CN111598220B - Gas turbine fault prediction method based on correlation analysis - Google Patents
Gas turbine fault prediction method based on correlation analysis Download PDFInfo
- Publication number
- CN111598220B CN111598220B CN202010404291.6A CN202010404291A CN111598220B CN 111598220 B CN111598220 B CN 111598220B CN 202010404291 A CN202010404291 A CN 202010404291A CN 111598220 B CN111598220 B CN 111598220B
- Authority
- CN
- China
- Prior art keywords
- monitoring node
- monitoring
- node vector
- vector
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- 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
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/14—Testing gas-turbine engines or jet-propulsion engines
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a gas turbine fault prediction method based on correlation analysis, which comprises the following steps: 1. reading in monitoring node vectors to be processed one by one in a streaming manner; 2. performing correlation analysis on each currently read monitoring node vector and the monitoring node vectors which are already read in by the system; 3. carrying out redundancy analysis on the selected related monitoring nodes; 4. orienting the newly added monitoring nodes, determining the causal relationship with other monitoring nodes, repeating the steps 1-4 until the number of the read-in monitoring node vectors exceeds a limit value, and finally obtaining a corresponding causal structure diagram of the monitoring system and using the causal structure diagram to train a fault prediction model; therefore, a fault prediction model is obtained, and the fault can be more accurately predicted. The invention can obtain a more accurate fault prediction model, thereby being capable of predicting faults more accurately.
Description
Technical Field
The invention belongs to the field of data mining, and particularly relates to a gas turbine fault prediction method based on correlation analysis.
Background
At present, the state monitoring and fault diagnosis research status of domestic gas turbines is greatly improved recently, but the technology is relatively laggard and the application results are few. With the advent of big data technology, how to apply big data correlation technology to gas turbine condition monitoring and fault diagnosis is a topic worth studying. The gas turbine set continuously generates a large amount of monitoring data during operation, and based on the massive operation monitoring data, the state analysis, performance monitoring and fault intelligent diagnosis and prediction research of the gas turbine set are carried out, so that the method has very important practical significance. Through data modeling, the state of the gas turbine unit can be evaluated healthily in real time, the state trend can be predicted, early warning can be carried out before major faults occur, and the faults of the gas turbine can be found early, so that economic loss is avoided, maintenance suggestions are provided, and safe and reliable operation of the gas turbine is facilitated. However, the distribution of the data is often arbitrary, and the relationship between the data and each other is often characterized by nonlinearity, and the research on the nonlinear data is a certain challenge. The operational data forms a complex network system, and identifies relationships between network nodes of the complex system to facilitate condition monitoring and fault prediction for the gas turbine.
The outstanding model describing the relationship between complex networks is a Bayesian network model based on probability theory and graph theory, which is proposed by Judea Pearl of California university in America, and obtains 2011 annual map prize with outstanding contribution. Hoyer et al further extended the bayesian network causal model to propose an additive noise model that can model data that is not gaussian non-linear. The operating data of the gas turbine assembly are also precisely non-gaussian non-linear. Therefore, analyzing the operating data of a gas turbine plant based on an additive noise model is a very meaningful research direction. As for structure learning of additive noise models, hoyer et al propose methods for identifying causal structures based on nonlinear regression and HSIC standards, mooij et al propose algorithms based on HSIC regression, zhang et al propose two-stage algorithms, tillman et al propose kPC algorithm, yamada et al propose methods for least squares independence regression, mooij et al propose methods based on maximum posterior, zhang et al propose a kernel-based condition independence test, peters et al propose regression methods based on subsequent independence tests, zhang et al propose a regression-based condition independence test method, etc., nowzohour et al propose methods based on penalized likelihood, etc.
The data of the gas turbine unit also has high-dimensional characteristics, and one method for processing the high-dimensional data is dimension reduction, and a principal component analysis method, an independent component analysis method and the like are generally adopted, and the methods all need to know information of all data dimensions in advance and load the information into a memory at one time, but sometimes the data of the gas turbine unit has huge dimensions and cannot be loaded into the memory at one time. And new station data may continually appear, resulting in a dynamic, unknown feature space of the data. The method for processing dynamic high-dimensional data has emerged in recent years, is a new research direction in the field of data mining, and can effectively process high-dimensional large data.
The major limitations of these current approaches include:
(1) The calculation complexity of most algorithms is high, and the requirement of online real-time learning of the operation data of the gas turbine unit cannot be met;
(2) The gas turbine set data is large in dimension and cannot be loaded into a memory at one time, new measuring point data can continuously appear, and the existing method cannot handle the situation.
Disclosure of Invention
The invention provides a gas turbine fault prediction method based on correlation analysis for overcoming the defects in the prior art, so that a more accurate fault prediction model can be obtained, and the fault can be predicted more accurately.
The invention adopts the following technical scheme for solving the technical problems:
the invention relates to a gas turbine fault prediction method based on correlation analysis, which is applied to a gas turbine system, and monitors the operation states of Z monitoring nodes in the gas turbine system at intervals, so that a gas turbine operation data set D consisting of m monitoring value vectors is obtained and is recorded as D = { sam 1 ,sam 2 ,...,sam v ,...,sam m Wherein, sam v Represents a vector of the v-th monitored value, an
Representing the monitoring value of the ith monitoring node in the v-th monitoring value vector; v is more than or equal to 1 and less than or equal to m, i is more than or equal to 1 and less than or equal to Z; defining a vector formed by monitoring values of the ith monitoring node under m-time monitoring as X i The method is characterized in that the fault prediction of the gas turbine is carried out according to the following steps:
step 1, defining a time t, and initializing t =0;
defining the limit value of the number Z of the monitoring nodes as max, namely Z is less than or equal to max;
step 2, defining the selected monitoring node vector set as EF, and initializing the selected monitoring node vector set at the t-th moment as
Step 3, defining a variable j, and initializing j =1;
step 4, judging whether the j is less than or equal to Z, if so, reading a jth monitoring node vector X with m values from a gas turbine operation data set D j (ii) a And initializing the jth monitor node vector X j Of the relevant monitoring node vector set MB (X) j ) Initializing jth monitoring node vector X for null j Newly added monitoring node vector set FA (X) j ) Initializing jth monitoring node vector X for null j Redundant monitor node vector set FD (X) j ) Is empty; then step 5 is executed; otherwise, the final causal structure diagram formed by the monitoring nodes is obtained, wherein the father node and the child node of each monitoring node are the monitoring nodes related to the corresponding monitoring node, and step 16 is executed;
step 5, judging whether j =1 is true, if so, determining the jth monitoring node vector X j Adding the selected monitoring node vector set EF at the t moment t Thereby obtaining the selected monitoring node vector set EF at the t +1 th moment t+1 (ii) a Assigning t +1 to t, assigning j +1 to j, and returning to the step 4; otherwise, executing step 6;
step 6, for the jth monitoring node vector X j Performing correlation analysis;
step 7, judging the jth monitoring node vector X j Of the relevant monitoring node vector set MB (X) j ) If the set is an empty set, returning to the step 4; otherwise, the jth monitoring node vector X is used j Adding the monitoring node vector set EF selected at the t moment t To obtain the monitor selected at the t +1 th timeVector set EF of measured nodes t+1 ＝EF t ∪X j (ii) a Assigning t +1 to t, and executing the step 8;
step 8, defining a variable k, and initializing k =1;
step 9, for the monitoring node vector set EF selected at the t-th moment t Of the kth monitoring node vector X k Performing redundancy check analysis;
step 10, assigning k +1 to k, judging whether k is greater than j, and executing step 11 if k is greater than j; otherwise, returning to the step 9 for execution;
step 11, defining a variable count; and initializing count =0; initializing k =1;
step 12, judging the k-th monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) Whether the vector set is an empty set or not, if the vector set is the empty set, selecting a monitoring node vector set EF from the t-th moment t Deleting the k-th monitoring node vector X k Then, after assigning the count +1 to the count, executing step 13; otherwise, directly executing step 13;
step 13, assigning k +1 to k; judging whether k is more than j, if so, assigning j-count to j, and then obtaining an updated monitoring node vector set EF selected at the t-th moment t ', is denoted as EF t ′＝{X′ 1 ,X′ 2 ,...,X′ i ,...X′ j-count }；X′ i Set of monitoring node vectors EF representing the t-th moment of update t The ith monitor node vector in' and, in combination,
represents the ith monitor node vector X' i The nth monitored value; i is more than or equal to 1 and less than or equal to j-count; assigning j-count to j, and executing step 14; otherwise, returning to the step 12 for execution;
step 14, for the monitoring node vector set EF selected at the t-th time t 'j-th monitor node vector X' j Carrying out online local orientation to obtain a t moment causal structure diagram;
step 15, assigning j +1 to j, and returning to the step 4;
step 16, selecting a monitoring node vector of a monitoring node at will, and using the monitoring node vector as the output of the LSTM neural network model, and using the monitoring node vector related to the selected monitoring node as the input of the LSTM neural network model, so as to train the LSTM neural network model, thereby obtaining a fault prediction model;
and step 17, monitoring the operation state of any monitoring node in real time, obtaining a corresponding gas turbine operation data set, obtaining a predicted value of the monitoring node monitored in real time by using the fault prediction model, comparing the predicted value with a real value of the monitoring node monitored in real time, indicating that the corresponding monitoring node is likely to have a fault when the predicted value exceeds a set threshold value, and giving an early warning prompt.
The method for predicting the fault of the gas turbine based on the correlation analysis is also characterized in that the step 6 is carried out according to the following steps:
step 6.1, setting a correlation threshold value as alpha;
step 6.2, defining a variable w; and initializing w =1; defining a variable theta;
step 6.3, calculating the jth monitoring node vector X by using a Hilbert-Schmidt independence criterion j And w-th monitor node vector X w Degree of correlation HSIC jw ；
Step 6.4, correlating degree HSIC jw Assigning to theta, judging whether theta is more than or equal to alpha, and if so, indicating a jth monitoring node vector X j And w-th monitor node vector X w Correlating and executing step 6.5; otherwise, the j monitoring node vector X is represented j And w-th monitor node vector X w Independent, and step 6.6 is performed;
step 6.5, monitoring the jth node vector X j Vector X added to the w-th monitor node w Of the relevant monitoring node vector set MB (X) w ) In (1), i.e. MB (X) w )＝MB(X w )∪X j The jth monitor node vector X j Adding newly added monitoring node vector set FA (X) w ) In (1), namely FA (X) w )＝FA(X w )∪{X j H, thereby updating the w-th monitor node vector X w Of the relevant monitoring node vector set MB (X) w ) And a newly added monitoring node vector set FA (X) w ) (ii) a At the same time, the w-th monitoring node vector X w Vector X added to jth monitor node j Of the relevant monitoring node vector set MB (X) j ) I.e. MB (X) j )＝MB(X j )∪X w The w-th monitor node vector X w Adding newly added monitoring node vector set FA (X) j ) In (1), namely FA (X) j )＝FA(X j )∪{X w H, update the jth monitor node vector X j Relevant monitoring node vector set MB (X) j ) And a newly added monitoring node vector set FA (X) j ) (ii) a Then step 6.6 is executed;
6.6, assigning k +1 to k, judging whether k is greater than j-1, and if so, executing step 7; otherwise, the step 6.3 is returned to for execution.
The online redundancy check analysis of the step 9 is carried out according to the following steps:
step 9.1, setting a redundancy threshold value beta; calculating the kth monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) The number of the monitoring node vectors in (1) is recorded as S k ；
Step 9.2, defining a variable s; and initializing s =1; defining a variable sigma;
step 9.3, obtaining the relevant monitoring node vector set MB (X) k ) The vector of the middle s-th monitoring node is denoted by tau s ；
Step 9.4, calculating the t < th > by using Hilbert-Schmidt independence criterion s Vector of monitoring nodes
And the kth monitoring node vector X k Degree of correlation of
Step 9.5, correlating the degree of correlation
Assigning to sigma, judging whether sigma is less than or equal to beta, if yes, representing the tau s Vector of monitoring nodes
And the kth monitoring node vector X k Irrelevant, namely, the node is a redundant monitoring node, and step 9.6 is executed; otherwise, it indicates the τ th s Vector of monitoring nodes
And the kth monitoring node vector X k Correlation and step 9.7 is performed;
step 9.6, from the k-th monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) In which the τ th is deleted s A vector of monitoring nodes
Namely, it is
And will be tau s Vector of monitoring nodes
Adding the kth monitoring node vector X k Redundant monitor node vector set FD (X) k ) In, i.e.
From the said τ th s A vector of monitoring nodes
Relevant monitoring node vector set
Deleting the k-th monitoring node vector X k I.e. MB (X) τs )＝MB(X τs )-X k And the k-th monitoring node vector X k Adding said t s Vector of monitoring nodes
Redundant monitoring node vector set
Namely that
Step 9.7, assigning s +1 to s; and judging S > S k If yes, executing step 10; otherwise, the step 9.3 is returned to for execution.
The step 14 is carried out according to the following steps:
step 14.1, setting a direction support degree threshold value as gamma;
step 14.2, from the jth monitoring node vector X j Relevant monitoring node vector set MB (X) j ) Optionally a monitoring node vector X g And the g-th monitoring node vector X g Vector set MB (X) from related monitoring nodes i ) Deleting;
step 14.3, when the g-th monitoring node vector X g As the jth monitor node vector X j Parent monitoring node vector of (i.e. X) g →X j Then, the p-value of the least square mutual information method is utilized to calculate X g →X j Support of orientation and is denoted as p-value (X) g ,X j )；
Step 14.4, when the jth monitoring node vector X j As the g-th monitor node vector X g Of parent monitoring node vectors, i.e. X j →X g Then, X is calculated by using the p-value of the least square mutual information method j →X g Support of orientation and is denoted as p-value (X) j ,X g )；
Step 14.5, if p-value (X) g ,X j ) Gamma or p-value (X) j ,X g ) Gamma is less than or equal to gamma, then X is represented g →X j The direction has larger support degree and is oriented as X g →X j ；
If p-value (X) j ,X g ) Gamma or p-value (X) g ,X j ) Gamma is less than or equal to gamma, then X is represented j →X g The direction has larger support degree and is oriented as X j →X g ；
If p-value (X) j ,X g ) Gamma or p-value (X) g ,X j ) Gamma or p-value (X) g ,X j ) Gamma or p-value (X) j ,X g ) If the vector is more than gamma, the causal relationship between the two monitoring node vectors does not exist, and the orientation is not needed;
step 14.6, if the jth monitoring node vector X j Of the relevant monitoring node vector set MB (X) j ) If it is empty, step 15 is executed, otherwise, step 14.2 is returned to.
Compared with the prior art, the invention has the beneficial effects that:
1. aiming at the characteristics that the operation monitoring data distribution of the gas turbine unit is random and the relation between the operation monitoring data distribution and the operation monitoring data distribution is nonlinear, the correlation of the monitoring nodes is researched based on the Hilbert-Schmidt independence criterion, the correlation is a new research, the learning of the monitoring nodes related to the monitoring nodes is realized by combining a local learning strategy, the learning complexity is obviously reduced, and the requirement of real-time monitoring of the state of the gas turbine is met.
2. Aiming at the operation monitoring data of the gas turbine unit, the causal connection among the monitoring nodes is researched, the complexity of a common greedy search method is high, and the timeliness of online learning cannot be met.
3. The invention aims at the dynamic and high-dimensional performance of the operation data of the gas turbine unit, processes the operation data in a streaming mode, and can process the high-dimensional and dynamic operation monitoring data of the gas turbine unit. On the basis of correlation analysis and redundancy check, online update of a related monitoring node set of the monitoring nodes is achieved, real-time orientation is integrated, rapid online adjustment of a local cause and effect structure is achieved, the learning time complexity can be reduced through a flow processing mode, the timeliness requirement of online learning is met, and the method is suitable for high-dimensional dynamic gas turbine unit operation data.
Detailed Description
In this embodiment, a gas turbine fault prediction method based on correlation analysis is applied to a gas turbine system, the operating states of Z monitoring nodes in the gas turbine system are monitored at intervals, a period of time is continuously recorded, and a gas turbine operating data set D consisting of m monitoring value vectors is obtained by assuming that monitoring is performed m times in total, and is marked as D = { sam) = 1 ,sam 2 ,...,sam v ,...,sam m Wherein, sam v Represents a vector of the v-th monitored value, and
representing the monitoring value of the ith monitoring node in the v-th monitoring value vector; v is more than or equal to 1 and less than or equal to m, i is more than or equal to 1 and less than or equal to Z; defining a vector formed by monitoring values of the ith monitoring node under m-time monitoring as X i ，
Represents the ith monitor node vector X i And m values are provided, and m monitoring values exist because m times of monitoring are carried out on the ith monitoring node. The gas turbine fault prediction method aims to find out the relationship among monitoring nodes, find out the monitoring nodes with strong correlation with any monitoring node, and predict the future trend of the monitoring nodes by using a neural network method on the basis of the method, thereby monitoring the running state of the gas turbine and carrying out fault early warning. Specifically, the fault prediction of the gas turbine is carried out according to the following steps:
step 1, defining a time t, and initializing t =0;
defining the limit value of the number Z of the monitoring nodes as max, namely Z is less than or equal to max;
step 2, defining the selected monitoring node vector set as EF, and initializing the selected monitoring node vector set at the t-th moment as
Step 3, defining a variable j, and initializing j =1;
step 4, judging whether the j is less than or equal to Z, if so, reading a jth monitoring node vector X with m values from a gas turbine operation data set D j (ii) a And initializing the jth monitor node vector X j Of the relevant monitoring node vector set MB (X) j ) Initializing jth monitoring node vector X for null j Newly added monitoring node vector set FA (X) j ) Initializing jth monitoring node vector X for null j Redundant monitor node vector set FD (X) j ) Is empty; then step 5 is executed; otherwise, the final causal structure diagram formed by the monitoring nodes is obtained, and the father node and the child nodes of each monitoring node are the monitoring nodes related to the corresponding monitoring nodes, and step 16 is executed;
step 5, judging whether j =1 is true, if so, carrying out the j-th monitoring node vector X j Adding the monitoring node vector set EF selected at the t moment t Thereby obtaining a monitoring node vector set EF selected at the t +1 th moment t+1 (ii) a Assigning t +1 to t, assigning j +1 to j, and returning to the step 4; otherwise, executing step 6;
step 6, for the jth monitoring node vector X j Performing correlation analysis;
step 6.1, setting a correlation threshold value as alpha;
step 6.2, defining a variable w; and initializing w =1; defining a variable theta;
step 6.3, calculating the jth monitoring node vector X by using a Hilbert-Schmidt independence criterion j And w-th monitor node vector X w Degree of correlation HSIC jw ；
Computing the independence criterion HSIC according to equation (1) jw The value of (c):
n is X of the vector j And X w The dimension numbers, H, K, L are all n rows and n columns of matrix, K ij ＝k(x i ,x j )，L ij ＝l(x i ,x j )，K ij And L ij Is a kernel function of the mapping, H = I-n -1 11 T 1 is the full 1 vector of n × 1, and trace is the trace operation of the matrix.
Step 6.4, correlating degree HSIC jw Assigning to theta, judging whether theta is more than or equal to alpha, and if so, indicating a jth monitoring node vector X j And the w-th monitor node vector X w Correlating and executing step 6.5; otherwise, it represents the jth monitoring node vector X j And w-th monitor node vector X w Independent, and step 6.6 is performed;
step 6.5, monitoring the jth node vector X j Vector X added to the w-th monitor node w Of the relevant monitoring node vector set MB (X) w ) In (1), i.e. MB (X) w )＝MB(X w )∪X j The jth monitor node vector X j Adding newly added monitoring node vector set FA (X) w ) In (b), i.e. FA (X) w )＝FA(X w )∪{X j H, thereby updating the w-th monitor node vector X w Of the relevant monitoring node vector set MB (X) w ) And a newly added monitoring node vector set FA (X) w ) (ii) a At the same time, the w-th monitoring node vector X w Vector X added to jth monitor node j Of the relevant monitoring node vector set MB (X) j ) I.e. MB (X) j )＝MB(X j )∪X w The w-th monitor node vector X w Adding newly added monitoring node vector set FA (X) j ) In (1), namely FA (X) j )＝FA(X j )∪{X w H, update the jth monitor node vector X j Of the relevant monitoring node vector set MB (X) j ) And a newly added monitoring node vector set FA (X) j ) (ii) a Then step 6.6 is executed;
6.6, assigning k +1 to k, judging whether k is greater than j-1, and if so, executing step 7; otherwise, the step 6.3 is returned to for execution.
Step 7, judging the jth monitoring node vector X j Relevant monitoring node vector set MB (X) j ) If the set is an empty set, returning to the step 4; otherwise, the jth monitoring node vector X is used j Adding the monitoring node vector set EF selected at the t moment t To obtain a monitoring node vector set EF selected at the t +1 th moment t+1 ＝EF t ∪X j (ii) a Assigning t +1 to t, and executing the step 8;
step 8, defining a variable k, and initializing k =1;
step 9, selecting a monitoring node vector set EF at the t-th moment t Of the kth monitoring node vector X k Performing redundancy check analysis;
step 9.1, setting a redundancy threshold value beta; calculating the kth monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) The number of the monitoring node vectors in (1) is recorded as S k ；
Step 9.2, defining a variable s; and initializing s =1; defining a variable sigma;
step 9.3, obtaining relevant monitoring node vector set MB (X) k ) The vector of the middle s-th monitoring node is marked by the subscript of tau s ；
Step 9.4, calculating the t < th > by using Hilbert-Schmidt independence criterion s Vector of monitoring nodes
And the kth monitoring node vector X k Degree of correlation of
Step 9.5, correlating the degrees
Assigning to sigma, judging whether sigma is less than or equal to beta, if yes, representing the tau s A vector of monitoring nodes
And the kth monitoring node vector X k Irrelevant, namely, the node is a redundant monitoring node, and step 9.6 is executed; otherwise, the tableBright tau s Vector of monitoring nodes
And the kth monitoring node vector X k Correlation and step 9.7 is performed;
step 9.6, from the kth monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) Of deletion s Vector of monitoring nodes
Namely, it is
And will be tau s Vector of monitoring nodes
Adding the kth monitoring node vector X k Redundant monitor node vector set FD (X) k ) In, i.e.
From the th tau s Vector of monitoring nodes
Relevant monitoring node vector set
Middle deletion k-th monitoring node vector X k I.e. by
And the kth monitoring node vector X k Addition of the t s Vector of monitoring nodes
Redundant monitoring node vector set
Namely that
Step 9.7, assigning s +1 to s; and judging S > S k If yes, executing step 10; otherwise, the step 9.3 is returned to for execution.
Step 10, assigning k +1 to k, judging whether k is greater than j, and executing step 11 if k is greater than j; otherwise, returning to the step 9 for execution;
step 11, defining a variable count; and initializing count =0; initializing k =1;
step 12, judging the k monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) Whether the vector set is an empty set or not, if the vector set is the empty set, a monitoring node vector set EF selected from the t-th time t Middle deletion k-th monitoring node vector X k Then, after assigning the count +1 to the count, executing step 13; otherwise, directly executing step 13;
step 13, assigning k +1 to k; judging whether k is more than j, if so, assigning j-count to j, and then obtaining an updated monitoring node vector set EF selected at the t-th moment t ', is marked as EF t ′＝{X′ 1 ,X′ 2 ,...,X′ i ,...X′ j-count }；X′ i Set of monitoring node vectors EF representing the t-th moment of update t The ith monitor node vector in' and, in combination,
representing the ith monitor node vector X' i The nth monitored value; i is more than or equal to 1 and less than or equal to j-count; then j-count is assigned to j, and then step 14 is executed; otherwise, returning to the step 12 for execution;
step 14, for the monitoring node vector set EF selected at the t-th moment t 'j-th monitor node vector X' j Carrying out on-line local orientation to obtain a t-time cause and effect structure diagram;
step 14.1, setting a direction support degree threshold value as gamma;
step 14.2, from the jth monitoring node vector X j Related monitoring sectionPoint vector set MB (X) j ) Optionally a monitoring node vector X g And the g-th monitoring node vector X g Vector set MB (X) from related monitoring nodes i ) Deleting;
step 14.3, when the g-th monitoring node vector X g As the jth monitor node vector X j Of parent monitoring node vectors, i.e. X g →X j Then, X is calculated by using p-value of least square mutual information method g →X j Support of orientation and is denoted as p-value (X) g ,X j ) (ii) a The reason why the support of the direction representation by the p-value of the least square mutual information method is because, for the nonlinear non-gaussian data, the p-value of the least square mutual information method can measure the support of the direction, as in the document "dependent Minimizing Regression with Model Selection for non-Linear road under noise", which is published by Makoto Yamada and Masashi Sugiyama, and the calculation method is described in the above-mentioned paper.
Step 14.4, when the jth monitoring node vector X j As the g-th monitor node vector X g Parent monitoring node vector of (i.e. X) j →X g Then, X is calculated by using the p-value of the least square mutual information method j →X g Support of orientation and is denoted as p-value (X) j ,X g )；
Step 14.5, if p-value (X) g ,X j ) Gamma or p-value (X) j ,X g ) Gamma is less than or equal to gamma, then X is represented g →X j The direction has larger support degree and is oriented as X g →X j ；
If p-value (X) j ,X g ) Gamma or p-value (X) g ,X j ) Gamma is less than or equal to gamma, then X is represented j →X g The direction has larger support degree and is oriented as X j →X g ；
If p-value (X) j ,X g ) Gamma or p-value (X) g ,X j ) Gamma or p-value (X) g ,X j ) Gamma or p-value (X) j ,X g ) If the vector is more than gamma, the causal relationship between the two monitoring node vectors does not exist, and the orientation is not needed;
step 14.6, if the jth monitoring node vector X j Of the relevant monitoring node vector set MB (X) j ) If it is empty, step 15 is executed, otherwise, step 14.2 is returned to.
Step 15, assigning j +1 to j, and returning to the step 4;
step 16, selecting a monitoring node vector of a monitoring node at will, and using the monitoring node vector as the output of the LSTM neural network model, and using the monitoring node vector related to the selected monitoring node as the input of the LSTM neural network model, so as to train the LSTM neural network model, thereby obtaining a fault prediction model;
and step 17, monitoring the operation state of any one monitoring node in real time, obtaining a corresponding gas turbine operation data set, obtaining a predicted value of the monitoring node monitored in real time by using a fault prediction model, comparing the predicted value with a real value of the monitoring node monitored in real time, indicating that the corresponding monitoring node is likely to have faults when the predicted value exceeds a set threshold value, and giving an early warning prompt.
Claims (4)
1. A gas turbine fault prediction method based on correlation analysis is applied to a gas turbine system, and the operation states of Z monitoring nodes in the gas turbine system are monitored at intervals, so that a gas turbine operation data set D consisting of m monitoring value vectors is obtained and is recorded as D = { sam 1 ,sam 2 ,...,sam v ,...,sam m Wherein, sam v Represents a vector of the v-th monitored value, and
representing the monitoring value of the ith monitoring node in the v-th monitoring value vector; v is more than or equal to 1 and less than or equal to m, i is more than or equal to 1 and less than or equal to Z; defining a vector formed by monitoring values of the ith monitoring node under m-time monitoring as X i The method is characterized in that the fault prediction of the gas turbine is carried out according to the following steps:
step 1, defining a time t, and initializing t =0;
defining the limit value of the number Z of the monitoring nodes as max, namely Z is less than or equal to max;
step 2, defining the selected monitoring node vector set as EF, and initializing the selected monitoring node vector set at the t-th moment as
Step 3, defining a variable j, and initializing j =1;
step 4, judging whether the j is less than or equal to Z, if so, reading a jth monitoring node vector X with m values from a gas turbine operation data set D j (ii) a And initializing the jth monitor node vector X j Relevant monitoring node vector set MB (X) j ) Initializing jth monitoring node vector X for null j Newly added monitor node vector set FA (X) j ) Initializing jth monitoring node vector X for null j Redundant monitor node vector set FD (X) j ) Is empty; then step 5 is executed; otherwise, the final causal structure diagram formed by the monitoring nodes is obtained, wherein the father node and the child node of each monitoring node are the monitoring nodes related to the corresponding monitoring node, and step 16 is executed;
step 5, judging whether j =1 is true, if so, determining the jth monitoring node vector X j Adding the selected monitoring node vector set EF at the t moment t Thereby obtaining the selected monitoring node vector set EF at the t +1 th moment t+1 (ii) a Assigning t +1 to t and j +1 to j, and returning to the step 4; otherwise, executing step 6;
step 6, for the jth monitoring node vector X j Performing correlation analysis;
step 7, judging the jth monitoring node vector X j Of the relevant monitoring node vector set MB (X) j ) If the set is an empty set, returning to the step 4; otherwise, the jth monitoring node vector X is used j Adding the monitoring node vector set EF selected at the t moment t FromAnd obtaining a monitoring node vector set EF selected at the t +1 th moment t+1 ＝EF t ∪X j (ii) a Assigning t +1 to t, and executing the step 8;
step 8, defining a variable k, and initializing k =1;
step 9, for the monitoring node vector set EF selected at the t-th moment t Of the kth monitoring node vector X k Performing redundancy check analysis;
step 10, assigning k +1 to k, judging whether k is greater than j, and executing step 11 if k is greater than j; otherwise, returning to the step 9 for execution;
step 11, defining a variable count; and initializing count =0; initializing k =1;
step 12, judging the k-th monitoring node vector X k Relevant monitoring node vector set MB (X) k ) Whether the vector set is an empty set or not, if the vector set is the empty set, selecting a monitoring node vector set EF from the t-th moment t Deleting the k-th monitoring node vector X k Then, after assigning the count +1 to the count, executing step 13; otherwise, directly executing step 13;
step 13, assigning k +1 to k; judging whether k is more than j, if so, assigning j-count to j, and then obtaining an updated monitoring node vector set EF selected at the t-th moment t ', is marked as EF t ′＝{X′ 1 ,X′ 2 ,...,X′ i ,...X′ j-count }；X′ i Set of monitoring node vectors EF representing the updated t-th moment t The ith monitor node vector in' and, in combination,
representing the ith monitor node vector X' i The middle-th monitoring value; i is more than or equal to 1 and less than or equal to j-count; assigning j-count to j, and executing step 14; otherwise, returning to the step 12 for execution;
step 14, for the monitoring node vector set EF selected at the t-th time t 'j-th monitor node vector X' j Carrying out on-line local orientation to obtain a t-time cause and effect structure diagram;
step 15, assigning j +1 to j, and returning to the step 4;
step 16, selecting a monitoring node vector of a monitoring node at will, and using the monitoring node vector as the output of the LSTM neural network model, and using the monitoring node vector related to the selected monitoring node as the input of the LSTM neural network model, so as to train the LSTM neural network model, thereby obtaining a fault prediction model;
and step 17, monitoring the operation state of any monitoring node in real time, obtaining a corresponding gas turbine operation data set, obtaining a predicted value of the monitoring node monitored in real time by using the fault prediction model, comparing the predicted value with a real value of the monitoring node monitored in real time, indicating that the corresponding monitoring node is likely to have a fault when the predicted value exceeds a set threshold value, and giving an early warning prompt.
2. The correlation analysis-based gas turbine engine failure prediction method of claim 1, wherein the step 6 is performed as follows:
step 6.1, setting a correlation threshold value as alpha;
step 6.2, defining a variable w; and initializing w =1; defining a variable theta;
step 6.3, calculating the jth monitoring node vector X by using a Hilbert-Schmidt independence criterion j And w-th monitor node vector X w Degree of correlation HSIC jw ；
Step 6.4, correlating degree HSIC jw Assigning to theta, judging whether theta is more than or equal to alpha, and if so, representing the jth monitoring node vector X j And w-th monitor node vector X w Correlating and executing step 6.5; otherwise, the j monitoring node vector X is represented j And the w-th monitor node vector X w Independently, and perform step 6.6;
step 6.5, monitoring the jth node vector X j Vector X added to the w-th monitor node w In a related monitorVector set MB (X) of measured nodes w ) In (1), i.e. MB (X) w )＝MB(X w )∪X j The jth monitor node vector X j Adding newly added monitoring node vector set FA (X) w ) In (1), namely FA (X) w )＝FA(X w )∪{X j H, thereby updating the w-th monitor node vector X w Of the relevant monitoring node vector set MB (X) w ) And a newly added monitoring node vector set FA (X) w ) (ii) a At the same time, the w-th monitoring node vector X w Vector X added to jth monitor node j Of the relevant monitoring node vector set MB (X) j ) I.e. MB (X) j )＝MB(X j )∪X w The w-th monitor node vector X w Adding newly added monitoring node vector set FA (X) j ) In (1), namely FA (X) j )＝FA(X j )∪{X w H, thereby updating the jth monitor node vector X j Relevant monitoring node vector set MB (X) j ) And a newly added monitoring node vector set FA (X) j ) (ii) a Then step 6.6 is executed;
6.6, assigning k +1 to k, judging whether k is greater than j-1, and if so, executing step 7; otherwise, the step 6.3 is returned to for execution.
3. The correlation analysis-based gas turbine engine failure prediction method of claim 1, wherein the step 9 of on-line redundancy check analysis is performed by the steps of:
step 9.1, setting a redundancy threshold value beta; calculating the kth monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) The number of the monitoring node vectors in (1) is recorded as S k ；
Step 9.2, defining a variable s; and initializing s =1; defining a variable sigma;
step 9.3, obtaining the relevant monitoring node vector set MB (X) k ) The vector of the middle s-th monitoring node is denoted by tau s ；
Step 9.4, calculating the t < th > by using Hilbert-Schmidt independence criterion s Vector of monitoring nodes
And the kth monitoring node vector X k Degree of correlation of
Step 9.5, correlating the degree of correlation
Assigning to sigma, judging whether sigma is less than or equal to beta, if yes, representing the tau s Vector of monitoring nodes
And the kth monitoring node vector X k Irrelevant, namely, the node is a redundant monitoring node, and step 9.6 is executed; otherwise, it indicates the τ th s Vector of monitoring nodes
And the kth monitoring node vector X k Correlation and step 9.7 is performed;
step 9.6, from the k-th monitoring node vector X k Of the relevant monitoring node vector set MB (X) k ) In which the τ th is deleted s A vector of monitoring nodes
Namely that
And will be tau s Vector of monitoring nodes
Adding the kth monitoring node vector X k Redundant monitor node vector set FD (X) k ) In, i.e.
From the th τ s Vector of monitoring nodes
Relevant monitoring node vector set
Deleting the k-th monitoring node vector X k I.e. by
And the kth monitoring node vector X k Adding the τ th s A vector of monitoring nodes
Redundant monitoring node vector set
Namely, it is
Step 9.7, assigning s +1 to s; and judging S > S k If yes, executing step 10; otherwise, the step 9.3 is returned to for execution.
4. The correlation analysis-based gas turbine engine fault prediction method of claim 1, wherein said step 14 is performed by:
step 14.1, setting a direction support degree threshold value as gamma;
step 14.2 from the jth monitor node vector X j Of the relevant monitoring node vector set MB (X) j ) Optionally one monitoring node vector X g And the g-th monitoring node vector X g Vector set MB (X) from related monitoring nodes i ) Deleting;
step 14.3, when the g-th monitoring node vector X g As the jth monitor node vector X j Of parent monitoring node vectors, i.e. X g →X j When usingP-value calculation X of least square mutual information method g →X j Support of orientation and is denoted as p-value (X) g ,X j )；
Step 14.4, when the jth monitoring node vector X j As the g-th monitor node vector X g Of parent monitoring node vectors, i.e. X j →X g Then, X is calculated by using the p-value of the least square mutual information method j →X g Support of orientation and is denoted as p-value (X) j ,X g )；
Step 14.5, if p-value (X) g ,X j ) Gamma or p-value (X) j ,X g ) Gamma is less than or equal to gamma, then X is represented g →X j The direction has larger support degree and is oriented as X g →X j ；
If p-value (X) j ,X g ) Gamma or p-value (X) g ,X j ) Gamma is less than or equal to gamma, then X is represented j →X g The direction has larger support degree and is oriented as X j →X g ；
If p-value (X) j ,X g ) Gamma or p-value (X) g ,X j ) Gamma or p-value (X) g ,X j ) Gamma or p-value (X) j ,X g ) If the value is more than gamma, no causal relationship exists between the two monitoring node vectors, and no orientation is needed;
step 14.6, if the jth monitoring node vector X j Of the relevant monitoring node vector set MB (X) j ) If it is empty, step 15 is executed, otherwise, step 14.2 is returned to.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010404291.6A CN111598220B (en) | 2020-05-13 | 2020-05-13 | Gas turbine fault prediction method based on correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010404291.6A CN111598220B (en) | 2020-05-13 | 2020-05-13 | Gas turbine fault prediction method based on correlation analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598220A CN111598220A (en) | 2020-08-28 |
| CN111598220B true CN111598220B (en) | 2023-03-14 |
Family
ID=72185425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010404291.6A Active CN111598220B (en) | 2020-05-13 | 2020-05-13 | Gas turbine fault prediction method based on correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598220B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011043108A1 (en) * | 2009-10-09 | 2011-04-14 | 株式会社日立製作所 | Equipment status monitoring method, monitoring system, and monitoring program |
| CN109061341A (en) * | 2018-07-10 | 2018-12-21 | 杭州安脉盛智能技术有限公司 | Kalman filtering transformer fault prediction technique and system neural network based |
-
2020
- 2020-05-13 CN CN202010404291.6A patent/CN111598220B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011043108A1 (en) * | 2009-10-09 | 2011-04-14 | 株式会社日立製作所 | Equipment status monitoring method, monitoring system, and monitoring program |
| CN109061341A (en) * | 2018-07-10 | 2018-12-21 | 杭州安脉盛智能技术有限公司 | Kalman filtering transformer fault prediction technique and system neural network based |
Non-Patent Citations (1)
| Title |
|---|
| 基于SVM-BN的天然气长输管道燃气轮机故障预警方法研究;王明达等;《天然气工业》;20171125(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598220A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | A data-driven approach for remaining useful life prediction of aircraft engines | |
| Peng et al. | A prognosis method using age-dependent hidden semi-Markov model for equipment health prediction | |
| CN111274737A (en) | Method and system for predicting remaining service life of mechanical equipment | |
| CN110807257A (en) | Method for predicting residual life of aircraft engine | |
| CN111325403B (en) | Method for predicting residual life of electromechanical equipment of highway tunnel | |
| CN112785091B (en) | Method for carrying out fault prediction and health management on oil field electric submersible pump | |
| CN111340282B (en) | DA-TCN-based method and system for estimating residual service life of equipment | |
| CN113642754B (en) | Complex industrial process fault prediction method based on RF noise reduction self-coding information reconstruction and time convolution network | |
| Liu et al. | Complex engineered system health indexes extraction using low frequency raw time-series data based on deep learning methods | |
| Xu et al. | Global attention mechanism based deep learning for remaining useful life prediction of aero-engine | |
| CN111400850B (en) | Equipment fault analysis method, device, equipment and storage medium | |
| CN111122811A (en) | Sewage treatment process fault monitoring method of OICA and RNN fusion model | |
| CN111241629B (en) | Intelligent prediction method for performance change trend of hydraulic pump of airplane based on data driving | |
| CN117521512A (en) | Bearing residual service life prediction method based on multi-scale Bayesian convolution transducer model | |
| CN118188342A (en) | Fan-oriented fault early warning and life prediction method | |
| CN111931420B (en) | Gas turbine fault prediction method based on nuclear regeneration Hilbert space | |
| Chen et al. | Reliability analysis using deep learning | |
| CN112560252A (en) | Prediction method for residual life of aircraft engine | |
| CN111598220B (en) | Gas turbine fault prediction method based on correlation analysis | |
| CN114154266B (en) | Gas turbine fault prediction method based on bias rank correlation flow causal structure learning | |
| CN114818116B (en) | Aircraft engine failure mode identification and life prediction method based on joint learning | |
| CN114386603B (en) | Thermal power plant generator fault early warning method based on time sequence causal network | |
| CN114548701B (en) | Full-measurement-point-oriented coupling structure analysis and estimation process early warning method and system | |
| Chen et al. | Multi-granularity Cross-Domain Temporal Regression Network for Remaining Useful Life Estimation of Aero Engines | |
| He et al. | Abnormal data detection and recovery of sensors network based on spatiotemporal deep learning methodology |
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 |