A data processing method and related device for a gear transmission

Abstract

The embodiment of the present application discloses a data processing method for a gear transmission, including: acquiring first operating condition data and state data; calculating a predicted value of a target measuring point according to the first operating condition data and the state data; when the difference between the actual value of the target measuring point and the predicted value of the target measuring point is greater than an alarm threshold, issuing a warning signal and acquiring second operating condition data and first historical data within a preset time period before a fault warning moment; determining a target fault mode; acquiring a first fault sample matrix of the target fault mode; determining a maintenance time point of the target fault mode according to the first fault sample matrix; and outputting prompt information.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of thermal power generation, and in particular to a data processing method and related devices for a gear transmission. Background Art

[0002] Gearbox equipment is widely used in coal mill reducers, slurry circulation pump reducers, and turbine turning devices. Due to the large fluctuation range of working load and frequent start and stop, the gearbox has a high equipment failure rate, which brings certain problems to production.

[0003] The common practice in the industry is to return the equipment to the equipment manufacturer for inspection and repair when it is detected that the gear box vibration exceeds the limit or the on-site noise is abnormal, and replace the faulty gearbox with a spare gearbox to maintain the operation of the unit.

[0004] However, this maintenance method must be used when the gear transmission fails. The specific circumstances of the failure cannot be known in advance, so a reasonable maintenance plan cannot be formulated, which brings inconvenience to users. Summary of the invention

[0005] The embodiments of the present application provide a data processing method and related device for a gear transmission.

[0006] A data processing method for a gear transmission, comprising:

[0007] Acquire first operating condition data and state data, wherein the first operating condition data includes time series data of a measuring point on a power input side and time series data of a measuring point on a load output side, and the state data includes time series data of a measuring point on a gear transmission body side;

[0008] Calculate a predicted value of a target measuring point according to the first operating condition data and the state data;

[0009] When the difference between the actual value of the target measuring point and the predicted value of the target measuring point is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are obtained, the actual value of the target measuring point is a part of the first operating condition data, the second operating condition data is the time series data of the power input side and the load output side, the first historical data is the time domain data of the operating parameters of each bearing, each shaft system and each group of meshing gears of the gear transmission, and the alarm threshold is a preset value;

[0010] determining a target failure mode according to the second operating condition data and the first historical data;

[0011] Acquire a first fault sample matrix of the target fault mode;

[0012] Determine a maintenance time point of the target failure mode according to the first failure sample matrix;

[0013] Outputting prompt information, wherein the prompt information includes information about the target failure mode and information about the maintenance time point.

[0014] Optionally, calculating a predicted value of a target measuring point according to the first operating condition data and the state data includes:

[0015] Eliminating abnormal values ​​from the first operating condition data to obtain third operating condition data;

[0016] Performing a transformation between the time domain and the frequency domain on the state data to obtain first frequency domain data of the state data;

[0017] Calculate the frequency band factors of the bearings, shaft system and meshing gears of the gear transmission respectively according to the first frequency domain data;

[0018] Normalizing the third operating condition data to obtain fourth operating condition data;

[0019] Performing dimension reduction on the fourth operating condition data and the frequency band factor to obtain a dimension reduction feature vector;

[0020] Establishing a high-dimensional feature space through the dimension-reduced feature vector, wherein the high-dimensional feature space is a matrix of time series data including state information;

[0021] Classifying the time series data in the high-dimensional feature space by a clustering model to obtain time series data of different categories, wherein each category of time series data represents an operating state of the gear transmission;

[0022] Analyze the time segments of the time series data under each category through a regression model to determine a first mathematical relationship between a target measuring point and all measuring points except the target measuring point;

[0023] The predicted value of the target measuring point is calculated through the first mathematical relationship and the time series data of all measuring points except the target measuring point.

[0024] Optionally, after calculating the predicted value of the target measuring point through the mathematical relationship and the time series data of all measuring points except the target measuring point, the method further includes:

[0025] If there are multiple clustering models and multiple regression models, respectively, the clustering models and the regression models are evaluated to select the optimal clustering model and the optimal regression model;

[0026] Filtering out target prediction values ​​corresponding to the optimal clustering model and the optimal regression model from the prediction values;

[0027] When the difference between the actual value of the target measuring point and the predicted value of the target measuring point is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are obtained, including:

[0028] When the difference between the actual value of the target measurement point and the target predicted value is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are acquired.

[0029] Optionally, determining a target failure mode according to the second operating condition data and the first historical data includes:

[0030] Performing a transformation between the time domain and the frequency domain on the first historical data to obtain second frequency domain data;

[0031] Calculating, based on the second frequency domain data, a first change rate of an operating parameter of each bearing, each shaft system, and each set of meshing gears and a first statistical characteristic value of an operating parameter of each bearing, each shaft system, and each set of meshing gears;

[0032] Classifying first input data by a clustering model to obtain warning sample data, wherein the first input data includes the second operating condition data, the first change rate, and the first statistical characteristic value;

[0033] Establishing a warning sample matrix through the warning sample data, wherein the row vector of the warning sample matrix includes the first statistical eigenvalue and the first change rate;

[0034] Calculating the state eigenvector of the warning sample matrix;

[0035] Calculating a plurality of similarity values ​​between the state feature vector and a plurality of candidate feature vectors, each candidate feature vector representing a fault mode;

[0036] The fault mode corresponding to the candidate feature vector with the maximum similarity value is determined as the target fault mode, and the maximum similarity value is the maximum value among the multiple similarity values.

[0037] Optionally, before performing a transformation between the time domain and the frequency domain on the first historical data to obtain the second frequency domain data, the method further includes:

[0038] Acquire fifth operating condition data and second historical data characterizing historical faults, wherein the fifth operating condition data includes time series data of operating parameters on the power input side and time series data of operating parameters on the load output side, and the second historical data is second time domain data characterizing multiple faults of the gear transmission;

[0039] Eliminating abnormal values ​​from the fifth operating condition data to obtain sixth operating condition data;

[0040] converting the second historical data into second frequency domain data;

[0041] Calculating a second change rate of the operating parameters of each bearing, each shaft system, and each set of meshing gears and a second statistical characteristic value of the operating parameters of each bearing, each shaft system, and each set of meshing gears based on the second frequency domain data;

[0042] Performing fault mode classification on the second input data through a clustering model to obtain fault sample data of each fault set, wherein the second input data includes the sixth operating condition data, the second change rate and the second statistical characteristic value;

[0043] Establishing a plurality of second fault sample matrices of a plurality of fault modes through the fault sample data of each fault set, wherein the row vector of each fault sample matrix includes a second statistical characteristic value and a second change rate corresponding to each fault mode;

[0044] A plurality of candidate eigenvectors of the second fault sample matrix are calculated.

[0045] Optionally, determining the maintenance time point of the target failure mode according to the first failure sample matrix includes:

[0046] Normalizing the first fault sample matrix to obtain a third fault sample matrix, wherein the first fault sample matrix is ​​a matrix of time series data of the target fault mode in the warning sample matrix;

[0047] Classifying the third fault sample matrix by using a clustering model to obtain classified sample data;

[0048] Analyzing the classified sample data by a regression model to determine a second mathematical relationship between the target measuring point and all measuring points except the target measuring point;

[0049] Calculate the predicted value of the target measuring point by using the second mathematical relationship and the sample data of all measuring points except the target measuring point;

[0050] A time point corresponding to a minimum value among the predicted values ​​that are greater than or equal to the expected value is determined as a maintenance time point, and the expected value is a preset value for distinguishing the state of the gear transmission.

[0051] Optionally, converting the second historical data into second frequency domain data includes:

[0052] Converting the second historical data into second frequency domain data by fast Fourier transform;

[0053] or,

[0054] The second historical data is converted into second frequency domain data by discrete Fourier transform.

[0055] A data processing device, comprising:

[0056] An acquisition unit, used to acquire first operating condition data and state data, wherein the first operating condition data includes time series data of a measuring point on a power input side and time series data of a measuring point on a load output side, and the state data includes time series data of a measuring point on a gear transmission body side;

[0057] a calculation unit, configured to calculate a predicted value of a target measuring point according to the first operating condition data and the state data;

[0058] a processing unit, configured to, when a difference between an actual value of the target measuring point and a predicted value of the target measuring point is greater than an alarm threshold, issue an early warning signal and obtain second operating condition data and first historical data within a preset time period before a fault early warning moment, wherein the actual value of the target measuring point is a part of the first operating condition data, the second operating condition data is time series data of a power input side and a load output side, the first historical data is time domain data of operating parameters of each bearing, each shaft system, and each group of meshing gears of a gear transmission, and the alarm threshold is a preset value;

[0059] a determination unit, configured to determine a target fault mode according to the second operating condition data and the first historical data;

[0060] The acquisition unit is further used to acquire a first fault sample matrix of the target fault mode;

[0061] The determining unit is further configured to determine a maintenance time point of the target failure mode according to the first failure sample matrix;

[0062] The output unit is used to output prompt information, wherein the prompt information includes information about the target failure mode and information about the maintenance time point.

[0063] A data processing device, comprising:

[0064] CPU, memory and input / output interface;

[0065] The memory is a transient storage memory or a persistent storage memory;

[0066] The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the above method.

[0067] A computer-readable storage medium includes instructions. When the instructions are executed on a computer, the computer is caused to execute the above method.

[0068] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0069] The first operating condition data and status data are obtained to calculate the predicted value of the target measuring point. When the difference between the actual value and the predicted value of the target measuring point is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within the preset time period before the fault warning moment are obtained. Then, the target fault mode is determined based on the second operating condition data and the first historical data, the first fault sample matrix of the target fault mode is obtained, and then the maintenance time point of the target fault mode is determined, and prompt information is output. When there are signs of faults, it can be warned, a warning signal can be issued, and then the possible target fault mode and the corresponding maintenance time point can be prompted, so that a reasonable maintenance plan can be formulated, which brings great convenience to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 This is a schematic diagram of an embodiment of the gear transmission data processing method of the present application embodiment;

[0071] Figure 2 This is a schematic diagram of another embodiment of the gear transmission data processing method of the present application embodiment;

[0072] Figure 3 This is a schematic diagram of an embodiment of a gear transmission data processing device according to an embodiment of the present application;

[0073] Figure 4 This is a schematic diagram of another embodiment of the gear transmission data processing device of the embodiment of the present application. DETAILED DESCRIPTION

[0074] The embodiments of the present application provide a data processing method and related device for a gear transmission.

[0075] Gearboxes have complex working conditions. Bearings and gears gradually deteriorate from early abnormalities to functional failures. Fault warning and diagnosis using existing technologies have serious time lags and passive responses, which brings inconvenience to users. The data processing method and related devices for gearboxes provided in the embodiments of the present application can help users formulate reasonable maintenance plans and improve production efficiency.

[0076] The following is a description of the gearbox data processing method of the present application embodiment. Figure 1 , an embodiment of the gear transmission data processing method of the present application embodiment includes:

[0077] 101. Acquire first operating condition data and state data;

[0078] The first operating condition data and state data are obtained from the monitoring information system, the distributed control system, the rotating machinery monitoring and management system, etc. through sensors. Among them, the measuring point can be understood as a physical quantity. The first operating condition data includes the time series data of the measuring point on the power input side and the time series data of the measuring point on the load output side, and the state data includes the time series data of the measuring point on the gear transmission body side.

[0079] 102. Calculate a predicted value of a target measuring point according to the first operating condition data and the state data;

[0080] After obtaining the first working condition data and the state data, the predicted value of the target measuring point is calculated. Specifically, the first working condition data and the state data are preprocessed first, and then a feature space is established. Cluster analysis and regression analysis are performed on the feature space to predict the predicted value of the target measuring point.

[0081] 103. When the difference between the actual value of the target measuring point and the predicted value of the target measuring point is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are acquired;

[0082] After obtaining the predicted value of the target measuring point, compare it with the actual value of the measuring point obtained by the sensor. If the difference between the two is greater than the preset alarm threshold, it means that the deviation is too large and the gear transmission deviates from the normal working state. In this case, an early warning signal is issued to prompt the user, and the second operating condition data and the first historical data within the preset time period before the fault warning moment are obtained for subsequent operations. Among them, the actual value of the target measuring point is part of the first operating condition data, the second operating condition data is the time series data of the power input side and the load output side, and the first historical data is the time domain data of the operating parameters of each bearing, each shaft system and each group of meshing gears of the gear transmission. The alarm threshold is a preset value and can be pre-set according to experience and needs.

[0083] 104. Determine a target failure mode according to the second operating condition data and the first historical data;

[0084] After obtaining the second operating condition data and the first historical data, the target fault mode is determined. Specifically, the second operating condition data and the first historical data are preprocessed, and 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 are calculated, and then a warning sample matrix is ​​established based on the first change rate and the first statistical characteristic value, and the state characteristic vector of the warning sample matrix is ​​calculated. Finally, the similarity between the state characteristic vector and the candidate characteristic vector is compared, and the fault mode corresponding to the maximum similarity is the target fault mode.

[0085] 105. Obtain a first fault sample matrix of the target fault mode;

[0086] After the target fault mode is known, the first fault sample matrix corresponding thereto is obtained, wherein the first fault sample matrix is ​​a matrix including the time series data of the target fault mode, and the target fault mode is the most probable fault mode among the possible fault modes of the gear transmission.

[0087] 106. Determine a maintenance time point of the target failure mode according to the first failure sample matrix;

[0088] The maintenance time point of the target fault mode is determined according to the first fault sample matrix. Specifically, the first fault sample matrix is ​​normalized, then cluster analysis is performed for classification, and then regression analysis is performed to determine the time point corresponding to the minimum value among the predicted values ​​that are greater than or equal to the expected value as the maintenance time point.

[0089] 107. Output prompt information;

[0090] After the maintenance time point is obtained, a prompt message is output, wherein the prompt message includes information about the target failure mode and information about the maintenance time point, for example, the prompt message may be "Warning: Possible failure occurs, the target failure mode is loose bearing, and the maintenance time point is xx year xx month xx day xx hour...".

[0091] In the embodiment of the present application, the first operating condition data and state data are obtained to calculate the predicted value of the target measuring point. When the difference between the actual value of the target measuring point and the predicted value is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are obtained. Then, the target fault mode is determined based on the second operating condition data and the first historical data, the first fault sample matrix of the target fault mode is obtained, and then the maintenance time point of the target fault mode is determined, and prompt information is output. When there are signs of faults, they can be warned, a warning signal can be issued, and then the possible target fault mode and the corresponding maintenance time point can be prompted, so that a reasonable maintenance plan can be formulated, which brings great convenience to users.

[0092] See also Figure 2 Another embodiment of the gear transmission data processing method of the present application embodiment includes:

[0093] 201. Acquire first working condition data and state data;

[0094] The first operating condition data and status data are obtained from the monitoring information system, distributed control system, rotating machinery monitoring and management system, etc. through sensors. Among them, the measuring point can be understood as a physical quantity. The first operating condition data includes the timing data of the measuring point on the power input side and the timing data of the measuring point on the load output side, and the status data includes the timing data of the measuring point on the gear transmission body side. The parameters on the power input side are motor current, power, etc., the parameters on the gear transmission body side are horizontal, vertical, and axial vibrations of the input shaft and horizontal, vertical, and axial vibrations of the output shaft, etc., and the parameters on the load output side are water pump, fan medium flow, density, head, etc.

[0095] 202. Eliminate abnormal values ​​from the first operating condition data to obtain third operating condition data;

[0096] The outliers in the first working condition data are removed to obtain the third working condition data. The outliers refer to individual values ​​in the sample, whose values ​​are obviously deviated from the remaining observed values ​​of the sample to which they belong. The outliers in the first working condition data can be filtered to ensure the accuracy of subsequent model predictions.

[0097] 203. Perform a transformation between the time domain and the frequency domain on the state data to obtain first frequency domain data of the state data;

[0098] The acquired state data is time domain data. To facilitate subsequent calculations, the state data is transformed into corresponding first frequency domain data through fast Fourier transform to complete the transformation from time domain to frequency domain.

[0099] It is understandable that the state data may also be transformed into the corresponding first frequency domain data by using a mathematical method such as discrete Fourier transform to transform the time domain data into the frequency domain state, which is not limited here.

[0100] 204. Calculate frequency band factors of the bearing, shaft system, and meshing gear of the gear transmission respectively according to the first frequency domain data;

[0101] The first frequency domain data is used to calculate the frequency band factors of the bearings, shaft system and meshing gears of the gear transmission according to the following formula.

[0102] Specifically, the frequency band factor representing the gearbox bearing state can be calculated according to the bandwidth of 1‰ to 5‰ of the inner ring passing frequency, outer ring passing frequency, ball rotation frequency and cage passing frequency of the gearbox input shaft and output shaft bearings, and the specific formula is as follows:

[0103]

[0104] The frequency band factor representing the alignment and balance state of the gearbox shaft system can be calculated according to the bandwidth of 1% to 3% of the rotation frequency of the gearbox input shaft and output shaft. The specific formula is as follows:

[0105]

[0106] The frequency band factor representing the gear meshing state of the gear transmission can be calculated according to the bandwidth of 3% to 5% of the gear meshing frequency between the input shaft and the output shaft of the gear transmission. The specific formula is as follows:

[0107]

[0108] It is understandable that other equivalent variations of the above formula may also be used to calculate the frequency band factor, which is not specifically limited here.

[0109] If the gear transmission has multiple bearings or intermediate shafts, the frequency band factors of each bearing, shaft system and each set of meshing gears are calculated separately using the same method.

[0110] 205. Normalize the third operating condition data to obtain fourth operating condition data;

[0111] For the convenience of processing, the third working condition data is normalized to obtain the fourth working condition data. Normalization is a method of simplifying calculations, which can be linear function normalization or zero mean normalization, which is not limited here.

[0112] 206. Perform dimension reduction on the fourth operating condition data and the frequency band factor to obtain a dimension reduction feature vector;

[0113] The fourth working condition data and frequency band factors are screened by dimensionality reduction method to obtain the dimensionality reduction feature vector. Dimensionality reduction refers to the use of a certain mapping method to map the data points in the original high-dimensional space to a low-dimensional space. The intuitive benefit is that the dimension is reduced, which is convenient for calculation and visualization. Its deeper meaning lies in the extraction and synthesis of effective information and the abandonment of useless information.

[0114] Specifically, the dimensionality reduction method may be a principal component analysis method, which converts the third operating condition data and the frequency band factor into a feature vector through an orthogonal transformation to filter out non-orthogonal data. The dimensionality reduction method may also be a T-distribution random neighborhood embedding method, etc., which is not specifically limited here.

[0115] 207. Establish a high-dimensional feature space through the dimension-reduced feature vector;

[0116] A high-dimensional feature space is established using the dimension-reduced feature vector, wherein the high-dimensional feature space is a matrix of time series data including state information, and the state information is related information in a normal state under different working conditions.

[0117] 208. Classifying the time series data in the high-dimensional feature space by using a clustering model to obtain time series data of different categories;

[0118] In order to process the established high-dimensional feature space, a clustering model can be further used to classify it. The state to which the time series data belongs is classified to obtain the time series data of each classification, wherein the time series data of each category represents an operating state of the gear transmission. Among them, the clustering model is an analytical method for studying classification problems, based on similarity, so that the time series data in one classification has more similarity than the time series data in different classifications.

[0119] Specifically, the clustering model may be a fuzzy C-means clustering model, a density-based noise application space clustering model, a K-means clustering model, or other models, which are not specifically limited here.

[0120] Here we take the K-means clustering model as an example for description. The K-means clustering model divides the data set into multiple different categories according to the data features existing within the data, so that the data within the category is relatively similar, and the data similarity between categories is relatively small. Select the n initialized category centers, calculate the distance from each data in the first input data to the category center, and set the category of each data to the category of the nearest category center, such as the bearing inner ring wear category or the ball wear category. Replace the previous category center with the mean of each category to become the new category center, and repeat the above steps until the preset termination condition is reached.

[0121] 209. Analyze the time segments of the time series data under each category by using a regression model to determine a first mathematical relationship between a target measuring point and all measuring points except the target measuring point;

[0122] The regression model is used to analyze the time segments of the time series data under each classification to determine the first mathematical relationship between the target measuring point and all measuring points except the target measuring point. Among them, the regression model is a predictive modeling technology that studies the relationship between the dependent variable and the independent variable. The regression model is used to predict the values ​​of other unobtained measuring points through the values ​​of the obtained measuring points to obtain the predicted values ​​of the measuring points to be predicted.

[0123] Specifically, the regression model can be an approximate nearest neighbor retrieval model, a long short-term memory network model, a Hopfeldt neural network model, etc., which are not limited here.

[0124] 210. Calculate a predicted value of the target measuring point by using the first mathematical relationship and the time series data of all measuring points except the target measuring point;

[0125] Substitute the time series data of all measuring points except the target measuring point into the mathematical formula representing the relationship between the target measuring point and all measuring points except the target measuring point to calculate the predicted value of the target measuring point. Use the time series data of the measured points that have been acquired to predict the values ​​of other unobtained measuring points to obtain the predicted value of the target measuring point. For example, if 10 time series data are collected from 10 sensors and processed through the above steps, to obtain the predicted value of the first measuring point, the time series data of the other 9 measuring points are analyzed, that is, the predicted value of the first measuring point is used as the dependent variable, and the time series data of the other 9 measuring points are used as the independent variable.

[0126] 211. If there are multiple clustering models and multiple regression models respectively, evaluate the clustering models and the regression models to select the optimal clustering model and the optimal regression model;

[0127] When there are multiple clustering models and regression models, there are multiple predicted values. The receiver operating characteristic (ROC) method is used to evaluate the model to select the optimal clustering model and the optimal regression model. For example, prepare other time series data in advance, use clustering model classification and regression model for prediction, and compare the results with the results obtained by the clustering model and the regression model. The clustering model and regression model corresponding to the two results with the smallest error evaluated by the ROC method are the optimal clustering model and the optimal regression model.

[0128] 212. Filtering out target prediction values ​​corresponding to the optimal clustering model and the optimal regression model from the prediction values;

[0129] The target prediction value, that is, the value corresponding to the optimal clustering model and the optimal regression model, is selected from multiple prediction values ​​for subsequent comparison.

[0130] 213. When the difference between the actual value of the target measurement point and the target predicted value is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are acquired;

[0131] After obtaining the target predicted value, compare it with the actual value of the measuring point obtained by the sensor. If the difference between the two is greater than the preset alarm threshold, it means that the deviation is too large and the gear transmission deviates from the normal working state. Then, an early warning signal is issued to prompt the user, and the second operating condition data and the first historical data within the preset time period before the fault warning moment are obtained for subsequent operations. Among them, the actual value of the target measuring point is part of the first operating condition data, the second operating condition data is the time series data of the power input side and the load output side, and the first historical data is the time domain data of the operating parameters of each bearing, each shaft system and each group of meshing gears of the gear transmission. The alarm threshold is a preset value, which can be pre-set according to experience and needs.

[0132] 214. Acquire fifth operating condition data and second historical data representing historical faults;

[0133] The fifth operating condition data and the second historical data representing the historical faults are obtained through sensors. The fifth operating condition data include the time series data of the operating parameters of the power input side and the time series data of the operating parameters of the load output side, and the second historical data are the second time domain data representing multiple faults of the gear transmission. The fifth operating condition data and the second historical data are both data of the previously existing fault mode, and these data are used for subsequent comparison.

[0134] 215. Eliminate abnormal values ​​from the fifth operating condition data to obtain sixth operating condition data;

[0135] After obtaining the fifth operating condition data, in order to make the calculation more accurate, the fifth operating condition data is eliminated of abnormal values ​​to obtain the sixth operating condition data.

[0136] 216. Convert the second historical data into second frequency domain data;

[0137] The acquired second historical data is time domain data. To facilitate calculation, the second historical data is transformed into corresponding second frequency domain data through mathematical transformation to complete the transformation from time domain to frequency domain.

[0138] 217. Calculate a second change rate of an operating parameter of each bearing, each shaft system, and each set of meshing gears and a second statistical characteristic value of an operating parameter of each bearing, each shaft system, and each set of meshing gears based on the second frequency domain data;

[0139] After obtaining the second frequency domain data, the second change rate of the operating parameters of each bearing, each shaft system and each set of meshing gears and the second statistical characteristic value of the operating parameters of each bearing, each shaft system and each set of meshing gears are calculated based on the second frequency domain data.

[0140] Specifically, based on the second frequency domain data, the second change rate and second statistical characteristic value of the inner ring passing frequency of the bearing of the gear transmission, the outer ring passing frequency of the bearing, the ball rotation frequency, the cage passing frequency, the shaft system rotation frequency and the gear meshing frequency are calculated respectively, for example, based on the relationship curve between the amplitude and time of the six, the second change rate and the second statistical characteristic value are calculated. Among them, the second statistical characteristic value includes maximum value, minimum value, mean value, median value, mean square error, kurtosis, kurtosis, skewness, etc.

[0141] If the gear transmission has multiple bearings or an intermediate shaft other than the input shaft and the output shaft, the change rate and statistical characteristic value of each bearing, shaft system and each group of meshing gears are calculated separately according to the above method.

[0142] 218. Classify the fault modes of the second input data by using a clustering model to obtain fault sample data of each fault set;

[0143] After obtaining the second input data, the second input data can be classified into fault modes through the clustering model to obtain sample data of each fault set. The second input data includes the sixth operating condition data, the second change rate and the second statistical characteristic value. The clustering model is a statistical analysis method for classification problems, which consists of several patterns. Cluster analysis is based on similarity, and the patterns in a cluster have more similarities than the patterns in different clusters.

[0144] It is understandable that the clustering model may be a fuzzy C-means clustering model, a density clustering model, a K-means clustering model, etc., which is not specifically limited here.

[0145] 219. Establish multiple second fault sample matrices of multiple fault modes through the fault sample data of each fault set;

[0146] Multiple fault sample matrices are established using sample data of each fault set, wherein the row vector of each fault sample matrix includes the second statistical characteristic value and the second change rate corresponding to each fault mode.

[0147] 220. Calculate multiple candidate feature vectors of the second fault sample matrix;

[0148] Multiple candidate eigenvectors of the second fault sample matrix can be calculated by methods such as standard deviation method, mean square error method, etc. The candidate eigenvector is a eigenvector of the second fault sample matrix, representing the corresponding fault mode.

[0149] The characteristic polynomial equation is calculated for the second fault sample matrix, and then all its roots are obtained according to the characteristic equation, which are the eigenvalues. Then, a homogeneous linear equation system is obtained for each eigenvalue to obtain the eigenvector. If the candidate eigenvectors of the category corresponding to the matrix can be represented by their geometric center, the distance can be calculated by the standard deviation method, mean square error method, etc. to obtain multiple candidate eigenvectors.

[0150] 221. Perform a transformation between the time domain and the frequency domain on the first historical data to obtain second frequency domain data;

[0151] The first historical data obtained is time domain data. To facilitate calculation, the first historical data is transformed into corresponding second frequency domain data through mathematical transformation to complete the transformation from time domain to frequency domain.

[0152] 222. Calculate, based on the second frequency domain data, a first change rate of an operating parameter of each bearing, each shaft system, and each set of meshing gears and a first statistical characteristic value of an operating parameter of each bearing, each shaft system, and each set of meshing gears;

[0153] After obtaining the second frequency domain data, the first change rate of the operating parameters of each bearing, each shaft system and each set of meshing gears and the first statistical characteristic value of the operating parameters of each bearing, each shaft system and each set of meshing gears are calculated based on the second frequency domain data.

[0154] Among them, the first change rate and the first statistical characteristic value can be calculated based on the relationship curve between the amplitude and time of the aforementioned operating parameters. The first statistical characteristic value includes but is not limited to maximum value, minimum value, mean, median, mean square error, kurtosis, kurtosis, skewness, etc.

[0155] 223. Classify the first input data by using a clustering model to obtain warning sample data;

[0156] After obtaining the first input data, the first input data can be classified by the clustering model to obtain the early warning sample data. The first input data includes the first operating condition data, the first change rate and the first statistical characteristic value. For example, the operating condition data under the bearing inner ring wear mode, the corresponding change rate and the corresponding statistical characteristic value are one category.

[0157] The clustering model is a statistical analysis method for classification problems, which consists of several patterns. Cluster analysis is based on similarity, and the patterns in a category have more similarities than those in different categories.

[0158] Here we take the K-means clustering model as an example for description. The K-means clustering model divides the data set into multiple different categories according to the data features existing within the data, so that the data within the category is relatively similar, and the data similarity between categories is relatively small. Select the n initialized category centers, calculate the distance from each data in the first input data to the category center, and set the category of each data to the category of the nearest category center, such as the bearing inner ring wear category or the ball wear category. Replace the previous category center with the mean of each category to become the new category center, and repeat the above steps until the preset termination condition is reached.

[0159] 224. Establishing a warning sample matrix through the warning sample data;

[0160] A warning sample matrix is ​​established using the warning sample data, wherein a row vector of the warning sample matrix includes a first statistical eigenvalue and a first change rate.

[0161] 225. Calculate the state characteristic vector of the warning sample matrix;

[0162] The warning sample matrix is ​​analyzed and calculated to obtain a state characteristic vector, wherein the state characteristic vector is a characteristic vector of the warning sample matrix, and represents the state of the speed change gear box within the above-mentioned preset time period.

[0163] The characteristic polynomial equation is obtained by calculating the warning sample matrix, and then all its roots are obtained according to the characteristic equation, which are the eigenvalues. Then, the homogeneous linear equation system is obtained for each eigenvalue to obtain the eigenvector.

[0164] 226. Calculate multiple similarity values ​​between the state feature vector and multiple candidate feature vectors;

[0165] In order to compare the similarity between the state feature vector and multiple candidate feature vectors, the similarity value between the state feature vector and the candidate feature vector can be calculated by mathematical methods such as Euler distance method, Manhattan distance method, cosine distance method, Pearson correlation coefficient method, Spearman (rank) correlation coefficient method, etc. Among them, each candidate feature vector represents a specific fault mode, and there are multiple similarity values.

[0166] The distance between the state feature vector and the candidate feature vector, i.e., the similarity, can be calculated by the Euler distance method, and multiple similarity values ​​can be obtained. If it is a two-dimensional scene, the Euler distance method is a formula for calculating the straight-line distance between two points on a plane.

[0167] 227. Determine the fault mode corresponding to the candidate feature vector with the maximum similarity value as the target fault mode;

[0168] The value with the largest similarity value is selected from the obtained multiple similarity values ​​and determined as the maximum similarity value. Then, the target fault mode corresponding to the state feature vector is determined according to the maximum similarity value, wherein the target fault mode is the fault mode corresponding to the candidate feature vector with the maximum similarity value.

[0169] 228. Obtain a first fault sample matrix of the target fault mode;

[0170] After the target fault mode is known, the first fault sample matrix corresponding thereto is obtained, wherein the first fault sample matrix is ​​a matrix including the time series data of the target fault mode, and the target fault mode is the most probable fault mode among the possible fault modes of the gear transmission.

[0171] 229. Normalize the first fault sample matrix to obtain a third fault sample matrix;

[0172] For the convenience of processing, the first fault sample matrix is ​​normalized to obtain the third fault sample matrix. Normalization is a way to simplify calculations, which can be linear function normalization or zero mean normalization, which is not limited here. The first fault sample matrix is ​​a matrix of the time series data of the target fault mode in the warning sample matrix.

[0173] 230. Classify the third fault sample matrix by using a clustering model to obtain classified sample data;

[0174] After obtaining the third fault sample matrix, the third fault sample matrix is ​​classified to obtain classified sample data. The classified sample data includes data classified by different life time of the gear transmission. The classification clustering model is a statistical analysis method for classification problems, based on similarity, and the patterns in a category have more similarities than the patterns in different categories. The clustering model in the embodiment of the present application can be a K-means clustering model, a density-based noise application space clustering model, or a Gaussian mixture clustering model, which is not specifically limited here.

[0175] 231. Analyze the classified sample data by using a regression model to determine a second mathematical relationship between the target measuring point and all measuring points except the target measuring point;

[0176] The regression model is used to analyze the classified sample data to determine the mathematical relationship between the target measurement point and all measurement points except the target measurement point, providing the prerequisite for subsequent calculations. Among them, the regression model is a predictive modeling technology that studies the relationship between the predicted value and the sample data used to predict it. Specifically, the regression model can be an approximate nearest neighbor retrieval model, a long short-term memory network model, or a Hopfeldt neural network model, etc., which are not limited here.

[0177] 232. Calculate the predicted value of the target measuring point by using the second mathematical relationship and the sample data of all measuring points except the target measuring point;

[0178] The sample data of all measuring points except the target measuring point are brought into the mathematical relationship representing the relationship between the target measuring point and all measuring points except the target measuring point to calculate the predicted value of the target measuring point. The values ​​of other unobtained measuring points are predicted by the data of the obtained measuring points to obtain the predicted value of the target measuring point. For example, if 10 sample data are obtained and processed through the above steps, to obtain the predicted value of the first measuring point, the sample data of the other 9 measuring points are analyzed, that is, the predicted value of the first measuring point is used as the dependent variable, and the sample data of the other 9 measuring points are used as the independent variable.

[0179] 233. Determine the time point corresponding to the minimum value among the predicted values ​​that are greater than or equal to the expected values ​​as the maintenance time point;

[0180] After calculating multiple predicted values, find the minimum value among the predicted values ​​that are greater than or equal to the expected value, and then determine the time point corresponding to the minimum value as the maintenance time point. The expected value is a preset value used to distinguish the state of the gear transmission, which can be set by the user based on experience.

[0181] For example, the preset expected value of the inner ring passing frequency of the bearing is 2. If it exceeds 2, it means that the gearbox is faulty, and if it does not exceed 2, it means that the gearbox is working normally. The minimum value among the predicted values ​​that are greater than or equal to the expected value is 2.05, and the time point corresponding to the value 2.05 is the maintenance time point, which is the best time for maintenance.

[0182] 234. Output prompt information.

[0183] After the maintenance time point is obtained, a prompt message is output, wherein the prompt message includes information about the target failure mode and information about the maintenance time point, for example, the prompt message may be "Warning: Possible failure occurs, the target failure mode is loose bearing, and the maintenance time point is xx year xx month xx day xx hour...".

[0184] In this embodiment, the first operating condition data and state data are obtained to calculate the predicted value of the target measuring point. When the difference between the actual value of the target measuring point and the predicted value is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are obtained. Then, the target fault mode is determined based on the second operating condition data and the first historical data, the first fault sample matrix of the target fault mode is obtained, and then the maintenance time point of the target fault mode is determined, and prompt information is output. When there are signs of faults, it can be warned, a warning signal can be issued, and then the possible target fault mode and the corresponding maintenance time point can be prompted, so that a reasonable maintenance plan can be formulated. In addition, through operations such as normalization and elimination of outliers, the complexity of the calculation is greatly reduced, the efficiency is improved, and great convenience is brought to the user.

[0185] The data processing device of the gearbox according to the embodiment of the present application is described below. Figure 3 , an embodiment of the gear transmission data processing device of the present application includes:

[0186] An acquisition unit 301 is used to acquire first operating condition data and state data, wherein the first operating condition data includes time series data of a measuring point on a power input side and time series data of a measuring point on a load output side, and the state data includes time series data of a measuring point on a gear transmission body side;

[0187] A calculation unit 302, configured to calculate a predicted value of a target measuring point according to the first operating condition data and the state data;

[0188] The processing unit 303 is used to send out a warning signal and obtain the second operating condition data and the first historical data within a preset time period before the fault warning moment when the difference between the actual value of the target measuring point and the predicted value of the target measuring point is greater than the alarm threshold, wherein the actual value of the target measuring point is a part of the first operating condition data, the second operating condition data is the time series data of the power input side and the load output side, the first historical data is the time domain data of the operating parameters of each bearing, each shaft system and each group of meshing gears of the gear transmission, and the alarm threshold is a preset value;

[0189] A determination unit 304, configured to determine a target fault mode according to the second operating condition data and the first historical data;

[0190] The acquisition unit 301 is further configured to acquire a first fault sample matrix of the target fault mode;

[0191] The determining unit 304 is further configured to determine a maintenance time point of the target failure mode according to the first failure sample matrix;

[0192] The output unit 305 is used to output prompt information, where the prompt information includes information about the target failure mode and information about the maintenance time point.

[0193] In the embodiment of the present application, the acquisition unit 301 acquires the first operating condition data and state data for the calculation unit 302 to calculate the predicted value of the target measuring point. When the difference between the actual value of the target measuring point and the predicted value is greater than the alarm threshold, the processing unit 303 sends out a warning signal and acquires the second operating condition data and the first historical data within a preset time period before the fault warning moment. Then the determination unit 304 determines the target fault mode according to the second operating condition data and the first historical data, the acquisition unit 301 acquires the first fault sample matrix of the target fault mode, and then determines the maintenance time point of the target fault mode, and the output unit 305 outputs prompt information. When there is a sign of a fault, it can be warned, a warning signal can be issued, and then the possible target fault mode and the corresponding maintenance time point can be prompted, so that a reasonable maintenance plan can be formulated, which brings great convenience to the user.

[0194] The functions and processes performed by each unit in the data processing device of this embodiment are similar to those described above. Figure 1 to Figure 2 The functions and processes performed by the data processing device are similar and will not be repeated here.

[0195] Figure 4 It is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application. The data processing device 400 may include one or more central processing units (CPU) 401 and a memory 405. The memory 405 stores one or more application programs or data.

[0196] The memory 405 may be a volatile storage or a persistent storage. The program stored in the memory 405 may include one or more modules, each of which may include a series of instruction operations in the data processing device 400. Furthermore, the central processing unit 401 may be configured to communicate with the memory 405 and execute a series of instruction operations in the memory 405 on the data processing device 400.

[0197] The data processing device 400 may also include one or more power supplies 402, one or more wired or wireless network interfaces 403, one or more input and output interfaces 404, and / or one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0198] The CPU 401 can execute the aforementioned Figure 1 to Figure 2The operations performed by the data processing device in the illustrated embodiment will not be described in detail herein.

[0199] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0200] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0201] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0202] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0203] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), disk or optical disk and other media that can store program code.

Claims

1. A data processing method for a gear transmission, characterized in that: include: Acquire first operating condition data and state data, wherein the first operating condition data includes time series data of a measuring point on a power input side and time series data of a measuring point on a load output side, and the state data includes time series data of a measuring point on a gear transmission body side; Calculate a predicted value of a target measuring point according to the first operating condition data and the state data; When the difference between the actual value of the target measuring point and the predicted value of the target measuring point is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are obtained, the actual value of the target measuring point is a part of the first operating condition data, the second operating condition data is the time series data of the power input side and the load output side, the first historical data is the time domain data of the operating parameters of each bearing, each shaft system and each group of meshing gears of the gear transmission, and the alarm threshold is a preset value; determining a target failure mode according to the second operating condition data and the first historical data; Acquire a first fault sample matrix of the target fault mode; Determine a maintenance time point of the target failure mode according to the first failure sample matrix; Outputting prompt information, wherein the prompt information includes information about the target failure mode and information about the maintenance time point; The determining the maintenance time point of the target failure mode according to the first failure sample matrix includes: Normalizing the first fault sample matrix to obtain a third fault sample matrix, wherein the first fault sample matrix is ​​a matrix of time series data of the target fault mode in the warning sample matrix; Classifying the third fault sample matrix by using a clustering model to obtain classified sample data; Analyzing the classified sample data by a regression model to determine a second mathematical relationship between the target measuring point and all measuring points except the target measuring point; Calculate the predicted value of the target measuring point by using the second mathematical relationship and the sample data of all measuring points except the target measuring point; A time point corresponding to a minimum value among the predicted values ​​that are greater than or equal to the expected value is determined as a maintenance time point, and the expected value is a preset value for distinguishing the state of the gear transmission.

2. The data processing method according to claim 1, characterized in that: Calculating a predicted value of a target measuring point according to the first operating condition data and the state data includes: Eliminating abnormal values ​​from the first operating condition data to obtain third operating condition data; Performing a transformation between the time domain and the frequency domain on the state data to obtain first frequency domain data of the state data; Calculate the frequency band factors of the bearings, shaft system and meshing gears of the gear transmission respectively according to the first frequency domain data; Normalizing the third operating condition data to obtain fourth operating condition data; Performing dimension reduction on the fourth operating condition data and the frequency band factor to obtain a dimension reduction feature vector; Establishing a high-dimensional feature space through the dimension-reduced feature vector, wherein the high-dimensional feature space is a matrix of time series data including state information; Classifying the time series data in the high-dimensional feature space by a clustering model to obtain time series data of different categories, wherein each category of time series data represents an operating state of the gear transmission; Analyze the time segments of the time series data under each category through a regression model to determine a first mathematical relationship between a target measuring point and all measuring points except the target measuring point; The predicted value of the target measuring point is calculated through the first mathematical relationship and the time series data of all measuring points except the target measuring point.

3. The data processing method according to claim 2, characterized in that: After calculating the predicted value of the target measuring point through the mathematical relationship and the time series data of all measuring points except the target measuring point, the method further includes: If there are multiple clustering models and multiple regression models, respectively, the clustering models and the regression models are evaluated to select the optimal clustering model and the optimal regression model; Filtering out target prediction values ​​corresponding to the optimal clustering model and the optimal regression model from the prediction values; When the difference between the actual value of the target measuring point and the predicted value of the target measuring point is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are obtained, including: When the difference between the actual value of the target measurement point and the target predicted value is greater than the alarm threshold, a warning signal is issued and the second operating condition data and the first historical data within a preset time period before the fault warning moment are acquired.

4. The data processing method according to claim 1, characterized in that: Determining a target failure mode according to the second operating condition data and the first historical data includes: Performing a transformation between the time domain and the frequency domain on the first historical data to obtain second frequency domain data; Calculate, based on the second frequency domain data, a first change rate of an operating parameter of each bearing, each shaft system, and each set of meshing gears and a first statistical characteristic value of an operating parameter of each bearing, each shaft system, and each set of meshing gears; Classifying first input data by a clustering model to obtain warning sample data, wherein the first input data includes the second operating condition data, the first change rate, and the first statistical characteristic value; Establishing a warning sample matrix through the warning sample data, wherein the row vector of the warning sample matrix includes the first statistical eigenvalue and the first change rate; Calculating the state eigenvector of the 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 representing a fault mode; The fault mode corresponding to the candidate feature vector with the maximum similarity value is determined as the target fault mode, and the maximum similarity value is the maximum value among the multiple similarity values.

5. The data processing method according to claim 4, characterized in that: Before performing a transformation between the time domain and the frequency domain on the first historical data to obtain the second frequency domain data, the method further includes: Acquire fifth operating condition data and second historical data characterizing historical faults, wherein the fifth operating condition data includes time series data of operating parameters on the power input side and time series data of operating parameters on the load output side, and the second historical data is second time domain data characterizing multiple faults of the gear transmission; Eliminating abnormal values ​​from the fifth operating condition data to obtain sixth operating condition data; converting the second historical data into second frequency domain data; Calculating a second change rate of the operating parameters of each bearing, each shaft system, and each set of meshing gears and a second statistical characteristic value of the operating parameters of each bearing, each shaft system, and each set of meshing gears based on the second frequency domain data; Performing fault mode classification on the second input data through a clustering model to obtain fault sample data of each fault set, wherein the second input data includes the sixth operating condition data, the second change rate and the second statistical characteristic value; Establishing a plurality of second fault sample matrices of a plurality of fault modes through the fault sample data of each fault set, wherein the row vector of each fault sample matrix includes a second statistical characteristic value and a second change rate corresponding to each fault mode; A plurality of candidate eigenvectors of the second fault sample matrix are calculated.

6. The data processing method according to claim 5, characterized in that: Converting the second historical data into second frequency domain data includes: Converting the second historical data into second frequency domain data by fast Fourier transform; or, The second historical data is converted into second frequency domain data by discrete Fourier transform.

7. A data processing device, characterized in that: include: An acquisition unit, used to acquire first operating condition data and state data, wherein the first operating condition data includes time series data of a measuring point on a power input side and time series data of a measuring point on a load output side, and the state data includes time series data of a measuring point on a gear transmission body side; a calculation unit, configured to calculate a predicted value of a target measuring point according to the first operating condition data and the state data; a processing unit, configured to, when a difference between an actual value of the target measuring point and a predicted value of the target measuring point is greater than an alarm threshold, issue an early warning signal and obtain second operating condition data and first historical data within a preset time period before a fault early warning moment, wherein the actual value of the target measuring point is a part of the first operating condition data, the second operating condition data is time series data of a power input side and a load output side, the first historical data is time domain data of operating parameters of each bearing, each shaft system, and each group of meshing gears of a gear transmission, and the alarm threshold is a preset value; a determination unit, configured to determine a target fault mode according to the second operating condition data and the first historical data; The acquisition unit is further used to acquire a first fault sample matrix of the target fault mode; The determining unit is further configured to determine a maintenance time point of the target failure mode according to the first failure sample matrix; An output unit, used to output prompt information, wherein the prompt information includes information about the target failure mode and information about the maintenance time point; The determining unit is specifically configured to: Normalizing the first fault sample matrix to obtain a third fault sample matrix, wherein the first fault sample matrix is ​​a matrix of time series data of the target fault mode in the warning sample matrix; Classifying the third fault sample matrix by using a clustering model to obtain classified sample data; Analyzing the classified sample data by a regression model to determine a second mathematical relationship between the target measuring point and all measuring points except the target measuring point; Calculate the predicted value of the target measuring point by using the second mathematical relationship and the sample data of all measuring points except the target measuring point; A time point corresponding to a minimum value among the predicted values ​​that are greater than or equal to the expected value is determined as a maintenance time point, and the expected value is a preset value for distinguishing the state of the gear transmission.

8. A data processing device, characterized in that: include: CPU, memory and input / output interface; The memory is a transient storage memory or a persistent storage memory; The central processing unit is configured to communicate with the memory and execute instructions in the memory to perform the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The method comprises instructions, which, when executed on a computer, cause the computer to execute the method according to any one of claims 1 to 6.

Images