Gas-liquid interface identification and ship sloshing liquid level correction method and system

Abstract

The invention provides a gas-liquid interface identification and ship sloshing liquid level correction method and system, and the method comprises the steps: extracting image edge and gray texture features, achieving the state identification of a liquid-gas interface through a lightweight convolutional neural network model, and dynamically generating a collection strategy according to the state identification; then collecting original liquid level signals and synchronously obtaining IMU data, extracting a multi-mode component through signal decomposition, constructing a disturbance recognition model by combining an IMU, filtering disturbance related components and reconstructing a stable liquid level; and further modeling the disturbance component into a residual sequence, realizing disturbance trend prediction and liquid level dynamic correction by using a time sequence prediction model, and outputting more stable and reliable liquid level data. The problem that liquid level measurement is unstable in the LNG ship sloshing environment can be effectively solved, image recognition and IMU data are fused, liquid level disturbance suppression and dynamic correction are achieved, and the method has the advantages of being self-adaptive, resistant to interference, stable in measurement and the like and is suitable for high-precision liquid level monitoring under the complex working condition.

Description

Technical Field

[0001] This application relates to the field of liquefied natural gas storage and transportation technology, and more specifically to a gas-liquid interface identification and ship sloshing level correction method and system. Background Technology

[0002] Liquefied natural gas (LNG), as a clean and efficient form of energy, has seen its share in global energy transportation steadily increase in recent years. Because it must be transported at extremely low temperatures (approximately -162°C) and stable pressures, the safety and accurate monitoring of LNG storage and transportation are paramount. During LNG transportation, monitoring the liquid level in the ship's storage tanks is one of the core elements ensuring safe loading, unloading, and navigational stability.

[0003] Currently, LNG carriers commonly use differential pressure, float, capacitive, and radar level gauges for level monitoring. However, during navigation, especially in adverse sea conditions (such as strong winds and large waves), the liquid level in the storage tanks of LNG carriers experiences violent sloshing and irregular fluctuations. These violent fluctuations not only cause frequent fluctuations in the level gauge output signal but may also lead to severe distortion of the measured value or even momentary failure of the measuring sensor. This dynamic disturbance results in significant deviations in the tracking of the actual liquid level using traditional level gauges, affecting the reliability and response efficiency of the storage and transportation system's level data. Summary of the Invention

[0004] This application provides a gas-liquid interface identification and ship sloshing liquid level correction method and system, which can improve the accuracy of gas-liquid interface identification, dynamically correct liquid level by integrating multi-source data, has strong anti-interference ability and prediction function, and reduces the impact of ship sloshing on liquid level measurement results.

[0005] In a first aspect, this application provides a method for gas-liquid interface identification and ship sloshing level correction. The method includes: extracting edge information and grayscale texture features from real-time acquired image data and classifying the state of the gas-liquid interface using a trained lightweight convolutional neural network model; generating an acquisition strategy based on the classification results of the gas-liquid interface state; acquiring real-time raw liquid level signals according to the acquisition strategy and simultaneously acquiring IMU (Inertial Measurement Unit) data; processing the raw liquid level signals using a preset decomposition method to generate multimodal components and constructing a liquid surface disturbance prediction model based on the IMU data; identifying the principal component mode of the disturbance and filtering out the mode components related to the disturbance to reconstruct a stable liquid level signal; modeling the filtered disturbance mode components as a disturbance residual sequence and constructing a residual time series prediction model to predict the liquid level disturbance trend and achieve dynamic correction of the liquid level; and outputting dynamically corrected liquid level data.

[0006] In one alternative embodiment of the first aspect, when generating the acquisition strategy, the method includes: acquiring an edge map of the image data using an edge detection algorithm and extracting texture features of the image data using a gray-level co-occurrence matrix, wherein the texture features include at least contrast, energy, homogeneity, and entropy features; inputting the edge map and texture features into a trained MobileNet or EfficientNet-Lite lightweight convolutional neural network recognition model and outputting a predicted liquid-gas interface height and a liquid-gas state classification vector; and dynamically switching the weight source signal based on the liquid-gas state classification vector result. Where w imu For IMU channel weights, w liq Here, W represents the channel weights of the level sensor, W is the weight mapping matrix, and b is the bias term; a corresponding acquisition strategy is generated based on the weight source signal: s t =[f t ,w imu ,w liq ,F pre ], where f t F is the sampling frequency. pre The filtering strategy is selected based on the disturbance level; at the same time, the gas-liquid interface status label is output, which includes at least the following: stable liquid surface, presence of bubbles or foam, violent shaking, and severe splashing interference.

[0007] In one alternative embodiment of the first aspect, when selecting a filtering strategy based on the perturbation level, the method includes: inputting image data within a time window and performing time-series encoding on the image data using a time encoder to extract time-series perturbation features; decoding the time-series perturbation features to generate a vertical perturbation index, a horizontal perturbation index, and a local perturbation index; constructing a three-dimensional perturbation vector based on the vertical perturbation index, the horizontal perturbation index, and the local perturbation index and introducing a perturbation level label to map the three-dimensional perturbation vector to the perturbation level; and dynamically selecting a filtering strategy based on the perturbation level, wherein the filtering strategy includes at least one of mean filtering, Kalman filtering, and wavelet denoising.

[0008] In one alternative of the first aspect, when acquiring real-time data according to the acquisition strategy, the method includes: acquiring real-time raw differential pressure signal data, capacitance signal data, and radar signal data of liquid level according to the liquid level sampling frequency and filtering strategy corresponding to the acquisition strategy; and acquiring real-time three-axis attitude angle and acceleration data of the IMU inertial measurement unit according to the IMU sampling frequency and filtering strategy corresponding to the acquisition strategy.

[0009] In one alternative embodiment of the first aspect, when reconstructing a stable liquid level signal, the method includes: decomposing the original liquid level signal into several modal components using empirical mode decomposition or variational mode decomposition.

[0010] Where u k (t) represents the k-th modal component, K is the total number of modes obtained from the decomposition, and L(t) is the original liquid level signal, including the original differential pressure, capacitance, and radar signal data; for each modal component u k (t), calculate the cross-correlation strength between it and the acceleration signal: Where R k Let a be the average cross-correlation between the k-th mode and the z-axis acceleration. z (t) represents the vertical acceleration, and T is the integration time window. If |R k If the value is greater than the disturbance discrimination threshold, the corresponding modal component is considered to be the principal component of the disturbance; an acceleration-driven liquid surface disturbance prediction model is established: in For the predicted disturbance signal,

[0011] a i (t)∈{a x (t),a y (t),a z (t)} represents the triaxial acceleration of the IMU inertial measurement unit, β i For regression weights, τ i The lag time for each acceleration channel reflects the dynamic response; modal components identified as disturbance-related are removed and the stable liquid level signal is reconstructed. Where I non-disturb ={1,2,…,K}\I disturb I disturb The set of modal components that are identified as disturbances.

[0012] In one alternative embodiment of the first aspect, when predicting liquid level disturbance trends and implementing dynamic correction of the liquid level, the method includes: extracting disturbance residuals from the original liquid level signal and the stable liquid level signal.

[0013] r(t) = L raw (t)-L stable r(t) is the disturbance residual signal, representing the influence of the sloshing disturbance on the liquid level. Based on the time dependence of the disturbance residual signal, a residual time series prediction model is constructed to predict the disturbance trend at the next moment. in For predicting the residuals at the next time step, n is the length of the input sequence of the residual time series prediction model, and M is the residual time series prediction model, including at least one of LSTM, GRU, 1D-CNN, Transformer, and ARIMA models; after predicting the perturbation trend, the liquid level data is corrected based on the predicted values: Where L corrected (t+1) represents the corrected liquid level data, taking into account both the current stable trend and future disturbance trends; Lstable (t+1) represents the stable liquid level trend.

[0014] In one alternative embodiment of the first aspect, when correcting the liquid level data, the method further includes: extracting spatiotemporal dynamic embedding features based on real-time acquired image data; introducing a deformable convolutional network to enhance the model's ability to perceive disturbances; and performing dynamic offset recognition of edge regions: ΔL img (t)=V deformCNN (I t-n ), where ΔL img (t) represents the image backtracking perturbation compensation term, I t-n For the image frame at time tn; the image backtracking perturbation compensation term is combined with the stable liquid level trend and the predicted perturbation residual value to dynamically correct the liquid level data:

[0015]

[0016] In one alternative embodiment of the first aspect, when dynamically correcting the liquid level data, the method further includes: constructing a liquid level sensing signal confidence factor, an IMU confidence factor, and an image confidence factor based on the perturbation level, signal-to-noise ratio, and mean prediction residual of the liquid level sensor channel, IMU channel, and image acquisition channel within a preset time range; and dynamically weighting and fusing the constructed confidence factors to correct the liquid level data.

[0017] Where ∈1, ∈2, and ∈3 are the confidence factors of the liquid level sensing signal, the IMU confidence factor, and the image confidence factor, respectively. fused (t+1) represents the dynamically weighted fusion corrected liquid level data; output the dynamically weighted fusion corrected liquid level data.

[0018] In one alternative to the first aspect, when dynamically weighted fusion and correction of liquid level data, the method includes: constructing a liquid level variation rate monitoring index within a sliding window based on a stable liquid level trend.

[0019] Where n is the sliding window size; if the variation rate monitoring index exceeds the preset threshold or any value of the confidence factor is lower than the preset tolerance value, the current state is determined to be abnormal and the emergency liquid level correction process is entered. The emergency liquid level correction process includes: reducing the sampling frequency and extending the sliding window stabilization period, temporarily shielding the channel with the lowest confidence and increasing the confidence weight of other channels, or introducing the moving average trend of the historical liquid level stabilization sequence for short-term compensation.

[0020] Secondly, this application provides a gas-liquid interface identification and ship sloshing level correction system using the above-mentioned liquid level correction method, comprising: a sensor assembly including a liquid level sensor, an image acquisition unit, and an IMU inertial measurement unit, wherein the liquid level sensor is used to acquire raw pressure difference signal data, capacitance signal data, and radar signal data of the target container; the image acquisition unit is used to acquire image data inside the target container; and the IMU inertial measurement unit is used to acquire three-axis attitude angle and acceleration data of the target container; and a control unit connected to the sensor assembly, wherein the control unit includes: an image processing module used to extract edge information and grayscale texture features contained in the real-time acquired image data and use a trained lightweight convolutional neural network model to analyze the gas-liquid interface. The system comprises several modules: a state classification module, which generates a data acquisition strategy based on the liquid-gas interface state classification results; a data acquisition module, which acquires image data and, according to the acquisition strategy, acquires real-time raw liquid level signals and simultaneously obtains IMU (Inertial Measurement Unit) data; a stabilization reconstruction module, which processes the raw liquid level signal using a preset decomposition method to generate multimodal components and constructs a liquid surface disturbance prediction model based on the IMU data, thereby identifying the principal disturbance modal components and filtering out disturbance-related modal components to reconstruct a stable liquid level signal; and a liquid level correction module, which models the filtered disturbance modal components as disturbance residual sequences and constructs a residual time series prediction model to predict liquid level disturbance trends and achieve dynamic liquid level correction, outputting dynamically corrected liquid level data.

[0021] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0022] The accompanying drawings, which are incorporated herein and form part of this specification, illustrate one or more embodiments of the present application and, together with the description, serve to explain the principles of the present application and to enable those skilled in the art to make and use the present application.

[0023] Figure 1 This is a schematic diagram of the module connections of an exemplary gas-liquid interface recognition and ship sloshing level correction system according to some embodiments of this application.

[0024] Figure 2 This is a schematic flowchart illustrating an exemplary gas-liquid interface identification and ship sloshing liquid level correction method according to some embodiments of this application.

[0025] Figure 3 This is a flowchart illustrating an exemplary data collection strategy generation method according to some embodiments of this application.

[0026] Figure 4This is a schematic diagram showing the output of a predicted liquid-gas interface height and liquid-gas state classification vector by an exemplary lightweight convolutional neural network recognition model according to some embodiments of this application.

[0027] Figure 5 This is a flowchart illustrating an exemplary filtering strategy selection method according to some embodiments of this application.

[0028] Figure 6 This is a flowchart illustrating an exemplary method for acquiring real-time data according to some embodiments of this application.

[0029] Figure 7 This is a flowchart illustrating an exemplary method for reconstructing a stable liquid level signal according to some embodiments of this application.

[0030] Figure 8 This is a schematic flowchart illustrating an exemplary implementation of a dynamic liquid level correction method according to some embodiments of this application.

[0031] Figure 9 This is a flowchart illustrating an exemplary method for correcting liquid level data according to some embodiments of this application.

[0032] Figure 10 This is a flowchart illustrating an exemplary method for dynamically correcting liquid level data according to some embodiments of this application.

[0033] Figure 11 This is a flowchart illustrating an exemplary method for dynamically weighted fusion correction of liquid level data according to some embodiments of this application.

[0034] Figure 12 This is a connection diagram of an exemplary electronic device according to some embodiments of this application. Detailed Implementation

[0035] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided to make this application more complete and comprehensive, and to fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of this application.

[0036] Currently, liquefied natural gas (LNG) is usually transported using dedicated LNG carriers, which generally employ differential pressure, float, capacitive, and radar level gauges for level monitoring.

[0037] Differential pressure level gauges, based on the principle of static pressure, calculate the liquid level by measuring the pressure difference between the bottom and top of the LNG storage tank. They are simple in structure, low in cost, and easy to maintain. However, they are significantly affected by changes in LNG density (temperature and composition), changes in tank pressure, condensation / vaporization of the pressure tapping pipe, and surface fluctuations and dynamic pressure changes caused by ship swaying. Specifically, LNG density fluctuates with temperature and composition, and density errors directly lead to deviations in liquid level calculations. Condensation / vaporization of the pressure tapping pipe can easily cause measurement lag, drift, or even blockage and failure. Ship swaying causes instability in the liquid surface, resulting in abnormal instantaneous dynamic pressure differences and misjudgment of the liquid level.

[0038] Servo / float level gauges use a motor to control the movement of a small ball or float up and down, measuring its equilibrium point when it floats on the liquid surface. They use the principle of buoyancy to sense the height of the float. However, under the long-term shaking and alternating hot and cold conditions at sea, they are prone to problems such as jamming and zero drift. The float needs to move with the liquid surface, and it will frequently impact the support when it shakes, making it unsuitable for environments with violent shaking.

[0039] Capacitive level gauges can change the capacitance between probes by using liquid as a medium, and calculate the liquid level based on the capacitance change. They can also indirectly measure the change in dielectric constant, helping to determine the gas-liquid interface and changes in the medium (such as density). However, they are also affected by liquid surface fluctuations caused by ship swaying, medium adhering to the wall, electrode icing / contamination, and small changes in the dielectric constant of LNG. Calibration is complex and requires frequent adjustments in dynamic environments. Specifically, ship swaying causes liquid to adhere to the probe, leading to misjudgment due to electrode adhering; electrode icing / contamination affects the measurement capacitance, causing long-term drift; and small changes in the dielectric constant of LNG require high signal discrimination capability and have a low signal-to-noise ratio.

[0040] Radar level gauges determine the level by emitting high-frequency electromagnetic waves (usually K-band or W-band) to the liquid surface and receiving the reflected wave signals, and calculating the reflection time. They are highly accurate and unaffected by density. However, the upper layer of LNG storage tanks is filled with low-temperature vapor, and the change in refractive index affects the propagation of radar waves. Furthermore, the refractive interface between the high-temperature layer and the low-temperature layer is prone to generating false echoes. Especially under violent shaking, the repeated reflection of liquid droplets in the gas phase space can cause measurement errors. In low-temperature environments, the antenna is prone to frost and ice formation, leading to signal attenuation or misjudgment.

[0041] Therefore, for reference Figure 1 As shown, Figure 1 The diagram illustrates the module connections of a gas-liquid interface identification and ship sloshing level correction system according to some embodiments of this application. To address measurement problems in liquefied natural gas (LNG) shipping, this application designs a gas-liquid interface identification and ship sloshing level correction system 1, including a sensor assembly 10 and a control unit 11.

[0042] Specifically, the sensor assembly 10 includes a liquid level sensor 101, an image acquisition unit 102, and an IMU inertial measurement unit 103. The liquid level sensor 101 is used to acquire raw differential pressure signal data, capacitance signal data, and radar signal data of the target container. The image acquisition unit 102 is used to acquire image data inside the target container. The IMU inertial measurement unit 103 is used to acquire three-axis attitude angle and acceleration data of the target container.

[0043] The liquid level sensor 101 includes a differential pressure level gauge, a capacitive level gauge, and a radar level gauge. The differential pressure level gauge is used to collect the raw differential pressure signal data of the liquid level in the target container, the capacitive level gauge is used to collect the raw capacitance signal data of the liquid level in the target container, and the radar level gauge is used to collect the raw radar signal data of the liquid level in the target container. The image acquisition unit 102 includes an industrial camera and / or an infrared thermal imager. The industrial camera can acquire high-definition image data inside the target container, and the infrared thermal imager can acquire infrared image data inside the target container. The IMU inertial measurement unit 103 includes at least a three-axis accelerometer, a three-axis gyroscope, and a three-axis magnetometer. The three-axis accelerometer is used to measure linear acceleration, reflecting the movement trend in each direction; the three-axis gyroscope measures angular velocity, acquiring rotation and attitude changes; the three-axis magnetometer is used to provide orientation reference and assist in calibrating gyroscope offset and drift. Optionally, the IMU inertial measurement unit 103 can also be equipped with a temperature sensor to compensate for temperature drift and improve measurement accuracy.

[0044] Specifically, the control unit 11 is connected to the sensor assembly 10. The control unit 11 includes: an image processing module 111, used to extract edge information and grayscale texture features contained in real-time acquired image data and classify the liquid-gas interface state using a trained lightweight convolutional neural network model, and generate an acquisition strategy based on the liquid-gas interface state classification result; a data acquisition module 112, used to acquire image data, and also used to acquire real-time raw liquid level signals according to the acquisition strategy and synchronously acquire data from the IMU inertial measurement unit 103; a stabilization reconstruction module 113, used to process the raw liquid level signal using a preset decomposition method, generate multi-modal components, and construct a liquid surface disturbance prediction model based on the IMU inertial measurement unit 103 data, thereby identifying the principal component mode of disturbance and filtering out the mode components related to the disturbance, and reconstructing a stable liquid level signal; and a liquid level correction module 114, used to model the filtered disturbance mode components as disturbance residual sequences and construct a residual time series prediction model, predict the liquid level disturbance trend and realize dynamic correction of the liquid level, and output dynamically corrected liquid level data.

[0045] In some embodiments of this application, reference is made to Figure 2 As shown, Figure 2The diagram illustrates a flow chart of a gas-liquid interface identification and ship sloshing level correction method according to some embodiments of this application. This application also designs a gas-liquid interface identification and ship sloshing level correction method, comprising the following steps:

[0046] S1: Extract edge information and grayscale texture features from real-time acquired image data and use a trained lightweight convolutional neural network model to classify the liquid-gas interface state. Generate an acquisition strategy based on the liquid-gas interface state classification results.

[0047] Specifically, refer to Figure 3 and Figure 4 As shown, Figure 3 The following is a flowchart illustrating a method for generating acquisition strategies according to some embodiments of this application. Figure 4 This diagram illustrates the predicted liquid-gas interface height and liquid-gas state classification vector output by a lightweight convolutional neural network recognition model according to some embodiments of this application. When generating the acquisition strategy in S1, the method includes:

[0048] S11: An edge detection algorithm is used to obtain the edge map of the image data and the gray-level co-occurrence matrix is ​​used to extract the texture features of the image data. The texture features include at least contrast, energy, homogeneity and entropy features.

[0049] Among them, the Sobel or Canny edge detection algorithm is used to obtain the edge map of the image data:

[0050] E(x,y,t) = Sobel(I(x,y,t)), or E(x,y,t) = Canny(I(x,y,t)), where x and y are pixel coordinates, t is the image data acquisition time, and E(x,y,t) is the edge map. The Sobel algorithm uses the gradient of gray-level differences in the image to detect edges, while the Canny algorithm is a multi-stage edge detection algorithm that includes noise reduction, gradient calculation, non-maximum suppression, and double thresholding.

[0051] The gray-level co-occurrence matrix (GLCM) is a statistical tool describing the gray-level relationships between pixels, reflecting the spatial structure distribution of image texture. By calculating the GLCM of the original image data, texture feature indicators including contrast, energy, homogeneity, and entropy can be calculated. Contrast reflects the drasticness of gray-level changes, energy reflects the repetition of image texture, homogeneity measures whether the gray-level distribution of the image is concentrated (higher the closer to the diagonal), and entropy reflects the complexity or uncertainty of the image (higher values ​​represent more complex texture). The specific process of extracting texture features from image data using the GLCM is as follows: Convert the image data to grayscale, set the number of gray levels (e.g., 256 levels) and relative positions, iterate through each pair of adjacent pixels in the grayscale image data, count their gray levels, and fill them into matrix P(i,j). Normalize the matrix so that all element values ​​represent co-occurrence probabilities; (i,j)∈[0,G-1], where G is the number of gray levels. Therefore:

[0052] The process of extracting contrast features is as follows: A larger difference indicates a larger value, and higher contrast occurs when there are drastic changes in texture (such as at the edges).

[0053] The process of extracting energy features is as follows: The higher the energy value, the more uniform the image, the more regular the texture, and the higher the energy in flat areas.

[0054] The process of extracting homogeneous features is as follows: When the gray values ​​of neighboring pixels are close (i≈j), the score is larger, reflecting the smoothness of the image.

[0055] The process of extracting entropy features is as follows: Where ψ is a very small number (e.g., 1e-10), to avoid log(0); the more complex the image and the more random the grayscale distribution, the greater the entropy.

[0056] S12: Input the edge map and texture features into the trained MobileNet or EfficientNet-Lite lightweight convolutional neural network recognition model and output the predicted liquid-gas interface height and liquid-gas state classification vector.

[0057] The MobileNet or EfficientNet-Lite lightweight convolutional neural network recognition model is selected by technicians from existing lightweight convolutional neural network recognition models and adaptively trained according to actual needs. The trained lightweight convolutional neural network recognition model is then deployed at the required locations. It then uses its receiving edge map and texture features to output the vertical position of the liquid surface in the image and the classification of the liquid-gas state of the current image, such as stable liquid surface, presence of bubbles / foam, violent shaking, or severe interference from droplet splashing.

[0058] S13: Dynamically switch the weight source signal based on the liquid-gas state classification vector results:

[0059] Where w imu For IMU channel weights, w liq Here, W represents the weights for the 101 channels of the level sensor, W is the weight mapping matrix, and b is the bias term; a corresponding acquisition strategy is generated based on the weight source signals.

[0060] s t =[f t ,w imu ,w liq ,F pre ], where f t F is the sampling frequency. pre The filtering strategy is selected based on the disturbance level; at the same time, the gas-liquid interface status label is output, which includes at least the following: stable liquid surface, presence of bubbles or foam, violent shaking, and severe splashing interference.

[0061] In some examples of this application, see reference Figure 5 As shown, Figure 5 A flowchart illustrating a filtering strategy selection method according to some embodiments of this application is shown. In S13, when selecting a filtering strategy based on the disturbance level, the method includes:

[0062] S131: Input image data within the time window and use a timing encoder to perform timing encoding on the image data to extract timing perturbation features.

[0063] S132: Decode the temporal disturbance characteristics to generate vertical disturbance indices, horizontal disturbance indices, and local disturbance indices.

[0064] The vertical disturbance index is as follows: Where L top (y,t) represents the height of the liquid level edge in the y-th row of the image at time t. σ is the stable mean of the corresponding position in historical images. v This is the normalized scaling factor.

[0065] The horizontal disturbance index is: Where θ t The slope angle of the liquid surface in the current frame. For reference average angle, σ h This is the scaling factor.

[0066] The local disturbance index is: Among them, R i Let σ represent the i-th local perturbation region in the image (e.g., a bubble spot). Entropy is the entropy feature used to reflect the perturbation complexity. o This is the normalization factor.

[0067] S133: Based on the vertical perturbation index, horizontal perturbation index and local perturbation index, construct the perturbation three-dimensional vector: U(t)=[Z(t),h(t),O(t)], and introduce the perturbation level label C(t)={0,,1,2,3,4}, and then map the perturbation three-dimensional vector to the perturbation level through the classifier D: C(t)=D(U(t)).

[0068] The disturbance levels are as follows:

[0069] Disturbance level describe feature 0 Static stability (stable liquid surface) All perturbation terms < threshold 1 Slight disturbance (microwave or gentle tilt) Z(t) and H(t) are close to the threshold. 2 Moderate disturbance (significant tilt or bubble interference) H(t) and O(t) increase 3 Strong disturbance (violent fluctuations, large-scale liquid overflow) Z(t), H(t), and O(t) exceed the threshold

[0070] S134: Dynamically select a filtering strategy based on the disturbance level, wherein the filtering strategy includes at least one of mean filtering, Kalman filtering, and wavelet denoising.

[0071] By combining vertical disturbance index, horizontal disturbance index, and local disturbance index with a disturbance level classifier and dynamic filtering strategy selection, adaptive control of liquid level measurement error can be achieved.

[0072] For example, the data collection strategy is shown in the table below:

[0073]

[0074] By adopting the above technical solution, multi-dimensional texture features extracted from image edge detection and gray-level co-occurrence matrix are integrated. A lightweight convolutional neural network model is used to accurately identify the height and state of the liquid-gas interface, and to classify disturbances such as liquid surface stability, bubbles, foam, and splashing. Furthermore, based on the state classification results, the trust weights of the IMU and the liquid level sensing channel are adaptively adjusted through softmax mapping, and a dynamic acquisition strategy including sampling frequency and filtering strategy is generated. A time-series encoder is introduced to extract image disturbance evolution features, construct a three-dimensional disturbance vector and map the disturbance level to achieve level adjustment of the filtering strategy.

[0075] S2: Acquire real-time raw liquid level signals according to the acquisition strategy and simultaneously acquire data from the IMU inertial measurement unit 103.

[0076] Specifically, refer to Figure 6 As shown, Figure 6 A flowchart illustrating a method for acquiring real-time data according to some embodiments of this application is shown. In S2, when acquiring real-time data according to an acquisition strategy, the method includes:

[0077] S21: Based on the corresponding liquid level sampling frequency and filtering strategy of the acquisition strategy, acquire real-time raw liquid level differential pressure signal data, capacitance signal data and radar signal data.

[0078] S22: Based on the IMU sampling frequency and filtering strategy corresponding to the acquisition strategy, acquire the real-time three-axis attitude angle and acceleration data of the IMU inertial measurement unit 103.

[0079] S23: Acquire real-time image data from image acquisition unit 102 according to the visual sampling frequency and filtering strategy corresponding to the acquisition strategy.

[0080] By adopting the above technical solution, based on differentiated sampling and filtering configuration, the acquisition accuracy and resource consumption can be flexibly adjusted according to the needs of the scenario. While ensuring the dynamic response capability of key disturbances, invalid high-frequency interference is suppressed. This multi-channel, configurable data acquisition mechanism provides a high-quality, time-consistent data foundation for subsequent liquid level fusion estimation, disturbance identification and liquid level correction steps, thereby improving the overall accuracy and stability of liquid level measurement.

[0081] S3: The original liquid level signal is processed by a preset decomposition method to generate multimodal components and a liquid surface disturbance prediction model is constructed based on the data of the IMU inertial measurement unit 103. Then, the main disturbance modal components are identified and the modal components related to the disturbance are filtered out to reconstruct a stable liquid level signal.

[0082] Specifically, refer to Figure 7 As shown, Figure 7 A flowchart illustrating a method for reconstructing a stable liquid level signal according to some embodiments of this application is shown. When reconstructing the stable liquid level signal in S3, the method includes:

[0083] S31: The original liquid level signal is decomposed into several modal components using empirical mode decomposition or variational mode decomposition.

[0084] Where u k L(t) represents the k-th modal component, K represents the total number of modes obtained from the decomposition, and L(t) represents the original liquid level signal, including the original differential pressure, capacitance, and radar signal data.

[0085] The original liquid level signals in this application include the original differential pressure signal acquired in real time by the differential pressure level gauge, the capacitance signal acquired in real time by the capacitive level gauge, and the radar signal acquired in real time by the radar level gauge.

[0086] In empirical mode decomposition, the nonlinear, non-stationary signal L(t) is decomposed into several modal components with intrinsic frequency characteristics: Empirical Mode Decomposition (EMD) is an adaptive data-driven method suitable for processing noisy raw liquid level signals.

[0087] In variational mode decomposition, the signal is considered to consist of several band-limited modes, and L(t) is decomposed into several modal components through variational optimization: Each modal component uk (t) is a band-limited signal characterized by different center frequencies. Optimal decoupling between modes is achieved by minimizing the total modal bandwidth.

[0088] By selectively preserving and reconstructing modal components, interference information can be suppressed and the true liquid level change trend can be extracted, thereby enhancing the system's adaptability to swaying disturbances.

[0089] S32: For each modal component u k (t), calculate the cross-correlation strength between it and the acceleration signal:

[0090] Where R k Let a be the average cross-correlation between the k-th mode and the z-axis acceleration. z (t) represents the vertical acceleration, and T is the integration time window. If |R k If the value is greater than the interference discrimination threshold, the corresponding modal component is considered to be a perturbation principal component.

[0091] Here, a perturbation discrimination threshold δ is set. If a certain modal component satisfies |R k The value δ indicates that this mode is highly correlated with vertical acceleration and belongs to the component dominated by sway disturbance.

[0092] S33: Establish a prediction model for liquid surface disturbance based on acceleration:

[0093] in For the predicted disturbance signal,

[0094] a i (t)∈{a x (t),a y (t),a z (t)} represents the triaxial acceleration of the IMU inertial measurement unit 103, β i For regression weights, τ i The lag time for each acceleration channel reflects the dynamic response.

[0095] When a ship moves on the sea surface, its attitude changes will cause fluctuations in the liquid level signal measured by the liquid level sensor 101. These fluctuations are not changes in the actual liquid level height, but disturbance components caused by the ship's acceleration. By learning the mapping relationship between the acceleration signal and the liquid level disturbance, a regression model can be established to predict the disturbance value. Then, by subtracting the predicted disturbance from the original liquid level signal, a relatively stable liquid level trend signal can be obtained.

[0096] S34: Remove the modal components identified as disturbance-related and reconstruct the stable liquid level signal:

[0097] Where I non-disturb ={1,2,…,K}\I disturb I disturb The set of modal components that are identified as disturbances.

[0098] The reconstructed stable liquid level signal is the liquid level estimate after removing swaying disturbances, which is more stable than the original signal.

[0099] By adopting the above technical solution, the influence of factors such as swaying, tilting, and vibration on liquid level measurement can be significantly reduced in a strongly disturbed environment, improving the accuracy and stability of liquid level estimation, and possessing good adaptive capabilities. It is particularly suitable for liquid level monitoring applications in complex working conditions such as ships.

[0100] S4: The filtered disturbance mode components are modeled as disturbance residual sequences and residual time series prediction models are constructed to predict the liquid level disturbance trend and realize the dynamic correction of the liquid level, and output the dynamically corrected liquid level data.

[0101] Specifically, refer to Figure 8 As shown, Figure 8 A flowchart illustrating a method for dynamically correcting liquid levels according to some embodiments of this application is shown. In step S4, when predicting liquid level disturbance trends and implementing dynamic liquid level correction, the method includes:

[0102] S41: Extract the disturbance residual from the original liquid level signal and the stable liquid level signal:

[0103] r(t) = L raw (t)-L stable r(t) is the disturbance residual signal, which represents the influence of sloshing disturbance on liquid level. r(t) ≈ disturbance component + measurement error.

[0104] Among them, the extraction of disturbance residuals is mainly used to quantify the disturbance effect in the liquid level signal caused by non-real liquid level change factors such as sloshing and vibration.

[0105] S42: Based on the time dependence of the perturbation residual signal, construct a residual time series prediction model to predict the perturbation trend at the next time step: in For the prediction of the residual at the next time step, n is the length of the input sequence of the residual time series prediction model, and M is the residual time series prediction model, including at least one of LSTM, GRU, 1D-CNN, Transformer, and ARIMA models.

[0106] Among them, by learning the temporal evolution law of the disturbance residual r(t), the disturbance trend at the next moment is predicted, which is used for future liquid level disturbance prediction and early correction, and enhances the adaptability to swaying or fluctuating environments, improving the stability and accuracy of multi-sensor liquid level measurement; LSTM long short-term memory network model, which is suitable for capturing long-term dependent nonlinear disturbance features; GRU gated recurrent unit, which has fewer parameters and faster training, is suitable for edge deployment; 1D-CNN one-dimensional convolutional network, which is suitable for extracting local temporal features in disturbance signals; Transformer multi-head attention mechanism, which can consider long and short-term dependencies at the same time, is suitable for complex disturbances; ARIMA model is suitable for linear disturbance trend modeling and has strong parameter interpretability.

[0107] By fitting the time evolution law of disturbance, we can achieve forward-looking prediction of disturbance trend and provide dynamic compensation support for liquid level correction.

[0108] S43: After predicting the disturbance trend, correct the liquid level data based on the predicted values:

[0109] Where L corrected (t+1) represents the corrected liquid level data, taking into account both the current stable trend and future disturbance trends; L stable (t+1) represents the stable liquid level trend.

[0110] This process involves incorporating predictable disturbance trends back into the stable trend, thereby more accurately simulating the actual liquid level reading at the next moment. Thus, this correction process comprehensively considers both stable liquid level change trends and future disturbance trends, enabling more precise liquid level data estimation even under disturbances such as surface sloshing.

[0111] By adopting the above technical solution, it is possible to extract the disturbance residual from the original liquid level signal and the stable liquid level signal, and to construct a residual time series prediction model based on its time dependence. This effectively enables the prediction of the disturbance trend at the next moment. It also enables the final liquid level estimate to retain the long-term stable trend while having the ability to make forward-looking corrections to short-term disturbances. In the case of strong disturbances or measurement delays, the data can still remain stable and continuous, thus improving the accuracy of liquid level monitoring.

[0112] In some examples of this application, in complex environments (such as foam, water splashes, and spot occlusion), visual errors often cause offsets. To improve the accuracy of liquid level estimation, spatiotemporal information of the image and deformable convolutional perception capabilities are introduced to compensate for image perturbations and combine stable liquid level and perturbation predictions for final liquid level correction. Therefore, [reference to...] Figure 9 As shown, Figure 9 A flowchart illustrating a method for correcting liquid level data according to some embodiments of this application is shown. The specific method for correcting liquid level data includes:

[0113] S431: Extract spatiotemporal dynamic embedding features based on real-time acquired image data.

[0114] Specifically, a three-dimensional convolutional network (3DCNN) or an image time series Transformer model is used to extract the spatiotemporal dynamic embedding features of the image data, that is, to extract the liquid level region features of each frame of the image data as the input of the deformable convolutional network in S432.

[0115] S432: Introducing a deformable convolutional network to enhance the model's ability to perceive perturbations and perform dynamic offset recognition of edge regions: ΔL img (t)=V deformCNN (I t-n ), where ΔL img (t) represents the image backtracking disturbance compensation term, used to correct the liquid level error caused by visual interference; I t-n This is the image frame at time tn.

[0116] Specifically, a deformable convolutional network, DeformableConvNet, is introduced to enhance the model's ability to identify and locate irregular perturbations (such as bubbles, foam outlines, and spot occlusions), thereby inferring perturbation errors and compensating for them. The backbone network can be ResNet-18 / ResNet-50+DeformableConvolution (DCNv2) or YOLOv5backbone+deformablefeaturemodule. The training method uses a dataset with real liquid level labels and perturbation image samples (foam, occlusion) and uses regression loss (such as SmoothL1Loss) to train the network to output perturbation errors.

[0117] S433: Combines the image backtracking perturbation compensation term with the stable liquid level trend and perturbation residual prediction value to dynamically correct the liquid level data.

[0118] By adopting the above technical solution, deformable convolution is used to accurately perceive irregular disturbance areas, improve edge recognition and error localization capabilities, thereby enhancing the adaptability to complex disturbance scenarios, extracting dynamic deformation evolution features, realizing three-dimensional disturbance recognition of the liquid surface, and reducing liquid level errors under visual interference through an image-guided residual backoff mechanism.

[0119] In some examples of this application, in complex dynamic environments (such as ship swaying, image occlusion, and liquid level fluctuations), a single channel may exhibit information distortion. By analyzing parameters such as the disturbance level, signal-to-noise ratio, and prediction residual amplitude of each channel, a confidence factor is calculated to achieve multi-source data fusion and improve the accuracy of liquid level estimation. Therefore, referencing... Figure 10 As shown, Figure 10A flowchart illustrating a method for dynamically correcting liquid level data according to some embodiments of this application is shown. The specific method for dynamically correcting liquid level data includes:

[0120] S434: Based on the disturbance level, signal-to-noise ratio, and mean prediction residual of the liquid level sensor 101 channel, IMU channel, and image acquisition channel within a preset time range, construct the liquid level sensing signal confidence factor, IMU confidence factor, and image confidence factor.

[0121] The preset time range is set by technicians using a sliding time window [t-Δt,t] to analyze the stability of each channel. The time window size can be set to 1-3 seconds. The calculation process for the disturbance level of channel 101 of the liquid level sensor is as follows:

[0122] D L =Var(L(t-Δt:t)), where Var is the variance operator used to measure the dispersion of the data. The signal-to-noise ratio is calculated as follows: Power signal The effective power of the liquid level signal is typically the average energy of the liquid level signal. noise The noise power generated during sensor measurement; the calculation process for the disturbance level of channel 103 of the IMU inertial measurement unit is as follows: Where a x (t) is the lateral acceleration, a z (t) represents the longitudinal acceleration; the image edge variation in the image acquisition channel (such as the fluctuation of the liquid surface edge area) can be used as an indicator of the degree of perturbation, and the signal-to-noise ratio (SNR) can be indirectly estimated by image sharpness (such as the Laplacian coefficient of variation). Then, weights are constructed through normalization: where each α i (i = 1, 2, 3), representing the channel reliability score:

[0123] in δ represents the mean of the prediction residuals for channel 101 of the liquid level sensor, where δ is a positive number to prevent the denominator from being zero. This represents the mean of the prediction residuals for the image acquisition channels.

[0124] S435: Dynamically weighted and corrected liquid level data based on the constructed confidence factors:

[0125] Where ∈1, ∈2, and ∈3 are the confidence factors of the liquid level sensing signal, the IMU confidence factor, and the image confidence factor, respectively. fused (t+1) represents the liquid level data after dynamic weighted fusion correction.

[0126] S436: Outputs dynamically weighted fusion-corrected liquid level data.

[0127] By adopting the above technical solution, a multi-channel confidence evaluation mechanism based on disturbance amplitude, signal-to-noise ratio and prediction residual is introduced to realize dynamic weighted fusion of liquid level sensor 101, IMU and image information. Compared with the traditional single source liquid level estimation method, it can improve the stability and accuracy of liquid level measurement in complex disturbance environment and reduce the interference of abnormal fluctuations on the final liquid level result.

[0128] In some examples of this application, when dynamically weighted fusion corrects liquid level data, to improve stability against sudden abnormal disturbances (such as sensor failure, severe ship collision, surge disturbance, etc.) or sensing channel anomalies (such as image blurring, signal loss), liquid level anomaly variation detection is introduced to monitor and statistically identify anomalies in the stable liquid level signal sequence in real time. Therefore, referencing... Figure 11 As shown, Figure 11 A flowchart illustrating a method for dynamically weighted fusion correction of liquid level data according to some embodiments of this application is shown. The method includes:

[0129] S4351: Set the sliding window size n, for example, n = 5~20, and then collect the stable liquid level trend L from time point tn-1 to t-1. stable (ti), and then construct a monitoring index for the liquid level variation rate within the sliding window based on the stable liquid level trend:

[0130] This allows the liquid level variation rate monitoring index to reflect the average rate of change of the liquid level during the sliding period.

[0131] S4352: If the variability rate monitoring index exceeds the preset threshold or any value of the confidence factor is lower than the preset tolerance value, the current state is determined to be abnormal, and the emergency liquid level correction process is initiated. The emergency liquid level correction process includes:

[0132] Short-term compensation can be achieved by reducing the sampling frequency and extending the sliding window stabilization period, temporarily shielding the channel with the lowest confidence and increasing the confidence weight of other channels, or introducing the moving average trend of historical liquid level stabilization sequences.

[0133] The preset threshold can be set based on historical data statistics, such as empirical values ​​or standard deviation.

[0134] The process of reducing the sampling frequency and extending the stabilization period of the sliding window includes at least one of the following: temporarily reducing the liquid level update frequency, for example from 1 Hz to 0.2 Hz, increasing the sliding window length n, improving data smoothness (e.g. from n=10 to n=30), and reducing the interference of short-term fluctuations on the calculation of the variation rate.

[0135] The process of temporarily masking the channel with the lowest confidence and increasing the confidence weight of other channels includes: identifying the channel with the lowest current confidence (e.g., the lowest image confidence factor ∈ 3), temporarily masking that channel (with the corresponding weight set to 0), and then renormalizing and adjusting the remaining two channels proportionally.

[0136] The process of introducing the moving average trend of historical stable liquid level series for short-term compensation includes: extracting the average trend of liquid level in a previous stable period, and then using the moving average to replace unreliable data for short-term compensation correction during abnormal periods.

[0137] By adopting the above technical solutions, the system's stability against sudden disturbances and extreme anomalies can be improved, and level errors caused by decreased confidence can be avoided. Furthermore, the continuity of level monitoring can be ensured through redundant channel coordination and historical trend compensation.

[0138] In some embodiments, reference Figure 12 As shown, Figure 12 A connection diagram of an electronic device used to implement embodiments of this application is shown. The electronic device 3 includes a memory 301 and a processor 302. The memory 301 stores a computer program that can run on the processor 302. When the processor 302 executes the computer program, it implements the methods described in the above embodiments. The number of memories 301 and processors 302 can be one or more.

[0139] The electronic device 3 also includes:

[0140] Communication interface 303 is used to communicate with external devices and perform data exchange and transmission.

[0141] If the memory 301, processor 302, and communication interface 303 are implemented independently, then the memory 301, processor 302, and communication interface 303 can be interconnected through a bus and complete communication between them.

[0142] This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 12 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0143] Optionally, in a specific implementation, if the memory 301, processor 302, and communication interface 303 are integrated on a single chip, then the memory 301, processor 302, and communication interface 303 can communicate with each other through an internal interface.

[0144] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor 302, implements the method provided in this application.

[0145] This application also provides a chip, which includes a processor 302 for calling and running instructions stored in a memory 301, causing a communication device equipped with the chip to execute the method provided in this application.

[0146] This application also provides a chip, including: an input interface, an output interface, a processor 302 and a memory 301. The input interface, the output interface, the processor 302 and the memory 301 are connected through an internal connection path. The processor 302 is used to execute code in the memory 301. When the code is executed, the processor 302 is used to execute the method provided in the application embodiment.

[0147] It should be understood that the processor 302 mentioned above can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that processor 302 can be a processor supporting the Advanced Reduced Instruction Set Computing (ARM) architecture.

[0148] Furthermore, the aforementioned memory 301 may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory 301 may be volatile memory or non-volatile memory, or may include both. The non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic Random Access Memory (SDRAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDRSDRAM), Enhanced Synchronous Dynamic Random Access Memory (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DRRAM).

[0149] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the flow or function according to this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.

[0150] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for gas-liquid interface identification and ship sloshing level correction, characterized in that, The method includes: The edge information and grayscale texture features contained in the real-time acquired image data are extracted and the liquid-gas interface state is classified using a trained lightweight convolutional neural network model. The acquisition strategy is generated based on the liquid-gas interface state classification results. Real-time raw liquid level signals are acquired according to the acquisition strategy, and IMU inertial measurement unit data is acquired simultaneously. The original liquid level signal is processed by a preset decomposition method to generate multimodal components. A liquid surface disturbance prediction model is constructed based on the IMU inertial measurement unit data. Then, the main disturbance modal components are identified and the disturbance-related modal components are filtered out to reconstruct a stable liquid level signal. The filtered perturbation mode components are modeled as perturbation residual sequences and residual time series prediction models are constructed to predict liquid level disturbance trends and realize dynamic correction of liquid level, outputting dynamically corrected liquid level data.

2. The liquid level correction method according to claim 1, characterized in that, When generating the acquisition strategy, the method includes: An edge detection algorithm is used to obtain the edge map of the image data, and the gray-level co-occurrence matrix is ​​used to extract the texture features of the image data. The texture features include at least contrast, energy, homogeneity and entropy features. The edge map and texture features are input into the trained MobileNet or EfficientNet-Lite lightweight convolutional neural network recognition model, and the predicted liquid-gas interface height and liquid-gas state classification vector are output. Dynamically switch the weight source signal based on the liquid-gas state classification vector results: Where w imu For IMU channel weights, w liq Here, W represents the channel weights of the level sensor, W is the weight mapping matrix, and b is the bias term; a corresponding acquisition strategy is generated based on the weight source signal: s t =[f t ,w imu ,w liq ,F pre ], where f t F is the sampling frequency. pre The filtering strategy is selected based on the disturbance level; at the same time, the gas-liquid interface status label is output, which includes at least the following: stable liquid surface, presence of bubbles or foam, violent shaking, and severe splashing interference.

3. The liquid level correction method according to claim 2, characterized in that, When selecting a filtering strategy based on the disturbance level, the method includes: Input image data within the time window and use a time encoder to perform time-series encoding on the image data to extract time-series perturbation features; Decode the temporal disturbance characteristics to generate vertical disturbance indices, horizontal disturbance indices, and local disturbance indices; Based on the vertical disturbance index, horizontal disturbance index, and local disturbance index, a three-dimensional disturbance vector is constructed and a disturbance level label is introduced to map the three-dimensional disturbance vector to the disturbance level. The filtering strategy is dynamically selected based on the disturbance level. The filtering strategy includes at least one of mean filtering, Kalman filtering, and wavelet denoising.

4. The liquid level correction method according to claim 2 or 3, characterized in that, When collecting real-time data according to the collection strategy, the method includes: Based on the corresponding liquid level sampling frequency and filtering strategy of the acquisition strategy, real-time raw liquid level differential pressure signal data, capacitance signal data and radar signal data are acquired; Based on the corresponding IMU sampling frequency and filtering strategy, the real-time three-axis attitude angle and acceleration data of the IMU inertial measurement unit are acquired.

5. The liquid level correction method according to claim 1 or 2, characterized in that, When reconstructing a stable liquid level signal, the method includes: The original liquid level signal is decomposed into several modal components using empirical mode decomposition or variational mode decomposition: Where u k (t) represents the k-th modal component, K represents the total number of modes obtained from the decomposition, and L(t) represents the original liquid level signal, including the original differential pressure, capacitance, and radar signal data. For each modal component u k (t), calculate the cross-correlation strength between it and the acceleration signal: Where R k Let a be the average cross-correlation between the k-th mode and the z-axis acceleration. z (t) represents the vertical acceleration, and T is the integration time window. If |R k If the value is greater than the interference discrimination threshold, the corresponding modal component is considered to be the principal perturbation component. Establish an acceleration-driven liquid surface disturbance prediction model: in For the predicted disturbance signal, a i (t)∈{a x (t),a y (t),a z (t)} represents the triaxial acceleration of the IMU inertial measurement unit, β i For regression weights, τ i The lag time for each acceleration channel reflects the dynamic response; The modal components identified as disturbance-related will be removed and the stable liquid level signal will be reconstructed. Where I non-disturb ={1,2,…,K}\I disturb I disturb The set of modal components that are identified as disturbances.

6. The liquid level correction method according to claim 5, characterized in that, When predicting liquid level disturbance trends and implementing dynamic liquid level correction, the method includes: Extract the disturbance residual from the original liquid level signal and the stable liquid level signal: r(t) = L raw (t)-L stable (t), where r(t) is the disturbance residual signal, representing the effect of sloshing disturbance on liquid level; Based on the time dependence of the perturbation residual signal, a residual time series prediction model is constructed to predict the perturbation trend at the next time step: in For the prediction of the residual at the next time step, n is the length of the input sequence of the residual time series prediction model, and M is the residual time series prediction model, including at least one of LSTM, GRU, 1D-CNN, Transformer, and ARIMA models; After predicting the disturbance trend, the liquid level data is corrected based on the predicted values: Where L corrected (t+1) represents the corrected liquid level data, taking into account both the current stable trend and future disturbance trends; L stable (t+1) represents the stable liquid level trend.

7. The liquid level correction method according to claim 6, characterized in that, When correcting the liquid level data, the method further includes: Based on real-time acquired image data, extract spatiotemporal dynamic embedding features; A deformable convolutional network is introduced to enhance the model's ability to perceive perturbations and perform dynamic offset recognition of edge regions: ΔL img (t)=V deformCNN (I t-n ), where ΔL img (t) represents the image backtracking perturbation compensation term, I t-n The image frame at time tn; The image backtracking perturbation compensation term is combined with the stable liquid level trend and the predicted perturbation residual value to dynamically correct the liquid level data:

8. The liquid level correction method according to claim 7, characterized in that, When dynamically correcting liquid level data, the method further includes: Based on the disturbance level, signal-to-noise ratio, and mean prediction residual of the liquid level sensor channel, IMU channel, and image acquisition channel within a preset time range, a confidence factor for the liquid level sensing signal, an IMU confidence factor, and an image confidence factor are constructed. The liquid level data is dynamically weighted and corrected based on the constructed confidence factors: Where ∈1, ∈2, and ∈3 are the confidence factors of the liquid level sensing signal, the IMU confidence factor, and the image confidence factor, respectively. fused (t+1) represents the liquid level data after dynamic weighted fusion correction; Output the dynamically weighted fusion corrected liquid level data.

9. The liquid level correction method according to claim 8, characterized in that, When dynamically weighted and correcting liquid level data, the method includes: Based on the stable liquid level trend, a liquid level variation rate monitoring index is constructed within the sliding window: Where n is the size of the sliding window; If the variation rate monitoring index exceeds the preset threshold or any value of the confidence factor is lower than the preset tolerance value, the current state is determined to be abnormal, and the emergency liquid level correction process is initiated. The emergency liquid level correction process includes: reducing the sampling frequency and extending the sliding window stabilization period, temporarily shielding the channel with the lowest confidence and increasing the confidence weight of other channels, or introducing the moving average trend of historical liquid level stabilization sequences for short-term compensation.

10. A gas-liquid interface identification and ship sloshing level correction system using the liquid level correction method according to any one of claims 1-9, characterized in that, include: The sensor assembly includes a liquid level sensor, an image acquisition unit, and an IMU inertial measurement unit. The liquid level sensor is used to acquire raw differential pressure signal data, capacitance signal data, and radar signal data of the target container. The image acquisition unit is used to acquire image data inside the target container. The IMU inertial measurement unit is used to acquire three-axis attitude angle and acceleration data of the target container. A control unit, connected to the sensor assembly, the control unit comprising: The image processing module is used to extract edge information and grayscale texture features contained in real-time acquired image data and use a trained lightweight convolutional neural network model to classify the liquid-gas interface state, and generate an acquisition strategy based on the liquid-gas interface state classification results. The data acquisition module is used to acquire image data, and also to acquire real-time raw liquid level signals according to the acquisition strategy and simultaneously acquire IMU inertial measurement unit data. The stable reconstruction module is used to process the original liquid level signal using a preset decomposition method, generate multi-modal components, construct a liquid surface disturbance prediction model based on the IMU inertial measurement unit data, identify the main disturbance modal components, filter out the disturbance-related modal components, and reconstruct a stable liquid level signal. The liquid level correction module is used to model the filtered disturbance modal components as disturbance residual sequences and construct residual time series prediction models to predict liquid level disturbance trends and realize dynamic correction of liquid level, and output dynamically corrected liquid level data.

Images