A Method and System for On-Site Dynamic Balancing Calculation of Stern Compartment Based on Multi-Sensor Information Fusion

Abstract

This invention provides a method and system for on-site dynamic balancing calculation of the stern compartment using multi-sensor information fusion, comprising: acquiring parameter signals of the entire stern compartment using multiple sensors, extracting features through multi-source information fusion technology, and establishing a multi-objective optimization model for counterweight calculation; monitoring the vibration state of the entire stern compartment using multiple sensors to gain a more comprehensive understanding of the vibration distribution characteristics, and simultaneously considering vibration components of multiple frequency bands; and using multi-source information fusion technology to combine vibration signals, acoustic signals, and operating parameters for comprehensive balancing to improve the balancing effect.

Description

Technical Field

[0001] This invention relates to the field of vibration control technology for marine power equipment, and in particular to a method and system for on-site dynamic balance calculation of the stern compartment using multi-sensor information fusion. Background Technology

[0002] The stern structure of a ship is subjected to excitation from the main engine, shafting, and propeller, making it one of the most severely vibrating parts of the ship. The propeller shafting is a key component connecting all parts of the stern, and dynamic balancing of the propeller shafting is one of the main means of controlling the vibration of the stern structure. Traditional ship dynamic balancing methods mostly use a single sensor or a single type of sensor to collect data and optimize for a single measuring point, which can only reflect the local vibration situation. Especially when dealing with the complex structure of the stern, it may even lead to the deterioration of vibration at other measuring points while the vibration of the target measuring point is optimized.

[0003] Dynamic balancing technology for ship stern compartments is one of the key technologies to ensure the stable operation of ship propulsion systems. Traditional on-site dynamic balancing methods mainly optimize single measuring points or specific low-frequency bands, such as single-plane balancing methods. These methods are based on simplification assumptions and have obvious limitations under actual complex working conditions. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method and system for on-site dynamic balance calculation of the stern compartment based on multi-sensor information fusion, to solve the limitations of traditional single-point dynamic balance methods, to achieve comprehensive balance optimization of multi-frequency vibration across the entire stern compartment, and to improve the stability and reliability of the ship propulsion system.

[0005] In a first aspect, embodiments of the present invention provide a method for on-site dynamic balance calculation of a stern compartment based on multi-sensor information fusion, the method comprising:

[0006] Determine the multi-objective optimization model;

[0007] Multiple sensors are installed inside the stern compartment, and the first parameter signal is collected synchronously.

[0008] After preprocessing and feature extraction of the first parameter signal, the first multi-dimensional feature is obtained;

[0009] The first multi-dimensional feature is input into the deep learning algorithm to obtain the first multi-source heterogeneous data;

[0010] The first multi-source heterogeneous data is input into the multi-objective optimization model to obtain the initial fused vibration vector;

[0011] After adding a test weight to the propulsion shaft system, the second parameter signal was collected;

[0012] After preprocessing and feature extraction of the second parameter signal, the second multi-dimensional feature is obtained;

[0013] The second multi-dimensional feature is input into the deep learning algorithm to obtain the second multi-source heterogeneous data;

[0014] The second multi-source heterogeneous data is input into the multi-objective optimization model to obtain the fused vibration vector under the trial weight state;

[0015] The initial fusion vibration vector and the fusion vibration vector under the trial weight state are used to obtain the residual unbalance of the propulsion shaft system through the influence coefficient algorithm;

[0016] A counterweight recommendation is obtained based on the residual imbalance of the propulsion shaft system; wherein the counterweight recommendation includes the counterweight mass and phase.

[0017] Furthermore, the multi-objective optimization model is determined, including:

[0018] Obtain the stern compartment dynamics model;

[0019] The multi-objective optimization model is constructed based on the stern compartment dynamics model and the set compartment vibration and noise evaluation indicators.

[0020] The stern compartment dynamics model includes a shaft dynamics model, a structural vibration propagation model, and a fluid-structure coupling model.

[0021] The shaft dynamics model is used to describe the dynamic response of the shaft system under unbalanced excitation; the structural vibration propagation model is used to describe the propagation law of vibration in the stern compartment structure; and the fluid-structure coupling model is used to characterize the influence of hydrodynamics on the vibration.

[0022] Furthermore, after preprocessing and feature extraction of the first parameter signal, a first multi-dimensional feature is obtained, including:

[0023] The first parameter signal is subjected to noise reduction filtering, integer period sampling and fundamental frequency component extraction to obtain the preprocessed first parameter signal;

[0024] The preprocessed first parameter signal is imported into the dynamic balance module of multi-information fusion to extract the first multi-dimensional feature;

[0025] The first multidimensional feature includes peak value, phase, characteristic spectral lines, and vibration level.

[0026] Furthermore, the first parameter signal includes: a first vibration acceleration, a first vibration velocity, a first vibration displacement, a first temperature, a first noise signal, and a bond phase signal; the method further includes:

[0027] The initial operating state of the stern compartment is determined by the first vibration acceleration, the first vibration velocity, the first vibration displacement, the first temperature, and the first noise signal.

[0028] The initial phase information is provided by the key phase signal.

[0029] Furthermore, the second parameter signal includes: a second vibration acceleration, a second vibration velocity, a second vibration displacement, a second temperature, and a second noise signal. The method further includes:

[0030] The operating status of the stern compartment under the test weight condition is determined by the second vibration acceleration, the second vibration velocity, the second vibration displacement, the second temperature, and the second noise signal.

[0031] Furthermore, the sensor's placement location includes:

[0032] Vibration acceleration sensors and temperature sensors are installed at the stern bearing, thrust bearing, and motor base of the propulsion shaft system; vibration velocity sensors are installed in the space on the bulkhead; vibration displacement sensors and key phase sensors are installed on the propulsion shaft system; and acoustic sensors are installed on the top of the compartment.

[0033] Secondly, embodiments of the present invention provide a multi-sensor information fusion-based on-site dynamic balance calculation system for the stern compartment, the system comprising:

[0034] The determination module is used to determine the multi-objective optimization model;

[0035] The first acquisition module is used to install multiple sensors in the stern compartment and simultaneously acquire the first parameter signal;

[0036] The first preprocessing and feature extraction module is used to preprocess and extract features from the first parameter signal to obtain the first multi-dimensional feature;

[0037] The first input module is used to input the first multi-dimensional features into the deep learning algorithm to obtain the first multi-source heterogeneous data.

[0038] The second input module is used to input the first multi-source heterogeneous data into the multi-objective optimization model to obtain an initial fused vibration vector;

[0039] The second acquisition module is used to acquire the second parameter signal after adding a trial weight to the propulsion shaft system;

[0040] The second preprocessing and feature extraction module is used to preprocess and extract features from the second parameter signal to obtain the second multi-dimensional feature.

[0041] The third input module is used to input the second multi-dimensional features into the deep learning algorithm to obtain the second multi-source heterogeneous data.

[0042] The fourth input module inputs the second multi-source heterogeneous data into the multi-objective optimization model to obtain the fused vibration vector under the trial weight state;

[0043] The residual imbalance acquisition module is used to obtain the residual imbalance of the propulsion shaft system by taking the initial fusion vibration vector and the fusion vibration vector under the trial weight state through the influence coefficient algorithm.

[0044] The counterweight suggestion acquisition module is used to obtain a counterweight suggestion based on the residual imbalance of the propulsion shaft system; wherein, the counterweight suggestion includes the counterweight mass and phase.

[0045] Furthermore, the determining module is specifically used for:

[0046] Obtain the stern compartment dynamics model;

[0047] The multi-objective optimization model is constructed based on the stern compartment dynamics model and the set compartment vibration and noise evaluation indicators.

[0048] The stern compartment dynamics model includes a shaft dynamics model, a structural vibration propagation model, and a fluid-structure coupling model.

[0049] The shaft dynamics model is used to describe the dynamic response of the shaft system under unbalanced excitation; the structural vibration propagation model is used to describe the propagation law of vibration in the stern compartment structure; and the fluid-structure coupling model is used to characterize the influence of hydrodynamics on the vibration.

[0050] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program that can run on the processor, and the processor executes the computer program to implement the method described above.

[0051] Fourthly, embodiments of the present invention provide a computer-readable medium having processor-executable non-volatile program code that causes the processor to perform the method described above.

[0052] This invention provides a method and system for on-site dynamic balance calculation of a stern compartment using multi-sensor information fusion, comprising: determining a multi-objective optimization model; setting up multiple sensors in the stern compartment and simultaneously acquiring a first parameter signal; preprocessing and extracting features from the first parameter signal to obtain a first multi-dimensional feature; inputting the first multi-dimensional feature into a deep learning algorithm to obtain first multi-source heterogeneous data; inputting the first multi-source heterogeneous data into the multi-objective optimization model to obtain an initial fused vibration vector; acquiring a second parameter signal after adding a trial weight to the propulsion shaft system; and preprocessing and extracting features from the second parameter signal to obtain a second multi-dimensional feature. The system first identifies two multi-dimensional features. A second multi-dimensional feature is input into a deep learning algorithm to obtain second multi-source heterogeneous data. This second multi-source heterogeneous data is then input into a multi-objective optimization model to obtain a fused vibration vector under trial weight conditions. The initial fused vibration vector and the fused vibration vector under trial weight conditions are then combined using an influence coefficient algorithm to obtain the residual imbalance of the propulsion shaft system. A counterweight recommendation is then derived based on the residual imbalance of the propulsion shaft system, including the counterweight mass and phase. This approach addresses the limitations of traditional single-point dynamic balancing methods, achieving comprehensive balance optimization of multi-frequency vibrations across the entire stern compartment, thereby improving the stability and reliability of the ship's propulsion system.

[0053] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0054] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0055] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0056] Figure 1 The flowchart shows the on-site dynamic balance calculation method for the stern compartment based on multi-sensor information fusion provided in Embodiment 1 of the present invention.

[0057] Figure 2 This is a schematic diagram of the sensor position setting provided in Embodiment 1 of the present invention;

[0058] Figure 3 This is a schematic diagram of the on-site dynamic balance calculation process for the stern compartment based on multi-sensor information fusion, as provided in Embodiment 1 of the present invention.

[0059] Figure 4 This is a schematic diagram of the on-site dynamic balance calculation system for the stern compartment based on multi-sensor information fusion provided in Embodiment 2 of the present invention. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] To facilitate understanding of this embodiment, the embodiments of the present invention will be described in detail below.

[0062] Example 1:

[0063] Figure 1 This is a flowchart of the on-site dynamic balance calculation method for the stern compartment based on multi-sensor information fusion provided in Embodiment 1 of the present invention.

[0064] Reference Figure 1 The method includes the following steps:

[0065] Step S101: Determine the multi-objective optimization model;

[0066] Step S102: Install multiple sensors in the stern compartment and simultaneously collect the first parameter signal;

[0067] Here, the sensor setup is as follows: Multiple sensors are deployed within the stern compartment to simultaneously collect signals such as vibration acceleration, vibration velocity, vibration displacement, temperature, noise, and key phase, with the key phase signal being indispensable. Data acquisition system setup: The data acquisition system is arranged considering the compartment structure and spatial accessibility.

[0068] Step S103: After preprocessing and feature extraction of the first parameter signal, the first multi-dimensional feature is obtained;

[0069] Step S104: Input the first multi-dimensional feature into the deep learning algorithm to obtain the first multi-source heterogeneous data;

[0070] Step S105: Input the first multi-source heterogeneous data into the multi-objective optimization model to obtain the initial fused vibration vector;

[0071] Specifically, the preprocessed first parameter signal is imported into the dynamic balance module of multi-information fusion to extract the first multi-dimensional features such as peak value, phase, characteristic spectral lines, and vibration level. The first multi-dimensional features are then input into the deep learning algorithm to output the first multi-source heterogeneous data, forming an "initial fused vibration vector" based on multiple measurement points and multiple signals that more realistically reflects the dynamic balance state of the stern compartment. This vector contains the fused equivalent amplitude and equivalent phase.

[0072] Step S106: After adding a trial weight to the propulsion shaft system, the second parameter signal is acquired;

[0073] Specifically, a suitable location is found on the propulsion shaft to add a test weight. The product of the test weight's mass and the distance from the test weight should be approximately equal to... Where G is the allowable imbalance corresponding to the rotor balance level, and the ship propulsion shafting is generally in accordance with the requirements of G6.3; For rotor mass, Rated speed; For safety margin, it is generally taken as .

[0074] Step S107: After preprocessing and feature extraction of the second parameter signal, the second multi-dimensional feature is obtained;

[0075] Step S108: Input the second multi-dimensional features into the deep learning algorithm to obtain the second multi-source heterogeneous data;

[0076] Step S109: Input the second multi-source heterogeneous data into the multi-objective optimization model to obtain the fused vibration vector under the trial weight state;

[0077] Specifically, refer to Figure 3 By collecting the second parameter signal, the operating state of the stern compartment under the test weight state is determined. Based on the deep learning algorithm, the second multi-source heterogeneous data is output. The second multi-source heterogeneous data is input into the multi-objective optimization model to obtain the fused vibration vector under the test weight state.

[0078] Step S110: The initial fused vibration vector and the fused vibration vector under trial weight are used to obtain the residual unbalance of the propulsion shaft system through the influence coefficient algorithm;

[0079] Step S111: Obtain a counterweight recommendation based on the residual imbalance of the propulsion shaft system; wherein, the counterweight recommendation includes the counterweight mass and phase.

[0080] Here, based on the feasibility requirements of the project, we provide recommendations for counterweights, including the weight and phase.

[0081] Specifically, a multi-objective optimization model is formed by combining the stern compartment dynamics model, including the shaft dynamics model, the structural vibration propagation model, and the fluid-structure coupling model, with specific compartment vibration and noise evaluation indicators, to comprehensively consider multiple optimization objectives.

[0082] Based on the results of multi-information fusion, the residual imbalance and phase of the propulsion shaft system are given. Combined with engineering feasibility requirements, counterweight recommendations are provided to reduce the overall vibration level of the stern compartment, including vibrations at multiple measuring points and across multiple frequency bands. Simultaneously, the overall operating condition of the ship is considered, and interference from other abnormal factors is eliminated.

[0083] Furthermore, step S101 includes the following steps:

[0084] Step S201: Obtain the stern compartment dynamics model;

[0085] Step S202: Based on the stern compartment dynamics model and the set compartment vibration and noise evaluation indicators, a multi-objective optimization model is constructed.

[0086] The stern compartment dynamics model includes a shaft system dynamics model, a structural vibration propagation model, and a fluid-structure coupling model. The shaft system dynamics model is used to describe the dynamic response of the shaft system under unbalanced excitation. The structural vibration propagation model is used to describe the propagation law of vibration in the stern compartment structure. The fluid-structure coupling model is used to characterize the influence of hydrodynamics on vibration.

[0087] Furthermore, step S103 includes the following steps:

[0088] Step S301: The first parameter signal is subjected to noise reduction filtering, integer cycle sampling and fundamental frequency component extraction to obtain the preprocessed first parameter signal;

[0089] Here, the first parameter signal is input into the data acquisition and preprocessing module, where noise reduction filtering, whole-cycle sampling, and fundamental frequency component extraction are performed on the acquired first parameter signal; operating parameters such as rotor speed, load condition, and power are acquired simultaneously to determine whether the ship's operating condition is normal.

[0090] Step S302: The preprocessed first parameter signal is imported into the dynamic balance module of multi-information fusion to extract the first multi-dimensional feature;

[0091] The first multidimensional feature includes peak value, phase, characteristic spectral lines, and vibration level.

[0092] Here, the preprocessing and feature extraction of the second parameter signal yields the second multi-dimensional feature, which is similar to the processing of the first parameter signal and will not be elaborated here.

[0093] Furthermore, the first parameter signal includes: a first vibration acceleration, a first vibration velocity, a first vibration displacement, a first temperature, a first noise signal, and a bond phase signal. The method also includes the following steps:

[0094] Step S401: Determine the initial operating state of the stern compartment using the first vibration acceleration, first vibration velocity, first vibration displacement, first temperature, and first noise signal.

[0095] Step S402: Initial phase information is provided through the key phase signal.

[0096] Furthermore, the second parameter signal includes: a second vibration acceleration, a second vibration velocity, a second vibration displacement, a second temperature, and a second noise signal. The method also includes the following steps:

[0097] Step S501: Determine the operating status of the stern compartment under test weight conditions using the second vibration acceleration, second vibration velocity, second vibration displacement, second temperature, and second noise signal.

[0098] Furthermore, the sensor placement locations include:

[0099] Vibration acceleration sensors and temperature sensors are installed at the stern bearing, thrust bearing, and motor base of the propulsion shaft system; vibration velocity sensors are installed in the space on the bulkhead; vibration displacement sensors and key phase sensors are installed on the propulsion shaft system; and acoustic sensors are installed on the top of the compartment.

[0100] Specifically, refer to Figure 2 By arranging sensors for vibration acceleration, vibration velocity, vibration displacement, temperature, noise, and key phase at key measuring points such as the stern bearing, thrust bearing, bulkhead, and motor in the stern compartment, key signals are collected and sent to the data acquisition module. After signal preprocessing, the signals are imported into the dynamic balancing module that integrates multiple information to obtain the residual imbalance of the propulsion shaft system.

[0101] First, vibration acceleration and temperature sensors are installed at the bases of key components in the stern compartment, such as the stern bearing, thrust bearing, and motor of the propulsion shaft system; vibration velocity sensors are installed in the space on the bulkhead; vibration displacement and key phase sensors are installed on the propulsion shaft system; and acoustic sensors are installed on the top of the compartment, forming a system covering the key parts of the stern compartment.

[0102] Vibration acceleration, vibration velocity, vibration displacement, temperature, noise, and key phase signals are measured at various locations of interest using a multimodal sensor network. The vibration acceleration, vibration velocity, vibration displacement, temperature, and noise signals are used to determine the stern compartment's operating status, while the key phase provides initial phase information for dynamic balance calculations. Data acquisition employs simultaneous basis sampling technology to ensure temporal consistency of all sensor data, while also considering the compartment structure and spatial accessibility.

[0103] The technical problems that this application can solve are: 1) constructing a multimodal sensor network covering key parts of the stern compartment; 2) synchronously collecting vibration, noise, and temperature signals, and integrating the monitoring of multiple physical quantities such as vibration, noise, and temperature into the dynamic balance system of the stern compartment; 3) breaking through the limitations of traditional single measuring points to conduct on-site dynamic balance tests on the entire stern compartment of the ship.

[0104] This application achieves comprehensive perception, accurate diagnosis, and collaborative optimization of stern compartment vibration. In recent years, multi-information fusion technology has been widely used in the field of mechanical fault diagnosis. Through multi-information fusion technology, various heterogeneous data are comprehensively collected and integrated, such as vibration signals, speed signals, acoustic signals, process parameters, and environmental data. Data fusion algorithms are used to complement, verify, and correct multi-source information, filter out noise and interference, and extract the characteristic information that best reflects the rotor imbalance state, thereby fundamentally improving the reliability of diagnostic data.

[0105] This application utilizes a multi-sensor network to comprehensively perceive the vibration state of the stern compartment, avoiding the limitations of single-point measurements. By comprehensively considering multiple factors such as vibration, temperature, and noise, it more accurately reflects the actual operating state of the system. Intelligent optimization algorithms are employed to achieve optimal trim under multi-objective and multi-constraint conditions, adapting to the complex changes in the ship's operating environment.

[0106] Example 2:

[0107] Figure 4 This is a schematic diagram of a multi-sensor information fusion system for on-site dynamic balance calculation of the stern compartment, provided in an embodiment of the present invention.

[0108] Reference Figure 4 The system includes:

[0109] The determination module is used to determine the multi-objective optimization model;

[0110] The first acquisition module is used to install multiple sensors in the stern compartment and simultaneously acquire the first parameter signal;

[0111] The first preprocessing and feature extraction module is used to preprocess and extract features from the first parameter signal to obtain the first multi-dimensional feature;

[0112] The first input module is used to input the first multi-dimensional features into the deep learning algorithm to obtain the first multi-source heterogeneous data.

[0113] The second input module is used to input the first multi-source heterogeneous data into the multi-objective optimization model to obtain the initial fused vibration vector;

[0114] The second acquisition module is used to acquire the second parameter signal after adding a trial weight to the propulsion shaft system;

[0115] The second preprocessing and feature extraction module is used to preprocess and extract features from the second parameter signal to obtain the second multi-dimensional features.

[0116] The third input module is used to input the second multi-dimensional features into the deep learning algorithm to obtain the second multi-source heterogeneous data.

[0117] The fourth input module inputs the second multi-source heterogeneous data into the multi-objective optimization model to obtain the fused vibration vector under the trial weight state;

[0118] The residual imbalance acquisition module is used to obtain the residual imbalance of the propulsion shaft system by taking the initial fused vibration vector and the fused vibration vector under trial weight conditions and using the influence coefficient algorithm.

[0119] The counterweight recommendation acquisition module is used to obtain counterweight recommendations based on the residual imbalance of the propulsion shaft system; the counterweight recommendations include the counterweight mass and phase.

[0120] Furthermore, the module is specifically used for:

[0121] Obtain the stern compartment dynamics model;

[0122] Based on the stern compartment dynamics model and the set compartment vibration and noise evaluation indicators, a multi-objective optimization model is constructed.

[0123] The stern compartment dynamics model includes a shaft dynamics model, a structural vibration propagation model, and a fluid-structure coupling model.

[0124] The shaft dynamics model is used to describe the dynamic response of the shaft system under unbalanced excitation; the structural vibration propagation model is used to describe the propagation law of vibration in the stern compartment structure; and the fluid-structure coupling model is used to characterize the influence of hydrodynamics on vibration.

[0125] This application employs multiple sensors to collect parameter signals from the entire stern compartment, extracts features through multi-source information fusion technology, and establishes a multi-objective optimization model for counterweight calculation. By using multiple sensors to monitor the vibration state of the entire stern compartment, a more comprehensive understanding of the vibration distribution characteristics can be achieved. Furthermore, considering vibration components in multiple frequency bands simultaneously, multi-source information fusion technology is used to combine vibration signals, acoustic signals, and operating parameters for comprehensive balancing, thereby improving the balancing effect.

[0126] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the multi-sensor information fusion method for on-site dynamic balance calculation of the stern compartment provided in the above embodiments.

[0127] This invention also provides a computer-readable medium having processor-executable non-volatile program code, on which a computer program is stored. When the computer program is run by a processor, it executes the steps of the multi-sensor information fusion method for on-site dynamic balance calculation of the stern compartment described in the above embodiments.

[0128] The computer program product provided in this embodiment of the invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the preceding method embodiments. For specific implementation details, please refer to the method embodiments, which will not be repeated here.

[0129] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system and apparatus described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0130] Furthermore, in the description of the embodiments of the present invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention based on the specific circumstances.

[0131] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0132] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0133] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A stern compartment field dynamic balancing calculation method of multi-sensor information fusion, characterized in that, The method comprises: determining a multi-objective optimization model; setting multiple sensors in the stern cabin and synchronously collecting first parameter signals; after pre-processing and feature extraction of the first parameter signals, obtaining first multi-dimensional features; inputting the first multi-dimensional features into a deep learning algorithm to obtain first multi-source heterogeneous data; inputting the first multi-source heterogeneous data into the multi-objective optimization model to obtain an initial fusion vibration vector; after adding a test weight on the propulsion shafting, collecting second parameter signals; after pre-processing and feature extraction of the second parameter signals, obtaining second multi-dimensional features; inputting the second multi-dimensional features into a deep learning algorithm to obtain second multi-source heterogeneous data; inputting the second multi-source heterogeneous data into the multi-objective optimization model to obtain a fusion vibration vector under a test weight state; obtaining a propulsion shafting residual unbalance amount by an influence coefficient algorithm based on the initial fusion vibration vector and the fusion vibration vector under the test weight state; obtaining a counterweight suggestion according to the propulsion shafting residual unbalance amount; wherein the counterweight suggestion comprises a counterweight mass and a phase.

2. The stern compartment field dynamic balancing calculation method of multi-sensor information fusion according to claim 1, characterized in that, determining a multi-objective optimization model, comprising: obtaining a stern cabin dynamics model; constructing the multi-objective optimization model according to the stern cabin dynamics model and a set cabin vibration noise evaluation index; wherein the stern cabin dynamics model comprises a shafting dynamics model, a structure vibration propagation model and a fluid-structure coupling model; the shafting dynamics model is used to describe the dynamic response of the shafting under unbalanced excitation; the structure vibration propagation model is used to describe the propagation law of vibration in the stern cabin structure; and the fluid-structure coupling model is used to represent the influence of hydrodynamic action on the vibration.

3. The multi-sensor information fusion stern compartment field dynamic balancing calculation method according to claim 1, characterized in that, after pre-processing and feature extraction of the first parameter signals, obtaining first multi-dimensional features, comprising: performing noise reduction filtering, integral period sampling and fundamental component extraction on the first parameter signals to obtain pre-processed first parameter signals; inputting the pre-processed first parameter signals into a multi-information fusion dynamic balancing module to extract the first multi-dimensional features; wherein the first multi-dimensional features comprise a peak value, a phase, a characteristic spectrum line and a vibration level.

4. The multi-sensor information fusion stern compartment field dynamic balancing calculation method according to claim 1, characterized in that, The first parameter signals comprise first vibration acceleration, first vibration velocity, first vibration displacement, first temperature, first noise signals and key phase signals, and the method further comprises: determining an initial running state of the stern cabin by the first vibration acceleration, the first vibration velocity, the first vibration displacement, the first temperature and the first noise signals; providing initial phase information by the key phase signals.

5. The multi-sensor information fusion stern compartment field dynamic balancing calculation method according to claim 1, characterized in that, The second parameter signals comprise second vibration acceleration, second vibration velocity, second vibration displacement, second temperature and second noise signals, and the method further comprises: determining a running state of the stern cabin under the test weight state by the second vibration acceleration, the second vibration velocity, the second vibration displacement, the second temperature and the second noise signals.

6. The multi-sensor information fusion stern compartment field dynamic balancing calculation method according to claim 1, characterized in that, The setting positions of the sensors comprise: Vibration acceleration sensors and temperature sensors are arranged at the stern bearing, thrust bearing and base of the motor of the propulsion shafting; vibration velocity sensors are arranged on the bulkhead; vibration displacement sensors and key phase sensors are arranged on the propulsion shafting; and sound sensors are arranged on the top of the cabin.

7. A stern compartment field dynamic balancing calculation system of multi-sensor information fusion, characterized in that, The system comprises: a determination module configured to determine a multi-objective optimization model; a first acquisition module configured to arrange multiple sensors in the stern cabin and synchronously acquire first parameter signals; a first preprocessing and feature extraction module configured to obtain first multi-dimensional features by preprocessing and feature extraction of the first parameter signals; a first input module configured to input the first multi-dimensional features into a deep learning algorithm to obtain first multi-source heterogeneous data; a second input module configured to input the first multi-source heterogeneous data into the multi-objective optimization model to obtain an initial fusion vibration vector; a second acquisition module configured to acquire second parameter signals after adding a test weight on the propulsion shafting; a second preprocessing and feature extraction module configured to obtain second multi-dimensional features by preprocessing and feature extraction of the second parameter signals; a third input module configured to input the second multi-dimensional features into a deep learning algorithm to obtain second multi-source heterogeneous data; a fourth input module configured to input the second multi-source heterogeneous data into the multi-objective optimization model to obtain a fusion vibration vector under a test weight state; a residual unbalance amount acquisition module configured to obtain a propulsion shafting residual unbalance amount by an influence coefficient algorithm based on the initial fusion vibration vector and the fusion vibration vector under the test weight state; a weight suggestion acquisition module configured to obtain a weight suggestion based on the propulsion shafting residual unbalance amount; wherein the weight suggestion comprises a weight quality and a phase.

8. The multi-sensor information fusion stern compartment on-site dynamic balancing calculation system according to claim 7, characterized in that, The determination module is specifically configured to: obtain a stern cabin dynamics model; construct the multi-objective optimization model based on the stern cabin dynamics model and a set cabin vibration noise evaluation index; wherein the stern cabin dynamics model comprises an shafting dynamics model, a structure vibration propagation model and a fluid-structure coupling model; the shafting dynamics model is configured to describe a dynamic response of the shafting under unbalanced excitation; the structure vibration propagation model is configured to describe a propagation law of vibration in the stern cabin structure; and the fluid-structure coupling model is configured to represent an influence of hydrodynamic action on the vibration.

9. An electronic device comprising a memory, a processor, the memory having stored thereon a computer program executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1 to 6.

10. A computer readable medium having non-transitory program code executable by a processor, the program code comprising instructions for: The program code causes the processor to execute the method of any one of claims 1 to 6.

Images