Data processing method, device, equipment and storage medium for ship power system

Abstract

The present application discloses a data processing method, device, equipment and storage medium for a ship power system, and relates to the technical field of ship data processing. The method comprises: obtaining a first type of collected data and a second type of collected data of the ship power system; using a first sparse algorithm and a second sparse algorithm to perform sparse processing on the first type of collected data and the second type of collected data, respectively, and obtaining first sparse representation data and second sparse representation data, respectively; and performing under-sampling compression on the first sparse representation data and the second sparse representation data. Thus, it can be achieved that: according to the characteristics of different data of the ship system operation and maintenance platform, different sparse algorithms are used for sparse processing, and the sparsely processed data is under-sampled and compressed, which can save data storage space, improve storage compression efficiency, and enable the data of the ship system operation and maintenance platform to be greatly compressed and stored, thereby improving the utilization efficiency of storage space and reducing the storage cost of the operation and maintenance platform.

Description

Technical Field

[0001] The present application relates to the technical field of ship data processing, and in particular to a data processing method, device, equipment and storage medium for a ship power system. Background Art

[0002] In the intelligent operation and maintenance platform system of the ship power system, the healthy operation status of the power system is monitored and evaluated by collecting high-frequency vibration, cylinder pressure, top dead center, speed and displacement signals and combining a large number of thermal parameters. In order to achieve data analysis over a long time span and meet the regulatory requirements of the intelligent engine room, it is often necessary to configure a larger storage space to store the data. However, this will undoubtedly cause greater storage pressure on the server storage hardware and increase costs. The traditional storage method is to compress data files, but this compression method has limited compression on files and it is difficult to significantly improve storage performance. Summary of the invention

[0003] Purpose of the invention: An embodiment of the present application provides a data processing method for a ship power system, aiming to overcome the technical problem in the prior art that the compression space for ship operation and maintenance data storage is limited, which is not conducive to improving storage performance; another purpose of an embodiment of the present application is to provide a data processing device for a ship power system; the third purpose of the present application is to provide an electronic device; the fourth purpose of the present application is to provide a computer-readable storage medium.

[0004] Technical solution: A data processing method for a ship power system according to an embodiment of the present application includes:

[0005] Acquire the first type of collected data and the second type of collected data of the ship power system;

[0006] Performing sparse processing on the first type of collected data and the second type of collected data using a first sparse algorithm and a second sparse algorithm, respectively, and obtaining first sparse representation data and second sparse representation data, respectively;

[0007] Undersampling compression is performed on the first sparse representation data and the second sparse representation data.

[0008] In some embodiments, the step of performing sparse processing on the first type of collected data using a first sparse algorithm includes:

[0009] The first type of collected data is sparsely represented using a traditional Fourier matrix.

[0010] In some embodiments, the sparse representation of the first type of acquired data using a traditional Fourier matrix includes:

[0011] The first type of collected data is intercepted according to a first preset unit, and a Fourier matrix satisfying a second preset unit is constructed;

[0012] The Fourier matrix is ​​used to perform sparse representation on the first type of acquired data.

[0013] In some embodiments, the first category of collected data includes at least one of: rotational speed data of the ship power system, displacement data of the ship power system, cylinder pressure of the ship power system and top dead center of the ship power system.

[0014] In some embodiments, the step of performing sparse processing on the second type of collected data using a second sparse algorithm includes:

[0015] Using a dictionary training algorithm to train the second type of collected data to obtain a corresponding sparse dictionary;

[0016] The second type of collected data is sparsely represented using a sparse dictionary.

[0017] In some embodiments, the second category of collected data includes at least one of vibration data and thermal data of the ship power system.

[0018] In some embodiments, the ship power system includes multiple load conditions; the second type of collected data includes vibration data of multiple load conditions and thermal data of multiple load conditions; the second type of collected data is trained using a dictionary training algorithm to obtain a corresponding sparse dictionary, including:

[0019] Dictionary training is performed separately for the vibration data of each channel under each load condition to obtain a sparse dictionary corresponding to the vibration data of each channel under each load condition;

[0020] The thermal data of all measuring points corresponding to each load condition are taken as a whole for dictionary training, and a sparse dictionary corresponding to the thermal data of each load condition is obtained.

[0021] In some embodiments, the under-sampling and compressing the first sparse representation data and the second sparse representation data comprises:

[0022] Based on the compressed sensing theory, a Gaussian random matrix is ​​used to perform under-sampling compression on the first sparse representation data and the second sparse representation data.

[0023] In some embodiments, the data processing method of the ship power system also includes: reconstructing and restoring the under-sampled compressed and stored data using an orthogonal matching pursuit algorithm.

[0024] Accordingly, a data processing device for a ship power system according to an embodiment of the present application includes:

[0025] An acquisition module, used to acquire the first type of collected data and the second type of collected data of the ship power system;

[0026] A processing module, used to perform sparse processing on the first type of collected data and the second type of collected data using a first sparse algorithm and a second sparse algorithm, respectively, and obtain first sparse representation data and second sparse representation data, respectively;

[0027] An undersampling compression module is used to perform undersampling compression on the first sparse representation data and the second sparse representation data.

[0028] Correspondingly, an electronic device described in an embodiment of the present application includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the data processing method for the ship power system described above is implemented.

[0029] Correspondingly, a computer-readable storage medium described in an embodiment of the present application stores a computer program thereon, and when the computer program is executed by a processor, the data processing method of the ship power system described above is implemented.

[0030] Beneficial effects: Compared with the prior art, the data processing method, device, equipment and storage medium of the ship power system of the embodiment of the present application, the data processing method of the ship power system includes: obtaining the first type of collected data and the second type of collected data of the ship power system; using the first sparse algorithm and the second sparse algorithm to perform sparse processing on the first type of collected data and the second type of collected data, respectively, and obtaining the first sparse representation data and the second sparse representation data, respectively; performing under-sampling compression on the first sparse representation data and the second sparse representation data. It can be seen that this method can achieve: according to the characteristics of different data of the ship system operation and maintenance platform, different sparse algorithms are used for sparse processing, and the sparsely processed data is under-sampled and compressed, which can save data storage space, improve storage compression efficiency, and make the data of the ship system operation and maintenance platform be greatly compressed and stored, thereby improving the utilization efficiency of storage space and reducing the storage cost of the operation and maintenance platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1is a flow chart of a data processing method for a ship power system provided in an embodiment of the present application;

[0033] Figure 2 It is a data processing schematic diagram of a ship power system provided in an embodiment of the present application;

[0034] Figure 3 is a data processing schematic diagram of another ship power system provided in an embodiment of the present application;

[0035] Figure 4 is a schematic diagram of processing the first type of collected data provided in an embodiment of the present application;

[0036] Figure 5 is a schematic diagram of processing the second type of collected data provided in an embodiment of the present application;

[0037] Figure 6 It is a schematic diagram of dictionary training and sparseness of the second type of collected data under various working conditions provided in the embodiments of the present application;

[0038] Figure 7 It is a principle structure block diagram of a data processing device for a ship power system provided in an embodiment of the present application;

[0039] Figure 8 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application.

[0040] Reference numerals:

[0041] 101 - acquisition module; 102 - processing module; 103 - undersampling compression module; 100 - data processing device of the ship power system. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0043] It should be understood that although the terms first, second, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the concepts of the present application. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0044] Those skilled in the art will appreciate that the drawings are only schematic diagrams of example embodiments and may not be to scale. The modules or processes in the drawings are not necessarily required to implement the present application and therefore cannot be used to limit the scope of protection of the present application.

[0045] Figure 1 This is a flow chart of a data processing method for a ship power system provided in an embodiment of the present application. This method can be applied to the case where the monitoring data of the operation and maintenance platform is stored in the intelligent operation and maintenance platform of the ship power system, and the storage space is reduced and the storage performance is improved. This method can be executed by a data processing device of the ship power system, which can be implemented by software and / or hardware, and the device can be configured in the processor of the intelligent operation and maintenance platform of the ship power system. Please refer to Figure 1 , the method comprises the following steps:

[0046] Step 110: Acquire the first type of collected data and the second type of collected data of the ship power system.

[0047] The ship power system data includes: a large amount of monitoring data generated by the diesel engine, generator, propulsion and shaft system of the ship power system, such as vibration data, top dead center data, speed data and thermal data of the diesel engine, vibration data and thermal data of the generator, vibration data, displacement data and thermal data of the propulsion and shaft system, etc.

[0048] Among them, the first type of collected data is data with better sparsity in the ship power system, such as cylinder pressure, top dead center, speed and displacement, etc. Among them, the second type of collected data is data with poor sparsity, such as vibration data and thermal data.

[0049] Step 120: Perform sparse processing on the first type of collected data and the second type of collected data using a first sparse algorithm and a second sparse algorithm, respectively, to obtain first sparse representation data and second sparse representation data, respectively.

[0050] Among them, in the ship power system, the data characteristics of the first type of collected data and the second type of collected data are different. For example, the first type of collected data is data with good sparsity, and the second type of collected data is data with poor sparsity. Therefore, according to different data characteristics, different sparse algorithms are used to perform sparse processing on various data in the ship power system, which can effectively save data storage space, improve data compression storage efficiency, and reduce the storage cost of the operation and maintenance platform. Especially in the case of large-scale monitoring data sets that need to be processed in the ship power system and storage resources of the operation and maintenance platform are limited, data storage is performed, which is conducive to improving the utilization rate of the storage space of the ship power system.

[0051] Step 130: Perform under-sampling compression on the first sparse representation data and the second sparse representation data.

[0052] Specifically, after obtaining the first type of collected data and the second type of collected data of the ship power system, the first sparse algorithm and the second sparse algorithm are used to perform sparse processing on the first type of collected data and the second type of collected data respectively, and the sparsely processed data are under-sampled, so as to achieve significant compression storage of the ship power system data and improve the data storage capacity of the ship power system operation and maintenance platform.

[0053] In the technical solution of this embodiment, the working principle of the data processing method of the ship power system is as follows: Figure 1 First, obtain the first type of collected data and the second type of collected data of the ship power system. Then, the first type of collected data and the second type of collected data are sparsely processed by using the first sparse algorithm and the second sparse algorithm respectively, and the first sparse representation data and the second sparse representation data are obtained respectively. Finally, the first sparse representation data and the second sparse representation data are undersampled and compressed. It can be seen that different sparse algorithms are used for sparse processing for different data types of the ship power system, such as using the first sparse algorithm to sparse the first type of collected data, and using the second sparse algorithm to sparse the second type of collected data. This can effectively save data storage space, improve data compression storage efficiency, improve the storage performance of the ship power system, and reduce the storage cost of the operation and maintenance platform. It is suitable for situations where large-scale monitoring data sets need to be processed in the ship power system and the storage resources of the operation and maintenance platform are limited.

[0054] In some embodiments, under-sampling compression is performed on the first sparse representation data and the second sparse representation data, including: under-sampling compression is performed on the first sparse representation data and the second sparse representation data using a Gaussian random matrix based on compressed sensing theory.

[0055] Specifically, a corresponding Gaussian matrix is ​​created according to the sparse first-category acquisition data and the second-category acquisition data, i.e., the first sparse representation data and the second sparse representation data. The sparse data is multiplied with the Gaussian matrix, i.e., the first sparse representation data and the second sparse representation data are multiplied with the Gaussian matrix respectively, to obtain corresponding compressed dense vectors respectively, and the dense vectors are undersampled to compress and store data.

[0056] Figure 2 is a data processing schematic diagram of a ship power system provided in an embodiment of the present application. Figure 2 The data processing method of the ship power system also includes: reconstructing and restoring the under-sampled compressed and stored data using an orthogonal matching pursuit algorithm (Orthogonal Matching Pursuit, OMP).

[0057] Among them, when dealing with the data of the ship power system, different sparse algorithms are used for sparse processing according to different data characteristics. On the one hand, it is helpful to save data storage space, improve data compression storage efficiency, reduce the storage cost of the operation and maintenance platform, and realize the storage of ship power system data with high space utilization. On the other hand, when it is necessary to reconstruct and restore the data stored in the ship power system, it is helpful to improve the accuracy and efficiency of data reconstruction.

[0058] In the technical solution of this embodiment, the implementation process of the data processing method of the ship power system is as follows: Figure 2 , the monitoring and operation and maintenance platform obtains the monitoring data of the ship's power system in real time, for example, the monitoring data (i.e., original monitoring data) of the diesel engine, generator, propulsion and shaft system, and propeller, etc. After the monitoring and operation and maintenance platform obtains the original monitoring data, on the one hand, it is used to perform real-time data analysis and fault diagnosis on the ship's power system, and display the results. On the other hand, the original monitoring data is under-sampled and compressed based on the compressed sensing theory to obtain under-sampled compressed storage data. When it is necessary to call or read the stored data, the sampling OMP reconstruction algorithm reconstructs and restores the under-sampled compressed storage data to obtain the reconstructed and restored data. Among them, the reconstructed and restored data can be used for historical data analysis and fault diagnosis, and the results can be displayed.

[0059] In some embodiments, the first category of collected data includes at least one of: rotational speed data of the ship power system, displacement data of the ship power system, cylinder pressure of the ship power system and top dead center of the ship power system.

[0060] Among them, the rotation speed data of the ship power system, the displacement data of the ship power system, the cylinder pressure of the ship power system and the top dead center of the ship power system are high-frequency data in the ship power system.

[0061] Among them, the speed data of the ship power system can be the speed of the diesel engine, the displacement data of the ship power system can be the displacement of the intermediate bearing of the shaft system, the cylinder pressure of the ship power system can be the cylinder pressure of the diesel engine, and the top dead center of the ship power system can be the top dead center of the diesel engine.

[0062] In some embodiments, the second category of collected data includes at least one of vibration data and thermal data of the ship power system.

[0063] Among them, the vibration data of the ship power system is the high-frequency data in the ship power system, and the thermal data is the low-frequency data in the ship power system.

[0064] The vibration data of the ship power system can be the vibration data of the diesel engine, generator, gearbox, propulsion and shaft system. The thermal data can come from the monitoring data of the monitoring alarm system of the ship's engine room. Its monitoring range covers the entire engine room equipment, including diesel engines, generators, gearboxes, shaft systems, etc. The types of data it monitors include pressure, temperature, speed, etc.

[0065] Figure 3 is another data processing schematic diagram of a ship power system provided in an embodiment of the present application. Figure 3 , using a first sparse algorithm to perform sparse processing on the first type of collected data, including: using a traditional Fourier matrix to perform sparse representation on the first type of collected data.

[0066] The first sparse algorithm is: using the traditional Fourier matrix to perform sparse processing on the first type of collected data. For example, using the traditional Fourier matrix to perform sparse representation on the high-frequency cylinder pressure, top dead center data, speed data and displacement data in the ship power system.

[0067] In some embodiments, see Figure 3 , using a second sparse algorithm to perform sparse processing on the second type of collected data, including: using a dictionary training algorithm to train the second type of collected data to obtain a corresponding sparse dictionary; using the sparse dictionary to perform sparse representation on the second type of collected data.

[0068] The dictionary training algorithm may be a K-SVD algorithm (K-Singular Value Decomposition, K-SVD).

[0069] Among them, the second sparse algorithm is: using a dictionary training algorithm to perform dictionary training on the high-frequency vibration data and low-frequency thermal data of the ship power system to obtain a corresponding sparse dictionary, and using the trained sparse dictionary to perform sparse representation on the vibration data and thermal data.

[0070] In the technical solution of this embodiment, the implementation process of the data processing method of the ship power system is as follows: Figure 3According to the characteristics of different types of data in the ship power system monitoring and operation and maintenance platform, different sparse matrices are used for sparseness and then Gaussian random matrices are used for under-sampling compression. For example, for the first type of collected data with better sparsity, such as cylinder pressure, top dead center, speed, and displacement, the traditional Fourier matrix is ​​used for sparse representation. For the second type of collected data with poor sparsity, such as vibration data and thermal data, the K-SVD dictionary training method is used to train the corresponding sparse dictionary of vibration data and sparse dictionary of thermal data, and then the sparse dictionary of vibration data is used to sparsely represent the vibration data, and the sparse dictionary of thermal data is used to sparsely represent the thermal data. In this way, data storage space can be effectively saved, data compression storage efficiency can be improved, and the storage cost of the operation and maintenance platform can be reduced, especially in the case of large-scale monitoring data sets that need to be processed in the ship power system and the storage resources of the operation and maintenance platform are limited for data storage, which is conducive to improving the utilization of the storage space of the ship power system.

[0071] Figure 4 is a schematic diagram of processing the first type of collected data provided in the embodiments of the present application. Figure 4 , using a traditional Fourier matrix to sparsely represent the first type of collected data, including: intercepting the first type of collected data according to a first preset unit, and constructing a Fourier matrix that satisfies a second preset unit; using the Fourier matrix to sparsely represent the first type of collected data.

[0072] The first preset unit is a processable unit size, which can be set according to actual conditions and is not specifically limited here. The specific value of the second preset unit can be set according to actual conditions and is not specifically limited here.

[0073] For details, see Figure 4 The implementation process of sparse compression of the first type of collected data using the traditional Fourier matrix is ​​as follows: First, the cylinder pressure high-frequency data, the top dead center high-frequency data, the speed high-frequency data and the displacement high-frequency data are intercepted according to the processable unit size. Then, a unit Fourier matrix of suitable size is constructed, and the Fourier matrix is ​​used to sparse the cylinder pressure high-frequency data, the top dead center high-frequency data, the speed high-frequency data and the displacement high-frequency data to be compressed. Finally, the data is sub-randomly sampled by the constructed Gaussian random matrix, and the compression multiple is selected, such as 10 times, on the premise that the accuracy after reconstruction meets the use requirements. In this way, the first type of collected data is sparsely and compressed for storage.

[0074] Figure 5 is a schematic diagram of processing the second type of collected data provided in the embodiments of the present application. Figure 5, the ship power system includes multiple load conditions; the second type of collected data includes vibration data of multiple load conditions and thermal data of multiple load conditions; the second type of collected data is trained using a dictionary training algorithm to obtain a corresponding sparse dictionary, including: performing dictionary training on the vibration data of each channel under each load condition separately to obtain a sparse dictionary corresponding to the vibration data of each channel under each load condition; performing dictionary training on the thermal data of all measuring points corresponding to each load condition as a whole to obtain a sparse dictionary corresponding to the thermal data of each load condition.

[0075] Among them, the ship power system includes multiple load conditions. Exemplarily, the ship power system includes a low load condition (hereinafter referred to as low condition), a medium load condition (hereinafter referred to as medium condition) and a high load condition (hereinafter referred to as high condition). Correspondingly, the second type of collected data includes vibration data of low condition, medium condition and high condition, as well as thermal data of low condition, medium condition and high condition.

[0076] The process of using K-SVD algorithm to perform dictionary training and sparseness on the second type of collected data is as follows: Figure 5 In the process of K-SVD dictionary training, dictionary training is performed according to the vibration data and thermal data under low, medium and high working conditions of the ship power system. And the corresponding dictionaries of vibration data and thermal data are trained under three working conditions, such as low working condition dictionary of low working condition vibration data, medium working condition dictionary of medium working condition vibration data, high working condition dictionary of high working condition vibration data, low working condition dictionary of low working condition thermal data, medium working condition dictionary of medium working condition thermal data, and high working condition dictionary of high working condition thermal data. And the corresponding dictionaries are used to sparsely represent the vibration data and thermal data of each working condition. Therefore, by performing dictionary training and sparse representation on the vibration data and thermal data of different working conditions, it is beneficial to improve the accuracy of subsequent data reconstruction.

[0077] Furthermore, since the amount of vibration data of the ship power system is relatively large and the characteristics of the vibration data at different measuring points are different, it is necessary to perform dictionary training on the vibration data of each channel under each load condition separately to obtain a sparse dictionary corresponding to the vibration data of each channel under each load condition.

[0078] Considering that the thermal data in the ship power system is low-frequency data, in order to improve the data processing speed, the thermal data within the preset sampling period is taken as a whole for dictionary training, that is, the thermal data of all measuring points corresponding to each load condition within the preset sampling period are taken as a whole for dictionary training, and the sparse dictionary corresponding to the thermal data of each load condition is obtained. For example, for thermal data updated once every 1s, all thermal values ​​of low conditions are taken as a whole for K-SVD dictionary training, all thermal values ​​of medium conditions are taken as a whole for K-SVD dictionary training, and all thermal values ​​of high conditions are taken as a whole for K-SVD dictionary training, thereby obtaining the low condition sparse dictionary, the medium condition sparse dictionary and the high condition sparse dictionary of the thermal data.

[0079] Figure 6 Schematic diagram of dictionary training and sparseness of the second type of collected data under various working conditions provided in the embodiment of the present application. Figure 6 For the sampled vibration high-frequency data and thermal low-frequency data, the K-SVD dictionary training method is used to perform corresponding single-condition dictionary training according to low, medium and high conditions, and then the dictionary groups under low, medium and high conditions are obtained. The low, medium and high condition dictionary groups obtained through training can sparsely represent the vibration high-frequency data and thermal data, and the data compression can be achieved through sub-random sampling of Gaussian random matrix.

[0080] Among them, single-condition dictionary training: the training set data includes data from different vibration channels and thermal data from different measuring points. Among them, the vibration high-frequency data has a large amount of data per second, and the vibration characteristics of different channel measuring points are different. When performing dictionary training, each channel is trained separately. The thermal data generates a small amount of data per second for each measuring point, so the data generated by all measuring points in one second are combined into a data matrix, and a thermal sparse dictionary is trained through the K-SVD dictionary training method.

[0081] Figure 7 is a principle structure block diagram of a data processing device for a ship power system provided in an embodiment of the present application. Correspondingly, an embodiment of the present application also provides a data processing device for a ship power system, see Figure 7 The data processing device 100 of the ship power system includes: an acquisition module 101, used to acquire the first type of collected data and the second type of collected data of the ship power system. A processing module 102, used to perform sparse processing on the first type of collected data and the second type of collected data using a first sparse algorithm and a second sparse algorithm, respectively, and obtain first sparse representation data and second sparse representation data, respectively. An undersampling compression module 103, used to perform undersampling compression on the first sparse representation data and the second sparse representation data.

[0082] The technical solution of this embodiment provides a data processing device for a ship power system, and the data processing device for the ship power system includes: an acquisition module for acquiring a first type of collected data and a second type of collected data of the ship power system; a processing module for sparsely processing the first type of collected data and the second type of collected data using a first sparse algorithm and a second sparse algorithm, respectively, and obtaining first sparse representation data and second sparse representation data, respectively; an undersampling compression module for undersampling compression of the first sparse representation data and the second sparse representation data. It can be seen that through this device, it can be achieved that: according to the characteristics of different data of the ship system operation and maintenance platform, different sparse algorithms are used for sparse processing, and the sparsely processed data is undersampled and compressed, which can save data storage space and improve storage compression efficiency, so that the data of the ship system operation and maintenance platform can be compressed and stored to a large extent, thereby improving the utilization efficiency of storage space and reducing the storage cost of the operation and maintenance platform.

[0083] In some embodiments, the processing module 102 further includes a first processing unit configured to perform sparse representation on the first type of acquired data using a traditional Fourier matrix.

[0084] In some embodiments, the first processing unit is further used to: intercept the first type of collected data according to a first preset unit, and construct a Fourier matrix that satisfies a second preset unit; and use the Fourier matrix to sparsely represent the first type of collected data.

[0085] In some embodiments, the first category of collected data includes at least one of: rotational speed data of the ship power system, displacement data of the ship power system, cylinder pressure of the ship power system and top dead center of the ship power system.

[0086] In some embodiments, the processing module 102 further includes a second processing unit, which is used to train the second type of collected data using a dictionary training algorithm to obtain a corresponding sparse dictionary; and use the sparse dictionary to perform sparse representation on the second type of collected data.

[0087] In some embodiments, the second category of collected data includes at least one of vibration data and thermal data of the ship power system.

[0088] In some embodiments, the ship power system includes multiple load conditions; the second type of collected data includes vibration data of multiple load conditions and thermal data of multiple load conditions; the second processing unit is also used to: perform dictionary training on the vibration data of each channel under each load condition separately, and obtain a sparse dictionary corresponding to the vibration data of each channel under each load condition; perform dictionary training on the thermal data of all measuring points corresponding to each load condition as a whole, and obtain a sparse dictionary corresponding to the thermal data of each load condition.

[0089] In some embodiments, the undersampling compression module is further used to: perform undersampling compression on the first sparse representation data and the second sparse representation data using a Gaussian random matrix based on compressed sensing theory.

[0090] In some embodiments, the data processing method of the ship power system also includes: a reconstruction and restoration module, which is used to reconstruct and restore the under-sampled compressed and stored data using an orthogonal matching pursuit algorithm.

[0091] Accordingly, the present application also provides an electronic device, see Figure 8 , Figure 8 The structure diagram of the electronic device of the embodiment of the present application is illustrated. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the data processing method of the ship power system are implemented. Since the data processing method of the ship power system is described in detail above, it will not be repeated here.

[0092] Accordingly, the embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the data processing method for the ship power system are implemented. Since the data processing method for the ship power system is described in detail above, it will not be repeated here.

[0093] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0094] The above is a detailed introduction to the data processing method, device, equipment and storage medium of the ship power system provided in the embodiments of the present application, and the principles and implementation methods of the present application are explained by using specific examples. The description of the above embodiments is only used to help understand the technical solution and core idea of ​​the present application; ordinary technicians in this field should understand that: they can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and these modifications or replacements do not make the essence of the corresponding technical solution deviate from the scope of the technical solution of the embodiments of the present application.

Claims

1. A data processing method for a ship power system, characterized in that: include: Acquire the first type of collected data and the second type of collected data of the ship power system; Performing sparse processing on the first type of collected data and the second type of collected data using a first sparse algorithm and a second sparse algorithm, respectively, and obtaining first sparse representation data and second sparse representation data, respectively; Under-sampling compression is performed on the first sparse representation data and the second sparse representation data.

2. The data processing method of a ship power system according to claim 1, characterized in that: The step of performing sparse processing on the first type of collected data using a first sparse algorithm includes: The first type of collected data is sparsely represented using a traditional Fourier matrix.

3. The data processing method of a ship power system according to claim 2, characterized in that: The method of using a traditional Fourier matrix to sparsely represent the first type of collected data includes: The first type of collected data is intercepted according to a first preset unit, and a Fourier matrix satisfying a second preset unit is constructed; The Fourier matrix is ​​used to perform sparse representation on the first type of acquired data.

4. The data processing method of a ship power system according to claim 1, characterized in that: The first type of collected data includes at least one of: rotation speed data of the ship power system, displacement data of the ship power system, cylinder pressure of the ship power system and top dead center of the ship power system.

5. The data processing method of a ship power system according to claim 1, characterized in that: The step of performing sparse processing on the second type of collected data using a second sparse algorithm includes: Using a dictionary training algorithm to train the second type of collected data to obtain a corresponding sparse dictionary; The second type of collected data is sparsely represented using a sparse dictionary.

6. The data processing method of a ship power system according to claim 5, characterized in that: The second type of collected data includes at least one of vibration data and thermal data of the ship power system.

7. The data processing method of a ship power system according to claim 6, characterized in that: The ship power system includes multiple load conditions; the second type of collected data includes vibration data of multiple load conditions and thermal data of multiple load conditions; the second type of collected data is trained using a dictionary training algorithm to obtain a corresponding sparse dictionary, including: Dictionary training is performed separately for the vibration data of each channel under each load condition to obtain a sparse dictionary corresponding to the vibration data of each channel under each load condition; The thermal data of all measuring points corresponding to each load condition are taken as a whole for dictionary training, and a sparse dictionary corresponding to the thermal data of each load condition is obtained.

8. The data processing method of a ship power system according to claim 1, characterized in that: The under-sampling compression of the first sparse representation data and the second sparse representation data comprises: Based on the compressed sensing theory, a Gaussian random matrix is ​​used to perform under-sampling compression on the first sparse representation data and the second sparse representation data.

9. The data processing method of a ship power system according to claim 1, characterized in that: Also includes: The orthogonal matching pursuit algorithm is used to reconstruct and restore the under-sampled compressed data.

10. A data processing device for a ship power system, characterized in that: include: An acquisition module, used to acquire the first type of collected data and the second type of collected data of the ship power system; A processing module, used to perform sparse processing on the first type of collected data and the second type of collected data using a first sparse algorithm and a second sparse algorithm, respectively, and obtain first sparse representation data and second sparse representation data, respectively; An undersampling compression module is used to perform undersampling compression on the first sparse representation data and the second sparse representation data.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the data processing method for the ship power system according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the data processing method for a ship power system according to any one of claims 1 to 9 is implemented.

Images