Gas path fault hypersphere clustering method based on angle interval constraint

Abstract

The invention belongs to the technical field of aero-engine gas path fault diagnosis, and discloses a gas path fault hyper-spherical clustering method based on angle interval constraint, comprising the following steps: S1, acquiring a gas path fault data sample and a fault-free data sample; s2, extracting features in the gas circuit fault data sample and the fault-free data sample, and obtaining sample features; s3, calculating a characteristic residual error according to the sample characteristics, and calculating a residual error difference according to the characteristic residual error; s4, constructing an angle interval constraint loss function, an L2 norm constraint loss function and a class center aggregation function; s5, constructing a total loss function; and S6, inputting the sample features, the feature residuals and the difference of the residuals into a total loss function to obtain a hyperspherical clustering result. The accuracy and robustness of gas path fault diagnosis are improved, and assistance is provided for health management and gas path fault analysis of an engine.

Description

Technical Field

[0001] This invention belongs to the field of aero-engine gas path fault diagnosis technology, and particularly relates to a hyperspherical clustering method for gas path faults based on angular interval constraints. Background Technology

[0002] As a complex system, an aero-engine cannot reflect the characteristics and performance of its gas path by a single parameter within its entire envelope. It is necessary to analyze the performance by calculating the ratio between different cross-sectional parameters. Furthermore, the performance dispersion between different engines is also large. Therefore, the change pattern of cross-sectional parameters caused by faults in each gas path is not obvious, and it is difficult to accurately distinguish the fault characteristics using conventional methods. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a hyperspherical clustering method for gas path faults based on angular interval constraints, comprising the following steps: S1. Obtain gas path fault data samples and fault-free data samples; S2. Extract features from the gas path fault data samples and fault-free data samples to obtain sample features; The sample features include: several types of gas path fault features and fault-free features; S3. Calculate the feature residuals based on the sample characteristics. The feature residuals include gas path fault feature residuals and fault-free feature residuals. Calculate the difference between the residuals based on the feature residuals. S4. Construct the angle interval constraint loss function, the L2 norm constraint loss function, and the class center aggregation function; S5. Construct the total loss function based on the angle interval constraint loss function, the L2 norm constraint loss function, and the class center aggregation function; S6. Input the sample features, feature residuals, and the difference between residuals into the total loss function to obtain the hyperspherical clustering results. The hyperspherical clustering results include fault-free feature clusters and several residual difference clusters.

[0004] Preferably, the gas path fault data sample includes: parameters measured by the sensor under gas path fault conditions and baseline model output parameters; The parameters measured by the sensor under gas path failure conditions include: total temperature at the inlet of the faulty engine, speed of the faulty fan, speed of the faulty compressor, static pressure at the inlet of the faulty fan, static pressure after the faulty compressor, pressure after the faulty low-pressure turbine, total temperature after the faulty low-pressure turbine, main fuel flow rate, afterburner fuel flow rate, and nozzle area. The fault-free data sample includes: parameters measured by the sensor under fault-free conditions and output parameters of the benchmark model; The parameters measured by the sensor under fault-free conditions include: fault-free engine inlet total temperature, fault-free fan speed, fault-free compressor speed, fault-free fan inlet static pressure, fault-free compressor after static pressure, fault-free low-pressure turbine after pressure, fault-free low-pressure turbine after total temperature, fault-free main fuel flow rate, fault-free afterburner fuel flow rate, and fault-free nozzle area. The benchmark model output parameters include: standard engine inlet total temperature, standard fan speed, standard compressor speed, standard fan inlet static pressure, standard compressor back static pressure, standard low-pressure turbine back pressure, standard low-pressure turbine back total temperature, standard main fuel flow rate, standard afterburner fuel flow rate, and standard nozzle area.

[0005] Preferably, step S2, extracting features from gas path fault data samples and fault-free data samples to obtain sample features, includes the following steps: S21. Extract features from gas path fault data samples and fault-free data samples to obtain high-dimensional data features; S22. Reduce the dimensionality of high-dimensional data features to three-dimensional feature vectors to obtain sample features.

[0006] Preferably, the gas path fault characteristics are composed of the correlation between parameters of the gas path fault data samples, including: gas path fault sensor measurement characteristics and baseline model output characteristics; The fault-free characteristics are composed of the correlation between parameters of fault-free data samples, including: fault-free sensor measurement characteristics and benchmark model output characteristics.

[0007] Preferably, the step of calculating the feature residual based on the sample features includes the following steps: S31. Calculate the residual of gas path fault characteristics based on the gas path fault characteristics; The gas path fault characteristic residual specifically refers to the difference between the gas path fault sensor measurement characteristics and the baseline model output characteristics; S32. Calculate the fault-free characteristic residuals based on the fault-free characteristics; The fault-free feature residual specifically refers to the difference between the measurement features of the fault-free sensor and the output features of the benchmark model; The difference in residuals specifically refers to the difference between the residuals of gas path fault characteristics and the residuals of no-fault characteristics.

[0008] Preferably, the construction of the angular interval constraint loss function includes the following steps: S41. Introduce the minimum angle interval parameter; S42. Set the feature angle threshold for similar samples and the angle threshold for dissimilar samples based on the minimum angle interval parameter; S43. Construct an angle interval constraint loss function based on the feature angle thresholds of similar samples and the angle thresholds of dissimilar samples.

[0009] Preferably, the angle interval constraint loss function is used to: force the angle between features of the same type of samples to be less than the angle threshold of features of the same type of samples, and force the angle between features of different types of samples to be greater than the angle threshold of features of different types of samples. The angle interval constraint loss function The expression is as follows: In the formula: For loss value, For sample features, For the category labels corresponding to the sample features, For the minimum angular interval parameter, The condition is denoted by i, and the sample numbers are i and j.

[0010] Preferably, the L2 norm-constrained loss function is expressed as follows: In the formula: For the number of features of fault-free samples, Let C be the number of fault samples of type n, C be the total number of fault types, and r be the radius of the hypersphere. For fault-free characteristic residuals, For fault characteristic residuals, It is the difference of residuals.

[0011] Preferably, the class center aggregation function The expression is as follows: In the formula: Let C be the number of fault samples of type n, and C be the total number of fault types. The difference between residuals It is the center of the difference of residuals.

[0012] Preferably, the total loss function The expression is as follows: In the formula: The scaling factor of the L2 norm constrained loss function, L2 norm constrained loss function The proportional function of the class center aggregation function, For class center aggregation functions, The scaling factor of the angle interval constraint loss function. This is the loss function for the angular interval constraint.

[0013] The beneficial effects of this invention are as follows: It can effectively extract the characteristics of gas path faults in aero-engines, cluster similar faults, separate dissimilar faults, and ensure that the center of each fault data is evenly distributed on a hypersphere. Geometric constraints enhance the interpretability of fault diagnosis tasks and improve the accuracy and robustness of aero-engine gas path fault diagnosis. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the system structure provided in an embodiment of the present invention; Figure 2 The hyperspherical clustering results provided in the embodiments of the present invention are viewed in front of the present invention. Figure 1 ; Figure 3 The hyperspherical clustering results provided in the embodiments of the present invention are viewed in front of the present invention. Figure 2 ; Figure 4 This is a top view of the hyperspherical clustering results provided in an embodiment of the present invention; Figure 5 This is an isometric projection of the hyperspherical clustering results provided in this embodiment of the invention. Detailed Implementation

[0015] The technical solution of the present invention is further described below, but the scope of protection is not limited to what is described.

[0016] like Figure 1 As shown, a hyperspherical clustering method for gas path faults based on angular interval constraints includes the following steps: S1. Obtain gas path fault data samples and fault-free data samples; The gas path fault data sample includes: parameters measured by the sensor under gas path fault conditions and baseline model output parameters; The parameters measured by the sensor under gas path failure conditions include: total temperature at the inlet of the faulty engine, speed of the faulty fan, speed of the faulty compressor, static pressure at the inlet of the faulty fan, static pressure after the faulty compressor, pressure after the faulty low-pressure turbine, total temperature after the faulty low-pressure turbine, main fuel flow rate, afterburner fuel flow rate, and nozzle area. The fault-free data sample includes: parameters measured by the sensor under fault-free conditions and output parameters of the benchmark model; The parameters measured by the sensor under fault-free conditions include: fault-free engine inlet total temperature, fault-free fan speed, fault-free compressor speed, fault-free fan inlet static pressure, fault-free compressor after static pressure, fault-free low-pressure turbine after pressure, fault-free low-pressure turbine after total temperature, fault-free main fuel flow rate, fault-free afterburner fuel flow rate, and fault-free nozzle area. The benchmark model output parameters include: standard engine inlet total temperature, standard fan speed, standard compressor speed, standard fan inlet static pressure, standard compressor back static pressure, standard low-pressure turbine back pressure, standard low-pressure turbine back total temperature, standard main fuel flow rate, standard afterburner fuel flow rate, and standard nozzle area.

[0017] In this embodiment, the sensor measurement parameters are denoted as... The output parameters of the baseline model are denoted as Furthermore, the parameters measured by the sensor under gas path failure conditions are recorded as follows: The parameters measured by the sensor under fault-free conditions are recorded as follows: The output parameters of the baseline model are denoted as .

[0018] S2. Extract features from the gas path fault data samples and fault-free data samples to obtain sample features; S2, extracting features from gas path fault data samples and fault-free data samples to obtain sample features includes the following steps: S21. Extract features from gas path fault data samples and fault-free data samples to obtain high-dimensional data features; S22. Reduce the dimensionality of high-dimensional data features to three-dimensional feature vectors to obtain sample features.

[0019] In this embodiment, the high-dimensional data characteristics are reduced to three-dimensional feature vectors by using the t-distributed random neighborhood embedding method, also known as t-SNE.

[0020] The sample features include: several types of gas path fault features and fault-free features; Gas circuit fault characteristics are divided into several categories, such as fault A, fault B, ..., fault N, based on gas circuit fault data samples.

[0021] In this embodiment, there are three types of gas path fault data samples, namely fault A, fault B and fault C.

[0022] The gas path fault characteristics are composed of the correlation between parameters of the gas path fault data samples, including: gas path fault sensor measurement characteristics and baseline model output characteristics; The fault-free characteristics are composed of the correlation between parameters of fault-free data samples, including: fault-free sensor measurement characteristics and benchmark model output characteristics.

[0023] In this embodiment, the sensor measurement features are denoted as... The output features of the baseline model are denoted as Furthermore, the measurement characteristics of the gas path fault sensor are denoted as... The parameters measured by the sensor under fault-free conditions are recorded as follows: The output features of the baseline model are denoted as , where n is the fault type number.

[0024] S3. Calculate the feature residuals based on the sample characteristics. The feature residuals include gas path fault feature residuals and fault-free feature residuals. Calculate the difference between the residuals based on the feature residuals. The calculation of feature residuals based on sample features includes the following steps: S31. Calculate the residual of gas path fault characteristics based on the gas path fault characteristics; The gas path fault characteristic residual specifically refers to the difference between the gas path fault sensor measurement characteristics and the baseline model output characteristics; In this embodiment, the residual characteristic of the gas path fault is denoted as... , where n is the fault type number.

[0025] S32. Calculate the fault-free characteristic residuals based on the fault-free characteristics; In this embodiment, the fault-free characteristic residual is denoted as... The fault-free feature residual specifically refers to the difference between the measurement features of the fault-free sensor and the output features of the benchmark model; The difference in residuals specifically refers to the difference between the residuals of gas path fault characteristics and the residuals of no-fault characteristics.

[0026] The difference between the residuals of the gas path fault characteristics and the residuals of the fault-free characteristics is the difference of residuals, denoted as . .

[0027] S4. Construct the angle interval constraint loss function, the L2 norm constraint loss function, and the class center aggregation function; The construction of the angle interval constraint loss function includes the following steps: S41. Introduce the minimum angle interval parameter; In this embodiment, the minimum angular interval parameter is denoted as... .

[0028] S42. Set the feature angle threshold for similar samples and the angle threshold for dissimilar samples based on the minimum angle interval parameter; The feature angle threshold for similar samples is The angle threshold for outlier samples is .in, The initial angle for the characteristics of similar samples. The initial angle for the outlier sample.

[0029] S43. Construct an angle interval constraint loss function based on the feature angle thresholds of similar samples and the angle thresholds of dissimilar samples.

[0030] The angle interval constraint loss function is used to: force the angle between features of the same type of samples to be less than the angle threshold of features of the same type of samples. Force the angle between outlier samples to be greater than the outlier sample angle threshold. ; Thus, by using the angle interval constraint loss function, we can minimize the geodesic distance between features of the same class of samples in the hyperspherical feature space, while maximizing the interval between features of different classes of samples, thereby improving intra-class compactness and inter-class separability.

[0031] The angle interval constraint loss function The expression is as follows: In the formula: For loss value, For sample features, For the category labels corresponding to the sample features, For the minimum angular interval parameter, The condition is denoted by i, and the sample numbers are i and j.

[0032] The L2 norm-constrained loss function is expressed as follows: In the formula: For the number of features of fault-free samples, Let C be the number of fault samples of type n, C be the total number of fault types, and r be the radius of the hypersphere. For fault-free characteristic residuals, For fault characteristic residuals, It is the difference of residuals.

[0033] L2 norm-constrained loss functions are used to achieve fault-free characteristic residuals. The modulus length tends to 0, and all fault characteristic residuals Compared with fault-free characteristic residual difference The modulus tends to a constant value.

[0034] That is, the difference of residuals Located in the residual with fault-free characteristics On a hypersphere with the center of the sphere.

[0035] The class center aggregation function The expression is as follows: In the formula: Let C be the number of fault samples of type n, and C be the total number of fault types. The difference between residuals It is the center of the difference of residuals.

[0036] in, These are called class centers, initialized as random numbers, and gradually shift towards the current batch of samples during training. Center update.

[0037] The specific update formula is as follows: In the formula: For the class center before iteration, For the iterated class center, For class center update rate, Let n be the number of samples of the nth type of fault.

[0038] Implementing class-centric aggregation functions Aggregation, Heterogeneous The centers are evenly distributed on the hypersphere.

[0039] S5. Construct the total loss function based on the angle interval constraint loss function, the L2 norm constraint loss function, and the class center aggregation function; The total loss function The expression is as follows: In the formula: The scaling factor of the L2 norm constrained loss function, L2 norm constrained loss function The proportional function of the class center aggregation function, For class center aggregation functions, The scaling factor of the angle interval constraint loss function. This is the loss function for the angular interval constraint.

[0040] The total loss function consists of an angular interval constraint loss function, an L2 norm constraint loss function, and a class center aggregation function. This total loss function clusters the unordered three-dimensional feature vectors (sample features) into a hypersphere centered on the features of fault-free samples. The residual differences are clustered on the surface of this hypersphere. Ultimately, this achieves the clustering and differentiation of different types of faults, enabling the effective extraction of fault features.

[0041] S6. Input the sample features, feature residuals, and the difference between residuals into the total loss function to obtain the hyperspherical clustering results. The hyperspherical clustering results include fault-free feature clusters and several residual difference clusters.

[0042] like Figures 2 to 5The image shows the hyperspherical clustering results obtained in this embodiment. The difference in residuals is obtained by constraining the loss function using the L2 norm. Located in the residual with fault-free characteristics On a hypersphere with the center of the sphere, class aggregation functions are used to achieve class-based aggregation. Aggregation, Heterogeneous The centers of the faults are evenly distributed on the hypersphere. An angular interval constraint loss function is used to minimize the geodesic distance between features of the same class of samples in the hypersphere feature space, while maximizing the interval between features of different classes of samples, thereby improving intra-class compactness and inter-class separability. Finally, fault-free feature clusters are located at the center of the sphere, and residual difference clusters are distributed on the hypersphere surface, enabling the clustering and differentiation of various faults. When unknown gas path fault data enters, it can accurately classify the gas path fault data into the corresponding category.

[0043] This invention addresses complex aero-engine gas path fault diagnosis by employing an angular interval contrast loss function, along with an L2 norm constraint loss function and a class center aggregation loss function. By enhancing the interpretability of image classification tasks through geometric constraints, it minimizes the geodesic distance between gas path fault samples of the same type while maximizing the interval between samples of different types, thereby improving the compactness of samples of the same type and the classification accuracy between samples of different types. This method is then used to analyze the difference between fault feature residuals and fault-free feature residuals. The analysis was performed to determine the even distribution of different classes. On a hypersphere, and controlling the distance from the center of the sphere and the fault-free characteristic residual as the center of the sphere. The L2 norm approaches 0, which leads to the aggregation of similar fault samples and the uniform distribution of the centers of dissimilar fault samples on the hypersphere. This can solve the problem of difficulty in accurately extracting the characteristics of engine gas path faults, and lay the groundwork for accurate localization of aero-engine gas path faults. It improves the accuracy and robustness of gas path fault diagnosis and provides assistance for engine health management and gas path fault analysis.

Claims

1. A hyperspherical clustering method for gas path faults based on angular interval constraints, characterized in that, Includes the following steps: S1. Obtain gas path fault data samples and fault-free data samples; S2. Extract features from the gas path fault data samples and fault-free data samples to obtain sample features; The sample features include several types of gas path fault features and fault-free features; S3. Calculate the feature residuals based on the sample characteristics. The feature residuals include gas path fault feature residuals and fault-free feature residuals. Calculate the difference between the residuals based on the feature residuals. S4. Construct the angle interval constraint loss function, the L2 norm constraint loss function, and the class center aggregation function; S5. Construct the total loss function based on the angle interval constraint loss function, the L2 norm constraint loss function, and the class center aggregation function; S6. Input the sample features, feature residuals, and the difference between residuals into the total loss function to obtain the hyperspherical clustering results. The hyperspherical clustering results include fault-free feature clusters and several residual difference clusters.

2. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The gas path fault data sample includes: parameters measured by the sensor under gas path fault conditions and baseline model output parameters; The parameters measured by the sensor under gas path failure conditions include: total temperature at the inlet of the faulty engine, speed of the faulty fan, speed of the faulty compressor, static pressure at the inlet of the faulty fan, static pressure after the faulty compressor, pressure after the faulty low-pressure turbine, total temperature after the faulty low-pressure turbine, main fuel flow rate, afterburner fuel flow rate, and nozzle area. The fault-free data sample includes: parameters measured by the sensor under fault-free conditions and output parameters of the benchmark model; The parameters measured by the sensor under fault-free conditions include: fault-free engine inlet total temperature, fault-free fan speed, fault-free compressor speed, fault-free fan inlet static pressure, fault-free compressor after static pressure, fault-free low-pressure turbine after pressure, fault-free low-pressure turbine after total temperature, fault-free main fuel flow rate, fault-free afterburner fuel flow rate, and fault-free nozzle area. The benchmark model output parameters include: standard engine inlet total temperature, standard fan speed, standard compressor speed, standard fan inlet static pressure, standard compressor back static pressure, standard low-pressure turbine back pressure, standard low-pressure turbine back total temperature, standard main fuel flow rate, standard afterburner fuel flow rate, and standard nozzle area.

3. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, S2, extracting features from gas path fault data samples and fault-free data samples to obtain sample features includes the following steps: S21. Extract features from gas path fault data samples and fault-free data samples to obtain high-dimensional data features; S22. Reduce the dimensionality of high-dimensional data features to three-dimensional feature vectors to obtain sample features.

4. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The gas path fault characteristics are composed of the correlation between parameters of the gas path fault data samples, including: gas path fault sensor measurement characteristics and baseline model output characteristics; The fault-free characteristics are composed of the correlation between parameters of fault-free data samples, including: fault-free sensor measurement characteristics and benchmark model output characteristics.

5. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The calculation of feature residuals based on sample features includes the following steps: S31. Calculate the residual of gas path fault characteristics based on the gas path fault characteristics; The gas path fault characteristic residual specifically refers to the difference between the gas path fault sensor measurement characteristics and the baseline model output characteristics; S32. Calculate the fault-free characteristic residuals based on the fault-free characteristics; The fault-free feature residual specifically refers to the difference between the measurement features of the fault-free sensor and the output features of the benchmark model; The difference in residuals specifically refers to the difference between the residuals of gas path fault characteristics and the residuals of no-fault characteristics.

6. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The construction of the angle interval constraint loss function includes the following steps: S41. Introduce the minimum angle interval parameter; S42. Set the feature angle threshold for similar samples and the angle threshold for dissimilar samples based on the minimum angle interval parameter; S43. Construct an angle interval constraint loss function based on the feature angle thresholds of similar samples and the angle thresholds of dissimilar samples.

7. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The angle interval constraint loss function is used to: force the angle between features of the same type of samples to be less than the angle threshold of features of the same type of samples, and force the angle between features of different types of samples to be greater than the angle threshold of features of different types of samples. The angle interval constraint loss function The expression is as follows: In the formula: For loss value, For sample features, For the category labels corresponding to the sample features, For the minimum angular interval parameter, The condition is i, and i and j are the sample numbers.

8. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The L2 norm-constrained loss function is expressed as follows: In the formula: For the number of features of fault-free samples, Let C be the number of fault samples of type n, C be the total number of fault types, and r be the radius of the hypersphere. For fault-free characteristic residuals, For fault characteristic residuals, It is the difference of residuals.

9. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The class center aggregation function The expression is as follows: In the formula: Let C be the number of fault samples of type n, and C be the total number of fault types. The difference between residuals It is the center of the difference of residuals.

10. The hyperspherical clustering method for gas path faults as described in claim 1, characterized in that, The total loss function The expression is as follows: In the formula: The scaling factor of the L2 norm constrained loss function, L2 norm constrained loss function The proportional function of the class center aggregation function, For class center aggregation functions, The scaling factor of the angle interval constraint loss function. This is the loss function for the angular interval constraint.

Images