A gyroscope group fault prediction method based on IHBA-RF

Abstract

The present invention relates to the technical field of artificial intelligence fault diagnosis, and discloses a gyroscope group fault prediction method based on IHBA-RF, performs dimension reduction and normalization preprocessing on the collected data through KPCA algorithm, and screens pin signal data with high correlation as a model input data set; improves the honey badger optimization algorithm HBA, introduces Sine chaotic mapping in the HBA population initialization stage, and calculates fitness; introduces a segmented optimal neighborhood strategy in the HBA mining stage and the honey-seeking stage to enhance the global search capability; adopts the improved honey badger optimization algorithm IHBA to perform parameter optimization on the random forest algorithm RF, constructs an IHBA-RF fault diagnosis model, and trains the training data set; inputs the test data set into the IHBA-RF prediction model, performs fault diagnosis on the gyroscope group, and outputs a prediction result. The present invention optimizes the main parameters of the random forest (RF) through an improved honey badger optimization algorithm (IHBA), makes up for the defect of blindness of parameter selection during the training process, and improves the prediction accuracy of the regression prediction model.

Description

Technical Field

[0001] The present invention relates to the technical field of artificial intelligence fault diagnosis, and in particular to a gyroscope group fault prediction method based on IHBA-RF. Background Art

[0002] The gyroscope group is an important component of the gun control system, which consists of a rate gyroscope, a temperature control board, a power board and a detection board. The gyroscope group is used in the system to accurately measure the angular position and angular velocity of the turret and gun, and provide the system with a drive signal to give the gun a new position. The gyroscope group plays an important role in battlefield operations, and frequent use also increases the incidence of failures. Fault prediction can improve battlefield combat mobility and firepower output, and maximize combat capabilities.

[0003] At present, various artificial intelligence-based algorithms have been widely used in the field of fault diagnosis. The randomness of kernel function selection and the limitation of large-scale training of support vector machines lead to the lack of accuracy of prediction results. The difficulty of expert system knowledge acquisition and the disadvantages of knowledge base limited to storage cannot guarantee the efficiency and correctness of prediction results. The fault tree analysis method has a large calculation scale, cumbersome work, and excessive memory usage, which also leads to a slow running speed in fault prediction. Compared with other algorithms, the random forest algorithm (RF) has the advantages of interpretability and robustness and perfectly solves the problem of complex internal mechanisms; RF has strong generalization and expression capabilities, which also makes the fault prediction results have higher accuracy. The ensemble learning method has improved the limitations of other machine learning algorithms in the field of fault diagnosis to a certain extent, such as weak generalization ability. Summary of the invention

[0004] In view of the shortcomings of the fault analysis algorithm in the prior art, such as large calculation scale, high complexity, cumbersome work, and lack of accuracy in prediction results, the technical solution adopted by the present invention is: a gyroscope group fault prediction method based on IHBA-RF, characterized in that it includes the following steps:

[0005] S1, collect data of gyroscope group pin signal;

[0006] S2. Perform dimension reduction and normalization preprocessing on the collected data through KPCA algorithm, and select pin signal data with high correlation as the model input data set;

[0007] Divide the model input dataset into a test dataset and a training dataset;

[0008] S3. Improvements to the honey badger optimization algorithm HBA, including the introduction of Sine chaos mapping in the HBA population initialization phase to calculate fitness; the introduction of segmented optimal neighborhood strategy in the HBA mining phase and honey-seeking phase to enhance global search capabilities;

[0009] The specific steps include:

[0010] S301, introduce Sine chaos mapping in the HBA population initialization phase,

[0011] , (2-1)

[0012] , (2-2)

[0013] Where: and is the chaotic number generated by the sinusoidal chaotic mapping, the value of 𝜇 ​​is 0.99, is the position of the i-th honey badger, and are the lower and upper boundaries of the search respectively;

[0014] S302, calculate the density factor α and the intensity factor I; the intensity is related to the concentration of the prey and the distance between the prey and the honey badger, and I is the smell intensity of the prey; if the smell is high, the movement speed is fast, and vice versa. The update formula is as follows:

[0015] , (2-3)

[0016] Where I is the intensity factor, S is the source intensity or concentrated intensity, Indicates the distance between the prey and the current honey badger individual, For the prey location, is the position of the i-th honey badger, is the position of the i+1th honey badger;

[0017] Density factor update: The density factor α controls the time-varying randomization to ensure a smooth transition from digging to honey collection. The formula is as follows:

[0018] , (2-4)

[0019] In the formula, α is the density factor, Represents the maximum number of iterations, ;

[0020] S303, introducing the segmented optimal neighborhood strategy in the HBA mining stage and the honey-seeking stage to enhance the global search capability is specifically: setting a direction correction coefficient F to change the search direction, so as to make use of a large number of opportunities to allow the search individuals to strictly scan the search space,

[0021] During the digging phase, the honey badger performs a heart-shaped motion, which can be simulated by equation (2-5):

[0022] (2-5)

[0023] In the formula, This is the updated individual position of the honey badger; For the prey location, is a random parameter, It represents the ability of honey badger to obtain food, I is the intensity factor, α is the density factor, is the distance between the prey and the current honey badger individual, Represents three different random numbers between [0,1], F is the direction correction coefficient, see the specific expression:

[0024] , (2-6)

[0025] In the honey-seeking stage, the formula for the honey badger following the honey guide badger to reach the hive is:

[0026] , (2-7)

[0027] In the formula, is the updated individual position of the honey badger, For the prey location, is a random parameter, F is a direction correction coefficient, and α is a density factor, is a random number between [0,1], based on the distance information Honey badger in prey position In this phase, the search is affected by the search behavior α which varies with iterations.

[0028] At this time, the segmented optimal neighborhood strategy is introduced in the mining stage and the honey-seeking stage to enhance the global search capability, so as to deal with the situation where there are better individuals near the optimal individual. The segmented nonlinear decreasing weight is introduced in the neighborhood parameter, which is defined as follows: , (2-8)

[0029] In the formula, is the piecewise nonlinear decreasing parameter, δ is the neighborhood parameter, is a random number uniformly distributed in the interval [0,1];

[0030] are nonlinear decreasing coefficients, representing three different downward trends. is the current iteration number, is the maximum number of iterations.

[0031] The position update of the mining phase after the improved segmented optimal neighborhood strategy is as follows:

[0032] , (2-9)

[0033] In the formula, is the piecewise nonlinear decreasing parameter, For prey location; is the updated position of the honey badger, F is the direction correction coefficient, It represents the ability of honey badger to obtain food, I is the intensity factor, α is the density factor, is the distance between the prey and the current honey badger individual, Represents three different random numbers between [0,1];

[0034] The position update of the honey-seeking phase after the segmented optimal neighborhood strategy is improved is as follows:

[0035] , (2-10)

[0036] In the formula, is the piecewise nonlinear decreasing parameter; For prey location; is the updated position of the honey badger, F is the direction correction coefficient, is a random parameter in [0,1], α is the density factor, is the distance between the i-th honey badger and its prey

[0037] S4, using the improved honey badger optimization algorithm IHBA to optimize the parameters of the random forest algorithm RF, building an IHBA-RF fault diagnosis model, and training the training data set;

[0038] S5. Input the test data set into the IHBA-RF prediction model, perform fault diagnosis on the gyroscope group, and output the prediction results.

[0039] like Figure 2 As shown, in step S2, the dimensionality reduction and normalization preprocessing of the collected data by the KPCA algorithm is specifically as follows:

[0040] S201, construct a decision matrix: suppose n sample data with m dimensions, and obtain an n*m decision matrix X，

[0041] ,(1-1)

[0042] in is a vector, n is a positive integer;

[0043] The matrix X Mapped to a d-dimensional high-dimensional space, the mapping relationship is as follows:

[0044] ,(1-2)

[0045] inR m is the low-dimensional space before mapping, R d is the high-dimensional space after mapping, and the new kernel matrix after mapping is:

[0046] ,(1-3).

[0047] S202. Center the kernel matrix: return the sample data to the zero vector. After dimensionality increase, the covariance matrix is:

[0048] ,(1-4)

[0049] Where C is a d-dimensional matrix; for The transposed matrix of is the i-th mapping function, .

[0050] S203, eigenvalue solution: According to the eigenvalue solution formula:

[0051] ,(1-5)

[0052] In the formula, p is the eigenvector, is the characteristic coefficient. Substitute formula (1-4) into formula (1-5) and omit the coefficient to obtain formula (1-6):

[0053] ,(1-6)

[0054] Divide both sides of formula (1-6) by , we get formula (1-7)

[0055] ;

[0056] In the formula, The linear combination of is represented by the eigenvector:

[0057] ,(1-8)

[0058] In the formula, is an n-dimensional column vector. Substitute formula (1-8) into formula (1-6) and multiply both sides by Get formula (1-9)

[0059] , (1-9)

[0060] make is an n-dimensional symmetric semi-positive definite matrix, , then the above formula can be simplified to:

[0061] ,(1-10)

[0062] The non-zero eigenvalues ​​obtained by solving formula (1-10) are equivalent to the non-zero eigenvalues ​​of formula (1-5). p After unitization, we have:

[0063] , (1-11).

[0064] S204, projecting the data processed in step S203 onto the selected principal component to form a new low-dimensional representation of the data in the feature vector p Projection on t , and get the dimension-reduced data:

[0065] , (1-12).

[0066] S205, using a normalization formula to normalize the obtained dimension reduction data, the formula is:

[0067] , (1-13)

[0068] In the formula, represents the normalized data. represents the normalized data, Represents the maximum value of the normalized data, Indicates the minimum value of the normalized data.

[0069] The step S4 uses the improved honey badger optimization algorithm IHBA to optimize the parameters of the random forest algorithm RF, specifically: judging whether the random parameter r is less than 0.5, and using the segmented optimal neighborhood strategy to update the position of the honey badger;

[0070] If the random parameter r < 0.5 , then it is the excavation stage, and the location information of the honey badger individual is updated according to formula (2-9); if the random parameter r ≥ 0.5 , it is the honey-seeking stage, and the individual location information of the honey badger is updated according to formula (2-10);

[0071] Determine whether the maximum number of iterations has been reached. If so, output the individual position and fitness value of the optimal group; if not, ， Re-execute S3 and update the individual positions of honey badgers again.

[0072] Compared with the prior art, the present invention has the following beneficial technical effects and advantages:

[0073] 1. Compared with other comprehensive evaluation algorithms (hierarchy analysis method, grey relational analysis, etc.), using KPCA algorithm to preprocess data can effectively process nonlinear data, map data to high-dimensional space through kernel techniques, capture complex structures, reduce dimensions, remove redundant features, improve the performance of subsequent models, and also have a good effect on noise reduction and help improve data quality;

[0074] 2. Compared with support vector machines (SVMs) and decision trees, random forests (RFs) can handle various types of data, including discrete and continuous values; they can use some robust loss functions; they can handle nonlinear data; and they have higher prediction accuracy with relatively few parameter adjustments;

[0075] 3. The main parameters of random forest (RF) are optimized by using improved honey badger optimization algorithm (IHBA), which makes up for the blindness of parameter selection in the training process and improves the prediction accuracy of the regression prediction model. Compared with the decision tree, support vector machine and GBDT algorithm experiments, IHBA-RF has higher prediction accuracy and practicality. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] Figure 1 It is a main frame diagram of a gyroscope group fault prediction method based on IHBA-RF of the present invention;

[0077] Figure 2 This is a flow chart of the KPCA algorithm of the present invention. DETAILED DESCRIPTION

[0078] The present invention is described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited by the accompanying drawings.

[0079] The present invention provides a gyroscope group fault prediction method based on IHBA-RF, such as Figure 1 As shown: The following steps are included:

[0080] S1. The research object is a gyroscope group of a certain type of tank. The data value of the pin signal of the gyroscope group is collected through the equipment test bench, and the data value of the port number is collected as the initial data of the experiment.

[0081] S2. Perform dimension reduction and normalization preprocessing on the collected data through KPCA algorithm, and select pin signal data with high correlation as the model input data set;

[0082] Divide the model input dataset into a test dataset and a training dataset;

[0083] Further, S201, construct a decision matrix: suppose n sample data with m dimensions, and obtain an n*m decision matrix X ,

[0084] ,(1-1)

[0085] in is a vector, n is a positive integer;

[0086] The matrix X Mapped to a d-dimensional high-dimensional space, the mapping relationship is as follows:

[0087] ,(1-2)

[0088] in R m is the low-dimensional space before mapping, R d is the high-dimensional space after mapping, and the new kernel matrix after mapping is:

[0089] ,(1-3).

[0090] S202. Center the kernel matrix: return the sample data to the zero vector. After dimensionality increase, the covariance matrix is:

[0091] ,(1-4)

[0092] Where C is a d-dimensional matrix; for The transposed matrix of is the i-th mapping function, .

[0093] S203, eigenvalue solution: According to the eigenvalue solution formula:

[0094] ,(1-5)

[0095] In the formula, p is the eigenvector, is the characteristic coefficient. Substitute formula (1-4) into formula (1-5) and omit the coefficient to obtain formula (1-6):

[0096] ,(1-6)

[0097] Divide both sides of formula (1-6) by , we get formula (1-7)

[0098] ,(1-7)

[0099] In the formula, The linear combination of is represented by the eigenvector:

[0100] ,(1-8)

[0101] In the formula, is an n-dimensional column vector. Substitute formula (1-8) into formula (1-6) and multiply both sides by Get formula (1-9)

[0102] , (1-9)

[0103] make is an n-dimensional symmetric semi-positive definite matrix, , then the above formula can be simplified to:

[0104] ,(1-10)

[0105] The non-zero eigenvalues ​​obtained by solving formula (1-10) are equivalent to the non-zero eigenvalues ​​of formula (1-5). p After unitization, we have:

[0106] , (1-11).

[0107] S204, projecting the data processed in step S203 onto the selected principal component to form a new low-dimensional representation of the data in the feature vector p Projection on t , and get the dimension-reduced data:

[0108] , (1-12).

[0109] S205, using a normalization formula to normalize the obtained dimension reduction data, the formula is:

[0110] , (1-13)

[0111] In the formula, represents the normalized data. represents the normalized data, Represents the maximum value of the normalized data, Indicates the minimum value of the normalized data.

[0112] S3. Improvements to the honey badger optimization algorithm HBA, including the introduction of Sine chaos mapping in the HBA population initialization phase to calculate fitness; the introduction of segmented optimal neighborhood strategy in the HBA mining phase and honey-seeking phase to enhance global search capabilities;

[0113] S301. The diversity of the initial population plays a vital role in the convergence speed and convergence accuracy of the algorithm. In order to further expand the scope of the initial population to improve the local search capability and make it easier to find the location of the optimal solution, the Sine chaotic mapping and population filtering mechanism are used to optimize the initialization phase of HBA, as shown in the expression:

[0114] , (2-1)

[0115] , (2-2)

[0116] Where: and is the chaotic number generated by the sinusoidal chaotic mapping, the value of 𝜇 ​​is 0.99, is the position of the i-th honey badger, and are the lower and upper bounds of the search, respectively.

[0117] S302, calculate the density factor α and the intensity factor I; the intensity is related to the concentration of the prey and the distance between the prey and the honey badger, and I is the smell intensity of the prey; if the smell is high, the movement speed is fast, and vice versa. The update formula is as follows:

[0118] , (2-3)

[0119] Where I is the intensity factor, S is the source intensity or concentrated intensity, Indicates the distance between the prey and the current honey badger individual, For the prey location, is the position of the i-th honey badger, is the position of the i+1th honey badger;

[0120] Density factor update: The density factor α controls the time-varying randomization to ensure a smooth transition from digging to honey collection. The formula is as follows:

[0121] , (2-4)

[0122] In the formula, α is the density factor, Represents the maximum number of iterations, ;

[0123] Jump out of local optimum: This step and the next two steps are used to jump out of the local optimum area. In this case, the proposed algorithm uses a flag F that changes the search direction to take advantage of a large number of opportunities for the search individuals to strictly scan the search space.

[0124] S303, introducing the segmented optimal neighborhood strategy in the HBA mining stage and the honey-seeking stage to enhance the global search capability is specifically: setting a direction correction coefficient F to change the search direction, so as to make use of a large number of opportunities to allow the search individuals to strictly scan the search space,

[0125] During the digging phase, the honey badger performs a heart-shaped motion, which can be simulated by equation (2-5):

[0126] (2-5)

[0127] In the formula, This is the updated individual position of the honey badger; For the prey location, is a random parameter, It represents the ability of honey badger to obtain food, I is the intensity factor, α is the density factor, is the distance between the prey and the current honey badger individual, Represents three different random numbers between [0,1], F is the direction correction coefficient, see the specific expression:

[0128] , (2-6)

[0129] In the honey-seeking stage, the formula for the honey badger following the honey guide badger to reach the hive is:

[0130] , (2-7)

[0131] In the formula, is the updated individual position of the honey badger, For the prey location, is a random parameter, F is a direction correction coefficient, and α is a density factor, is a random number between [0,1], based on the distance information Honey badger in prey position Search is performed nearby, at this stage the search is affected by the search behavior α which changes with iterations; in addition, a honey badger may be disturbed by F.

[0132] At this time, the segmented optimal neighborhood strategy is introduced in the mining stage and the honey-seeking stage to enhance the global search capability, so as to deal with the situation where there are better individuals near the optimal individual, which can effectively deal with the problem that the algorithm is prone to fall into local problems. Therefore, the segmented nonlinear decreasing weight is introduced in the neighborhood parameter. Its definition is as follows:

[0133] , (2-8)

[0134] In the formula, is the piecewise nonlinear decreasing parameter, δ is the neighborhood parameter, is a random number uniformly distributed in the interval [0,1];

[0135] are nonlinear decreasing coefficients, representing three different downward trends. is the current iteration number, is the maximum number of iterations.

[0136] The position update of the mining phase after the improved segmented optimal neighborhood strategy is as follows:

[0137] , (2-9)

[0138] In the formula, is the piecewise nonlinear decreasing parameter, For prey location; is the updated position of the honey badger, F is the direction correction coefficient, It represents the ability of honey badger to obtain food, I is the intensity factor, α is the density factor, is the distance between the prey and the current honey badger individual, Represents three different random numbers between [0,1];

[0139] The position update of the honey-seeking phase after the segmented optimal neighborhood strategy is improved is as follows:

[0140] , (2-10)

[0141] In the formula, is the piecewise nonlinear decreasing parameter; For prey location; is the updated position of the honey badger, F is the direction correction coefficient, is a random parameter in [0,1], α is the density factor, is the distance between the i-th honey badger and its prey.

[0142] S4, using the improved honey badger optimization algorithm IHBA to optimize the parameters of the random forest algorithm RF, building an IHBA-RF fault diagnosis model, and training the training data set;

[0143] Furthermore, the Random Forest algorithm (RF) is an intelligent ensemble learning algorithm composed of multiple decision trees. Classification and Regression Trees (CART) is a statistical model that can obtain different classes or values ​​after inputting features. CART is used as the base learner in RF, and the Gini index minimization criterion is used to select features and divide them. Suppose the input sample set In the classification problem, for a given sample D, assuming there are K categories, the probability of the Kth category is , and its Gini index is: The leaf node variance is used to determine the partition point K and set D. The variance of the leaf node P is defined as: , For leaf node p up to The average value. Then divide the next level leaf nodes in the same way until the preset node domain value is reached to generate the final decision tree. After the training is completed, an estimation function is established, and the new X can get the estimated value Y through S. Random forest combines multiple decision trees to achieve data classification. It has the advantages of fewer adjustment parameters, fast training speed, high estimation accuracy, and strong generalization ability. The algorithm extracts multiple sample data from the original data through the Bootstrap sampling method to construct a new training sample set. Based on the CART idea, a decision tree is established for each training set. Finally, the results of q decision trees are averaged to obtain the final estimated value Y: The parameters involved in modeling the random forest algorithm mainly include the learning rate (learning_rate), which is used to control the step size of parameter updates during learning. If the step size is too large, the learning process may diverge. Otherwise, the model will be iterated too many times, which will greatly increase the learning time. The maximum number of iterations (n_estimators) indicates the number of base learners and interacts with the learning_rate. When the learning_rate is small, the number of iterations needs to be increased to converge the training error. Subsampling (subsample) is used to control the proportion of data set samples involved in fitting. When it is set to less than 1, it can effectively reduce the variance of the overall model and prevent overfitting. The maximum depth of the decision tree (max_depth), the minimum number of samples required for internal node re-division (min_samples_split) and the minimum number of samples contained in the leaf node (min_samples_leaf) are all used to control the complexity of each tree. The specific value depends on the data distribution. If the value is too large, the model structure will be complicated and easily lead to overfitting. Otherwise, it will easily lead to underfitting.

[0144] In this embodiment, the fitness value of each honey badger is calculated to determine the global optimal solution, select the first half of the excellent honey badger individuals, and retain the location information and fitness value information of the optimal honey badger individual;

[0145] Calculate the value of the odor intensity parameter according to formula (2-3); calculate the value of the convergence factor according to formula (2-4);

[0146] Determine whether the random value is less than 0.5, and use the segmented optimal neighborhood strategy to update the position of the honey badger;

[0147] If the random parameterr < 0.5 , then it is the excavation stage, and the location information of the honey badger individual is updated according to formula (2-9); if the random parameter r ≥ 0.5 , it is the honey-seeking stage, and the individual position information of the honey badger is updated according to formula (2-10); determine whether the maximum number of iterations has been reached. If so, output the individual position and fitness value of the optimal group; if not, ， Re-execute S3 and update the individual positions of honey badgers again.

[0148] S5. Input the test data set into the IHBA-RF prediction model, perform fault diagnosis on the gyroscope group, and output the prediction results.

[0149] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A gyroscope group fault prediction method based on IHBA-RF, characterized in that The following steps are involved: S1, collect data of gyroscope group pin signal; S2. Perform dimension reduction and normalization preprocessing on the collected data through KPCA algorithm, and select pin signal data with high correlation as the model input data set; Divide the model input dataset into a test dataset and a training dataset; S3. Improvements to the honey badger optimization algorithm HBA, including the introduction of Sine chaos mapping in the HBA population initialization phase to calculate fitness; the introduction of segmented optimal neighborhood strategy in the HBA mining phase and honey-seeking phase to enhance global search capabilities; The specific steps include: S301, introduce Sine chaos mapping in the HBA population initialization phase, ，(2-1) ，(2-2) Where: and is the chaotic number generated by the sinusoidal chaotic mapping, the value of 𝜇 ​​is 0.99, is the position of the i-th honey badger, and are the lower and upper boundaries of the search respectively; S302, calculate the density factor α and the intensity factor I; the intensity is related to the concentration of the prey and the distance between the prey and the honey badger, and I is the smell intensity of the prey; if the smell is high, the movement speed is fast, and vice versa. The update formula is as follows: ，(2-3) Where I is the intensity factor, S is the source intensity or concentrated intensity, Indicates the distance between the prey and the current honey badger individual, For the prey location, is the position of the i-th honey badger, is the position of the i+1th honey badger; Density factor update: The density factor α controls the time-varying randomization to ensure a smooth transition from digging to honey collection. The formula is as follows: ，(2-4) In the formula, α is the density factor, Represents the maximum number of iterations, ; S303, introducing the segmented optimal neighborhood strategy in the HBA mining stage and the honey-seeking stage to enhance the global search capability is specifically: setting a direction correction coefficient F to change the search direction, so as to take advantage of a large number of opportunities to allow the search individuals to strictly scan the search space, During the digging phase, the honey badger performs a heart-shaped motion, which can be simulated by equation (2-5): (2-5) In the formula, This is the updated individual position of the honey badger; For the prey location, is a random parameter, It represents the ability of honey badger to obtain food, I is the intensity factor, α is the density factor, is the distance between the prey and the current honey badger individual, Represents three different random numbers between [0,1], F is the direction correction coefficient, see the specific expression: ，(2-6) In the honey-seeking stage, the formula for the honey badger following the honey guide badger to reach the hive is: ，(2-7) In the formula, is the updated individual position of the honey badger, For the prey location, is a random parameter, F is a direction correction coefficient, and α is a density factor, is a random number between [0,1], based on the distance information Honey badger in prey position Search is performed nearby. In this phase, the search is affected by the search behavior α which changes with iterations; At this time, the segmented optimal neighborhood strategy is introduced in the mining stage and the honey-seeking stage to enhance the global search capability, so as to deal with the situation where there are better individuals near the optimal individual. The segmented nonlinear decreasing weight is introduced in the neighborhood parameter, which is defined as follows: ，(2-8) In the formula, is the piecewise nonlinear decreasing parameter, δ is the neighborhood parameter, is a random number uniformly distributed in the interval [0,1]; are nonlinear decreasing coefficients, representing three different downward trends. is the current iteration number, is the maximum number of iterations; The position update of the mining phase after the improved segmented optimal neighborhood strategy is as follows: ，(2-9) In the formula, is the piecewise nonlinear decreasing parameter, For prey location; is the updated position of the honey badger, F is the direction correction coefficient, It represents the ability of honey badger to obtain food, I is the intensity factor, α is the density factor, is the distance between the prey and the current honey badger individual, Represents three different random numbers between [0,1]; The position update of the honey-seeking phase after the segmented optimal neighborhood strategy is improved is as follows: ，(2-10) In the formula, is the piecewise nonlinear decreasing parameter; For prey location; is the updated position of the honey badger, F is the direction correction coefficient, is a random parameter in [0,1], α is the density factor, is the distance between the i-th honey badger and its prey; S4, using the improved honey badger optimization algorithm IHBA to optimize the parameters of the random forest algorithm RF, building an IHBA-RF fault diagnosis model, and training the training data set; S5. Input the test data set into the IHBA-RF prediction model, perform fault diagnosis on the gyroscope group, and output the prediction results.

2. A gyroscope group fault prediction method based on IHBA-RF according to claim 1: In step S2, the collected data is preprocessed by dimension reduction and normalization using the KPCA algorithm, specifically: S201, construct a decision matrix: suppose n sample data with m dimensions, and obtain an n*m decision matrix X , ,(1-1) in is a vector, n is a positive integer; The matrix X Mapped to a d-dimensional high-dimensional space, the mapping relationship is as follows: ,(1-2) in R m is the low-dimensional space before mapping, R d is the high-dimensional space after mapping, and the new kernel matrix after mapping is: ,(1-3) S202. Center the kernel matrix: return the sample data to the zero vector. After dimensionality increase, the covariance matrix is: ,(1-4) Where C is a d-dimensional matrix; for The transposed matrix of is the i-th mapping function, ; S203, eigenvalue solution: According to the eigenvalue solution formula: ,(1-5) In the formula, p is the eigenvector, is the characteristic coefficient. Substitute formula (1-4) into formula (1-5) and omit the coefficient to obtain formula (1-6): ,(1-6) Divide both sides of formula (1-6) by , we get formula (1-7) ； In the formula, The linear combination of is represented by the eigenvector: ,(1-8) In the formula, is an n-dimensional column vector. Substitute formula (1-8) into formula (1-6) and multiply both sides by Get formula (1-9) ，(1-9) make is an n-dimensional symmetric semi-positive definite matrix, , then the above formula can be simplified to: ,(1-10) The non-zero eigenvalues ​​obtained by solving formula (1-10) are equivalent to the non-zero eigenvalues ​​of formula (1-5). p After unitization, we have: ，(1-11) S204, projecting the data processed in step S203 onto the selected principal component to form a new low-dimensional representation of the data in the feature vector p Projection on t , and get the dimension-reduced data: ，(1-12) S205, using a normalization formula to normalize the obtained dimension reduction data, the formula is: ，(1-13) In the formula, represents the normalized data, represents the normalized data, Represents the maximum value of the normalized data, Indicates the minimum value of the normalized data.

3. A gyroscope group fault prediction method based on IHBA-RF according to claim 1: said step S4 uses an improved honey badger optimization algorithm IHBA to perform parameter optimization on the random forest algorithm RF, specifically: judging whether the random parameter r is less than 0.5, and using a segmented optimal neighborhood strategy to update the position of the honey badger; If the random parameter r < 0.5 , then it is the excavation stage, and the location information of the honey badger individual is updated according to formula (2-9); if the random parameter r ≥ 0.5 , it is the honey-seeking stage, and the individual location information of the honey badger is updated according to formula (2-10); Determine whether the maximum number of iterations has been reached. If so, output the individual position and fitness value of the optimal group; if not, ， Re-execute S3 and update the individual positions of honey badgers again.

Images