Disclosure of Invention
The embodiment of the application provides a fault diagnosis method and a fault diagnosis device for a gearbox, which are used for diagnosing faults.
A method of fault diagnosis of a gear box comprising:
acquiring first working condition data and first historical data in a preset time period before a fault early warning moment, wherein the first working condition data are time sequence data of a power input side and a load output side in the preset time period, and the first historical data are time domain data of operation parameters of bearings, shafting and groups of meshing gears of a gear transmission;
performing transformation between a time domain and a frequency domain on the first historical data to obtain first frequency domain data;
calculating a first change rate of the operating parameters of each bearing, each shafting and each group of meshing gears and a first statistical characteristic value of the operating parameters of each bearing, each shafting and each group of meshing gears based on the first frequency domain data;
classifying first input data through a clustering model to obtain early warning sample data, wherein the first input data comprise the first working condition data, the first change rate and the first statistical characteristic value;
establishing an early warning sample matrix through the early warning sample data, wherein a row vector of the early warning sample matrix comprises the first statistical characteristic value and the first change rate;
calculating a state feature vector of the early warning sample matrix;
calculating a plurality of similarity values between the state feature vector and a plurality of candidate feature vectors, each candidate feature vector characterizing a failure mode;
and determining a target fault mode corresponding to the state feature vector according to the maximum similarity value, wherein the maximum similarity value is the maximum value of the similarity values, and the target fault mode is a fault mode corresponding to the candidate feature vector with the maximum similarity value.
Optionally, before the first operating condition data and the first historical data within a preset time period before the fault early warning time are obtained, the method further includes:
acquiring sensor data, wherein the sensor data are data representing historical faults and comprise second working condition data and second historical data, the second working condition data comprise time sequence data of power input side operation parameters and time sequence data of load output side operation parameters, and the second historical data are second time domain data representing a plurality of faults of the gearbox;
converting the second time domain data into second frequency domain data;
calculating a second change rate of the operating parameters of the bearings, the shafting and the sets of meshing gears and a second statistical characteristic value of the operating parameters of the bearings, the shafting and the sets of meshing gears based on the second frequency domain data;
carrying out fault mode classification on second input data through a clustering model to obtain sample data of each fault set, wherein the second input data comprise the second working condition data, the second change rate and the second statistical characteristic value;
establishing a plurality of fault sample matrixes of a plurality of fault modes through sample data of each fault set, wherein a row vector of each fault sample matrix comprises a second statistical characteristic value and a second change rate corresponding to each fault mode;
a plurality of candidate feature vectors for the plurality of fault sample matrices are calculated.
Optionally, after the acquiring the sensor data and before the converting the second time domain data into the second frequency domain data, the method further includes:
removing abnormal values from the second working condition data to obtain third working condition data;
performing fault mode classification on second input data through a clustering model to obtain sample data of each fault set, where the second input data includes the second operating condition data, the second change rate, and the second statistical characteristic value and includes:
and carrying out fault mode classification on second input data through a clustering model to obtain sample data of each fault set, wherein the second input data comprise the third working condition data, the second change rate and the second statistical characteristic value.
Optionally, the transforming the first historical data between the time domain and the frequency domain to obtain first frequency domain data includes:
performing fast Fourier transform on the first historical data to obtain first frequency domain data;
or the like, or, alternatively,
and performing discrete Fourier transform on the first historical data to obtain first frequency domain data.
Optionally, calculating the first change rate of the operating parameters of each bearing, each shaft system and each group of meshing gears and the first statistical characteristic value of the operating parameters of each bearing, each shaft system and each group of meshing gears based on the first frequency domain data includes:
and respectively calculating the first change rate and the first statistical characteristic value of six of the inner ring passing frequency, the outer ring passing frequency, the ball rotation frequency, the retainer passing frequency, the shafting rotation frequency and the gear meshing frequency of a bearing of the gearbox based on the first frequency domain data.
Optionally, the failure modes include wear of inner rings of bearings, wear of outer rings of bearings, wear of bearing retainers, wear of bearing balls, poor meshing of gears, poor centering of a shafting, looseness of bearings, looseness of a base or unbalance of mass of the shafting.
Optionally, calculating a plurality of similarity values between the state feature vector and a plurality of candidate feature vectors includes:
calculating similarity values between the candidate feature vectors and the state feature vector by a Euclidean distance method, a Manhattan distance method or a cosine distance method.
A fault diagnosis apparatus comprising:
the system comprises an acquisition unit, a fault early warning unit and a fault early warning unit, wherein the acquisition unit is used for acquiring first working condition data and first historical data in a preset time period before a fault early warning moment, the first working condition data are time sequence data of a power input side and a load output side in the preset time period, and the first historical data are time domain data of operation parameters of bearings, shafting and meshing gears of a gearbox;
the transformation unit is used for carrying out transformation between a time domain and a frequency domain on the first historical data to obtain first frequency domain data;
the calculating unit is used for calculating a first change rate of the operating parameters of the bearings, the shafting and the sets of meshing gears and a first statistical characteristic value of the operating parameters of the bearings, the shafting and the sets of meshing gears based on the first frequency domain data;
the classification unit is used for classifying first input data through a clustering model to obtain early warning sample data, wherein the first input data comprises the first working condition data, the first change rate and the first statistical characteristic value;
the establishing unit is used for establishing an early warning sample matrix through the early warning sample data, and a row vector of the early warning sample matrix comprises the first statistical characteristic value and the first change rate;
the calculation unit is further configured to calculate a state feature vector of the early warning sample matrix;
the computing unit is further configured to compute a plurality of similarity values between the state feature vector and a plurality of candidate feature vectors, each candidate feature vector characterizing a failure mode;
and the determining unit is used for determining a target fault mode corresponding to the state feature vector according to a maximum similarity value, wherein the maximum similarity value is the maximum value of a plurality of similarity values, and the target fault mode is a fault mode corresponding to a candidate feature vector of the maximum similarity value.
A fault diagnosis apparatus comprising:
the system comprises a central processing unit, a memory and an input/output interface;
the memory is a transient memory or a persistent memory;
the central processor is configured to communicate with the memory and execute the instruction operations in the memory to perform the aforementioned methods.
A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the aforementioned method.
According to the technical scheme, the embodiment of the application has the following advantages:
after the first historical data are obtained, the first historical data are transformed to obtain first frequency domain data, and a first change rate and a first statistical characteristic value are calculated. And then establishing an early warning sample matrix by using the first change rate and the first statistical eigenvalue, and then calculating the geometric center of the high-dimensional matrix to obtain a state eigenvector. And comparing the similarity degrees of the candidate characteristic vectors and the state characteristic vectors, and calculating the similarity value to obtain the maximum similarity value so as to determine a target fault mode, so that a user can perform subsequent related operation on the fault mode.
Detailed Description
The embodiment of the application provides a fault diagnosis method and a fault diagnosis device for a gearbox, which are used for diagnosing the fault of the gearbox.
The gear box has wide application in the field of thermal power generation. However, the gear box has complex working conditions and high possibility of failure. Besides the early warning of the fault, the mode of the fault is diagnosed so as to facilitate the subsequent relevant operation of a user.
Referring to fig. 1, an embodiment of a fault diagnosis method according to the embodiment of the present application includes:
101. acquiring first working condition data and first historical data in a preset time period before a fault early warning moment, wherein the first working condition data are time sequence data of a power input side and a load output side in the preset time period, and the first historical data are time domain data of operation parameters of bearings, shafting and groups of meshing gears of a gear transmission;
the first working condition data and the first historical data are obtained from systems such as a monitoring information system, a distributed control system, a rotary machine monitoring and management system and the like through sensors. The first working condition data is time sequence data in a preset time period before the fault early warning time, and comprises operation parameter data of a power input side and operation parameter data of a load output side, the first historical data is data in the preset time period before the fault early warning time and comprises time domain data of operation parameters of bearings, shafting and groups of meshing gears of the gearbox, wherein the preset time period can be 24 hours before the fault early warning time or 48 hours before the fault early warning time, and the duration of the preset time period is not specifically limited.
102. Performing transformation between a time domain and a frequency domain on the first historical data to obtain first frequency domain data;
the acquired first historical data is time domain data, and for calculation convenience, the first historical data is transformed into corresponding first frequency domain data through mathematical transformation, so that the transformation from the time domain to the frequency domain is completed.
Specifically, the mathematical transformation from the time domain to the frequency domain may be a fast fourier transformation or a discrete fourier transformation, which is not limited herein.
103. Calculating a first change rate of the operating parameters of each bearing, each shafting and each group of meshing gears and a first statistical characteristic value of the operating parameters of each bearing, each shafting and each group of meshing gears based on the first frequency domain data;
after the first frequency domain data are obtained, calculating first change rates of the operating parameters of the bearings, the shafting and the sets of meshing gears and first statistical characteristic values of the operating parameters of the bearings, the shafting and the sets of meshing gears based on the first frequency domain data.
Wherein, a first rate of change and a first statistical characteristic value can be calculated based on the amplitude versus time curve of the aforementioned operating parameter, the first statistical characteristic value including but not limited to maximum value, minimum value, mean value, median, mean square error, kurtosis, skewness, etc.
104. Classifying first input data through a clustering model to obtain early warning sample data, wherein the first input data comprise the first working condition data, the first change rate and the first statistical characteristic value;
after the first input data are obtained, the first input data can be classified through the clustering model, and early warning sample data are obtained. The first input data comprises first working condition data, a first change rate and a first statistical characteristic value.
The clustering model is a statistical analysis method for classification problems and consists of a plurality of modes. Clustering analysis is based on similarity, with more similarity between patterns in one class than between patterns not in the same class.
The K-means clustering model is described here as an example. The K-means clustering model divides the data set into a plurality of different categories according to the data characteristics existing in the data, so that the data in the categories are relatively similar, and the data similarity between the categories is relatively low. Selecting n initialized class centers, calculating the distance from each data in the first input data to the class center, and setting the class of each data as the class of the class center closest to the class center, such as the class of bearing inner ring wear or the class of ball wear. And replacing the previous category center with the mean value of each category to become a new category center, and repeating the steps until a preset termination condition is reached.
105. Establishing an early warning sample matrix through the early warning sample data, wherein a row vector of the early warning sample matrix comprises the first statistical characteristic value and the first change rate;
and establishing an early warning sample matrix by using the early warning sample data, wherein the row vector of the early warning sample matrix comprises a first statistical characteristic value and a first change rate.
And establishing a matrix by utilizing the data of each category, wherein the row vector of the matrix consists of a first statistical characteristic value and a first change rate.
106. Calculating a state feature vector of the early warning sample matrix;
and analyzing and calculating the early warning sample matrix to obtain a state characteristic vector. And the state characteristic vector is a characteristic vector of the early warning sample matrix and represents the state of the variable speed gearbox in the preset time period.
And calculating the early warning sample matrix to obtain a characteristic polynomial equation, and solving all roots of the early warning sample matrix according to the characteristic equation, wherein the roots are characteristic values. And solving a homogeneous linear equation set for each characteristic value to obtain a characteristic vector.
107. Calculating a plurality of similarity values between the state feature vector and a plurality of candidate feature vectors, each candidate feature vector characterizing a failure mode;
in order to compare the similarity between the state feature vector and the candidate feature vectors, a plurality of similarity values between the state feature vector and the candidate feature vectors may be calculated by a mathematical method such as the euler distance method. Wherein each candidate feature vector characterizes a particular failure mode.
The distance between the state feature vector and the candidate feature vector, i.e., the similarity, can be obtained by the euler distance method, and a plurality of similarity values can be obtained. If the scene is a two-dimensional scene, the Euler distance method is a formula for solving the linear distance between two points on the plane.
108. And determining a target fault mode corresponding to the state feature vector according to the maximum similarity value, wherein the maximum similarity value is the maximum value of the similarity values, and the target fault mode is a fault mode corresponding to the candidate feature vector with the maximum similarity value.
And selecting the value with the largest similarity value from the acquired similarity values, and determining the value as the largest similarity value. And determining a target fault mode corresponding to the state feature vector according to the maximum similarity value, wherein the target fault mode is a fault mode corresponding to the candidate feature vector with the maximum similarity value.
In the embodiment of the application, after the first historical data is obtained, the first historical data is transformed to obtain first frequency domain data, and a first change rate and a first statistical characteristic value are calculated. And then establishing an early warning sample matrix by using the first change rate and the first statistical eigenvalue, and then calculating the geometric center of the high-dimensional matrix to obtain a state eigenvector. And comparing the similarity degrees of the candidate characteristic vectors and the state characteristic vectors, and calculating the similarity value to obtain the maximum similarity value so as to determine a target fault mode, so that a user can perform subsequent related operation on the fault mode.
Based on the embodiment described in fig. 1, the following describes the process of obtaining a plurality of candidate feature vectors: referring to fig. 2, another embodiment of the fault diagnosis method according to the embodiment of the present application includes:
201. acquiring sensor data, wherein the sensor data are data representing historical faults and comprise second working condition data and second historical data, the second working condition data comprise time sequence data of power input side operation parameters and time sequence data of load output side operation parameters, and the second historical data are second time domain data representing a plurality of faults of the gearbox;
sensor data is acquired by the sensor. The sensor data is data representing historical faults and comprises second working condition data and second historical data, the second working condition data comprises time sequence data of power input side operation parameters and time sequence data of load output side operation parameters, and the second historical data is second time domain data representing multiple faults of the gearbox.
Specifically, the operation parameters of the power input side include motor current, power and the like, and the operation parameters of the load output side include medium flow, density, lift and the like of a water pump or a fan.
202. Converting the second time domain data into second frequency domain data;
the obtained second historical data is time domain data, and for convenience of calculation, the second historical data is transformed into corresponding second frequency domain data through mathematical transformation, so that the transformation from the time domain to the frequency domain is completed.
Specifically, the mathematical transformation from the time domain to the frequency domain may be a fast fourier transformation or a discrete fourier transformation, which is not limited herein.
203. Calculating a second change rate of the operating parameters of the bearings, the shafting and the sets of meshing gears and a second statistical characteristic value of the operating parameters of the bearings, the shafting and the sets of meshing gears based on the second frequency domain data;
and after second frequency domain data are obtained, calculating second change rates of the operating parameters of the bearings, the shafting and the sets of the meshing gears and second statistical characteristic values of the operating parameters of the bearings, the shafting and the sets of the meshing gears based on the second frequency domain data.
Specifically, the second change rate and the second statistical characteristic value of six of the inner ring passing frequency of the bearing of the gearbox, the outer ring passing frequency of the bearing, the ball rotation frequency, the cage passing frequency, the rotation frequency of the shafting and the gear meshing frequency are respectively calculated based on the second frequency domain data, for example, the second change rate and the second statistical characteristic value are calculated based on the amplitude-time relation curves of the six. The second statistical characteristic value comprises a maximum value, a minimum value, a mean value, a median value, a mean square error, a kurtosis, a skewness and the like.
If the gear box has a plurality of bearings or intermediate shafts except the input shaft and the output shaft, the change rate and the statistical characteristic value of each bearing, each shafting and each group of meshed gears are respectively calculated according to the method.
204. Carrying out fault mode classification on second input data through a clustering model to obtain sample data of each fault set, wherein the second input data comprise the second working condition data, the second change rate and the second statistical characteristic value;
after the second input data is obtained, fault mode classification can be carried out on the second input data through the clustering model, and sample data of each fault set is obtained. The second input data comprises second working condition data, a second change rate and a second statistical characteristic value. The clustering model is a statistical analysis method for classification problems and consists of a plurality of modes. Cluster analysis is based on similarity, with more similarity between patterns in one cluster than between patterns not in the same cluster.
It can be understood that the clustering model may be a fuzzy C-means clustering model, a density clustering model, a K-means clustering model, or the like, and is not limited herein.
The K-means clustering model is described here as an example. The K-means clustering model divides the data set into a plurality of different categories according to the data characteristics existing in the data, so that the data in the categories are relatively similar, and the data similarity between the categories is relatively low. Selecting n initialized class centers, calculating the distance from each data in the first input data to the class center, and setting the class of each data as the class of the class center closest to the class center, such as the class of bearing inner ring wear or the class of ball wear. And replacing the previous category center with the mean value of each category to become a new category center, and repeating the steps until a preset termination condition is reached.
Specifically, the failure modes include wear of inner rings of bearings, wear of outer rings of bearings, wear of bearing retainers, wear of bearing balls, poor meshing of gears, poor centering of a shafting, looseness of bearings, looseness of a base or unbalanced mass of the shafting and the like.
205. Establishing a plurality of fault sample matrixes of a plurality of fault modes through sample data of each fault set, wherein a row vector of each fault sample matrix comprises a second statistical characteristic value and a second change rate corresponding to each fault mode;
and establishing a plurality of fault sample matrixes by using the sample data of each fault set. And the row vector of each fault sample matrix comprises a second statistical characteristic value and a second change rate corresponding to each fault mode.
206. Calculating a plurality of candidate feature vectors for the plurality of fault sample matrices;
the candidate eigenvectors of each fault sample matrix can be calculated by a standard deviation method, a mean square deviation method, and the like. And the candidate characteristic vector is a characteristic vector of the fault sample matrix and represents a corresponding fault mode.
And calculating the fault sample matrix to obtain a characteristic polynomial equation, and solving all roots of the fault sample matrix according to the characteristic equation, wherein the roots are characteristic values. And solving a homogeneous linear equation set for each characteristic value to obtain a characteristic vector. If the candidate eigenvectors of the category corresponding to the matrix can be represented by the geometric centers of the candidate eigenvectors, the candidate eigenvectors can be obtained by calculating the distances by methods such as a standard deviation method and a mean square error method.
207. Acquiring first working condition data and first historical data in a preset time period before a fault early warning moment, wherein the first working condition data are time sequence data of a power input side and a load output side in the preset time period, and the first historical data are time domain data of operation parameters of bearings, shafting and groups of meshing gears of a gear transmission;
the first working condition data and the first historical data are obtained from systems such as a monitoring information system, a distributed control system, a rotary machine monitoring and management system and the like through sensors. The first working condition data are time sequence data in a preset time period before the fault early warning time, and comprise operation parameter data of a power input side and operation parameter data of a load output side, and the first historical data are data in the preset time period before the fault early warning time and comprise time domain data of operation parameters of bearings, shafting and groups of meshing gears of the gearbox.
208. Performing transformation between a time domain and a frequency domain on the first historical data to obtain first frequency domain data;
the acquired first historical data is time domain data, and for calculation convenience, the first historical data is transformed into corresponding first frequency domain data through mathematical transformation, so that the transformation from the time domain to the frequency domain is completed. The mathematical transformation may be a fast fourier transformation or a discrete fourier transformation, and is not limited herein.
209. Calculating a first change rate of the operating parameters of each bearing, each shafting and each group of meshing gears and a first statistical characteristic value of the operating parameters of each bearing, each shafting and each group of meshing gears based on the first frequency domain data;
after the first frequency domain data are obtained, calculating first change rates of the operating parameters of the bearings, the shafting and the sets of meshing gears and first statistical characteristic values of the operating parameters of the bearings, the shafting and the sets of meshing gears based on the first frequency domain data. Wherein, a first change rate and a first statistical characteristic value can be calculated based on the relationship curve of the amplitude of the operation parameter and the time, and the first statistical characteristic value comprises a maximum value, a minimum value, a mean value, a median, a mean square error, a kurtosis, a skewness and the like.
If the gear box has a plurality of bearings or intermediate shafts except the input shaft and the output shaft, the change rate and the statistical characteristic value of each bearing, each shafting and each group of meshed gears are respectively calculated according to the method.
210. Classifying first input data through a clustering model to obtain early warning sample data, wherein the first input data comprise the first working condition data, the first change rate and the first statistical characteristic value;
after the first input data are obtained, the first input data can be classified through the clustering model, and early warning sample data are obtained. The first input data comprises first working condition data, a first change rate and a first statistical characteristic value. The clustering model is a statistical analysis method for classification problems and consists of a plurality of modes. Cluster analysis is based on similarity, with more similarity between patterns in one cluster than between patterns not in the same cluster. It is to be understood that the clustering model may be a fuzzy C-means clustering model, or may also be a density clustering model or a gaussian mixture model, and is not limited herein.
211. Establishing an early warning sample matrix through the early warning sample data, wherein a row vector of the early warning sample matrix comprises the first statistical characteristic value and the first change rate;
and establishing an early warning sample matrix by using the early warning sample data, wherein the row vector of the early warning sample matrix comprises a first statistical characteristic value and a first change rate.
212. Calculating a state feature vector of the early warning sample matrix;
and analyzing and calculating the early warning sample matrix to obtain a state characteristic vector. And the state characteristic vector is a characteristic vector of the early warning sample matrix and represents the state of the variable speed gearbox in the preset time period.
And calculating the early warning sample matrix to obtain a characteristic polynomial equation, and solving all roots of the early warning sample matrix according to the characteristic equation, wherein the roots are characteristic values. And solving a homogeneous linear equation set for each characteristic value to obtain a characteristic vector.
213. Calculating a plurality of similarity values between the state feature vector and a plurality of candidate feature vectors, each candidate feature vector characterizing a failure mode;
in order to compare the similarity between the state feature vector and the plurality of candidate feature vectors, the similarity value between the state feature vector and the candidate feature vectors may be calculated by a mathematical method such as an euler distance method, a manhattan distance method, a cosine distance method, a pearson correlation coefficient method, and a spearman (rank) correlation coefficient method. Wherein each candidate feature vector characterizes a particular failure mode and there are multiple similarity values.
The distance between the state feature vector and the candidate feature vector, i.e., the similarity, can be obtained by the euler distance method, and a plurality of similarity values can be obtained. If the scene is a two-dimensional scene, the Euler distance method is a formula for solving the linear distance between two points on the plane.
214. And determining a target fault mode corresponding to the state feature vector according to the maximum similarity value, wherein the maximum similarity value is the maximum value of the similarity values, and the target fault mode is a fault mode corresponding to the candidate feature vector with the maximum similarity value.
And selecting the value with the largest similarity value from the acquired similarity values, and determining the value as the largest similarity value. And determining a target fault mode corresponding to the state feature vector according to the maximum similarity value, wherein the target fault mode is a fault mode corresponding to the candidate feature vector with the maximum similarity value.
In this embodiment, the candidate feature vectors are obtained by performing fault classification on the obtained data and then establishing a high-dimensional matrix. The state feature vector is also calculated by a similar method, and then the candidate feature vector and the state feature vector are compared in similarity. And selecting the maximum similarity value from the obtained multiple similarity values, and determining a target fault mode corresponding to the state feature vector according to the maximum similarity value. This allows for the diagnosis of a fault in the change speed gearbox and thus provides an indication of subsequent operation.
Referring to fig. 3, another embodiment of the fault diagnosis method according to the embodiment of the present application includes:
301. acquiring sensor data, wherein the sensor data are data representing historical faults and comprise second working condition data and second historical data, the second working condition data comprise time sequence data of power input side operation parameters and time sequence data of load output side operation parameters, and the second historical data are second time domain data representing a plurality of faults of the gearbox;
step 301 in this embodiment is similar to step 201 in the embodiment shown in fig. 2, and is not described here again.
302. Removing abnormal values from the second working condition data to obtain third working condition data;
and after the second working condition data are obtained, in order to make the calculation more accurate, removing abnormal values from the second working condition data to obtain third working condition data.
303. Converting the second time domain data into second frequency domain data;
304. calculating a second change rate of the operating parameters of the bearings, the shafting and the sets of meshing gears and a second statistical characteristic value of the operating parameters of the bearings, the shafting and the sets of meshing gears based on the second frequency domain data;
steps 303 to 304 in this embodiment are similar to steps 202 to 203 in the embodiment shown in fig. 2, and are not repeated here.
305. Performing fault mode classification on second input data through a clustering model to obtain sample data of each fault set, wherein the second input data comprise the third working condition data, the second change rate and the second statistical characteristic value;
after the second input data is obtained, fault mode classification can be carried out on the second input data through the clustering model, and sample data of each fault set is obtained. The second input data comprises third working condition data, a second change rate and a second statistical characteristic value. The clustering model is a statistical analysis method for classification problems and consists of a plurality of modes. Cluster analysis is based on similarity, with more similarity between patterns in one cluster than between patterns not in the same cluster.
306. Establishing a plurality of fault sample matrixes of a plurality of fault modes through sample data of each fault set, wherein a row vector of each fault sample matrix comprises a second statistical characteristic value and a second change rate corresponding to each fault mode;
307. calculating a plurality of candidate feature vectors for the plurality of fault sample matrices;
308. acquiring first working condition data and first historical data in a preset time period before a fault early warning moment, wherein the first working condition data are time sequence data of a power input side and a load output side in the preset time period, and the first historical data are time domain data of operation parameters of bearings, shafting and groups of meshing gears of a gear transmission;
309. performing transformation between a time domain and a frequency domain on the first historical data to obtain first frequency domain data;
310. calculating a first change rate of the operating parameters of each bearing, each shafting and each group of meshing gears and a first statistical characteristic value of the operating parameters of each bearing, each shafting and each group of meshing gears based on the first frequency domain data;
311. classifying first input data through a clustering model to obtain early warning sample data, wherein the first input data comprise the first working condition data, the first change rate and the first statistical characteristic value;
312. establishing an early warning sample matrix through the early warning sample data, wherein a row vector of the early warning sample matrix comprises the first statistical characteristic value and the first change rate;
313. calculating a state feature vector of the early warning sample matrix;
314. calculating a plurality of similarity values between the state feature vector and a plurality of candidate feature vectors, each candidate feature vector characterizing a failure mode;
315. and determining a target fault mode corresponding to the state feature vector according to the maximum similarity value, wherein the maximum similarity value is the maximum value of the similarity values, and the target fault mode is a fault mode corresponding to the candidate feature vector with the maximum similarity value.
Steps 306 to 315 in this embodiment are similar to steps 205 to 214 in the embodiment shown in fig. 2, and are not repeated here.
In this embodiment, an operation of removing an abnormal value from the second operating condition data is required to obtain third operating condition data, sample data of each fault set is obtained by using the third operating condition data, and a high-dimensional matrix is established to obtain a candidate eigenvector. And after the state characteristic vector is obtained by a similar method, similarity comparison is carried out so as to determine a target fault mode. Therefore, the calculation is more accurate, and the calculated information of the target failure mode is more reliable.
The following describes the failure diagnosis device according to the embodiment of the present application in detail. Referring to fig. 4, an embodiment of a fault diagnosis apparatus according to the embodiment of the present application includes:
the system comprises an obtaining unit 401, configured to obtain first working condition data and first historical data in a preset time period before a fault early warning time, where the first working condition data is time sequence data of a power input side and a load output side in the preset time period, and the first historical data is time domain data of operating parameters of bearings, shafting, and sets of meshing gears of a gearbox;
a transforming unit 402, configured to perform transformation between a time domain and a frequency domain on the first history data to obtain first frequency domain data;
a calculating unit 403, configured to calculate, based on the first frequency domain data, first change rates of the operating parameters of the bearings, the shafting, and the sets of meshing gears, and first statistical characteristic values of the operating parameters of the bearings, the shafting, and the sets of meshing gears;
a classifying unit 404, configured to classify first input data through a clustering model to obtain early warning sample data, where the first input data includes the first operating condition data, the first change rate, and the first statistical characteristic value;
an establishing unit 405, configured to establish an early warning sample matrix according to the early warning sample data, where a row vector of the early warning sample matrix includes the first statistical eigenvalue and the first change rate;
the calculating unit 403 is further configured to calculate a state feature vector of the early warning sample matrix;
the calculating unit 403 is further configured to calculate a plurality of similarity values between the state feature vector and a plurality of candidate feature vectors, each candidate feature vector representing a failure mode;
a determining unit 406, configured to determine a target failure mode corresponding to the state feature vector according to a maximum similarity value, where the maximum similarity value is a maximum value among multiple similarity values, and the target failure mode is a failure mode corresponding to a candidate feature vector of the maximum similarity value.
In this embodiment, after obtaining unit 401 obtains the first history data, converting unit 402 converts the first history data to obtain first frequency domain data, and calculating unit 403 calculates a first change rate and a first statistical characteristic value. Then, an early warning sample matrix is established by the establishing unit 405 by using the first change rate and the first statistical eigenvalue, and then the geometric center of the high-dimensional matrix is calculated to obtain a state eigenvector. The similarity degrees of the candidate feature vectors and the state feature vectors are compared, and the similarity value is calculated to obtain the maximum similarity value, so that the determining unit 406 can determine the target failure mode, so that the user can perform subsequent related operations on the failure mode.
The functions and processes performed by each unit in the fault diagnosis device of this embodiment are similar to those performed by the fault diagnosis device in fig. 1 to 3, and are not described again here.
Fig. 5 is a schematic structural diagram of a fault diagnosis device according to an embodiment of the present disclosure, where the fault diagnosis device 500 may include one or more Central Processing Units (CPUs) 501 and a memory 505, and one or more applications or data are stored in the memory 505.
Memory 505 may be volatile storage or persistent storage, among others. The program stored in memory 505 may include one or more modules, each of which may include a sequence of instructions operating on the fault diagnosis device 500. Further, the central processor 501 may be configured to communicate with the memory 505 and execute a series of instruction operations in the memory 505 on the fault diagnosis apparatus 500.
The fault diagnosis device 500 may also include one or more power supplies 502, one or more wired or wireless network interfaces 503, one or more input-output interfaces 504, and/or one or more operating systems, such as Windows Server, MacOSXTM, UnixTM, LinuxTM, FreeBSDTM, etc.
The central processing unit 501 may perform the operations performed by the fault diagnosis apparatus in the embodiments shown in fig. 1 to fig. 3, and details thereof are not repeated herein.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes.