CN114547942B - Shafting state monitoring and evaluating method based on CAS analysis and neural network - Google Patents
Shafting state monitoring and evaluating method based on CAS analysis and neural network Download PDFInfo
- Publication number
- CN114547942B CN114547942B CN202210194009.5A CN202210194009A CN114547942B CN 114547942 B CN114547942 B CN 114547942B CN 202210194009 A CN202210194009 A CN 202210194009A CN 114547942 B CN114547942 B CN 114547942B
- Authority
- CN
- China
- Prior art keywords
- shafting
- state
- data
- monitoring
- neural network
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 50
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 41
- 238000004458 analytical method Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 43
- 238000012360 testing method Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000006073 displacement reaction Methods 0.000 claims description 12
- 238000010219 correlation analysis Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 claims description 7
- 230000036541 health Effects 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000010206 sensitivity analysis Methods 0.000 claims description 5
- 238000009434 installation Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 238000011549 displacement method Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000008439 repair process Effects 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000011160 research Methods 0.000 description 4
- 238000005299 abrasion Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The application belongs to the technical field of ship state monitoring and evaluating methods, and particularly relates to a shafting state monitoring and evaluating method based on CAS analysis and a neural network. The method comprises the following steps: constructing a model to determine measuring points, determining a test scheme, determining a rated operation working condition point of a shafting, constructing and training a neural network aiming at various data measuring points and processed historical data, and checking the correctness of the neural network; and collecting test data under different working conditions, and monitoring and evaluating the state of the shafting according to the state evaluation membership value under each test working condition. The shafting state monitoring and evaluating method based on CAS analysis and the neural network can improve the arrangement efficiency of measuring points, reduce the dimension and complexity of analysis data and improve the representativeness of characteristic data on the basis of the existing monitoring, so that the evaluation result has higher accuracy and reliability on the basis of the method, and is beneficial to improving the efficiency of monitoring and evaluating the shafting state of the ship.
Description
Technical Field
The application belongs to the technical field of ship state monitoring and evaluating methods, and particularly relates to a shafting state monitoring and evaluating method based on CAS analysis and a neural network.
Background
The shafting is used as an important component of a ship power device, the main function of the shafting is to transmit power generated by a host to a propeller so as to further drive the ship to move, and as an important energy transmission device, the reliability and safety of the shafting operation are the precondition of ensuring that the ship completes various tasks and missions, and at present, the problems of abnormal abrasion and the like of a stern bearing of the propeller shafting still exist in a certain ship developed in China, so that the causes of the problems are mainly dependent on the dynamic state in the operation stage of the shafting.
Because the shafting has the characteristics of long arrangement span, high rotating speed, complex stress and the like, the shafting is easy to be influenced by various factors in operation, such as: the research on the ship shafting mainly focuses on shafting vibration and centering characteristic analysis at present on unsteady exciting force, hull deformation, bearing oil film rigidity, temperature and the like of the propeller in an uneven wake field, the monitoring and evaluation research on the shafting state is less, the monitoring and evaluation research on the shafting operation state at present is only monitoring on certain operation parameters of the shafting, but whether the data can reflect the shafting state scientifically, reasonably and efficiently and how to improve the utilization rate of the data is yet to be further verified and researched.
Disclosure of Invention
The application aims to provide a shafting state monitoring and evaluating method based on CAS analysis and a neural network, which processes shafting load displacement signals by combining simulation calculation, parameter correlation analysis, sensitivity analysis, BP neural network data analysis and membership theory, screens out independent measuring points and state parameters with characteristic representativeness, so as to realize higher efficiency acquisition and analysis of the change rule of shafting dynamic characteristic states along with each characteristic parameter under different states, and improve the accuracy of ship shafting dynamic state monitoring and evaluating results.
In order to achieve the above purpose, the present application adopts the following technical scheme.
A shafting state monitoring and evaluating method based on CAS analysis and neural network comprises the following steps:
step one, constructing a model to determine measuring points
According to the shafting structure, constructing a shafting finite element simulation calculation model, acquiring the shafting overall deformation state and the load state thereof, and determining all measurement points x 1、x2...xn of the shafting except the bearing position, and measuring point y 1、y2...ym of the bearing position;
Step two, determining a test scheme
Measuring the bearing load of the measuring point y 1、y2...ym based on a resistance strain gauge method; measuring shafting three-way amplitude values at measuring points x 1、x2...xp (p < n) with gyratory vibration and longitudinal vibration based on a three-way photoelectric displacement sensor; measuring the torsion angle of the shafting cross section of the measuring point x p+1、xp+2...xn with torsional vibration based on a pulse time sequence method;
Thirdly, selecting different operation working condition points of the shafting, acquiring monitoring data of a plurality of groups of shafting in normal operation and fault operation under each operation working condition as historical data, and respectively performing expert scoring on the shafting operation state reflected by each group of monitoring data to acquire the health evaluation membership degree corresponding to each group of data;
Step four, carrying out normalization processing on the obtained historical data according to the class, wherein a normalization formula is as follows: Wherein z i is the same type of monitored value; z i-norm is this type of normalized data; z min is the minimum value in this type of monitored data; z max is the maximum value in this type of monitored data;
step five, aiming at various data measuring points and processed historical data, carrying out correlation analysis on the data by adopting a Pearson correlation coefficient, selecting independent and representative measuring point data, and further combining sensitivity analysis to determine the contribution value of each measuring point data to the state membership;
Taking the extracted monitoring data as characteristic data, taking the data under each working condition as a group, respectively corresponding to a neural network, taking the three evaluation membership values under the corresponding working conditions as output variables, performing network model training by adopting a BP neural network with error back propagation, and performing simulation verification on the trained neural network;
And step seven, collecting test data under different working conditions, taking the data under each working condition as a group, preprocessing and normalizing each group of data, taking the data as a trained neural network input variable, outputting a state evaluation membership value under each test working condition, and monitoring and evaluating the state of the shafting according to the state evaluation membership value under each test working condition.
In the third step, the membership degree at least comprises three types of normal state values, potential failure state values and fault state values.
The method for monitoring and evaluating the state of the shafting based on the CAS analysis and the neural network according to claim 2, wherein in the seventh step, the monitoring and evaluating the state of the shafting according to the state evaluation membership value under each test working condition specifically means:
when the evaluation membership degree of the shafting fault state is greater than 0, the shafting is evaluated as the fault state;
When the membership degree of the shafting fault state is 0 and the evaluation membership degree of the shafting potential fault state is 0.65-1, the shafting is evaluated as a fault rapid development state;
When the membership degree of the shafting fault state is 0 and the evaluation membership degree of the shafting potential fault state is 0.25-0.65, the shafting is evaluated as a possible fault state;
And when the membership degree of the shafting fault state is 0 and the evaluation membership degree of the shafting potential fault state is 0-0.25, the shafting is evaluated as a normal running state.
In the further improvement or preferred implementation of the above-mentioned shafting state monitoring and evaluating method based on CAS analysis and neural network, in the specific execution monitoring process, when the shafting fault state evaluation membership is greater than 0, the shafting state should be stopped immediately to repair the fault; the membership degree of the shafting fault state is 0, and when the evaluation membership degree of the shafting potential fault state is 0.65-1, the fault generation cause should be checked; the membership degree of the shafting fault state is 0, and fault monitoring is carried out when the evaluation membership degree of the shafting potential fault state is 0.25-0.65; the membership degree of the shafting fault state is 0, and when the evaluation membership degree of the shafting potential fault state is 0-0.25, no treatment is performed.
Further improvement or preferred implementation of the above shafting state monitoring and evaluating method based on CAS analysis and neural network is that each measuring point of the shafting is obtained by the following steps:
a1, based on a shafting design and installation drawing, a bidirectional spring supporting unit is used for replacing each supporting bearing of a shafting, and a shafting finite element analysis model is constructed;
a2, calculating propeller hydrodynamic force under the working condition based on hydrodynamic analysis, and simulating propeller exciting force borne by the shafting under the working condition;
a3, carrying out first-order cyclotron vibration modal analysis and statics analysis on the shafting on the basis of determining the shafting stress state and constraint conditions;
a4, selecting the position with obvious deformation displacement and the point nearby the position as each measuring point of the shafting based on the integral deformation state of the shafting.
In the second step, a measuring point dynamic displacement method is adopted for the axis system cyclotron vibration state parameter; the method specifically comprises the steps of monitoring vertical displacement variation and transverse displacement variation of each measuring point of a shafting by adopting a displacement sensor, and acquiring a plurality of groups of data to be measured under a certain specific rotating speed working condition of the shafting.
The beneficial effects are that:
The shafting state monitoring and evaluating method based on the CAS analysis and the neural network can improve the arrangement efficiency of measuring points on the basis of the existing monitoring, reduce the dimension and complexity of analysis data, improve the representativeness of characteristic data, enable the evaluation result to be more scientific and reasonable based on the method, have higher accuracy and reliability, improve the efficiency of monitoring and evaluating the shafting state of the ship, and provide scientific basis and auxiliary decision for the condition maintenance of shafting.
Drawings
FIG. 1 is a schematic flow chart of a method for monitoring and evaluating shafting states based on CAS analysis and neural network;
FIG. 2 is a pressure cloud of a propeller;
FIG. 3 is a shafting wake velocity diagram;
FIG. 4 is a schematic diagram of shafting dynamics simulation and measuring point arrangement;
FIG. 5 is a graph of a neural network linear regression analysis;
Detailed Description
The invention is described in detail below with reference to specific steps and examples.
Referring to fig. 1, a specific flow chart of the method of the present invention is shown, and a specific implementation process of the present invention is described in detail below with respect to a shafting stern bearing wear degree state evaluation under a certain working condition by taking a certain ship shafting as a research object.
Firstly, a shafting finite element analysis model is constructed by replacing each support bearing of a shafting by a bidirectional spring support unit based on a shafting design and installation drawing, propeller hydrodynamic force under the working condition is calculated based on a hydrodynamic analysis module so as to simulate propeller excitation force borne by the shafting under the working condition, as shown in fig. 2 and 3, a propeller pressure cloud chart and a wake velocity chart are shown, and on the basis of determining a shafting stress state and a constraint condition, as the abrasion of a stern bearing mainly influences the whirling vibration greatly and the shafting is mainly influenced by low-frequency vibration, first-order whirling vibration modal analysis and statics analysis are mainly considered for the shafting, and finally, each measuring point x 1、x2...x8 of the shafting is preliminarily determined based on the shafting integral deformation state, as shown in fig. 4.
The method is based on the evaluation of the rotating vibration state of the shafting, the measuring method selects a measuring point dynamic displacement method, the installation of a displacement sensor is used for monitoring the vertical and transverse displacement changes of each measuring point of the shafting, and a plurality of groups of data to be measured under a certain rotating speed working condition of the shafting are obtained.
The historical data of the shafting under the working condition is obtained as an analysis object, expert judgment is carried out on each group of data under the working condition based on an expert judgment system, the health evaluation membership degree of each group of data is determined through an expert scoring method, normalization processing is carried out on the data for accelerating the learning speed of the BP neural network and reducing the influence of singular values among different types of data, and each group can be divided into four types according to expert judgment results after the processing: fault status, rapid development period of fault, "sick" and normal status.
To reduce the dimensionality of the analyzed data, to improve the representativeness of the data and the accuracy of the evaluation result, CAS data analysis (correlation analysis and sensitivity analysis) is performed on the obtained data,
A Spearman correlation coefficient method is selected to respectively conduct parameter correlation analysis on each group of monitoring data, and correlation coefficients among various data are obtained;
the relevant visual data are shown in tables 1, 2 and 3
TABLE 1 correlation results at measurement points 1 to 8
TABLE 2 correlation results for measurement points 1 to 8
| Measuring point 6 vertical | 0.98 | -0.24 |
| Measuring point 6 is transverse | 0.25 | -0.99 |
| Measuring point 5 vertical | Measuring point 5 is transverse |
TABLE 3 correlation results for measurement points 1 to 8
| Measuring point 8 vertical | -0.98 | -0.08 |
| Measuring point 8 is transverse | 0.15 | 1 |
| Measuring point 7 vertical | Measuring point 7 is transverse |
As shown in the table, for the vertical data, the vertical data of the measuring point x 1 has strong positive correlation with the vertical monitoring data of the measuring point x 2、x3、x4, has correlation with x 5、x6, but has relatively weak correlation with x 7、x8, has no obvious correlation with x 7、x8, further carries out correlation analysis on the measuring point x 5、x6 and the x 7、x8, and can obtain the vertical data of the measuring point x 5 and the x 6 to have strong positive correlation, the vertical data of the measuring point x 7 and the x 8 has strong negative correlation, therefore, the vertical data at the measuring points x 1、x5 and the x 7 are selected as characteristic data, for the transverse data, the transverse data of the measuring point x 1 and the x 2、x3 have obvious positive correlation, the transverse data of the measuring point x 4、 x5 has stronger correlation, and the transverse data of the measuring point x 6、x7、x8 have obvious negative correlation, the transverse data of the measuring point x 4、x5 are selected as characteristic data, the sensitivity of each group of data is further combined with a state evaluation membership value, the sensitivity of each group of data is analyzed, the weight value of each parameter on the change of the state is obtained, the state value of a shafting is mainly influenced by the vibration value of the measuring points x 1、x2、x3、 x4 and x 5 and is not greatly influenced by other points, so that the transverse data and the vertical data of the measuring point x 1, the transverse data of the measuring point x 4 and the vertical data of the measuring point x 5 are finally selected as characteristic monitoring data based on the analysis, the characteristic monitoring data are used as input variables of a neural network, and the health evaluation membership corresponding to each group is used as output variables to construct and train the BP neural network; neural networks used for training are divided into three layers: the system comprises an input layer, an hidden layer and an output layer, wherein the number of nodes of the input layer is 4, the number of neurons of the hidden layer is 10, the number of nodes of the output layer is 3, each node of the input layer corresponds to each group of characteristic monitoring data, and each node of the output layer corresponds to a shafting normal state value, a potential fault state value and a fault state value. The trained neural network can be known through regression analysis, and the data regression values for training, verifying and testing are respectively as follows: the regression value of the total input data is R all = 0.97983, so that the network has higher network accuracy, as shown in fig. 5, the graph reflects that the neural network randomly selects training data, verification data and test data according to the proportions of 70%, 15% and 15%, the regression value R reflects the correlation between the measured output and the target, and the closer the R value is to 1, the better the correlation is, namely the better the trained neural network performance, and the regression values of the training data, the verification data, the test data and the total input data are reflected.
In order to further verify the feasibility of the method, firstly, a health state evaluation value is given to a plurality of groups of data to be tested under the working condition, which are acquired before, based on an expert evaluation system, further based on the neural network, the plurality of groups of data to be tested under the working condition are input into the neural network as input variables for intelligent evaluation after being preprocessed, the evaluation results are shown in a table 4,
Table 4 expert judgment and neural network output result and error comparison analysis table
According to result analysis, the error between the neural network output result and the expert judgment result is in the level of 10 -2 and can be ignored, so that the neural network output result is basically consistent with the expert judgment result, and the accuracy and the reliability of the method are verified.
The invention improves the defects in the aspects of monitoring and evaluating the current shafting state, provides a measuring point selection method based on the simulation model state, reduces the blindness of measuring point selection, reduces the workload, provides a CAS analysis method combining parameter correlation analysis and sensitivity analysis, further reduces the dimension of analyzed data, improves the representativeness of the data, combines an expert evaluation system, can reflect the importance degree of a decision maker on different attributes while considering the objectivity of the data, and further combines the fitting prediction analysis capability of a neural network on multidimensional nonlinear data, thereby providing a ship shafting state evaluation method.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present application, and not for limiting the scope of the present application, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made to the technical solution of the present application without departing from the spirit and scope of the technical solution of the present application.
Claims (4)
1. The shafting state monitoring and evaluating method based on CAS analysis and neural network is characterized by comprising the following steps:
step one, constructing a model to determine measuring points
According to the shafting structure, constructing a shafting finite element simulation calculation model, acquiring the shafting overall deformation state and the load state thereof, and determining all measurement points x 1、x2...xn of the shafting except the bearing position, and measuring point y 1、y2...ym of the bearing position;
Step two, determining a test scheme
Measuring the bearing load of the measuring point y 1、y2...ym based on a resistance strain gauge method; measuring shafting three-way amplitude values at measuring points x 1、x2...xp (p < n) with rotary vibration and longitudinal vibration based on a three-way photoelectric displacement sensor; measuring the torsion angle of the shafting cross section of the measuring point x p+1、xp+2...xn with torsional vibration based on a pulse time sequence method;
Thirdly, selecting different operation working condition points of the shafting, acquiring monitoring data of a plurality of groups of shafting in normal operation and fault operation under each operation working condition as historical data, and respectively performing expert scoring on the shafting operation state reflected by each group of monitoring data to acquire the health evaluation membership degree corresponding to each group of data;
step four, carrying out normalization processing on the obtained historical data according to the class, wherein a normalization formula is as follows: Wherein z i is the same type of monitored value; z i-norm is this type of normalized data; z min is the minimum value in this type of monitored data; z max is the maximum value in this type of monitored data;
step five, aiming at various data measuring points and processed historical data, carrying out correlation analysis on the data by adopting a Pearson correlation coefficient, selecting independent and representative measuring point data, and further combining sensitivity analysis to determine the contribution value of each measuring point data to the state membership;
Taking the extracted monitoring data as characteristic data, taking the data under each working condition as a group, respectively corresponding to a neural network, taking three evaluation membership values under the corresponding working conditions as output variables, performing network model training by adopting a BP neural network with error back propagation, and performing simulation verification on the trained neural network;
Step seven, collecting test data under different working conditions, taking the data under each working condition as a group, preprocessing and normalizing each group of data, taking the data as a trained neural network input variable, outputting a state evaluation membership value under each test working condition, and monitoring and evaluating the state of a shafting according to the state evaluation membership value under each test working condition;
each measuring point of the shafting is obtained by the following steps:
A1, based on a shafting design and installation drawing, a bidirectional spring supporting unit is used for replacing each supporting bearing of a shafting, and a shafting finite element analysis model is constructed;
A2, calculating propeller hydrodynamic force under the working condition based on hydrodynamic analysis, and simulating propeller exciting force borne by the shafting under the working condition;
a3, carrying out first-order cyclotron vibration modal analysis and statics analysis on the shafting on the basis of determining the shafting stress state and constraint conditions;
a4, selecting the position with obvious deformation displacement and the point positions nearby the position as each measuring point of the shafting based on the integral deformation state of the shafting;
In the second step, a measuring point dynamic displacement method is adopted for the rotating vibration state parameter of the shaft system; the method specifically comprises the steps of monitoring vertical and transverse displacement changes of each measuring point of a shafting by adopting a displacement sensor, and acquiring a plurality of groups of data to be measured under a certain rotating speed working condition of the shafting.
2. The method for monitoring and evaluating the shafting state based on the CAS analysis and the neural network according to claim 1, wherein in the third step, the membership degree at least comprises three types of normal state values, potential fault state values and fault state values.
3. The method for monitoring and evaluating the state of the shafting based on the CAS analysis and the neural network according to claim 2, wherein in the seventh step, the monitoring and evaluating the state of the shafting according to the state evaluation membership value under each test condition specifically means:
when the evaluation membership degree of the shafting fault state is greater than 0, the shafting is evaluated as the fault state;
When the membership degree of the shafting fault state is 0 and the evaluation membership degree of the shafting potential fault state is 0.65-1, the shafting is evaluated as a fault rapid development state;
when the membership degree of the shafting fault state is 0 and the evaluation membership degree of the shafting potential fault state is 0.25-0.65, the shafting is evaluated as a possible fault state;
and when the membership degree of the shafting fault state is 0 and the evaluation membership degree of the shafting potential fault state is 0-0.25, the shafting is evaluated as a normal running state.
4. The method for monitoring and evaluating the shafting state based on the CAS analysis and the neural network according to claim 3, wherein in the specific implementation of the monitoring, when the shafting fault state evaluation membership is greater than 0, the machine should be stopped immediately to repair the fault; the membership degree of the shafting fault state is 0, and when the evaluation membership degree of the shafting potential fault state is 0.65-1, the fault generation cause should be checked; the membership degree of the shafting fault state is 0, and fault monitoring is carried out when the evaluation membership degree of the shafting potential fault state is 0.25-0.65; the membership degree of the shafting fault state is 0, and when the evaluation membership degree of the shafting potential fault state is 0-0.25, no treatment is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194009.5A CN114547942B (en) | 2022-03-01 | 2022-03-01 | Shafting state monitoring and evaluating method based on CAS analysis and neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210194009.5A CN114547942B (en) | 2022-03-01 | 2022-03-01 | Shafting state monitoring and evaluating method based on CAS analysis and neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114547942A CN114547942A (en) | 2022-05-27 |
| CN114547942B true CN114547942B (en) | 2024-04-30 |
Family
ID=81661161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210194009.5A Active CN114547942B (en) | 2022-03-01 | 2022-03-01 | Shafting state monitoring and evaluating method based on CAS analysis and neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114547942B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038300A (en) * | 2017-12-07 | 2018-05-15 | 长春理工大学 | Optical fiber state evaluating method based on improved membership function combination neutral net |
| CN110543140A (en) * | 2019-07-26 | 2019-12-06 | 四川大学 | time characteristic-based numerical control machine tool spindle system thermal key point selection modeling method |
| CN112192319A (en) * | 2020-09-28 | 2021-01-08 | 上海交通大学 | Tool wear monitoring method and system of unsupervised model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239694B (en) * | 2014-08-28 | 2016-11-23 | 北京交通大学 | The failure predication of a kind of municipal rail train bogie and condition maintenarnce method |
-
2022
- 2022-03-01 CN CN202210194009.5A patent/CN114547942B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038300A (en) * | 2017-12-07 | 2018-05-15 | 长春理工大学 | Optical fiber state evaluating method based on improved membership function combination neutral net |
| CN110543140A (en) * | 2019-07-26 | 2019-12-06 | 四川大学 | time characteristic-based numerical control machine tool spindle system thermal key point selection modeling method |
| CN112192319A (en) * | 2020-09-28 | 2021-01-08 | 上海交通大学 | Tool wear monitoring method and system of unsupervised model |
Non-Patent Citations (1)
| Title |
|---|
| 基于PCA-NAR神经网络的风电机组健康趋势评估;邢幼圣 等;电气自动化;20200130(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114547942A (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108171263B (en) | Based on the Fault Diagnosis of Roller Bearings for improving variation mode decomposition and extreme learning machine | |
| CN107016235B (en) | Equipment running state health degree evaluation method based on multi-feature adaptive fusion | |
| CN102520697B (en) | Onsite information preprocessing method of remote cooperative diagnosis | |
| CN110823576B (en) | Mechanical anomaly detection method based on generation of countermeasure network | |
| CN101872165A (en) | Method for fault diagnosis of wind turbines on basis of genetic neural network | |
| CN109858104A (en) | A kind of rolling bearing health evaluating and method for diagnosing faults and monitoring system | |
| CN111922095A (en) | Vibration diagnosis method for abnormal torsional vibration fault of roller of cold rolling mill | |
| CN110131109A (en) | A kind of pneumatic equipment bladess unbalance detection based on convolutional neural networks | |
| KR102321607B1 (en) | Rotating machine fault detecting apparatus and method | |
| CN113188794A (en) | Gearbox fault diagnosis method and device based on improved PSO-BP neural network | |
| CN112729834B (en) | Bearing fault diagnosis method, device and system | |
| CN110046409A (en) | A kind of components of steam turbine health state evaluation method based on ResNet | |
| Chen et al. | Rotor fault diagnosis system based on sGA-based individual neural networks | |
| CN112711850A (en) | Unit online monitoring method based on big data | |
| Xing et al. | Detection of magnitude and position of rotor aerodynamic imbalance of wind turbines using Convolutional Neural Network | |
| CN113187674A (en) | Fault determination method and system for wind turbine generator pitch system | |
| CN114169718A (en) | Method for improving reliability of wind turbine generator based on state evaluation of wind turbine generator | |
| CN114547942B (en) | Shafting state monitoring and evaluating method based on CAS analysis and neural network | |
| CN207066742U (en) | A kind of automobile speed variator bearing testing stand | |
| CN117232809A (en) | Fan main shaft fault pre-diagnosis method based on DEMATEL-ANP-CRITIC combined weighting | |
| CN116499742A (en) | Rotary machine fault monitoring method based on ensemble learning | |
| CN111368379B (en) | Rolling bearing reliability evaluation method and system for improving HWPSO-WPHM model | |
| CN113987870A (en) | State evaluation method for main transmission system of wind turbine generator and terminal equipment | |
| Shen et al. | Quantitative Detection of Blade Crack Damage Based on Vibro-Acoustic Information and Multi-Dimensional Feature Fusion CNN | |
| CN118036479B (en) | Transmission stability analysis method and system for planetary gear reduction device |
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 |