Ship acoustic state intelligent forecasting method and system based on lightweight digital model

Abstract

The invention discloses a ship acoustic state intelligent forecasting method and system based on a lightweight digital model, and belongs to the field of ship acoustic monitoring. The method is based on a lightweight digital model technology, vibration acceleration of key parts of a ship is measured in real time, a complex ship structure is modeled and simplified, a digital mapping relation between the ship structure and acoustic characteristics is constructed, and efficient and rapid forecasting and evaluation of the acoustic state of the ship are achieved. A three-dimensional graphic rendering technology is utilized to dynamically display key information such as a vibration monitoring result, a main noise source and an equipment operation state of the ship, so that comprehensive reproduction of an overall vibration state of the ship and intelligent forecasting of an acoustic state of the whole ship are realized. The patent provides a highly integrated, intelligent and portable comprehensive solution for ship acoustic state perception, and has significant engineering application value and scientific perspectiveness.

Description

Technical Field

[0001] The present invention belongs to the field of ship acoustic monitoring, and in particular relates to a method and system for intelligently predicting the acoustic state of a ship based on a lightweight digital model. Background Art

[0002] With the development of the shipping industry, acoustic status monitoring and control during ship operation are becoming increasingly important. During navigation, the operation of internal mechanical equipment and the external environment generate vibration and noise, which not only affects crew comfort but also threatens the safety of the ship's structure and the normal operation of its equipment.

[0003] Traditional methods for monitoring ship acoustic conditions present numerous challenges. In terms of modeling, there is a lack of effective methods for analyzing the acoustic properties of complex structures, making it difficult to understand the connection between structural and acoustic characteristics, resulting in inaccurate and inefficient forecasts. In terms of hardware, equipment often suffers from low integration, limited functionality, and poor interoperability, hindering efficient data collection and real-time status feedback. In field testing, most equipment is limited by size and portability, making flexible deployment difficult, cumbersome, and inefficient.

[0004] Foreign countries had an early start in the field of ship acoustic monitoring, with some research institutions and companies employing advanced sensor technologies and data analysis methods. However, these efforts often focus on monitoring single indicators, lacking comprehensive solutions. Furthermore, some technologies are hardware-intensive and expensive. While domestic research has made some progress, it still faces challenges in lightweight models and the integration of intelligent forecasting algorithms. Most systems also lack visualization and interactivity. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for intelligent prediction of ship acoustic state based on a lightweight digital model, so as to solve the problem of insufficient accuracy and timeliness of traditional ship radiated noise monitoring methods.

[0006] The purpose of the present invention is achieved through the following technical solutions:

[0007] A method for intelligently predicting the acoustic state of a ship based on a lightweight digital model comprises the following steps:

[0008] Step 1: Build a 3D model of the ship and perform lightweight processing, then assign material acoustic and physical properties to the structure;

[0009] Step 2: Select typical mechanical equipment and arrange vibration monitoring points at key locations and sensitive locations on the ship structure, ensuring that the monitoring points are consistent with the 3D model coordinate system and have accurate coordinate values;

[0010] Step 3: Construct a mapping relationship between ship structure vibration and acoustics through numerical simulation or experimental measurement to generate a standardized data set of ship structure vibration response and underwater radiated noise;

[0011] Step 4: Vibration acceleration sensors are placed at vibration monitoring locations to measure vibration acceleration in real time, and the data is transmitted to the monitoring system. A visual interface for ship vibration and acoustic monitoring is designed, and the monitoring data is mapped to the three-dimensional model.

[0012] Step 5: Preprocess the measured vibration acceleration and extract the vibration spectrum data through fast Fourier transform. Build a deep learning model, input the preprocessed vibration spectrum data, and output the underwater radiated noise spectrum prediction results. Input the standardized data set obtained in step 3 as the training set into the deep learning model, and optimize the model's prediction performance by adjusting the network parameters. Integrate the lightweight three-dimensional model in step 1 with the deep learning model to build an intelligent prediction system to achieve real-time mapping and prediction of ship structure and vibration acoustics.

[0013] Step 6: Intelligent prediction and display of the acoustic status of the entire ship: Based on real-time data and prediction results, abnormal areas are marked with dynamic arrows and flashing icons in the three-dimensional visualization interface, and historical data is traced back through the timeline and future noise distribution trends are predicted. Finally, the prediction results are displayed through the visualization interface.

[0014] Furthermore, the three-dimensional model of the ship in step 1 includes the ship's hull outline, internal cabin layout, structural components, and typical mechanical equipment; the lightweighting process reduces model complexity by removing redundant geometric details, merging adjacent surfaces, and optimizing the model topology while retaining key acoustic features; the assignment of material acoustic physical properties to the structure includes classifying and assigning physical properties to beams, plates, and columns in the model, and the data volume of the lightweight three-dimensional model is reduced by 30%-80%;

[0015] The computational complexity reduction after model lightweighting:

[0016] ΔC=C 原 -C 优化ˉ =k·N 冗余

[0017] Where C is the computational complexity, k is the computational cost of a single geometric detail, and N 冗余 is the redundant geometry quantity.

[0018] Furthermore, the typical equipment in step 2 includes the main engine, propellers in the propulsion system, auxiliary mechanical equipment and other equipment that generates large vibration and noise during the navigation of the ship, and vibration monitoring points are arranged at their bases, bulkheads or structural connection nodes.

[0019] Furthermore, in step 3, a mapping relationship between ship structure vibration and acoustics is constructed:

[0020] The frequency domain transfer function of the vibration response is: Among them, U(ω) is the displacement spectrum, F(ω) is the excitation force spectrum;

[0021] The mapping relationship between structural vibration and acoustics is: Where p is the sound pressure, is the displacement velocity;

[0022] The numerical simulation is based on ship structural mechanics, acoustic principles, and vibration theory to establish a finite element / boundary element model of the ship. Taking into account the physical parameters of the ship structure, such as mass, stiffness, and damping, as well as the excitation effects of typical mechanical equipment, the vibration response of the ship structure at the vibration monitoring position under different working conditions is simulated and calculated. The propagation process of sound waves inside the ship structure and in the underwater acoustic field is simulated and calculated based on the acoustic properties of the ship structure material and the acoustic parameters of the surrounding fluid medium. The underwater radiated noise of the ship is simulated and calculated.

[0023] The test measurements include: conducting actual ship vibration and acoustic test experiments, installing high-precision vibration sensors and acoustic sensors at vibration monitoring positions, collecting data on the ship under different operating conditions and at different speeds, loads, and navigation postures, and obtaining the vibration response and radiated noise data of the structure.

[0024] Furthermore, in step 4, the analog signals collected by the sensors are converted into digital signals through a data acquisition card, and the data is transmitted to the ship's central monitoring system; a ship vibration and acoustic monitoring visualization interface is designed based on front-end application development technology, and the monitoring data is associated and mapped with the three-dimensional model; the vibration amplitude, frequency, and acoustic intensity information of typical equipment and structures are intuitively displayed through changes in color, shape, and size visualization elements, and an alarm signal is triggered based on a preset threshold;

[0025] Vibration acceleration a(t) is mapped to color or shape or size; where the color is based on the acceleration magnitude:

[0026] C=map(a(t),a min ,a max ,C green ,C red )

[0027] Among them, map: linear mapping function; a min , a max : acceleration range; C green ,C red : Green to red color value;

[0028] The same applies to mapping acoustic intensity into a three-dimensional model;

[0029] The ship status determination is as follows:

[0030]

[0031] Among them, a safe 、a warning 、a critical are the safety, critical and exceeding thresholds of vibration acceleration monitoring values, respectively. safe <a warning <a ial , the same applies to sound pressure level.

[0032] Render the updated scene including the ship model, equipment model, and measurement point model, as well as the camera view, with high quality according to the rendering loop mechanism of the selected software library;

[0033] The scene update formula is:

[0034] Scene t =update(Model,Data t ,Camera)

[0035] Among them: Model is the ship, equipment and measurement point model; Data t is the monitoring data at time t; Camera is the camera position and viewing angle;

[0036] Add interactive functionality to the model so that when you click on a vibration monitoring point i, a pop-up window displays detailed information:

[0037] Info i ={ID i ,a i (t),SPL i (t),History i ,Maintenance i}

[0038] Among them, ID i is the measuring point identification, a i (t) is the vibration acceleration, SPL i (t) is the sound pressure level, History is the historical data curve, Maintenance i For maintenance records; the window displays the equipment's real-time operating parameters, historical monitoring data curves, equipment maintenance records and other information to provide comprehensive decision-making support for ship operation and maintenance personnel.

[0039] Furthermore, the step 5 extracts the vibration spectrum data by fast Fourier transform,

[0040]

[0041] Where N is the number of sampling points, t n is a discrete time point, f is a frequency, and j is an imaginary unit. It serves as the input data of the intelligent forecasting algorithm of the lightweight digital model;

[0042] Design the input layer, hidden layer, and output layer of the deep learning model. The input layer receives the preprocessed vibration spectrum data, and the output layer outputs the underwater radiated noise spectrum and vibration prediction results:

[0043] y=W (out) h (L) +b (out)

[0044] Among them, y is the prediction result, W (out) is the weight matrix of the output layer, h (L) is the output of the last hidden layer, b (out) is the output bias term;

[0045] Using vibration acceleration spectrum and radiated noise spectrum datasets as training data, a deep learning model is trained. The training data is input into the deep learning model, and the prediction performance of the model is optimized by adjusting the network parameters, including forward propagation, loss calculation, backpropagation, and parameter update.

[0046] Finally, the lightweight three-dimensional model is integrated with the trained deep learning model:

[0047] y final =w d ·f d (X)+w l ·f l (X)

[0048] Among them, f d (X) and f l (X) are the outputs of the deep learning model and the lightweight model, respectively, and the weights w d and w l Set according to the performance of the validation set;

[0049] The ship's position coordinates c i Compared with the vibration data of monitoring point a i and working condition w i Associated to form an input tuple (a i ,c i ,w i ), forming a joint feature vector x i =[a i ,c i ,w i ]∈R m+3+d ; Design data interface to collect real-time vibration spectrum data i and the monitoring point coordinates c in the lightweight model i Exact match: Represented as a paired dataset where a iis collected from position c i Vibration spectrum;

[0050] Input the vibration spectrum ai into the deep learning model to obtain the radiation noise spectrum y i =f θ (a i ); then, the predicted result y is mapped one by one to the position in the three-dimensional coordinate system. i Associated to the coordinate c in the 3D model i , generate the radiation noise forecast value at the noise monitoring point.

[0051] Furthermore, step 6 is based on the intelligent prediction algorithm of the lightweight digital model, which takes the real-time collected ship vibration and acoustic monitoring data as input to intelligently predict the acoustic state of the entire ship, and display the prediction results through the designed visual interface; the predicted distribution change trend of the radiated noise of the entire ship is displayed in the form of color gradient and dynamic arrow indication, and the areas or equipment where acoustic anomalies may occur are identified with flashing icons or special marks, and the predicted position change history and future change trends of the main noise sources are displayed in the form of charts, curves, etc. Ship operation and maintenance personnel judge the changing trend of the ship's acoustic state based on the information displayed on the visual interface and take corresponding control measures in a timely manner.

[0052] A computer device / equipment / system comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the steps of a method for intelligent prediction of ship acoustic state based on a lightweight digital model.

[0053] The beneficial effects of the present invention are:

[0054] (1) By constructing a lightweight digital model of the ship, combining the accurate definition of typical mechanical equipment and vibration monitoring locations, and constructing the mapping relationship between ship structure vibration and acoustics, high-precision vibration sensors are used to collect ship vibration data in real time, achieving an accurate prediction of the ship's acoustic state, and dynamically displaying the monitoring results through a visual interface, allowing users to intuitively understand the changing trend of the ship's acoustic state. At the same time, rich interactive functions are provided to facilitate users to conduct data analysis and decision-making.

[0055] (2) The ship acoustic state intelligent prediction method, system and device based on the lightweight digital model are also equipped with complete ship vibration monitoring hardware equipment and ship acoustic state intelligent prediction module, which can monitor the vibration of the ship in real time and promptly discover potential problems in the operation of the ship. Based on the results of the intelligent prediction, the control strategy of the ship can be optimized to improve the acoustic performance and vibration performance of the ship.

[0056] The intelligent prediction method and system for ship acoustic status based on lightweight digital models of the present invention measures the vibration acceleration of key parts through high-precision vibration monitoring hardware equipment, and combines the digital mapping relationship between ship structure and acoustic characteristics constructed by lightweight digital models to efficiently, quickly and accurately predict and evaluate the ship's acoustic status, providing strong support for the safe operation, performance optimization and intelligent management of ships. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 Flowchart of the intelligent prediction method for ship acoustic state based on lightweight digital model. DETAILED DESCRIPTION

[0058] The present invention will be further described below with reference to the accompanying drawings.

[0059] The present invention provides a method and system for intelligent prediction of ship acoustic status based on lightweight digital models, which deeply integrates front-end application development, three-dimensional graphics rendering technology, high-precision vibration monitoring hardware equipment, and advanced ship radiation noise intelligent prediction algorithms. The system can use mature software tools to build a three-dimensional digital model of the ship (such as ANSYS, Abaqus and other software) to display ship acoustic related information on a visual platform. At the same time, relying on lightweight digital model technology, the complex structure and acoustic characteristics of the ship are accurately modeled and efficiently simplified, and combined with the ship radiation noise intelligent prediction algorithm, etc. to realize the intelligent prediction, comprehensive reproduction and visual interactive display of the ship's acoustic status. According to Figure 1 , the specific steps are as follows:

[0060] Step 1: Build a 3D model of the ship and make it lightweight:

[0061] Comprehensively collect ship design drawings and materials, such as line drawings, general arrangement drawings, detailed structural drawings, and material property information, and use professional 3D modeling software to build a high-precision 3D model of the ship, covering the ship's hull outline, internal cabin layout, structural components (such as beams, plates, columns, etc.) and typical mechanical equipment (such as main engines, propellers, etc.).

[0062] While ensuring the key acoustic characteristics and mechanical properties of the ship structure, the model's data volume and complexity are significantly reduced by removing redundant geometric details, merging adjacent surfaces and volumes, and optimizing the model's topology. This improves the efficiency of the model's storage, transmission, processing, and 3D display. The physical properties of the ship structure are assigned by fully considering the impact of different materials on sound wave propagation characteristics.

[0063] The computational complexity reduction after model lightweighting:

[0064] ΔC=C 原 -C 优化ˉ =k·N 冗余

[0065] Where C is the computational complexity, k is the computational cost of a single geometric detail, and N 冗余 is the redundant geometry quantity.

[0066] Step 2: Define typical machinery and vibration monitoring locations:

[0067] Based on ship acoustics theory and statistical analysis of a large amount of actual ship operation data, typical mechanical equipment that has a significant impact on the overall acoustic state of the ship is determined, including the main engine in the ship's power system, the propeller in the propulsion system, various auxiliary mechanical equipment (such as generators, air conditioning systems, hydraulic pumps, etc.), and other equipment that generates large vibrations and noise during the ship's navigation. Vibration monitoring points are arranged at key locations of typical mechanical equipment and sensitive locations of the ship's structure (such as bulkheads, decks, etc.), ensuring that the typical mechanical locations and monitoring points are in the same coordinate system as the ship's three-dimensional model and have precise coordinate values. The layout of the monitoring points should follow the principle of being able to comprehensively and accurately reflect the overall vibration and acoustic characteristics of the ship, while taking into account operability and installation convenience in the actual ship environment to ensure the validity and reliability of the monitoring data.

[0068] Step 3: Construct the mapping relationship between ship structure vibration and acoustics:

[0069] The frequency domain transfer function of the vibration response is: Among them, U(ω) is the displacement spectrum and F(ω) is the excitation force spectrum.

[0070] The mapping relationship between structural vibration and acoustics is: Where p is the sound pressure, is the displacement velocity.

[0071] There are two ways to obtain the mapping relationship between ship structure vibration and acoustics: numerical simulation and experimental measurement:

[0072] The numerical simulation method is to establish a finite element / boundary element model of a ship based on ship structural mechanics, acoustic principles and vibration theory.

[0073] Finite Element Model (FEM): The ship structure is discretized into a finite number of units, each of which has mass, stiffness, and damping characteristics. The equation of motion of the vibration system is:

[0074] Mu¨+Cu˙+Ku=F(t)

[0075] Among them, M is the mass matrix, C is the damping matrix, K is the stiffness matrix, u, are displacement, velocity, and acceleration vectors respectively, and F(t) is the external excitation force.

[0076] The excitation of typical mechanical equipment (such as main engine, auxiliary engine, propeller, etc.) can be modeled as a simple harmonic force: F(t) = F0e jwt , where F0 is the excitation force amplitude and w is the excitation frequency.

[0077] The vibration response of the vibration monitoring position determined in step S2 under different working conditions of the ship structure is obtained by simulation calculation;

[0078] u(ω)=(K-ω 2 M+iωC) -1 F(ω)

[0079] Combining the acoustic properties of the ship's structural materials and the acoustic parameters of the surrounding fluid media (such as seawater and air), the propagation process of sound waves inside the ship's structure and the underwater acoustic field is simulated, and the ship's underwater radiated noise is obtained through simulation calculation.

[0080] The test measurement method includes: conducting a real-ship vibration and acoustic test experiment, installing high-precision vibration sensors and acoustic sensors at the vibration monitoring positions determined in step S2, and collecting structural vibration response and radiated noise data of the ship under different operating conditions, different speeds (such as 5 knots, 10 knots, and 15 knots), loads (such as empty, half-loaded, and fully loaded), and navigation attitudes (such as straight sailing and turning).

[0081] Based on unified data standards and naming conventions, detailed identification information, including name, ID, type, and system affiliation, is set for equipment models and vibration monitoring points to ensure their uniqueness and identifiability in complex data interaction environments. Simulation and measurement data are labeled, including information such as operating conditions and monitoring point coordinates, to form a complete ship structure vibration and radiated noise dataset.

[0082] Step 4: Dynamically display the vibration monitoring results of typical ship equipment and structures:

[0083] The vibration acceleration a(t) is measured in real time by placing a high-precision vibration acceleration sensor at the vibration monitoring position defined in step S2. The unit is m / s 2 The sensor sampling frequency must meet the Nyquist sampling theorem and is usually more than twice the highest frequency of the vibration signal (such as 10kHz). The sensor measures the three-axis acceleration a x (t),a y (t),a z (t) The resultant acceleration is: a(t) = a x (t) 2 +a y (t) 2 +a z (t) 2 .

[0084] A data acquisition card is used to convert the analog signals collected by the sensor into digital signals, and data transmission technology (such as wired network, wireless network, etc.) is used to transmit the data to the ship's central monitoring system.

[0085] A visual interface for ship vibration and acoustic monitoring is designed based on front-end application development technology, and the vibration monitoring data are associated and mapped with the corresponding positions in the three-dimensional model.

[0086] Vibration amplitude, frequency, acoustic intensity and other information of typical equipment and structures are intuitively displayed through changes in visual elements such as color, shape, and size.

[0087] Vibration acceleration a(t) is mapped to color, shape, or size. For example, color is based on acceleration magnitude.

[0088] C=map(a(t),a min ,a max ,C green ,C red )

[0089] Among them, map: linear mapping function; a min , a max : acceleration range; C green ,C red : Green to red color value.

[0090] The same applies to mapping acoustic intensity into a three-dimensional model.

[0091] Add rich dynamic interactive functions to the visual interface, allowing users to easily view, analyze and operate monitoring data.

[0092] A data warning and event triggering mechanism has been established, referencing the International Maritime Organization (IMO) ship vibration standards, classification society standards, and national standards for different ship navigation conditions, compartment locations, and equipment. When vibration monitoring data exceeds a preset threshold or an abnormal acoustic event occurs, the system automatically triggers an alarm signal and highlights the equipment area with excessive vibration amplitude in flashing red. Detailed alarm information and response recommendations are provided to assist ship managers in making timely decisions. Equipment areas with critical vibration amplitudes are displayed in yellow as a warning; areas with lower vibration amplitudes within a safe range are displayed in green. The specific values of the monitoring data are displayed in real time on the model as dynamic digital labels. The status determination is shown in the following formula.

[0093]

[0094] Among them, a safe 、a warning 、a criticalare the safety, critical and exceeding thresholds of vibration acceleration monitoring values, respectively. safe <a warning <a ial , the same applies to sound pressure level.

[0095] Based on the rendering loop mechanism of the selected software library (such as Three.js), the updated scene containing the ship model, equipment model, and measurement point model, as well as the camera view, is rendered with high quality.

[0096] The scene update formula is:

[0097] Scene t =update(Model,Data t ,Camera)

[0098] Including: Model ship, equipment and measurement point model; Data t Monitoring data at time t; Camera position and viewing angle.

[0099] This allows for an intuitive display of the relationship between equipment and vibration monitoring points in the ship’s three-dimensional space, providing rich and accurate visualization.

[0100] Add interactive functionality to the model so that when you click on a vibration monitoring point i, a pop-up window displays detailed information:

[0101] Info i ={ID i ,a i (t),SPL i (t),History i ,Maintenance i}

[0102] Among them, ID i : Measuring point identification, a i (t) is the vibration acceleration, SPL i (t) is the sound pressure level, History is the historical data curve, Maintenance i The window displays the equipment's real-time operating parameters, historical monitoring data curves, equipment maintenance records, and other information to provide comprehensive decision-making support for ship operation and maintenance personnel.

[0103] Set timestamps so users can view changes in the ship's vibroacoustic state at different historical moments by dragging the timeline. Provides zoom, pan, and rotate controls for the 3D model, allowing users to freely adjust the viewing angle by dragging the mouse and delve into detailed information on different parts of the ship.

[0104] Step 5: Implement intelligent forecasting algorithm based on lightweight digital model:

[0105] First, the ship vibration acceleration a(t) collected by the high-precision vibration acceleration sensor arranged at the vibration monitoring position defined in step 2 is preprocessed. Wavelet denoising or low-pass filtering is applied to filter out high-frequency noise and retain effective vibration information. Fast Fourier transform (FFT) is used to convert the vibration time domain signal into a frequency domain signal. The FFT formula is:

[0106]

[0107] Where N is the number of sampling points, t n is a discrete time point, f is a frequency, and j is an imaginary unit. It serves as the input data of the intelligent forecasting algorithm of the lightweight digital model;

[0108] The input layer, hidden layer, and output layer of the deep learning model are redesigned. The input layer receives the preprocessed vibration spectrum data, and the output layer outputs the underwater radiated noise spectrum and vibration prediction results:

[0109] y=W (out) h (L) +b (out)

[0110] Among them, y is the prediction result, W (out) is the weight matrix of the output layer, h (L) is the output of the last hidden layer, b (out) is the output bias term;

[0111] The vibration acceleration spectrum and radiated noise spectrum dataset are used as training data. This dataset contains ship structure vibration data, underwater radiated noise data, and corresponding label information. The dataset contains the following information:

[0112] The input features are X: pre-processed ship structure vibration spectrum data, with a dimension of n×m, where n is the number of monitoring points and m is the frequency point;

[0113] The target output is Y n : The corresponding underwater radiation noise data, dimension is n×c n , where c n is the characteristic quantity of the radiated noise output;

[0114] Input the training data into the deep learning model and optimize the model's prediction performance by adjusting the network parameters, including forward propagation, loss calculation, backpropagation and parameter update:

[0115] Given input data X, after layer l:

[0116] z (l) =W(l) h (l-1) +b (l)

[0117] h (l) =f(z (l) )

[0118] Among them, W (l) is the weight matrix of the lth layer, b (l) is the bias vector of the lth layer, h (l-1) is the activation value of the previous layer (X for the input layer), and f is the activation function.

[0119] Final output y pred is the activation output of the last layer;

[0120] Based on the model output y pred And the true label y, calculate the loss:

[0121]

[0122] Where N is the number of samples, θ = {W, b} is the set of all network parameters;

[0123] Obtain the gradient by deriving the parameters through the loss function:

[0124] and

[0125] This process applies the chain rule to propagate the error back from the output layer to the input layer layer by layer;

[0126] Use the gradient descent algorithm to adjust the parameters:

[0127]

[0128] Among them, γ is the learning rate, which controls the update step size;

[0129] Use cross-validation, regularization and other techniques to prevent overfitting and ensure the generalization ability of the model; divide the data set into K subsets, select one subset each time as the validation set, and the remaining K-1 subsets as the training set, repeat the training and evaluation process K times, and finally calculate the average of the K evaluation results as the estimate of the model performance. The performance evaluation formula is:

[0130]

[0131] in, is the loss function value calculated in the k-th cross validation;

[0132] Finally, the lightweight three-dimensional model is integrated with the trained deep learning model:

[0133] yfinal =w d ·f d (X)+w l ·f l (X)

[0134] Among them, f d (X) and f l (X) are the outputs of the deep learning model and the lightweight model, respectively, and the weights w d and w l Set according to the performance of the validation set;

[0135] The ship's position coordinates c i Compared with the vibration data of monitoring point a i and working condition w i Associated to form an input tuple (a i ,c i ,w i ), forming a joint feature vector x i =[a i ,c i ,w i ]∈R m+3+d ; Design data interface to collect real-time vibration spectrum data i and the monitoring point coordinates c in the lightweight model i Exact match: Represented as a paired dataset where a i is collected from position c i Vibration spectrum;

[0136] The vibration spectrum a i Input into the deep learning model to obtain the radiation noise spectrum y i =f θ (a i ); then, the predicted result y is mapped one by one to the position in the three-dimensional coordinate system. i Associated to the coordinate c in the 3D model i , generate the radiation noise forecast value at the noise monitoring point.

[0137] Ensure accurate matching and synchronization between the input data of the deep learning model and the structural positions in the lightweight model, and achieve real-time mapping and prediction of ship structure and vibroacoustics.

[0138] Step 6: Intelligent prediction and display of the entire ship's acoustic status:

[0139] Based on the intelligent prediction algorithm based on the lightweight digital model constructed in step 5, the ship vibration and acoustic monitoring data collected in real time in step 4 is used as input to perform intelligent prediction of the acoustic state of the entire ship.

[0140] An intuitive and easy-to-use visualization interface is designed to display the ship's acoustic status prediction results obtained by the intelligent prediction model. The predicted distribution trend of the ship's radiated noise is displayed through color gradients and dynamic arrow indicators. Areas or equipment that may experience acoustic anomalies are identified with flashing icons or special markers. The predicted location changes and future trends of major noise sources are displayed in charts and curves.

[0141] Based on the information displayed on the visual interface, ship operation and maintenance personnel can judge the changing trend of the ship's acoustic status and take corresponding control measures in a timely manner, such as adjusting equipment operating parameters and optimizing the ship's navigation route, to reduce the impact of ship noise on personnel health, equipment operation and the surrounding environment, and ensure the safe, comfortable and environmentally friendly operation of the ship.

[0142] Example 1:

[0143] Taking a 5000-ton bulk carrier as an example, the application of the present invention is described in detail. The specific steps are as follows:

[0144] Step S1: construct a three-dimensional model of the ship and perform lightweight processing;

[0145] Comprehensive design drawings and documentation for the vessel were collected, including lines, general arrangement drawings, detailed structural drawings, and material properties. Using professional 3D modeling software SolidWorks, a 3D model of the vessel was constructed, encompassing the hull profile, interior cabin layout, structural components, and typical mechanical equipment. Unnecessary geometric details were removed, adjacent faces and volumes were merged, and the topology was optimized. The impact of materials on sound wave propagation characteristics was fully considered, and physical properties were assigned to the model. This reduced the model data volume by 40%, significantly improving storage and transmission efficiency.

[0146] Step S2: defining typical mechanical equipment and vibration monitoring locations;

[0147] Based on marine acoustics theory and the vessel's operational data, the main engine, propeller, generator, and air conditioning system were identified as representative equipment. Vibration monitoring points were placed at key locations, including the main engine feet, propeller shafting, generator base, and air conditioning system inlet and outlet piping, as well as sensitive locations such as bulkheads and decks, to ensure alignment with the 3D model coordinates.

[0148] Step S3: constructing a mapping relationship between ship structure vibration and acoustics;

[0149] Numerical simulation: Based on ship structural mechanics, acoustic principles, and vibration theory, a finite element model of the ship is established in Abaqus software. Taking into account physical parameters such as mass, stiffness, and damping of the ship structure, as well as the excitation effects of typical mechanical equipment, simulation calculations are performed to obtain the vibration response and radiated noise of the ship structure under various operating conditions.

[0150] Test measurement: High-precision sensors are installed at the monitoring location to collect vibration and noise data under different speeds, loads, and navigation postures.

[0151] The ship vibration and noise data are labeled to form a complete ship structure vibration and radiation noise data set, which is stored in the database.

[0152] Step S4: Dynamically display the vibration monitoring results of typical ship equipment and structures;

[0153] High-precision vibration accelerometers are deployed at vibration monitoring locations to measure vibration acceleration in real time. Data acquisition cards convert the analog signals collected by the sensors into digital signals and transmit the data to the ship's central monitoring system. A visualization interface, developed using the Vue architecture and Three.js, maps the monitoring data to the 3D model. An early warning mechanism, based on International Maritime Organization standards, is implemented. When vibration data exceeds standards, the system automatically issues an alarm, highlights the areas exceeding the standard, and provides response recommendations.

[0154] Step S5: Intelligent forecasting algorithm based on lightweight digital model.

[0155] The ship structure vibration data collected by the vibration acceleration sensor is preprocessed, and the vibration data spectrum is extracted using Fast Fourier Transform (FFT) as the input data of the lightweight digital model intelligent prediction algorithm.

[0156] The deep learning model's input, hidden, and output layers are designed. The input layer receives preprocessed vibration spectrum data, and the output layer outputs the predicted underwater radiated noise spectrum. A ship structure vibration and radiated noise dataset, containing ship structure vibration data, underwater radiated noise data, and corresponding label information (coordinates and operating conditions), is used as training data. The training data is fed into the deep learning model, and the model's predictive performance is optimized by adjusting network parameters. Cross-validation and regularization techniques are used to prevent overfitting.

[0157] The lightweight digital model and the trained deep learning model are integrated, and a data interface is developed to associate the ship's position coordinates with the monitoring point data, ensuring that the input data of the deep learning model (vibration monitoring point data) accurately matches the structural position in the lightweight model, realizing real-time mapping and prediction of ship structure and vibration acoustics.

[0158] Step S6: Intelligent prediction and display of the acoustic status of the entire ship.

[0159] An intelligent prediction algorithm based on a lightweight digital model uses real-time ship vibration and acoustic monitoring data as input to intelligently predict the acoustic status of the entire ship. An intuitive and easy-to-use visual interface is designed to display the prediction results of the entire ship's acoustic status obtained by the intelligent prediction model through a visual interface. The predicted distribution trend of the entire ship's radiated noise is displayed through color gradients and dynamic arrow indicators. Areas or equipment that may experience acoustic anomalies are identified with flashing icons or special marks. The predicted location change history and future change trends of major noise sources are displayed in the form of charts and curves. Ship operation and maintenance personnel can judge the changing trend of the ship's acoustic status based on the information displayed on the visual interface and take corresponding control measures in a timely manner.

[0160] The functions of the intelligent prediction system for ship acoustic states based on lightweight digital models in the present invention can be described by the aforementioned intelligent prediction method for ship acoustic states based on lightweight digital models, and will not be repeated here.

[0161] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A method for intelligent prediction of ship acoustic state based on a lightweight digital model, characterized by: The following steps are involved: Step 1: Build a 3D model of the ship and perform lightweight processing, then assign material acoustic and physical properties to the structure; Step 2: Select typical mechanical equipment and arrange vibration monitoring points at key locations and sensitive locations on the ship structure, ensuring that the monitoring points are consistent with the 3D model coordinate system and have accurate coordinate values; Step 3: Construct a mapping relationship between ship structure vibration and acoustics through numerical simulation or experimental measurement to generate a standardized data set of ship structure vibration response and underwater radiated noise; Step 4: Vibration acceleration sensors are placed at vibration monitoring locations to measure vibration acceleration in real time, and the data is transmitted to the monitoring system. A visual interface for ship vibration and acoustic monitoring is designed, and the monitoring data is mapped to the three-dimensional model. Step 5: Preprocess the measured vibration acceleration and extract the vibration spectrum data through fast Fourier transform. Build a deep learning model, input the preprocessed vibration spectrum data, and output the underwater radiated noise spectrum prediction results. Input the standardized data set obtained in step 3 as the training set into the deep learning model, and optimize the model's prediction performance by adjusting the network parameters. Integrate the lightweight three-dimensional model in step 1 with the deep learning model to build an intelligent prediction system to achieve real-time mapping and prediction of ship structure and vibration acoustics. Step 6: Intelligent prediction and display of the acoustic status of the entire ship: Based on real-time data and prediction results, abnormal areas are marked with dynamic arrows and flashing icons in the three-dimensional visualization interface, and historical data is traced back through the timeline and future noise distribution trends are predicted. Finally, the prediction results are displayed through the visualization interface.

2. The method for intelligent prediction of ship acoustic state based on a lightweight digital model according to claim 1, characterized in that: The three-dimensional model of the ship in step 1 includes the ship's hull outline, internal cabin layout, structural components, and typical mechanical equipment; the lightweighting process reduces model complexity by removing redundant geometric details, merging adjacent surfaces, and optimizing the model topology while retaining key acoustic features; the assignment of material acoustic physical properties to the structure includes classifying and assigning physical properties to the beams, plates, and columns in the model, and the amount of data in the lightweight three-dimensional model is reduced by 30%-80%; The computational complexity reduction after model lightweighting: ΔC=C 原 -C 优化ˉ =k·N 冗余 Where C is the computational complexity, k is the computational cost of a single geometric detail, and N 冗余 is the redundant geometry quantity.

3. The method for intelligent prediction of ship acoustic state based on a lightweight digital model according to claim 1, characterized in that: Typical equipment in step 2 includes the main engine, propellers in the propulsion system, auxiliary mechanical equipment, and other equipment that generates large vibration and noise during the ship's navigation, and vibration monitoring points are arranged at their bases, bulkheads, or structural connection nodes.

4. The method for intelligent prediction of ship acoustic state based on a lightweight digital model according to claim 1, characterized in that: In step 3, the mapping relationship between ship structure vibration and acoustics is constructed: The frequency domain transfer function of the vibration response is: Where U(ω) is the displacement spectrum, F(ω) is the excitation force spectrum; The mapping relationship between structural vibration and acoustics is: Where p is the sound pressure, is the displacement velocity; The numerical simulation is based on ship structural mechanics, acoustic principles, and vibration theory to establish a finite element / boundary element model of the ship. Taking into account the physical parameters of the ship structure, such as mass, stiffness, and damping, as well as the excitation effects of typical mechanical equipment, the vibration response of the ship structure at the vibration monitoring position under different working conditions is simulated and calculated. The propagation process of sound waves inside the ship structure and in the underwater acoustic field is simulated and calculated based on the acoustic properties of the ship structure material and the acoustic parameters of the surrounding fluid medium. The underwater radiated noise of the ship is simulated and calculated. The test measurements include: conducting actual ship vibration and acoustic test experiments, installing high-precision vibration sensors and acoustic sensors at vibration monitoring positions, collecting data on the ship under different operating conditions and at different speeds, loads, and navigation postures, and obtaining the vibration response and radiated noise data of the structure.

5. The method for intelligent prediction of ship acoustic state based on a lightweight digital model according to claim 1, characterized in that: Step 4 converts the analog signals collected by the sensors into digital signals through a data acquisition card and transmits the data to the ship's central monitoring system; designs a ship vibration and acoustic monitoring visualization interface based on front-end application development technology, and associates and maps the monitoring data with the three-dimensional model; intuitively displays the vibration amplitude, frequency, and acoustic intensity information of typical equipment and structures through changes in color, shape, and size visualization elements, and triggers an alarm signal based on a preset threshold; Vibration acceleration a(t) is mapped to color or shape or size; where the color is based on the acceleration magnitude: C=map(a(t),a min ,a max ,C green ,C red ) Among them, map: linear mapping function; a min , a max : acceleration range; C green ,C red : Green to red color value; The same applies to mapping acoustic intensity into a three-dimensional model; The ship status determination is as follows: Among them, a safe 、a warning 、a critical are the safety, critical and exceeding thresholds of vibration acceleration monitoring values, respectively. safe <a warning <a ial , the same applies to sound pressure level. Render the updated scene including the ship model, equipment model, and measurement point model, as well as the camera view, with high quality according to the rendering loop mechanism of the selected software library; The scene update formula is: Scene t =update(Model,Data t ,Camera) Among them: Model is the ship, equipment and measurement point model; Data t is the monitoring data at time t; Camera is the camera position and viewing angle; Add interactive functionality to the model so that when you click on a vibration monitoring point i, a pop-up window displays detailed information: Info i ={ID i ,a i (t),SPL i (t),History i ,Maintenance i } Among them, ID i is the measuring point identification, a i (t) is the vibration acceleration, SPL i (t) is the sound pressure level, History is the historical data curve, Maintenance i For maintenance records; the window displays the equipment's real-time operating parameters, historical monitoring data curves, equipment maintenance records and other information to provide comprehensive decision-making support for ship operation and maintenance personnel.

6. The method for intelligent prediction of ship acoustic state based on a lightweight digital model according to claim 1, characterized in that: Step 5 extracts vibration spectrum data by fast Fourier transform, Where N is the number of sampling points, t n is a discrete time point, f is a frequency, and j is an imaginary unit. It serves as the input data of the intelligent forecasting algorithm of the lightweight digital model; Design the input layer, hidden layer, and output layer of the deep learning model. The input layer receives the preprocessed vibration spectrum data, and the output layer outputs the underwater radiated noise spectrum and vibration prediction results: y=W (out) h (L) +b (out) Among them, y is the prediction result, W (out) is the weight matrix of the output layer, h (L) is the output of the last hidden layer, b (out) is the output bias term; The deep learning model is trained using the vibration acceleration spectrum and radiation noise spectrum datasets as training data. The training data is fed into the deep learning model, and the prediction performance of the model is optimized by adjusting the network parameters, including forward propagation, loss calculation, backpropagation, and parameter update. Finally, the lightweight three-dimensional model is integrated with the trained deep learning model: y final =w d ·f d (X)+w l ·f l (X) Among them, f d (X) and f l (X) are the outputs of the deep learning model and the lightweight model, respectively, and the weights w d and w l Set based on the performance of the validation set; The ship's position coordinates c i Compared with the vibration data of monitoring point a i and working condition w i Associated to form an input tuple (a i ,c i ,w i ), forming a joint feature vector x i =[a i ,c i ,w i ]∈R m+3+d ; Design data interface to collect real-time vibration spectrum data i and the monitoring point coordinates c in the lightweight model i Exact match: Represented as a paired dataset where a i is collected from position c i Vibration spectrum; The vibration spectrum a i Input into the deep learning model to obtain the radiation noise spectrum y i =f θ (a i ); then, the predicted result y is mapped one by one to the position in the three-dimensional coordinate system. i Associated to the coordinate c in the 3D model i , generate the radiation noise forecast value at the noise monitoring point.

7. The method for intelligent prediction of ship acoustic state based on a lightweight digital model according to claim 1, characterized in that: In step 6, an intelligent prediction algorithm based on a lightweight digital model uses the real-time collected ship vibration and acoustic monitoring data as input to perform an intelligent prediction of the acoustic state of the entire ship, and displays the prediction results through a designed visual interface; The predicted distribution change trend of the entire ship's radiated noise is displayed in the form of color gradients and dynamic arrow indicators. Flashing icons or special marks are used to identify areas or equipment where acoustic anomalies may occur. The predicted position change history and future change trends of major noise sources are displayed in the form of charts and curves. Ship operation and maintenance personnel can judge the changing trend of the ship's acoustic status based on the information displayed on the visual interface and take corresponding control measures in a timely manner.

8. A computer device / apparatus / system comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 7.

Images