A method and system for diagnosing engine vibration faults based on over-criticality characteristics

Abstract

The present invention belongs to the technical field of engine fault diagnosis. It provides a method and system for diagnosing complete engine vibration faults based on over-criticality characteristics. The method comprises: during an operation monitoring cycle, using a laser vibrometer to monitor the engine in real time while in operation to obtain operation amplitude data; performing a phase difference analysis on multiple adjacent monitoring points within the engine based on the operation amplitude data; and obtaining a shaft system fault diagnosis value in combination with the operation amplitude data. The method then performs engine fault diagnosis based on the degree of difference between the corresponding phases and amplitudes of adjacent monitoring points, thereby identifying not only whether an engine fault has occurred but also the type of engine fault, thereby improving the diagnostic accuracy of engine vibration faults.

Description

Technical Field

[0001] The present invention belongs to the technical field of engine fault diagnosis, and in particular relates to a method and system for diagnosing engine whole machine vibration faults based on over-criticality characteristics. Background Art

[0002] Vibration failure of the entire engine is one of the common problems of the engine. Traditional fault diagnosis methods often rely on single parameter analysis, such as judging the fault only by the vibration amplitude. The diagnostic accuracy is low, and it is difficult to accurately identify the fault type and locate the fault location.

[0003] In the existing technology, most of them rely on a single parameter or simple analysis means, such as judging the fault only by the vibration amplitude. The diagnostic accuracy is poor, and it is impossible to effectively distinguish different types of faults, and it is difficult to accurately locate the location of the fault. Therefore, the present application solves the problem of how to accurately identify the type of shaft system angle misalignment fault by analyzing the relationship between the shaft rotation frequency and the phase difference frequency, and the periodicity of the phase difference when the engine shaft system fails. It improves the accuracy of engine vibration fault diagnosis, and further identifies the type of engine fault, providing data support for subsequent maintenance personnel to perform targeted repairs, speeding up the efficiency of engine fault repair, and further determining key critical characteristics.

[0004] To this end, the present invention provides a method and system for diagnosing engine vibration faults based on over-criticality characteristics. Summary of the Invention

[0005] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0006] The technical solution adopted by the present invention to solve its technical problem is:

[0007] In a first aspect, a method for diagnosing engine vibration faults based on over-criticality characteristics comprises the following steps:

[0008] During the operation monitoring cycle, the laser vibrometer is used to monitor the engine in real time during operation to obtain the operation amplitude data;

[0009] Based on the operating amplitude data, the phases of multiple monitoring points in the engine are obtained, and the phase difference between adjacent monitoring points is analyzed. Combined with the operating amplitude data, the engine shaft system is evaluated for faults.

[0010] If the engine shaft system fails, the shaft rotation frequency is obtained through the speed sensor, and the correlation between it and the phase difference frequency is analyzed to determine whether the phase difference changes periodically and identify the type of shaft system failure;

[0011] The diagnosis results of multiple shafting fault types are recorded and compared with the actual diagnosis results of the corresponding maintenance personnel to evaluate whether the diagnosis results of the shafting fault types are accurate and obtain key critical features.

[0012] As a further solution of the present invention, the process of obtaining the amplitude data is as follows:

[0013] Divide the operation monitoring cycle equally into several monitoring nodes;

[0014] The engine surface is evenly divided into several monitoring points. The operating amplitude of each monitoring point at each monitoring node is obtained using a laser vibrometer, and the data are sorted according to the time series and integrated into the operating amplitude data.

[0015] As a further solution of the present invention, the phase of the monitoring point is obtained, and the process is as follows:

[0016] With the X-axis as time and the Y-axis as amplitude, an operating amplitude change curve is constructed based on the operating amplitude data, and all peaks in the operating amplitude change curve are extracted;

[0017] The time difference between the monitoring nodes corresponding to adjacent peaks is obtained respectively, and the phase of the monitoring point is obtained through the phase acquisition formula.

[0018] As a further solution of the present invention, the phase difference analysis of adjacent monitoring points is carried out as follows:

[0019] Based on the same time series, the phases of the monitoring points corresponding to adjacent monitoring points are processed by the Manhattan distance formula, and the phase difference value is output.

[0020] As a further solution of the present invention, the operating amplitude data is combined to evaluate whether the engine shaft system has a fault. The process is as follows:

[0021] Extract all the running amplitudes in the running amplitude data corresponding to the monitoring points, and combine the running amplitudes corresponding to different monitoring points in the same monitoring node to obtain multiple amplitude analysis groups. Then process them using the Manhattan distance formula to output the amplitude difference value.

[0022] The phase difference values ​​and amplitude difference values ​​corresponding to adjacent monitoring points are input into the geometric product model, and the mean is calculated to obtain the shafting fault diagnosis value. If the shafting fault diagnosis value is greater than the shafting fault diagnosis threshold, a shafting fault signal is generated.

[0023] As a further solution of the present invention, the speed sensor obtains the shaft rotation frequency, and the process is as follows:

[0024] According to the frequency of the alternating signal output by the electromagnetic induction stator and the magnetoelectric speed sensor, the shaft rotation frequency is calculated using the shaft rotation frequency formula during the operation monitoring period.

[0025] As a further solution of the present invention, the correlation between the shaft rotation frequency and the phase difference frequency is analyzed, and the process is as follows:

[0026] Count multiple phase differences corresponding to adjacent monitoring points, with the X-axis as time and the Y-axis as phase difference, to construct a phase difference change curve;

[0027] On the phase difference variation curve, extract the phase difference peaks respectively;

[0028] All phase difference frequencies and shaft rotation frequencies are sorted according to time series to obtain phase difference frequency sequence and shaft rotation frequency sequence;

[0029] All phase difference frequencies in the phase difference frequency sequence and all shaft rotation frequencies in the shaft rotation frequency sequence are input into the Pearson correlation coefficient improved model respectively, and the frequency correlation coefficient is output;

[0030] If the frequency correlation coefficient is less than or equal to the frequency correlation standard coefficient, the correlation between the shaft rotation frequency and the phase difference frequency is relatively close.

[0031] As a further solution of the present invention, it is to determine whether the phase difference changes periodically and identify the type of shaft system fault. The process is as follows:

[0032] If the correlation between the shaft rotation frequency and the phase difference frequency is relatively close, then all shaft rotation frequencies are averaged and the inverse is taken to obtain the shaft rotation period;

[0033] Based on the duration corresponding to the axis rotation period, the phase difference change curve is divided to obtain several period analysis curves. The starting point coordinates and the end point coordinates corresponding to the period analysis curves are obtained respectively, and the period analysis fitting line is obtained by fitting using the least squares method. The starting point coordinates and the end point coordinates are used to calculate the slope of the period analysis fitting line using the slope calculation formula.

[0034] Arbitrarily combine the slopes of adjacent cycle analysis fitting lines and input them into the Manhattan distance formula to output the cycle trend analysis value;

[0035] After inputting the starting point Y coordinate and the ending point Y coordinate corresponding to all periodic analysis curves into the Manhattan distance formula, the periodic deviation analysis value is obtained;

[0036] The period trend analysis value and the period deviation analysis value are calculated by geometric product method to obtain the period determination value;

[0037] If the period determination value is less than or equal to the period determination threshold, the shaft misalignment fault type is determined to be angular misalignment.

[0038] As a further solution of the present invention, it is determined whether the phase difference is a critical feature, and the process is as follows:

[0039] The diagnosis results of multiple shaft fault types and the corresponding actual diagnosis results are sorted according to the diagnosis time series, and the diagnosis result sequence and the actual diagnosis result sequence are constructed respectively;

[0040] A diagnosis result is randomly extracted from the diagnosis result sequence, and an actual diagnosis result is correspondingly extracted from the actual diagnosis result sequence, and the results are combined to obtain multiple diagnosis result comparison groups. The proportion of the number of diagnosis result overlapping groups to the total number of diagnosis result groups is obtained to obtain the diagnosis result overlapping ratio. If the diagnosis result overlapping ratio is greater than the diagnosis result overlapping ratio threshold, the phase difference is recorded as a key over-critical feature.

[0041] In a second aspect, an engine vibration fault diagnosis system based on over-criticality characteristics includes:

[0042] Amplitude data acquisition module: During the operation monitoring cycle, the laser vibrometer is used to monitor the engine in real time and obtain the operation amplitude data;

[0043] Fault diagnosis and analysis module: Based on the operating amplitude data, the module obtains the phases of multiple monitoring points within the engine, analyzes the phase differences between adjacent monitoring points, and combines the operating amplitude data to assess whether the engine shaft system has a fault.

[0044] Shaft fault identification module: If the engine shaft fault occurs, the shaft rotation frequency is obtained through the speed sensor, and the correlation between the rotation frequency and the phase difference frequency is analyzed to determine whether the phase difference changes periodically and identify the type of shaft fault.

[0045] Key feature screening module: records the diagnosis results of multiple shaft system fault types and compares them with the actual diagnosis results of the corresponding maintenance personnel to evaluate whether the diagnosis results of the shaft system fault types are accurate and obtain key critical features.

[0046] The beneficial effects of the present invention are as follows:

[0047] 1. During the operation monitoring cycle, the present invention uses a laser vibrometer to perform real-time monitoring of the running engine, obtaining operating amplitude data. Based on this operating amplitude data, the phase differences of multiple adjacent monitoring points within the engine are analyzed. Combined with the operating amplitude data, a shafting fault diagnosis value is obtained. Based on the differences in the corresponding phases and amplitudes at adjacent monitoring points, engine fault diagnosis is performed. This not only identifies whether an engine fault has occurred, but also further identifies the type of engine fault, thereby improving the diagnostic accuracy of engine vibration faults.

[0048] 2. The present invention uses a magnetoelectric constant-speed sensor to calculate the shaft rotation frequency, and simultaneously constructs a curve by statistically analyzing the phase difference between adjacent monitoring points and calculating the phase difference frequency. The Pearson correlation coefficient is then used to improve the model and analyze the correlation between the two. If the correlation is close, the phase difference curve is divided according to the shaft rotation period. The period determination value is obtained by calculating the slope of the fitting line, the trend analysis value, and the deviation analysis value, thereby identifying whether the shaft system fault is angular misalignment. This solves the problem of how to accurately identify the type of shaft system angular misalignment fault by analyzing the relationship between the shaft rotation frequency and the phase difference frequency and the periodicity of the phase difference when an engine shaft system fault occurs. This improves the accuracy of engine vibration fault diagnosis, provides data support for subsequent maintenance personnel to perform targeted repairs, and accelerates the efficiency of engine fault repair.

[0049] 3. The present invention compares the diagnosis results of multiple shaft system fault types with the actual diagnosis results detected by the corresponding maintenance personnel to obtain a diagnosis result overlap group and a diagnosis result non-overlap group. If the diagnosis result overlap group is smaller than the result non-overlap group, it indicates whether there is periodicity through the phase difference change, and the diagnosis result accuracy of the engine shaft system fault type is low. If the diagnosis result overlap group is larger than the result non-overlap group, it indicates whether there is periodicity through the phase difference change, and the diagnosis result accuracy of the engine shaft system fault type is high. The phase difference is a key over-critical feature, which can not only identify whether there is periodicity in the phase difference change, but also the accuracy of the diagnosis result of the engine shaft system fault type can be provided for subsequent diagnosis, thereby improving the efficiency of engine diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The present invention will be further described below with reference to the accompanying drawings.

[0051] Figure 1 This is a flowchart of the steps of a method for diagnosing engine vibration faults based on over-criticality characteristics of the present invention;

[0052] Figure 2 The present invention is a schematic diagram of an engine vibration fault diagnosis system based on over-criticality characteristics. DETAILED DESCRIPTION

[0053] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0054] Example 1:

[0055] See also Figure 1 As shown, an embodiment of the present invention provides a method for diagnosing engine vibration faults based on over-critical characteristics, wherein the over-critical characteristics include amplitude, vibration phase difference, vibration frequency, and rotational speed. Since different types of faults may cause engine vibration to exhibit different characteristics in amplitude and phase, combining the amplitude and phase difference to diagnose the engine vibration fault is beneficial for identifying the vibration fault type while identifying the engine vibration fault. This not only improves the diagnostic accuracy of the engine vibration fault, but also improves the subsequent maintenance efficiency of the vibration fault based on the identification of the vibration fault type. The method includes the following steps:

[0056] Step 1: During the operation monitoring period, the laser vibrometer is used to monitor the engine in real time to obtain the operating amplitude data.

[0057] In a preferred embodiment, the engine surface is evenly divided into several monitoring points;

[0058] It should be noted that the distances between adjacent monitoring points are equal;

[0059] The laser vibrometer is used to monitor the engine in real time during operation. The process is as follows:

[0060] A laser vibrometer is used to transmit laser light to any monitoring point on the surface of the running engine. Due to the principle of laser interference, the frequency of the reflected laser light will change due to the vibration of the running engine, thus obtaining the running amplitude.

[0061] It should be noted that when using a laser vibrometer to emit laser light to any monitoring point on the surface of an operating engine, the purpose is to: since the engine surface is evenly divided into several monitoring points, the amplitude changes or phase difference changes at different monitoring points during the operating monitoring cycle can be compared to improve the accuracy of engine fault diagnosis and provide data support for diagnosing engine faults;

[0062] Divide the operation monitoring cycle equally into several monitoring nodes;

[0063] It should be noted that the time intervals between adjacent monitoring nodes are equal;

[0064] Obtain the monitoring nodes corresponding to each operating amplitude, sort them according to the time series, and integrate them into operating amplitude data;

[0065] Step 2: Based on the operating amplitude data, obtain the phases of multiple monitoring points in the engine, analyze the phase differences between adjacent monitoring points, and combine the operating amplitude data to assess whether the engine shaft system has a fault;

[0066] In a preferred embodiment, the X-axis is time and the Y-axis is amplitude. Based on the operating amplitude data, an operating amplitude change curve is constructed and analyzed using the peak value method. The process is as follows:

[0067] Extract all peaks or troughs in the running amplitude change curve;

[0068] For example, taking the peak as an example, the time difference between the monitoring nodes corresponding to adjacent peaks is obtained respectively, and the phase acquisition formula is used: , calculate the monitoring point phase ,in, It is expressed as the time difference between the monitoring nodes corresponding to adjacent peaks, It is expressed as the operation monitoring cycle;

[0069] Based on the same time series, the phases of the monitoring points corresponding to adjacent monitoring points are processed by the Manhattan distance formula, and the phase difference value is output. ;

[0070] It should be noted that, based on the same time series, the monitoring nodes corresponding to adjacent monitoring points are nodes A, B, and C respectively;

[0071] The phases of the adjacent monitoring points at the AB monitoring node and the BC monitoring node are processed by the Manhattan distance formula to obtain the phase difference value;

[0072] Specifically, the Manhattan distance formula is: ,in, It is represented as the phase of the pth monitoring point corresponding to one of the adjacent monitoring points. It is expressed as the phase of the pth monitoring point of another monitoring point teammate among the adjacent monitoring points. It is expressed as the total number of adjacent monitoring nodes;

[0073] Any monitoring point;

[0074] Extract all the running amplitudes in the running amplitude data corresponding to the monitoring point, and combine the running amplitudes corresponding to different monitoring points in the same monitoring node to obtain multiple amplitude analysis groups, and process them through the Manhattan distance formula to output the amplitude difference value ;

[0075] Specifically, the amplitude difference formula is: ,in, Expressed as the total number of amplitude analysis groups, Expressed as One of the running amplitudes in the amplitude analysis group, For the Another running amplitude within the amplitude analysis group;

[0076] It should be noted that the use of the Manhattan distance formula is:

[0077] Function 1: From the perspective of amplitude difference analysis, the amplitudes of the same monitoring node corresponding to adjacent monitoring points are processed to quantify the overall difference between the amplitudes of all monitoring points on the engine surface, thereby determining whether the engine is faulty.

[0078] Function 2: From the perspective of phase difference analysis, processing the phases corresponding to adjacent monitoring points can quantify the overall difference between the phases corresponding to all monitoring points on the engine surface. Based on the amplitude difference judgment, it can further determine whether the engine shaft system is faulty, thereby improving the accuracy of identifying the engine fault type and fault location.

[0079] The phase difference and amplitude difference values ​​corresponding to adjacent monitoring points are input into the geometric product model, and the mean is calculated to output the shafting fault diagnosis value.

[0080] It can be understood that the meaning of the shaft fault diagnosis value is: obtained by inputting the phase difference values ​​and adjacent amplitude difference values ​​corresponding to adjacent monitoring points into the geometric product model and performing mean calculation. Specifically, the phase difference value quantifies the degree of difference between the corresponding phases of adjacent monitoring points, while the adjacent amplitude difference value quantifies the degree of difference between the corresponding amplitudes of different monitoring points within the same monitoring node. Based on the two, not only whether the engine fault occurs can be identified, but also the type of engine fault can be further identified;

[0081] If the shafting fault diagnosis value is greater than the shafting fault diagnosis threshold, it means that the amplitude and phase differences between adjacent monitoring points are relatively obvious, and a shafting fault signal is generated;

[0082] If the shafting fault diagnosis value is less than or equal to the shafting fault diagnosis threshold, it means that the amplitude and phase differences between adjacent monitoring points are not obvious, and a shafting normal signal is generated;

[0083] The technical solution of the embodiment is as follows: during the operation monitoring cycle, a laser vibrometer is used to monitor the engine in the running state in real time to obtain operation amplitude data. Based on the operation amplitude data, a difference analysis is performed on the phases of multiple adjacent monitoring points in the engine. Combined with the operation amplitude data, a shaft system fault diagnosis value is obtained. The engine fault diagnosis is then performed based on the degree of difference between the corresponding phases of adjacent monitoring points and the degree of difference between the amplitudes. This not only identifies whether the engine has a fault, but also further identifies the type of engine fault, thereby improving the accuracy of the diagnosis of engine vibration faults.

[0084] Example 2:

[0085] See also Figure 1 As shown, a method for diagnosing engine vibration faults based on over-criticality characteristics according to an embodiment of the present invention includes the following steps:

[0086] Step 3: If the engine shaft system is faulty, the shaft rotation frequency is obtained through the speed sensor, and the correlation between the rotation frequency and the phase difference frequency is analyzed to determine whether the phase difference changes periodically and diagnose the type of shaft system fault.

[0087] In a preferred embodiment, the shaft rotation frequency is obtained by a speed sensor, and the process is as follows:

[0088] It should be noted that the speed sensor includes a magnetoelectric speed sensor, a Hall sensor or a photoelectric sensor;

[0089] For example, taking a magnetoelectric speed sensor as an example, according to the law of electromagnetic induction and the frequency of the alternating signal output by the magnetoelectric speed sensor, during the operation monitoring cycle, the shaft rotation frequency formula is: , calculate the shaft rotation frequency ,in, Expressed as the alternating signal frequency, Expressed as the total number of teeth on the sensing gear in the magnetoelectric speed sensor;

[0090] Count multiple phase differences corresponding to adjacent monitoring points, with the X-axis as time and the Y-axis as phase difference, to construct a phase difference change curve;

[0091] On the phase difference variation curve, extract the phase difference peak or phase difference trough respectively;

[0092] For example, taking the phase difference peak as an example, the interval time corresponding to adjacent difference peaks is extracted, averaged and then the inverse is taken to output the phase difference frequency;

[0093] Sort all phase difference frequencies according to the time series to obtain a phase difference frequency sequence;

[0094] Similarly, all axis rotation frequencies are sorted according to the time series to obtain the axis rotation frequency sequence;

[0095] The correlation degree between the phase difference frequency in the phase difference frequency sequence and the shaft rotation frequency in the shaft rotation frequency sequence is analyzed by using the improved model of Pearson correlation coefficient. The process is as follows:

[0096] A1, averages all phase difference frequencies in the phase difference frequency sequence and outputs the phase difference frequency mean;

[0097] The shaft system rotation frequency in the shaft system rotation frequency sequence is averaged and the output is the rotation frequency mean;

[0098] A2, input the phase difference frequency mean and the rotation frequency mean into the Pearson correlation coefficient improved model respectively, and output the frequency correlation coefficient ;

[0099] Specifically, the Pearson correlation coefficient improves the model: ,in, Expressed as the phase difference frequency mean, represents the e-th phase difference frequency in the phase difference frequency sequence, Expressed as the mean rotation frequency, It is expressed as the e-th axis rotation frequency in the axis rotation frequency sequence;

[0100] It should be noted that since the Pearson correlation coefficient is In the range, if the Pearson correlation coefficient is close to 0, it means that the correlation is not close. If the Pearson correlation coefficient is close to 1 or -1, it means that the correlation is close. Therefore, the Pearson correlation coefficient is processed in absolute value. If the Pearson correlation coefficient is close to 1 or -1, the frequency correlation coefficient obtained by the improved model based on the Pearson correlation coefficient is The smaller it is, the closer the correlation between the axis rotation frequency and the phase difference frequency is. If the Pearson correlation coefficient is close to 0, the larger the frequency correlation coefficient obtained by the improved model based on the Pearson correlation coefficient is, the less close the correlation between the axis rotation frequency and the phase difference frequency is.

[0101] If the frequency correlation coefficient If it is greater than the frequency correlation standard coefficient, it means that the correlation between the shaft rotation frequency and the phase difference frequency is not close;

[0102] If the frequency correlation coefficient If it is less than or equal to the frequency correlation standard coefficient, it means that the correlation between the shaft rotation frequency and the phase difference frequency is relatively close. Then, after averaging all the shaft rotation frequencies, the reciprocal is taken to obtain the shaft rotation period.

[0103] Based on the duration corresponding to the axis rotation period, the phase difference variation curve is divided to obtain several period analysis curves;

[0104] Randomly select a periodic analysis curve, obtain the starting point coordinates and end point coordinates corresponding to the periodic analysis curve, and fit it using the least squares method to obtain the periodic analysis fitting line. Use the slope calculation formula to calculate the starting point coordinates and end point coordinates to obtain the slope of the periodic analysis fitting line.

[0105] Arbitrarily combine the slopes of adjacent cycle analysis fitting lines and input them into the Manhattan distance formula to output the cycle trend analysis value;

[0106] After inputting the starting point Y coordinate and the ending point Y coordinate corresponding to all periodic analysis curves into the Manhattan distance formula, the periodic deviation analysis value is obtained;

[0107] The period trend analysis value and the period deviation analysis value are calculated by geometric product method to obtain the period determination value;

[0108] It can be understood that the meaning of the period determination value is: a value obtained by comprehensively considering the slope change of the period analysis curve (reflected by the period trend analysis value) and the amplitude of the phase difference change within a period (reflected by the period deviation analysis value), and is used to comprehensively judge the periodic characteristics of the phase difference change curve;

[0109] The period determination value is compared with the period determination threshold value. The process is as follows:

[0110] If the period determination value is greater than the period determination threshold, it means that the phase difference change does not have periodicity within the shaft rotation period, and a phase difference aperiodic signal is generated;

[0111] If the period determination value is less than or equal to the period determination threshold, it means that the phase difference change is periodic within the shaft rotation period, and a phase difference period signal is generated, and the shaft misalignment fault type is determined to be angular misalignment;

[0112] The specific implementation plan of this embodiment is: use a magnetoelectric constant speed sensor to calculate the shaft rotation frequency, and at the same time, count the phase differences of adjacent monitoring points to construct a curve and calculate the phase difference frequency. Then use the Pearson correlation coefficient to improve the model to analyze the correlation between the two. If the correlation is close, divide the phase difference curve according to the shaft rotation period. By calculating the slope of the fitting line, the trend analysis value, and the deviation analysis value, the period judgment value is obtained, so as to identify whether the shaft system fault is angular misalignment. This solves the problem of how to accurately identify the type of shaft system angular misalignment fault by analyzing the relationship between the shaft rotation frequency and the phase difference frequency and the periodicity of the phase difference when the engine shaft system fails. It improves the accuracy of engine vibration fault diagnosis, provides data support for subsequent maintenance personnel to perform targeted maintenance, and speeds up the efficiency of engine fault repair.

[0113] Example 3:

[0114] The method for diagnosing an engine vibration fault based on a transcritical characteristic according to an embodiment of the present invention further includes the following steps:

[0115] Step 4: Record the diagnosis results of multiple shaft fault types and compare them with the actual diagnosis results of the corresponding maintenance personnel to determine whether the phase difference is a critical feature;

[0116] Among them, the diagnosis results include angular misalignment or parallel misalignment;

[0117] Exemplarily, multiple diagnosis results of shaft system fault types are sorted according to the time series of each diagnosis to obtain a diagnosis result sequence;

[0118] For example, the sequence of diagnostic results may be: diagnose angular misalignment, diagnose angular misalignment, diagnose parallel misalignment, diagnose angular misalignment, diagnose parallel misalignment;

[0119] Similarly, the actual diagnosis results of multiple corresponding maintenance personnel are sorted according to the time sequence of each actual detection to obtain the actual diagnosis result sequence;

[0120] For example, the sequence of actual diagnosis results can be actual diagnosis angle misalignment, actual diagnosis parallel misalignment, actual diagnosis parallel misalignment, actual diagnosis angle misalignment, actual diagnosis angle misalignment;

[0121] Randomly extract a diagnosis result from the diagnosis result sequence, and extract a corresponding actual diagnosis result from the actual diagnosis result sequence, and combine them to obtain multiple diagnosis result comparison groups;

[0122] It should be noted that the method of extracting combinations as diagnostic result comparison groups is: extracting combinations according to the order of the results in the diagnostic result sequence and the actual diagnosis result sequence, and the number of results in the diagnostic result sequence and the actual diagnosis result sequence is consistent, and the number of results is an odd number;

[0123] For example, the diagnostic angle misalignment and the actual diagnostic angle misalignment form a diagnostic result comparison group, the diagnostic angle misalignment and the actual diagnostic parallel misalignment form a diagnostic result comparison group, the diagnostic parallel misalignment and the actual diagnostic angle misalignment form a diagnostic result comparison group, and the diagnostic parallel misalignment and the actual diagnostic angle misalignment form a diagnostic result comparison group.

[0124] Based on multiple diagnostic result comparison groups, if the diagnostic result within the diagnostic result comparison group is consistent with the actual diagnosis result, the diagnostic result overlap group is recorded;

[0125] If the diagnosis result within the comparison group is inconsistent with the actual diagnosis result, it will be recorded as a non-overlapping diagnosis result group;

[0126] Count the number of groups with overlapping diagnostic results, calculate the ratio with the total number of diagnostic result groups, and output the overlapping ratio of diagnostic results;

[0127] If the diagnostic result overlap ratio is greater than the diagnostic result overlap ratio threshold, it indicates whether there is periodicity in the phase difference change, and the diagnostic result accuracy of the engine shaft fault type is high, and the phase difference is a key over-critical feature;

[0128] If the diagnostic result overlap ratio is less than or equal to the diagnostic result overlap ratio threshold, it indicates whether there is periodicity in the phase difference change, and the diagnostic result accuracy of the engine shaft system fault type is low, and the phase difference is a non-critical over-critical feature;

[0129] The technical solution of this embodiment is: comparing the diagnosis results of multiple shaft system fault types with the actual diagnosis results detected by the corresponding maintenance personnel to obtain a diagnosis result overlap group and a diagnosis result non-overlap group. If the diagnosis result overlap ratio is less than or equal to the diagnosis result overlap ratio threshold, it indicates whether there is periodicity through the phase difference change, and the diagnosis result accuracy of the engine shaft system fault type is low. If the diagnosis result overlap ratio is greater than the diagnosis result overlap ratio threshold, it indicates whether there is periodicity through the phase difference change, and the diagnosis result accuracy of the engine shaft system fault type is high. The phase difference is a key over-critical feature, which can not only identify whether there is periodicity in the phase difference change, but also the accuracy of the diagnosis result of the engine shaft system fault type can be provided for subsequent diagnosis, thereby improving the efficiency of engine diagnosis.

[0130] Example 4:

[0131] like Figure 2 As shown, an engine vibration fault diagnosis system based on over-criticality characteristics according to an embodiment of the present invention includes the following modules:

[0132] Amplitude data acquisition module: During the operation monitoring cycle, the laser vibrometer is used to monitor the engine in real time and obtain the operation amplitude data;

[0133] Fault diagnosis and analysis module: Based on the operating amplitude data, the module obtains the phases of multiple monitoring points within the engine, analyzes the phase differences between adjacent monitoring points, and combines the operating amplitude data to assess whether the engine shaft system has a fault.

[0134] Shaft fault identification module: If the engine shaft fault occurs, the shaft rotation frequency is obtained through the speed sensor, and the correlation between the rotation frequency and the phase difference frequency is analyzed to determine whether the phase difference changes periodically and identify the type of shaft fault.

[0135] Key feature determination module: records the diagnosis results of multiple shaft fault types and compares them with the actual diagnosis results of the corresponding maintenance personnel to determine whether the phase difference is a key critical feature.

[0136] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for diagnosing engine vibration faults based on over-criticality characteristics, characterized by: include: During the operation monitoring cycle, the laser vibrometer is used to monitor the engine in real time during operation to obtain the operation amplitude data; Based on the operating amplitude data, the phases of multiple monitoring points in the engine are obtained, and the phase difference between adjacent monitoring points is analyzed. Combined with the operating amplitude data, the engine shaft system is evaluated for faults. If the engine shaft system fails, the shaft rotation frequency is obtained through the speed sensor, and the correlation between it and the phase difference frequency is analyzed to determine whether the phase difference changes periodically and identify the type of shaft system failure; The diagnosis results of multiple shafting fault types are recorded and compared with the actual diagnosis results of the corresponding maintenance personnel to evaluate whether the diagnosis results of the shafting fault types are accurate and obtain key critical features.

2. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 1, characterized in that: The process of obtaining running amplitude data is as follows: Divide the operation monitoring cycle equally into several monitoring nodes; The engine surface is evenly divided into several monitoring points, and the operating amplitudes of the monitoring points at the monitoring nodes are obtained. These points are sorted according to the time series and integrated into the operating amplitude data.

3. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 1, characterized in that: To obtain the phase of the monitoring point, the process is as follows: Based on the operating amplitude data, the operating amplitude change curve is constructed, and all peaks are extracted. The time difference between the monitoring nodes corresponding to adjacent peaks is obtained respectively, and the phase of the monitoring point is obtained through the phase acquisition formula.

4. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 3, characterized in that: The process of analyzing the phase difference between adjacent monitoring points is as follows: Based on the same time series, the monitoring point phases corresponding to adjacent monitoring points are input into the Manhattan distance formula, and the phase difference value is output.

5. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 1, characterized in that: Combined with the operating amplitude data, the process of evaluating whether the engine shaft system has a fault is as follows: Extract all the running amplitudes in the running amplitude data corresponding to the monitoring point, extract the running amplitudes of different monitoring points in the same monitoring node period and combine them to obtain multiple amplitude analysis groups, and process them using the Manhattan distance formula to output the amplitude difference value; The phase difference and amplitude difference values ​​corresponding to adjacent monitoring points are input into the geometric product model, and the mean is calculated to obtain the shafting fault diagnosis value. If it is greater than the shafting fault diagnosis threshold, a shafting fault signal is generated.

6. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 1, characterized in that: The speed sensor obtains the shaft rotation frequency. The process is as follows: According to the law of electromagnetic induction and the frequency of the alternating signal output by the magnetoelectric speed sensor, the shaft rotation frequency is calculated using the shaft rotation frequency formula during the operation monitoring period.

7. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 1, characterized in that: Analyze the correlation between the shaft rotation frequency and the phase difference frequency. The process is as follows: Count the multiple phase differences corresponding to adjacent monitoring points, construct a phase difference change curve, extract the interval time between all adjacent phase difference peaks, perform averaging processing and take the inverse to obtain the phase difference frequency; All phase difference frequencies and shaft rotation frequencies are sorted according to time series to obtain phase difference frequency sequence and shaft rotation frequency sequence; All phase difference frequencies in the phase difference frequency sequence and all shaft rotation frequencies in the shaft rotation frequency sequence are input into the Pearson correlation coefficient improved model respectively, and the frequency correlation coefficient is output; If the frequency correlation coefficient is less than or equal to the frequency correlation standard coefficient, the correlation between the shaft rotation frequency and the phase difference frequency is relatively close.

8. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 7, characterized in that: Determine whether the phase difference changes periodically and identify the type of shafting fault. The process is as follows: If the correlation between the shaft rotation frequency and the phase difference frequency is relatively close, then all shaft rotation frequencies are averaged and the inverse is taken to obtain the shaft rotation period; The phase difference variation curve is divided based on the duration corresponding to the axis rotation period, and fitted using the least squares method to obtain multiple period analysis fitting lines and the slopes of the period analysis fitting lines. Input the slopes of all adjacent cycle analysis fitting lines into the Manhattan distance formula, and output the cycle trend analysis value; After inputting the starting point Y coordinate and the ending point Y coordinate corresponding to all periodic analysis curves into the Manhattan distance formula, the periodic deviation analysis value is obtained; The period trend analysis value and the period deviation analysis value are calculated by geometric product method to obtain the period determination value; If the period determination value is less than or equal to the period determination threshold, the shaft misalignment fault type is determined to be angular misalignment.

9. The method for diagnosing engine vibration faults based on over-criticality characteristics according to claim 1, characterized in that: To determine whether the phase difference is a critical feature, the process is as follows: The diagnosis results of multiple shaft fault types and the corresponding actual diagnosis results are sorted according to the diagnosis time series, and the diagnosis result sequence and the actual diagnosis result sequence are constructed respectively; A diagnosis result is randomly extracted from the diagnosis result sequence, and an actual diagnosis result is correspondingly extracted from the actual diagnosis result sequence, and the results are combined to obtain multiple diagnosis result comparison groups. The proportion of the number of diagnosis result overlapping groups to the total number of diagnosis result groups is obtained to obtain the diagnosis result overlapping ratio. If the diagnosis result overlapping ratio is greater than the diagnosis result overlapping ratio threshold, the phase difference is recorded as a key over-critical feature.

10. An engine vibration fault diagnosis system based on over-criticality characteristics, characterized by: Includes the following modules: Amplitude data acquisition module: During the operation monitoring cycle, the laser vibrometer is used to monitor the engine in real time and obtain the operation amplitude data; Fault diagnosis and analysis module: Based on the operating amplitude data, the module obtains the phases of multiple monitoring points within the engine, analyzes the phase differences between adjacent monitoring points, and combines the operating amplitude data to assess whether the engine shaft system has a fault. Shaft fault identification module: If the engine shaft fault occurs, the shaft rotation frequency is obtained through the speed sensor, and the correlation between the rotation frequency and the phase difference frequency is analyzed to determine whether the phase difference changes periodically and identify the type of shaft fault. Key feature screening module: records the diagnosis results of multiple shaft fault types and compares them with the actual diagnosis results of the corresponding maintenance personnel to determine whether the phase difference is a key critical feature.

Images