Method for Measuring Spatial Angle of Dredger Rake Pipe

Abstract

The invention relates to the field of ship engineering technology, and specifically discloses a method for measuring the spatial angle of a dredger rake pipe. The method collects motion data of a hull and a rake pipe in real time, uses median filtering to remove high-frequency noise, extracts features and constructs a comprehensive feature vector, uses a fuzzy inference system to separate the nonlinear influence of hull sway and rake pipe posture, and corrects the posture estimation result in combination with real-time error feedback. The estimation result is dynamically optimized through Bayesian estimation and particle filtering algorithms, and the system deviation is corrected, thereby improving the measurement accuracy. The system also evaluates the overall measurement accuracy in combination with a machine learning model, automatically adjusts measurement parameters and processes, and improves the system adaptability and robustness. For inaccurate measurement results, the system can analyze the causes and re-measure the spatial angle to ensure long-term stable operation.

Description

Technical Field

[0001] The present invention relates to the technical field of ship engineering, and particularly to a method for measuring the spatial angle of a dredger rake pipe. Background Art

[0002] As an important equipment for water area dredging, port construction and river regulation, dredgers are widely used in complex underwater operations. The rake pipe system of a dredger is one of its core components, responsible for excavating and transporting sediment. To ensure the accuracy and efficiency of operations, it is necessary to accurately measure and real-time monitor the spatial angle of the rake pipe. Accurate measurement of the spatial angle of the rake pipe not only helps to optimize the operation angle, improve the dredging effect, but also reduces the impact on the water environment and avoids unnecessary resource waste. With the development of modern computing technology, the angle measurement method based on sensor data has gradually become the mainstream, and with the continuous progress of signal processing, data fusion and artificial intelligence technologies, the measurement accuracy and real-time performance of the spatial angle of the dredger rake pipe have been significantly improved.

[0003] The existing technology has the following deficiencies:

[0004] Due to the dynamic changes of the ship itself, such as the hull swaying and wave influence, there may be non-linear errors in attitude calculation, resulting in inaccurate angle calculation. The rake pipe may generate complex non-linear motions due to sediment resistance factors during operation, which makes it difficult for sensors to accurately track its spatial angle. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for measuring the spatial angle of a dredger rake pipe to solve the problems in the above background.

[0006] The purpose of the present invention can be achieved by the following technical solutions:

[0007] A method for measuring the spatial angle of a dredger rake pipe includes the following steps:

[0008] S1: Real-time collect the motion data of the hull and the rake pipe, including acceleration, angular velocity and attitude information;

[0009] S2: According to the motion data of the hull and the rake pipe, separate the non-linear influence and optimize the attitude estimation;

[0010] S3: According to the optimized attitude estimation, through real-time error feedback calculation, evaluate the difference between the estimation result and the actual measurement value;

[0011] S4: Based on the evaluation result, use the error feedback information to real-time correct the estimation result in the filtering process;

[0012] S5: Evaluate the overall accuracy of the dredger's dragline spatial angle measurement system according to the real-time correction results. For inaccurate identification results, analyze the reasons for inaccurate identification and re-measure the spatial angle.

[0013] As a further solution of the present invention: Obtain the motion data of the hull and the dragline, and use median filtering to remove high-frequency noise;

[0014] Extract features from the acceleration, angular velocity, and attitude information of the hull and the dragline, and construct a comprehensive feature vector.

[0015] As a further solution of the present invention: The construction process of the comprehensive feature vector is as follows:

[0016] Obtain the motion data of the hull and the dragline, and extract time-domain features from the acceleration, angular velocity, and attitude data, including mean, standard deviation, maximum value, minimum value, peak value, and variance;

[0017] Use the fast Fourier transform to perform frequency-domain analysis on the acceleration and angular velocity data, and extract spectral features such as frequency distribution, spectral density, and frequency components;

[0018] Combine time-frequency analysis techniques to extract time-frequency domain features and capture the time-varying characteristics in the data;

[0019] Merge the extracted time-domain, frequency-domain, and time-frequency domain features to form a preliminary feature vector;

[0020] Use the gradient boosting tree algorithm to train the preliminary feature vector, automatically select the features most relevant to the target prediction; during the training process of the gradient boosting tree, automatically generate new feature combinations and cross features to improve the feature expression ability; evaluate the influence of each feature on the final target, remove irrelevant features, retain the most qualified features, and generate the final comprehensive feature vector from the optimized feature combination.

[0021] As a further solution of the present invention: Separating the non-linear influence and optimizing the attitude estimation specifically includes:

[0022] Obtain the comprehensive feature vector, use singular spectrum decomposition to transform the comprehensive feature vector of the hull and the dragline into input features processed by the fuzzy inference system; and formulate fuzzy rules to describe the mutual relationship between the hull sway and the dragline attitude; adopt an adaptive method to adjust the membership function and rule weights of the fuzzy rules based on real-time data, and dynamically optimize the performance of the inference system;

[0023] Input the collected motion data into the fuzzy inference system, and based on the output of the fuzzy inference system, separate the non-linear influence between the hull sway and the dragline attitude;

[0024] Calculate the influence of hull sway and the estimated value of the rake pipe attitude through the membership degree value of fuzzy inference to achieve the dynamic separation of non-linear influence;

[0025] According to the real-time feedback data, dynamically update the fuzzy rules and membership functions in the fuzzy inference system. Through the output of the fuzzy inference system, combined with the real-time data and the optimized model, provide the accurate attitude estimation results of the hull and the rake pipe.

[0026] As a further solution of the present invention: The difference between the evaluation estimation result and the actual measurement value specifically includes:

[0027] According to the optimized attitude estimation result, compare and analyze the actual measurement value with the estimated value, and calculate the estimation deviation value. The calculation process is as follows:

[0028] Calculate the difference between the estimated value and the actual measurement value to obtain the estimation deviation. Obtain the posterior distribution by combining the prior distribution and the likelihood function, and update the deviation estimation value. The calculation expression is:

[0029] ;

[0030] In the formula, represents the actual measurement value, represents the estimation deviation, represents the given actual measurement value After that, the update of the estimation deviation ; represents the probability of the actual measurement value under the given estimation deviation ; represents the probability distribution of the estimation deviation, represents the normalization constant to ensure that the total probability of the posterior distribution is 1;

[0031] The estimation deviation follows a normal distribution, and the prior distribution is:

[0032] ;

[0033] In the formula, represents the prior variance of the estimation deviation, represents the covariance matrix of the estimated value, represents the transpose operation, represents the dimension of the data;

[0034] Substitute the prior distribution and the likelihood function into the Bayesian formula to obtain the posterior distribution. The calculation expression is:

[0035] ;

[0036] Wherein, represents an estimated value;

[0037] By maximizing the posterior distribution, the maximum a posteriori estimation of the estimation deviation is obtained, and the calculation expression is:

[0038] ;

[0039] Wherein, represents the maximum a posteriori estimation, represents the maximum value function;

[0040] By taking the derivative of the posterior distribution and setting it to 0, the estimation deviation value is obtained, and the calculation expression is:

[0041] ;

[0042] Wherein, represents the estimation deviation value, represents the precision matrix of the actual measurement data, represents the precision matrix of the prior estimated value.

[0043] As a further solution of the present invention: the estimated result in the filtering process is corrected in real time by using the error feedback information, which specifically includes:

[0044] Obtain the estimation deviation value, and according to the estimation deviation value, combine with the particle filter algorithm to calculate the correction coefficient, and adjust the estimation result at the current moment according to the correction coefficient to obtain the corrected estimation state.

[0045] As a further solution of the present invention: the process of obtaining the correction coefficient is:

[0046] Obtain the estimation deviation value, and calculate the correction coefficient according to the estimation deviation value, and the calculation expression is:

[0047] ;

[0048] Wherein, represents the correction coefficient, represents the estimation deviation value, represents the transpose operation, represents the th particle during the particle operation, represents the total number of particles, represents the time step, represents the covariance matrix of the state estimation, particle weight.

[0049] As a further solution of the present invention: the overall accuracy of the dredger rake pipe space angle measurement system is evaluated, which specifically includes:

[0050] According to the real-time correction result, an estimated deviation value and a correction coefficient during the measurement of the spatial angle of the dredger's drag pipe are used to construct a combined comprehensive feature vector, which is used as the input of the machine learning model. Combining historical data, the machine learning model is trained. According to the training result, an overall accuracy evaluation result of the system is output. The machine learning model is a deep learning model, and the deep learning model includes an input layer: used to receive the combined comprehensive feature vector, a hidden layer: composed of multiple fully connected neural networks, used to extract non-linear features, and an output layer: outputting the overall accuracy evaluation result of the system. The deep learning model is trained by supervised learning using historical data, and the accuracy label in the historical data is the overall accuracy score of the system.

[0051] As a further solution of the present invention: according to the overall accuracy evaluation result of the system, the quality identification result of the system is divided into an accurate identification result and an inaccurate identification result, specifically including:

[0052] Obtain the accuracy score of the dredger's drag pipe spatial angle measurement system, and judge whether the accuracy score is greater than or equal to a preset threshold. If so, it is divided into an accurate identification result; if not, it is divided into an inaccurate identification result.

[0053] As a further solution of the present invention: for the inaccurate identification result, analyze the reason for the inaccuracy and re-measure the spatial angle, specifically including:

[0054] By comparing the similarity between the inaccurate identification result and the historical measurement data, if the similarity is lower than the preset threshold, it is determined that the current measurement value is inconsistent with the historical data characteristics; according to the reason for the inaccurate identification, the measurement parameters and processes are dynamically adjusted, including: re-calibrating the sensor, adjusting the parameters of the sampling frequency; re-measuring the spatial angle of the drag pipe, obtaining a new measurement value, and correcting the measurement value based on the correction coefficient, calculating a new corrected estimated value, reconstructing the comprehensive feature vector, combining the corrected estimated value and the measurement value with the historical data, and updating the overall accuracy evaluation result of the system.

[0055] The beneficial effects of the present invention:

[0056] (1) The present invention optimizes the measurement process of the spatial angle of the dredger's rake pipe by combining a variety of advanced technical means. In terms of real-time optimizing attitude estimation, the system collects the acceleration, angular velocity, and attitude information of the hull and the rake pipe, and uses median filtering to remove high-frequency noise to ensure the smoothness and accuracy of the input data. In the error feedback correction process, the system uses Bayesian estimation and particle filtering algorithms to dynamically adjust the estimation results and correct the estimation deviation in real time, thereby eliminating the interference of external environmental changes (such as hull swaying, waves) on the measurement results. Through continuous error feedback and adaptive correction, the system can accurately separate the non-linear effects and ensure that the measurement results are highly consistent with the actual state. In addition, by combining a fuzzy inference system to model the complex relationship between the hull and the rake pipe attitude, and dynamically updating through the optimized model, the robustness and accuracy of the angle measurement are further improved, enabling this method to provide stable and reliable measurement results in complex and changeable environments.

[0057] (2) The present invention enables the dredger's rake pipe spatial angle measurement system to have a high degree of adaptability by integrating the mechanism of real-time correction and machine learning model feedback. The system first analyzes the real-time correction results and continuously updates the estimation model to ensure the accuracy and stability of the measurement results. When inaccurate recognition results occur during the measurement process, the system analyzes the historical data through a deep learning model, automatically identifies the error sources, and adjusts the measurement parameters and processes. For example, the system can recalibrate the sensors, adjust the sampling frequency, or change the filtering strategy to cope with the impact of environmental changes. Through continuous optimization and adaptive adjustment, the system can maintain the stability of the measurement accuracy in different working environments, operating conditions, and complex dynamic scenarios. In addition, the system can also dynamically evaluate its overall accuracy, timely feedback and correct inaccurate results, thereby ensuring long-term stable operation, avoiding the performance decline or accuracy degradation problems that are prone to occur in traditional methods under complex conditions, and enhancing the robustness and reliability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The present invention will be further described below in conjunction with the drawings.

[0059] Figure 1 It is the specific step flow block diagram of the method for measuring the spatial angle of the dredger's rake pipe of the present invention;

[0060] Figure 2 It is the calculation flow block diagram of the estimated deviation value in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0062] Please refer to Figure 1 as shown, the present invention is a method for measuring the spatial angle of the dredger's rake pipe, including the following steps:

[0063] S1: Real-time collect the motion data of the hull and the rake pipe, including acceleration, angular velocity, and attitude information;

[0064] S2: Separate the non-linear influence according to the motion data of the hull and the rake pipe, and optimize the attitude estimation;

[0065] S3: According to the optimized attitude estimation, calculate through real-time error feedback to evaluate the difference between the estimation result and the actual measurement value;

[0066] S4: Based on the evaluation result, use the error feedback information to perform real-time correction on the estimation result in the filtering process;

[0067] S5: According to the real-time correction result, evaluate the overall accuracy of the dredger's rake pipe spatial angle measurement system, analyze the reasons for inaccurate identification results for inaccurate identification, and re-measure the spatial angle.

[0068] In S1, real-time collect the motion data of the hull and the rake pipe, including acceleration, angular velocity, and attitude information, specifically including:

[0069] Install a variety of high-precision inertial measurement units (IMUs) on the hull and the rake pipe of the dredger, including accelerometers, gyroscopes, and attitude sensors. The IMUs of the hull are arranged near the central center of gravity to ensure that the collected data can accurately reflect the overall motion state; the IMUs of the rake pipe are installed at key moving parts, such as joint nodes and ends, to facilitate capturing local motion characteristics. Each sensor is in close contact with the measurement surface through an industrial-grade fixing device to avoid data deviation caused by loose installation.

[0070] The sensors collect the three-dimensional acceleration, three-dimensional angular velocity, and attitude (such as Euler angles) information of the hull and the rake pipe. The designed data collection frequency is set to, for example, 100Hz to ensure capturing the high-frequency details of the dynamic motion. The collected raw data is transmitted to the central processing unit (CPU) in real time through a high-speed communication protocol (such as wireless network) for unified processing, and the data streams of each sensor are synchronized using timestamps to ensure the alignment of the motion information of the hull and the rake pipe.

[0071] The raw data received in real time is preprocessed, including noise filtering, zero bias correction, and drift compensation. The acceleration and angular velocity data are fused through a Kalman filter to eliminate the influence of random noise and obtain more stable attitude information. At the same time, according to the known sensor installation positions and reference coordinate systems, the collected data is uniformly transformed into the global coordinate system to provide accurate input data for subsequent spatial angle measurement and correction.

[0072] In S2, according to the hull and drag pipe motion data, the non-linear effects are separated and the attitude estimation is optimized, specifically including:

[0073] Obtain the motion data of the hull and drag pipe, and use median filtering to remove high-frequency noise;

[0074] Extract the features of the acceleration, angular velocity, and attitude information of the hull and drag pipe and construct a comprehensive feature vector;

[0075] The construction process of the comprehensive feature vector is as follows:

[0076] First, the motion data of the hull and drag pipe are collected in real time through IMU, accelerometer, and gyroscope sensors. The collected data includes acceleration (Ax, Ay, Az), angular velocity (ωx, ωy, ωz), and attitude angles (pitch angle, roll angle, yaw angle).

[0077] Perform median filtering on the collected raw data to remove high-frequency noise. Median filtering can effectively filter out instantaneous spike noise, maintain the smoothness of the signal, and avoid the interference of high-frequency noise on subsequent feature extraction.

[0078] Feature extraction includes:

[0079] Time-domain features: Extract basic statistical features from acceleration, angular velocity, and attitude data, such as mean, standard deviation, maximum value, minimum value, peak value, and variance. By calculating these features, the basic laws and fluctuation characteristics of the motion can be captured from the raw data.

[0080] Frequency-domain features: Use the fast Fourier transform (FFT) to perform frequency-domain analysis on acceleration and angular velocity data, and extract spectral features, such as frequency distribution, spectral density, and main frequency components. Frequency-domain features can reveal the motion patterns of the hull and drag pipe at different frequencies and help identify the laws of non-linear motion.

[0081] Time-domain and frequency-domain combined features: Through time-frequency analysis techniques (such as short-time Fourier transform, wavelet transform), extract the combined features of the time domain and frequency domain to capture the time-varying characteristics of the hull and drag pipe under dynamic changes.

[0082] Constructing the comprehensive feature vector includes:

[0083] Merge the time-domain features, frequency-domain features, and time-frequency domain features extracted from acceleration, angular velocity, and attitude data to form a preliminary feature set. Each feature vector will include:

[0084] Acceleration features (such as mean, standard deviation, maximum value)

[0085] Angular velocity features (such as frequency components, variance)

[0086] Attitude features (such as statistics of pitch angle, roll angle, yaw angle)

[0087] Concatenate these multi-dimensional features into a large feature vector, which contains all important dynamic information;

[0088] Use gradient boosting trees for feature selection to evaluate the influence of each feature on the prediction target. Automatically screen out the most informative features through the gradient boosting tree algorithm, remove irrelevant features, and improve the expressive ability of features.

[0089] During the training process of gradient boosting trees, consider the cross effects of different features. Gradient boosting trees adaptively process the feature crosses through tree structures to generate new composite features. For example, combine different axis components of acceleration with angular velocity to create new features to enhance the ability to capture complex dynamic patterns.

[0090] The specific steps for separating non-linear effects are as follows:

[0091] Real-time collect the motion data of the hull and the rake pipe, including acceleration (Ax, Ay, Az), angular velocity (ωx, ωy, ωz), and attitude angle (pitch angle, roll angle, yaw angle) information;

[0092] Preprocess the collected raw data, use median filtering to remove high-frequency noise, and perform data normalization to ensure the unified scale of the input data;

[0093] Use the singular spectrum decomposition method in "nonlinear dynamics analysis" to identify potential non-linear dynamic features from acceleration, angular velocity, and attitude data;

[0094] Decompose the signal through the SSD method to identify the main periodic components and mutation points, and understand the behavior patterns of the hull and the rake pipe in a non-linear environment;

[0095] Map the acceleration, angular velocity, and attitude data of the hull and the rake pipe to the dynamic non-linear feature space, and extract the dynamic features in the time domain and frequency domain. These features will be used for analysis in the subsequent fuzzy inference system.

[0096] Design an adaptive fuzzy inference system (FIS) to process non - linear dynamic characteristics in the form of a fuzzy rule base. The inputs to the fuzzy system are acceleration, angular velocity, attitude angle, and features extracted from non - linear dynamics analysis.

[0097] Based on the non - linear relationships observed in the data, formulate appropriate fuzzy rules to describe the interaction between the hull and the rake pipe. These include: "When the hull acceleration is large and the angular velocity is small, the attitude change of the rake pipe is slow."

[0098] Use an adaptive fuzzy inference method to automatically adjust the membership functions and rule weights of the fuzzy rules. These adjustments are based on real - time data feedback to optimize the system's response ability to non - linear effects.

[0099] Utilize the fuzzy inference system to automatically identify the non - linear effects between hull sway and rake pipe attitude and perform dynamic separation. Based on real - time data input, the system calculates the output of the fuzzy rules, gives the membership degree values for each state, and thus estimates the non - linear dynamics of the hull and the rake pipe respectively.

[0100] Through the output of fuzzy inference, obtain the influence value of hull sway and the estimated value of rake pipe attitude to separate the non - linear effects. This process does not rely on traditional non - linear models but dynamically adapts to changing motion states through the rules of the fuzzy inference system.

[0101] According to the data collected in real - time, the system automatically updates the fuzzy rules and membership functions. Through a real - time feedback mechanism, the fuzzy inference system can adaptively adjust the inference process according to changes in the environment (such as wave changes, hull load changes), avoiding error accumulation caused by improper initial settings.

[0102] Use real - time control algorithms to optimize the performance of the fuzzy system, gradually improving the system's recognition and separation accuracy of the non - linear relationship between hull sway and rake pipe attitude.

[0103] The output of the fuzzy inference system will be used as the input for the final attitude estimation. Combining real - time feedback information, give the accurate attitude angles of the hull and the rake pipe. The final attitude estimation result is output through a data fusion method and used for the dynamic control and positioning of the hull and the rake pipe.

[0104] Please refer to Figure 2 As shown, in S3, according to the optimized attitude estimation, through real - time error feedback calculation, evaluate the difference between the estimation result and the actual measurement value, specifically including:

[0105] According to the optimized attitude estimation result, compare and analyze the actual measurement value with the estimated value, calculate the estimation deviation value, and the calculation process is:

[0106] Calculate the difference between the estimated value and the actual measured value to obtain the estimation deviation. Then, update the deviation estimation value by obtaining the posterior distribution through combining the prior distribution and the likelihood function. The calculation expression is as follows:

[0107] ;

[0108] In the formula, represents the actual measured value, represents the estimation deviation, represents the updated estimation deviation given the actual measured value . represents the probability of the actual measured value given the estimation deviation . represents the probability distribution of the estimation deviation, represents the normalization constant, ensuring that the total probability of the posterior distribution is 1;

[0109] The estimation deviation follows a normal distribution, and the prior distribution is:

[0110] ;

[0111] In the formula, represents the prior variance of the estimation deviation, represents the covariance matrix of the estimated value, represents the transpose operation, represents the dimension of the data;

[0112] Substitute the prior distribution and the likelihood function into the Bayesian formula to obtain the posterior distribution. The calculation expression is as follows:

[0113] ;

[0114] In the formula, represents the estimated value;

[0115] Maximize the posterior distribution to obtain the maximum a posteriori (MAP) estimate of the estimation deviation. The calculation expression is as follows:

[0116] ;

[0117] In the formula, represents the maximum a posteriori estimate, represents the maximum value function;

[0118] Derive the posterior distribution and set it to 0 to obtain the estimation deviation value. The calculation expression is as follows:

[0119] ;

[0120] In the formula, represents the estimated deviation value, represents the precision matrix of the actual measurement data, represents the precision matrix of the prior estimated value.

[0121] It should be noted that: In this embodiment, based on Bayesian theory, the deviation of the optimized attitude estimation result is corrected. By combining the comparison and analysis of the actual measurement value and the estimated value, the estimated deviation value is calculated. First, the initial deviation is obtained through difference calculation, and the posterior distribution is constructed by combining the prior distribution and the likelihood function. The prior distribution describes the initial belief of the estimated deviation. Usually, it is assumed to follow a normal distribution, and the variance is calculated based on the covariance matrix of the estimated value; the likelihood function represents the probability distribution of the actual measurement value under the given estimated deviation. By substituting the prior distribution and the likelihood function into the Bayesian formula, the posterior distribution of the estimated deviation is obtained, and the maximum a posteriori estimate value is obtained by maximizing the posterior distribution. By taking the derivative of the posterior distribution and setting it to zero, the accurate estimated deviation value is obtained, where the measurement data and the prior estimate are combined using the definition of the precision matrix to ensure that the corrected deviation value is more in line with the actual situation, thereby improving the accuracy and robustness of the estimation.

[0122] In S4, based on the evaluation result, the estimated result in the filtering process is corrected in real time using the error feedback information, specifically including:

[0123] Obtain the estimated deviation value. According to the estimated deviation value and in combination with the particle filter algorithm, calculate the correction coefficient, and adjust the estimated result at the current moment according to the correction coefficient to obtain the corrected estimated state;

[0124] The process of obtaining the correction coefficient is as follows:

[0125] Obtain the estimated deviation value, calculate the correction coefficient according to the estimated deviation value, and the calculation expression is:

[0126] ;

[0127] In the formula, represents the correction coefficient, represents the estimated deviation value, represents the transpose operation, represents the th particle during the particle operation, represents the total number of particles, represents the time step, represents the covariance matrix of the state estimation, particle weight.

[0128] The correction process is: Adjust the current estimated state by combining the correction coefficient and the estimated deviation value, and calculate the corrected estimated state. The calculation expression is:

[0129] ;

[0130] In the formula, represents the estimated state before correction, represents the estimated state after correction, represents the correction coefficient, represents the estimated deviation value.

[0131] It should be noted that: through the evaluation results and error feedback information, the estimated results in the filtering process are corrected in real time to improve the estimation accuracy. First, by comparing the current estimated value with the actual measured value, the estimated deviation value is obtained. Then, using the particle filter algorithm, the correction coefficient is calculated according to the deviation value. The correction coefficient synthesizes the covariance matrix and weight information of the particle state, and expresses the influence degree of the current deviation on the correction of the estimated state. Finally, combining the correction coefficient and the deviation value, the estimated state at the current moment is adjusted to obtain the estimated state after correction. Through such a dynamic correction mechanism, it is ensured that the difference between the estimated result and the actual measured value in the filtering process can be adjusted in real time, thereby improving the accuracy and robustness of the system.

[0132] In S5, according to the real-time correction result, the accuracy of the overall dredger dragline pipe spatial angle measurement system is evaluated. For inaccurate recognition results, the reasons for inaccurate recognition are analyzed and the spatial angle measurement is performed again, specifically including:

[0133] According to the real-time correction result, the estimated deviation value and the correction coefficient in the process of dredger dragline pipe spatial angle measurement are constructed into a combined comprehensive feature vector, which is used as the input of the machine learning model. Combining historical data, the machine learning model is trained. According to the training result, the accuracy evaluation result of the overall system is output. The machine learning model is a deep learning model. The deep learning model includes an input layer: used to receive the combined comprehensive feature vector, a hidden layer: composed of multiple fully connected neural networks, used to extract non-linear features, and an output layer: output the accuracy evaluation result of the overall system. The deep learning model is supervised and learned using historical data, and the accuracy label in the historical data is the accuracy score of the overall system.

[0134] Obtain the accuracy score of the dredger dragline pipe spatial angle measurement system, and judge whether the accuracy score is greater than or equal to the preset threshold. If so, it is classified as an accurate recognition result; if not, it is classified as an inaccurate recognition result.

[0135] By comparing the similarity between the inaccurate recognition result and the historical measurement data, if the similarity is lower than the preset threshold, it is determined that the current measurement value is inconsistent with the characteristics of the historical data; according to the reasons for inaccurate recognition, the measurement parameters and processes are dynamically adjusted, including: recalibrating the sensor, adjusting the parameters of the sampling frequency; re-measuring the spatial angle of the rake pipe to obtain a new measurement value, and correcting the measurement value based on the correction coefficient, calculating a new corrected estimated value, reconstructing the comprehensive feature vector, combining the corrected estimated value and the measurement value with the historical data, and updating the overall accuracy evaluation result of the system.

[0136] The working principle of the present invention: By collecting the motion data of the hull and the rake pipe in real time, and adopting a variety of data processing technologies, such as median filtering, feature extraction, fuzzy inference, and particle filtering, to optimize the estimation of the rake pipe attitude. This method gradually improves the measurement accuracy of the system through dynamic feedback and error correction. In particular, the accuracy of the system is evaluated by a machine learning model, and automatic adjustment is made according to the evaluation result. For inaccurate recognition results, the system can analyze and locate the error cause, re-measure the spatial angle, ensure the accuracy and stability of the measurement result, and adapt to complex working environments and dynamic changes.

[0137] The above formulas are all dimensionless and take their numerical calculations. The formula is obtained by collecting a large amount of data for software simulation to obtain a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0138] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire or wireless (such as infrared, wireless, microwave) means. The computer-readable storage medium can be any available medium that the computer can access or a server, data center data storage device containing one or more available medium sets. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0139] It should be understood that the term "and / or" in this text is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. Additionally, the character " / " in this text generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, and the specific meaning can be understood by referring to the context before and after.

[0140] It should be understood that in various embodiments of this application, the magnitude of the sequence numbers of the above processes does not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of this application.

[0141] The above has described in detail one embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as being used to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. Method for measuring the spatial angle of the dredging pipe, characterized in that It includes the following steps: S1: Real-time collect the motion data of the hull and the dredging pipe, including acceleration, angular velocity, and attitude information; S2: According to the motion data of the hull and the dredging pipe, separate the non-linear influence and optimize the attitude estimation, specifically including: Obtain the comprehensive feature vector, use singular spectrum decomposition to transform the comprehensive feature vector of the hull and the dredging pipe into the input features processed by the fuzzy inference system; and formulate fuzzy rules to describe the mutual relationship between the hull sway and the attitude of the dredging pipe; adopt an adaptive method to adjust the membership function and rule weight of the fuzzy rules based on real-time data, and dynamically optimize the performance of the inference system; Input the collected motion data into the fuzzy inference system, and based on the output of the fuzzy inference system, separate the non-linear influence between the hull sway and the attitude of the dredging pipe; Calculate the influence of the hull sway and the estimated value of the attitude of the dredging pipe through the membership values of fuzzy inference, and realize the dynamic separation of non-linear influence; According to the real-time feedback data, dynamically update the fuzzy rules and membership function in the fuzzy inference system. Through the output of the fuzzy inference system, combined with real-time data and the optimized model, provide accurate attitude estimation results of the hull and the dredging pipe; S3: According to the optimized attitude estimation, calculate through real-time error feedback to evaluate the difference between the estimation result and the actual measurement value; S4: Based on the evaluation result, use the error feedback information to perform real-time correction on the estimation result in the filtering process, specifically including: Obtain the estimation deviation value, according to the estimation deviation value, combined with the particle filter algorithm, calculate the correction coefficient, and adjust the estimation result at the current moment according to the correction coefficient to obtain the corrected estimation state; S5: According to the real-time correction result, evaluate the overall accuracy of the dredging pipe spatial angle measurement system of the dredger, analyze the reasons for inaccurate recognition results for inaccurate recognition, and re-measure the spatial angle.

2. The method for measuring the spatial angle of the dredging pipe of a dredger according to claim 1, wherein Obtain the motion data of the hull and the dredging pipe, and use median filtering to remove high-frequency noise; Extract the features of the acceleration, angular velocity, and attitude information of the hull and the dredging pipe and construct a comprehensive feature vector.

3. The method for measuring the spatial angle of the dredger rake pipe according to claim 2, characterized in that The construction process of the comprehensive feature vector is as follows: Obtain the motion data of the hull and the dredging pipe, and extract the time-domain features from the acceleration, angular velocity, and attitude data, including mean, standard deviation, maximum value, minimum value, peak value, and variance; Use the fast Fourier transform to perform frequency-domain analysis on the acceleration and angular velocity data, and extract spectral features such as frequency distribution, spectral density, and frequency components; Combine time-frequency analysis techniques to extract time-frequency domain features and capture the time-varying characteristics in the data; Merge the extracted time-domain, frequency-domain, and time-frequency domain features to form a preliminary feature vector; Use the gradient boosting tree algorithm to train the preliminary feature vector and automatically select the features most relevant to the target prediction; During the training process of the gradient boosting tree, automatically generate new feature combinations and cross features to enhance the feature expression ability; evaluate the influence of each feature on the final target, remove irrelevant features, retain the most qualified features, and generate the final comprehensive feature vector from the optimized feature combination.

4. The method for measuring the spatial angle of the dredger rake pipe according to claim 1, characterized in that, The evaluation of the difference between the estimation result and the actual measurement value specifically includes: According to the optimized attitude estimation results, the actual measured values are compared with the estimated values for comparative analysis, and the estimation deviation values are calculated. The calculation process is as follows: The difference between the estimated value and the actual measured value is calculated to obtain the estimation deviation. The posterior distribution is obtained by combining the prior distribution and the likelihood function to update the deviation estimation value. The calculation expression is: ； In the formula, represents the actual measured value, represents the estimated deviation, represents the given actual measured value After that, the estimated deviation is updated, represents the case of a given estimated deviation Under this condition, the probability of the actual measured value is, represents the probability distribution of the estimated deviation, represents the normalization constant to ensure that the total probability of the posterior distribution is 1; Estimation deviation Following a normal distribution, the prior distribution is as follows: ； In the formula, represents the prior variance of the estimation deviation, represents the covariance matrix of the estimated value, represents the transpose operation, represents the dimension of the data; The prior distribution and the likelihood function are substituted into the Bayesian formula to obtain the posterior distribution. The calculation expression is: ； In the formula, represents the estimated value; By maximizing the posterior distribution, the maximum a posteriori estimate of the estimation deviation is obtained. The calculation expression is: ； In the formula, represents the maximum a posteriori estimation, represents the maximum value function; By taking the derivative of the posterior distribution and setting it to 0, the estimation deviation value is obtained. The calculation expression is: ； In the formula, represents the estimated deviation value, represents the precision matrix of the actual measurement data, represents the precision matrix of the prior estimated value.

5. The method for measuring the spatial angle of the dredger rake pipe according to claim 1, wherein The process of obtaining the correction coefficient is as follows: The estimation deviation value is obtained, and the correction coefficient is calculated according to the estimation deviation value. The calculation expression is: ； In the formula, represents the correction coefficient, represents the estimated deviation value, represents the transpose operation, represents the th particle during the particle operation, represents the total number of particles, represents the time step, represents the covariance matrix of the state estimate, particle weight.

6. The method for measuring the spatial angle of the dredger rake pipe according to claim 1, characterized in that The overall accuracy of the dredger rake pipe spatial angle measurement system is evaluated, specifically including: According to the real-time correction results, the estimation deviation value and the correction coefficient during the dredger rake pipe spatial angle measurement are constructed into a combined comprehensive feature vector as the input of the machine learning model. Combining historical data, the machine learning model is trained. According to the training results, the overall accuracy evaluation result of the system is output. The machine learning model is a deep learning model. The deep learning model includes an input layer: used to receive the combined comprehensive feature vector, a hidden layer: composed of multiple fully connected neural networks, used to extract non-linear features, and an output layer: outputting the overall accuracy evaluation result of the system. The deep learning model is supervised and learned using historical data. The accuracy label in the historical data is the overall accuracy score of the system.

7. The method for measuring the spatial angle of the dredger rake pipe according to claim 6, characterized in that, According to the overall accuracy evaluation result of the system, the quality recognition result of the system is divided into an accurate recognition result and an inaccurate recognition result, specifically including: The accuracy score of the dredger rake pipe spatial angle measurement system is obtained, and it is judged whether the accuracy score is greater than or equal to the preset threshold. If so, it is divided into an accurate recognition result; if not, it is divided into an inaccurate recognition result.

8. The method for measuring the spatial angle of the dredger rake pipe according to claim 1, characterized in that For the inaccurate recognition result, analyze the reasons for the inaccuracy and re-measure the spatial angle, specifically including: By comparing the similarity between the inaccurate recognition result and the historical measurement data, if the similarity is lower than the preset threshold, it is determined that the current measured value is inconsistent with the historical data characteristics. According to the reasons for the inaccurate recognition, the measurement parameters and processes are dynamically adjusted, including: recalibrating the sensor, adjusting the parameters of the sampling frequency; re-measuring the spatial angle of the rake pipe to obtain new measured values, and correcting the measured values based on the correction coefficient, calculating new corrected estimation values, reconstructing the comprehensive feature vector, combining the corrected estimation values and measured values with the historical data, and updating the overall accuracy evaluation result of the system.

Images