Ship propulsion shafting fault identification method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a ship propulsion shafting fault identification method and system, electronic equipment and a storage medium, and belongs to the field of intelligent fault identification. According to the method, multi-modal monitoring signals of the ship propulsion shafting are obtained, the multi-modal monitoring signals comprise multi-source vibration signals and sound signals, the multi-source vibration signals comprise single vibration signals of multiple different monitoring positions, space-time correlation analysis and weighted fusion are conducted on the multi-source vibration signals, and fused vibration signals are obtained; the enhancement of the vibration signal is realized, and the credibility is improved; the ship propulsion shafting fault identification model is used for processing the processed multi-modal monitoring signals to obtain a fault identification result, dynamic weighted fusion is performed on multi-modal features based on a dynamic routing algorithm in the model, the importance of different modal signals is fully considered, the feature expression capability is enhanced, and the fault identification accuracy is improved. And the accuracy of ship propulsion shafting fault identification is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent fault identification, and in particular to a method, system, electronic device and storage medium for identifying a ship propulsion shafting fault. Background Art

[0002] As a core component of the ship's power system, the ship's propulsion shaft system undertakes the key task of transmitting the power generated by the main engine to the propeller. Due to its harsh working environment and heavy load, the performance of the shaft system equipment gradually declines over time. Once the performance declines to a critical point, it may lead to equipment failure, and then cause system performance degradation, equipment collapse or even system paralysis, causing economic losses, casualties and environmental pollution.

[0003] At present, the fault identification methods of ship propulsion shaft systems mainly rely on traditional monitoring technologies, which are often time-consuming and fail to make full use of modern diagnostic technologies based on deep learning, which is not conducive to real-time monitoring and rapid diagnosis. In addition, the fault identification methods in related technologies mostly use single modal signals, such as vibration, acoustic or current signals, as input features for analysis. However, the single modal signal contains limited information, and in the complex working environment of the ship, it is easily interfered by external noise and equipment vibration, resulting in low diagnostic accuracy and insufficient robustness of the model.

[0004] In response to the above problems, although some studies have attempted to use multimodal signals for fault identification, they have failed to consider the sensitivity of different monitoring signals to different fault types, resulting in low accuracy in ship propulsion shaft fault identification. Summary of the invention

[0005] The main purpose of the embodiments of the present application is to propose a method, system, electronic device and storage medium for identifying a ship propulsion shaft system fault, aiming to improve the accuracy of identifying a ship propulsion shaft system fault.

[0006] To achieve the above-mentioned purpose, an embodiment of the present application provides a method for identifying a ship propulsion shaft fault, comprising:

[0007] Acquire a multimodal monitoring signal of a ship propulsion shaft system, wherein the multimodal monitoring signal includes a multi-source vibration signal and a sound signal, and the multi-source vibration signal includes single vibration signals at multiple different monitoring positions;

[0008] Performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, and replacing the multi-source vibration signals in the multimodal monitoring signal with the fused vibration signal;

[0009] Inputting the multimodal monitoring signal into a ship propulsion shaft system fault identification model to obtain a ship propulsion shaft system fault identification result;

[0010] The ship propulsion shafting fault identification model specifically performs the following steps:

[0011] Extracting features from each modal signal of the multimodal monitoring signal to obtain a feature vector of each modality;

[0012] Based on the dynamic routing algorithm, the feature vectors of each mode are dynamically weighted and fused to obtain the fault identification result.

[0013] In some embodiments, before the step of performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, the ship propulsion shafting fault identification method further includes the following steps:

[0014] Performing noise reduction processing on each signal in the multi-source vibration signal to obtain a noise-reduced multi-modal monitoring signal;

[0015] The multimodal monitoring signal after noise reduction is normalized to obtain a normalized multimodal monitoring signal.

[0016] In some embodiments, performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal comprises the following steps:

[0017] Performing a spatiotemporal correlation analysis on the multi-source vibration signals to determine a first weight of each single vibration signal;

[0018] The multi-source vibration signals are weightedly fused according to the first weights of the single vibration signals to obtain a fused vibration signal.

[0019] In some embodiments, the performing spatiotemporal correlation analysis on the multi-source vibration signals to determine the first weight of each single vibration signal comprises the following steps:

[0020] Determining the time deviation between each single vibration signal according to the signal source position of each single vibration signal in the multi-source vibration signal;

[0021] Correcting each of the single vibration signals according to the time deviation to obtain a time-synchronized single vibration signal;

[0022] Calculate the cross-correlation energy between each single vibration signal after time synchronization;

[0023] Determining the total correlation energy of each single vibration signal according to the multiple cross-correlation energies of the single vibration signal;

[0024] The first weight of each single vibration signal is determined according to the total correlation energy of each single vibration signal.

[0025] In some embodiments, the step of determining the time deviation between each single vibration signal according to the signal source position of each single vibration signal in the multi-source vibration signal comprises the following steps:

[0026] According to the signal source positions of multiple single vibration signals, a spatial coordinate matrix is ​​constructed;

[0027] Determine the target coordinate system according to the signal source position of one of the single vibration signals, and transform the signal source positions of each of the single vibration signals into the target coordinate system according to the spatial coordinate matrix to obtain the position transformation matrix of each single vibration signal;

[0028] According to the position conversion matrix of each single vibration signal, a time deviation between the single vibration signal and the single vibration signal corresponding to the target coordinate system is determined.

[0029] In some embodiments, the multimodal monitoring signal includes a fused vibration signal and a sound signal, and the feature extraction of each modal signal of the multimodal monitoring signal is performed to obtain a feature vector of each modality, including the following steps:

[0030] Inputting the fused vibration signal into a first time convolutional neural network module for feature extraction to obtain a vibration feature vector;

[0031] Inputting the sound signal into a second time convolutional neural network module for feature extraction to obtain a sound feature vector;

[0032] Among them, the first temporal convolutional neural network module and the second temporal convolutional neural network module both include multiple residual-connected temporal convolution blocks.

[0033] In some embodiments, the dynamic weighted fusion of the feature vectors of each mode based on the dynamic routing algorithm to obtain the fault identification result includes the following steps:

[0034] Reconstruct the feature vectors of each mode respectively to obtain the feature reconstruction vectors of each mode;

[0035] Using a dynamic routing algorithm to perform modal dynamic weight allocation on the feature reconstruction vector of each modality to obtain a second weight of each modality;

[0036] A weighted calculation is performed on the plurality of feature reconstruction vectors according to the second weight of each mode to obtain a prediction vector, wherein the prediction vector is used to determine a fault identification result.

[0037] To achieve the above-mentioned purpose, another aspect of the embodiment of the present application provides a ship propulsion shaft fault identification system, comprising:

[0038] The first module is used to obtain a multi-modal monitoring signal of a ship propulsion shaft system, wherein the multi-modal monitoring signal includes a multi-source vibration signal and a sound signal, and the multi-source vibration signal includes a single vibration signal at a plurality of different monitoring positions;

[0039] The second module is used to perform spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, and replace the multi-source vibration signal in the multimodal monitoring signal with the fused vibration signal;

[0040] The third module is used to input the multimodal monitoring signal into a ship propulsion shaft system fault identification model to obtain a ship propulsion shaft system fault identification result;

[0041] The ship propulsion shafting fault identification model is specifically used for:

[0042] Extracting features from each modal signal of the multimodal monitoring signal to obtain a feature vector of each modality;

[0043] Based on the dynamic routing algorithm, the feature vectors of each mode are dynamically weighted and fused to obtain the fault identification result.

[0044] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes an electronic device, which includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program implements the method described in the above embodiment when executed by the processor.

[0045] To achieve the above-mentioned purpose, another aspect of an embodiment of the present application proposes a storage medium, which is a computer-readable storage medium used for computer-readable storage, and the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method described in the above embodiment.

[0046] The present application proposes a ship propulsion shaft system fault identification method, system, electronic device and storage medium, which obtains a multi-modal monitoring signal of the ship propulsion shaft system, wherein the multi-modal monitoring signal includes a multi-source vibration signal and a sound signal, and the multi-source vibration signal includes a single vibration signal of multiple different monitoring positions, performs spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signal to obtain a fused vibration signal, thereby enhancing the vibration signal and improving its credibility; uses a ship propulsion shaft system fault identification model to process the processed multi-modal monitoring signal to obtain a fault identification result, and in the model, dynamically weighted fusion of multi-modal features is performed based on a dynamic routing algorithm, fully considering the importance of different modal signals, enhancing the representation capability of features, and improving the accuracy of ship propulsion shaft system fault identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a method for identifying a ship propulsion shafting fault provided by an embodiment of the present application;

[0048] Figure 2 It is a flow chart of a ship propulsion shafting fault identification model processing method provided in an embodiment of the present application;

[0049] Figure 3 It is a schematic diagram of the structure of a ship propulsion shafting fault identification model provided in an embodiment of the present application;

[0050] Figure 4 Schematic diagram of the TCN residual block structure provided in an embodiment of the present application;

[0051] Figure 5 Schematic diagram of the network architecture of the multimodal feature weighted fusion module provided in the embodiment of the present application;

[0052] Figure 6 It is a schematic diagram of the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0054] It should be noted that, although the functional modules are divided in the system and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0056] The embodiments of the present application provide a method, system, electronic device and storage medium for identifying a ship propulsion shaft system fault, aiming to improve the accuracy of identifying a ship propulsion shaft system fault.

[0057] The ship propulsion shaft system fault identification method, system, electronic device and storage medium provided in the embodiments of the present application are specifically illustrated through the following embodiments. First, the ship propulsion shaft system fault identification method in the embodiments of the present application is described.

[0058] The ship propulsion shaft fault identification method provided in the embodiment of the present application relates to the field of intelligent fault identification. The ship propulsion shaft fault identification method provided in the embodiment of the present application can be applied to the terminal, can also be applied to the server side, and can also be software running in the terminal or the server side. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured as a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application that implements the ship propulsion shaft fault identification method, etc., but is not limited to the above forms.

[0059] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0060] Figure 1 is an optional flow chart of a method for identifying a ship propulsion shafting fault provided in an embodiment of the present application. Figure 1 The method may include but is not limited to steps S101 to S103.

[0061] Step S101, obtaining a multi-modal monitoring signal of a ship propulsion shaft system, wherein the multi-modal monitoring signal includes a multi-source vibration signal and a sound signal, and the multi-source vibration signal includes a single vibration signal at a plurality of different monitoring positions;

[0062] Step S102, performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, and replacing the multi-source vibration signals in the multi-modal monitoring signal with the fused vibration signal;

[0063] Step S103: input the multi-modal monitoring signal into a ship propulsion shaft system fault identification model to obtain a ship propulsion shaft system fault identification result.

[0064] In step S101 of some embodiments, multiple single vibration signals of the ship propulsion shaft system are collected by multiple vibration sensors arranged at different monitoring positions to form a multi-source vibration signal. The sound signal of the ship propulsion shaft system is collected by an acoustic sensor. The multimodal monitoring signal of this embodiment includes a multi-source vibration signal of a vibration mode and a sound signal of an acoustic mode. It can be understood that the multimodal monitoring signal of the embodiment of the present application can also include signals of more different types of modes based on actual monitoring needs.

[0065] In step S102 of some embodiments, time-space correlation analysis is a method for studying the relationship between data in time and space. In this embodiment, the monitoring signal of the ship propulsion shaft system is continuously collected. The monitoring signal is a time series signal with time attributes, while the multi-source vibration signal is composed of vibration signals of sensors at different positions and has space attributes. Based on the time-space correlation analysis, the multi-source vibration signal is fused to enhance the vibration signal and improve the credibility of the vibration mode.

[0066] In step S103 of some embodiments, this embodiment constructs a ship propulsion shaft system fault identification model, which is a classification model for performing feature extraction and feature classification based on the input multi-modal monitoring signal, and outputting the fault identification result of the ship propulsion shaft system. The fault identification result is used to determine the state type label of the ship propulsion shaft system, for example, no fault and fault, and the fault type under the fault. The ship propulsion shaft system fault identification model includes two parts: feature extraction and feature classification. The feature extraction part can be implemented based on a time convolutional neural network (TCN). The time convolutional neural network can analyze the time series features in the input data, and perform feature extraction of various modes such as vibration and sound, capture the long-term dependency of the modal time series signal, and mine early fault features. Feature classification can be implemented based on a neural network with a dynamic routing algorithm. The dynamic routing algorithm is a mechanism for allocating information and determining the path for information transmission. It is particularly suitable for new neural network architectures such as capsule networks. The dynamic routing algorithm is mainly used in neural networks to dynamically determine how to allocate information to different network parts or paths based on the characteristics of the input data, thereby improving adaptability to different modal features. For example, the feature classification part uses a capsule network and a dynamic routing algorithm between capsules.

[0067] The ship propulsion shafting fault identification model of this embodiment is trained in the following way:

[0068] The data set is divided into a training set and a test set according to a preset ratio. The data set includes a large number of samples. Each sample includes a multimodal monitoring signal after vibration signal fusion processing and a sample label. The sample label is the state of the ship propulsion shaft system corresponding to the multimodal monitoring signal, such as no fault, fault, and fault type.

[0069] After the initialized ship propulsion shaft fault identification model is trained using the training set, the trained model is tested using the test set to obtain an applicable ship propulsion shaft fault identification model.

[0070] The specific process of training the initialized ship propulsion shaft fault identification model with the training set is as follows:

[0071] The training set is input into the initialized ship propulsion shafting fault recognition model to obtain a predicted label vector;

[0072] The recognition accuracy of the ship propulsion shaft fault recognition model is calculated based on the predicted label vector and the true label vector;

[0073] If the recognition accuracy is less than the threshold accuracy, the model parameters are adjusted and training is performed again until the number of training times is greater than the threshold number of times or the recognition accuracy after training is greater than or equal to the threshold accuracy. At this time, a trained ship propulsion shafting fault recognition model is obtained.

[0074] In some embodiments, before step S102, the ship propulsion shafting fault identification method of the embodiment of the present application may also include but is not limited to the following steps:

[0075] Step S301, performing noise reduction processing on each signal in the multi-source vibration signal to obtain a noise-reduced multi-modal monitoring signal;

[0076] Step S302, normalizing the denoised multimodal monitoring signal to obtain a normalized multimodal monitoring signal.

[0077] In this embodiment, each signal in the multi-source vibration signal can be input into a suitable signal filter for noise reduction processing to remove noise and outliers in the data. Then the multi-modal monitoring signal is normalized so that data with different characteristics are at the same level, which is convenient for subsequent model calculation and improves the model convergence speed. Specifically, each single vibration signal of the multi-source vibration signal can be normalized first, and then each modal signal in the multi-modal monitoring signal can be normalized.

[0078] Please refer to Figure 2 ,The ship propulsion shafting fault identification model specifically performs the following steps:

[0079] Step S201, extracting features from each modal signal of the multimodal monitoring signal to obtain a feature vector of each modality;

[0080] Step S202 , dynamically weighted fusion is performed on the feature vectors of each mode based on a dynamic routing algorithm to obtain a fault identification result.

[0081] In this embodiment, after preprocessing operations such as noise reduction and normalization are performed on the multimodal monitoring signal, and the multi-source vibration signal in the multimodal monitoring signal is processed into a fused vibration signal, the multimodal monitoring signal is input into the ship propulsion shafting fault identification model to obtain the fault identification result of the ship propulsion shafting. The ship propulsion shafting fault identification model performs dynamic weighted fusion of multimodal features based on a dynamic routing algorithm, fully considers the importance of different modal signals, enhances the performance of features, and improves the accuracy of fault identification.

[0082] In some embodiments, in step S102, the step of performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal may include but is not limited to the following steps:

[0083] Step S401, performing spatiotemporal correlation analysis on multi-source vibration signals to determine a first weight of each single vibration signal;

[0084] Step S402, weighted fusion of multi-source vibration signals is performed according to the first weights of the individual single vibration signals to obtain a fused vibration signal.

[0085] In step S401 of some embodiments, the step of performing spatiotemporal correlation analysis on the multi-source vibration signals to determine the first weight of each single vibration signal may include but is not limited to the following steps:

[0086] Step S501, determining the time deviation between each single vibration signal according to the signal source position of each single vibration signal in the multi-source vibration signal;

[0087] Step S502, correcting each single vibration signal according to the time deviation to obtain a time-synchronized single vibration signal;

[0088] Step S503, calculating the cross-correlation energy between each pair of single vibration signals after time synchronization;

[0089] Step S504, determining the total correlation energy of the single vibration signal according to the multiple cross-correlation energies of each single vibration signal;

[0090] Step S505: determining the first weight of each single vibration signal according to the total correlation energy of each single vibration signal.

[0091] In this embodiment, first, according to the signal source position of each single vibration signal in the multi-source vibration signal, the time deviation between each single vibration signal is determined. By way of example, the embodiment of the present application can use three vibration sensors to collect three single vibration signals, namely vibration signal 1, vibration signal 2 and vibration signal 3. One of the single vibration signals (vibration signal 1) can be used as the time reference to calculate the time deviation between the other two single vibration signals and the single vibration signal, that is, to obtain the time deviation between each single vibration signal, the time deviation of vibration signal 1 is 0, and the time deviation of vibration signal 2 and vibration signal 1 is τ 1 , the time deviation between vibration signal 3 and vibration signal 1 is τ 2 .

[0092] Secondly, each single vibration signal is corrected according to the time deviation to obtain a single vibration signal with time synchronization. For example, in combination with the time deviation, the corrected vibration signal 2 is expressed as y(t+τ 1 )=y(t)·δ(τ 1 ), the corrected vibration signal 3 is expressed as z(t+τ 2 )=z(t)·δ(τ 2 ), where δ(t) is the Dirac function, which is used to represent the time shift of the signal. The time synchronization signals of the three vibration sensors are x(t), y(t+τ 1 ), z(t+τ 2 ).

[0093] Then, the cross-correlation energy between each single vibration signal after time synchronization is calculated. For example, the discrete signals x(t) and y(t+τ 1 ) is calculated as follows:

[0094]

[0095] Among them, R xy is the cross-correlation function of the vibration signal, i represents the ordinal number of the cross-correlation function, and the cross-correlation function calculation formula is as follows:

[0096]

[0097] Where N is the number of sampling points, k represents the maximum time delay value, and m represents the index variable of the time delay, which varies in the range of 1-k.

[0098] Assume that a cross-correlation operation is performed on each signal, and the energy of the signal is E ij , then the total correlation energy between single vibration signal i and single vibration signal is expressed as follows:

[0099]

[0100] Among them, i represents the code of a single vibration signal, j represents a signal other than the single vibration signal i, and i≠j.

[0101] Assume there are three single vibration signals. When the weight p of single vibration signal i is i When it is proportional to the energy of the correlation function, then:

[0102] p 1 :p 2 :p 3 =E 1 :E 2 :E 3 ;

[0103] Normalize to get:

[0104] p 1 +p 2 +p 3 =1;

[0105] According to the above operation, the first weight of the vibration sensor signal at each position can be obtained, which is expressed as follows:

[0106]

[0107] In step S402 of some embodiments, weighted calculation is performed according to the first weights of the individual vibration signals to obtain a fused vibration signal, which is expressed as:

[0108] X=p 1 x+p 2 Y+p 3 z;

[0109] Among them, x, y, and z are the single vibration signals of three vibration sensors respectively.

[0110] At this point, the weighted fusion of multi-source vibration signals is completed, and the weighted fused signal is obtained.

[0111] In some embodiments, in step S501, the step of determining the time deviation between each single vibration signal according to the signal source position of each single vibration signal in the multi-source vibration signal may include but is not limited to the following steps:

[0112] Step S601, constructing a spatial coordinate matrix according to the signal source positions of multiple single vibration signals;

[0113] Step S602, determining a target coordinate system according to a signal source position of one of the single vibration signals, and transforming the signal source positions of each single vibration signal into the target coordinate system according to a spatial coordinate matrix, to obtain a position transformation matrix of each single vibration signal;

[0114] Step S603: determining the time deviation between the single vibration signal and the single vibration signal corresponding to the target coordinate system according to the position conversion matrix of each single vibration signal.

[0115] In this embodiment,

[0116] With the signal source as the origin, a spatial coordinate system is established to obtain the spatial coordinates of multiple sensors. This embodiment combines the common mechanical system vibration sensor layout principles and intends to use three vibration sensors at horizontal, vertical, and arbitrary positions to monitor the vibration of the ship propulsion shaft system. The spatial coordinate matrix of the three vibration sensors (i.e., signal sources) is:

[0117]

[0118] Among them, X 1 , X 2 , X 3 Represents the horizontal coordinates of the three vibration sensors respectively; Y 1 , Y 2 , Y 3 Represents the vertical coordinates of the three vibration sensors; Z 1 , Z 2 , Z 3 Represents the vertical coordinates of the three vibration sensors; b 1 、c 1 、a 1 、c 2 、a 3 、b 3 、c 3 etc. represent the specific corresponding coordinate values ​​respectively.

[0119] The spatial information of the three vibration sensors is unified into the coordinate system of sensor 1 to eliminate the time deviation between different sensors. The formula is as follows:

[0120]

[0121] Spatial position correlation is used to estimate the time deviation between two sensors. For example, taking sensor 1 as the reference, the time deviation of sensor 2 and sensor 3 relative to sensor 1 is expressed as follows:

[0122]

[0123] Among them, τ 1 , τ 2 They respectively represent the time deviation of sensor 2 and sensor 3 compared with sensor 1, that is, the time deviation of single vibration signal 2 and single vibration signal 3 compared with single vibration signal 1.

[0124] Substituting the coordinate values, we get:

[0125]

[0126] In some embodiments, the multimodal monitoring signal includes a fused vibration signal and a sound signal. In step S201, the steps of extracting features from each modal signal of the multimodal monitoring signal to obtain a feature vector of each modality may include but are not limited to the following steps:

[0127] Step S701, inputting the fused vibration signal into a first time convolutional neural network module for feature extraction to obtain a vibration feature vector;

[0128] Step S702, inputting the sound signal into a second time convolutional neural network module for feature extraction to obtain a sound feature vector;

[0129] Among them, the first time convolutional neural network module and the second time convolutional neural network module both include multiple residual connected temporal convolution blocks.

[0130] Please refer to Figure 3 , the fused vibration signal and the preprocessed sound signal are separately input into two parallel TCN modules (i.e., temporal convolutional neural network modules) for feature extraction and time series feature analysis.

[0131] The TCN module consists of multiple TCN residual blocks (i.e., residual connected temporal convolution blocks) structures. Please refer to Figure 4 The TCN residual block consists of a main path and a residual connection. The main path includes an expanded causal convolution layer, a weight normalization layer, a ReLU activation function, a Dropout layer, etc., which are used to extract features and analyze the timing features of the input time series signal. The residual connection path contains a 1*1 convolution layer to make up for the difference between the input and output dimensions and capture the long-term dependency of the timing signal.

[0132] After the signal passes through multiple TCN residual blocks, the outputs of the main path and residual connection in the TCN residual block are added to obtain the vector output of various modal features such as vibration and acoustics.

[0133] In some embodiments, in step S202, the step of performing dynamic weighted fusion on the feature vectors of each mode based on the dynamic routing algorithm to obtain a fault identification result may include but is not limited to the following steps:

[0134] Step S801, reconstructing the feature vectors of each mode respectively to obtain the feature reconstruction vectors of each mode;

[0135] Step S802, using a dynamic routing algorithm to perform modality dynamic weight allocation on the feature reconstruction vectors of each modality to obtain a second weight of each modality;

[0136] Step S803 , performing weighted calculation on multiple feature reconstruction vectors according to the second weight of each mode to obtain a prediction vector, wherein the prediction vector is used to determine the fault identification result.

[0137] In this embodiment, please continue to refer to Figure 3 In this embodiment, a multimodal feature weighted fusion module is constructed based on a capsule network structure to fuse and analyze the input features to obtain a prediction vector. The multimodal feature weighted fusion module includes a main capsule layer, a dynamic routing algorithm module, and a conditional capsule layer. The main capsule layer is used to reconstruct the feature vectors of each mode to obtain feature reconstruction vectors of each mode such as sound and vibration. Through feature reconstruction, features with stronger correlation with the target variable can be generated, thereby improving the prediction performance and generalization ability of the model. The reconstructed features can better capture the laws in the data, making the model more accurate and stable. The dynamic routing algorithm module is used to perform modal dynamic weight allocation on the feature reconstruction vectors of each mode output by the main capsule layer to obtain the second weight of each mode, and output it to the conditional capsule layer. The conditional capsule layer is used to perform weighted summation on multiple feature reconstruction vectors according to the second weight of each mode, and output a prediction vector. Among them, the output prediction vector has size and direction, and the direction represents different fault labels; its modulus represents the probability of different fault labels. The fault type represented by the vector with the largest modulus is selected, which is the fault identification result of the ship propulsion shaft system.

[0138] Specifically, the network architecture of the multimodal feature weighted fusion module is as follows: Figure 5 As shown, the implementation process is as follows:

[0139] The modal vectors output by the temporal convolutional neural network module are input into the main capsule layer for reconstruction to obtain the reconstructed vector P i ;

[0140] The vector P i Squash compression is performed to obtain S i , the compression operation is expressed as follows:

[0141]

[0142] Construct a transformation matrix for the input vector S i The conversion operation is: S′ i =W i ·S i , where S i is the transformed vector, W i is the transformation matrix, i is the current capsule number in the main capsule layer;

[0143] Initialize the coupling coefficient temporary variable Where j is the current capsule ordinal number in the conditional capsule layer;

[0144] The Softmax function is used to calculate the weight between the main capsule and the conditional capsule. The specific calculation method of the weight is as follows:

[0145]

[0146] Among them, k is the total number of conditional capsules;

[0147] Calculate the prediction vector D of all conditional capsules j , prediction vector D j The specific calculation is as follows:

[0148]

[0149] Update the coupling coefficient temporary variable The update process is:

[0150] The weights are updated iteratively until the predefined number of routes is reached, and the output vector D after dynamic weighted fusion is obtained. j .

[0151] The embodiment of the present application also provides a ship propulsion shaft fault identification system, including:

[0152] The first module is used to obtain a multi-modal monitoring signal of a ship propulsion shaft system, wherein the multi-modal monitoring signal includes a multi-source vibration signal and a sound signal, and the multi-source vibration signal includes a single vibration signal at multiple different monitoring positions;

[0153] The second module is used to perform spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, and replace the multi-source vibration signals in the multi-modal monitoring signal with the fused vibration signal;

[0154] The third module is used to input the multi-modal monitoring signal into the ship propulsion shaft system fault identification model to obtain the fault identification result of the ship propulsion shaft system;

[0155] Among them, the ship propulsion shaft fault identification model is specifically used for:

[0156] Extract features of each modal signal of the multimodal monitoring signal respectively to obtain a feature vector of each modality;

[0157] Based on the dynamic routing algorithm, the feature vectors of each mode are dynamically weighted and fused to obtain the fault identification result.

[0158] It can be understood that the contents of the above-mentioned ship propulsion shaft system fault identification method embodiment are all applicable to the present system embodiment, the functions specifically implemented by the present system embodiment are the same as those in the above-mentioned ship propulsion shaft system fault identification method embodiment, and the beneficial effects achieved are also the same as the beneficial effects achieved by the above-mentioned ship propulsion shaft system fault identification method embodiment.

[0159] The embodiment of the present application also provides an electronic device, the electronic device comprising: a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory, and the program is executed by the processor to realize the above-mentioned ship propulsion shaft system fault identification method. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0160] See also Figure 6 , Figure 6 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0161] The processor 601 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application;

[0162] The memory 602 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 602, and the processor 601 calls and executes the ship propulsion shafting fault identification method of the embodiment of the present application;

[0163] Input / output interface 603, used to implement information input and output;

[0164] Communication interface 604, used to realize communication interaction between the device and other devices, which can be realized by wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0165] Bus 605 , which transmits information between various components of the device (e.g., processor 601 , memory 602 , input / output interface 603 , and communication interface 604 );

[0166] The processor 601 , the memory 602 , the input / output interface 603 and the communication interface 604 are connected to each other in communication within the device via a bus 605 .

[0167] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium used for computer-readable storage. The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the above-mentioned ship propulsion shaft system fault identification method.

[0168] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0170] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0171] The system embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0172] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0173] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0174] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0175] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0176] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0178] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0179] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A method for identifying a ship propulsion shaft fault, characterized in that: The following steps are involved: Acquire a multimodal monitoring signal of a ship propulsion shaft system, wherein the multimodal monitoring signal includes a multi-source vibration signal and a sound signal, and the multi-source vibration signal includes single vibration signals at multiple different monitoring positions; Performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, and replacing the multi-source vibration signals in the multimodal monitoring signal with the fused vibration signal; Inputting the multimodal monitoring signal into a ship propulsion shaft system fault identification model to obtain a ship propulsion shaft system fault identification result; The ship propulsion shafting fault identification model specifically performs the following steps: Extracting features from each modal signal of the multimodal monitoring signal to obtain a feature vector of each modality; Based on the dynamic routing algorithm, the feature vectors of each mode are dynamically weighted and fused to obtain the fault identification result.

2. The method for identifying ship propulsion shafting faults according to claim 1, characterized in that: Before the step of performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, the ship propulsion shafting fault identification method further includes the following steps: Performing noise reduction processing on each signal in the multi-source vibration signal to obtain a noise-reduced multi-modal monitoring signal; The multimodal monitoring signal after noise reduction is normalized to obtain a normalized multimodal monitoring signal.

3. The method for identifying ship propulsion shafting faults according to claim 1, characterized in that: The step of performing spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal comprises the following steps: Performing a spatiotemporal correlation analysis on the multi-source vibration signals to determine a first weight of each single vibration signal; The multi-source vibration signals are weightedly fused according to the first weights of the single vibration signals to obtain a fused vibration signal.

4. The method for identifying ship propulsion shafting faults according to claim 1, characterized in that: The step of performing spatiotemporal correlation analysis on the multi-source vibration signals to determine the first weight of each single vibration signal comprises the following steps: Determining the time deviation between each single vibration signal according to the signal source position of each single vibration signal in the multi-source vibration signal; Correcting each of the single vibration signals according to the time deviation to obtain a time-synchronized single vibration signal; Calculate the cross-correlation energy between each single vibration signal after time synchronization; Determining the total correlation energy of each single vibration signal according to the multiple cross-correlation energies of the single vibration signal; The first weight of each single vibration signal is determined according to the total correlation energy of each single vibration signal.

5. The method for identifying ship propulsion shafting faults according to claim 4, characterized in that: Determining the time deviation between each single vibration signal according to the signal source position of each single vibration signal in the multi-source vibration signal comprises the following steps: According to the signal source positions of multiple single vibration signals, a spatial coordinate matrix is ​​constructed; Determine the target coordinate system according to the signal source position of one of the single vibration signals, and transform the signal source positions of each of the single vibration signals into the target coordinate system according to the spatial coordinate matrix to obtain the position transformation matrix of each single vibration signal; According to the position conversion matrix of each single vibration signal, a time deviation between the single vibration signal and the single vibration signal corresponding to the target coordinate system is determined.

6. The method for identifying ship propulsion shafting faults according to claim 1, characterized in that: The multimodal monitoring signal includes a fused vibration signal and a sound signal, and the feature extraction of each modal signal of the multimodal monitoring signal is performed to obtain a feature vector of each modality, including the following steps: Inputting the fused vibration signal into a first time convolutional neural network module for feature extraction to obtain a vibration feature vector; Inputting the sound signal into a second time convolutional neural network module for feature extraction to obtain a sound feature vector; Among them, the first temporal convolutional neural network module and the second temporal convolutional neural network module both include multiple residual-connected temporal convolution blocks.

7. The method for identifying ship propulsion shafting faults according to claim 1, characterized in that: The method of dynamically weighting and fusing the feature vectors of each mode based on the dynamic routing algorithm to obtain a fault identification result includes the following steps: Reconstruct the feature vectors of each mode respectively to obtain the feature reconstruction vectors of each mode; Using a dynamic routing algorithm to perform modal dynamic weight allocation on the feature reconstruction vector of each modality to obtain a second weight of each modality; A weighted calculation is performed on the plurality of feature reconstruction vectors according to the second weight of each mode to obtain a prediction vector, wherein the prediction vector is used to determine a fault identification result.

8. A ship propulsion shaft fault identification system, characterized in that: include: The first module is used to obtain a multi-modal monitoring signal of a ship propulsion shaft system, wherein the multi-modal monitoring signal includes a multi-source vibration signal and a sound signal, and the multi-source vibration signal includes a single vibration signal at a plurality of different monitoring positions; The second module is used to perform spatiotemporal correlation analysis and weighted fusion on the multi-source vibration signals to obtain a fused vibration signal, and replace the multi-source vibration signal in the multimodal monitoring signal with the fused vibration signal; The third module is used to input the multimodal monitoring signal into a ship propulsion shaft system fault identification model to obtain a ship propulsion shaft system fault identification result; The ship propulsion shafting fault identification model is specifically used for: Extracting features from each modal signal of the multimodal monitoring signal to obtain a feature vector of each modality; Based on the dynamic routing algorithm, the feature vectors of each mode are dynamically weighted and fused to obtain the fault identification result.

9. An electronic device, characterized in that: The electronic device includes a memory, a processor, a program stored in the memory and executable on the processor, and a data bus for realizing connection and communication between the processor and the memory. When the program is executed by the processor, the steps of the method described in any one of claims 1 to 7 are realized.

10. A storage medium, the storage medium being a computer-readable storage medium, used for computer-readable storage, characterized in that: The storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of claims 1 to 7.

Images