Multi-source data fusion ship fault prediction system

Abstract

The invention provides a ship fault prediction system based on multi-source data fusion, and relates to the technical field of ship fault prediction, and the system comprises a data collection module which is used for obtaining original signal data; the data preprocessing module is used for aligning the original signal data from different sources, and after data alignment, preprocessing the original signal data after data alignment according to a preprocessing step to obtain preprocessed data; the data fusion module is used for performing multi-source fusion on the preprocessed data by using an improved Kalman filtering algorithm to obtain fused data; the feature engineering module is used for performing multi-dimensional feature extraction and feature selection on the fused data, and fusing the selected features to obtain fused features; and the fault prediction module is used for receiving the fusion features and performing ship fault prediction according to the fusion features based on a pre-trained fault prediction model. According to the invention, accurate prediction of ship faults can be realized, and finally the safety and reliability of ship operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ship fault prediction, and in particular to a ship fault prediction system based on multi-source data fusion. Background Art

[0002] The normal operation of ship engine room equipment, especially the key components such as engines, transmissions, shafting, etc. in the propulsion system, is crucial to ship safety. In recent years, with the development of sensing technology, data analysis and artificial intelligence, ship fault prediction and diagnosis technology has made significant progress. Traditional methods mainly rely on expert experience and simple threshold judgments, while modern methods use more data-driven intelligent algorithms.

[0003] In terms of fault diagnosis, technologies such as vibration analysis, acoustic emission, and oil analysis are widely used in the detection of engine faults. Researchers have proposed signal processing methods based on wavelet transform and empirical mode decomposition (EMD) to extract fault features. At the same time, machine learning algorithms such as support vector machines (SVM) and artificial neural networks (ANN) are used for fault pattern recognition and classification.

[0004] However, existing technologies still have some limitations. First, a single data source is often difficult to fully reflect the complex state of the equipment. Second, the correlation between different types of data (such as vibration, temperature, pressure, etc.) is not fully utilized. Furthermore, existing feature extraction methods may not be able to effectively capture key information in multi-source heterogeneous data. Finally, in practical applications, the impact of data quality issues (such as noise, missing, etc.) on prediction accuracy has not been well resolved.

[0005] Therefore, how to effectively fuse multi-source heterogeneous data, extract more representative features, and on this basis improve the accuracy and reliability of fault prediction has become an important research direction in the current field of ship fault prediction. Summary of the invention

[0006] In view of this, the present invention proposes a ship fault prediction system with multi-source data fusion, which effectively integrates various sensor data of ship engine room equipment through multi-source data fusion and feature engineering technology, and uses an improved Kalman filter algorithm and an optimized SVM model to process complex and nonlinear systems, thereby extracting more representative features, realizing accurate prediction of ship faults, and ultimately improving the safety and reliability of ship operation.

[0007] The technical solution of the present invention is implemented as follows: The present invention provides a ship fault prediction system with multi-source data fusion, comprising:

[0008] Data acquisition module, used to obtain the original signal data of the engine room equipment related to the ship operation;

[0009] A data preprocessing module is used to align the original signal data from different sources. After the data is aligned, the original signal data after the data alignment is preprocessed according to the preprocessing steps to obtain the preprocessed data;

[0010] The data fusion module is used to perform multi-source fusion on the pre-processed data using an improved Kalman filter algorithm to obtain fused data;

[0011] The feature engineering module is used to extract and select multi-dimensional features from the fused data, and fuse the selected features to obtain fused features;

[0012] The fault prediction module is used to receive the fused features and perform ship fault prediction according to the fused features based on a pre-trained fault prediction model.

[0013] On the basis of the above technical solution, preferably, the data preprocessing module includes:

[0014] The data alignment unit is used to perform preliminary checks on the original signal data from different sources, standardize the timestamps, create a unified time index, map the original signal data from different sources to the unified time index, make the original signal data in time series format, and complete data alignment;

[0015] The data preprocessing unit is used to preprocess the original signal data after data alignment, including data interpolation and outlier filtering, to obtain preprocessed data.

[0016] On the basis of the above technical solution, preferably, the improved Kalman filter algorithm includes:

[0017] Based on the characteristics of the engine room equipment related to ship operation, a state space model containing key state variables is established. The state space model consists of state equations and observation equations, which respectively describe the evolution and observation process of the system state. Among them, the key state variables include engine speed, engine temperature, fuel consumption rate, exhaust temperature, cooling water temperature and lubricating oil pressure.

[0018] Obtain the initial state space model parameters, and optimize the parameters through the optimization method to obtain the optimal parameter set;

[0019] Iterate the Kalman filter algorithm on the preprocessed data:

[0020] Prediction step: predict the current state based on previous state estimates and control inputs;

[0021] Unknown input estimation: Estimate slowly changing and rapidly changing unknown inputs separately;

[0022] Update step: Combine the observations and position input estimates to update the state estimate and error covariance matrix;

[0023] Adjustment step: dynamically adjust the process noise covariance matrix and the observation noise covariance matrix according to the innovation sequence;

[0024] By extending the observation equation, data from different sources are fused, and the observation noise covariance matrix is ​​adjusted according to the reliability of each data source;

[0025] Output the denoised and fused state estimate as the fused data.

[0026] Based on the above technical solution, preferably, in the state space model:

[0027] Equation of state:

[0028] x(k+1)=A(k)x(k)+B(k)u(k)+F(k)d(k)+w(k)

[0029] Observation equation:

[0030] y(k)=C(k)x(k)+v(k)

[0031] Where x(k+1) is the state vector at time k+1, x(k) is the state vector at time k, u(k) is the control input vector, d(k) is the unknown input vector, w(k) is the process noise, A(k) is the state transfer matrix, B(k) is the control input matrix, F(k) is the unknown input matrix, y(k) is the observation vector, C(k) is the observation matrix, and v(k) is the observation noise;

[0032] Kalman filter algorithm iteration:

[0033] Prediction steps:

[0034]

[0035] P(k|k-1)=A(k-1)P(k-1|k-1)A(k-1) T +Q(k-1)

[0036] Unknown input estimation:

[0037] M(k)=C(k)P(k|k-1)C(k) T +R(k)

[0038] K d (k)=P(k|k-1)C(k) T M(k) -1

[0039]

[0040] Update steps:

[0041] K(k)=P(k|k-1)C(k) T (C(k)(k|k-1)C(k) T +R(k)) -1

[0042]

[0043] P(k|k)=(IK(k)C(k))P(k|k-1)

[0044] Adjustment steps:

[0045]

[0046] S(k)=C(k)P(k|k-1)C(k) T +R(k)

[0047] Q(k)=λQ(k-1)+(1-λ)K(k)ε(k)ε(k) T K(k) T

[0048] R(k)=λR(k-1)+(1-λ)(ε(k)ε(k) T -C(k)P(k|k-1)C(k) T )

[0049] In the formula, is the prior state estimate at time k, is the a priori state estimate at time k-1, P(k|k-1) is the a priori error covariance matrix at time k, P(k-1|k-1) is the a priori error covariance matrix at time k-1, Q(k-1) is the process noise covariance matrix, R(k) is the observation noise covariance matrix, M(k) is the innovation covariance matrix, K d (k) is the unknown input gain, For slowly varying unknown input estimates, is the estimation of the rapidly changing unknown input, ρ(k) is the intermittent coefficient matrix, θ(k) is the rapidly changing part parameter, K(k) is the Kalman gain, is the posterior state estimate at time k, P(k|k) is the posterior error covariance matrix at time k, F(k) is the unknown input matrix, I is the identity matrix, ε(k) is the innovation sequence, S(k) is the innovation covariance matrix, and λ is the forgetting factor;

[0050] Extend the observation equation for data fusion:

[0051] y(k)=[C1(k);C2(k);...;C a (k)]x(k)+v(k)

[0052] Where, C1(k); C2(k); ...; C a (k) represent the observation matrices of different data sources.

[0053] On the basis of the above technical solution, preferably, the initial state space model parameters are estimated based on the maximum likelihood estimation method, and the optimization method is a hybrid optimization method based on particle swarm optimization and simulated annealing.

[0054] Based on the above technical solution, preferably, the feature engineering module includes:

[0055] The feature extraction unit is used to perform signal decomposition on the fused data according to the VMD decomposition algorithm, separate K IMF components from each data, and use the trained autoencoder to perform feature extraction on the K IMF components respectively to obtain the multi-dimensional features of the data;

[0056] The feature selection unit is used to calculate the relative disorder of the multi-dimensional features, sort the multi-dimensional features from small to large according to the relative disorder, and select the first M dimensional features as the features to be fused;

[0057] The feature fusion unit is used to fuse the features to be fused of each data according to the fusion formula to obtain the fused features.

[0058] Based on the above technical solution, preferably, the loss function of the autoencoder during training is:

[0059]

[0060] In the formula, m is the number of samples, s represents the sth sample, O s Indicates output data, I s Represents input data. When z=1, it means is the weight matrix of the encoder, when z=2, it means is the weight matrix of the decoder, r h is the number of hidden layers of the encoder, r g is the number of hidden layers in the decoder, γ is the weight decay parameter, SG[·] is the prohibition of gradient backpropagation, and h e (s) is the vector representation of the encoder mapping sample s to the latent space, e is the embedding vector, represents the squared L2 norm.

[0061] On the basis of the above technical solution, preferably, the relative disorder degree calculation formula is:

[0062]

[0063] In the formula, RD(X i ) is the i-th dimension feature X i The relative disorder degree, AC(X i ) is X i The first-order autocorrelation coefficient of For X i The average mutual information of N is the total dimension of multidimensional features, MI(X i ,X j ) is X i and X j The mutual information between i ) is X i The information entropy, α and β are adjustable parameters used to adjust the influence of autocorrelation coefficient and mutual information.

[0064] Based on the above technical solution, preferably, the fusion formula is:

[0065]

[0066] In the formula, F is the fusion feature, w i is the weight.

[0067] On the basis of the above technical solution, preferably, the fault prediction model is SVM, and during pre-training, an optimization algorithm is used to optimize the penalty parameters and kernel function parameters of SVM, and after optimization, the SVM is trained based on the sample set.

[0068] Compared with the prior art, the present invention has the following beneficial effects:

[0069] (1) By integrating multiple modules, the whole process from data collection, preprocessing, fusion to feature extraction and fault prediction is optimized. This systematic approach significantly improves the accuracy and reliability of ship fault prediction and effectively reduces ship operation risks and maintenance costs;

[0070] (2) The improved Kalman filter algorithm can better handle nonlinearity and uncertainty by introducing unknown input estimation and dynamically adjusting the noise covariance matrix, thus improving the accuracy of data fusion. At the same time, the design of the extended observation equation makes the fusion of multi-source data more flexible and effective, and enhances the system's adaptability to complex ship operating environments;

[0071] (3) Combining the VMD decomposition algorithm with the feature extraction method of the autoencoder and the feature selection strategy based on relative chaos, the most representative and informative features can be extracted from the complex ship operation data. This not only reduces the data dimension, but also improves the efficiency and accuracy of subsequent fault prediction;

[0072] (4) By optimizing and pre-training the SVM model parameters, this method enhances the model's ability to learn ship failure modes. This optimized SVM model can more accurately capture various complex failure modes and improve the accuracy and reliability of fault prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0074] Figure 1 It is a system framework diagram of the present invention. DETAILED DESCRIPTION

[0075] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] like Figure 1 As shown, the present invention provides a ship fault prediction system with multi-source data fusion, comprising:

[0077] Data acquisition module, used to obtain the original signal data of the engine room equipment related to the ship operation;

[0078] A data preprocessing module is used to align the original signal data from different sources. After the data is aligned, the original signal data after the data alignment is preprocessed according to the preprocessing steps to obtain the preprocessed data;

[0079] A data fusion module is used to perform multi-source fusion on the pre-processed data using an improved Kalman filter algorithm to obtain fused data;

[0080] The feature engineering module is used to extract and select multi-dimensional features from the fused data, and fuse the selected features to obtain fused features;

[0081] The fault prediction module is used to receive the fused features and perform ship fault prediction according to the fused features based on a pre-trained fault prediction model.

[0082] Specifically, in one embodiment of the present invention, the data acquisition module is targeted at the following engine room equipment in the ship: main engine system, auxiliary starting point system, fuel system, cooling system, lubrication system and exhaust system. The original signal data is collected from the operation status of these engine room equipment using sensors, acquisition cards, etc. The specific data types include physical quantities such as temperature, pressure, vibration measured by sensors, engine speed, fuel consumption rate, exhaust temperature and other operating parameters, and some environmental data such as sea conditions, air temperature, humidity, etc. are also collected as backup data. When collecting data, the sampling frequency is set according to the characteristics of different equipment and parameters. For key parameters such as engine speed, engine temperature, fuel consumption rate, exhaust temperature, cooling water temperature and lubricating oil pressure, high-frequency sampling can be set, and other parameters can be set to low-frequency sampling.

[0083] Specifically, in one embodiment of the present invention, the data preprocessing module includes:

[0084] The data alignment unit is used to perform preliminary checks on the original signal data from different sources, standardize the timestamps, create a unified time index, map the original signal data from different sources to the unified time index, make the original signal data in time series format, and complete data alignment;

[0085] The data preprocessing unit is used to preprocess the original signal data after data alignment, including data interpolation and outlier filtering, to obtain preprocessed data.

[0086] In this embodiment, the preliminary data check includes integrity check, format check and range check, for example, checking whether there is missing data, ensuring that the format of all data sources is consistent, and verifying whether the data is within a reasonable range. Timestamp standardization refers to converting the timestamps of all data sources to the same format, such as ISO 8601 standard (YYYY-MM-DD HH:MM:SS). Ensure that all timestamps have the same accuracy, for example, accurate to seconds or milliseconds.

[0087] In this embodiment, the process of creating a unified time index is as follows: based on the timestamps of all data sources, determine the overall start and end time; determine the appropriate time interval according to the nature of the data and the sampling frequency; use the determined time range and interval to create a continuous time series as a unified index. According to the sampling frequency set when collecting data, for data with a sampling frequency lower than the unified index, use linear interpolation to fill in missing time points, and for data with a sampling frequency higher than the unified index, downsample by averaging or other appropriate methods to map the data to the unified index and complete data alignment.

[0088] Specifically, in one embodiment of the present invention, the data interpolation process is:

[0089] Obtain the missing data found during the preliminary inspection. For each missing data, use it as the data T that needs to be interpolated. Set a time period, with T as the center, and obtain the data in the previous time period and the next time period as candidate data.

[0090] Calculate the Euclidean distance d between each candidate data and the data T to be interpolated;

[0091] Arrange the candidate data in ascending order according to the Euclidean distance d;

[0092] Select the first k candidate data as the nearest neighbor data set;

[0093] The interpolation formula is used to calculate the interpolation result of the data T to be interpolated based on the nearest neighbor data set.

[0094] The interpolation formula is as follows:

[0095]

[0096] Where y(T) is the interpolation result of T, w i is the weight calculated based on the Euclidean distance, x i represents the i-th neighbor data, i = 1, 2, ..., k, d(T, x i ) represents the neighbor data x i The Euclidean distance from T, p is the weight index, which takes a value of 1 or 2.

[0097] Specifically, in one embodiment of the present invention, the outlier filtering uses the k-means algorithm to identify outliers, and the k-means algorithm is used to iteratively cluster the data. After the iteration, the distance between each data point and its cluster center in each cluster is calculated, and the data points with a distance greater than a threshold are regarded as outliers. According to the abnormality of the outlier and the importance of the outlier, the outlier is repaired or directly removed. The repair method can treat the outlier as a missing point and interpolate it using the above-mentioned data interpolation method.

[0098] Specifically, in one embodiment of the present invention, the improved Kalman filter algorithm includes:

[0099] Based on the characteristics of the engine room equipment related to ship operation, a state space model containing key state variables is established. The state space model consists of state equations and observation equations, which respectively describe the evolution and observation process of the system state. Among them, the key state variables include engine speed, engine temperature, fuel consumption rate, exhaust temperature, cooling water temperature and lubricating oil pressure.

[0100] Among them, the state equation is:

[0101] x(k+1)=A(k)x(k)+B(k)u(k)+F(k)d(k)+w(k)

[0102] Observation equation:

[0103] y(k)=C(k)x(k)+v(k)

[0104] In the formula, x(k+1) is the state vector at time k+1, x(k) is the state vector at time k, u(k) is the control input vector, d(k) is the unknown input vector, w(k) is the process noise, A(k) is the state transfer matrix, B(k) is the control input matrix, F(k) is the unknown input matrix, y(k) is the observation vector, C(k) is the observation matrix, and v(k) is the observation noise. This model describes the evolution of the system state and the observation process.

[0105] Obtain the initial state space model parameters, and optimize the parameters through the optimization method to obtain the optimal parameter set;

[0106] Specifically, the initial state space model parameters are estimated based on the maximum likelihood estimation method, and the process includes: constructing a log-likelihood function, maximizing the likelihood function using the Newton-Raphson method, and obtaining initial parameter estimates.

[0107] Specifically, the optimization method is a hybrid optimization method based on particle swarm optimization and simulated annealing. The optimization process is as follows:

[0108] a) Initialize the particle swarm, where each particle represents a set of possible parameter solutions; set the number of particles to N, the parameter dimension to D, and for each particle, its position is represented by X i , X i =[x i1 ,x i2 ,...,x iD ] Its speed is expressed as V i , V i =[v i1 ,v i2 ,...,v iD ]. Let the optimal position of the individual be P i , the global optimal position is G = argmin{f(P i )}, i = 1, 2, ..., N. f represents the fitness function.

[0109] b) Calculate the fitness value for each particle, and use the root mean square error (RMSE) as the fitness function.

[0110] c) Update the individual optimal position and global optimal position of each particle;

[0111] For each particle i:

[0112] If f(X i ) < f(P i ), then P i = X i ;

[0113] If f(P i ) < G, then G = P i .

[0114] d) Update the velocity and position of the particle according to the velocity update formula and the position update formula.

[0115] The update formulas are as follows:

[0116] V i (t + 1) = χ * (ω * V i (t) + c1 * r1 * (P i - X i (t)) + c2 * r2 * (G - X i (t)))

[0117] X i (t + 1) = X i (t) + V i (t + 1)

[0118] Where: χ is the contraction factor, ω is the inertia weight, ω = ω max - (ω max - ω min ) * t / T max ; c1, c2 are acceleration constants; r1, r2 are random numbers uniformly distributed in [0, 1]; t is the current iteration number; T max is the maximum number of iterations.

[0119] Specifically, when adjusting c1 and c2, the following formulas are used for adjustment:

[0120] c1 = c 1min + (c 1max - c 1min ) * (T max - t) / T max

[0121] c2 = c 2max - (c 2max - c 2min ) * (T max - t) / T max .

[0122] e) Apply the simulated annealing operation to the global optimal solution G of each iteration to increase the probability of jumping out of the local optimum:

[0123] Generate a new solution θ after perturbation new =G+σ*N(0,1), where σ is the disturbance intensity and N(0,1) is the standard normal distribution.

[0124] Calculate the energy difference ΔE=f(θ new )-f(G).

[0125] If ΔE<0, G=θ new ; otherwise accept the new solution θ with probability p = exp(-ΔE / T) new , where T is the current temperature.

[0126] The temperature is reduced according to the exponential decay law: T = αT, where α is the cooling coefficient, and its value is 0.9-1.

[0127] f) Repeat steps be until the maximum number of iterations is reached or the convergence condition is met. Output the optimal parameter solution G and the corresponding fitness value f(G).

[0128] The hybrid optimization method improves the convergence speed and global search capability of the algorithm by introducing shrinkage factors, adaptive parameter adjustment and local search strategies. At the same time, the simulated annealing operation enhances the ability of the algorithm to jump out of the local optimum, making it more suitable for dealing with complex parameter optimization problems.

[0129] Iterate the Kalman filter algorithm on the preprocessed data:

[0130] Prediction step: predict the current state based on previous state estimates and control inputs;

[0131]

[0132] P(k|k-1)=A(k-1)P(k-1|k-1)A(k-1) T +Q(k-1)

[0133] Unknown input estimation: Estimate slowly changing and rapidly changing unknown inputs separately;

[0134] M(k)=C(k)P(k|k-1)C(k) T +R(k)

[0135] K d (k)=P(k|k-1)C(k) T M(k) -1

[0136]

[0137]

[0138] Update step: Combine the observations and position input estimates to update the state estimate and error covariance matrix;

[0139] K(k)=P(k|k-1)C(k) T (C(k)(k|k-1)C(k) T +R(k)) -1

[0140]

[0141] P(k|k)=(IK(k)C(k))P(k|k-1)

[0142] Adjustment step: dynamically adjust the process noise covariance matrix and the observation noise covariance matrix according to the innovation sequence;

[0143]

[0144] S(k)=C(k)P(k|k-1)C(k) T +R(k)

[0145] Q(k)=λQ(k-1)+(1-λ)K(k)ε(k)ε(k) T K(k) T

[0146] R(k)=λR(k-1)+(1-λ)(ε(k)ε(k) T -C(k)P(k|k-1)C(k) T )

[0147] In the formula, is the prior state estimate at time k, is the a priori state estimate at time k-1, P(k|k-1) is the a priori error covariance matrix at time k, P(k-1|k-1) is the a priori error covariance matrix at time k-1, Q(k-1) is the process noise covariance matrix, R(k) is the observation noise covariance matrix, M(k) is the innovation covariance matrix, K d (k) is the unknown input gain, For slowly varying unknown input estimates, is the estimation of the rapidly changing unknown input, ρ(k) is the intermittent coefficient matrix, θ(k) is the rapidly changing part parameter, K(k) is the Kalman gain, is the posterior state estimate at time k, P(k|k) is the posterior error covariance matrix at time k, F(k) is the unknown input matrix, I is the identity matrix, ε(k) is the innovation sequence, S(k) is the innovation covariance matrix, and λ is the forgetting factor.

[0148] By extending the observation equation, data from different sources are fused, and the observation noise covariance matrix is ​​adjusted according to the reliability of each data source;

[0149] y(k)=[C1(k);C2(k);...;C a (k)]x(k)+v(k)

[0150] Where, C1(k); C2(k); ...; C a (k) represent the observation matrices of different data sources.

[0151] Output the denoised and fused state estimate as the fused data.

[0152] Specifically, the algorithm takes into account the impact of unknown inputs and estimates slowly changing and rapidly changing unknown inputs separately. The covariance matrix of process noise and observation noise is dynamically adjusted to improve the adaptability of the algorithm. Multi-source data fusion is achieved by expanding the observation equation to improve the accuracy of the estimation.

[0153] Specifically, in one embodiment of the present invention, the feature engineering module includes:

[0154] The feature extraction unit is used to perform signal decomposition on the fused data according to the VMD decomposition algorithm, separate K IMF components from each data, and use the trained autoencoder to perform feature extraction on the K IMF components respectively to obtain the multi-dimensional features of the data;

[0155] The feature selection unit is used to calculate the relative disorder of the multi-dimensional features, sort the multi-dimensional features from small to large according to the relative disorder, and select the first M dimensional features as the features to be fused;

[0156] The feature fusion unit is used to fuse the features to be fused of each data according to the fusion formula to obtain the fused features.

[0157] In this embodiment, the feature extraction unit first uses the variational mode decomposition (VMD) algorithm to decompose the fused data. Each data is separated into K intrinsic mode function (IMF) components. The purpose of this step is to decompose the complex signal into multiple simple components. Then design and train an autoencoder model. The autoencoder is an unsupervised learning algorithm used to learn the effective representation (encoding) of data. The training process uses the following loss function:

[0158]

[0159] In the formula, m is the number of samples, s represents the sth sample, O s Indicates output data, I s Represents input data. When z=1, it means is the weight matrix of the encoder, when z=2, it means is the weight matrix of the decoder, r h is the number of hidden layers of the encoder, r g is the number of hidden layers in the decoder, γ is the weight decay parameter, SG[·] is the prohibition of gradient backpropagation, and h e (s) is the vector representation of the encoder mapping sample s to the latent space, e is the embedding vector, represents the squared L2 norm.

[0160] Use the trained autoencoder to extract features from each IMF component. The specific steps are as follows:

[0161] a) Each IMF component is used as the input of the autoencoder.

[0162] b) Use the encoder part to map the IMF components to the latent space to obtain their compressed representation.

[0163] c) This compressed representation is the extracted feature.

[0164] For each original data, there are now K IMF components, each with its corresponding features. These features are combined to form a multidimensional feature representation of the data.

[0165] Repeat the above process for all fused data, and finally obtain the multi-dimensional feature representation of each data.

[0166] In this embodiment, the loss function of the autoencoder includes three items. The first item is the reconstruction error item, which prompts the encoder to learn effective representations of the input data, and the decoder can recover the original data from these representations; the second item is the regularization item, which prevents overfitting and simplifies the model by penalizing large weight values; the third item is the contrastive learning item, which guides the model to learn more meaningful and structured feature representations. This loss function is designed so that the autoencoder can learn feature representations that can reconstruct the original data and have a specific structure through the joint action of the reconstruction error item and the contrastive learning item.

[0167] Specifically, in this embodiment, the feature selection unit selects the most valuable feature subset from the multidimensional features, and for this purpose introduces a relative chaos calculation method, which comprehensively considers the autocorrelation of the features, the mutual information between the features, and the uncertainty of the features to represent the value of the features. The specific calculation formula is as follows:

[0168]

[0169] In the formula, RD(X i ) is the i-th dimension feature X i The relative disorder degree, AC(X i) is X i The first-order autocorrelation coefficient of For X i The average mutual information of N is the total dimension of multidimensional features, MI(X i ,X j ) is X i and X j The mutual information between i ) is X i The information entropy, α and β are adjustable parameters used to adjust the influence of autocorrelation coefficient and mutual information.

[0170] In the calculation formula of relative disorder, the numerator considers the autocorrelation of the feature. When AC(X i ) is larger, The numerator approaches 1, and the high autocorrelation indicates that the feature is more stable in the time series and is more likely to contain useful information. The denominator comprehensively considers the product of average mutual information, autocorrelation, and mutual information. The average mutual information reflects the overall correlation between the feature and other features. i )×MI(X i )) reflects the joint effect of autocorrelation and mutual information. In the average mutual information calculation, normalization is performed according to the information entropy to make the mutual information of different features comparable.

[0171] After calculating the RD value of each feature, sort all features from small to large by RD value, and select the first M features with the smallest RD value as the features to be fused. The smaller the RD value, the more important the feature. Important features usually have high autocorrelation, high mutual information and low entropy.

[0172] Through the calculation of relative chaos and feature selection, the most valuable information can be effectively extracted from complex multi-source ship data, laying the foundation for subsequent feature fusion and fault prediction.

[0173] Specifically, in this embodiment, the feature fusion unit constructs a fusion formula according to the calculation result of the relative chaos degree, and fuses the selected features to be fused. The fusion formula is as follows:

[0174]

[0175] In the formula, F is the fusion feature, w i is the weight.

[0176] Specifically, the fusion formula uses the relative degree of confusion as the inverse of the weight to implement an adaptive feature fusion method. It can not only effectively integrate the information of multiple features, but also automatically emphasize important features and weaken minor features, thus providing a high-quality, low-dimensional input feature for the ship fault prediction system.

[0177] Specifically, in one embodiment of the present invention, the fault prediction model uses SVM. During pre-training, the penalty parameters and kernel function parameters of the SVM are optimized using an optimization algorithm, and after optimization, the SVM is trained based on a sample set. The optimization algorithm may use a sparrow optimization algorithm. The fusion features are input into the SVM to obtain the fault diagnosis result.

[0178] It should be noted that, in the various modules of the present invention, when executing various algorithms to achieve the purpose of fault prediction, the specific process is as follows: the data acquisition module collects data from multiple cabin equipment through different sources, and the cabin equipment includes the main engine system, the auxiliary starting point system, the fuel system, the cooling system, the lubrication system and the exhaust system. The data preprocessing module preprocesses the original data. The data fusion module uses the improved Kalman filter algorithm to fuse the data from different sources to obtain the fused data, that is, each cabin equipment will have a set of fused time series data. The feature engineering module extracts features from the fused data, decomposes each data signal, obtains k IMF components, and then extracts multiple features from each IMF component. For example, each IMF component extracts B features, and each data finally extracts K+B dimensional features, and then performs feature selection, which is to select the most important and valuable M dimensions from these K+B dimensions, and then each data will obtain M-dimensional features to be fused. When the features are fused, the features to be fused of each data are fused to finally obtain the fused features of each data. Finally, the fused features of all data are input into SVM to perform fault diagnosis on the ship. Since each data represents an engine room equipment, the diagnosis result of the corresponding fused feature is the diagnosis result of the engine room equipment.

[0179] 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. The ship fault prediction system based on multi-source data fusion is characterized by: include: Data acquisition module, used to obtain the original signal data of the engine room equipment related to the ship operation; A data preprocessing module is used to align the original signal data from different sources. After the data is aligned, the original signal data after the data alignment is preprocessed according to the preprocessing steps to obtain the preprocessed data; The data fusion module is used to perform multi-source fusion on the pre-processed data using an improved Kalman filter algorithm to obtain fused data; The feature engineering module is used to extract and select multi-dimensional features from the fused data, and fuse the selected features to obtain fused features; The fault prediction module is used to receive the fused features and perform ship fault prediction according to the fused features based on a pre-trained fault prediction model.

2. The ship fault prediction system based on multi-source data fusion according to claim 1, characterized in that: The data preprocessing module includes: The data alignment unit is used to perform preliminary checks on the original signal data from different sources, standardize the timestamps, create a unified time index, map the original signal data from different sources to the unified time index, make the original signal data in time series format, and complete data alignment; The data preprocessing unit is used to preprocess the original signal data after data alignment, including data interpolation and outlier filtering, to obtain preprocessed data.

3. The ship fault prediction system based on multi-source data fusion according to claim 1, characterized in that: The improved Kalman filter algorithm includes: Based on the characteristics of the engine room equipment related to ship operation, a state space model containing key state variables is established. The state space model consists of state equations and observation equations, which respectively describe the evolution and observation process of the system state. Among them, the key state variables include engine speed, engine temperature, fuel consumption rate, exhaust temperature, cooling water temperature and lubricating oil pressure. Obtain the initial state space model parameters, and optimize the parameters through the optimization method to obtain the optimal parameter set; Iterate the Kalman filter algorithm on the preprocessed data: Prediction step: predict the current state based on previous state estimates and control inputs; Unknown input estimation: Estimate slowly changing and rapidly changing unknown inputs separately; Update step: Combine the observations and position input estimates to update the state estimate and error covariance matrix; Adjustment step: dynamically adjust the process noise covariance matrix and the observation noise covariance matrix according to the innovation sequence; By extending the observation equation, data from different sources are fused, and the observation noise covariance matrix is ​​adjusted according to the reliability of each data source; Output the denoised and fused state estimate as the fused data.

4. The ship fault prediction system based on multi-source data fusion according to claim 3, characterized in that: In the state space model: Equation of state: x(k+1)=A(k)x(k)+B(k)u(k)+F(k)d(k)+w(k) Observation equation: y(k)=C(k)x(k)+v(k) Where x(k+1) is the state vector at time k+1, x(k) is the state vector at time k, u(k) is the control input vector, d(k) is the unknown input vector, w(k) is the process noise, A(k) is the state transfer matrix, B(k) is the control input matrix, F(k) is the unknown input matrix, y(k) is the observation vector, C(k) is the observation matrix, and v(k) is the observation noise; Kalman filter algorithm iteration: Prediction steps: P(k|k-1)=A(k-1)P(k-1|k-1)A(k-1) T +Q(k-1) Unknown input estimation: M(k)=C(k)P(k|k-1)C(k) T +R(k) K d (k)=P(k|k-1)C(k) T M(k) -1 Update steps: K(k)=P(k|k-1)C(k) T (C(k)(k|k-1)C(k) T +R(k)) -1 P(k|k)=(IK(k)C(k))P(k|k-1) Adjustment steps: S(k)=C(k)P(k|k-1)C(k) T +R(k) Q(k)=λQ(k-1)+(1-λ)K(k)ε(k)ε(k) T K(k) T R(k)=λR(k-1)+(1-λ)(ε(k)ε(k) T -C(k)P(k|k-1)C(k) T ) In the formula, is the prior state estimate at time k, is the a priori state estimate at time k-1, P(k|k-1) is the a priori error covariance matrix at time k, P(k-1|k-1) is the a priori error covariance matrix at time k-1, Q(k-1) is the process noise covariance matrix, R(k) is the observation noise covariance matrix, M(k) is the innovation covariance matrix, K d (k) is the unknown input gain, For slowly varying unknown input estimates, is the estimation of the rapidly changing unknown input, ρ(k) is the intermittent coefficient matrix, θ(k) is the rapidly changing part parameter, K(k) is the Kalman gain, is the posterior state estimate at time k, P(k|k) is the posterior error covariance matrix at time k, F(k) is the unknown input matrix, I is the identity matrix, ε(k) is the innovation sequence, S(k) is the innovation covariance matrix, and λ is the forgetting factor; Extend the observation equation for data fusion: y(k)=[C1(k);C2(k);...;C a (k)]x(k)+v(k) Where, C1(k); C2(k); ...; C a (k) represent the observation matrices of different data sources.

5. The ship fault prediction system of multi-source data fusion according to claim 3, characterized in that: The initial state space model parameters are estimated based on the maximum likelihood estimation method, and the optimization method is a hybrid optimization method based on particle swarm optimization and simulated annealing.

6. The ship fault prediction system of multi-source data fusion according to claim 1, characterized in that: Feature engineering modules include: The feature extraction unit is used to perform signal decomposition on the fused data according to the VMD decomposition algorithm, separate K IMF components from each data, and use the trained autoencoder to perform feature extraction on the K IMF components respectively to obtain the multi-dimensional features of the data; The feature selection unit is used to calculate the relative disorder of the multi-dimensional features, sort the multi-dimensional features from small to large according to the relative disorder, and select the first M dimensional features as the features to be fused; The feature fusion unit is used to fuse the features to be fused of each data according to the fusion formula to obtain the fused features.

7. The ship fault prediction system of multi-source data fusion according to claim 6, characterized in that: The loss function of the autoencoder during training is: In the formula, m is the number of samples, s represents the sth sample, O s Indicates output data, I s Represents input data. When z=1, it means is the weight matrix of the encoder, when z=2, it means is the weight matrix of the decoder, r h is the number of hidden layers of the encoder, r g is the number of hidden layers in the decoder, γ is the weight decay parameter, SG[·] is the prohibition of gradient backpropagation, and h e (s) is the vector representation of the encoder mapping sample s to the latent space, e is the embedding vector, represents the squared L2 norm.

8. The ship fault prediction system of multi-source data fusion according to claim 6, characterized in that: The relative disorder calculation formula is: In the formula, RD(X i ) is the i-th dimension feature X i The relative disorder degree, AC(X i ) is X i The first-order autocorrelation coefficient of For X i The average mutual information of N is the total dimension of multidimensional features, MI(X i ,X j ) is X i and X j The mutual information between i ) is X i The information entropy, α and β are adjustable parameters used to adjust the influence of autocorrelation coefficient and mutual information.

9. The ship fault prediction system of multi-source data fusion according to claim 8, characterized in that: The fusion formula is: In the formula, F is the fusion feature, w i is the weight.

10. The ship fault prediction system of multi-source data fusion according to claim 1, characterized in that: The fault prediction model is SVM. During pre-training, the optimization algorithm is used to optimize the penalty parameters and kernel function parameters of SVM. After optimization, the SVM is trained based on the sample set.

Images