CN112487362B - Satellite step remote parameter stability monitoring method and system based on K-Means + + algorithm - Google Patents
Satellite step remote parameter stability monitoring method and system based on K-Means + + algorithm Download PDFInfo
- Publication number
- CN112487362B CN112487362B CN202011394595.5A CN202011394595A CN112487362B CN 112487362 B CN112487362 B CN 112487362B CN 202011394595 A CN202011394595 A CN 202011394595A CN 112487362 B CN112487362 B CN 112487362B
- Authority
- CN
- China
- Prior art keywords
- module
- telemetry
- signal space
- data
- data set
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Pure & Applied Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Evolutionary Biology (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Radio Relay Systems (AREA)
- Selective Calling Equipment (AREA)
Abstract
The invention provides a method and a system for monitoring satellite step remote parameter stability based on a K-Means + + algorithm, which comprises the following steps: step 1: cutting and segmenting the satellite step change type telemetering signals by taking a natural day as a unit to obtain a telemetering data set; step 2: identifying a signal step scale according to the telemetering data set, and establishing a standard signal space; and step 3: measuring the matching degree of the data to be monitored and a standard signal space; and 4, step 4: and judging the stability according to the matching degree. The invention uses a data-driven self-recognition method, thereby solving the problem that the traditional stability monitoring method depends on expert knowledge and manpower; meanwhile, the method has strong expansibility and can be used for various multi-scale step type telemetering.
Description
Technical Field
The invention relates to the technical field of satellite telemetry, in particular to a method and a system for monitoring satellite step telemetry stability based on a K-Means + + algorithm.
Background
During the in-orbit operation of the satellite, sensor parameter information obtained by an internal operation state monitoring system is transmitted to the ground through a remote measuring system after being encoded, and the remote measuring data is the only basis for ground satellite operation and management personnel to know the in-orbit operation state of the spacecraft. The method has the advantages that the method is large in telemetering data volume, high in dimensionality, complex in relation, correlation and profession, and belongs to the typical application field of industrial big data, the method reflects orbit information, performance change, working mode switching, whether a fault occurs or not and the like of a satellite, and effective analysis and intelligent calculation of telemetering data provide effective basis for ground operation management personnel to judge the performance of the satellite and develop various operation and maintenance management works.
The satellite step change type telemetering data has the characteristic of random step, and the parameter abnormal points are difficult to interpret through a simple threshold rule. The stability of the satellite telemetry parameters is an important index for reflecting the running state of the satellite, and whether the satellite has an abnormal state in a certain period is judged through the characteristics of data waveforms.
In patent document CN101718864A (application number: CN 200910237621.0), the parameter abnormality is determined based on a given parameter effective value interval and a long-short term variation range;
patent document CN103646167A (application number: CN 201310596516.2) compares the relative error between the measured telemetry parameter and the corresponding extreme point of the historical telemetry parameter with the threshold interval of the extreme point, and realizes the abnormal judgment of the parameter.
These methods have the following problems:
(1) Aiming at the random step characteristics of satellite step change type telemetering, the abnormity judgment of the telemetering parameters based on various fixed threshold intervals can not adapt to the random variability telemetering characteristics, and the misjudgment is easily caused.
(2) The method of manually monitoring the combination threshold faces the problems of huge labor cost, poor expansibility and the like, when the satellite model is changed, the threshold needs to be reset, and the method does not have universal adaptability.
(3) The expert system based approach is difficult to establish accurate and complete interpretation rules and cannot handle unknown anomalies in step change telemetry.
Because the conventional method has the problems, an efficient satellite telemetry parameter stability detection method is needed, the interpretation accuracy is improved, and the investment of labor cost is reduced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a satellite step telemetry stability monitoring method and system based on a K-Means + + algorithm.
The method for monitoring the stability of the satellite step remote parameter based on the K-Means + + algorithm comprises the following steps:
step 1: cutting and segmenting the satellite step change type telemetering signals by taking a natural day as a unit to obtain a telemetering data set;
and 2, step: identifying a signal step scale according to the telemetering data set, and establishing a standard signal space;
and step 3: measuring the matching degree of the data to be monitored and a standard signal space;
and 4, step 4: and judging the stability according to the matching degree.
Preferably, the step 2 includes:
step 2.1: inputting a telemetry data set with natural days as a unit;
step 2.2: selecting a centroid meeting preset conditions in the telemetry data set;
step 2.3: a standard signal space is established according to the centroid.
Preferably, said step 2.2 comprises:
randomly selecting a sample from the telemetry data set as an initial clustering center, calculating the shortest distance between each sample and the initial clustering center, and calculating the probability of each sample being selected as a centroid;
k centroids are selected in a wheel disc mode, wherein K is set according to the actual step condition of the telemetering data, and the K centroids are used as initialization centroids to run a K mean value clustering algorithm.
Preferably, said step 2.3 comprises:
step 2.3.1: calculating Euclidean distances from each feature vector in the telemetry data set to K centroids, and dividing the Euclidean distances into signal spaces corresponding to centroids with minimum distances;
step 2.3.2: recalculating the centroid of each signal space;
step 2.3.3: and (5) repeatedly executing the step 2.3.1 to the step 2.3.2 until the mass centers are not changed any more, and outputting the K mass centers and the corresponding signal spaces thereof.
Preferably, the step 3 comprises: and counting the ratio of sample points falling in the signal space in the data to be monitored according to a statistical method so as to measure the matching degree of the data to be monitored and the standard signal space.
Preferably, if the ratio of the sample points in the data to be monitored falling in the signal space is greater than or equal to a preset value, the telemetering data section is determined to be stable, otherwise, the telemetering data section is determined to be an abnormal data section.
The system for monitoring the stability of the satellite step remote parameter based on the K-Means + + algorithm comprises the following components:
a module M1: cutting and segmenting the satellite step change type telemetering signals by taking a natural day as a unit to obtain a telemetering data set;
a module M2: identifying a signal step scale according to the telemetering data set, and establishing a standard signal space;
a module M3: measuring the matching degree of the data to be monitored and a standard signal space;
a module M4: and judging the stability according to the matching degree.
Preferably, the module M2 comprises:
module M2.1: inputting a telemetering data set taking natural days as units;
module M2.2: selecting a centroid meeting preset conditions in the telemetry data set;
module M2.3: establishing a standard signal space according to the centroid;
the module M2.2 comprises:
randomly selecting a sample from the telemetry data set as an initial clustering center, calculating the shortest distance between each sample and the initial clustering center, and calculating the probability of each sample being selected as a centroid;
selecting K centroids in a wheel disc mode, wherein K is set according to the actual step condition of the telemetering data, and operating a K mean value clustering algorithm by taking the K centroids as the initialized centroids;
said module M2.3 comprises:
module m2.3.1: calculating Euclidean distances from each feature vector in the telemetry data set to K centroids, and dividing the Euclidean distances into signal spaces corresponding to centroids with minimum distances;
module m2.3.2: recalculating the centroid of each signal space;
module m2.3.3: and repeatedly executing the modules M2.3.1-M2.3.2 until the barycenter is not changed any more, and outputting K barycenters and corresponding signal spaces thereof.
Preferably, the module M3 comprises: and counting the ratio of sample points falling in the signal space in the data to be monitored according to a statistical method so as to measure the matching degree of the data to be monitored and the standard signal space.
Preferably, if the ratio of the sample points falling in the signal space in the data to be monitored is greater than or equal to a preset value, the telemetering data segment is determined to be stable, otherwise, the telemetering data segment is determined to be an abnormal data segment.
Compared with the prior art, the invention has the following beneficial effects: according to the satellite step change type telemetering stability monitoring method based on the K-Means + + method, expert experience is not required to be obtained in advance, the self-adaptive normal signal space can be generated by normal data calculation, and the labor cost is greatly saved; meanwhile, the method has strong expansibility, can be simultaneously used for various multi-scale step type telemetering, and can remarkably reduce the workload of the system while improving the efficiency by using a data driving method.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a block flow diagram of a satellite step change telemetry stability monitoring method based on the K-Means + + method of the present application;
FIG. 2 is a stable data section of the transponder level TMC0002 telemetry channel;
FIG. 3 is a stable data segment of the transponder level TMC0005 telemetry channel;
FIG. 4 is an anomaly data segment of the transponder level TMC0002 telemetry channel;
fig. 5 shows an abnormal data segment of the transponder level TMC0005 telemetry channel.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the concept of the invention. All falling within the scope of the present invention.
The embodiment is as follows:
as in fig. 1, this example takes a step change type telemetry signal from a satellite for verification. In order to test the effect of the satellite transponder in practical application, two channels of electrical levels TMC0002 and TMC0005 of the satellite transponder are specifically used, and two groups of step signals are used for detecting and verifying the satellite step change type telemetry stability monitoring method based on the K-Means + + method, and the method specifically comprises the following steps:
the method comprises the following steps: and (3) carrying out sectional processing on the collected satellite step change type telemetering by taking the natural day as a unit, setting a judgment condition and rejecting the non-data natural day. The total number of segments of telemetry TMC0002 and TMC0005 is 334.
Step two: inputting normal telemetering data for 30 days, identifying and classifying step signals with different scales by using a K-Means + + method, and establishing signal spaces with different scales.
The K-Means + + method is used for realizing identification and classification of step signals with different scales, and the steps of establishing a normal signal space are as follows:
1) Inputting a normal telemetry data set with natural days as units, T = { (x) 1 ,y 1 ),(x 2 ,y 2 ),...,(x N ,y N ) Therein ofAs feature vectors of the telemetry data, y i ∈Y={c 1 ,c 2 ,...,c K And the types of step signals with different scales comprise high level and low level.
2) Optimized selection of initial centroids:
a. randomly selecting a sample from the data set as an initial clustering center c i 。
b. The shortest distance between each sample and the current existing cluster center (centroid), i.e. the distance to the nearest centroid, is first calculated, expressed as euclidean distance D (x),
d. The next centroid is selected according to the roulette method until a total of K centroids are selected, where K is set according to the actual step condition of normal telemetry data, where K =2. K-Means algorithm using the K centroids as initialization centroids to operate standard
3) Standard K-Means calculation methods:
a. for each feature vector x in the data set T i Calculating Euclidean distances from the K centroids to the signal space V corresponding to the centroid with the minimum distance i In (1).
b. For each signal space V i Recalculating its centroid(i.e., belong to the centroid of the signal space).
c. Repeating the iteration until the mass center is not changed, and outputting K mass centers c 1 ,c 2 ,...,c K And its corresponding signal space V i ={D(x i )<D(x i ) max }。
The centroid obtained by the K-Means + + method and the normal signal space of different dimensions in this example are shown in the following table.
TABLE 1 telemetering TMC0002 centroid and signal space
Center of mass | Corresponding normal signal space |
C 1 =-80 | v 1 ={D(x i )<20} |
C 2 =-130 | v 2 ={D(x i )<10} |
TABLE 2 telemetering TMC0005 centroids and signal spaces
Center of mass | Corresponding normal signal space |
C 1 =4.75 | v 1 ={D(x i )<0.25} |
C 2 =0.5 | v 2 ={D(x i )<0.5} |
The signal spaces with different scales obtained by the K-Means + + method are respectively V 1 ,V 2 ,...V i Full space table of standard signalsShown as S, then S = V 1 ∪V 2 ∪...∪V i 。
Step three: and calculating the ratio of the data segment to be monitored in the normal signal space by using a statistical method so as to judge the telemetry stability.
In this example, when the ratio of the sample points in the monitoring data falling in the normal signal space S is greater than 99.5%, the telemetry data segment is considered to be stable, the stable data is as shown in fig. 2 and fig. 3, otherwise, the telemetry data segment is judged to be an abnormal data segment as shown in fig. 4 and fig. 5.
The invention provides a satellite step change type telemetry stability monitoring system, which comprises:
a module M1: cutting and segmenting the satellite step change type telemetering signals by taking natural days as units to obtain a telemetering data set;
a module M2: identifying a signal step scale according to the telemetering data set, and establishing a standard signal space;
a module M3: measuring the matching degree of the data to be monitored and a standard signal space;
a module M4: and judging the stability according to the matching degree.
Preferably, the module M2 comprises:
module M2.1: inputting a telemetry data set with natural days as a unit;
module M2.2: selecting a centroid meeting preset conditions in the telemetry data set;
module M2.3: establishing a standard signal space according to the mass center;
said module M2.2 comprises:
randomly selecting a sample from the telemetry data set as an initial clustering center, calculating the shortest distance between each sample and the initial clustering center, and calculating the probability of each sample being selected as a centroid;
selecting K centroids in a wheel disc mode, wherein K is set according to the actual step condition of the telemetering data, and operating a K mean value clustering algorithm by taking the K centroids as the initialized centroids;
said module M2.3 comprises:
module m2.3.1: calculating Euclidean distances from each feature vector in the telemetry data set to K centroids, and dividing the Euclidean distances into signal spaces corresponding to centroids with minimum distances;
module m2.3.2: recalculating the centroid of each signal space;
module m2.3.3: and repeatedly executing the modules M2.3.1-M2.3.2 until the centroids are not changed any more, and outputting K centroids and corresponding signal spaces thereof.
Preferably, the module M3 comprises: and counting the ratio of sample points falling in the signal space in the data to be monitored according to a statistical method so as to measure the matching degree of the data to be monitored and the standard signal space.
Preferably, if the ratio of the sample points falling in the signal space in the data to be monitored is greater than or equal to a preset value, the telemetering data segment is determined to be stable, otherwise, the telemetering data segment is determined to be an abnormal data segment.
Those skilled in the art will appreciate that, in addition to implementing the systems, apparatus, and various modules thereof provided by the present invention in purely computer readable program code, the same procedures can be implemented entirely by logically programming method steps such that the systems, apparatus, and various modules thereof are provided in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Therefore, the system, the device and the modules thereof provided by the present invention can be considered as a hardware component, and the modules included in the system, the device and the modules thereof for implementing various programs can also be considered as structures in the hardware component; modules for performing various functions may also be considered to be both software programs for performing the methods and structures within hardware components.
The foregoing description has described specific embodiments of the present invention. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (6)
1. A satellite step telemetry stability monitoring method based on a K-Means + + algorithm is characterized by comprising the following steps:
step 1: cutting and segmenting the satellite step change type telemetering signals by taking natural days as units to obtain a telemetering data set;
and 2, step: identifying a signal step scale according to the telemetering data set, and establishing a standard signal space;
and step 3: measuring the matching degree of the data to be monitored and a standard signal space;
and 4, step 4: judging the stability according to the matching degree;
the step 2 comprises the following steps:
step 2.1: inputting a telemetry data set with natural days as a unit;
step 2.2: selecting a centroid meeting preset conditions in the telemetry data set;
step 2.3: establishing a standard signal space according to the mass center;
the step 2.2 comprises:
randomly selecting a sample from the telemetry data set as an initial clustering center, calculating the shortest distance between each sample and the initial clustering center, and calculating the probability of each sample being selected as a centroid;
selecting K centroids in a wheel disc mode, wherein K is set according to the actual step condition of the telemetering data, and operating a K mean value clustering algorithm by taking the K centroids as the initialized centroids;
the step 2.3 comprises:
step 2.3.1: calculating Euclidean distances from each feature vector in the telemetry data set to K centroids, and dividing the Euclidean distances into signal spaces corresponding to the centroids with the minimum distances;
step 2.3.2: re-computing the centroid of each signal space;
step 2.3.3: and (4) repeatedly executing the step 2.3.1 to the step 2.3.2 until the mass centers do not change any more, and outputting K mass centers and corresponding signal spaces thereof.
2. The method for monitoring the stability of satellite step telemetry based on K-Means + + algorithm as claimed in claim 1, wherein the step 3 comprises: and counting the ratio of sample points falling in the signal space in the data to be monitored according to a statistical method so as to measure the matching degree of the data to be monitored and the standard signal space.
3. The method for monitoring the stability of satellite step telemetry based on the K-Means + + algorithm as claimed in claim 1, wherein the telemetry data segment is determined to be stable if the ratio of the sample points falling in the signal space in the data to be monitored is greater than or equal to a preset value, and otherwise the telemetry data segment is determined to be abnormal.
4. A satellite step telemetry stability monitoring system based on a K-Means + + algorithm is characterized by comprising:
a module M1: cutting and segmenting the satellite step change type telemetering signals by taking a natural day as a unit to obtain a telemetering data set;
a module M2: identifying a signal step scale according to the telemetering data set, and establishing a standard signal space;
a module M3: measuring the matching degree of the data to be monitored and a standard signal space;
a module M4: judging the stability according to the matching degree;
the module M2 comprises:
module M2.1: inputting a telemetering data set taking natural days as units;
module M2.2: selecting a centroid meeting preset conditions in the telemetry data set;
module M2.3: establishing a standard signal space according to the mass center;
said module M2.2 comprises:
randomly selecting a sample from the telemetry data set as an initial clustering center, calculating the shortest distance between each sample and the initial clustering center, and calculating the probability of each sample being selected as a centroid;
selecting K centroids in a wheel disc mode, wherein K is set according to the actual step condition of the telemetering data, and operating a K mean value clustering algorithm by taking the K centroids as the initialized centroids;
said module M2.3 comprises:
module m2.3.1: calculating Euclidean distances from each feature vector in the telemetry data set to K centroids, and dividing the Euclidean distances into signal spaces corresponding to the centroids with the minimum distances;
module m2.3.2: recalculating the centroid of each signal space;
module m2.3.3: and repeatedly executing the modules M2.3.1-M2.3.2 until the barycenter is not changed any more, and outputting K barycenters and corresponding signal spaces thereof.
5. The system for satellite step telemetry stability monitoring based on K-Means + + algorithm as claimed in claim 4, wherein the module M3 comprises: and counting the ratio of sample points falling in the signal space in the data to be monitored according to a statistical method so as to measure the matching degree of the data to be monitored and the standard signal space.
6. The system for monitoring the stability of satellite step telemetry based on the K-Means + + algorithm as claimed in claim 4, wherein the telemetry data segment is determined to be stable if the ratio of the sample points falling in the signal space in the data to be monitored is greater than or equal to a preset value, and otherwise the telemetry data segment is determined to be abnormal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011394595.5A CN112487362B (en) | 2020-12-03 | 2020-12-03 | Satellite step remote parameter stability monitoring method and system based on K-Means + + algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011394595.5A CN112487362B (en) | 2020-12-03 | 2020-12-03 | Satellite step remote parameter stability monitoring method and system based on K-Means + + algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112487362A CN112487362A (en) | 2021-03-12 |
CN112487362B true CN112487362B (en) | 2022-12-23 |
Family
ID=74939506
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011394595.5A Active CN112487362B (en) | 2020-12-03 | 2020-12-03 | Satellite step remote parameter stability monitoring method and system based on K-Means + + algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112487362B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104569694A (en) * | 2015-01-28 | 2015-04-29 | 北京空间飞行器总体设计部 | Electric signal feature extraction and recognition system oriented to aircraft flying process |
CN106354889A (en) * | 2016-11-07 | 2017-01-25 | 北京化工大学 | Batch process unequal-length time period synchronization method based on LWPT-DTW (lifting wavelet package transform-dynamic time warping) |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105794215B (en) * | 2013-12-06 | 2020-03-27 | Lg电子株式会社 | Apparatus and method for transmitting and receiving broadcast signal |
-
2020
- 2020-12-03 CN CN202011394595.5A patent/CN112487362B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104569694A (en) * | 2015-01-28 | 2015-04-29 | 北京空间飞行器总体设计部 | Electric signal feature extraction and recognition system oriented to aircraft flying process |
CN106354889A (en) * | 2016-11-07 | 2017-01-25 | 北京化工大学 | Batch process unequal-length time period synchronization method based on LWPT-DTW (lifting wavelet package transform-dynamic time warping) |
Non-Patent Citations (1)
Title |
---|
An Improved Scene Learning Method for Cloud Detection Based on NormalizedLinear Detector;Zhenyu An;《2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC)》;20200206;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112487362A (en) | 2021-03-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113255795B (en) | Equipment state monitoring method based on multi-index cluster analysis | |
Li et al. | A data-driven strategy for detection and diagnosis of building chiller faults using linear discriminant analysis | |
CN105184084B (en) | Method and system for predicting fault type of electric power metering automation terminal | |
US20070239629A1 (en) | Cluster Trending Method for Abnormal Events Detection | |
CN112910859B (en) | Internet of things equipment monitoring and early warning method based on C5.0 decision tree and time sequence analysis | |
EP3364157A1 (en) | Method and system of outlier detection in energy metering data | |
CN113592019B (en) | Fault detection method, device, equipment and medium based on multi-model fusion | |
CN104317681A (en) | Behavioral abnormality automatic detection method and behavioral abnormality automatic detection system aiming at computer system | |
CN105675038A (en) | Device for predicting faults of instruments | |
CN109947815B (en) | Power theft identification method based on outlier algorithm | |
CN111157850B (en) | Mean value clustering-based power grid line fault identification method | |
CN112070180B (en) | Power grid equipment state judging method and device based on information physical bilateral data | |
CN111126820A (en) | Electricity stealing prevention method and system | |
Chen et al. | A whole building fault detection using weather based pattern matching and feature based PCA method | |
CN112911627A (en) | Wireless network performance detection method, device and storage medium | |
CN112418065A (en) | Equipment operation state identification method, device, equipment and storage medium | |
CN114201374A (en) | Operation and maintenance time sequence data anomaly detection method and system based on hybrid machine learning | |
CN114266289A (en) | Complex equipment health state assessment method | |
CN113866455A (en) | Bridge acceleration monitoring data anomaly detection method, system and device based on deep learning | |
CN111932146A (en) | Method and device for analyzing pollution cause, computer equipment and readable storage medium | |
CN115617784A (en) | Data processing system and processing method for informationized power distribution | |
CN117076869B (en) | Time-frequency domain fusion fault diagnosis method and system for rotary machine | |
CN112487362B (en) | Satellite step remote parameter stability monitoring method and system based on K-Means + + algorithm | |
TWI639908B (en) | Method for detecting and diagnosing an abnormal process | |
CN114167837B (en) | Intelligent fault diagnosis method and system for railway signal 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 | ||
GR01 | Patent grant |