[go: nahoru, domu]

CN111366184A - Shield tunneling machine multi-sensor performance online monitoring method - Google Patents

Shield tunneling machine multi-sensor performance online monitoring method Download PDF

Info

Publication number
CN111366184A
CN111366184A CN202010303058.9A CN202010303058A CN111366184A CN 111366184 A CN111366184 A CN 111366184A CN 202010303058 A CN202010303058 A CN 202010303058A CN 111366184 A CN111366184 A CN 111366184A
Authority
CN
China
Prior art keywords
sensor
performance
matrix
information
steps
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
CN202010303058.9A
Other languages
Chinese (zh)
Other versions
CN111366184B (en
Inventor
张阐娟
李怀
张磊
刘作威
周远航
石富明
王春晓
刘伟涛
何建平
李凤远
刘洛汉
陈乾坤
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.)
China Railway Tunnel Group Co Ltd CRTG
Original Assignee
China Railway Tunnel Group Co Ltd CRTG
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 China Railway Tunnel Group Co Ltd CRTG filed Critical China Railway Tunnel Group Co Ltd CRTG
Priority to CN202010303058.9A priority Critical patent/CN111366184B/en
Publication of CN111366184A publication Critical patent/CN111366184A/en
Application granted granted Critical
Publication of CN111366184B publication Critical patent/CN111366184B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D18/00—Testing or calibrating apparatus or arrangements provided for in groups G01D1/00 - G01D15/00
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning

Landscapes

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

Abstract

The invention belongs to the technical field of shield machine detection, and provides an on-line monitoring method for the performance of multiple sensors of a shield machine. The shield machine multi-sensor performance on-line monitoring method is characterized by comprising the steps of fusing an expert system, an adaptive filtering method and a principal component analysis method to achieve shield machine multi-sensor performance on-line monitoring, enabling the expert system to conduct reasoning, judging and deciding on fault information input to a sensor, enabling the adaptive filtering method to adopt a normalized adaptive filter to convert a multi-sensor physical index measurement problem into an adjacent sensor signal delay point acquisition problem and extract delay information of adjacent sensors, and enabling a performance judgment system to adopt the principal component analysis method to conduct dimensionality reduction on an acquired original characteristic matrix of each sensor. The invention ensures the stability of the output of the sensor and solves the technical defect of monitoring the performance of the sensor of the shield tunneling machine.

Description

Shield tunneling machine multi-sensor performance online monitoring method
Technical Field
The invention belongs to the technical field of shield machine detection, and particularly relates to an online monitoring method for multi-sensor performance of a shield machine.
Background
The shield machine is a special device which can construct a tunnel supporting structure in the tunneling process of a tunnel, because the operation condition is hard and the working time is long, the electrical system part of the shield machine is easy to damage, in order to ensure the safe production, a large number of motors need to be maintained and monitored, a sensor is used as an important monitoring part, the performance monitoring precision of the sensor influences the operation performance of the whole shield machine, and the monitoring of the sensor of the shield machine is in an off-line state at present, so that a high-precision, simple and convenient multi-sensor on-line monitoring method needs to be invented. In addition, the stability of the output signal of the sensor in the full working condition range directly relates to the use reliability of the shield machine, but the working environment of the shield machine is poor, the noise is high, the signal output which can cause the sensor to sense is unstable, the engineering quality is reduced, and more resources are wasted.
Disclosure of Invention
The invention aims to provide an on-line monitoring method for the performance of multiple sensors of a shield machine, which can ensure the output stability of the sensors and solve the technical defect of monitoring the performance of the sensors of the shield machine.
The invention adopts the following technical scheme for solving the technical problems:
a shield constructs the online monitoring method of the machine multisensor performance, the online monitoring method of the machine multisensor performance of the shield constructs the online monitoring of machine multisensor performance of the machine by expert system, adaptive filtering and principal component analysis method and combines together; the expert system carries out reasoning, judgment and decision on the fault information input into the sensor, therefore, the information of the sensor and the related judgment result thereof are displayed on the monitoring main interface; the operation performance of the expert system comprises a pressure information performance index sample, a current information performance index sample and a performance decision system; the adaptive filtering adopts a normalized adaptive filter, converts the problem of measuring the physical indexes of the multiple sensors into the problem of acquiring the number of delay points of signals of adjacent sensors, extracting time delay information of adjacent sensors; the performance judgment system adopts a principal component analysis method to perform dimensionality reduction processing on the acquired original feature matrix of each sensor;
the self-adaptive filtering and denoising operation steps are as follows:
is provided with
Figure 100002_DEST_PATH_IMAGE001
And
Figure 361004DEST_PATH_IMAGE002
the method comprises the following steps of respectively inputting and outputting adjacent sensors:
(1) determining m-order filter weight coefficient matrix, and making the initial values of all weights be
Figure 100002_DEST_PATH_IMAGE003
For any fixed value or 0, the sampling time of each weight is carried outThe following steps are performed.
(2) Filter output signal
Figure 91194DEST_PATH_IMAGE004
；
(3) Calculating error
Figure 100002_DEST_PATH_IMAGE005
；
(4) Determining new weights for next time instant
Figure 244832DEST_PATH_IMAGE006
；
Ensuring the weight coefficient vector quantity when the self-adaptive filter is converged according to the steps (2) to (4)
Figure 577725DEST_PATH_IMAGE008
Obtaining a wiener solution, thereby removing noise and ensuring the measurement accuracy;
the method for extracting fault information by the principal component analysis method comprises the following steps:
(a) establishing a characteristic matrix of the sensor: the expert system comprises
Figure 329780DEST_PATH_IMAGE010
Each sample of sensors contains sensor fault characteristic value of which the quantity is
Figure 588461DEST_PATH_IMAGE012
Then the original feature matrix is composed of the sensor information samples in the system
Figure 100002_DEST_PATH_IMAGE013
;
Figure 730860DEST_PATH_IMAGE014
Variance of the values;
(c) computing
Figure 867444DEST_PATH_IMAGE016
Covariance matrix of
Figure 972541DEST_PATH_IMAGE018
：
Figure 100002_DEST_PATH_IMAGE019
;
(d) Computing
Figure 778954DEST_PATH_IMAGE018
Characteristic value of
Figure 100002_DEST_PATH_IMAGE021
And feature vector
Figure 100002_DEST_PATH_IMAGE023
In the covariance matrix, take the first
Figure 100002_DEST_PATH_IMAGE025
The characteristic value and corresponding characteristic vector according to
Figure 100002_DEST_PATH_IMAGE027
Calculating a principal component score matrix
Figure 100002_DEST_PATH_IMAGE029
Scoring a matrix from the principal components
Figure 179890DEST_PATH_IMAGE029
The cumulative contribution rate of (a) gives the number of principal components:
when in use
Figure 854584DEST_PATH_IMAGE029
The first G cumulative contribution rates reach to
Figure 315653DEST_PATH_IMAGE031
Then the original matrix
Figure 181715DEST_PATH_IMAGE033
The number of the main components is G;
and (d) realizing the dimension reduction processing of the fault feature matrix of the sensor according to the steps (a) to (f), reducing the complexity of the feature matrix, retaining the main information in the original feature space in the sample, enhancing the identification degree and facilitating the extraction of fault information.
The on-line monitoring method for the performance of the multiple sensors of the shield machine, provided by the invention, realizes the on-line monitoring of the performance of the multiple sensors of the shield machine by combining an expert system, a self-adaptive filtering method and a principal component analysis method, ensures the stability of the output of the sensors and solves the technical defect of the performance monitoring of the sensors of the shield machine.
Drawings
FIG. 1 is a schematic diagram of performance monitoring implementation of multiple sensors of a shield tunneling machine.
FIG. 2 is a diagram of a shield tunneling machine sensor monitoring expert system.
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.
An on-line monitoring method for the performance of multiple sensors of shield machine is characterized by that the on-line monitoring method for the performance of multiple sensors of shield machine is implemented by combining expert system, adaptive filter and principal component analysis method, the expert system can make reasoning, judgement and decision-making on the fault information of input sensor so as to display the information of sensor and its related judgement result on the monitoring main interface, and the operation performance of said expert system includes pressure information, current information performance index sample and performance decision-making system, and the adaptive filter adopts normalized adaptive filter to convert the physical index measurement problem of multiple sensors into the acquisition problem of delay point number of adjacent sensor signal, and can extract the delay information of adjacent sensor, can remove noise well and can prevent the monitoring system from being influenced by model error and external noise, the validity of the monitoring result is ensured, and the monitoring precision is improved. And the performance judgment system adopts a principal component analysis method to perform dimensionality reduction processing on the acquired original characteristic matrix of each sensor, so that the complexity of the characteristic matrix is reduced, main information in an original characteristic space in a sample is reserved, the identification degree is enhanced, and fault information is convenient to extract.
FIG. 1 is a schematic diagram of performance monitoring implementation of a shield machine speed sensor, and as shown in FIG. 1, the performance monitoring of the shield machine speed sensor of the present invention includes an expert system, an adaptive filtering method and a principal component analysis method;
the self-adaptive filtering and denoising operation steps are as follows:
is provided with
Figure DEST_PATH_IMAGE034
Respectively the input and output of adjacent sensors.
(1) Determining m-order filter weight coefficient matrix, and making the initial values of all weights be
Figure DEST_PATH_IMAGE036
For any fixed value or 0, the following steps are executed at the rest sampling time of each weight;
(2) filter output signal
Figure 236390DEST_PATH_IMAGE037
;
(3) Calculating error
Figure DEST_PATH_IMAGE038
;
(4) Determining new weights for next time instant
Figure 885415DEST_PATH_IMAGE039
;
Ensuring the weight coefficient vector quantity when the self-adaptive filter is converged according to the steps (2) to (4)
Figure DEST_PATH_IMAGE040
And obtaining a wiener solution, thereby removing noise and ensuring the measurement accuracy.
The method for extracting fault information by the principal component analysis method comprises the following steps:
(a) establishing a characteristic moment of a sensorArraying: the expert system comprises
Figure DEST_PATH_IMAGE042
Each sample of sensors contains sensor fault characteristic value of which the quantity is
Figure DEST_PATH_IMAGE044
Then the original feature matrix is composed of the sensor information samples in the system
Figure 778154DEST_PATH_IMAGE045
;
Figure DEST_PATH_IMAGE046
Variance of the values;
(c) computing
Figure 424904DEST_PATH_IMAGE016
Covariance matrix of
Figure 91509DEST_PATH_IMAGE018
：
Figure 108007DEST_PATH_IMAGE047
;
(d) Computing
Figure 543667DEST_PATH_IMAGE018
Characteristic value of
Figure DEST_PATH_IMAGE048
And feature vector
Figure 689216DEST_PATH_IMAGE049
In the covariance matrix, take the first
Figure 577537DEST_PATH_IMAGE025
The characteristic value and corresponding characteristic vector according to
Figure DEST_PATH_IMAGE050
Calculating a principal component score matrix
Figure 833944DEST_PATH_IMAGE029
Scoring a matrix from the principal components
Figure 61794DEST_PATH_IMAGE029
The cumulative contribution rate of (a) gives the number of principal components:
when in use
Figure 942025DEST_PATH_IMAGE029
The first G cumulative contribution rates reach to
Figure 753861DEST_PATH_IMAGE031
Then the original matrix
Figure 112161DEST_PATH_IMAGE033
The number of the main components is G;
and (d) realizing the dimension reduction processing of the fault feature matrix of the sensor according to the steps (a) to (f), reducing the complexity of the feature matrix, retaining the main information in the original feature space in the sample, enhancing the identification degree and facilitating the extraction of fault information.
As shown in FIG. 1, the expert system theory construction related to the invention is composed of five parts, namely a knowledge base, an inference engine, a comprehensive database, a human-computer interface and knowledge acquisition. The knowledge base is used for storing experience knowledge of experts in the field of the shield tunneling machine and providing knowledge required for solving problems for the inference machine. In knowledge acquisition, machine learning is utilized to establish a computer software system with the realities of the sensor field and the empirical knowledge specific to an expert, and the whole expert system is coordinated and controlled. And establishing an initial evidence, an intermediate result and a sensor performance monitoring result of sensor reasoning in the comprehensive database, thereby improving the control performance.
As shown in fig. 2, the expert system design structure of the present invention includes a monitoring system submodule, a three-dimensional simulation module, a fault processing submodule, etc. of various sensors, and sends the sensor data obtained by signal acquisition to a computer for monitoring, analysis, fault processing, etc., and can monitor the performance of the sensors on line and provide a visual three-dimensional monitoring interface. Sending out an alarm signal when the performance index of the monitoring sensor exceeds a threshold value; the expert system can be correspondingly set according to the requirements of users, wherein each sensor monitoring module is used for selecting the input parameters of each sensor to generate corresponding early warning information, judging whether the input parameters deviate from a performance target, and generating a 3D simulation model according to design requirements, so that the sensors can be conveniently stored and data can be conveniently replaced. Each sensor data module is used for establishing various sensor monitoring data tables of the shield machine, the monitoring server and the basic database are in butt joint through the Ethernet, and fault points are found in the three-dimensional simulation module through data fusion, so that the sensors can be conveniently monitored and analyzed.
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. While the invention has been shown and described with respect to the preferred embodiments, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the scope of the invention as defined in the following claims.

Claims (1)

1. The on-line monitoring method for the performance of the multiple sensors of the shield tunneling machine is characterized by comprising the following steps: the on-line monitoring method for the performance of the multiple sensors of the shield machine is implemented by fusing an expert system, a self-adaptive filtering method and a principal component analysis method; the expert system carries out reasoning, judgment and decision on the fault information input into the sensor, therefore, the information of the sensor and the related judgment result thereof are displayed on the monitoring main interface; the operation performance of the expert system comprises a pressure information performance index sample, a current information performance index sample and a performance decision system; the adaptive filtering adopts a normalized adaptive filter, converts the problem of measuring the physical indexes of the multiple sensors into the problem of acquiring the number of delay points of signals of adjacent sensors, extracting time delay information of adjacent sensors; the performance judgment system adopts a principal component analysis method to perform dimensionality reduction processing on the acquired original feature matrix of each sensor;
the self-adaptive filtering and denoising operation steps are as follows:
is provided with
Figure DEST_PATH_IMAGE001
And
Figure 286452DEST_PATH_IMAGE002
the method comprises the following steps of respectively inputting and outputting adjacent sensors:
(1) determining m-order filter weight coefficient matrix, and making the initial values of all weights be
Figure DEST_PATH_IMAGE003
For any fixed value or 0, the remaining sampling instants for each weight perform the following steps.
(2) Filter output signal
Figure 711486DEST_PATH_IMAGE004
；
(3) Calculating error
Figure DEST_PATH_IMAGE005
；
(4) Determining new weights for next time instant
Figure 512083DEST_PATH_IMAGE006
；
Ensuring the weight coefficient vector quantity when the self-adaptive filter is converged according to the steps (2) to (4)
Figure 674074DEST_PATH_IMAGE008
Obtaining a wiener solution, thereby removing noise and ensuring the measurement accuracy;
the method for extracting fault information by the principal component analysis method comprises the following steps:
(a) establishing a characteristic matrix of the sensor: the expert system comprises
Figure 132910DEST_PATH_IMAGE010
Each sample of sensors contains sensor fault characteristic value of which the quantity is
Figure 354944DEST_PATH_IMAGE012
Then the original feature matrix is composed of the sensor information samples in the system
Figure DEST_PATH_IMAGE013
;
Figure 16738DEST_PATH_IMAGE014
Variance of the values;
(c) computing
Figure 982420DEST_PATH_IMAGE016
Covariance matrix of
Figure 600221DEST_PATH_IMAGE018
：
Figure DEST_PATH_IMAGE019
;
(d) Computing
Figure 39162DEST_PATH_IMAGE018
Characteristic value of
Figure DEST_PATH_IMAGE021
And feature vector
Figure DEST_PATH_IMAGE023
In the covariance matrix, take the first
Figure DEST_PATH_IMAGE025
The characteristic value and corresponding characteristic vector according to
Figure DEST_PATH_IMAGE027
Calculating a principal component score matrix
Figure DEST_PATH_IMAGE029
Scoring a matrix from the principal components
Figure 63618DEST_PATH_IMAGE029
The cumulative contribution rate of (a) gives the number of principal components:
when in use
Figure 567412DEST_PATH_IMAGE029
The first G cumulative contribution rates reach to
Figure 305299DEST_PATH_IMAGE031
Then the original matrix
Figure 603556DEST_PATH_IMAGE033
The number of the main components is G;
and (d) realizing the dimension reduction processing of the fault feature matrix of the sensor according to the steps (a) to (f), reducing the complexity of the feature matrix, retaining the main information in the original feature space in the sample, enhancing the identification degree and facilitating the extraction of fault information.
CN202010303058.9A 2020-04-17 2020-04-17 Shield tunneling machine multi-sensor performance online monitoring method Active CN111366184B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010303058.9A CN111366184B (en) 2020-04-17 2020-04-17 Shield tunneling machine multi-sensor performance online monitoring method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010303058.9A CN111366184B (en) 2020-04-17 2020-04-17 Shield tunneling machine multi-sensor performance online monitoring method

Publications (2)

Publication Number Publication Date
CN111366184A true CN111366184A (en) 2020-07-03
CN111366184B CN111366184B (en) 2022-03-01

Family

ID=71210849

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010303058.9A Active CN111366184B (en) 2020-04-17 2020-04-17 Shield tunneling machine multi-sensor performance online monitoring method

Country Status (1)

Country Link
CN (1) CN111366184B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113671471A (en) * 2021-08-18 2021-11-19 中国科学院声学研究所北海研究站 Underwater sound target detection blind source separation method

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6417797B1 (en) * 1998-07-14 2002-07-09 Cirrus Logic, Inc. System for A multi-purpose portable imaging device and methods for using same
CN104462846A (en) * 2014-12-22 2015-03-25 山东鲁能软件技术有限公司 Intelligent device failure diagnosis method based on support vector machine
CN106344005A (en) * 2016-10-28 2017-01-25 张珈绮 Mobile ECG (electrocardiogram) monitoring system and monitoring method
CN107438398A (en) * 2015-01-06 2017-12-05 大卫·伯顿 Portable wearable monitoring system
CN107748314A (en) * 2017-10-18 2018-03-02 国网重庆市电力公司北碚供电分公司 Transformer Faults Analysis system based on sound wave shock detection
CN108844533A (en) * 2018-04-24 2018-11-20 西安交通大学 A kind of free posture PDR localization method based on Multi-sensor Fusion and attitude algorithm
AU2019101183A4 (en) * 2019-10-02 2020-01-16 Han, Yining MISS Feature Extraction and Fusion for Industrial Data

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6417797B1 (en) * 1998-07-14 2002-07-09 Cirrus Logic, Inc. System for A multi-purpose portable imaging device and methods for using same
CN104462846A (en) * 2014-12-22 2015-03-25 山东鲁能软件技术有限公司 Intelligent device failure diagnosis method based on support vector machine
CN107438398A (en) * 2015-01-06 2017-12-05 大卫·伯顿 Portable wearable monitoring system
CN106344005A (en) * 2016-10-28 2017-01-25 张珈绮 Mobile ECG (electrocardiogram) monitoring system and monitoring method
CN107748314A (en) * 2017-10-18 2018-03-02 国网重庆市电力公司北碚供电分公司 Transformer Faults Analysis system based on sound wave shock detection
CN108844533A (en) * 2018-04-24 2018-11-20 西安交通大学 A kind of free posture PDR localization method based on Multi-sensor Fusion and attitude algorithm
AU2019101183A4 (en) * 2019-10-02 2020-01-16 Han, Yining MISS Feature Extraction and Fusion for Industrial Data

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
徐志远 等: "基于维纳滤波和主成分分析的脉冲涡流检测信号降噪方法", 《传感器技术学报》 *
毛前军 等: "基于经验模态分解去噪改进主成分分析的冷水机组传感器故障检测", 《暖通空调》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113671471A (en) * 2021-08-18 2021-11-19 中国科学院声学研究所北海研究站 Underwater sound target detection blind source separation method
CN113671471B (en) * 2021-08-18 2024-04-30 中国科学院声学研究所北海研究站 Underwater sound target detection blind source separation method

Also Published As

Publication number Publication date
CN111366184B (en) 2022-03-01

Similar Documents

Publication Publication Date Title
KR102011227B1 (en) Methods, and apparatus for monitoring failures of computer storage media, computer program products, and wind generator sets
CN110895526A (en) Method for correcting data abnormity in atmosphere monitoring system
CN114723285B (en) Power grid equipment safety evaluation prediction method
US20190121838A1 (en) A dynamically non-gaussian anomaly identification method for structural monitoring data
CN112565164B (en) Dangerous IP identification method, dangerous IP identification device and computer readable storage medium
CN111366184B (en) Shield tunneling machine multi-sensor performance online monitoring method
CN116049146B (en) Database fault processing method, device, equipment and storage medium
CN109729069B (en) Abnormal IP address detection method and device and electronic equipment
CN111046327A (en) Prony analysis method suitable for low-frequency oscillation and subsynchronous oscillation identification
JP2019105871A (en) Abnormality candidate extraction program, abnormality candidate extraction method and abnormality candidate extraction apparatus
CN112200060A (en) Network model-based rotating equipment fault diagnosis method and system and readable storage medium
CN116522096A (en) Three-dimensional digital twin content intelligent manufacturing method based on motion capture
CN109462242A (en) Electric system low-frequency oscillation detection method based on IIR digital filtering and ESPRIT identification algorithm
CN115705413A (en) Method and device for determining abnormal log
CN115225373B (en) Network space security situation expression method and device under incomplete information condition
CN115766176A (en) Network traffic processing method, device, equipment and storage medium
CN115168154A (en) Abnormal log detection method, device and equipment based on dynamic baseline
CN113236506B (en) Industrial time delay system fault detection method based on filtering
CN114881112A (en) System anomaly detection method, device, equipment and medium
CN117056711B (en) Multi-source data-based solder paste printer performance evaluation method, system and storage medium
CN115829160B (en) Time sequence abnormality prediction method, device, equipment and storage medium
CN118214691B (en) Network state abnormal data monitoring method, device, equipment, medium and product
CN117647392B (en) Downhole drilling instrument scrapping monitoring and early warning system based on data analysis
CN116796229A (en) Equipment fault detection method, device, equipment and storage medium
CN117367806A (en) Three-phase alternating current motor bearing fault detection method, device, equipment and medium

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