空航天大学 | Fault predicting and diagnosing method suitable for dynamic complex system |
| CN103645249A (en) * | 2013-11-27 | 2014-03-19 | 国网黑龙江省电力有限公司 | Online fault detection method for reduced set-based downsampling unbalance SVM (Support Vector Machine) transformer |
| CN104820146A (en) * | 2015-04-24 | 2015-08-05 | 中国电力科学研究院 | Transformer fault prediction method based on monitoring data of dissolved gas in oil of transformer |
| US20170016430A1 (en) * | 2015-07-17 | 2017-01-19 | General Electric Company | Systems and methods for improved wind power generation |
| CN106680012A (en) * | 2017-01-25 | 2017-05-17 | 浙江大学 | Fault detection method and fault diagnosis method for the non-stationary process of large coal-fired generator set |
| CN107085750A (en) * | 2017-03-10 | 2017-08-22 | 广东工业大学 | A kind of mixing dynamic fault Forecasting Methodology based on ARMA and ANN |
| CN107247230A (en) * | 2017-07-03 | 2017-10-13 | 浙江大学 | A kind of electric rotating machine state monitoring method based on SVMs and data-driven |
| US20200184373A1 (en) * | 2017-08-30 | 2020-06-11 | Siemens Aktiengesellschaft | Recurrent Gaussian Mixture Model For Sensor State Estimation In Condition Monitoring |
| CN108802525A (en) * | 2018-06-06 | 2018-11-13 | 浙江宇天科技股份有限公司 | Equipment fault intelligent Forecasting based on small sample |
| CN108805202A (en) * | 2018-06-11 | 2018-11-13 | 上海新增鼎数据科技有限公司 | A kind of machine learning method and its application for electrolytic cell fault pre-alarming |
| US20200241514A1 (en) * | 2019-01-28 | 2020-07-30 | Exxonmobil Research And Engineering Company | Method and systems for fault detection and identification |
| CN110333493A (en) * | 2019-07-19 | 2019-10-15 | 舒毅 | A kind of weather radar transmitter failure detection system and method |
| CN110736968A (en) * | 2019-10-16 | 2020-01-31 | 清华大学 | Radar abnormal state diagnosis method based on deep learning |
| CN111651312A (en) * | 2020-07-28 | 2020-09-11 | 南京宏声科技有限公司 | Three-level bidirectional early warning method and system for equipment fault based on edge calculation |
| CN112036480A (en) * | 2020-08-29 | 2020-12-04 | 大连海事大学 | Ship refrigeration system fault diagnosis method and device and storage medium |
| CN112214911A (en) * | 2020-10-31 | 2021-01-12 | 中国电子科技集团公司第十四研究所 | Power supply health state prediction method |
Non-Patent Citations (8)
| Title |
|---|
| CHENG ZHANXIN: "Research on Maintenance and Support Technology for Offshore Based on Beidou Satellite Navigation System", 《IEEE》, 21 March 2021 (2021-03-21), pages 210 - 213 * |
| LV, YL: "Measurement of Radar Performance Parameter\'s Predictability Based on Chaos Analysis Method", 《2018 PROGNOSTICS AND SYSTEM HEALTH MANAGEMENT CONFERENCE (PHM-CHONGQING 2018)》, 8 March 2019 (2019-03-08), pages 1106 - 1113 * |
| ZHAI, YT: "A Degradation Fault Prognostic Method of Radar Transmitter Combining Multivariate Long Short-Term Memory Network and Multivariate Gaussian Distribution", 《IEEE ACCESS》, vol. 8, 1 December 2020 (2020-12-01), pages 199781 - 199791, XP011819590, DOI: 10.1109/ACCESS.2020.3035622 * |
| 刘冬利: "舰载雷达探测精度标定方法及关键技术研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑 (月刊)》, no. 10, 15 October 2016 (2016-10-15), pages 036 - 2 * |
| 尹倩: "基于时间序列的船舶推进装置温度预测", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑 (月刊)》, no. 1, 15 January 2021 (2021-01-15), pages 036 - 75 * |
| 朱丽: "基于ARMA的雷达发射机故障预测及其实现", 《计算机测量与控制 》, vol. 18, no. 11, 25 November 2010 (2010-11-25), pages 2460 - 2468 * |
| 贺喆: "简析发射机故障分析预警系统的设计", 《数字传媒研究 》, vol. 37, no. 6, 15 June 2020 (2020-06-15), pages 38 - 43 * |
| 马溧溧;罗正华;胡德昆;: "融合型AR模型在雷达故障预测中的应用", 现代电子技术, no. 11, pages 28 - 31 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113255965B (en) | 2024-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| Ghasemi et al. | Optimal condition based maintenance with imperfect information and the proportional hazards model | |
| CN117176560B (en) | Monitoring equipment supervision system and method based on Internet of things | |
| CN110689141B (en) | Fault diagnosis method and equipment for wind generating set | |
| KR102515853B1 (en) | Abnormality diagnosis device, system and method based on battery cell unit | |
| US11423321B2 (en) | Method and system for predicting system status | |
| CN105209995A (en) | Monitoring system and diagnostic device and monitoring terminal thereof | |
| US12007745B2 (en) | Apparatus for predicting equipment damage | |
| CN116070802B (en) | Intelligent monitoring operation and maintenance method and system based on data twinning | |
| De Vita et al. | A novel data collection framework for telemetry and anomaly detection in industrial iot systems | |
| CN117826715A (en) | Intelligent device monitoring and early warning system | |
| CN114936504A (en) | Equipment residual life prediction method and system based on Bayesian multi-source data fusion | |
| US12008072B2 (en) | Control system and control method | |
| CN117992859B (en) | Early-stage fault early-warning and identifying method and device for electromechanical equipment provided with SCADA system | |
| CN116248674A (en) | Data transmission method, device and system | |
| EP4137815A1 (en) | Failure prediction system | |
| CN112595537B (en) | Equipment health state monitoring method and system based on signal analysis and storage medium | |
| CN113255965A (en) | Intelligent processing system for prognosis of degradation fault of radar transmitter | |
| CN115456168B (en) | Training method of reinforcement learning model, energy consumption determining method and device | |
| EP3413153A1 (en) | Method and distributed control system for carrying out an automated industrial process | |
| US11687061B2 (en) | Data collection and analysis system, data collection and analysis apparatus, machine learning apparatus, and data collection and analysis method | |
| US20200112577A1 (en) | Graph-based sensor ranking | |
| Xin et al. | Run-time probabilistic model checking for failure prediction: A smart lift case study | |
| US11093315B2 (en) | Systems and methods for detecting a fault or a model mismatch | |
| CN117670172B (en) | Foreign trade data processing method and system |
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 |