CN107832896B - Power plant equipment slow-changing fault early warning method and device - Google Patents
Power plant equipment slow-changing fault early warning method and device Download PDFInfo
- Publication number
- CN107832896B CN107832896B CN201711228433.2A CN201711228433A CN107832896B CN 107832896 B CN107832896 B CN 107832896B CN 201711228433 A CN201711228433 A CN 201711228433A CN 107832896 B CN107832896 B CN 107832896B
- Authority
- CN
- China
- Prior art keywords
- fault
- cluster
- data
- real
- power plant
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000013598 vector Substances 0.000 claims abstract description 243
- 238000012544 monitoring process Methods 0.000 claims abstract description 161
- 239000003550 marker Substances 0.000 claims abstract description 134
- 238000004422 calculation algorithm Methods 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 12
- 238000007621 cluster analysis Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 238000004138 cluster model Methods 0.000 claims description 4
- 230000001960 triggered effect Effects 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 9
- 239000003245 coal Substances 0.000 description 26
- 238000002485 combustion reaction Methods 0.000 description 6
- 230000002269 spontaneous effect Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003111 delayed effect Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000005094 computer simulation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The embodiment of the invention discloses a method and a device for early warning of a slowly-varying fault of power plant equipment. According to the method, the fault condition data and the normal condition data in the historical data of the power plant equipment are modeled and subjected to clustering analysis to obtain the normal condition data and the cluster marker vectors corresponding to the fault condition data, then the real-time monitoring data are input into a clustering model to obtain the cluster marker vectors of the real-time monitoring data, and the cluster marker vectors of the real-time monitoring data are matched with the cluster marker vectors corresponding to the normal condition data and the fault condition data, so that whether the power plant equipment normally operates or in a gradual fault evolution process can be judged, the fault type and early warning time of a gradual fault occurring in the equipment are obtained, and a worker is prompted to timely overhaul before the fault is formed, and the technical problems that the early warning method of the fault of the power plant equipment is lagged and effective prediction cannot be carried out before the fault occurs are solved.
Description
Technical Field
The invention relates to the field of power monitoring, in particular to a method and a device for early warning of a slowly-varying fault of power plant equipment.
Background
The working environment that thermal equipment in thermal power plant is located is abominable, and the emergence of trouble not only reduces the stability of production process, still makes the security in the production process can't obtain guaranteeing.
The current thermal power plant thermal equipment fault early warning method is limited in that when a fault occurs, the fault is warned and the fault type is judged, and although the fault occurrence of workers is reminded, the fault cannot be predicted before the fault occurs.
Therefore, the technical problems that the early warning of the current power plant equipment fault early warning method is delayed and effective prediction cannot be carried out before the fault occurs are caused.
Disclosure of Invention
The invention provides a power plant equipment slowly-changing fault early warning method and device, and solves the technical problem that the early warning of the current power plant equipment fault early warning method is lagged and the effective prediction cannot be carried out before the fault occurs.
The invention provides a power plant equipment slowly-changing fault early warning method, which comprises the following steps:
s1: taking a time period between a fault initial evolution time point and a fault occurrence time point in historical data of power plant equipment as a fault evolution time period, taking a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as a normal working condition time period, acquiring fault working condition data of a fault evolution time period and normal working condition data of a slowly-varying fault of at least one power plant equipment in the historical data, standardizing the fault working condition data and the normal working condition data, and splicing the fault working condition data and the normal working condition data after the standardization processing into modeling data;
s2: calculating the optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm;
s3: establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data, respectively acquiring cluster marking vectors corresponding to normal working condition data and fault working condition data, and recording the fault type and early warning time range of the slowly-varying fault of the power plant equipment corresponding to each cluster marking vector corresponding to the fault working condition data;
s4: the method comprises the steps of obtaining real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into a clustering model to obtain cluster marking vectors of the real-time monitoring data, matching the cluster marking vectors of the real-time monitoring data with cluster marking vectors corresponding to normal working condition data, judging whether the cluster marking vectors of the real-time monitoring data belong to the cluster marking vectors corresponding to the normal working condition data, if not, matching the cluster marking vectors of the real-time monitoring data with all the cluster marking vectors in fault working condition data, and obtaining fault types and early warning time ranges of the slowly-varying faults of the power plant equipment corresponding to the cluster marking vectors of the real-time monitoring data.
Preferably, step S3 specifically includes:
s31: establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data, and respectively obtaining cluster mark vectors corresponding to normal working condition data and fault working condition data;
s32: acquiring and recording the fault type of the gradual change fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault condition data;
s33: acquiring data acquisition time points of fault working condition data corresponding to each cluster marker vector, calculating evolution time between each data acquisition time point and a fault occurrence time point respectively, and acquiring and recording an early warning time range of each cluster marker vector according to the shortest evolution time and the longest evolution time corresponding to each cluster marker vector.
Preferably, step S4 specifically includes:
s41: acquiring real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into a clustering model to acquire cluster marker vectors of the real-time monitoring data, matching the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal working condition data, and judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal working condition data, if so, the power plant equipment operates normally, otherwise, the step S42 is executed;
s42: matching the cluster marker vectors of the real-time monitoring data with each cluster marker vector in the fault working condition data, judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the fault working condition data, if so, executing step S43, otherwise, executing step S44;
s43: acquiring a fault type and an early warning time range of the gradual change fault of the power plant equipment corresponding to the cluster mark vector of the real-time monitoring data;
s44: the status of the power plant is marked as abnormal.
Preferably, step S41 specifically includes: acquiring real-time monitoring data of power plant equipment, standardizing the real-time monitoring data, inputting the processed real-time monitoring data into a clustering model to acquire cluster marker vectors of the real-time monitoring data, matching the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal working condition data, and judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal working condition data, if so, the power plant equipment operates normally, otherwise, executing the step S42.
Preferably, step S4 is followed by: step S5;
s5: and returns to step S4 after the first preset time.
The invention provides a power plant equipment slowly-changing fault early warning device which is characterized by comprising the following components:
the data acquisition module is used for acquiring fault condition data of at least one power plant equipment slowly-varying fault evolution period and normal condition data of the normal condition period in historical data by taking a time period between a fault initial evolution time point and a fault occurrence time point in the historical data of the power plant equipment as a fault evolution period and taking a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as the normal condition period, standardizing the fault condition data and the normal condition data and splicing the standardized fault condition data and the standardized normal condition data into modeling data;
the cluster selection module is used for calculating the optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm;
the cluster analysis module is used for establishing a cluster model according to the optimal cluster number to perform cluster analysis on the modeling data, respectively acquiring cluster mark vectors corresponding to normal working condition data and fault working condition data, and recording the fault type and the early warning time range of the slowly-varying fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault working condition data;
and the state early warning module is used for acquiring real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into the clustering model to acquire cluster marking vectors of the real-time monitoring data, matching the cluster marking vectors of the real-time monitoring data with cluster marking vectors corresponding to normal working condition data, judging whether the cluster marking vectors of the real-time monitoring data belong to the cluster marking vectors corresponding to the normal working condition data, if not, matching the cluster marking vectors of the real-time monitoring data with each cluster marking vector in fault working condition data, and acquiring the fault type and early warning time range of the slowly-varying fault of the power plant equipment corresponding to the cluster marking vectors of the real-time monitoring data.
Preferably, the cluster analysis module specifically includes:
the vector submodule is used for establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data and respectively acquiring cluster mark vectors corresponding to normal working condition data and fault working condition data;
a recording submodule for acquiring and recording the fault type of the gradual change fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault working condition data
And the range submodule is used for acquiring data acquisition time points of fault working condition data corresponding to each cluster marker vector, calculating evolution time between each data acquisition time point and a fault occurrence time point respectively, and acquiring and recording the early warning time range of each cluster marker vector according to the shortest evolution time and the longest evolution time corresponding to each cluster marker vector.
Preferably, the state early warning module specifically includes:
the normal submodule is used for acquiring real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into the clustering model to acquire cluster marking vectors of the real-time monitoring data, matching the cluster marking vectors of the real-time monitoring data with cluster marking vectors corresponding to normal working condition data, and judging whether the cluster marking vectors of the real-time monitoring data belong to the cluster marking vectors corresponding to the normal working condition data or not;
the judging submodule is used for matching the cluster marker vector of the real-time monitoring data with each cluster marker vector in the fault working condition data, judging whether the cluster marker vector of the real-time monitoring data belongs to the cluster marker vector corresponding to the fault working condition data, if so, triggering the fault submodule, and if not, triggering the abnormal submodule;
the fault submodule is used for acquiring the fault type and the early warning time range of the slowly-varying fault of the power plant equipment corresponding to the cluster marking vector of the real-time monitoring data;
and the abnormality submodule is used for marking the state of the power plant equipment as abnormal.
Preferably, the normal sub-module is specifically configured to obtain real-time monitoring data of the power plant equipment, standardize the real-time monitoring data, input the processed real-time monitoring data into the clustering model to obtain cluster marker vectors of the real-time monitoring data, match the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal operating condition data, and determine whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal operating condition data, if yes, the power plant equipment operates normally, and if not, the determining sub-module is triggered.
Preferably, the method further comprises the following steps: a repeat execution module;
and the repeated execution module is used for triggering the state early warning module again after the first preset time.
According to the technical scheme, the invention has the following advantages:
the invention provides a power plant equipment slowly-changing fault early warning method, which comprises the following steps: s1: taking a time period between a fault initial evolution time point and a fault occurrence time point in historical data of power plant equipment as a fault evolution time period, taking a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as a normal working condition time period, acquiring fault working condition data of a fault evolution time period and normal working condition data of a slowly-varying fault of at least one power plant equipment in the historical data, standardizing the fault working condition data and the normal working condition data, and splicing the fault working condition data and the normal working condition data after the standardization processing into modeling data; s2: calculating the optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm; s3: establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data, respectively acquiring cluster marking vectors corresponding to normal working condition data and fault working condition data, and recording the fault type and early warning time range of the slowly-varying fault of the power plant equipment corresponding to each cluster marking vector corresponding to the fault working condition data; s4: the method comprises the steps of obtaining real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into a clustering model to obtain cluster marking vectors of the real-time monitoring data, matching the cluster marking vectors of the real-time monitoring data with cluster marking vectors corresponding to normal working condition data, judging whether the cluster marking vectors of the real-time monitoring data belong to the cluster marking vectors corresponding to the normal working condition data, if not, matching the cluster marking vectors of the real-time monitoring data with all the cluster marking vectors in fault working condition data, and obtaining fault types and early warning time ranges of the slowly-varying faults of the power plant equipment corresponding to the cluster marking vectors of the real-time monitoring data.
The invention carries out modeling and cluster analysis by using fault condition data and normal condition data in historical data of power plant equipment to obtain cluster marking vectors corresponding to the normal condition data and the fault condition data, then inputs real-time monitoring data into a cluster model to obtain the cluster marking vectors of the real-time monitoring data, matches the cluster marking vectors of the real-time monitoring data with the cluster marking vectors corresponding to the normal condition data and the fault condition data, can judge whether the power plant equipment normally operates or in the gradual fault evolution process, and can obtain the fault type and the early warning time of the gradual fault of the power plant equipment according to the cluster marking vectors of the real-time monitoring data because the fault type and the early warning time range of the gradual fault of the power plant equipment corresponding to the cluster marking vectors of the fault condition data are recorded so as to prompt a worker to overhaul the equipment in time before the fault is formed, the technical problem that the early warning of the current power plant equipment fault early warning method is delayed and effective prediction cannot be carried out before the fault occurs is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without inventive exercise.
Fig. 1 is a schematic flow chart of an embodiment of a method for warning a slowly-varying fault of a power plant according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a power plant equipment creep fault warning method according to another embodiment of the present invention;
fig. 3 is a schematic structural diagram of an embodiment of a power plant equipment creep fault early warning device according to an embodiment of the present invention.
Detailed Description
The embodiment of the invention provides a method and a device for early warning of a slowly-varying fault of power plant equipment, which solve the technical problem that the early warning of the current method for early warning of the fault of the power plant equipment is lagged and the effective prediction cannot be carried out before the fault occurs.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. 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 of the present invention provides an embodiment of a method for warning a gradual fault of a power plant device, including:
step 101: taking a time period between a fault initial evolution time point and a fault occurrence time point in historical data of power plant equipment as a fault evolution time period, taking a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as a normal working condition time period, acquiring fault working condition data of a fault evolution time period and normal working condition data of a slowly-varying fault of at least one power plant equipment in the historical data, standardizing the fault working condition data and the normal working condition data, and splicing the fault working condition data and the normal working condition data after the standardization processing into modeling data;
it should be noted that before the power plant equipment creep fault early warning is performed, an early warning model of the power plant equipment creep fault needs to be established, so that fault condition data and normal condition data in historical data need to be acquired as modeling data to establish a model.
Step 102: calculating the optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm;
it should be noted that the contour coefficient algorithm (Silhouette analysis algorithm) is a clustering evaluation algorithm, and can evaluate whether the clustering effect is good or bad by calculating the contour coefficient, and the contour coefficient algorithm can be used for evaluating the influence of different algorithms or different operation modes of the algorithms on the clustering result on the basis of the same original data by combining two factors of cohesion and separation;
the optimal cluster number of the modeling data in the preset cluster number searching range can be calculated and obtained through a contour coefficient algorithm.
Step 103: establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data, respectively acquiring cluster marking vectors corresponding to normal working condition data and fault working condition data, and recording the fault type and early warning time range of the slowly-varying fault of the power plant equipment corresponding to each cluster marking vector corresponding to the fault working condition data;
it should be noted that after the modeling data are analyzed, cluster marker vectors corresponding to normal working condition data and fault working condition data can be obtained, and the fault type and early warning time range of the gradual change fault of the power plant equipment corresponding to each cluster marker vector corresponding to the fault working condition data are recorded.
Step 104: acquiring real-time monitoring data of power plant equipment, inputting the real-time monitoring data into a clustering model to acquire cluster marker vectors of the real-time monitoring data, matching the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal working condition data, judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal working condition data, and if not, executing the step 105;
it should be noted that, after the real-time monitoring data is input into the clustering model, the cluster marker vector of the real-time monitoring can be obtained, and the cluster marker vector can be used to judge whether the real-time monitoring data belongs to normal working condition data or fault working condition data.
Step 105: and matching the cluster mark vectors of the real-time monitoring data with each cluster mark vector in the fault working condition data to obtain the fault type and the early warning time range of the gradual change fault of the power plant equipment corresponding to the cluster mark vectors of the real-time monitoring data.
It should be noted that, when the real-time monitoring data is judged to be fault condition data, the real-time monitoring data can be matched with the cluster marking vector corresponding to the fault condition data, so as to obtain the fault type and the early warning time range of the gradual change fault of the power plant equipment corresponding to the cluster marking vector of the real-time monitoring data.
In the embodiment, modeling is performed through fault condition data and normal condition data before a slowly-varying fault of the power plant, cluster marking vectors corresponding to the normal condition data and the fault condition data are obtained, then real-time monitoring data are input into a clustering model to obtain cluster marking vectors of the real-time monitoring data, the cluster marking vectors of the real-time monitoring data are matched with the cluster marking vectors corresponding to the normal condition data and the fault condition data, so that whether the power plant equipment runs normally or in a slowly-varying fault evolution process can be judged, and because the fault type and the early-warning time range of the slowly-varying fault of the power plant equipment corresponding to the cluster marking vectors of the fault condition data are recorded, the fault type and the early-warning time of the slowly-varying fault occurring in the equipment can be obtained according to the cluster marking vectors of the real-time monitoring data, so as to prompt a worker to overhaul in time before the fault is, the technical problem that the early warning of the current power plant equipment fault early warning method is delayed and effective prediction cannot be carried out before the fault occurs is solved.
The above is an embodiment of a method for warning a gradual failure of a power plant according to an embodiment of the present invention, and the following is another embodiment of a method for warning a gradual failure of a power plant according to an embodiment of the present invention.
Referring to fig. 2, an embodiment of the present invention provides another embodiment of a method for warning a gradual fault of a power plant device, including:
step 201: taking a time period between a fault initial evolution time point and a fault occurrence time point in historical data of power plant equipment as a fault evolution time period, taking a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as a normal working condition time period, acquiring fault working condition data of a fault evolution time period and normal working condition data of a slowly-varying fault of at least one power plant equipment in the historical data, standardizing the fault working condition data and the normal working condition data, and splicing the fault working condition data and the normal working condition data after the standardization processing into modeling data;
it should be noted that, if the power plant equipment generates a gradual fault a at 12 points, and observation data shows that 11 points start gradual fault evolution, a time period from 11 points to 12 points is used as a fault evolution period;
setting a preset time point before the initial evolution time point of the fault as a normal time point according to the actual requirements of the engineering, and if half an hour before the initial evolution of the default fault is the normal time point, taking a time period from 10 to 11 as a normal working condition time period;
and acquiring fault working condition data of a time period from 11 points to 12 points and normal working condition data of a time period from 10 points to half to 11 points, and carrying out standardization processing and splicing to obtain modeling data.
Step 202: calculating the optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm;
it should be noted that, if the preset cluster number search range is [2,8], the optimal cluster number may be calculated through the contour coefficient algorithm, for example, the optimal cluster number is 5.
Step 203: establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data, and respectively obtaining cluster mark vectors corresponding to normal working condition data and fault working condition data;
it should be noted that, after clustering, the normal operating condition data is divided into two classes, the cluster flag vectors are a1 and a2, and the fault operating condition data is divided into three classes, the cluster flag vectors are B1, B2 and B3.
Step 204: acquiring and recording the fault type of the gradual change fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault condition data;
it should be noted that, when the modeling data is obtained as described above, three kinds of faults are selected, and each cluster flag vector is one of B1, B2, or B3.
Step 205: acquiring data acquisition time points of fault working condition data corresponding to each cluster marker vector, respectively calculating evolution time between each data acquisition time point and a fault occurrence time point, and acquiring and recording an early warning time range of each cluster marker vector according to the shortest evolution time and the longest evolution time corresponding to each cluster marker vector;
it should be noted that each cluster marker vector contains a series of data, and thus, if B1 cluster marker vectors contain B1, B2, B3 and B4 data, B1 data acquisition time is 11 minutes from 11, B2 data acquisition time is 11 minutes from 21 from 11, B3 data acquisition time is 11 minutes from 31 from 11 and B4 data acquisition time is 11 minutes from 41, the time difference between 11 and 12 is 19 minutes for the shortest evolution time, and the time difference between 11 and 12 is 49 minutes for the longest evolution time, the early warning time range is [19,49], that is, when the real-time monitoring data is B1 cluster marker vectors, a fault occurs in the range of [19,49] minutes.
Step 206: acquiring real-time monitoring data of power plant equipment, inputting the real-time monitoring data into a clustering model to acquire cluster marker vectors of the real-time monitoring data, matching the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal working condition data, and judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal working condition data, if so, executing a step 207, otherwise, executing a step 208;
it should be noted that, the real-time monitoring data is input into the clustering model to obtain the cluster marker vector of the real-time monitoring data, and whether the cluster marker vector is the cluster marker vector corresponding to the normal operating condition data is determined, if the cluster marker vector of the real-time monitoring data is a1, step 207 is executed, and if the cluster marker vector of the real-time monitoring data is B1, step 208 is executed.
Step 207: the power plant equipment normally operates;
it should be noted that the cluster marker vector of the real-time monitoring data belongs to the cluster marker vector corresponding to the normal working condition data, which indicates that the power plant equipment is operating normally.
Step 208: matching the cluster marker vectors of the real-time monitoring data with each cluster marker vector in the fault working condition data, judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the fault working condition data, if so, executing a step 209, and if not, executing a step 210;
it should be noted that, when it is determined that the cluster flag vector of the real-time monitoring data is not the cluster flag vector corresponding to the normal operating condition data, it is determined that the cluster flag vector of the real-time monitoring data is not the cluster flag vector corresponding to the fault operating condition data, if the cluster flag vector of the real-time monitoring data is B1, step 209 is executed, and if the cluster flag vector of the real-time monitoring data is C1, step 210 is executed.
Step 209: acquiring a fault type and an early warning time range of the gradual change fault of the power plant equipment corresponding to the cluster mark vector of the real-time monitoring data;
it should be noted that when the cluster marker vector of the real-time monitoring data is B1 and is judged to be the cluster marker vector corresponding to the fault working condition data, the fault type and the early warning time range [19,49] of the gradual change fault of the power plant equipment corresponding to B1 are acquired;
step 210: marking the status of the power plant equipment as abnormal;
it should be noted that when the cluster marker vector of the real-time monitoring data is C1, C1 is not the cluster marker vector obtained after clustering the modeling data, and at this time, the power plant equipment may be in normal operation, but the data is different from the above normal operating condition data, and the power plant equipment may also be in the fault evolution process of other gradual faults, so that the state of the power plant equipment is marked as abnormal to remind a worker to check, and if the power plant equipment is in the fault evolution process of other gradual faults, C1 may also be recorded in the database as the cluster marker vector corresponding to the fault operating condition data.
Step 211: and returns to step 206 after the first preset time.
It should be noted that in the actual production process, detection and judgment need to be performed cyclically, and if the half-hour check is set once, the first preset time is 30 minutes.
In the embodiment, modeling is performed through fault condition data and normal condition data before a slowly-varying fault of the power plant, cluster marking vectors corresponding to the normal condition data and the fault condition data are obtained, then real-time monitoring data are input into a clustering model to obtain cluster marking vectors of the real-time monitoring data, the cluster marking vectors of the real-time monitoring data are matched with the cluster marking vectors corresponding to the normal condition data and the fault condition data, so that whether the power plant equipment runs normally or in a slowly-varying fault evolution process can be judged, and because the fault type and the early-warning time range of the slowly-varying fault of the power plant equipment corresponding to the cluster marking vectors of the fault condition data are recorded, the fault type and the early-warning time of the slowly-varying fault occurring in the equipment can be obtained according to the cluster marking vectors of the real-time monitoring data, so as to prompt a worker to overhaul in time before the fault is, the technical problem that the early warning of the current power plant equipment fault early warning method is lagged, and effective prediction cannot be carried out before the fault occurs is solved;
the above is another embodiment of the power plant equipment creep fault early warning method provided in the embodiment of the present invention, and an application example of the power plant equipment creep fault early warning method provided in the embodiment of the present invention is as follows.
The embodiment of the invention provides an application example of a power plant equipment slow-change fault early warning method, which comprises the following steps:
taking fault early warning of a coal mill in a thermal power generating unit as an example, 2-section coal mill fault data of a coal mill of a certain 1000MW unit is selected for fault early warning system modeling, and the sampling interval is 1 s;
selecting 8 variables to establish an early warning model, wherein the variables are as follows: coal mill current, primary air pressure, primary air temperature, coal mill outlet temperature, primary air flow, cold air opening, hot air opening and coal feeding amount;
the fault data section A is coal-breaking fault data of the coal mill, and the time length of a fault evolution period is 1353 s;
the fault data section B is coal mill spontaneous combustion fault data, and the time length of a fault evolution period is 1000 s;
in order to distinguish the coal pulverizer when the coal pulverizer breaks down from the normal operation of the coal pulverizer and after the failure is finished, 500s are taken forward as the normal working condition time period of the coal pulverizer when the coal-break failure data begins to evolve;
in addition, 1 section is selected as coal-breaking fault data of the coal mill, called as a fault data section C, the time length of a fault evolution period is 1000s, and the fault data section is used as verification data of a fault early warning system;
determining the searching range of the cluster number as [2,7], analyzing modeling data of a data section A, a data section B and a data section combination of a coal mill in a normal working condition period by using Silhouette, and determining the cluster number as 6;
the cluster center of each cluster depicts the coal mill evolution process as shown in table 1:
TABLE 1 Cluster center for coal mill failure clustering model
Wherein mu 0 is the cluster center of the normal operation of the coal mill, mu 1, mu 2 and mu 3 are the cluster centers of the coal-breaking fault stages 1,2 and 3 of the coal mill respectively, and mu 4 and mu 5 are the cluster centers of the spontaneous combustion fault stages 4 and 5 of the coal mill respectively;
the cluster marking results of the coal-break fault data and the spontaneous combustion fault data of the coal mill are shown in table 2, and when the coal-break fault and the spontaneous combustion fault of the coal mill occur, the coal-break fault and the spontaneous combustion fault can be divided into different evolution stages;
the cluster marking vector of the coal-breaking fault of the coal mill is (0,1,2,3), and the cluster marking vector of the spontaneous combustion fault is (0,4, 5). By counting the time from each stage of each fault to the occurrence of the fault of the coal mill, the time range is used as the predicted time range during fault alarm, and the final results are summarized as shown in table 2:
TABLE 2 early warning time range table for each stage of each fault
The data segment C is used as field real-time data, is sent into a clustering model after being subjected to standardization processing, and can be judged to be a coal breaking fault of a coal mill, wherein the corresponding cluster mark vector is (0,1,2, 3);
the actual occurrence time of each phase fault corresponding to the data segment C is obtained as shown in table 3:
TABLE 3 coal pulverizer Fault data segment C actual stage to Fault occurrence time Range
Therefore, the time range from the verification data segment C to the fault occurrence is close to the fault early warning time range, so that the power plant equipment slowly-varying fault early warning method can predict the occurrence of the power plant equipment slowly-varying fault, the predicted early warning time is high in accuracy, and the prediction result is real and reliable;
and with the increase of modeling data, the prediction accuracy of the power plant equipment slowly-varying fault early-warning method provided by the invention is improved.
The above is an application example of the power plant equipment creep fault early warning method provided by the embodiment of the present invention, and the following is an embodiment of the power plant equipment creep fault early warning device provided by the embodiment of the present invention.
Referring to fig. 3, an embodiment of the present invention provides an embodiment of a creep fault warning device for a power plant, including:
the data acquisition module 301 is configured to acquire fault condition data of a fault evolution period of at least one gradual change fault of the power plant equipment and normal condition data of the normal condition period in the historical data by using a time period between a fault initial evolution time point and a fault occurrence time point in the historical data of the power plant equipment as a fault evolution period and using a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as a normal condition period, perform standardization processing on the fault condition data and the normal condition data, and splice the fault condition data and the normal condition data after the standardization processing into modeling data;
a cluster selection module 302, configured to calculate an optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm;
the cluster analysis module 303 is configured to establish a cluster model according to the optimal cluster number to perform cluster analysis on the modeling data, obtain cluster marker vectors corresponding to the normal operating condition data and the fault operating condition data, and record a fault type and an early warning time range of the slowly varying fault of the power plant equipment corresponding to each cluster marker vector corresponding to the fault operating condition data;
the state early warning module 304 is configured to obtain real-time monitoring data of the power plant equipment, input the real-time monitoring data into the clustering model to obtain cluster marker vectors of the real-time monitoring data, match the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal operating condition data, determine whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to normal operating condition data, and if not, match the cluster marker vectors of the real-time monitoring data with each cluster marker vector in the fault operating condition data to obtain a fault type and an early warning time range of a slowly-varying fault of the power plant equipment corresponding to the cluster marker vectors of the real-time monitoring data.
Further, the cluster analysis module 303 specifically includes:
the vector submodule 3031 is used for establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data and respectively acquiring cluster mark vectors corresponding to normal working condition data and fault working condition data;
the recording submodule 3032 is used for acquiring and recording the fault type of the slowly-varying fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault working condition data;
the range submodule 3033 is configured to acquire data acquisition time points of fault condition data corresponding to each cluster marker vector, calculate evolution durations between the data acquisition time points and fault occurrence time points, and acquire and record an early warning time range of each cluster marker vector according to a shortest evolution duration and a longest evolution duration corresponding to each cluster marker vector.
Further, the state warning module 304 specifically includes:
a normal sub-module 3041, configured to obtain real-time monitoring data of the power plant equipment, input the real-time monitoring data into the clustering model to obtain a cluster marker vector of the real-time monitoring data, match the cluster marker vector of the real-time monitoring data with a cluster marker vector corresponding to normal operating condition data, and determine whether the cluster marker vector of the real-time monitoring data belongs to the cluster marker vector corresponding to the normal operating condition data, if yes, the power plant equipment operates normally, and if not, the determining sub-module 3042 is triggered;
a judging submodule 3042, configured to match the cluster marker vector of the real-time monitoring data with each cluster marker vector in the fault condition data, and judge whether the cluster marker vector of the real-time monitoring data belongs to the cluster marker vector corresponding to the fault condition data, if yes, trigger the fault submodule 3043, and if not, trigger the exception submodule 3044;
the fault submodule 3043 is configured to obtain a fault type and an early warning time range of the slowly-varying fault of the power plant equipment, which correspond to the cluster marker vector of the real-time monitoring data;
an exception submodule 3044 for flagging the status of the power plant equipment as an exception.
Further, the normal sub-module 3041 is specifically configured to obtain real-time monitoring data of the power plant equipment, standardize the real-time monitoring data, input the processed real-time monitoring data into the clustering model to obtain cluster marker vectors of the real-time monitoring data, match the cluster marker vectors of the real-time monitoring data with the cluster marker vectors corresponding to the normal operating condition data, and determine whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal operating condition data, if so, the power plant equipment operates normally, and if not, the determining sub-module 3042 is triggered.
Further, still include: the module 305 is repeatedly executed;
and the repeated execution module 305 is used for triggering the state early warning module 304 again after the first preset time.
It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the apparatus and the module described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A power plant equipment slow-change fault early warning method is characterized by comprising the following steps:
s1: taking a time period between a fault initial evolution time point and a fault occurrence time point in historical data of power plant equipment as a fault evolution time period, taking a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as a normal working condition time period, acquiring fault working condition data of a fault evolution time period and normal working condition data of a slowly-varying fault of at least one power plant equipment in the historical data, standardizing the fault working condition data and the normal working condition data, and splicing the fault working condition data and the normal working condition data after the standardization processing into modeling data;
s2: calculating the optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm;
s3: establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data, respectively acquiring cluster marking vectors corresponding to normal working condition data and fault working condition data, and recording the fault type and early warning time range of the slowly-varying fault of the power plant equipment corresponding to each cluster marking vector corresponding to the fault working condition data;
s4: acquiring real-time monitoring data of power plant equipment, inputting the real-time monitoring data into a clustering model to acquire cluster marker vectors of the real-time monitoring data, matching the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal working condition data, judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal working condition data, if not, matching the cluster marker vectors of the real-time monitoring data with each cluster marker vector in fault working condition data, and acquiring fault types and early warning time ranges of slowly-varying faults of the power plant equipment corresponding to the cluster marker vectors of the real-time monitoring data;
the step S3 specifically includes:
s31: establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data, and respectively obtaining cluster mark vectors corresponding to normal working condition data and fault working condition data;
s32: acquiring and recording the fault type of the gradual change fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault condition data;
s33: acquiring data acquisition time points of fault working condition data corresponding to each cluster marker vector, calculating evolution time between each data acquisition time point and a fault occurrence time point respectively, and acquiring and recording an early warning time range of each cluster marker vector according to the shortest evolution time and the longest evolution time corresponding to each cluster marker vector.
2. The power plant equipment creep fault early warning method according to claim 1, wherein the step S4 specifically includes:
s41: acquiring real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into a clustering model to acquire cluster marker vectors of the real-time monitoring data, matching the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal working condition data, and judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal working condition data, if so, the power plant equipment operates normally, otherwise, the step S42 is executed;
s42: matching the cluster marker vectors of the real-time monitoring data with each cluster marker vector in the fault working condition data, judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the fault working condition data, if so, executing step S43, otherwise, executing step S44;
s43: acquiring a fault type and an early warning time range of the gradual change fault of the power plant equipment corresponding to the cluster mark vector of the real-time monitoring data;
s44: the status of the power plant is marked as abnormal.
3. The power plant equipment creep fault early warning method according to claim 2, wherein the step S41 specifically includes: acquiring real-time monitoring data of power plant equipment, standardizing the real-time monitoring data, inputting the processed real-time monitoring data into a clustering model to acquire cluster marker vectors of the real-time monitoring data, matching the cluster marker vectors of the real-time monitoring data with cluster marker vectors corresponding to normal working condition data, and judging whether the cluster marker vectors of the real-time monitoring data belong to the cluster marker vectors corresponding to the normal working condition data, if so, the power plant equipment operates normally, otherwise, executing the step S42.
4. The power plant equipment creep fault warning method according to claim 1, wherein after the step S4, the method further comprises: step S5;
s5: and returns to step S4 after the first preset time.
5. The utility model provides a power plant equipment slowly becomes trouble early warning device which characterized in that includes:
the data acquisition module is used for acquiring fault condition data of at least one power plant equipment slowly-varying fault evolution period and normal condition data of the normal condition period in historical data by taking a time period between a fault initial evolution time point and a fault occurrence time point in the historical data of the power plant equipment as a fault evolution period and taking a time period between a preset time point before the fault initial evolution time point and the fault initial evolution time point as the normal condition period, standardizing the fault condition data and the normal condition data and splicing the standardized fault condition data and the standardized normal condition data into modeling data;
the cluster selection module is used for calculating the optimal cluster number of the modeling data in a preset cluster number search range through a contour coefficient algorithm;
the cluster analysis module is used for establishing a cluster model according to the optimal cluster number to perform cluster analysis on the modeling data, respectively acquiring cluster mark vectors corresponding to normal working condition data and fault working condition data, and recording the fault type and the early warning time range of the slowly-varying fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault working condition data;
the state early warning module is used for acquiring real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into the clustering model to acquire cluster marking vectors of the real-time monitoring data, matching the cluster marking vectors of the real-time monitoring data with cluster marking vectors corresponding to normal working condition data, judging whether the cluster marking vectors of the real-time monitoring data belong to the cluster marking vectors corresponding to the normal working condition data, if not, matching the cluster marking vectors of the real-time monitoring data with each cluster marking vector in fault working condition data, and acquiring the fault type and early warning time range of the slowly-varying fault of the power plant equipment corresponding to the cluster marking vectors of the real-time monitoring data;
the cluster analysis module specifically comprises:
the vector submodule is used for establishing a clustering model according to the optimal cluster number to perform clustering analysis on the modeling data and respectively acquiring cluster mark vectors corresponding to normal working condition data and fault working condition data;
the recording submodule is used for acquiring and recording the fault type of the slowly-varying fault of the power plant equipment corresponding to each cluster mark vector corresponding to the fault working condition data;
and the range submodule is used for acquiring data acquisition time points of fault working condition data corresponding to each cluster marker vector, calculating evolution time between each data acquisition time point and a fault occurrence time point respectively, and acquiring and recording the early warning time range of each cluster marker vector according to the shortest evolution time and the longest evolution time corresponding to each cluster marker vector.
6. The power plant equipment creep fault early warning device according to claim 5, wherein the state early warning module specifically comprises:
the normal submodule is used for acquiring real-time monitoring data of the power plant equipment, inputting the real-time monitoring data into the clustering model to acquire cluster marking vectors of the real-time monitoring data, matching the cluster marking vectors of the real-time monitoring data with cluster marking vectors corresponding to normal working condition data, and judging whether the cluster marking vectors of the real-time monitoring data belong to the cluster marking vectors corresponding to the normal working condition data or not;
the judging submodule is used for matching the cluster marker vector of the real-time monitoring data with each cluster marker vector in the fault working condition data, judging whether the cluster marker vector of the real-time monitoring data belongs to the cluster marker vector corresponding to the fault working condition data, if so, triggering the fault submodule, and if not, triggering the abnormal submodule;
the fault submodule is used for acquiring the fault type and the early warning time range of the slowly-varying fault of the power plant equipment corresponding to the cluster marking vector of the real-time monitoring data;
and the abnormality submodule is used for marking the state of the power plant equipment as abnormal.
7. The power plant equipment creep fault early warning device according to claim 6, wherein the normal submodule is specifically configured to obtain real-time monitoring data of the power plant equipment, standardize the real-time monitoring data, input the processed real-time monitoring data into a clustering model to obtain a cluster marker vector of the real-time monitoring data, match the cluster marker vector of the real-time monitoring data with a cluster marker vector corresponding to normal operating condition data, and determine whether the cluster marker vector of the real-time monitoring data belongs to the cluster marker vector corresponding to the normal operating condition data, if so, the power plant equipment operates normally, and if not, the determination submodule is triggered.
8. The power plant equipment creep fault early warning device of claim 5, further comprising: a repeat execution module;
and the repeated execution module is used for triggering the state early warning module again after the first preset time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711228433.2A CN107832896B (en) | 2017-11-29 | 2017-11-29 | Power plant equipment slow-changing fault early warning method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711228433.2A CN107832896B (en) | 2017-11-29 | 2017-11-29 | Power plant equipment slow-changing fault early warning method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107832896A CN107832896A (en) | 2018-03-23 |
CN107832896B true CN107832896B (en) | 2021-03-12 |
Family
ID=61646601
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711228433.2A Active CN107832896B (en) | 2017-11-29 | 2017-11-29 | Power plant equipment slow-changing fault early warning method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107832896B (en) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10810513B2 (en) * | 2018-10-25 | 2020-10-20 | The Boeing Company | Iterative clustering for machine learning model building |
CN109299201B (en) * | 2018-11-05 | 2020-09-04 | 远光软件股份有限公司 | Power plant production subsystem abnormity monitoring method and device based on two-stage clustering |
CN109300285B (en) * | 2018-11-30 | 2021-07-16 | 联想(北京)有限公司 | Early warning method and device |
CN110266541B (en) * | 2019-06-25 | 2022-11-29 | 湖南科技学院 | Equipment safety monitoring system based on cloud computing |
CN110262460B (en) * | 2019-07-01 | 2020-07-03 | 浪潮集团有限公司 | Concrete piston fault prediction method for extracting features by combining clustering idea |
CN110391936B (en) * | 2019-07-25 | 2022-03-01 | 长沙学院 | Clustering method based on time sequence alarm |
CN110658905B (en) * | 2019-09-23 | 2023-08-04 | 珠海格力电器股份有限公司 | Early warning method, early warning system and early warning device for equipment operation state |
CN110738255A (en) * | 2019-10-15 | 2020-01-31 | 和尘自仪(嘉兴)科技有限公司 | device state monitoring method based on clustering algorithm |
CN111046942A (en) * | 2019-12-09 | 2020-04-21 | 交控科技股份有限公司 | Turnout fault judgment method and device |
CN111046583B (en) * | 2019-12-27 | 2023-12-08 | 中国铁道科学研究院集团有限公司通信信号研究所 | Point machine fault diagnosis method based on DTW algorithm and ResNet network |
CN113537652A (en) * | 2020-03-31 | 2021-10-22 | 厦门邑通软件科技有限公司 | Equipment health monitoring and early warning method, system, storage medium and equipment |
CN112329828B (en) * | 2020-10-26 | 2024-07-23 | 北京旋极信息技术股份有限公司 | Fault association analysis method and device |
CN114088389A (en) * | 2021-12-10 | 2022-02-25 | 华润电力技术研究院有限公司 | Data processing method and related device for gearbox |
CN116361351B (en) * | 2022-12-01 | 2024-05-17 | 重庆科创职业学院 | Data mining method for health management of industrial equipment |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6834256B2 (en) * | 2002-08-30 | 2004-12-21 | General Electric Company | Method and system for determining motor reliability |
CN102768115B (en) * | 2012-06-27 | 2016-04-20 | 华北电力大学 | A kind of gearbox of wind turbine health status real-time dynamic monitoring method |
CN105425150B (en) * | 2015-11-09 | 2018-08-31 | 江苏科技大学 | A kind of Method of Motor Fault Diagnosis based on RBF and PCA-SVDD |
CN105573290B (en) * | 2015-12-16 | 2017-12-29 | 浙江中烟工业有限责任公司 | Cigarette factory ultrahigh speed case packing machine multiple operating modes process is monitored on-line and method for diagnosing faults |
CN106936627B (en) * | 2016-09-28 | 2020-05-22 | 清华大学 | Thermal power equipment performance monitoring method based on big data analysis and mining |
CN106407589B (en) * | 2016-09-29 | 2020-01-21 | 北京岳能科技股份有限公司 | Fan state evaluation and prediction method and system |
CN106779200A (en) * | 2016-12-07 | 2017-05-31 | 东北大学 | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data |
CN107346466A (en) * | 2017-05-26 | 2017-11-14 | 国网山东省电力公司淄博供电公司 | A kind of control method and device of electric power dispatching system |
-
2017
- 2017-11-29 CN CN201711228433.2A patent/CN107832896B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107832896A (en) | 2018-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107832896B (en) | Power plant equipment slow-changing fault early warning method and device | |
EP0843244B1 (en) | Diagnostic trend analysis for aircraft engines | |
US20150346066A1 (en) | Asset Condition Monitoring | |
EP3105644B1 (en) | Method of identifying anomalies | |
EP2161664B1 (en) | System and method for detecting temporal relationships uniquely associated with an underlying root cause | |
CN101902366B (en) | Method and system for detecting abnormal service behaviors | |
CN109886475B (en) | Information security situation perception system of measurement automation system based on AI | |
CN106020154A (en) | Safe dynamic health assessment method and assessment system for ethylene production | |
CN109948860A (en) | A kind of mechanical system method for predicting residual useful life and system | |
CN107463161A (en) | Predict the method and system and monitoring system of the failure in aircraft | |
CN104756029B (en) | A kind of system of the parts group of monitoring device | |
CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
CN109977146B (en) | Fault diagnosis method and device and electronic equipment | |
JP5621967B2 (en) | Abnormal data analysis system | |
CN117312879B (en) | Injection molding machine production data supervision and early warning method, system and medium | |
CN115375266A (en) | Method and device for processing equipment purchase data, storage medium and terminal | |
CN116466237A (en) | Charging safety monitoring and early warning method and system for lithium battery | |
CN105825130A (en) | Information security early-warning method and device | |
CN114338458A (en) | Data security detection method and device | |
CN106652393A (en) | Method for determining false alarm | |
US20160195872A1 (en) | System for Assisting Operation at the Time of Plant Accident and Method for Assisting Operation at the Time of Plant Accident | |
CN114048346B (en) | GIS-based safety production integrated management and control platform and method | |
CN115511374A (en) | Method, device and equipment for calculating correlation of process indexes and storage medium | |
CN114881112A (en) | System anomaly detection method, device, equipment and medium | |
CN113407520A (en) | Power network safety data cleaning system and method based on machine learning |
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 |