Hydraulic excitation early warning-based control method and system for steel pile trolley of cutter suction dredger

Abstract

The present application relates to the technical field of steel pile trolley control of cutter suction dredger, and discloses a steel pile trolley control method and system of cutter suction dredger based on hydraulic excitation early warning, which comprises the following steps: collecting the influence degree of multiple parameters on system stability, calculating pressure fluctuation factors and other state characteristic sets; constructing a dynamic pressure balance model, inputting pressure time sequence queue, sea state level and other data to output dynamic pressure adjustment value; constructing a cooperative control correction model, inputting steel pile posture data to output cooperative correction coefficient; combining the adjustment value and correction coefficient to calculate the final control output, and generating a hydraulic excitation control instruction set. The system comprises a multi-source sensor module, a state characteristic calculation module, a dynamic pressure balance module and the like, and realizes multi-dimensional data fusion and intelligent control. The present application improves the stability, control accuracy and environmental adaptability of the steel pile trolley system, and is suitable for the steel pile trolley control scene of cutter suction dredger.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of steel pile trolley control of a cutter suction dredger, in particular to a steel pile trolley control method and system based on hydraulic excitation early warning for a cutter suction dredger. BACKGROUND

[0002] As the core equipment in the fields of water conservancy projects and channel dredging, the stability and control accuracy of the steel pile trolley system of a cutter suction dredger directly affect the construction efficiency and safety. The steel pile trolley system mainly realizes key operations such as positioning, plugging and moving of the steel pile through the coordinated operation of the hydraulic execution unit, the steel pile clamp and the walking mechanism. However, in actual operation, the system faces complex working condition challenges, resulting in significant limitations of existing control methods.

[0003] From the perspective of the characteristics of the hydraulic system, the traditional control method is insufficient in dynamic response to hydraulic pressure fluctuations. The cylinder pressure of the hydraulic execution unit is easily affected by factors such as load mutation and hydraulic oil temperature change in different operation stages (such as steel pile plugging and trolley walking), resulting in pressure over-limit or instability. For example, when the hydraulic oil temperature rises, the decrease in oil viscosity may cause thermal attenuation effect, causing the actual pressure to deviate from the preset threshold, thereby affecting the stability of the clamping force of the steel pile clamp and the displacement accuracy of the walking mechanism. At the same time, the problem of electromagnetic valve response delay cannot be ignored, and the traditional control model does not fully consider the influence of electromagnetic valve opening and closing delay time on system synchronization, which may cause action lag or impact when multiple execution mechanisms work together, reducing the operation efficiency.

[0004] In terms of mechanical motion control, the real-time monitoring and correction ability of the steel pile posture is another shortcoming of the traditional method. The steel pile is prone to tilt or deviation in complex sea conditions (such as wave and current action), and the existing control model cannot effectively integrate real-time posture data such as steel pile tilt angle and clamp clamping force distribution, so it cannot adjust the output of each control node in time to compensate for the posture deviation. In addition, the displacement deviation accumulation problem of the walking mechanism has not been effectively solved, and long-term operation may cause displacement accuracy to decrease due to mechanical resonance or environmental vibration, affecting the positioning accuracy of the dredger.

[0005] The complexity of environmental interference factors further increases the control difficulty. Changes in sea state level (such as wave height and period) will produce different degrees of vibration excitation to the trolley system, and the traditional control method lacks analysis of the spectral characteristics of environmental vibration, cannot identify the influence of frequency spectrum main peak frequency shift on system stability, and is difficult to maintain normal operation of the system in strong vibration working conditions. At the same time, the motion coupling relationship between multiple execution mechanisms (such as the linkage of hydraulic execution unit and walking mechanism) has not been fully modeled, resulting in the inability of the coordinated control strategy to accurately coordinate the actions of each mechanism, which may easily cause mechanical stress concentration or abnormal wear.

[0006] In the prior art, although some control systems introduce sensor monitoring and closed-loop control, they are mostly single-parameter feedback control, lacking the ability of fusion analysis and dynamic modeling of multi-source data (pressure, displacement, temperature, vibration, etc.). For example, only the pressure sensor feedback is used to adjust the hydraulic output, while the comprehensive influence of electromagnetic valve response delay, hydraulic oil temperature and environmental vibration is ignored, resulting in insufficient robustness of the system under complex working conditions. In addition, the traditional model is mostly based on fixed control parameters, which cannot adapt to the dynamic changes of different equipment models (such as oil cylinders with different rated pressures, clamps with different clamping surface structures) and sea conditions, limiting the universality and adaptive ability of the system. SUMMARY

[0007] The purpose of the present application is to provide a hydraulic excitation early warning based control method and system for steel pile trolley of cutter suction dredger, to solve the problems raised in the background art.

[0008] To achieve the above-mentioned purpose, the present application provides the following technical solution: a hydraulic excitation early warning based control method for steel pile trolley of cutter suction dredger, the method comprising:

[0009] For any one control node of the hydraulic execution unit, steel pile clamp and walking mechanism in the trolley system, the influence degree of oil cylinder pressure value, electromagnetic valve response time, displacement sensor data, hydraulic oil temperature and environmental vibration parameters on system stability is collected respectively, and the pressure fluctuation factor, response delay factor, displacement deviation factor, thermal attenuation factor and mechanical resonance factor are calculated based on the obtained influence degrees to form a state feature set;

[0010] A dynamic pressure equalization model is constructed, for any one control node, the actual pressure data of the node in the previous M time units is arranged in the order of operation to form a pressure time sequence queue in any control period, and the preset pressure threshold, target displacement, hydraulic oil temperature limit and equipment code information of the next operation stage are obtained, and the current sea condition level identifier is also obtained; the pressure time sequence queue, preset pressure threshold, target displacement, hydraulic oil temperature limit, equipment code information, sea condition level identifier and state feature set of the current control period are input into the dynamic pressure equalization model, and the dynamic pressure adjustment value of the node in the next operation stage is output;

[0011] A cooperative control correction model is constructed, for any one control node, real-time steel pile attitude data is obtained in any control period; the inclination angle of the steel pile, the clamp clamping force distribution and the trolley displacement deviation of the current control period are input into the cooperative control correction model, and the cooperative correction coefficient of the node in the next operation stage is output;

[0012] For any one control node, based on the dynamic pressure adjustment value and the cooperative correction coefficient obtained in the current control period, the final control output of the node in the next operation stage is calculated.

[0013] Integrating the final control output quantities of all control nodes to generate the trolley system hydraulic excitation control instruction set.

[0014] Preferably, the influence degree of the collected cylinder pressure value, solenoid valve response time, displacement sensor data, hydraulic oil temperature and environmental vibration parameters on system stability specifically includes:

[0015] For any control node, the actual pressure data of each operation stage of the node in the historical operation cycle is obtained, and the solenoid valve opening and closing delay time, displacement sensor sampling value, hydraulic oil temperature peak value and environmental vibration spectrum data of each operation stage are collected; wherein the sea state level identifier is divided into six categories according to wave height and period, and each category corresponds to a unique code; the equipment code information includes cylinder model identifier and clamp type, the cylinder model identifier is divided into three levels according to the rated pressure, and the clamp type is divided into plane and curved surface according to the clamping surface structure;

[0016] The state sequence information of each operation stage includes the pressure fluctuation amplitude of n consecutive sampling points of the node in the operation stage; the n sampling points of each operation stage are coded in time sequence as 1 to n, and the sampling point code with the highest frequency of pressure overrun in the historical cycle is counted;

[0017] The influence degree of the cylinder pressure value, solenoid valve response time, displacement deviation, hydraulic oil temperature and environmental vibration on the stability of the current control node is calculated respectively, wherein the influence degree of the first four items is obtained through the correlation analysis of historical data and system failure, and the influence degree of environmental vibration is obtained by calculating the offset of the main peak frequency of the spectrum.

[0018] Preferably, the calculation method of the state feature set is: based on the influence degree of the cylinder pressure value, solenoid valve response time, displacement deviation, hydraulic oil temperature and environmental vibration, the pressure fluctuation factor to the mechanical resonance factor is obtained by normalized weighted summation respectively.

[0019] Preferably, the dynamic pressure equalization model is constructed based on a multi-modal perception network, including a data fusion layer, a time sequence coding layer, a feature extraction stacking layer, a cross-modal attention layer, a decision generation layer and an output calibration layer.

[0020] The data fusion layer is used to convert the pressure time sequence queue, the preset pressure threshold, the target displacement amount, the hydraulic oil temperature limit value, the equipment code information, the sea state level identifier and the state feature set into a multi-dimensional feature tensor;

[0021] The time sequence coding layer is used to generate operation sequence coding for each operation stage in the pressure time sequence queue to maintain the continuity of the operation process;

[0022] The feature extraction stack layer includes L parallel feature extraction modules, each of which respectively processes hydraulic parameter features, mechanical motion features and environmental interference features;

[0023] The cross-modal attention layer is used for cross-attention calculation on the state feature set and the multi-dimensional features of the feature extraction output, to generate a dynamic weight distribution matrix;

[0024] The decision generation layer is used for fusing the dynamic weight distribution matrix with the feature extraction result to generate a preliminary control policy vector;

[0025] The output calibration layer is used for mapping the preliminary control policy vector into a dynamic pressure adjustment value.

[0026] Preferably, the training process of the dynamic pressure balancing model comprises:

[0027] A plurality of historical control data sets of operation cycles are collected, each data sample including pressure data of consecutive M+1 operation stages, influence factor data of the M+1 stage and a state feature set; the data set is divided into a training set and a test set;

[0028] The data of the first M stages and the influence factors in the training set are used as input, and the pressure adjustment amount of the M+1 stage is used as target output, and the network parameters are optimized through error back propagation;

[0029] The test set is used to evaluate the model control error, and if the error does not meet the convergence standard, the number of feature extraction modules or the dimension of attention heads is adjusted and retrained.

[0030] Preferably, the collaborative control correction model is constructed based on a graph neural network, including a topological relationship modeling branch and a collaborative optimization branch;

[0031] The topological relationship modeling branch establishes the motion coupling relationship of each actuator of the trolley system through graph structure learning;

[0032] The collaborative optimization branch fuses the motion coupling relationship with the steel pile posture data, and outputs a collaborative correction coefficient after multi-layer perceptron calculation.

[0033] Preferably, the calculation method of the final control output quantity is to weight and fuse the dynamic pressure adjustment value and the collaborative correction coefficient according to a preset proportion, and to perform nonlinear compensation combined with the load characteristics of the current oil cylinder.

[0034] Preferably, the generation method of the hydraulic excitation control instruction set is to perform time domain synchronous calibration on the final control output quantities of all control nodes, and to generate an instruction sequence with timing constraints combined with the device response characteristics.

[0035] Preferably, the model training process further includes an adaptive optimization step:

[0036] According to the distribution characteristics of the test set error, the connection mode of the feature extraction module or the activation function of the attention head is automatically adjusted; if the error presents periodic fluctuations, a residual connection structure is added and the learning rate is reduced; if the error continues to diverge, the network topology is reconstructed and the parameters are reinitialized.

[0037] Preferably, the application also includes a hydraulic excitation early warning-based steel pile trolley control system for a cutter suction dredger, which is used to implement the hydraulic excitation early warning-based steel pile trolley control method for a cutter suction dredger as described above. The system comprises:

[0038] A multi-source sensor module is configured in the hydraulic execution unit, steel pile clamp, and walking mechanism of the trolley system, and is used to collect the cylinder pressure value, electromagnetic valve response time, displacement sensor data, hydraulic oil temperature, and environmental vibration parameters of each control node in real time.

[0039] A state feature calculation module is connected to the multi-source sensor module and is used to calculate the pressure fluctuation factor, response delay factor, displacement deviation factor, thermal attenuation factor, and mechanical resonance factor according to the collected data, and generate a state feature set.

[0040] A time series data storage module is equipped with a circular buffer unit and is used to store the actual pressure data of the previous M time units of each control node in the order of operation, forming a pressure time series queue.

[0041] A sea state recognition module integrates a ship attitude sensor and a wave monitoring unit and is used to analyze the current sea state grade identification in real time.

[0042] A dynamic pressure equalization module is constructed based on a multi-modal neural network, and the input end is connected to the state feature calculation module, time series data storage module, and sea state recognition module. The dynamic pressure equalization module is used to receive the pressure time series queue, preset pressure threshold, target displacement amount, hydraulic oil temperature limit, equipment code information, and sea state grade identification, and calculate and generate a dynamic pressure adjustment value through a cross-modal attention mechanism.

[0043] A collaborative control correction module is equipped with a steel pile attitude monitoring unit and a clamp stress analysis unit, and is used to obtain the real-time steel pile inclination angle, clamp clamping force distribution, and trolley displacement deviation. The collaborative control correction module models the motion coupling relationship through a graph neural network and outputs a collaborative correction coefficient.

[0044] An instruction generation module is connected to the input end of the dynamic pressure equalization module and the collaborative control correction module. The instruction generation module is used to perform nonlinear fusion calculation on the dynamic pressure adjustment value and the collaborative correction coefficient, generate the final control output of each control node, and synchronously generate a set of hydraulic excitation control instructions with time sequence constraints.

[0045] A safety warning module with a historical fault database and an abnormal pattern recognition unit is used to monitor abnormal fluctuations in the state feature set in real time, trigger a hierarchical alarm signal, and feed back to the instruction generation module for control quantity compensation.

[0046] Compared with the prior art, the present application has the following advantages:

[0047] The present application collects multi-dimensional data such as oil cylinder pressure value, solenoid valve response time, displacement sensor data, hydraulic oil temperature and environmental vibration parameters in real time through multi-source sensors, and calculates the influence degree of each parameter on system stability based on historical data correlation analysis and frequency spectrum analysis, to generate a state feature set containing pressure fluctuation factors, response delay factors, etc. This multi-parameter fusion analysis mechanism breaks through the limitations of traditional single parameter control, and can comprehensively capture the comprehensive influence of hydraulic system dynamic characteristics, mechanical motion state and environmental interference, providing rich feature input for precise control. For example, by analyzing the frequency shift of the main peak frequency in the environmental vibration spectrum, the risk of mechanical resonance can be identified in advance, avoiding displacement deviation accumulation or equipment damage caused by vibration.

[0048] The dynamic pressure equalization model is constructed based on a multi-modal perception network, which converts multi-modal data such as pressure time sequence, preset pressure threshold, sea state level identifier, etc. into a multi-dimensional feature tensor through a data fusion layer, a time sequence encoding layer and other multi-layer structures, and generates a dynamic weight distribution matrix using a cross-modal attention mechanism to realize dynamic weight adjustment of hydraulic parameters, mechanical motion characteristics and environmental interference. The model can predict the next stage of dynamic pressure adjustment value based on historical pressure time sequence data, and simultaneously adaptively adjust in combination with sea state level and equipment model (such as oil cylinder rated pressure level, clamp type), effectively compensating for problems such as pressure fluctuation, thermal decay and solenoid valve response delay of the hydraulic system. For example, in high sea state, the model can automatically increase the pressure adjustment value to cope with the load fluctuation caused by wave impact, ensuring the stability of the steel pile clamp clamping force.

[0049] The collaborative control correction model is constructed based on a graph neural network, which establishes the motion coupling relationship of each actuator of the trolley system through a topological relationship modeling branch, and outputs a collaborative correction coefficient through a collaborative optimization branch in combination with real-time steel pile inclination angle, clamp clamping force distribution and other attitude data. This graph structure-based modeling method can accurately describe the linkage relationship between the hydraulic execution unit, the steel pile clamp and the walking mechanism, and real-time correct the control error caused by the inclination of the steel pile or the motion coupling of the mechanism. For example, when the inclination of the steel pile is detected, the model can quickly calculate the collaborative correction coefficient of each control node, adjust the oil cylinder pressure and walking mechanism displacement, realize the dynamic calibration of the steel pile attitude, and avoid the positioning deviation or operation efficiency caused by inclination.

[0050] At the control output level, the dynamic pressure adjustment value and the collaborative correction coefficient are fused by preset proportion weighting, and combined with the nonlinear compensation of the cylinder load characteristics to generate the final control output of each control node. This composite control strategy not only considers the dynamic pressure balance of the hydraulic system, but also realizes the collaborative correction of multiple mechanisms, effectively improving the control accuracy and response speed. At the same time, the output of all control nodes is time domain synchronized calibration to generate a set of hydraulic excitation control commands with time sequence constraints, ensuring the synchronization and coordination of multiple actuator actions, reducing mechanical wear and energy loss caused by action lag or impact.

[0051] The safety warning module has a built-in historical fault database and an abnormal pattern recognition unit. By monitoring the abnormal fluctuations of the state feature set in real time (such as pressure fluctuation factor exceeding limit, mechanical resonance factor mutation), a hierarchical alarm signal is triggered and fed back to the instruction generation module for control quantity compensation. This early warning mechanism can identify potential system failures (such as high hydraulic oil temperature, electromagnetic valve response delay anomaly) in advance, and through dynamic adjustment of control parameters or triggering of protection measures, major failures are avoided, significantly improving the safety and reliability of the system.

[0052] The adaptive optimization mechanism in the model training process (such as automatically adjusting the feature extraction module connection mode according to the test set error distribution, adding residual connection structure, etc.), so that the dynamic pressure balance model can automatically optimize the network structure and parameters according to different working condition data, improve the generalization ability and convergence speed of the model. Combined with sea state level identification (six categories) and equipment code information (cylinder model, clamp type), the system can automatically switch control strategies for different operating environments and equipment configurations, significantly enhancing the versatility and working condition adaptability of the system. BRIEF DESCRIPTION OF DRAWINGS

[0053] Fig. 1 The working principle diagram of the hydraulic excitation warning-based steel pile trolley control method of the cutter suction dredger described in the present application;

[0054] Fig. 2 The principle diagram for influence degree collection and state feature set calculation;

[0055] Fig. 3 The working principle diagram of the dynamic pressure balance model. DETAILED DESCRIPTION

[0056] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0057] Referring to Figs. 1-3 The application relates to a steel pile platform truck control method based on hydraulic excitation early warning of a cutter suction dredger, and the implementation steps are as follows:

[0058] For any one control node of the hydraulic execution unit, the steel pile clamp and the walking mechanism in the platform truck system, the influence degree of the oil cylinder pressure value, the electromagnetic valve response time, the displacement sensor data, the hydraulic oil temperature and the environmental vibration parameters on the system stability is collected respectively. In the specific implementation, the original data of each control node is obtained in real time through a multi-source sensor module, wherein the oil cylinder pressure value is collected by a pressure sensor, the electromagnetic valve response time is calculated by the time difference between the electromagnetic valve opening and closing signal and the system clock, the displacement sensor data is directly read from the output value of the linear displacement sensor, the hydraulic oil temperature is monitored in real time by the temperature sensor buried in the hydraulic pipeline, and the environmental vibration parameters are collected by the vibration acceleration sensor and subjected to frequency spectrum analysis.

[0059] Based on the obtained influence degrees, a pressure fluctuation factor, a response delay factor, a displacement deviation factor, a thermal attenuation factor and a mechanical resonance factor are calculated through normalized weighted summation, and the above factors jointly constitute a state feature set. The normalization processing adopts the Z-score standardization method, and the weighting coefficients are determined through the correlation analysis of historical data and system faults, for example, the weight proportion of the oil cylinder pressure value can be set to 40% according to the frequency proportion of the system faults caused by the oil cylinder pressure value, and the weight proportions of the remaining parameters are determined in the same way.

[0060] A dynamic pressure equalization model based on a multi-modal perception network is constructed. For any one control node, in any control period, the actual pressure data of the node in the previous M time units is arranged in the operation order to form a pressure time sequence queue, and the queue is stored and updated through the circulating cache unit of the time sequence data storage module. Meanwhile, the preset pressure threshold value (set by the system process parameters), the target displacement amount (from the platform truck walking control instruction), the hydraulic oil temperature limit value (determined according to the hydraulic oil type and the working environment) and the equipment code information (including the oil cylinder model identifier and the clamp type, wherein the oil cylinder model identifier is divided into three levels according to the rated pressure, and the clamp type is divided into plane and curved surface according to the clamping surface structure) of the next operation stage are obtained, and the current sea state grade identifier (divided into six categories according to the wave height and period, and each category corresponds to a unique code, such as the sea state of grade 1 corresponding to code 01) is obtained through the sea state identification module.

[0061] The pressure time sequence queue, the preset pressure threshold, the target displacement amount, the hydraulic oil temperature limit value, the equipment code information, the sea state grade identifier and the state feature set are input into a dynamic pressure balance model. Inside the model, multi-source data is converted into a multi-dimensional feature tensor through a data fusion layer, a time sequence coding layer generates operation sequence coding for the pressure time sequence queue, a feature extraction stack layer processes hydraulic parameters, mechanical movement and environmental interference features through L parallel modules respectively, a cross-modal attention layer calculates a dynamic weight distribution matrix, a decision generation layer generates a preliminary control strategy vector after fusion, and finally an output calibration layer maps it to the dynamic pressure adjustment value of the node in the next operation phase.

[0062] A collaborative control correction model based on a graph neural network is constructed. For any control node, in any control cycle, the real-time steel pile inclination angle is obtained through a steel pile attitude monitoring unit, the clamp clamping force distribution data is obtained through a clamp stress analysis unit, and the trolley displacement deviation (the difference between the actual displacement and the target displacement) is read. The steel pile inclination angle, the clamp clamping force distribution and the trolley displacement deviation are input into the collaborative control correction model. The model establishes the motion coupling relationship of each actuator of the trolley system (such as the correlation matrix of the steel pile inclination angle and the clamp clamping force) through a topological relationship modeling branch, and fuses the motion coupling relationship with the real-time attitude data through a collaborative optimization branch. After calculation by a multilayer perceptron, the collaborative correction coefficient of the node in the next operation phase is output.

[0063] For any control node, based on the dynamic pressure adjustment value and the collaborative correction coefficient obtained in the current control cycle, the weighted fusion is performed according to the preset proportion (for example, the dynamic pressure adjustment value weight accounts for 60%, and the collaborative correction coefficient weight accounts for 40%), and the nonlinear compensation is performed in combination with the load characteristics of the current oil cylinder (querying through the oil cylinder load-pressure characteristic curve), and finally the final control output of the node in the next operation phase is obtained. The nonlinear compensation function adopts a piecewise linear interpolation method, and the compensation coefficient is automatically selected according to the load size.

[0064] The final control outputs of all control nodes are integrated. First, the outputs are time-domain synchronized (synchronizing the node calculation period through the system clock), and then the instruction sequence with time sequence constraints is generated in combination with the device response characteristics (such as electromagnetic valve opening and closing delay time and oil cylinder action lag time), forming the trolley system hydraulic excitation control instruction set. The instruction sequence adopts an event-triggered mechanism, and the completion signal of the previous operation phase is used as the trigger condition of the next stage instruction.

[0065] The application will be further described below in combination with Examples 1 to 5:

[0066] Example 1:

[0067] The embodiment specifically limits the collection and calculation of the influence degree in the state feature set construction process. For any control node of the hydraulic execution unit, steel pile clamp and walking mechanism in the trolley system, the actual pressure data of each operation stage of the node in the historical operation cycle needs to be obtained, and the electromagnetic valve opening and closing delay time, displacement sensor sampling value, hydraulic oil temperature peak value and environmental vibration spectrum data of the corresponding stage are also collected. Among them, the length of the historical operation cycle is determined according to the equipment working condition, and is usually 10 to 50 complete cycles of continuous operation, each cycle contains clamp clamping, trolley positioning, steel pile lowering, excavation operation, trolley displacement and other operation stages, and each stage is identified by photoelectric switch or travel sensor.

[0068] The collection of electromagnetic valve opening and closing delay time is realized by connecting a high-precision time stamp module in the electromagnetic valve control loop. The module synchronously records the time of the driving signal sent by the controller and the time of the in-place signal feedback by the electromagnetic valve. The time difference between the two is the delay time, and the resolution can reach microseconds. The displacement sensor sampling value adopts a high-frequency sampling mode, with a sampling frequency of 20Hz, i.e. data is obtained every 50ms, which is stored after being filtered by a low-pass filter to remove high-frequency noise. The collection of hydraulic oil temperature peak value uses a temperature sensor with peak holding function. The sensor probe is embedded 10cm away from the valve body at the outlet pipeline of the hydraulic pump, which monitors the oil temperature change in real time and records the maximum value of each operation stage. The environmental vibration spectrum data is collected by a three-axis vibration acceleration sensor, which is fixed to the non-stressed plane of the steel pile base, with a collection frequency of 10kHz. The time domain signal is converted to frequency domain spectrum by fast Fourier transform (FFT), and the frequency spectrum distribution in the range of 0.1Hz to 200Hz is obtained.

[0069] The division of sea state level identification follows the International Maritime Organization (IMO) standard, which is divided into six categories according to wave height and period and assigned a unique code. Among them, 1st sea state corresponds to wave height ≤ 0.5m and period ≤ 4s, coded as "01"; 2nd sea state corresponds to 0.5m < wave height ≤ 1.25m and 4s < period ≤ 6s, coded as "02"; 3rd sea state corresponds to 1.25m < wave height ≤ 2.5m and 6s < period ≤ 8s, coded as "03"; 4th sea state corresponds to 2.5m < wave height ≤ 4.0m and 8s < period ≤ 10s, coded as "04"; 5th sea state corresponds to 4.0m < wave height ≤ 6.0m and 10s < period ≤ 12s, coded as "05"; 6th sea state corresponds to wave height > 6.0m or period > 12s, coded as "06". The sea state level is calculated in real time by the wave radar and attitude sensor equipped on the ship, and updated every 10 minutes.

[0070] The equipment code information includes the oil cylinder model identification and the clamp type. The oil cylinder model identification is divided into three levels according to the rated pressure: P1 level, the rated pressure ≤ 16 MPa, P2 level, the rated pressure is 16 MPa~25 MPa (including 25 MPa), P3 level, the rated pressure > 25 MPa; the clamp type is divided into plane (code F1) and curved surface (code F2) according to the clamping surface structure, wherein the plane clamp is suitable for the steel pile with smooth surface, and the curved surface clamp is suitable for the special-shaped steel pile with arc. The equipment code is input by manual input or RFID tag reading mode during system initialization, and is stored in the controller register, which can be called in real time with the control data.

[0071] The state sequence information of each operation stage includes the pressure fluctuation amplitude of the node at n continuous sampling points in the stage, and the value of n is determined according to the operation stage length, usually not less than 100 sampling points, to ensure the reliability of the statistical result. For example, if the operation stage length is 5 seconds, 100 sampling points can be obtained at a sampling frequency of 20 Hz, and each point is encoded in time sequence as 1 to n. By traversing the historical cycle data, the frequency of pressure overrun corresponding to each sampling point code is counted, and the overrun judgment standard is that the actual pressure exceeds the preset pressure threshold ± 10%. The frequency statistics adopts a sliding window algorithm, and the window size is 5 historical cycles. The proportion of the number of overruns of each sampling point in the window is calculated, and the sampling point code with the highest proportion is taken as the sensitive time characteristic parameter of the operation stage. For example, the 50th sampling point in a stage accumulates 15 overruns in 5 cycles, the total sampling number is 500, and the proportion is 3%. If the proportion is the highest in the stage, the code is recorded as the characteristic parameter.

[0072] The influence degree of the oil cylinder pressure value, the electromagnetic valve response time, the displacement deviation, the hydraulic oil temperature and the environmental vibration on the system stability is calculated as follows:

[0073] The influence degree of the oil cylinder pressure value: through the correlation analysis of the historical data and the system failure, the odds ratio (OR value) is calculated by using the Logistic regression model. First, the historical data is divided into failure samples (marked as 1) and normal samples (marked as 0), the oil cylinder pressure value is taken as the independent variable, and the failure state is taken as the dependent variable, to construct a binary classification model. After the model training is completed, the OR value represents the change multiple of the failure probability when the oil cylinder pressure value changes by one unit, and the value is the influence degree coefficient. For example, if the OR value is 2.5, it means that the failure probability increases by 2.5 times when the pressure value increases by 1 MPa.

[0074] The influence degree of the electromagnetic valve response time: the same Logistic regression model is adopted, the independent variable is the response time, and the dependent variable is the failure state. The response time is quantified in milliseconds, and the OR value output by the model reflects the influence degree of the response time extension on the failure probability.

[0075] Impact of Displacement Deviation: Displacement deviation is defined as the absolute value of the difference between the actual displacement and the target displacement, in millimeters. The degree of impact is determined by calculating the Spearman rank correlation coefficient between this deviation value and the number of fault occurrences. The correlation coefficient ranges from [-1, 1], with a larger absolute value indicating a stronger correlation; here, the absolute value is used as the degree of impact coefficient.

[0076] Impact of Hydraulic Oil Temperature: The correlation analysis between peak hydraulic oil temperature and system failure uses the Cox proportional hazards model in survival analysis, with oil temperature as a covariate, and the hazard ratio (HR value) is calculated as the impact coefficient. The HR value represents the multiple by which the risk of system failure changes for every 1°C increase in oil temperature.

[0077] The degree of environmental vibration impact is determined by calculating the offset between the main peak frequency of the vibration spectrum and the natural frequency of the equipment. First, the natural frequency fnatural (in Hz) of the steel pile trolley system is obtained through hammer impact tests or finite element analysis. Then, the main peak frequency fmain is extracted from the vibration spectrum. The offset Δf = |fmain - fnatural|, and the impact coefficient = Δf / fnatural × 100%. When fmain coincides with fnatural, Δf = 0, and the impact coefficient is 0, indicating no resonance risk. When Δf exceeds fnatural × 20%, it is considered a high-risk state, with an impact coefficient ≥ 20%.

[0078] During data processing, all raw data undergo outlier removal and missing value imputation. Outlier detection uses the IQR (interquartile range) method to remove data points exceeding the range of Q1-1.5IQR or Q3+1.5IQR. Missing values ​​are imputed using linear interpolation or the mean of data from adjacent periods. After calculating the influence coefficient, normalization is performed to map the influence of each parameter to the [0,1] interval, facilitating the subsequent generation of the state feature set. The normalization formula is: Normalized value = (Parameter influence coefficient - Minimum value) / (Maximum value - Minimum value), where the minimum and maximum values ​​are taken from the statistical extreme values ​​in historical data.

[0079] Example 2:

[0080] This embodiment specifies the calculation method for the state feature set and the architecture of the dynamic pressure equilibrium model. The state feature set consists of a pressure fluctuation factor, a response delay factor, a displacement deviation factor, a thermal attenuation factor, and a mechanical resonance factor. Each factor is obtained by normalizing and weighting the sum of the influence coefficients of the corresponding parameters. Specifically, the influence coefficients of cylinder pressure, solenoid valve response time, displacement deviation, hydraulic oil temperature, and environmental vibration are first obtained. Each coefficient is obtained through correlation analysis of historical data and system faults or spectrum analysis (as described in Example 1). Then, the coefficients are normalized using the Z-score normalization method, as shown in the formula:

[0081]

[0082] wherein, is the mean value of the corresponding coefficient in historical data, is the standard deviation. The normalized data is mapped to the standard normal distribution, which is convenient for subsequent weighted calculation. In the weighting process, the weight of each parameter is determined by the analytic hierarchy process (AHP), for example, the weight of the cylinder pressure value is set to 40% because it directly affects the stability of the hydraulic system; the weight of the solenoid valve response time is 20% because it affects the control accuracy; the weights of the displacement deviation, hydraulic oil temperature and environmental vibration are 15%, 15% and 10%, respectively. Finally, the factors are generated by weighted summation, and the formula is:

[0083]

[0084] (Note: the calculation of each factor uses the sum of the product of the normalized value of the corresponding parameter and the weight. Here, the pressure fluctuation factor is taken as an example, and the rest are similar.)

[0085] The dynamic pressure balancing model is constructed based on a multi-modal perception network, which includes a data fusion layer, a time sequence encoding layer, a feature extraction stacking layer, a cross-modal attention layer, a decision generation layer and an output calibration layer. The structure and function of each layer are as follows:

[0086] ① Data fusion layer, which is responsible for converting multi-source heterogeneous input data into a unified dimension multi-dimensional feature tensor. The input data includes:

[0087] Pressure time sequence queue: composed of actual pressure data of the previous M time units in the operation order, with a dimension of , where M is the length of the historical window, usually 10 to 50, which is set according to the system response speed requirement.

[0088] Pre-set pressure threshold: the target pressure value of the next operation stage, determined by the system process parameters, with a dimension of .

[0089] Target displacement amount: the expected displacement value of the trolley walking mechanism, from the upper control instruction, with a dimension of .

[0090] Hydraulic oil temperature limit: the upper limit of the safe temperature set according to the type of hydraulic oil and the environmental temperature, with a dimension of .

[0091] Device encoding information: including cylinder model identification (P1 / P2 / P3, one-hot encoding as a 3-dimensional vector) and clamp type (F1 / F2, one-hot encoding as a 2-dimensional vector), with a total dimension of .

[0092] Sea state level identification: six levels (codes 01-06) are divided according to wave height and period, and a one-hot code is used Vector.

[0093] State feature set: a 5-dimensional vector containing five factors, with dimensions .

[0094] The data fusion layer first splices the above data into a raw feature vector with dimensions , and then performs linear transformation through a fully connected neural network, with the formula:

[0095]

[0096] where W is the weight matrix, and b is the bias vector, optimized through model training. The ReLU activation function is used to introduce nonlinearity, and the output dimension is (D is the feature dimension set by the model, usually 128 or 256).

[0097] ② Time encoding layer, which generates operation sequence encoding for each operation stage in the pressure time queue to preserve the time dependence of the job flow. The encoding method uses sine-cosine position encoding, with the formula:

[0098]

[0099] where t is the time unit number (1 to M), and d is the feature dimension number. Position encoding generates a unique phase feature for each time unit through different frequencies of sine and cosine functions, avoiding the long-term dependence problem of recurrent neural network (RNN) models. The generated encoding is added element-wise to the feature vector of the pressure time queue to form an input representation containing time sequence information.

[0100] ③ Feature extraction stacking layer, which contains L parallel feature extraction modules (usually L=3) that process hydraulic parameter features, mechanical motion features, and environmental interference features respectively:

[0101] Hydraulic parameter module: input is the pressure time queue, preset pressure threshold, hydraulic oil temperature limit, and pressure fluctuation factor and thermal decay factor in the state feature set, using 1D convolutional neural network (1D-CNN) for feature extraction. The convolution kernel size is 3, the step is 1, the padding is 1, the number of layers is 2, and each layer is followed by BatchNormalization and ReLU activation function, which is used to capture the time domain features of pressure fluctuation and the influence of oil temperature on the system.

[0102] ​​Mechanical motion module: the input is target displacement, displacement sensor data, and displacement deviation factor in state feature set, which is processed by gated recurrent unit (GRU) network to deal with sequence data. The GRU unit contains reset gate and update gate, which can effectively capture the dynamic trend of displacement deviation, and the output dimension is consistent with the hydraulic parameter module.

[0103] Environmental interference module: the input is sea state level identification, environmental vibration spectrum characteristics (main peak frequency offset extracted by preprocessing) and mechanical resonance factor, which is processed by fully connected neural network. This module combines discrete sea state level coding with continuous vibration characteristics, and outputs the comprehensive feature vector of environmental interference.

[0104] The feature vectors output by each module are spliced in the channel dimension to form a composite feature tensor containing multi-modal information, with a dimension of .

[0105] ④ Cross-modal attention layer, which uses multi-head self-attention mechanism (Multi-Head Attention) to realize the interaction between state feature set and multi-modal composite features. The specific steps are as follows:

[0106] The composite feature tensor is linearly mapped to query (Query), key (Key), and value (Value) matrices, with the formula:

[0107]

[0108] Where, is a trainable weight matrix.

[0109] The dot product similarity of each query and all keys is calculated, divided by ( is the dimension of the key), and the attention weight is generated by the Softmax function:

[0110]

[0111] The multi-head mechanism divides the query, key, and value into h heads (usually h = 2), and parallelly calculates the attention and splices it, with the formula:

[0112]

[0113] Where, is the output projection matrix.

[0114] Through cross-modal attention calculation, the model can dynamically allocate the weight of different modal features to generate a dynamic weight allocation matrix containing interaction information.

[0115] The decision generation layer element-wise multiplies the dynamic weight distribution matrix output by the cross-modal attention and the feature extraction result to realize feature weighted fusion. The fused feature vector is reduced in dimension by a fully connected neural network to generate a preliminary control policy vector, and the formula is:

[0116]

[0117] wherein, and are the parameters of the fully connected layer, the activation function Tanh limits the output value to the interval [-1, 1], and represents the direction (positive or negative) and relative amplitude of pressure adjustment.

[0118] The output calibration layer maps the preliminary control policy vector to the dynamic pressure adjustment value (unit: MPa) of the actual physical quantity. The mapping process adopts linear transformation, and the formula is:

[0119]

[0120] wherein, is a proportional factor, is an offset, which is determined by model training. For example, if the policy vector output is 0.5, , then the dynamic pressure adjustment value is .

[0121] In the model inference stage, the input data is processed according to the following process: first, the data fusion layer converts multi-source data into a unified feature space representation, the time sequence encoding layer injects time sequence information, the feature extraction stack layer extracts deep features of different modalities in parallel, the cross-modal attention layer calculates the interaction weight between modalities, the decision generation layer generates a preliminary control policy, and finally the output calibration layer converts it into a specific pressure adjustment value. The calculation delay of the whole process is controlled within 50 ms, meeting the real-time control requirements.

[0122] Example 3:

[0123] The training process and adaptive optimization steps of the dynamic pressure balancing model are specifically defined in this embodiment. The training of the dynamic pressure balancing model is based on a historical control data set, and the data collection covers multiple operation cycles, each cycle containing a complete trolley operation process, such as steel pile positioning, clamp clamping, excavation operation, trolley displacement, etc. Each data sample of the historical control data set is composed of a sequence of consecutive M+1 operation stages, where the first M stages are input features and the M+1 stage is the target output label. The input features include the pressure time sequence queue of each stage, the preset pressure threshold, the target displacement amount, the hydraulic oil temperature limit, the equipment code information, the sea state level identification and the state feature set; the target output is the pressure adjustment amount of the M+1 stage, which is determined by artificial calibration or expert experience combined with actual working conditions, as the benchmark for model learning.

[0124] The construction of the data set follows the following steps: first, through the multi-source sensor module and the time series data storage module, the original data of each control node is collected and stored according to the control period (such as 100ms), and the data storage time covers at least 200 operation cycles; second, the original data is preprocessed, including outlier rejection (using IQR method, rejecting data points exceeding Q1-1.5IQR or Q3+1.5IQR range), missing value filling (linear interpolation method) and stage marking (according to the photoelectric switch trigger signal to divide the operation stage); finally, the preprocessed data is segmented into independent samples according to the operation stage sequence, each sample contains a feature vector of consecutive M+1 stages and a corresponding pressure adjustment amount label. The data set is divided into training set and test set in the ratio of 7:3, where the training set is used for model parameter optimization and the test set is used to evaluate the generalization ability.

[0125] The model training adopts a supervised learning mode, taking the feature data of the first M stages in the training set as input and the pressure adjustment amount of the M+1 stage as target output. The loss function uses mean square error (MSE), and the calculation formula is:

[0126]

[0127] wherein, is the loss value, is the number of samples in the training batch, is the pressure adjustment amount predicted by the model, The actual label value is. The optimization algorithm uses the Adam algorithm, with an initial learning rate of 0.001, momentum parameters β1=0.9, β2=0.999, and ε=1e-8. During training, the batch size is set to 32, the number of iterations (epoch) is 100, the model parameters are saved every 5 epochs, and the loss value is evaluated on the validation set (20% of the training data is divided as the validation set). If the validation loss does not decrease for 10 consecutive epochs, the early stopping mechanism (EarlyStopping) is triggered to avoid overfitting.

[0128] The test phase uses the test set to evaluate the model control error, and the error indicators include root mean square error (RMSE) and mean absolute error (MAE). If the error does not meet the convergence criteria (such as RMSE>0.8MPa), then enter the adaptive optimization step. Adaptive optimization is based on the distribution characteristics of the test set error, automatically adjusting the model structure or parameters, which can be divided into two scenarios:

[0129] Scenario one: the error presents periodic fluctuations, when the test set loss curve appears regular oscillation (such as fluctuating once every 5 epochs), it is judged that the network has gradient disappearance or mode confusion problem. At this time, the following measures are taken:

[0130] Add residual connection structure: add residual skip connection (ResidualSkipConnection) between the parallel modules of the feature extraction stack layer, the formula is:

[0131]

[0132] where, is the input of the l-th layer, is the nonlinear transformation output of the l-th layer, is the output after residual connection. Residual connection preserves the original features through identity mapping, alleviating the gradient dissipation problem of deep network. Reduce learning rate: multiply the current learning rate by the decay factor 0.5, for example, from 0.001 to 0.0005, to slow down the parameter update step and avoid skipping the optimal solution in the optimization process.

[0133] Scenario two: the error continues to diverge, when the test set loss curve is monotonically increasing or has no convergence trend, it is judged that the network topology structure is unreasonable or the parameter initialization is improper. At this time, the following measures are taken:

[0134] Reconstruct the network topology: adjust the connection mode of the feature extraction module, such as changing the parallel structure to a series structure, or increasing / decreasing the number of modules (such as L from 3 to 4) to change the feature interaction path. For example, connect the hydraulic parameter module and the mechanical motion module in series, process the hydraulic features first and then input the motion features, to strengthen the causal relationship modeling.

[0135] Re-initialization parameters: the network weights are re-initialized using the Kaiming initialization method (HeInitialization), which automatically calculates the appropriate initialization variance according to the type of activation function (such as ReLU), and the formula is:

[0136]

[0137] where, is the weight parameter, is the number of input neurons, ensuring that the initialized network activation values have appropriate distribution ranges to avoid gradient explosion or disappearance.

[0138] During the adaptive optimization process, model structure adjustment and parameter updating are automatically implemented through code without human intervention. After each adjustment, the training process is reinitialized until the test set error converges to a preset threshold (such as RMSE≤0.5MPa) or reaches the maximum number of iterations (such as 200 times). The trained model parameters are stored in the non-volatile memory (such as EEPROM) of the controller, supporting power saving and power loading, ensuring that the system can be put into use without retraining after restarting.

[0139] It should be noted that the pressure adjustment amount label in the historical control data set needs to be strictly verified by technical personnel with rich experience in dredger operation combined with equipment operating manuals to ensure the rationality and safety of the label value. During model training, the use of unverified simulation data or hypothetical data is prohibited, and all input features and output labels are based on real working scene collection to ensure the engineering practicability of the model. In addition, the training environment uses an embedded computing platform (such as NVIDIA Jetson AGX Orin) integrated with a GPU acceleration module to ensure the efficiency of large-scale data training, with a single round of training period (100 epochs) controlled within 2 hours to meet the time cost requirements of engineering applications.

[0140] Example 4:

[0141] This embodiment specifically defines the architecture of the cooperative control correction model and the calculation method of the final control output. The cooperative control correction model is based on a graph neural network, aiming to model the motion coupling relationship of each actuator of the trolley system and generate a cooperative correction coefficient based on real-time steel pile attitude data to compensate for nonlinear errors when multiple mechanisms are linked. The model is divided into a topological relationship modeling branch and a cooperative optimization branch, and the implementation details of each branch are as follows:

[0142] The topological relationship modeling branch is used to establish the motion coupling relationship of each actuator of the trolley system. The actuators of the trolley system include hydraulic cylinders, steel pile clamps, walking mechanisms, etc., and each mechanism forms a dynamic correlation through mechanical connection or hydraulic oil circuit. For example, the extension and retraction action of the hydraulic cylinder will drive the steel pile to move up and down through the connecting rod mechanism, the change of the inclination angle of the steel pile will affect the clamping force distribution of the clamp, and the displacement deviation of the walking mechanism may cause uneven stress of the steel pile. In the modeling process, each actuator is first abstracted as a node in the graph structure, the number of nodes is determined according to the complexity of the system, usually 5 to 10 (such as cylinder node, clamp left node, clamp right node, trolley chassis node, steel pile top node, etc.). The node features include physical parameters of the mechanism (such as cylinder cross-sectional area, clamp clamping force range) and real-time state parameters (such as current pressure of the cylinder, opening and closing degree of the clamp).

[0143] The edges between the nodes represent the motion coupling relationship between the mechanisms, and the weights of the edges are determined by the correlation analysis in the historical data. For example, the Pearson correlation coefficient of the change of the cylinder pressure and the change of the inclination angle of the steel pile is calculated, if the coefficient is 0.7, the weight of the corresponding edge is set to 0.7, indicating that there is a strong positive correlation between the two; if the coefficient is -0.3, the weight is set to -0.3, indicating a weak negative correlation. The weight of the edge is in the range of [-1, 1], the greater the absolute value, the higher the coupling strength. The construction of the graph structure adopts an undirected graph model, that is, the weight matrix of the edge is a symmetric matrix, reflecting the bidirectional influence between the mechanisms. The topological relationship modeling branch is trained by a graph convolution network (GCN), the input is the node feature matrix and the initial adjacency matrix, and the output is the updated adjacency matrix, which represents the dynamic coupling strength between the mechanisms.

[0144] The collaborative optimization branch fuses the motion coupling relationship with the real-time steel pile attitude data to generate a collaborative correction coefficient. The real-time steel pile attitude data includes the inclination angle of the steel pile, the clamping force distribution of the clamp and the displacement deviation of the trolley. The inclination angle of the steel pile is collected by a dual-axis inclination sensor installed at the top of the steel pile, with an accuracy of ±0.1°. The sensor is installed by magnetic attraction, which is convenient for calibration and maintenance. The clamping force distribution of the clamp is collected by a strain gauge sensor array inside the clamp, which contains 4 to 8 measuring points evenly distributed on the clamping surface. The force value of each measuring point is converted into a voltage signal by a Wheatstone bridge circuit, and then input into the control system after amplification and analog-to-digital conversion. The displacement deviation of the trolley is monitored in real time by a laser displacement sensor installed on the guide rail, with a resolution of 0.1 mm and a detection range of 0 to 5000 mm.

[0145] The processing flow of the collaborative optimization branch is as follows: First, the real-time collected steel pile tilt angle (unit: °), clamping force distribution (unit: kN), and trolley displacement deviation (unit: mm) are normalized and mapped to the [0,1] interval to eliminate the influence of dimensions; then, the normalized attitude data is used as the node feature input to the graph neural network and fused with the adjacency matrix output by the topology relationship modeling branch. The fusion process is achieved through multi-layer graph convolution operations, and the calculation formula for each layer of graph convolution is:

[0146]

[0147] in, For the first The node feature matrix of the layer To add a self-loop adjacency matrix, This is the corresponding degree matrix. For a trainable weight matrix, The activation function is ReLU. After multiple convolutions, the node features contain coupling information between mechanisms and real-time attitude information. Finally, a multilayer perceptron (MLP) is used for nonlinear transformation to output cooperative correction coefficients, with values ​​ranging from -0.2 to 0.2. The sign of the correction coefficient indicates the direction of control adjustment: a positive value increases the output of the current control node (e.g., increases cylinder pressure), and a negative value decreases the output. The absolute value indicates the adjustment magnitude; for example, when the coefficient is 0.1, the output adjustment magnitude is 10% of the baseline value.

[0148] The final control output is calculated by combining the dynamic pressure adjustment value and the collaborative correction coefficient through weighted fusion and nonlinear compensation. The dynamic pressure adjustment value is output by the dynamic pressure equilibrium model, representing the pressure adjustment baseline value based on historical data and multimodal characteristics; the collaborative correction coefficient is output by the collaborative control correction model, representing the correction amount based on real-time attitude and mechanism coupling. During weighted fusion, the preset ratio is determined based on the system response characteristics; for example, the dynamic pressure adjustment value accounts for 60% of the weight, and the collaborative correction coefficient accounts for 40%. The calculation formula is as follows:

[0149]

[0150] The nonlinear compensation link is used to correct the influence of the cylinder load characteristics on the control accuracy. The load characteristics of the cylinder are represented by the nonlinearity of the pressure-flow curve, for example, the pressure fluctuation is sensitive to the flow change under light load, and the system inertia increases under heavy load, resulting in response lag. The load characteristics are determined by the pre-tested cylinder load-pressure curve, and the curve acquisition method is to apply different loads (such as 50kN, 100kN, 150kN) at both ends of the cylinder, record the corresponding relationship between the input pressure and the piston movement speed, and form a piecewise linear curve. When compensating for nonlinearity, the compensation coefficient is automatically adjusted according to the current cylinder load size. For example, when the load is 200kN, the compensation coefficient is 1.1, and the preliminary output quantity needs to be multiplied by the coefficient, the formula is:

[0151]

[0152] The value range of the compensation coefficient is usually 0.9 to 1.2, which is determined according to the test data.

[0153] Taking the actual working condition of a steel pile carriage of a cutter suction dredger as an example: during the steel pile lowering operation stage, the pressure adjustment value output by the dynamic pressure equalization model is +5MPa (indicating that the pressure needs to be increased by 5MPa), the collaborative control correction model detects that the steel pile tilts 0.8° to the left, the left clamping force of the clamp is 120kN, the right clamping force is 80kN, and the carriage displacement deviation is +15mm (offset to the right). Through graph neural network analysis, there is a strong coupling relationship between the steel pile tilt and the left and right clamping forces of the clamp (the corresponding weight of the adjacency matrix is 0.9), and the right deviation of the carriage aggravates the left force. The model outputs a collaborative correction coefficient of -0.15, indicating that the pressure adjustment amount needs to be reduced by 15%. The preliminary output quantity after weighted fusion is . At this time, the cylinder load is 180kN, according to the load characteristic curve, the compensation coefficient is 1.05, and the final control output quantity is , that is, the actual input pressure adjustment command to the cylinder is to increase 2.52MPa.

[0154] Example 5:

[0155] This embodiment specifically limits the generation method of the hydraulic excitation control instruction set and the hardware composition of the control system. The generation of the hydraulic excitation control instruction set needs to integrate the final control output quantities of all control nodes, and combine the device response characteristics and timing constraints to form an executable instruction sequence. Taking a steel pile carriage system of a cutter suction dredger as an example, the system includes 4 control nodes: left front cylinder node, right front cylinder node, left rear clamp node, and right rear walking mechanism node, and the final control output quantities of each node correspond to cylinder pressure adjustment value, clamp clamping force adjustment value, walking motor speed instruction, etc.

[0156] The first step of the instruction set generation is time domain synchronization calibration. The calculation period of each control node is 100 ms, but due to sensor sampling, data transmission and other delays, there may be slight time deviations. Synchronization calibration is achieved through a system global clock (accuracy ± 1 μs), and all nodes update data at the start of each calculation period (e.g. 0 ms, 100 ms, 200 ms, etc.) and complete control quantity calculation before the end of the period (e.g. 95 ms), ensuring that the instruction generation time is consistent. For example, the left front oil cylinder node calculates a pressure adjustment value of +3 MPa in the nth period, and the right rear walking mechanism node calculates a displacement increment of +200 mm, both of which are transmitted to the instruction generation module at 95 ms in the nth period, ensuring that they are executed simultaneously at the start of the nth+1 period.

[0157] The second step is to generate timing constraints based on device response characteristics. Device response characteristics include electromagnetic valve opening and closing delay, oil cylinder action lag, motor starting inertia, etc. Taking the electromagnetic valve as an example, its opening and closing delay time is 20 ms, the lag time from receiving the pressure instruction to completing the action of the oil cylinder is 80 ms, and the walking motor needs 150 ms from the speed instruction to reach a stable speed. The instruction sequence needs to set the execution order and delay time according to these characteristics. For example, in the steel pile positioning stage, the following operations need to be performed in sequence:

[0158] The left rear clamp node sends a clamping instruction, taking into account the electromagnetic valve delay of 20 ms, the instruction sending time is set to the start of the period (0 ms), and the actual clamping action completion time is 20 ms;

[0159] The left front oil cylinder node sends a pressurization instruction, which needs to wait for the clamp clamping in place signal (20 ms feedback), so the instruction sending time is set to 25 ms, and the oil cylinder action completion time is 25 ms + 80 ms = 105 ms;

[0160] The right rear walking mechanism node sends a displacement instruction, which needs to wait for the oil cylinder pressure to stabilize (set the stabilization time to 50 ms), so the instruction sending time is set to 105 ms + 50 ms = 155 ms, and the motor reaches the target speed at 155 ms + 150 ms = 305 ms.

[0161] Through the above timing constraints, it is ensured that each mechanism action is executed in the correct order according to the process requirements, avoiding mechanical impact or control failure due to synchronization errors. The instruction sequence uses an event-triggered mechanism, with the completion signal of the previous action (such as the clamp in place switch, pressure sensor stable signal) as the trigger condition for the next action instruction, rather than simply relying on time delay, to adapt to changes in device response speed under different working conditions.

[0162] The hardware components of the control system include a multi-source sensor module, a state feature calculation module, a time sequence data storage module, a sea state identification module, a dynamic pressure balancing module, a cooperative control correction module, an instruction generation module, and a safety warning module. The specific implementation of each module is as follows:

[0163] The multi-source sensor module is deployed at key positions of the trolley system:

[0164] The pressure sensor (precision ±0.5% FS) is installed on the inlet and outlet pipes of the hydraulic cylinder, with an armored stainless steel shell to adapt to humid and vibrating environments, and outputs a 4-20 mA analog signal.

[0165] The electromagnetic valve response time monitoring module is composed of a microsecond timer and a signal conditioning circuit, and is connected in parallel to the electromagnetic valve control loop, which monitors the time difference between the driving signal and the feedback signal in real time.

[0166] The laser displacement sensor (precision ±1 mm) is installed on both sides of the trolley guide rail, which monitors the displacement of the trolley in real time through the triangulation method, and outputs an RS485 digital signal.

[0167] The temperature sensor (precision ±1°C) uses a Pt100 thermal resistor, which is buried 10 cm away from the inlet of the hydraulic oil tank, to monitor the change of oil temperature.

[0168] The vibration sensor (frequency range 0.1-1000 Hz) is a three-axis accelerometer, which is fixed to the non-stress surface of the steel pile base, and is installed through magnetic attraction, which is convenient for disassembly and calibration.

[0169] The state feature calculation module is realized based on FPGA chip, which includes independent data preprocessing unit and feature calculation unit. The preprocessing unit filters (50 Hz power frequency notch), amplifies and digitizes (16-bit ADC) the sensor signal, and the feature calculation unit calculates five factors such as pressure fluctuation factor and response delay factor in real time according to the method described in embodiment 1, with a processing delay of ≤10 ms. The results are transmitted to the dynamic pressure balancing module through a high-speed bus.

[0170] The time sequence data storage module uses a circular buffer (CircularBuffer) structure, which is composed of SRAM memory and address counter, and can store 200 operating stage pressure data (each stage contains 100 sampling points, each point occupies 4 bytes, total capacity 200x100x4=80KB). The buffer supports first-in first-out (FIFO) read and write, and automatically covers the earliest data when full, ensuring that the latest historical window data is always retained.

[0171] The sea state identification module integrates inertial navigation system (INS) and wave radar:

[0172] INS fuses the roll, pitch and heading angle of the ship by gyroscopes, accelerometers and magnetometers, with a sampling frequency of 100 Hz.

[0173] Wave radar uses X-band radar, installed on the bow mast, monitors wave height, period and direction, with an update frequency of 1 Hz.

[0174] The data processing unit fuses the ship's attitude and wave parameters through the extended Kalman filter algorithm, outputs the sea state grade identification (01-06), and transmits it to the control system through the CAN bus.

[0175] The dynamic pressure balancing module and the collaborative control correction module are realized based on the NVIDIA Jetson AGX Orin embedded platform, which integrates a 6-core ARM CPU and a 200 TOPS power GPU, supporting CUDA acceleration. The multi-modal perception network of the dynamic pressure balancing module and the graph neural network of the collaborative control correction module are optimized through the TensorRT framework, with inference delays of 40 ms and 30 ms respectively, meeting the real-time requirements.

[0176] The instruction generation module uses STM32H7 series microcontrollers, integrating CANopen master controllers and D / A conversion modules. The microcontroller receives the calculation results of each module, performs time domain synchronization calibration and timing constraint algorithms, and generates control instructions, including:

[0177] Analog instructions: such as oil cylinder pressure adjustment value (output through 4-20 mA signal);

[0178] Digital instructions: such as solenoid valve on-off signal (24V level signal);

[0179] Pulse instructions: such as walking motor speed pulse (output through quadrature encoder interface). The instruction output period is consistent with the control period (100 ms), and the hardware watchdog timer is used to ensure reliability.

[0180] The safety warning module has a built-in historical fault database and an abnormal pattern recognition unit:

[0181] The historical fault database stores more than 5000 fault records, each record containing a set of state features at the time of failure, an operation stage and a fault type (such as pressure overrun, clamp loosening);

[0182] The abnormal pattern recognition unit is based on the One-Class SVM algorithm, which monitors the fluctuations in the state feature set in real time. When any factor exceeds the warning threshold (such as pressure fluctuation factor > 0.8), a three-level alarm is triggered:

[0183] Level 1 alarm (warning): the operation interface displays a yellow warning, and records abnormal data;

[0184] Secondary alarm (warning): accompanied by sound and light alarm, automatically reduce the control amount adjustment range of 20%;

[0185] Tertiary alarm (emergency): trigger safety shutdown program, cut off hydraulic power source and lock the position of the trolley.

[0186] For example, in the process of steel pile lowering, when the temperature sensor detects that the oil temperature peak value reaches 65℃ (exceeding the limit value of 60℃), the state feature calculation module generates a thermal decay factor of 0.9 (close to the threshold value of 1.0), the safety warning module identifies a secondary alarm, and the instruction generation module automatically reduces the pressure adjustment value of each oil cylinder by 20%, while starting the hydraulic oil cooling pump until the oil temperature falls back to the safety range.

[0187] It should be noted that, in this text, relational terms such as first and second are used merely to distinguish one entity or action from another, without necessarily requiring or implying that there is any such actual relationship or order between them. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment.

[0188] Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the application, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A control method for a steel pile platform truck of a cutter suction dredger based on hydraulic excitation pre-warning, characterized in that, The method comprises the following steps: For any control node of the hydraulic actuator unit, the steel pile clamp and the walking mechanism in the trolley system, the influence degree of the oil cylinder pressure value, the electromagnetic valve response time, the displacement sensor data, the hydraulic oil temperature and the environmental vibration parameters on the system stability is collected respectively, and the pressure fluctuation factor, the response delay factor, the displacement deviation factor, the thermal attenuation factor and the mechanical resonance factor are calculated based on the obtained influence degrees to form a state feature set; A dynamic pressure balancing model is constructed, for any control node, the actual pressure data of the node in the previous M time units in any control period is arranged in the operation order to form a pressure time sequence queue, and the preset pressure threshold, the target displacement amount, the hydraulic oil temperature limit and the equipment code information of the next operation stage are obtained, and the current sea state level identifier is also obtained; the pressure time sequence queue, the preset pressure threshold, the target displacement amount, the hydraulic oil temperature limit, the equipment code information, the sea state level identifier and the state feature set of the current control period are input into the dynamic pressure balancing model, and the dynamic pressure adjustment value of the node in the next operation stage is output; A cooperative control correction model is constructed, for any control node, real-time steel pile attitude data is obtained in any control period; the inclination angle of the steel pile, the clamp clamping force distribution and the trolley displacement deviation of the current control period are input into the cooperative control correction model, and the cooperative correction coefficient of the node in the next operation stage is output; For any control node, based on the dynamic pressure adjustment value and the cooperative correction coefficient obtained in the current control period, the final control output of the node in the next operation stage is calculated; The final control outputs of all control nodes are integrated to generate a trolley system hydraulic excitation control instruction set.

2. The hydraulic excitation-based early warning control method for the steel pile dolly of the cutter suction dredger according to claim 1, characterized in that, The influence degree of the oil cylinder pressure value, the electromagnetic valve response time, the displacement sensor data, the hydraulic oil temperature and the environmental vibration parameters on the system stability is collected, which specifically comprises: For any control node, the actual pressure data of each operation stage of the node in the historical operation period is obtained, and the electromagnetic valve opening and closing delay time, the displacement sensor sampling value, the hydraulic oil temperature peak value and the environmental vibration spectrum data of each operation stage are collected; wherein the sea state level identifier is divided into six categories according to the wave height and the period, and each category corresponds to a unique code; the equipment code information includes the oil cylinder model identifier and the clamp type, the oil cylinder model identifier is divided into three levels according to the rated pressure, and the clamp type is divided into plane and curved surface according to the clamping surface structure; The state sequence information of each operation stage includes the pressure fluctuation amplitude of n continuous sampling points of the node in the operation stage; the n sampling points of each operation stage are coded in time sequence as 1 to n, and the sampling point code with the highest frequency of pressure overrun in the historical period is counted; The influence degree of the oil cylinder pressure value, the electromagnetic valve response time, the displacement deviation, the hydraulic oil temperature and the environmental vibration on the stability of the current control node is calculated respectively, wherein the influence degrees of the first four items are obtained through the correlation analysis of the historical data and the system failure, and the influence degree of the environmental vibration is obtained by calculating the offset of the main peak frequency of the spectrum.

3. The hydraulic excitation-based early-warning control method for the steel-pile platform truck of the cutter-suction dredger according to claim 2, characterized in that, The state feature set is calculated based on the influence degree of the cylinder pressure value, the electromagnetic valve response time, the displacement deviation, the hydraulic oil temperature and the environmental vibration, and a pressure fluctuation factor to a mechanical resonance factor is obtained by normalized weighted summation.

4. The hydraulic excitation-based early-warning control method for the steel-pile platform truck of the cutter-suction dredger according to claim 3, characterized in that, The dynamic pressure balancing model is constructed based on a multi-modal perception network, and includes a data fusion layer, a time sequence coding layer, a feature extraction stack layer, a cross-modal attention layer, a decision generation layer and an output calibration layer. The data fusion layer is used for converting the pressure time sequence queue, the preset pressure threshold, the target displacement amount, the hydraulic oil temperature limit value, the equipment coding information, the sea state grade identifier and the state feature set into a multi-dimensional feature tensor. The time sequence coding layer is used for generating operation sequence coding for each operation stage in the pressure time sequence queue, so as to maintain the continuity of the operation process. The feature extraction stack layer includes L parallel feature extraction modules, each of which processes hydraulic parameter features, mechanical motion features and environmental interference features. The cross-modal attention layer is used for cross-attention calculation on the multi-dimensional features of the state feature set and the feature extraction output, to generate a dynamic weight distribution matrix. The decision generation layer is used for fusing the dynamic weight distribution matrix and the feature extraction result to generate a preliminary control strategy vector. The output calibration layer is used for mapping the preliminary control strategy vector into a dynamic pressure adjustment value.

5. The hydraulic excitation-based early-warning control method for the steel-pile platform truck of the cutter-suction dredger according to claim 4, characterized in that, The training process of the dynamic pressure balancing model includes: Collecting historical control data sets of multiple operation cycles, each data sample including pressure data of continuous M+1 operation stages, influence factor data of the M+1 stage and state feature set; dividing the data set into a training set and a test set; Taking the data of the first M stages and the influence factors in the training set as input, and taking the pressure adjustment amount of the M+1 stage as target output, the network parameters are optimized through error back propagation; Using the test set to evaluate the model control error, if the error does not reach the convergence standard, adjust the number of feature extraction modules or the dimension of attention head and retrain.

6. The hydraulic excitation-based early-warning control method for the steel-pile platform truck of the cutter-suction dredger according to claim 5, characterized in that, The collaborative control correction model is constructed based on a graph neural network, including a topological relationship modeling branch and a collaborative optimization branch. The topological relationship modeling branch establishes the motion coupling relationship of each actuator of the trolley system through graph structure learning; The collaborative optimization branch fuses the motion coupling relationship and the steel pile posture data, and outputs a collaborative correction coefficient after multi-layer perception machine calculation.

7. The hydraulic excitation-based early-warning control method for the steel-pile platform truck of the cutter-suction dredger according to claim 6, characterized in that, The calculation method of the final control output quantity is to weight and fuse the dynamic pressure adjustment value and the collaborative correction coefficient according to a preset proportion, and to perform nonlinear compensation combined with the load characteristics of the current cylinder.

8. The hydraulic excitation-based early-warning control method for the steel-pile platform truck of the cutter-suction dredger according to claim 7, characterized in that, The generation method of the hydraulic excitation control instruction set is to perform time domain synchronous calibration on the final control output quantity of all control nodes, and to generate an instruction sequence with time sequence constraints combined with the device response characteristics.

9. The hydraulic excitation-based early-warning control method for the steel-pile platform truck of the cutter-suction dredger according to claim 5, characterized in that, The model training process further includes an adaptive optimization step: According to the distribution characteristics of the test set error, the connection mode of the feature extraction module or the activation function of the attention head is automatically adjusted; if the error presents periodic fluctuation, a residual connection structure is added and the learning rate is reduced; if the error continuously diverges, the network topology is reconstructed and the parameters are reinitialized.

10. A hydraulic excitation-based early-warning control system for a steel-pile platform truck of a cutter-suction dredger, for implementing the control method according to any one of claims 1 to 9, characterized in that, ​ A multi-source sensor module is arranged in the hydraulic execution unit, steel pile clamp and walking mechanism of the trolley system, and is used for collecting the cylinder pressure value, electromagnetic valve response time, displacement sensor data, hydraulic oil temperature and environmental vibration parameters of each control node in real time; A state feature calculation module is connected to the multi-source sensor module, and is used for calculating a pressure fluctuation factor, response delay factor, displacement deviation factor, thermal attenuation factor and mechanical resonance factor according to the collected data, and generating a state feature set; A time sequence data storage module is provided with a circular buffer unit, and is used for storing the actual pressure data of the previous M time units of each control node in the order of operation, to form a pressure time sequence queue; A sea state recognition module integrates a ship attitude sensor and a wave monitoring unit, and is used for real-time analysis of the current sea state grade identification; A dynamic pressure equalization module is constructed based on a multi-modal neural network, and the input end is connected to the state feature calculation module, time sequence data storage module and sea state recognition module, and is used for receiving the pressure time sequence queue, preset pressure threshold value, target displacement amount, hydraulic oil temperature limit value, equipment code information and sea state grade identification, and generating a dynamic pressure adjustment value through a cross-modal attention mechanism calculation; A cooperative control correction module is provided with a steel pile attitude monitoring unit and a clamp stress analysis unit, and is used for obtaining the real-time steel pile inclination angle, clamp clamping force distribution and trolley displacement deviation, modeling the motion coupling relationship through a graph neural network, and outputting a cooperative correction coefficient; An instruction generation module is connected to the input end of the dynamic pressure equalization module and the cooperative control correction module, and is used for performing nonlinear fusion calculation on the dynamic pressure adjustment value and the cooperative correction coefficient, generating the final control output of each control node, and synchronously generating a set of hydraulic excitation control instructions with time sequence constraints; A safety warning module is provided with a historical fault database and an abnormal pattern recognition unit, and is used for real-time monitoring of abnormal fluctuations in the state feature set, triggering a hierarchical alarm signal and feeding back to the instruction generation module for control amount compensation.

Images