Cutter suction dredger control method and device, dredger, medium and program product

Abstract

The invention discloses a cutter suction dredger control method and device, a dredger, a medium and a program product, and relates to the technical field of cutter suction dredger control. Under the condition that the concentration difference between the current mud concentration and the preset mud concentration is larger than a preset threshold value, the preset mud concentration serves as an optimization target, a mud concentration fitting model of the cutter suction dredger is solved based on a preset optimization algorithm, and construction parameters of the cutter suction dredger are obtained; wherein the mud concentration fitting model is used for representing a parameter relationship between the construction parameters and the mud concentration; and based on the construction parameters, the cutter suction dredger is controlled to work. The construction parameters can be regulated and controlled in real time according to the current mud concentration of the cutter suction dredger, and the operation stability and the operation efficiency of the cutter suction dredger are guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of cutter suction dredger control, and in particular to a cutter suction dredger control method and device, a dredger, a medium and a program product. BACKGROUND

[0002] In the related art, the construction parameters of the cutter suction dredger are usually set and adjusted by the operating personnel according to historical experience to control the operation mud concentration of the cutter suction dredger.

[0003] However, under the condition of continuous operation, the working condition of the dredger changes frequently and the geological uncertainty is high. The control method of adjusting the parameters relying on manual experience is difficult to respond to the dynamic changes of the operation condition of the dredger in real time, resulting in large fluctuations in the mud concentration during the operation of the cutter suction dredger, which affects the operation stability and efficiency of the cutter suction dredger. SUMMARY

[0004] The main purpose of the present application is to provide a cutter suction dredger control method, device, dredger, medium and program product, which aims to solve the technical problem of poor real-time control of the cutter suction dredger in the related art, which affects the operation stability and efficiency of the dredger.

[0005] To achieve the above-mentioned purpose, the present application provides a cutter suction dredger control method, which comprises:

[0006] obtaining the current mud concentration of the cutter suction dredger;

[0007] In the case where the concentration difference between the current mud concentration and the preset mud concentration is greater than the preset threshold, the preset mud concentration is taken as the optimization target, and a mud concentration fitting model of the cutter suction dredger is solved based on a preset optimization algorithm to obtain the construction parameters of the cutter suction dredger; wherein the mud concentration fitting model is used to represent the parameter relationship between the construction parameters and the mud concentration;

[0008] controlling the operation of the cutter suction dredger based on the construction parameters.

[0009] In an embodiment, the step of taking the preset mud concentration as the optimization target, and solving the mud concentration fitting model of the cutter suction dredger based on the preset optimization algorithm to obtain the construction parameters of the cutter suction dredger comprises:

[0010] constructing a high-density grid in the target space range based on a grid search algorithm; the target space range is determined based on the preset safety interval of the construction parameters, and the high-density grid includes a plurality of grid points, each grid point corresponding to a set of construction parameters;

[0011] for each grid point, inputting the construction parameters corresponding to the grid point into the mud concentration fitting model to obtain a mud concentration fitting value;

[0012] determine a fitting concentration difference between each mud concentration fitting value and the preset mud concentration;

[0013] determine the construction parameters corresponding to the grid point with the minimum fitting concentration difference as the construction parameters of the cutter suction dredger.

[0014] In an embodiment, the construction parameters include the forward speed, the reamer rotation speed, the reamer cutting into silt thickness, and the mud pump rotation speed.

[0015] With the preset mud concentration as the optimization target, the mud concentration fitting model of the cutter suction dredger is solved based on a preset optimization algorithm to obtain the construction parameters of the cutter suction dredger. The steps include:

[0016] Based on the grid search algorithm, a two-dimensional high-density grid is constructed on a two-dimensional plane formed by the first safety interval and the second safety interval. The first safety interval is the safety interval corresponding to the forward speed, and the second safety interval is the safety interval corresponding to the reamer rotation speed. The two-dimensional high-density grid includes a plurality of two-dimensional grid points, and each two-dimensional grid point corresponds to a set of forward speed and reamer rotation speed.

[0017] For each two-dimensional grid point, the current reamer cutting into silt thickness, the current mud pump rotation speed, and the forward speed and reamer rotation speed corresponding to the two-dimensional grid point are input into the mud concentration fitting model to obtain a first mud concentration fitting value.

[0018] The first fitting concentration difference between each first mud concentration fitting value and the preset mud concentration is determined.

[0019] The forward speed and reamer rotation speed corresponding to the two-dimensional grid point with the minimum first fitting concentration difference, as well as the current reamer cutting into silt thickness and the current mud pump rotation speed, are determined as the construction parameters of the cutter suction dredger.

[0020] In an embodiment, the construction parameters include the forward speed, the reamer rotation speed, the reamer cutting into silt thickness, and the mud pump rotation speed.

[0021] In the case where the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, before the step of obtaining the construction parameters of the cutter suction dredger by solving the mud concentration fitting model of the cutter suction dredger based on the preset optimization algorithm with the preset mud concentration as the optimization target, the method further includes:

[0022] A plurality of different standard forward speeds, reamer rotation speeds, reamer cutting into silt thicknesses, and mud pump rotation speeds are arranged and combined to obtain a plurality of sets of sample construction parameters.

[0023] The sample mud concentration corresponding to each set of sample construction parameters is determined.

[0024] Based on all sample construction parameters and all sample mud concentrations, a sample data set is constructed.

[0025] training the preset neural network model based on the sample data set to obtain a mud concentration fitting model.

[0026] In an embodiment, the preset neural network model comprises a small sample deep learning neural network (DNNSS); neurons of the DNNSS are activated by a ReLU function, the DNNSS is optimized in weight based on an Adam algorithm, and the DNNSS is regularized based on a Dropout function.

[0027] In an embodiment, after the step of obtaining the current mud concentration of the cutter suction dredger, the method further comprises:

[0028] In a case where the concentration difference between the current mud concentration and the preset mud concentration is less than a preset threshold, the cutter suction dredger is controlled to continue operation according to the current construction parameter.

[0029] In addition, to achieve the above-mentioned purpose, the present application also provides a cutter suction dredger control device, which comprises:

[0030] a concentration obtaining module configured to obtain a current mud concentration of the cutter suction dredger;

[0031] a parameter determining model configured to, in a case where the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, solve a mud concentration fitting model of the cutter suction dredger based on a preset optimization algorithm, with the preset mud concentration as an optimization target, to obtain a construction parameter of the cutter suction dredger; wherein the mud concentration fitting model is used to represent a parameter relationship between the construction parameter and the mud concentration;

[0032] a construction control module configured to control the cutter suction dredger to operate based on the construction parameter.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a cutter suction dredger, which comprises a cutter suction dredger control device, the cutter suction dredger control device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the cutter suction dredger control method as described above.

[0034] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, which is a computer readable storage medium, the storage medium storing a computer program, the computer program being executable by a processor to implement the steps of the cutter suction dredger control method as described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which comprises a computer program, the computer program being executable by a processor to implement the steps of the cutter suction dredger control method as described above.

[0036] One or more technical solutions proposed in this application have at least the following technical effects:

[0037] The cutter suction dredger control method proposed in this application can automatically solve a mud concentration fitting model based on a preset optimization algorithm and the optimization target (i.e., the preset mud concentration) when the concentration difference between the current mud concentration and the preset mud concentration of the cutter suction dredger exceeds a preset threshold. This determines the optimal construction parameters for the cutter suction dredger and directly controls its operation based on these parameters. The mud concentration fitting model accurately represents the relationship between construction parameters and mud concentration. Therefore, when the current mud concentration deviates from the preset mud concentration, the optimization algorithm can solve this model to adjust the construction parameters in a timely manner, ensuring that the current mud concentration remains stable near the preset concentration. Through the automated control method of "real-time concentration detection—deviation-triggered optimization—model solving—closed-loop execution," the method can respond more accurately and in real-time to changes in the mud concentration of the cutter suction dredger, avoiding the impact of mud concentration fluctuations caused by frequent changes in operating conditions and geological uncertainties. This improves the stability of the cutter suction dredger operation and ensures operational efficiency. Attached Figure Description

[0038] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is a flowchart illustrating an embodiment of the control method for a cutter suction dredger in this application.

[0041] Figure 2 A schematic diagram showing the RMSE results under different model parameters;

[0042] Figure 3 This is a schematic diagram of the training results of the DNNSS model;

[0043] Figure 4 This is a schematic diagram of the model training results for BP.

[0044] Figure 5 This is a schematic diagram of the RBF model training results;

[0045] Figure 6 This is a schematic diagram of the SVR model training results;

[0046] Figure 7This is a schematic diagram of the training results of the RF model;

[0047] Figure 8 This is a schematic diagram showing the adjustment results based on the forward speed and the reamer speed;

[0048] Figure 9 This is a schematic diagram of the module structure of the cutter suction dredger control device according to an embodiment of this application;

[0049] Figure 10 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the cutter suction dredger control method in the embodiments of this application.

[0050] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0051] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0052] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0053] The main solution of this application embodiment is: to obtain the current mud concentration of the cutter suction dredger; when the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, to use the preset mud concentration as the optimization target, to solve the mud concentration fitting model of the cutter suction dredger based on the preset optimization algorithm, and to obtain the construction parameters of the cutter suction dredger; wherein, the mud concentration fitting model is used to characterize the parameter relationship between the construction parameters and the mud concentration; and to control the operation of the cutter suction dredger based on the construction parameters.

[0054] Cutter suction dredgers, with their advantages of continuous operation, wide adaptability to soil types, and high efficiency, have become one of the most widely used construction equipment in dredging projects. During dredging operations, mud concentration, as a crucial parameter reflecting construction efficiency and resource utilization, directly affects the dredging volume per unit time, energy consumption, and pipeline wear rate. Changes in mud concentration are driven by multiple factors, including cutterhead rotation speed, mud pump rotation speed, suction vacuum, lateral movement speed, propulsion speed, and suction head depth. In related technologies, operators typically set and adjust these construction parameters of the cutter suction dredger based on historical experience to control the mud concentration during operation.

[0055] However, under continuous operation conditions, due to the frequent changes in the working conditions of the dredger and the high uncertainty of the geology, the control method that relies on manual experience to adjust parameters is difficult to respond to the dynamic changes in the dredger's operating conditions in real time. This results in large fluctuations in mud concentration during the operation of the cutter suction dredger, which affects the operational stability of the cutter suction dredger. At the same time, the poor real-time performance of manual control also reduces the overall operating efficiency of the cutter suction dredger.

[0056] This application provides a solution that, when the concentration difference between the current mud concentration and the preset mud concentration of a cutter suction dredger exceeds a preset threshold, automatically solves a mud concentration fitting model based on a preset optimization algorithm and the optimization target (i.e., the preset mud concentration) to determine the optimal construction parameters for the cutter suction dredger, and directly controls the operation of the cutter suction dredger based on these parameters. The mud concentration fitting model accurately represents the relationship between construction parameters and mud concentration. Therefore, when the current mud concentration deviates from the preset mud concentration, the optimization algorithm can solve this mud concentration fitting model to adjust the construction parameters in a timely manner, ensuring that the current mud concentration remains stable near the preset mud concentration. Through the automated control method of "real-time concentration detection—deviation-triggered optimization—model solving—closed-loop execution," the system can respond more accurately and in real-time to changes in the mud concentration of the cutter suction dredger, avoiding the impact of mud concentration fluctuations caused by frequent changes in operating conditions and geological uncertainties, thereby improving the stability of the cutter suction dredger operation and ensuring operational efficiency.

[0057] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer or personal computer, or an electronic device capable of performing the above functions. The following description uses the cutter suction dredger control device (hereinafter referred to as the device) inside the dredger as an example to illustrate this embodiment and the following embodiments.

[0058] Based on this, the embodiments of this application provide a control method for a cutter suction dredger, referring to... Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the cutter suction dredger control method of this application.

[0059] In this embodiment, the cutter suction dredger control method includes steps S100 to S300:

[0060] Step S100: Obtain the current mud concentration of the cutter suction dredger.

[0061] Step S200: When the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, the preset mud concentration is used as the optimization target, and the mud concentration fitting model of the cutter suction dredger is solved based on the preset optimization algorithm to obtain the construction parameters of the cutter suction dredger; wherein, the mud concentration fitting model is used to characterize the parameter relationship between the construction parameters and the mud concentration.

[0062] Step S300: Control the operation of the cutter suction dredger based on construction parameters.

[0063] Specifically, mud concentration reflects the operating status of a cutter suction dredger. By comparing the current mud concentration with the preset mud concentration corresponding to the optimal operating state, it can be determined whether the cutter suction dredger is in a relatively good operating state, so as to adjust the parameters of the cutter suction dredger accordingly. The preset mud concentration is the optimal concentration that ensures the operating efficiency and operating status of the cutter suction dredger. Based on engineering experience, the preset mud concentration can generally be set in the range of 15% to 24%.

[0064] During the dredging process of a cutter suction dredger, the current mud concentration of the dredger can be monitored in real time by a mud concentration sensor installed on the dredger's discharge pipe. If the concentration difference between the current mud concentration and the preset mud concentration exceeds a preset threshold, the preset mud concentration can be used as the optimization target. A preset optimization algorithm can be used to solve a mud concentration fitting model that characterizes the parameter relationship between construction parameters and mud concentration, automatically determining the optimal construction parameters. Based on these construction parameters, the operation of the cutter suction dredger can be controlled to ensure that the mud concentration remains relatively stable during construction. The preset threshold is the allowable deviation between the current mud concentration and the preset mud concentration, which can be determined through technical specifications or construction experience. In practical applications, to ensure real-time parameter control, the preset threshold can be set as small as possible so that the equipment can respond promptly and adjust parameters when a concentration deviation begins to appear between the current and preset mud concentrations.

[0065] The aforementioned mud concentration fitting model is used to describe the potential relationship between construction parameters and mud concentration; it can be a physical mechanism model based on physical laws such as fluid mechanics and soil mechanics that reflects the relationship between mud concentration and construction parameters. For example, mud can be regarded as a solid-liquid two-phase flow, and the relationship between concentration and pump speed and cutter head rotation speed can be established through continuity equations and momentum equations.

[0066] Alternatively, to obtain a more accurate parameter relationship between construction parameters and mud concentration, the mud concentration fitting model can also be trained using multiple sample construction data from a cutter suction dredger to obtain a neural network model. The sample construction data can include sample construction parameters, and the label value of the mud concentration fitting model is mud concentration. It is understood that changes in mud concentration are driven by multiple factors, including key construction parameters such as cutterhead rotation speed, mud pump rotation speed, suction vacuum, lateral speed, propulsion speed, and suction head depth. These construction parameters may exhibit highly nonlinear and dynamically coupled characteristics. The mud concentration fitting model obtained by training a neural network model using sample construction data can effectively capture the nonlinear relationships of these construction parameters, thereby achieving accurate fitting of the mud concentration. In a feasible implementation, steps A100 to A400 can be included before step S200 to obtain the aforementioned mud concentration fitting model.

[0067] Step A100 involves arranging and combining various standard forward speeds, cutter speeds, cutter penetration depths into silt, and mud pump speeds to obtain multiple sets of sample construction parameters.

[0068] Step A200: Determine the mud concentration corresponding to the construction parameters of each sample group.

[0069] Step A300: Construct a sample dataset based on all sample construction parameters and all sample mud concentrations.

[0070] Step A400: Train a preset neural network model based on the sample dataset to obtain a mud concentration fitting model.

[0071] Specifically, based on the construction principles of cutter suction dredgers and relevant engineering experience, it was found that four construction parameters—forward speed, cutterhead rotation speed, cutterhead penetration depth in silt, and slurry pump rotation speed—significantly affect slurry concentration. Forward speed reflects the extent of dredging progress per unit time; cutterhead rotation speed directly affects the intensity of silt disturbance and the cutting rate; cutterhead penetration depth in silt characterizes the depth of cutterhead penetration and the volume of mixing; and slurry pump rotation speed determines the slurry delivery capacity, thus affecting concentration stability. These construction parameters are practically adjustable; therefore, a slurry concentration fitting model can be constructed based on these four parameters.

[0072] Based on the operating specifications and equipment performance of the cutter suction dredger, the reasonable variation range and step size of the above-mentioned construction parameters can be determined. Within the reasonable value range of each construction parameter, the parameters are varied step by step to determine multiple different standards corresponding to each construction parameter. Then, the forward speed, cutter rotation speed, cutter cutting depth into silt, and pump speed of these different standards are arranged and combined to obtain multiple sets of sample construction parameters. The cutter suction dredger is then controlled and monitored in real time based on each set of sample construction parameters to determine the sample mud concentration corresponding to each set of sample construction parameters. All sample construction parameters are mapped to all sample mud concentrations to construct a sample dataset; the sample mud concentration serves as the label value for model training. Using this sample dataset, a preset neural network model is trained to obtain a mud concentration fitting model. The preset neural network model can be SVR (Support Vector Regression), BP (Backpropagation Neural Network), RBF (Radial Basis Function), or RT (Random Forest), etc.

[0073] Alternatively, as an alternative implementation, given the lack of extensive training data on dredged mud concentration from continuous suction dredgers, the pre-defined neural network model can be a few-shot deep learning neural network (DNNSS). DNNSS is a deep learning neural network suitable for small-shot applications. The neurons in DNNSS are activated using the ReLU (Rectified Linear Unit) function. DNNSS uses the Adam (Adaptive Moment Estimation) algorithm for weight optimization and the Dropout function for regularization.

[0074] In the DNNSS model, the ReLU function effectively alleviates the vanishing gradient problem. While the Sigmoid function is commonly used for neuron activation, its gradient approaches zero when the input is large or small, making deep network training difficult. The ReLU function, however, maintains effective gradient propagation, preventing rapid gradient decay. Furthermore, ReLU "turns off" negative inputs, preventing some neurons from participating in computation during training, improving computational efficiency and enhancing model sparsity, thus reducing the impact of gradient vanishing. The Adam algorithm iteratively updates neural network weights and combines first and second moment estimations of the gradient to achieve adaptive learning rate adjustment of neural network parameters, accelerating network convergence. In this embodiment, Adam's hyperparameters can be set to default. Dropout is a regularization method used to prevent overfitting, aiming to reduce overfitting and improve the network's generalization ability. In this embodiment, the Dropout rate can be set to 0.5. The specific DNNSS algorithm can be implemented using compilation software such as MATLAB.

[0075] To facilitate understanding of the mud concentration fitting model training process under the above implementation method, the following example is provided. To ensure the generalization ability of the preset neural network model for multi-condition samples, this example sets three standards for four construction parameters—forward speed, cutter speed, cutter cutting depth into silt, and mud pump speed—combining typical working condition ranges and the actual control range of the cutter suction dredger. To achieve efficient data coverage and combined feature extraction, a full combination experiment was conducted on the three standards of the four construction parameters, generating 81 sets (3... 4 The sample construction parameters have different combinations of values. This method can comprehensively cover the variable space while controlling the number of samples for model training, meeting the requirements of representativeness and breadth for small-sample deep learning. The cutter suction dredger carries out dredging work according to the above-mentioned sample construction parameters with different combinations of values, and obtains the sample mud concentration corresponding to each set of sample construction parameters through on-site monitoring by sensors. The sample mud concentration will be used as the label value for model training. The value standards of each construction parameter are shown in Table 1.

[0076] Table 1 Standards for Construction Parameter Values

[0077]

[0078] After obtaining the construction parameters and corresponding mud concentrations of the 81 sets of samples, a sample dataset can be obtained for model training. Before model training, the data in the sample dataset can be normalized to limit each data point to a specific range, thereby reducing the impact of individual outlier samples or differences in units of measurement on model training. Specifically, standard deviation normalization can be used to ensure the uniformity of data distribution and improve training effectiveness.

[0079] In this example, the parameter values ​​of the DNNSS model were initially tested and filtered, as shown in Table 2.

[0080] Table 2. Range of Model Parameters

[0081] Number of hidden layers Number of neurons Number of iteration steps Random inactivation rate Learning rate 2-20(2) 2-26(2) 10-1610 0.5 0.001

[0082] In Table 2 above, “(2)” indicates that the adjustment step size is 2 when adjusting the number of hidden layers and the number of neurons.

[0083] Based on the optimal training principle, the aforementioned 81 sets of sample data can be used to train DNNSS models with different model parameters, obtaining DNNSS training results under different model parameters. The optimal model parameters can then be selected based on the training results. The training accuracy of the model can generally be evaluated using the root mean square error (RMSE). Figure 2 This is a schematic diagram showing the RMSE results under different model parameters. Figure 2 In this context, Number of Layers represents the number of layers in the neural network, Number of Neurons per Layer represents the number of neurons per layer, and Number of Epochs represents the number of iterations. Figure 2 Different colors in the text correspond to different RMSE values; according to Figure 2 The training results shown in the figure determine the final parameter structure of the DNNSS model. It should be noted that when determining the number of iterations, two conditions can be considered: 1) the RMSE value does not exceed 0.02; 2) the difference between 10 consecutive RMSE values ​​does not exceed 0.005. The final determined DNNSS model parameters are shown in Table 3.

[0084] Table 3 Model Parameters of DNNSS

[0085] Number of hidden layers Number of neurons Number of iteration steps 16 16 530

[0086] Furthermore, to compare the fitting effect of the mud concentration fitting model trained by DNNSS, this example uses the aforementioned sample dataset to train five models: DNNSS, BP, RBF, SVR, and RF, respectively, and uses multiple sets of construction parameters to verify the model training results, as shown below. Figure 3 , Figure 4 , Figure 5 , Figure 6 and Figure 7 The diagram shows the training results of the model. Figure 3 This is a schematic diagram of the DNNSS model training results. Figure 4 This is a schematic diagram of the model training results for BP. Figure 5 This is a schematic diagram of the RBF model training results. Figure 6This is a schematic diagram of the SVR model training results. Figure 7 This is a schematic diagram of the RF model training results. The purple triangles in the diagram represent the predicted mud concentration, i.e., the fitted mud concentration values ​​obtained by the model based on the input construction parameters. The yellow triangles represent the detected mud concentration, i.e., the measured mud concentration values ​​corresponding to the construction parameters. It should be noted that some data points appear on the same vertical line (i.e., perpendicular to the horizontal axis). This is because the measured mud concentration values ​​are the same in some samples. This phenomenon is caused by the inherent characteristics of the data and does not indicate data anomalies. The closer the data points are to the diagonal in the diagram, the better the prediction accuracy. Comparing the schematic diagrams of the model training results of the five models, it is easy to see that the DNNSS model has relatively better prediction accuracy.

[0087] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0088] As mentioned above, during dredging operations, the current mud concentration of the cutter suction dredger can be monitored in real time using mud concentration sensors. If the concentration difference between the current mud concentration and the preset mud concentration exceeds a preset threshold, the preset mud concentration can be used as the optimization target. A preset optimization algorithm is then used to solve the mud concentration fitting model to automatically determine the optimal construction parameters for controlling the cutter suction dredger's operation. For cutter suction dredgers operating for the first time, since they are not yet in operation, it is difficult to monitor the initial mud concentration using mud concentration sensors. In this case, initial construction parameters can be set based on manual experience and input into the aforementioned mud concentration fitting model to determine the corresponding initial mud concentration. If the concentration difference between this initial mud concentration and the preset mud concentration exceeds a preset threshold, the same preset algorithm is used to solve the mud concentration fitting model to determine the optimal construction parameters for controlling the cutter suction dredger's operation. After the cutter suction dredger starts operating, mud concentration sensors are used to monitor mud concentration changes in real time, and the preset optimization algorithm is used to adjust parameters accordingly.

[0089] In one feasible implementation, step S200 may specifically include steps B100 to B400, which are used to perform optimization calculations using a grid search algorithm.

[0090] Step B100: Construct a high-density grid within the target space based on a grid search algorithm; the target space is determined based on a preset safety range of construction parameters, and the high-density grid includes multiple grid points, each grid point corresponding to a set of construction parameters.

[0091] Step B200: For each grid point, input the construction parameters corresponding to the grid point into the mud concentration fitting model to obtain the mud concentration fitting value.

[0092] Step B300: Determine the fitted concentration difference between each fitted mud concentration value and the preset mud concentration.

[0093] Step B400: The construction parameters corresponding to the grid point with the smallest fitted concentration difference are determined as the construction parameters of the cutter suction dredger.

[0094] Specifically, preset safety intervals can be determined for construction parameters such as forward speed, cutter rotation speed, cutter penetration depth into silt, and mud pump rotation speed. These preset safety intervals can constitute a multi-dimensional target space. Within the preset safety intervals of each construction parameter, a high-density grid of points is constructed with a certain step size. The step size for different construction parameters can be the same or different. Taking forward speed, cutter rotation speed, and mud pump rotation speed as examples, the preset safety interval for forward speed is [5, 20] with a step size of 1; the preset safety interval for cutter rotation speed is [10, 30] with a step size of 1; and the preset safety interval for mud pump rotation speed is [400, 800] with a step size of 10. Thus, a high-density three-dimensional grid containing 16 × 21 × 41 = 13776 grid points can be obtained.

[0095] Each grid point represents a different set of construction parameters. The construction parameters corresponding to each grid point are input into the mud concentration fitting model to obtain the corresponding mud concentration fitting value. Then, the fitting concentration difference between each mud concentration fitting value and the preset mud concentration is calculated. The grid point with the smallest fitting concentration difference is selected from all grid points, and the construction parameters corresponding to this grid point are taken as the optimal construction parameters for the cutter suction dredger. The operation control of the cutter suction dredger is then performed based on these construction parameters. In other words, in this embodiment, an optimization calculation is performed using a grid search algorithm. Under the premise of ensuring the feasibility of the cutter suction dredger operation, all possible operating conditions within the preset safety range are traversed. With the preset mud concentration as the optimization target, a set of construction parameter combinations is found that makes the mud concentration fitting value closest to the preset mud concentration required for construction.

[0096] Considering the ease of adjustment of the cutter suction dredger, in a feasible implementation, step S200 may specifically include steps C100 to C400, which are used to adjust parameters based on the forward speed and cutter rotation speed to reduce the computational load of grid search.

[0097] Step C100: Based on the grid search algorithm, a two-dimensional high-density grid is constructed on the two-dimensional plane formed by the first and second safe intervals; the first safe interval is the safe interval corresponding to the forward speed, and the second safe interval is the safe interval corresponding to the reamer rotation speed. The two-dimensional high-density grid includes multiple two-dimensional grid points, and each two-dimensional grid point corresponds to a set of forward speed and reamer rotation speed.

[0098] Step C200: For each two-dimensional grid point, input the current cutter cutter thickness into the silt, the current pump speed, and the forward speed and cutter speed corresponding to the two-dimensional grid point into the mud concentration fitting model to obtain the first mud concentration fitting value.

[0099] Step C300: Determine the first fitted concentration difference between each first mud concentration fitted value and the preset mud concentration.

[0100] Step C400: The forward speed and cutter rotation speed corresponding to the two-dimensional grid point with the smallest first fitted concentration difference, as well as the current cutter cutting into the silt thickness and the current mud pump rotation speed, are determined as the construction parameters of the cutter suction dredger.

[0101] Specifically, in this embodiment, a two-dimensional high-density grid is obtained by dividing the grid based on the first safety interval corresponding to the forward speed and the second safety interval corresponding to the cutter speed. Similar to the aforementioned method, each two-dimensional grid point corresponds to a set of forward speeds and cutter speeds. For each two-dimensional grid point, the forward speed and cutter speed corresponding to that point, along with the current actual cutter depth into the silt and the current pump speed of the cutter suction dredger, are input into the aforementioned slurry concentration fitting model to obtain the corresponding slurry concentration fitting value. Then, the fitting concentration difference between each slurry concentration fitting value and the preset slurry concentration is calculated. The two-dimensional grid point with the smallest fitting concentration difference is selected from all two-dimensional grid points. The forward speed and cutter speed corresponding to this two-dimensional grid point are used as the optimal construction parameters for the cutter suction dredger, and the operation of the cutter suction dredger is controlled in conjunction with the current cutter depth into the silt and the current pump speed.

[0102] Understandably, in this embodiment, the forward speed and cutter rotation speed are combined to optimize parameters on a two-dimensional grid in order to reduce the computational load of the grid search algorithm, thereby quickly determining the construction parameters and improving the control efficiency of the cutter suction dredger.

[0103] During the operation of a cutter suction dredger, if the difference between the current mud concentration and the preset mud concentration is less than the preset threshold, it indicates that the cutter suction dredger is currently in a better operating state. At this time, the cutter suction dredger can be controlled to continue operating according to the current construction parameters without parameter adjustment.

[0104] It is easy to understand that the cutter suction dredger control method provided in this application can automatically solve a mud concentration fitting model based on a preset optimization algorithm and an optimization target (i.e., the preset mud concentration) when the concentration difference between the current mud concentration and the preset mud concentration of the cutter suction dredger is greater than a preset threshold. This determines the optimal construction parameters for the cutter suction dredger and directly controls its operation based on these parameters. The mud concentration fitting model accurately represents the relationship between construction parameters and mud concentration. Therefore, when the current mud concentration deviates from the preset mud concentration, the optimization algorithm can solve this model to adjust the construction parameters in a timely manner, ensuring that the current mud concentration remains stable near the preset concentration. Through the automated control method of "real-time concentration detection—deviation-triggered optimization—model solving—closed-loop execution," the method can respond more accurately and in real-time to changes in the mud concentration of the cutter suction dredger, avoiding the impact of mud concentration fluctuations caused by frequent changes in operating conditions and geological uncertainties. This improves the stability of the cutter suction dredger operation and ensures operational efficiency.

[0105] To aid in understanding the implementation process of the cutter suction dredger control method in this embodiment, the following explanation is provided in conjunction with the aforementioned example:

[0106] Before the cutter suction dredger is put into operation, the initial construction parameters (forward speed V0, cutter speed N0) can be input into the mud concentration fitting model trained by DNNSS in the previous example to predict the mud concentration, thus obtaining the initial mud concentration P0 corresponding to the initial construction parameters. It is then determined whether P0 meets the optimal concentration range (15%–24%), that is, whether the concentration difference between P0 and the preset mud concentration is less than a preset threshold. If the optimal concentration range is met, the initial construction parameters are used as the current optimal parameters (forward speed Vb, cutter speed Nb), and the corresponding mud concentration is used as the current optimal mud concentration Pb. At this point, the cutter suction dredger can be controlled to continue operating with the current construction parameters to maintain the current construction state. If the optimal range is not met, the search range near the initial construction parameters (V0, N0) is determined according to the nearest neighbor optimum principle. The step size of the two parameters can be determined according to the parameter range adjusted by the cutter suction dredger (i.e., the preset safety range). The step sizes for the forward speed and cutter speed are 0.2 m / min and 2 r / min, respectively. The preset optimization algorithm described in the aforementioned embodiments is used to solve the mud concentration fitting model, traversing all combinations of construction parameters within two parameter ranges. The actual mud concentration during operation is determined by monitoring the operation using sensors on the cutter suction dredger. Table 4 shows the initial state and the construction parameters and mud concentration after the above parameter optimization adjustment. As shown in Table 4, number 1 represents the initial state, and number 2 represents the state after parameter optimization adjustment. In the initial state, the mud concentration is 13%, which does not meet the optimal state's concentration range of 15% to 24%. Therefore, the construction parameters need to be adjusted autonomously using the optimization algorithm and the mud concentration fitting model. After parameter optimization adjustment, the mud concentration is 15.07%, which is within the optimal state's concentration range. Figure 8 This is a schematic diagram showing the adjustment results based on the forward speed and the reamer speed. Figure 8 Different colors correspond to different mud concentrations. Based on a mud concentration fitting model, and combined with grid search and adaptive optimization strategies, the construction parameters are dynamically optimized. This method can adjust key construction parameters (such as forward speed and cutterhead rotation speed) based on real-time monitoring of the current mud concentration without affecting operational efficiency, to ensure that the mud concentration remains stable within the optimal target range.

[0107] Table 4 Initial state and construction parameters and mud concentration after parameter optimization adjustment

[0108]

[0109] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the control method of the cutter suction dredger in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0110] This application also provides a control device for a cutter suction dredger; please refer to [reference needed].Figure 9 The control system for a cutter suction dredger includes:

[0111] Concentration acquisition module 10 is used to acquire the current mud concentration of the cutter suction dredger;

[0112] The parameter determination model 20 is used to solve the mud concentration fitting model of the cutter suction dredger based on a preset optimization algorithm when the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, with the preset mud concentration as the optimization target, to obtain the construction parameters of the cutter suction dredger; wherein, the mud concentration fitting model is used to characterize the parameter relationship between the construction parameters and the mud concentration.

[0113] Construction control module 30 is used to control the operation of the cutter suction dredger based on construction parameters.

[0114] The cutter suction dredger control device provided in this application, employing the cutter suction dredger control method described in the above embodiments, can solve the technical problem in related technologies where the real-time control of cutter suction dredgers is poor, affecting the stability and efficiency of dredger operations. Compared with related technologies, the beneficial effects of the cutter suction dredger control device provided in this application are the same as those of the cutter suction dredger control method provided in the above embodiments, and other technical features in the above cutter suction dredger control device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0115] This application provides a dredger, which includes a cutter suction dredger control device. The cutter suction dredger control device may include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the cutter suction dredger control method in the first embodiment described above.

[0116] The following is for reference. Figure 10 The diagram illustrates a structural schematic of a control device suitable for implementing the embodiments of this application. The control device for the cutter suction dredger in the embodiments of this application may include, but is not limited to, mobile terminals such as laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), etc., and fixed terminals such as desktop computers. Figure 10 The cutter suction dredger control equipment shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0117] like Figure 10As shown, the cutter suction dredger control equipment may include a processing unit 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the cutter suction dredger control equipment. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the cutter suction dredger control equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a cutter suction dredger control equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0118] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0119] The dredger provided in this application, employing the cutter suction dredger control method described in the above embodiments, can solve the technical problem in related technologies where the real-time control of cutter suction dredgers is poor, affecting the stability and efficiency of dredger operations. Compared with related technologies, the beneficial effects of the dredger provided in this application are the same as those of the cutter suction dredger control method provided in the above embodiments, and other technical features of this dredger are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0120] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0121] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0122] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the cutter suction dredger control method in the above embodiments.

[0123] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0124] The aforementioned computer-readable storage medium may be included in the control equipment of the cutter suction dredger; or it may exist independently and not be assembled into the control equipment of the cutter suction dredger.

[0125] The aforementioned computer-readable storage medium carries one or more programs. When these programs are executed by the cutter suction dredger control equipment, the cutter suction dredger control equipment: acquires the current mud concentration of the cutter suction dredger; when the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, it uses the preset mud concentration as the optimization target and solves the mud concentration fitting model of the cutter suction dredger based on a preset optimization algorithm to obtain the construction parameters of the cutter suction dredger; wherein, the mud concentration fitting model is used to characterize the parameter relationship between the construction parameters and the mud concentration; and controls the operation of the cutter suction dredger based on the construction parameters.

[0126] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0127] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0128] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0129] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., computer programs) for executing the above-described cutter suction dredger control method. This solves the technical problem in related technologies where the real-time control of cutter suction dredgers is poor, affecting the stability and efficiency of dredger operations. Compared with related technologies, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the cutter suction dredger control method provided in the above embodiments, and will not be elaborated upon here.

[0130] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the cutter suction dredger control method described above.

[0131] The computer program product provided in this application can solve the technical problem in related technologies where the real-time control of cutter suction dredgers is poor, affecting the stability and efficiency of dredger operations. Compared with related technologies, the beneficial effects of the computer program product provided in this application are the same as those of the cutter suction dredger control method provided in the above embodiments, and will not be repeated here.

[0132] The above description is only a part of the embodiments of this application and does not limit the scope of protection. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included within the scope of protection.

Claims

1. A control method for a cutter suction dredger, characterized in that, The control method for the cutter suction dredger includes: Obtain the current mud concentration of the cutter suction dredger; When the difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, the preset mud concentration is used as the optimization target, and the mud concentration fitting model of the cutter suction dredger is solved based on the preset optimization algorithm to obtain the construction parameters of the cutter suction dredger; wherein, the mud concentration fitting model is used to characterize the parameter relationship between the construction parameters and the mud concentration. The operation of the cutter suction dredger is controlled based on the construction parameters.

2. The control method for a cutter suction dredger as described in claim 1, characterized in that, The step of obtaining the construction parameters of the cutter suction dredger by solving the mud concentration fitting model of the cutter suction dredger based on a preset optimization algorithm with the preset mud concentration as the optimization target includes: A high-density grid is constructed within the target space based on a grid search algorithm; the target space is determined based on a preset safety range of the construction parameters; the high-density grid includes multiple grid points, and each grid point corresponds to a set of construction parameters. For each grid point, the construction parameters corresponding to the grid point are input into the mud concentration fitting model to obtain the mud concentration fitting value. Determine the fitted concentration difference between each of the aforementioned mud concentration fitted values ​​and the preset mud concentration; The construction parameters corresponding to the grid point with the smallest fitted concentration difference are determined as the construction parameters of the cutter suction dredger.

3. The control method for a cutter suction dredger as described in claim 1, characterized in that, The construction parameters include forward speed, cutter speed, cutter cutting depth into silt, and mud pump speed. The step of obtaining the construction parameters of the cutter suction dredger by solving the mud concentration fitting model of the cutter suction dredger based on a preset optimization algorithm with the preset mud concentration as the optimization target includes: A two-dimensional high-density grid is constructed on a two-dimensional plane formed by a first safety zone and a second safety zone based on a grid search algorithm; the first safety zone is the safety zone corresponding to the forward speed, and the second safety zone is the safety zone corresponding to the reamer rotation speed. The two-dimensional high-density grid includes multiple two-dimensional grid points, and each two-dimensional grid point corresponds to a set of forward speed and reamer rotation speed. For each of the two-dimensional grid points, the current cutter cut into the silt thickness, the current pump speed, and the forward speed and cutter speed corresponding to the two-dimensional grid point are input into the mud concentration fitting model to obtain the first mud concentration fitting value. Determine the first fitted concentration difference between each of the first mud concentration fitted values ​​and the preset mud concentration; The forward speed and cutter rotation speed corresponding to the two-dimensional grid point with the smallest first fitted concentration difference, as well as the current cutter cutting into the silt thickness and the current mud pump rotation speed, are determined as the construction parameters of the cutter suction dredger.

4. The control method for a cutter suction dredger as described in claim 1, characterized in that, The construction parameters include forward speed, cutter speed, cutter cutting depth into silt, and mud pump speed. Before the step of obtaining the construction parameters of the cutter suction dredger by solving the mud concentration fitting model of the cutter suction dredger based on a preset optimization algorithm when the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, the method further includes: Multiple sets of sample construction parameters were obtained by arranging and combining various standard forward speeds, cutter speeds, cutter cutting depths into silt, and mud pump speeds. Determine the mud concentration corresponding to the construction parameters of each group of samples; A sample dataset is constructed based on all the sample construction parameters and all the sample mud concentrations; A preset neural network model is trained based on the sample dataset to obtain the mud concentration fitting model.

5. The control method for a cutter suction dredger as described in any one of claims 4, characterized in that, The preset neural network model includes a few-shot deep learning neural network DNNSS; the neurons of the DNNSS are activated using the ReLU function, the DNNSS performs weight optimization based on the Adam algorithm, and the DNNSS performs regularization based on the Dropout function.

6. The control method for a cutter suction dredger as described in any one of claims 1 to 5, characterized in that, After the step of obtaining the current mud concentration of the cutter suction dredger, the method further includes: If the concentration difference between the current mud concentration and the preset mud concentration is less than a preset threshold, the cutter suction dredger is controlled to continue operating according to the current construction parameters.

7. A control device for a cutter suction dredger, characterized in that, The cutter suction dredger control device includes: The concentration acquisition module is used to acquire the current mud concentration of the cutter suction dredger. A parameter determination model is used to solve the mud concentration fitting model of the cutter suction dredger based on a preset optimization algorithm when the concentration difference between the current mud concentration and the preset mud concentration is greater than a preset threshold, with the preset mud concentration as the optimization target, to obtain the construction parameters of the cutter suction dredger; wherein, the mud concentration fitting model is used to characterize the parameter relationship between the construction parameters and the mud concentration. The construction control module is used to control the operation of the cutter suction dredger based on the construction parameters.

8. A dredger, characterized in that, The dredger includes a cutter suction dredger control device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The computer program is configured to implement the steps of the cutter suction dredger control method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the cutter suction dredger control method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the cutter suction dredger control method as described in any one of claims 1 to 6.

Images