CN115689071A - Equipment fault fusion prediction method and system based on correlation parameter mining - Google Patents
Equipment fault fusion prediction method and system based on correlation parameter mining Download PDFInfo
- Publication number
- CN115689071A CN115689071A CN202310001115.1A CN202310001115A CN115689071A CN 115689071 A CN115689071 A CN 115689071A CN 202310001115 A CN202310001115 A CN 202310001115A CN 115689071 A CN115689071 A CN 115689071A
- Authority
- CN
- China
- Prior art keywords
- fault
- equipment
- prediction result
- prediction
- current time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000004927 fusion Effects 0.000 title claims abstract description 19
- 238000005065 mining Methods 0.000 title claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims abstract description 31
- 238000010606 normalization Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims description 48
- 238000012360 testing method Methods 0.000 claims description 33
- 238000010801 machine learning Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 6
- 229910052731 fluorine Inorganic materials 0.000 claims description 5
- 125000001153 fluoro group Chemical group F* 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 230000033228 biological regulation Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical group [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 238000005234 chemical deposition Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an equipment fault fusion prediction method and system based on correlation parameter mining, which specifically comprises the following steps: collecting historical operating parameters and time sequence data of equipment; performing sequence normalization on each fault data based on the time sequence data to obtain a fault event sequence set; constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; for the operation parameters at the current time, predicting the abnormal working conditions of the equipment according to the relevance bipartite graph, and taking the prediction as a first prediction result; obtaining a second prediction of the fault by another method step; and effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result. The method takes the relevance of the operation parameters and the relevance of the time sequence into consideration, and can obtain more complete equipment abnormal information and more accurate prediction results in advance, so that the fault prediction method can achieve the aims of rapidness and high efficiency.
Description
Technical Field
The invention relates to the technical field of reliability maintenance engineering, in particular to an equipment fault fusion prediction method and system based on correlation parameter mining.
Background
Most of the traditional industrial equipment fault early warning methods are that a fault prediction model is trained based on a data set, and then relevant data is input into the trained prediction model to output a fault prediction result, for example, CN115186904A (China, published date: 20221014) discloses a method and a device for predicting the fault of industrial equipment based on a Transformer, which is realized by acquiring a time sequence data set corresponding to the health state of target industrial equipment; inputting the time sequence data set into a trained fault prediction model, and outputting a fault prediction value of the time sequence data set, wherein the fault prediction model is obtained on the basis of training of a training sample carrying a fault prediction value label; and when the failure prediction value is larger than the failure threshold value, judging that the target industrial equipment fails, otherwise, judging that the target industrial equipment normally operates. Although the conventional fault prediction method is convenient and simple to apply, the operation state of the equipment is not fixed and unchanged in the operation process of the industrial equipment, and the traditional prediction method is not high enough in accuracy along with the increase of data updating and cannot meet the prediction accuracy requirement under the complex industrial environment.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide an equipment fault fusion prediction method and system based on associated parameter mining, aiming at the defects of low prediction efficiency, low accuracy and low real-time performance of the traditional industrial equipment fault prediction technology. The first prediction result obtained by the bipartite graph and the second prediction result obtained by an alternative method are effectively fused to obtain a final equipment fault prediction result, so that the fault prediction result can achieve the aims of rapidness, high efficiency and high accuracy.
The technical scheme is as follows: in order to realize the purpose of the invention, the invention adopts the following technical scheme: a device fault fusion prediction method based on correlation parameter mining comprises the following steps:
s1, collecting historical operating parameters and time sequence data of equipment;
s2, performing sequence normalization on each fault data based on the time sequence data to obtain a fault event sequence set;
s3, constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; the nodes in the relevance bipartite graph comprise fault object nodes and operation parameter characteristic nodes, and connecting edges between the fault object nodes and the operation parameter characteristic nodes represent that relevance relations exist between the fault object nodes and the operation parameter characteristic nodes;
s4, predicting the abnormal working condition of the equipment according to the relevance bipartite graph for the operation parameters at the current time, and taking the prediction as a first prediction result;
s5, carrying out piecewise linearization vector representation on the time sequence data according to a fixed time distance: x K ={x 1 ,x 2 ,…, x K-1 , x K }; k is the total number of time series segments, K =1,2. x is the number of 1 The operating parameter characteristic of the first time sequence section; x is a radical of a fluorine atom 2 Characterizing the operating parameters of the second time series segment; x is a radical of a fluorine atom k-1 The operation parameter characteristics of the kth-1 time sequence section; x is a radical of a fluorine atom k The operation parameter characteristic of the kth time sequence section;
s6, assuming that the ith time sequence section is in a fault-free state, and the corresponding operation parameter characteristic is x i (ii) a Supposing that the jth time sequence segment is in a fault state, the corresponding operating parameter characteristic is x j ;
S7, calculating the operation parameter x of the current time a a And x i Characteristic distance D1:whereinIs a correction factor;
s8, calculating the operation parameter x of the current time a a And x j Characteristic distance D2:,a 2-norm representing a vector;
s9, integrating the value ranges of the D1 and the D2, predicting the abnormal working condition of the equipment, and taking the abnormal working condition as a second prediction result;
and S10, effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result.
Further, in S9, the value ranges of D1 and D2 are integrated, the abnormal operating condition of the device is predicted, and as a second prediction result, the method specifically includes:
operating parameter x for the current time a a And x i Characteristic distance between, setting a threshold;
Operating parameter x for the current time a a And x j Characteristic distance between, setting a threshold;
When D1 is less thanAnd D2 is greater thanIf so, indicating that the equipment at the current time has no fault;
when D1 is greater thanAnd D2 is less thanIf so, indicating that the equipment at the current time is faulty;
when D1 is greater thanAnd D2 is greater thanIf so, indicating the possibility of failure of the equipment at the current time;
when D1 is less thanAnd D2 is less thanAnd then indicating the possibility of the fault of the equipment at the current time.
Further, the step S10 of effectively fusing the first prediction result and the second prediction result to obtain a final device failure prediction result includes that the first prediction result and the second prediction result are fused by a decision-level model obtained by a machine learning method to obtain the final device failure prediction result.
Further, the decision-level model obtained by the machine learning method is obtained by pre-training, and specifically includes:
taking fault data related to equipment history as training data to carry out data preprocessing to form a training set and a test set;
training the decision-level model using the training set;
testing the decision-level model using the test set;
and updating the model parameters of the decision-making model according to the test result, and obtaining the decision-making model through iterative training.
Based on the same inventive concept, the invention discloses an equipment fault fusion prediction system based on correlation parameter mining, which comprises:
the acquisition module is used for acquiring historical operating parameters and time sequence data of the equipment;
the sorting module is used for sorting the sequence of each fault data based on the time sequence data to obtain a fault event sequence set;
the construction module is used for constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; the nodes in the relevance bipartite graph comprise fault object nodes and operation parameter characteristic nodes, and connecting edges between the fault object nodes and the operation parameter characteristic nodes represent that relevance relations exist between the fault object nodes and the operation parameter characteristic nodes;
the prediction module 1 is used for predicting the abnormal working condition of the equipment according to the relevance bipartite graph for the operation parameters at the current time and taking the prediction as a first prediction result;
the segmentation module is used for carrying out segmented linearization vector representation on the time sequence data according to a fixed time distance: x K ={x 1 ,x 2 ,…, x K-1 , x K }; k is the total number of time series segments, K =1,2. x is the number of 1 Characterizing the operating parameters of the first time sequence segment; x is a radical of a fluorine atom 2 Characterizing the operating parameters of the second time series segment; x is the number of k-1 The operation parameter characteristics of the kth-1 time sequence section; x is the number of k The operation parameter characteristic of the kth time sequence section;
assuming that the ith time sequence segment is in a fault-free state, the corresponding operation parameter characteristic is x i (ii) a Supposing that the jth time sequence segment is in a fault state, the corresponding operating parameter characteristic is x j ;
A calculation module 1 for calculating an operating parameter x at a current time a a And x i Characteristic distance D1 between:whereinIs a correction factor;
a calculation module 2 for calculating the operation parameter x of the current time a a And x j Characteristic distance D2:,a 2-norm representing a vector;
the prediction module 2 is used for integrating the value ranges of the D1 and the D2, predicting the abnormal working condition of the equipment and taking the abnormal working condition as a second prediction result;
and the fusion prediction module is used for effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result.
Further, the value ranges of D1 and D2 are integrated, the abnormal operating condition of the device is predicted, and as a second prediction result, the method specifically includes:
operating parameter x for the current time a a And x i Characteristic distance between, setting a threshold;
Operating parameter x for the current time a a And x j Characteristic distance between, setting a threshold;
When D1 is less thanAnd D2 is greater thanIf so, indicating that the equipment at the current time has no fault;
when D1 is greater thanAnd D2 is less thanIf so, indicating that the equipment at the current time is faulty;
when D1 is greater thanAnd D2 is greater thanIf so, indicating the possibility of failure of the equipment at the current time;
when D1 is less thanAnd D2 is less thanAnd then, the possibility that the equipment at the current time is in failure is indicated.
And further, effectively fusing the first prediction result and the second prediction result to obtain a final equipment fault prediction result.
Further, the decision-level model obtained by the machine learning method is obtained by pre-training, and specifically includes:
the preprocessing module is used for preprocessing data by taking fault data related to equipment history as training data to form a training set and a test set;
a training module for training the decision-level model using the training set;
a test module for testing the decision-level model using the test set;
and the iterative training module is used for updating the model parameters of the decision-making model according to the test result and obtaining the decision-making model through iterative training.
Has the advantages that:
1. the equipment fault fusion prediction method based on the correlation parameter mining can be used for equipment fault prediction under complex industrial conditions. Specifically, S1, collecting historical operating parameters and time sequence data of equipment; s2, performing sequence normalization on each fault data based on the time sequence data to obtain a fault event sequence set; s3, constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; s4, predicting the abnormal working condition of the equipment according to the relevance bipartite graph for the operation parameters at the current time, and taking the prediction as a first prediction result; s5, carrying out piecewise linearization vector representation on the time sequence data according to a fixed time distance; s6, supposing that the ith time sequence segment is no reasonThe barrier state and the corresponding operating parameter characteristic are x i (ii) a Supposing that the jth time sequence segment is in a fault state, the corresponding operating parameter characteristic is x j (ii) a S7, calculating the operation parameter x of the current time a a And x i A characteristic distance D1 therebetween; s8, calculating the operation parameter x of the current time a a And x j A characteristic distance D2 therebetween; s9, integrating the value ranges of the D1 and the D2, predicting the abnormal working condition of the equipment, and taking the abnormal working condition as a second prediction result; and S10, effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result. The method provided by the invention takes the relevance of the operation parameters and the relevance of the time sequence into consideration, and can obtain more complete equipment abnormal information and more advanced prediction results; innovatively providing a relevance bipartite graph for constructing operation parameters and fault events, converting a fault prediction problem into a bipartite graph prediction problem, realizing fault prediction by using the advantages of the bipartite graph, and effectively fusing a first prediction result and a second prediction result obtained by the bipartite graph to obtain a final equipment fault prediction result; therefore, the fault prediction method can achieve the aims of high speed and high efficiency.
2. According to the invention, the characteristic distance between the current time operation parameter and the operation parameter characteristic in the two pre-assumed fault states is calculated, and the two characteristic distances are comprehensively compared to obtain a second prediction result, so that the fault prediction is realized, and the fault prediction accuracy is greatly improved.
Drawings
FIG. 1 is a flow chart illustrating the implementation of the steps of the method of the present invention.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.
The industrial equipment applied by the invention is particularly an intelligent comprehensive energy-saving cabinet (intelligent voltage optimization device), which integrates a three-phase magnetic balance technology and a compensation type voltage regulation and stabilization technology, adopts a novel green environment-friendly energy-saving technology system designed for reducing the failure rate of the equipment, prolonging the service life of the equipment and saving the electric charge expenditure of users on the basis of optimizing the working voltage of the equipment by combining a Z-shaped isolation compensation transformer with an iron core and a multi-winding special wiring with a column type voltage regulation transformer. The normal use conditions of the intelligent voltage optimization device are as follows: (1) ambient temperature: -15 ℃ to 40 ℃; (2) altitude: not more than 1000 meters; note: when the altitude exceeds 1000 meters, the load capacity of the regulated power supply will decrease as the altitude increases. (3) relative humidity: less than or equal to 90 percent; (4) The installation place has no gas, steam, chemical deposition, dust, dirt and other explosive and corrosive media which seriously affect the insulation strength of the voltage-stabilized power supply; (5) the installation site should not have severe vibration or jolt. The intelligent comprehensive energy-saving cabinet (intelligent voltage optimization device) can predict and alarm abnormal conditions such as undervoltage, overload, overcurrent and overtemperature in time, and has important effect on the safety and reliability of the intelligent comprehensive energy-saving cabinet.
As shown in fig. 1, the present embodiment provides an apparatus failure fusion prediction method based on correlation parameter mining, which includes the following steps:
s1, collecting historical operating parameters and time sequence data of equipment;
specifically, historical operating parameters and corresponding time sequence data of the digital intelligent comprehensive energy-saving cabinet (intelligent voltage optimization device) are collected; the operating parameters include: input voltage, output voltage, working current, operation temperature, load condition and other data related to the operation of the equipment.
S2, performing sequence normalization on each fault data based on the time sequence data to obtain a fault event sequence set;
specifically, fault data is integrated according to the time sequence data to form a fault event sequence set.
S3, constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; the nodes in the relevance bipartite graph comprise fault object nodes and operation parameter characteristic nodes, and connecting edges between the fault object nodes and the operation parameter characteristic nodes represent that relevance relations exist between the fault object nodes and the operation parameter characteristic nodes;
s4, predicting the abnormal working condition of the equipment according to the relevance bipartite graph for the operation parameters at the current time, and taking the prediction as a first prediction result;
s5, carrying out piecewise linearization vector representation on the time sequence data according to a fixed time distance: x K ={x 1 ,x 2 ,…, x K-1 , x K }; k is the total number of time series segments, K =1,2. x is the number of 1 Characterizing the operating parameters of the first time sequence segment; x is the number of 2 Characterizing the operating parameters of the second time series segment; x is the number of k-1 The operation parameter characteristics of the k-1 time sequence segment are obtained; x is the number of k The operation parameter characteristics of the kth time sequence section;
specifically, for example, if the time series data relates to data of 1 month, the time series may be divided into segments at intervals meeting the demand, such as every half minute, every 1 minute, or every 1 hour;
if the time series data relates to data of 1 whole year, the time series can be divided into time series sections according to the time interval meeting the requirement, such as every 1 minute, every 1 hour, or every 1 day.
S6, assuming that the ith time sequence section is in a fault-free state, and the corresponding operation parameter characteristic is x i (ii) a Supposing that the jth time sequence segment is in a fault state, the corresponding operating parameter characteristic is x j ;
S7, calculating the operation parameter x of the current time a a And x i Characteristic distance D1 between:in whichIs a correction factor;
s8, calculating the operation parameter x of the current time a a And x j Characteristic distance D2:,a 2-norm representing a vector;
s9, integrating the value ranges of the D1 and the D2, predicting the abnormal working condition of the equipment, and taking the abnormal working condition as a second prediction result;
and S10, effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result.
Specifically, in S9, the value ranges of D1 and D2 are integrated, the abnormal operating condition of the device is predicted, and the method specifically includes, as a second prediction result:
operating parameter x for the current time a a And x i Characteristic distance between, setting a threshold;
Operating parameter x for the current time a a And x j Characteristic distance between, setting a threshold;
When D1 is less thanAnd D2 is greater thanIf so, indicating that the equipment at the current time has no fault;
when D1 is greater thanAnd D2 is less thanIf so, indicating that the equipment at the current time is faulty;
when D1 is greater thanAnd D2 is greater thanIf so, indicating the possibility of failure of the equipment at the current time;
when D1 is less thanAnd D2 is less thanAnd then indicating the possibility of the fault of the equipment at the current time.
Specifically, the S10 effectively fuses the first prediction result and the second prediction result to obtain a final equipment failure prediction result, and specifically includes that the first prediction result and the second prediction result are fused through a decision-level model obtained through a machine learning method to obtain the final equipment failure prediction result.
Specifically, the decision-level model obtained by the machine learning method is obtained by pre-training, and specifically includes:
taking fault data related to equipment history as training data to carry out data preprocessing to form a training set and a test set; the sample data ratio of the training set and the test set is 4:1.
Training the decision-level model using the training set;
testing the decision-level model using the test set;
and updating the model parameters of the decision-making model according to the test result, and obtaining the decision-making model through iterative training.
Specifically, a training set is input into a decision-level model for machine learning, and a fault prediction model is obtained preliminarily; and inputting the test set into the preliminarily obtained prediction model, and finally performing parameter adjustment on the model according to the test accuracy so as to obtain the optimal decision-level model.
Based on the same inventive concept, the equipment fault fusion prediction system based on the correlation parameter mining disclosed by the embodiment comprises:
the acquisition module is used for acquiring historical operating parameters and time sequence data of the equipment;
specifically, historical operating parameters and corresponding time sequence data of the digital intelligent comprehensive energy-saving cabinet (intelligent voltage optimization device) are collected; the operating parameters include: input voltage, output voltage, working current, operation temperature, load condition and other data related to the operation of the equipment.
The sorting module is used for sorting the sequence of each fault data based on the time sequence data to obtain a fault event sequence set;
specifically, fault data is integrated according to the time sequence data to form a fault event sequence set.
The construction module is used for constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; the nodes in the relevance bipartite graph comprise fault object nodes and operation parameter characteristic nodes, and connecting edges between the fault object nodes and the operation parameter characteristic nodes represent that relevance relations exist between the fault object nodes and the operation parameter characteristic nodes;
the prediction module 1 is used for predicting the abnormal working condition of the equipment according to the relevance bipartite graph for the operation parameters at the current time and taking the prediction as a first prediction result;
the segmentation module is used for carrying out segmented linearization vector representation on the time sequence data according to a fixed time distance: x K ={x 1 ,x 2 ,…, x K-1 , x K }; k is the total number of time series segments, K =1,2. x is the number of 1 Characterizing the operating parameters of the first time sequence segment; x is the number of 2 Characterizing the operating parameters of the second time series segment; x is the number of k-1 The operation parameter characteristics of the kth-1 time sequence section; x is the number of k The operation parameter characteristic of the kth time sequence section;
specifically, for example, if the time series data relates to data of 1 month, the time series may be divided into segments at intervals meeting the demand, such as every half minute, every 1 minute, or every 1 hour;
if the time series data relates to data of 1 whole year, the time series can be divided into time series sections according to the time interval meeting the requirement, such as every 1 minute, every 1 hour, or every 1 day.
Specifically, assuming that the ith time sequence segment is in a fault-free state, the corresponding operating parameter characteristic is x i (ii) a Supposing that the jth time sequence segment is in a fault state, the corresponding operating parameter characteristic is x j ;
A calculation module 1 for calculating an operating parameter x of the current time a a And x i Characteristic distance D1:whereinIs a correction factor;
a calculation module 2 for calculating the operation parameter x of the current time a a And x j Characteristic distance D2:,a 2-norm representing a vector;
the prediction module 2 is used for integrating the value ranges of the D1 and the D2, predicting the abnormal working condition of the equipment and taking the abnormal working condition as a second prediction result;
and the fusion prediction module is used for effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result.
Specifically, the value ranges of D1 and D2 are integrated, the abnormal operating condition of the device is predicted, and as a second prediction result, the method specifically includes:
operating parameter x for the current time a a And x i Characteristic distance between, setting a threshold;
When D1 is less thanAnd D2 is greater thanIf so, indicating that the equipment at the current time has no fault;
when D1 is greater thanAnd D2 is less thanIf so, indicating that the equipment at the current time is faulty;
when D1 is greater thanAnd D2 is greater thanIf so, indicating the possibility of failure of the equipment at the current time;
when D1 is less thanAnd D2 is less thanAnd then, the possibility that the equipment at the current time is in failure is indicated.
Specifically, the method comprises the step of effectively fusing a first prediction result and a second prediction result to obtain a final equipment fault prediction result, and specifically comprises the step of fusing the first prediction result and the second prediction result through a decision-level model obtained by a machine learning method to obtain the final equipment fault prediction result.
Specifically, the decision-level model obtained by the machine learning method is obtained by pre-training, and specifically includes:
the preprocessing module is used for preprocessing data by taking fault data related to equipment history as training data to form a training set and a test set; the sample data ratio of the training set and the test set is 4:1.
A training module for training the decision-level model using the training set;
a test module for testing the decision-level model using the test set;
and the iterative training module is used for updating the model parameters of the decision-making model according to the test result and obtaining the decision-making model through iterative training.
Specifically, a training set is input into a decision-level model for machine learning, and a fault prediction model is obtained preliminarily; and inputting the test set into the preliminarily obtained prediction model, and finally performing parameter adjustment on the model according to the test accuracy so as to obtain the optimal decision-level model.
Claims (8)
1. A device fault fusion prediction method based on correlation parameter mining is characterized by comprising the following steps:
s1, collecting historical operating parameters and time sequence data of equipment;
s2, performing sequence normalization on each fault data based on the time sequence data to obtain a fault event sequence set;
s3, constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; the nodes in the relevance bipartite graph comprise fault object nodes and operation parameter characteristic nodes, and connecting edges between the fault object nodes and the operation parameter characteristic nodes represent that relevance relations exist between the fault object nodes and the operation parameter characteristic nodes;
s4, predicting the abnormal working condition of the equipment according to the relevance bipartite graph for the operation parameters at the current time, and taking the prediction as a first prediction result;
s5, carrying out piecewise linearization vector representation on the time sequence data according to the fixed time distance: x K ={x 1 ,x 2 ,…, x K-1 , x K }; k is the total number of time sequence segments, K =1,2, · K; x is the number of 1 Characterizing the operating parameters of the first time sequence segment; x is the number of 2 Characterizing the operating parameters of the second time series segment; x is the number of k-1 The operation parameter characteristics of the kth-1 time sequence section; x is the number of k The operation parameter characteristics of the kth time sequence section;
s6, assuming that the ith time sequence section is in a fault-free state, and the corresponding operation parameter characteristic is x i (ii) a Supposing that the jth time sequence segment is in a fault state, the corresponding operating parameter characteristic is x j ;
S7, calculating the operation parameter x of the current time a a And x i Characteristic distance D1 between:in whichIs a correction factor;
s8, calculating the operation parameter x of the current time a a And x j Characteristic distance D2:,a 2-norm representing a vector;
s9, integrating the value ranges of the D1 and the D2, predicting the abnormal working condition of the equipment, and taking the abnormal working condition as a second prediction result;
and S10, effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result.
2. The method for predicting the equipment fault fusion based on the association parameter mining according to claim 1, wherein the step S9 is to synthesize the value ranges of D1 and D2, predict the abnormal working condition of the equipment, and as a second prediction result, specifically include:
operating parameter x for the current time a a And x i Characteristic distance between, setting a threshold;
Operating parameter x for the current time a a And x j Characteristic distance between, setting a threshold;
When D1 is less thanAnd D2 is greater thanIf so, indicating that the equipment at the current time has no fault;
when D1 is greater thanAnd D2 is less thanIf so, indicating that the equipment at the current time is faulty;
when D1 is greater thanAnd D2 is greater thanIf so, indicating the possibility of failure of the equipment at the current time;
3. The equipment fault fusion prediction method based on correlation parameter mining as claimed in claim 1, wherein S10, the first prediction result and the second prediction result are effectively fused to obtain a final equipment fault prediction result, and the method specifically comprises the step of fusing the first prediction result and the second prediction result through a decision-level model obtained by a machine learning method to obtain the final equipment fault prediction result.
4. The method for predicting the equipment failure fusion based on the correlation parameter mining as claimed in claim 3, wherein the decision-level model obtained by the machine learning method is obtained by pre-training, and specifically comprises:
taking fault data related to equipment history as training data to carry out data preprocessing to form a training set and a test set;
training the decision-level model using the training set;
testing the decision-level model using the test set;
and updating the model parameters of the decision-making model according to the test result, and obtaining the decision-making model through iterative training.
5. An equipment fault fusion prediction system based on correlation parameter mining is characterized by comprising:
the acquisition module is used for acquiring historical operating parameters and time sequence data of the equipment;
the sorting module is used for sorting the sequence of each fault data based on the time sequence data to obtain a fault event sequence set;
the construction module is used for constructing a correlation bipartite graph of the operation parameters and the fault events based on the fault event sequence set; the nodes in the relevance bipartite graph comprise fault object nodes and operation parameter characteristic nodes, and connecting edges between the fault object nodes and the operation parameter characteristic nodes represent that relevance relations exist between the fault object nodes and the operation parameter characteristic nodes;
the prediction module 1 is used for predicting the abnormal working condition of the equipment according to the relevance bipartite graph for the operation parameters at the current time and taking the prediction as a first prediction result;
the segmentation module is used for carrying out segmented linearization vector representation on the time sequence data according to a fixed time distance: x K ={x 1 ,x 2 ,…, x K-1 , x K }; k is the total number of time series segments, K =1,2. x is the number of 1 Characterizing the operating parameters of the first time sequence segment; x is a radical of a fluorine atom 2 Characterizing the operating parameters of the second time series segment; x is the number of k-1 The operation parameter characteristics of the kth-1 time sequence section; x is the number of k The operation parameter characteristic of the kth time sequence section;
assuming that the ith time sequence segment is in a fault-free state, the corresponding operation parameter characteristic is x i (ii) a Supposing that the jth time sequence segment is in a fault state, the corresponding operating parameter characteristic is x j ;
A calculation module 1 for calculating an operating parameter x of the current time a a And x i Characteristic distance D1 between:in whichIs a correction factor;
a calculation module 2 for calculating the operation parameter x of the current time a a And x j Characteristic distance D2:,a 2-norm representing a vector;
the prediction module 2 is used for integrating the value ranges of the D1 and the D2, predicting the abnormal working condition of the equipment and taking the abnormal working condition as a second prediction result;
and the fusion prediction module is used for effectively fusing the first prediction result and the second prediction result to obtain a final equipment failure prediction result.
6. The system according to claim 5, wherein the value ranges of D1 and D2 are integrated to predict the abnormal working condition of the device, and the system, as a second prediction result, specifically comprises:
operating parameter x for the current time a a And x i Characteristic distance between, setting a threshold;
Operating parameter x for the current time a a And x j Characteristic distance between, setting a threshold;
When D1 is less thanAnd D2 is greater thanIf so, indicating that the equipment at the current time has no fault;
when D1 is greater thanAnd D2 is less thanIf yes, indicating that the equipment at the current time is in fault;
when D1 is greater thanAnd D2 is greater thanIf yes, indicating the possibility of failure of the equipment at the current time;
7. The equipment fault fusion prediction system based on correlation parameter mining as claimed in claim 5, wherein the first prediction result and the second prediction result are effectively fused to obtain a final equipment fault prediction result, and the method specifically comprises the step of fusing the first prediction result and the second prediction result through a decision-level model obtained by a machine learning method to obtain the final equipment fault prediction result.
8. The system according to claim 7, wherein the decision-level model obtained by the machine learning method is obtained by pre-training, and specifically comprises:
the preprocessing module is used for preprocessing data by taking fault data related to equipment history as training data to form a training set and a test set;
a training module for training the decision-level model using the training set;
a test module for testing the decision-level model using the test set;
and the iterative training module is used for updating the model parameters of the decision-making model according to the test result and obtaining the decision-making model through iterative training.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310001115.1A CN115689071B (en) | 2023-01-03 | 2023-01-03 | Equipment fault fusion prediction method and system based on associated parameter mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310001115.1A CN115689071B (en) | 2023-01-03 | 2023-01-03 | Equipment fault fusion prediction method and system based on associated parameter mining |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115689071A true CN115689071A (en) | 2023-02-03 |
CN115689071B CN115689071B (en) | 2023-05-02 |
Family
ID=85057536
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310001115.1A Active CN115689071B (en) | 2023-01-03 | 2023-01-03 | Equipment fault fusion prediction method and system based on associated parameter mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115689071B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116755403A (en) * | 2023-06-13 | 2023-09-15 | 英利新能源(宁夏)有限公司 | Data acquisition method and system based on photovoltaic module production control system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008253A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | The industrial data association rule mining and unusual service condition prediction technique of strategy are generated based on two stages frequent item set |
CN110008565A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | A kind of industrial process unusual service condition prediction technique based on operating parameter association analysis |
CN110018670A (en) * | 2019-03-28 | 2019-07-16 | 浙江大学 | A kind of industrial process unusual service condition prediction technique excavated based on dynamic association rules |
CN112801426A (en) * | 2021-04-06 | 2021-05-14 | 浙江浙能技术研究院有限公司 | Industrial process fault fusion prediction method based on correlation parameter mining |
CN112906969A (en) * | 2021-03-01 | 2021-06-04 | 三一重工股份有限公司 | Engine fault prediction method, engine fault prediction device, electronic equipment and storage medium |
CN114818515A (en) * | 2022-06-24 | 2022-07-29 | 中国海洋大学 | Multidimensional time sequence prediction method based on self-attention mechanism and graph convolution network |
-
2023
- 2023-01-03 CN CN202310001115.1A patent/CN115689071B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008253A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | The industrial data association rule mining and unusual service condition prediction technique of strategy are generated based on two stages frequent item set |
CN110008565A (en) * | 2019-03-28 | 2019-07-12 | 浙江大学 | A kind of industrial process unusual service condition prediction technique based on operating parameter association analysis |
CN110018670A (en) * | 2019-03-28 | 2019-07-16 | 浙江大学 | A kind of industrial process unusual service condition prediction technique excavated based on dynamic association rules |
CN112906969A (en) * | 2021-03-01 | 2021-06-04 | 三一重工股份有限公司 | Engine fault prediction method, engine fault prediction device, electronic equipment and storage medium |
CN112801426A (en) * | 2021-04-06 | 2021-05-14 | 浙江浙能技术研究院有限公司 | Industrial process fault fusion prediction method based on correlation parameter mining |
CN114818515A (en) * | 2022-06-24 | 2022-07-29 | 中国海洋大学 | Multidimensional time sequence prediction method based on self-attention mechanism and graph convolution network |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116755403A (en) * | 2023-06-13 | 2023-09-15 | 英利新能源(宁夏)有限公司 | Data acquisition method and system based on photovoltaic module production control system |
CN116755403B (en) * | 2023-06-13 | 2024-03-26 | 英利新能源(宁夏)有限公司 | Data acquisition method and system based on photovoltaic module production control system |
Also Published As
Publication number | Publication date |
---|---|
CN115689071B (en) | 2023-05-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109146093B (en) | Power equipment field investigation method based on learning | |
CN105092999B (en) | Positioned using the power quality events of multiple instructions | |
US10355478B2 (en) | System and method for asset health monitoring using multi-dimensional risk assessment | |
CN111639921B (en) | Intelligent equipment fault judgment and auxiliary disposal method based on expert system | |
CN110222889B (en) | Power distribution network feeder automation terminal configuration method based on multiple intelligent algorithms | |
CN111369168B (en) | Associated feature selection method suitable for multiple regulation and control operation scenes of power grid | |
CN107844628B (en) | Redundancy optimization method for large-scale offshore wind farm power collection system | |
CN115689071B (en) | Equipment fault fusion prediction method and system based on associated parameter mining | |
CN111488896A (en) | Distribution line time-varying fault probability calculation method based on multi-source data mining | |
CN107632234A (en) | A kind of deformation of transformer winding appraisal procedure based on recorder data | |
CN109919432A (en) | A kind of substation equipment failure analysis of Influential Factors method based on big data | |
Liu et al. | Reinforcement learning for cyber-physical security assessment of power systems | |
CN113052473B (en) | Power grid risk analysis method based on fault rate and static safety analysis | |
CN114692787B (en) | Multi-source data-based three-winding main transformer event analysis processing method and system | |
CN115358355A (en) | Method and device for judging main transformer oil temperature gauge and top layer oil temperature abnormity | |
CN109377044A (en) | A kind of trouble hunting Cost Analysis Method of intelligent substation protection equipment | |
Huang et al. | Extracting substation cyber-physical architecture through intelligent electronic devices' data | |
Li et al. | Reliability improvement to UPFC with routine test to the abnormal state | |
Pedersen et al. | Data Validation for Digitally Enabled Operation & Maintenance of District Heating Systems | |
de Oliveira et al. | Voltage dips caused by faults in a transmission system: a monitoring case study of a sensitive industrial consumer | |
CN112001073A (en) | Reliability analysis research method of traction power supply system | |
CN110826179A (en) | Intelligent substation relay protection real-time reliability prediction method | |
CN117911196B (en) | Ring main unit full-period operation data supervision system and method based on artificial intelligence | |
Peharda et al. | An Advanced Tool for Data Analysis of Energy Management System Calculations | |
CN114291675B (en) | Elevator fault diagnosis method based on complex network and confidence rule reasoning |
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 | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240208 Address after: No.198 GANGLONG Road, Yangzhong Development Zone, Zhenjiang City, Jiangsu Province, 212000 Patentee after: Zhenjiang Anhua Electric Group Co.,Ltd. Country or region after: China Address before: Room 1001-3, Tower C, Zhimengyuan, 4 Gupinggang, Gulou District, Nanjing, Jiangsu, 210000 Patentee before: Nanjing University of Technology Jinhong Energy Technology Co.,Ltd. Country or region before: China |