CN117390468A - Dust removal equipment state monitoring and early warning method and system based on data mining - Google Patents
Dust removal equipment state monitoring and early warning method and system based on data mining Download PDFInfo
- Publication number
- CN117390468A CN117390468A CN202311358152.4A CN202311358152A CN117390468A CN 117390468 A CN117390468 A CN 117390468A CN 202311358152 A CN202311358152 A CN 202311358152A CN 117390468 A CN117390468 A CN 117390468A
- Authority
- CN
- China
- Prior art keywords
- equipment
- data
- sample
- abnormal
- state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000000428 dust Substances 0.000 title claims abstract description 121
- 238000012544 monitoring process Methods 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000007418 data mining Methods 0.000 title claims abstract description 18
- 230000002159 abnormal effect Effects 0.000 claims abstract description 113
- 238000011156 evaluation Methods 0.000 claims abstract description 113
- 238000012423 maintenance Methods 0.000 claims abstract description 51
- 230000000694 effects Effects 0.000 claims abstract description 50
- 238000013507 mapping Methods 0.000 claims abstract description 18
- 238000004519 manufacturing process Methods 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012795 verification Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 9
- 230000000737 periodic effect Effects 0.000 claims description 9
- 238000007405 data analysis Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000012545 processing Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Classifications
-
- 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
- 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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/20—Administration of product repair or maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a dust removal equipment state monitoring and early warning method and system based on data mining, and relates to the technical field of data processing, wherein the method comprises the following steps: acquiring historical operation parameter data and historical equipment fault data of the dust removing equipment, performing abnormal identification mapping on the equipment operation data to obtain a plurality of data feature combinations, and performing data clustering to obtain a plurality of equipment abnormal combinations; based on a plurality of abnormal equipment combinations, sample data acquisition is respectively carried out to obtain a plurality of abnormal sample data sets, an equipment state supervision network is constructed, equipment state analysis is carried out to generate equipment state evaluation results, and safety production early warning is carried out through evaluation result judgment. The invention solves the technical problems of the prior art that the dust removing effect and the service life of the equipment are influenced due to the untimely maintenance of the daily operation of the dust removing equipment, and achieves the technical effects of improving the operation stability and safety of the equipment and prolonging the service life by monitoring and early warning the real-time state of the dust removing equipment.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a dust removal equipment state monitoring and early warning method and system based on data mining.
Background
Enterprises engaged in dust operation are widely distributed in the industrial field, a large amount of dust is often accumulated, and environments with a large amount of dust exist, so that environmental pollution or safety accidents are easily caused, therefore, dust-related explosion-proof enterprises adopt dust removing equipment to remove dust from the environment to prevent dust accidents, but along with the aging of the dust removing equipment and dust accumulation in operation, the dust removing equipment may have structural loss or performance reduction and the like, faults are easily caused, the dust removing effect is reduced, and the service life of the equipment is reduced.
Disclosure of Invention
The application provides a dust collecting equipment state monitoring and early warning method and system based on data mining, which are used for solving the technical problems that in the prior art, the dust collecting effect and the service life of equipment are influenced due to untimely maintenance of daily operation of dust collecting equipment.
In a first aspect of the present application, a dust removal device status monitoring and early warning method based on data mining is provided, the method includes: acquiring historical operation parameter data and historical equipment fault data of the dust removing equipment, performing abnormal identification mapping of the equipment operation data, and establishing mapping association between the operation parameters and equipment faults to obtain a plurality of data characteristic combinations;
taking the plurality of data characteristic combinations as a basic combination space, and performing data clustering to obtain a plurality of equipment abnormal combinations, wherein the plurality of equipment abnormal combinations comprise single index abnormal combinations and multi-index abnormal combinations; based on the single index abnormal combination and the multiple index abnormal combination, respectively acquiring sample data to obtain multiple sample abnormal data sets; adopting a plurality of sample abnormal data sets to construct a device state supervision network; performing data analysis on the real-time monitoring data of the dust removing equipment according to the equipment state monitoring network to generate an equipment state evaluation result; and judging whether the equipment state evaluation result is within a safety threshold, and if not, carrying out safety production early warning.
In a second aspect of the present application, a dust removal device status monitoring and early warning system based on data mining is provided, the system comprising: the data feature combination acquisition module is used for acquiring historical operation parameter data and historical equipment fault data of the dust removing equipment, mapping abnormal identification of the equipment operation data, and establishing mapping association between the operation parameters and the equipment faults to obtain a plurality of data feature combinations; the equipment abnormal combination acquisition module is used for taking the plurality of data characteristic combinations as a basic combination space, and performing data clustering to obtain a plurality of equipment abnormal combinations, wherein the equipment abnormal combination acquisition module comprises a single index abnormal combination and a plurality of index abnormal combinations; the sample abnormal data set acquisition module is used for respectively acquiring sample data based on the single index abnormal combination and the multiple index abnormal combination to obtain a plurality of sample abnormal data sets; the equipment state monitoring network construction module is used for constructing an equipment state monitoring network by adopting a plurality of sample abnormal data sets; the equipment state evaluation module is used for carrying out data analysis on the real-time monitoring data of the dust removing equipment according to the equipment state supervision network to generate an equipment state evaluation result; and the safety production early warning module is used for judging whether the equipment state evaluation result is within a safety threshold value or not, and if not, carrying out safety production early warning.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the utility model provides a dust collecting equipment state monitoring early warning method based on data mining relates to the technical field of data processing, through obtaining historical operation parameter data of dust collecting equipment, historical equipment fault data, carry out the unusual identification mapping of equipment operation data, obtain a plurality of data characteristic combinations, cluster obtains a plurality of equipment unusual combinations, sample data acquisition respectively, obtain a plurality of sample unusual data sets, build equipment state supervision network, carry out equipment state analysis, generate equipment state evaluation result, judge through the evaluation result, carry out safe production early warning, the technical problem that because dust collecting equipment's daily operation maintenance is untimely in the prior art, influence dust collecting effect and equipment life is realized through carrying out real-time state monitoring early warning to dust collecting equipment, improve equipment operation stability and security, increase of service life, reduce cost of maintenance's technical effect.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a dust removing equipment state monitoring and early warning method based on data mining according to an embodiment of the present application;
fig. 2 is a schematic flow chart of obtaining a plurality of sample device state evaluation results in a dust removing device state monitoring and early warning method based on data mining according to an embodiment of the present application;
fig. 3 is a schematic flow chart of setting an impact weight of each device operation parameter according to an attenuation evaluation result in the dust removing device state monitoring and early warning method based on data mining according to the embodiment of the present application;
fig. 4 is a schematic structural diagram of a dust collecting equipment status monitoring and early warning system based on data mining according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a data characteristic combination acquisition module 11, an equipment abnormal combination acquisition module 12, a sample abnormal data set acquisition module 13, an equipment state supervision network construction module 14, an equipment state evaluation module 15 and a safety production early warning module 16.
Detailed Description
The application provides a dust collecting equipment state monitoring and early warning method based on data mining, which is used for solving the technical problems that in the prior art, the dust collecting effect and the service life of equipment are influenced due to untimely maintenance of the daily operation of the dust collecting equipment.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, the present application provides a dust removal device status monitoring and early warning method based on data mining, where the method includes:
t10: acquiring historical operation parameter data and historical equipment fault data of the dust removing equipment, performing abnormal identification mapping of the equipment operation data, and establishing mapping association between the operation parameters and equipment faults to obtain a plurality of data characteristic combinations;
it should be understood that, through the operation and maintenance record of the target device, the historical operation parameter data and the historical device fault data of the target dust removal device in a past period are collected according to a collection period, the collection period can be three months, half year, one year, and the like, the specific time can be adaptively adjusted according to actual conditions, the historical operation parameter data comprises historical operation parameter values of the device such as historical operation power, voltage, current, air flow and the like, the historical device fault data comprises a device fault type, a fault part, fault influence, a fault reason and the like, the historical operation parameter data and the historical device fault data are provided with time marks, abnormal mark mapping of the device operation data is carried out according to the time marks, namely, an association relation between operation parameters and device faults is established, for example, the air flow is low, wind power in a dust removal pipeline is insufficient, the pipeline is blocked due to dust accumulation, and a plurality of data feature combinations, namely, a plurality of associated feature combinations of the historical operation parameters and the historical device fault can be obtained through establishing a mapping association between a plurality of sets of operation parameters and the historical device fault association.
T20: taking the plurality of data characteristic combinations as a basic combination space, and performing data clustering to obtain a plurality of equipment abnormal combinations, wherein the plurality of equipment abnormal combinations comprise single index abnormal combinations and multi-index abnormal combinations;
the method includes the steps of taking the plurality of data feature combinations as a basic combination space, namely taking the plurality of data feature combinations as a basic data source, using data in the basic data source to perform data clustering, respectively grouping equipment anomalies caused by single operation parameter anomalies into one type, grouping equipment anomalies caused by a plurality of same operation parameter anomalies into one type, and obtaining a plurality of single index anomaly combinations and a plurality of multi-index anomaly combinations which can respectively represent one equipment state anomaly condition.
T30: based on the single index abnormal combination and the multiple index abnormal combination, respectively acquiring sample data to obtain multiple sample abnormal data sets;
further, step T30 in the embodiment of the present application further includes:
t31: setting a sample collection period;
t32: based on the sample collection period, referring to the single index abnormal combination and the multiple index abnormal combination, respectively collecting a plurality of groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data;
t33: performing equipment state evaluation according to the multiple groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data to obtain multiple sample equipment state evaluation results;
t34: and taking the operation parameters of the plurality of groups of sample equipment, the fault data of the sample equipment, the dust removal effect data of the sample and the state evaluation results of the plurality of sample equipment as a plurality of sample abnormal data sets.
Optionally, based on the single index abnormal combination and the multiple index abnormal combination, sample data acquisition is respectively performed, historical operation data and historical fault data of the target dust removing equipment are extracted to be used as sample data, the historical fault frequency and maintenance period of the target dust removing equipment are referred to, the sample acquisition period is set, for example, one month is set, and sample update acquisition is performed every month, so that accuracy and effectiveness of the sample data are ensured.
Further, based on the sample collection period and according to the single index abnormal combination and the multiple index abnormal combination, a plurality of groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data are respectively collected, wherein the sample collection period comprises a plurality of groups of sample data corresponding to the single index abnormal combination and a plurality of groups of sample data corresponding to the multiple index abnormal combination. Further, according to the multiple groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data, performing operation state evaluation of the target dust removal equipment, including equipment operation stability evaluation, equipment dust removal effect evaluation, equipment fault grade evaluation and the like, to obtain multiple sample equipment state evaluation results, and forming multiple sample abnormal data sets by the multiple groups of sample equipment operation parameters, the sample equipment fault data, the sample dust removal effect data and the multiple sample equipment state evaluation results together, wherein the sample abnormal data sets have a one-to-one correspondence relationship.
Further, as shown in fig. 2, step T33 in the embodiment of the present application further includes:
t33-1: the equipment state evaluation comprises operation stability evaluation, fault hazard evaluation and dust removal effect evaluation;
t33-2: according to the operation parameters of the multiple groups of sample equipment, the fault data of the sample equipment and the dust removal effect data of the sample, carrying out operation equipment state evaluation to obtain a stability evaluation result, a fault hazard evaluation result and a dust removal effect evaluation result;
t33-3: and carrying out weighted calculation on the stability evaluation result, the fault hazard evaluation result and the dust removal effect evaluation result according to preset evaluation weights to obtain a plurality of sample equipment state evaluation results.
The equipment state evaluation comprises operation stability evaluation, fault hazard evaluation and dust removal effect evaluation of the dust removal equipment, wherein the operation stability evaluation refers to data stability of operation parameters and dust removal effects of the equipment, a plurality of sample data sequences are generated according to time marks according to the operation parameters, the fault data and the dust removal effect data of the sample equipment, the operation parameter sequences, the equipment fault sequences and the dust removal effect sequences are respectively used, the stability of the operation data and the stability of the dust removal effects are judged through methods such as variance calculation and standard deviation calculation, and the stability evaluation results of the equipment are obtained through weighting.
Further, according to the damage degree and the fault result of the equipment in the sample equipment fault data, the fault hazard rating is carried out, the higher the damage degree is, the serious the fault result is, the higher the corresponding fault hazard rating is, the fault hazard assessment result is obtained, and according to the dust removal effect data, the environmental dust removal effect of the equipment is rated, and the dust removal effect assessment result is obtained. Further, according to the importance degree, corresponding evaluation weights are preset for the stability evaluation result, the fault hazard evaluation result and the dust removal effect evaluation result, for example, the evaluation weights are distributed as 2:4: and 4, carrying out weighted calculation according to preset evaluation weights to obtain a plurality of sample equipment state evaluation results, wherein the plurality of sample equipment state evaluation results are in one-to-one correspondence with the plurality of sample abnormal data sets.
T40: adopting a plurality of sample abnormal data sets to construct a device state supervision network;
further, step T40 of the embodiment of the present application further includes:
t41: dividing and acquiring a training data set, a verification data set and a test data set by using the plurality of groups of sample equipment operation parameters, sample equipment fault data, sample dust removal effect data and a plurality of sample equipment state evaluation results;
t42: and performing supervised training by using the training data set, the verification data set and the test data set and combining a neural network algorithm until convergence to obtain the equipment state supervision network.
In one possible embodiment of the present application, a uniform random sampling manner is used, the multiple sets of operation parameters of sample equipment, fault data of the sample equipment, dust removal effect data of the sample, and state evaluation results of the multiple sample equipment are marked and divided into a training data set, a verification data set and a test data set, the training data set, the verification data set and the test data set are used as construction data, an equipment state supervision network is built in combination with a neural network algorithm, for example, a BP neural network is built in combination with a BP neural network, the BP neural network is a multi-layer feedforward neural network trained according to an error back propagation algorithm, a mathematical equation of a mapping relation between input and output is not required to be determined in advance, a certain rule is learned only through self training, and a result closest to an expected output value is obtained when an input value is given.
Further, a group of training data in the training data set is input into the equipment state monitoring network to carry out monitoring training, then the network parameter adjustment is carried out by the difference value between the corresponding output data and the expected data, and so on until the training of all the training data and the adjustment of the network parameter are completed, the network parameter accords with the convergence condition, the data in the verification data set is used for carrying out verification adjustment on the network parameter, in order to ensure the accuracy of the equipment state monitoring network, the test data set is used for carrying out accuracy test, for example, the test accuracy is set to be 90%, and if the test accuracy of the current test data set meets 90%, the construction of the equipment state monitoring network is completed.
Further, step T42 of the embodiment of the present application further includes:
t42-1: referring to the single index abnormal combination and the multiple index abnormal combination, respectively constructing a plurality of single abnormal state identification sub-networks and a plurality of multiple abnormal state identification sub-networks;
t42-2: and the equipment state supervision network is composed of the plurality of single abnormal state identification sub-networks and the plurality of multiple abnormal state identification sub-networks.
The equipment state monitoring network comprises a plurality of abnormal state identification sub-networks, can adapt to abnormal state monitoring under various different abnormal conditions, refers to the single index abnormal combination and the multi index abnormal combination, extracts corresponding sample data, marks and divides the sample data into a corresponding training data set, a verification data set and a test data set, and further performs supervised training by combining a neural network algorithm to obtain a corresponding single abnormal state identification sub-network or a plurality of abnormal state identification sub-networks, and adds the plurality of single abnormal state identification sub-networks and the plurality of abnormal state identification sub-networks to perform the equipment state monitoring network so as to realize abnormal state identification of dust removing equipment under various conditions.
T50: performing data analysis on the real-time monitoring data of the dust removing equipment according to the equipment state monitoring network to generate an equipment state evaluation result;
specifically, the front-end monitoring window and the monitoring device are used for collecting real-time monitoring data of the target dust removing equipment in real time, wherein the real-time monitoring data comprise real-time operation parameter data and real-time environment monitoring data, such as real-time operation voltage, real-time operation current, real-time air flow and the like of the equipment, and real-time environment dust concentration, air dryness and the like, and the real-time monitoring data are input into the equipment state monitoring network for data analysis to obtain a real-time operation state evaluation result of the target dust removing equipment, so that the current equipment state of the target dust removing equipment can be reflected.
Further, as shown in fig. 3, step T50 in the embodiment of the present application further includes:
t51: establishing a maintenance data set, wherein the maintenance data set is maintenance record data for carrying out equipment maintenance on the dust removing equipment;
t52: determining a plurality of maintenance nodes according to the maintenance data set, and determining maintenance characteristic data under the corresponding maintenance nodes;
t53: and carrying out attenuation evaluation of the associated features by using the plurality of maintenance nodes and the maintenance feature data, and setting the influence weight of each equipment operation parameter according to the attenuation evaluation result.
Optionally, historical equipment operation and maintenance data of the target dust removing equipment are collected, including past operation and maintenance time nodes and operation and maintenance process data of the equipment, including parts, parameter types and the like maintained each time, a plurality of maintenance nodes, namely operation and maintenance time nodes, are determined by referring to the maintenance data set, maintenance feature data under the corresponding maintenance nodes, namely improved equipment performance types, corrected operation parameters and the like are determined, further, attenuation evaluation of relevant features is carried out by using the plurality of maintenance nodes and the maintenance feature data respectively, namely attenuation evaluation is carried out on the corresponding maintenance features for each maintenance node, so that corresponding attenuation evaluation results are obtained, for example, the accuracy of the adjusted operation parameters of the equipment is highest in the latest time of the maintenance nodes, the accuracy of the adjusted operation parameters gradually attenuates along with equipment use and aging, the influence weight of the operation parameters of the equipment is set according to the attenuation evaluation results, and the real-time monitoring data is corrected according to the influence weight so as to improve the accuracy of equipment state evaluation.
Further, step T50 of the embodiment of the present application further includes:
t54: acquiring the life cycle of equipment, and dividing the running cycle of the equipment according to the data expression of the dust removing equipment to obtain a cycle division result;
t55: setting a device periodic performance influence factor according to a periodic segmentation result;
t56: and correcting the equipment operation data through the equipment periodic performance influence factor.
It should be understood that, the life cycle of the target dust removing device is obtained, for example, the life cycle of the target dust removing device is divided into a running-in period, an adapting period and a declining period according to the use stages of the device, and the working performance and the working efficiency of the device in different life cycle stages deviate, so that the same set of evaluation criteria cannot be used, and therefore, the life cycle is divided according to the data representation of the target dust removing device, that is, the life cycle of the device is divided according to the data representation of the operation stability, the dust removing efficiency, the dust removing effect and the like of the target dust removing device, so as to obtain the cycle division result. Further, according to the cycle segmentation result, respectively establishing cycle attenuation influence factors of each life stage, setting the equipment performance attenuation coefficients to be 1.1, 1.0 and 1.3, and correcting real-time monitoring data according to the current equipment life cycle through the equipment cycle performance influence factors so as to ensure the accuracy of equipment state evaluation results in each equipment life cycle.
T60: and judging whether the equipment state evaluation result is within a safety threshold, and if not, carrying out safety production early warning.
In an actual use, the current equipment security risk level is determined by determining whether the equipment state evaluation result is within the security threshold, and a corresponding early warning instruction is generated according to the equipment security risk level to perform security production early warning, so that the operation stability and security of the dust removal equipment are improved, the service life of the equipment is prolonged, and production accidents are avoided.
In summary, the embodiments of the present application have at least the following technical effects:
according to the method, through obtaining historical operation parameter data and historical equipment fault data of the dust removal equipment, abnormal identification mapping of the equipment operation data is carried out, a plurality of data feature combinations are obtained, a plurality of equipment abnormal combinations are obtained through clustering, sample data acquisition is carried out respectively, a plurality of sample abnormal data sets are obtained, an equipment state supervision network is constructed, equipment state analysis is carried out, equipment state assessment results are generated, and safety production early warning is carried out through assessment result judgment.
The technical effects of improving the running stability and safety of the equipment, prolonging the service life and reducing the maintenance cost are achieved by carrying out real-time state monitoring and early warning on the dust removing equipment.
Example two
Based on the same inventive concept as the dust collecting equipment state monitoring and early warning method based on data mining in the foregoing embodiments, as shown in fig. 4, the present application provides a dust collecting equipment state monitoring and early warning system based on data mining, and the system and method embodiments in the embodiments of the present application are based on the same inventive concept. Wherein the system comprises:
the data feature combination acquisition module 11 is used for acquiring historical operation parameter data and historical equipment fault data of the dust removal equipment, mapping abnormal identification of the equipment operation data, and establishing mapping association between the operation parameters and the equipment faults to obtain a plurality of data feature combinations;
the device anomaly combination acquisition module 12 is configured to perform data clustering by using the plurality of data feature combinations as a basic combination space, to obtain a plurality of device anomaly combinations, including a single index anomaly combination and a plurality of index anomaly combinations;
the sample abnormal data set acquisition module 13 is used for respectively acquiring sample data based on the single index abnormal combination and the multiple index abnormal combination to obtain a plurality of sample abnormal data sets;
the device state monitoring network construction module 14, wherein the device state monitoring network construction module 14 is used for constructing a device state monitoring network by adopting a plurality of sample abnormal data sets;
the equipment state evaluation module 15 is used for carrying out data analysis on the real-time monitoring data of the dust removing equipment according to the equipment state supervision network to generate an equipment state evaluation result;
the safety production early-warning module 16 is used for judging whether the equipment state evaluation result is within a safety threshold value or not, and if not, carrying out safety production early-warning.
Further, the sample abnormal data set obtaining module 13 is further configured to perform the following steps:
setting a sample collection period;
based on the sample collection period, referring to the single index abnormal combination and the multiple index abnormal combination, respectively collecting a plurality of groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data;
performing equipment state evaluation according to the multiple groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data to obtain multiple sample equipment state evaluation results;
and taking the operation parameters of the plurality of groups of sample equipment, the fault data of the sample equipment, the dust removal effect data of the sample and the state evaluation results of the plurality of sample equipment as a plurality of sample abnormal data sets.
Further, the sample abnormal data set obtaining module 13 is further configured to perform the following steps:
the equipment state evaluation comprises operation stability evaluation, fault hazard evaluation and dust removal effect evaluation;
according to the operation parameters of the multiple groups of sample equipment, the fault data of the sample equipment and the dust removal effect data of the sample, carrying out operation equipment state evaluation to obtain a stability evaluation result, a fault hazard evaluation result and a dust removal effect evaluation result;
and carrying out weighted calculation on the stability evaluation result, the fault hazard evaluation result and the dust removal effect evaluation result according to preset evaluation weights to obtain a plurality of sample equipment state evaluation results.
Further, the device state supervision network construction module 14 is further configured to perform the following steps:
dividing and acquiring a training data set, a verification data set and a test data set by using the plurality of groups of sample equipment operation parameters, sample equipment fault data, sample dust removal effect data and a plurality of sample equipment state evaluation results;
and performing supervised training by using the training data set, the verification data set and the test data set and combining a neural network algorithm until convergence to obtain the equipment state supervision network.
Further, the device state supervision network construction module 14 is further configured to perform the following steps:
referring to the single index abnormal combination and the multiple index abnormal combination, respectively constructing a plurality of single abnormal state identification sub-networks and a plurality of multiple abnormal state identification sub-networks;
and the equipment state supervision network is composed of the plurality of single abnormal state identification sub-networks and the plurality of multiple abnormal state identification sub-networks.
Further, the device state evaluation module 15 is further configured to perform the following steps:
establishing a maintenance data set, wherein the maintenance data set is maintenance record data for carrying out equipment maintenance on the dust removing equipment;
determining a plurality of maintenance nodes according to the maintenance data set, and determining maintenance characteristic data under the corresponding maintenance nodes;
and carrying out attenuation evaluation of the associated features by using the plurality of maintenance nodes and the maintenance feature data, and setting the influence weight of each equipment operation parameter according to the attenuation evaluation result.
Further, the device state evaluation module 15 is further configured to perform the following steps:
acquiring the life cycle of equipment, and dividing the running cycle of the equipment according to the data expression of the dust removing equipment to obtain a cycle division result;
setting a device periodic performance influence factor according to a periodic segmentation result;
and correcting the equipment operation data through the equipment periodic performance influence factor.
It should be noted that the sequence of the embodiments of the present application is merely for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the present application is not intended to limit the invention to the particular embodiments of the present application, but to limit the scope of the invention to the particular embodiments of the present application.
The specification and drawings are merely exemplary of the application and are to be regarded as covering any and all modifications, variations, combinations, or equivalents that are within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the present application and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (8)
1. The dust removing equipment state monitoring and early warning method based on data mining is characterized by comprising the following steps of:
acquiring historical operation parameter data and historical equipment fault data of the dust removing equipment, performing abnormal identification mapping of the equipment operation data, and establishing mapping association between the operation parameters and equipment faults to obtain a plurality of data characteristic combinations;
taking the plurality of data characteristic combinations as a basic combination space, and performing data clustering to obtain a plurality of equipment abnormal combinations, wherein the plurality of equipment abnormal combinations comprise single index abnormal combinations and multi-index abnormal combinations;
based on the single index abnormal combination and the multiple index abnormal combination, respectively acquiring sample data to obtain multiple sample abnormal data sets;
adopting a plurality of sample abnormal data sets to construct a device state supervision network;
performing data analysis on the real-time monitoring data of the dust removing equipment according to the equipment state monitoring network to generate an equipment state evaluation result;
and judging whether the equipment state evaluation result is within a safety threshold, and if not, carrying out safety production early warning.
2. The method of claim 1, wherein the acquiring sample data based on the single index anomaly combination and the multiple index anomaly combination, respectively, includes:
setting a sample collection period;
based on the sample collection period, referring to the single index abnormal combination and the multiple index abnormal combination, respectively collecting a plurality of groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data;
performing equipment state evaluation according to the multiple groups of sample equipment operation parameters, sample equipment fault data and sample dust removal effect data to obtain multiple sample equipment state evaluation results;
and taking the operation parameters of the plurality of groups of sample equipment, the fault data of the sample equipment, the dust removal effect data of the sample and the state evaluation results of the plurality of sample equipment as a plurality of sample abnormal data sets.
3. The method of claim 2, wherein performing the device state evaluation according to the plurality of sets of sample device operation parameters, sample device fault data, and sample dust removal effect data to obtain a plurality of sample device state evaluation results comprises:
the equipment state evaluation comprises operation stability evaluation, fault hazard evaluation and dust removal effect evaluation;
according to the operation parameters of the multiple groups of sample equipment, the fault data of the sample equipment and the dust removal effect data of the sample, carrying out operation equipment state evaluation to obtain a stability evaluation result, a fault hazard evaluation result and a dust removal effect evaluation result;
and carrying out weighted calculation on the stability evaluation result, the fault hazard evaluation result and the dust removal effect evaluation result according to preset evaluation weights to obtain a plurality of sample equipment state evaluation results.
4. The method of claim 3, wherein constructing a device state supervision network using the plurality of sample anomaly data sets comprises:
dividing and acquiring a training data set, a verification data set and a test data set by using the plurality of groups of sample equipment operation parameters, sample equipment fault data, sample dust removal effect data and a plurality of equipment state evaluation results;
and performing supervised training by using the training data set, the verification data set and the test data set and combining a neural network algorithm until convergence to obtain the equipment state supervision network.
5. The method of claim 4, wherein using the training data set, the validation data set, and the test data set in conjunction with a neural network algorithm to perform supervised training until convergence, obtaining the device status supervisory network, comprises:
referring to the single index abnormal combination and the multiple index abnormal combination, respectively constructing a plurality of single abnormal state identification sub-networks and a plurality of multiple abnormal state identification sub-networks;
and the equipment state supervision network is composed of the plurality of single abnormal state identification sub-networks and the plurality of multiple abnormal state identification sub-networks.
6. The method of claim 1, wherein prior to the data analysis of the real-time monitoring data of the dust removal device according to the device status monitoring network, further comprising:
establishing a maintenance data set, wherein the maintenance data set is maintenance record data for carrying out equipment maintenance on the dust removing equipment;
determining a plurality of maintenance nodes according to the maintenance data set, and determining maintenance characteristic data under the corresponding maintenance nodes;
and carrying out attenuation evaluation of the associated features by using the plurality of maintenance nodes and the maintenance feature data, and setting the influence weight of each equipment operation parameter according to the attenuation evaluation result.
7. The method of claim 1, wherein the method further comprises:
acquiring the life cycle of equipment, and dividing the running cycle of the equipment according to the data expression of the dust removing equipment to obtain a cycle division result;
setting a device periodic performance influence factor according to a periodic segmentation result;
and correcting the equipment operation data through the equipment periodic performance influence factor.
8. The utility model provides a dust collecting equipment state monitoring early warning system based on data mining which characterized in that, the system includes:
the data feature combination acquisition module is used for acquiring historical operation parameter data and historical equipment fault data of the dust removing equipment, mapping abnormal identification of the equipment operation data, and establishing mapping association between the operation parameters and the equipment faults to obtain a plurality of data feature combinations;
the equipment abnormal combination acquisition module is used for taking the plurality of data characteristic combinations as a basic combination space, and performing data clustering to obtain a plurality of equipment abnormal combinations, wherein the equipment abnormal combination acquisition module comprises a single index abnormal combination and a plurality of index abnormal combinations;
the sample abnormal data set acquisition module is used for respectively acquiring sample data based on the single index abnormal combination and the multiple index abnormal combination to obtain a plurality of sample abnormal data sets;
the equipment state monitoring network construction module is used for constructing an equipment state monitoring network by adopting a plurality of sample abnormal data sets;
the equipment state evaluation module is used for carrying out data analysis on the real-time monitoring data of the dust removing equipment according to the equipment state supervision network to generate an equipment state evaluation result;
and the safety production early warning module is used for judging whether the equipment state evaluation result is within a safety threshold value or not, and if not, carrying out safety production early warning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311358152.4A CN117390468B (en) | 2023-10-19 | 2023-10-19 | Dust removal equipment state monitoring and early warning method and system based on data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311358152.4A CN117390468B (en) | 2023-10-19 | 2023-10-19 | Dust removal equipment state monitoring and early warning method and system based on data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117390468A true CN117390468A (en) | 2024-01-12 |
| CN117390468B CN117390468B (en) | 2024-06-04 |
Family
ID=89469709
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311358152.4A Active CN117390468B (en) | 2023-10-19 | 2023-10-19 | Dust removal equipment state monitoring and early warning method and system based on data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117390468B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN107679649A (en) * | 2017-09-13 | 2018-02-09 | 珠海格力电器股份有限公司 | Electric appliance fault prediction method and device, storage medium and electric appliance |
| CN114386312A (en) * | 2021-12-08 | 2022-04-22 | 华能沁北发电有限责任公司 | Equipment fault diagnosis method |
| CN114630352A (en) * | 2020-12-11 | 2022-06-14 | 中国移动通信集团湖南有限公司 | Fault monitoring method and device of access equipment |
| CN116402227A (en) * | 2023-04-13 | 2023-07-07 | 河北建投新能源有限公司 | Wind power big data analysis method and system based on cloud computing |
| CN116611817A (en) * | 2023-05-26 | 2023-08-18 | 江苏邦鼎科技有限公司 | Fault management method and system for feed factory equipment |
-
2023
- 2023-10-19 CN CN202311358152.4A patent/CN117390468B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN107679649A (en) * | 2017-09-13 | 2018-02-09 | 珠海格力电器股份有限公司 | Electric appliance fault prediction method and device, storage medium and electric appliance |
| CN114630352A (en) * | 2020-12-11 | 2022-06-14 | 中国移动通信集团湖南有限公司 | Fault monitoring method and device of access equipment |
| CN114386312A (en) * | 2021-12-08 | 2022-04-22 | 华能沁北发电有限责任公司 | Equipment fault diagnosis method |
| CN116402227A (en) * | 2023-04-13 | 2023-07-07 | 河北建投新能源有限公司 | Wind power big data analysis method and system based on cloud computing |
| CN116611817A (en) * | 2023-05-26 | 2023-08-18 | 江苏邦鼎科技有限公司 | Fault management method and system for feed factory equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117390468B (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111047082B (en) | Early warning method and device of equipment, storage medium and electronic device | |
| CN109501834B (en) | Method and device for predicting fault of turnout switch machine | |
| CN108446864B (en) | Big data analysis-based fault early warning system and method for rail transit equipment | |
| US20190334784A1 (en) | Methods and apparatus for analysing performance of a telecommunications network | |
| CN114630352B (en) | Fault monitoring method and device for access equipment | |
| CN116228174B (en) | Management method of printing control instrument with intelligent recognition function | |
| CN113676343B (en) | Fault source positioning method and device for power communication network | |
| CN107403279B (en) | Oil transfer pump working condition self-adaptive state early warning system and method | |
| CN111275136B (en) | Fault prediction system based on small sample and early warning method thereof | |
| CN116993329B (en) | Communication equipment operation maintenance decision management system based on data analysis | |
| CN116708038B (en) | Industrial Internet enterprise network security threat identification method based on asset mapping | |
| CN112001511A (en) | Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining | |
| CN116739829B (en) | Big data-based power data analysis method, system and medium | |
| CN117493498B (en) | Electric power data mining and analysis system based on industrial Internet | |
| CN108521346B (en) | Method for positioning abnormal nodes of telecommunication bearer network based on terminal data | |
| CN117390468B (en) | Dust removal equipment state monitoring and early warning method and system based on data mining | |
| CN113313365A (en) | Degradation early warning method and device for primary air fan | |
| CN109145773A (en) | A kind of failure prediction method of multi-source tendency information fusion | |
| CN117574292A (en) | Data fault detection method and system | |
| CN116910128A (en) | Wind turbine generator hard and soft fault data analysis system and analysis method thereof | |
| CN111934903A (en) | Docker container fault intelligent prediction method based on time sequence evolution genes | |
| CN116165939A (en) | Remote supervision system and method for environmental protection equipment based on big data | |
| CN116467592A (en) | Production equipment fault intelligent monitoring method and system based on deep learning | |
| CN115511156A (en) | Main transformer overload early warning method and system based on load prediction | |
| CN114358723A (en) | Working hour data processing method and system based on isolated forest algorithm |
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 |