Dredging ship control method and device based on Soft-PLC, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a soft-PLC-based dredging ship control method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a latest strategy network of a dredging operation reinforcement learning model based on a reward function; acquiring a real-time state space of a dredging operation reinforcement learning model based on the real-time first state parameter of the dredging ship; acquiring a real-time action space of the dredging operation reinforcement learning model based on the historical first state parameter and the real-time first state parameter of the dredging ship; based on the real-time state space and the real-time action space, current optimal operation parameters of the dredging ship are obtained through a latest strategy network of the dredging operation reinforcement learning model to serve as current optimal action of the dredging operation reinforcement learning model; and on the basis of the current optimal operation parameters, the dredging ship is controlled in real time through the Soft-PLC. The dredging ship can be automatically controlled by fusing expert experience, and the dredging operation efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of ship control technology, and in particular to a dredging vessel control method, device, electronic equipment and storage medium based on Soft-PLC. Background Technology

[0002] In existing technologies, the control of dredging vessels relies on operators manually adjusting dredging operation parameters based on their experience. Due to the real-time and ever-changing conditions such as soil quality and water flow at the dredging site, manual response is inherently delayed and judgment is difficult to make accurately. Furthermore, operation parameters such as lateral movement speed and cutter / mud pump speed are interdependent, making it difficult for humans to simultaneously achieve the optimal global match, often resulting in some aspects being overlooked. In addition, subjective factors such as the operator's experience and condition lead to poor operational consistency, and in order to avoid equipment failure, conservative adjustment strategies are often adopted, frequently sacrificing the theoretical maximum efficiency, thus resulting in poor dredging efficiency. Summary of the Invention

[0003] This invention provides a dredging vessel control method, device, electronic equipment, and storage medium based on Soft-PLC, which can automatically control dredging vessels by integrating expert experience and improve dredging operation efficiency.

[0004] In a first aspect, embodiments of the present invention provide a dredging vessel control method based on Soft-PLC, comprising:

[0005] The latest policy network of the reinforcement learning model for dredging operations is obtained based on the reward function. The reward function includes an expert experience term, which is a piecewise decision function of action conditions with the optimal action of the sample as the independent variable. The decision triggering conditions and branch action conditions of the piecewise decision function of action conditions are obtained based on historical expert experience.

[0006] The real-time state space of the reinforcement learning model for dredging operations is obtained based on the real-time first state parameters of the dredging vessel.

[0007] The real-time action space of the dredging operation reinforcement learning model is obtained based on the historical first state parameters and real-time first state parameters of the dredging vessel.

[0008] Based on the real-time state space and real-time action space, the current optimal operating parameters of the dredging vessel are obtained through the state-of-the-art policy network of the dredging operation reinforcement learning model, which serves as the current optimal action of the dredging operation reinforcement learning model; and

[0009] The dredging vessel is controlled in real time using a Soft-PLC based on the current optimal operating parameters.

[0010] Secondly, embodiments of the present invention provide a dredging vessel control device based on Soft-PLC, comprising:

[0011] The network update module is used to obtain the latest policy network of the dredging operation reinforcement learning model based on the reward function. The reward function includes an expert experience term, which is an action condition piecewise decision function with the optimal action of the sample as the independent variable. The decision triggering conditions and branch action conditions of the action condition piecewise decision function are obtained based on historical expert experience.

[0012] The real-time state space acquisition module is used to acquire the real-time state space of the dredging operation reinforcement learning model based on the real-time first state parameters of the dredging vessel.

[0013] The real-time action space acquisition module is used to acquire the real-time action space of the dredging operation reinforcement learning model based on the historical first state parameters and real-time first state parameters of the dredging vessel.

[0014] The optimal operation parameter acquisition module is used to obtain the current optimal operation parameters of the dredging vessel through the latest policy network of the dredging operation reinforcement learning model based on the real-time state space and real-time action space, as the current optimal action of the dredging operation reinforcement learning model; and

[0015] The real-time control module is used to control the dredging vessel in real time using a Soft-PLC based on the current optimal operating parameters.

[0016] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the Soft-PLC-based dredging vessel control method as described in any of the embodiments of the present invention.

[0017] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the dredging vessel control method based on Soft-PLC as described in any of the embodiments of the present invention.

[0018] This invention provides a dredging vessel control method, device, electronic equipment, and storage medium based on Soft-PLC. It determines the optimal parameters of the dredging vessel using a reinforcement learning model and controls the dredging process in real time based on these optimal parameters using a Soft Programmable Logic Controller (Soft-PLC). This eliminates the need for manual adjustment of data operation parameters, avoiding the lag in manual response and improving the accuracy of judgment. This allows for timely and precise adjustment of dredging operation parameters. Furthermore, this invention incorporates expert experience into the reward function of the reinforcement learning model, enabling the automatic control process to integrate expert experience. This effectively learns and solidifies the implicit operational experience accumulated by experts, preventing the loss of operational knowledge due to personnel turnover. Therefore, it can automatically, accurately, and efficiently control the dredging operation process of the dredging vessel, improving dredging efficiency. Attached Figure Description

[0019] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic flowchart of a dredging vessel control method based on Soft-PLC provided in an embodiment of the present invention;

[0021] Figure 2 This is another schematic diagram of the dredging vessel control method based on Soft-PLC provided in the embodiment of the present invention;

[0022] Figure 3 This is another schematic diagram of the dredging vessel control method based on Soft-PLC provided in the embodiment of the present invention;

[0023] Figure 4 This is another schematic diagram of the dredging vessel control method based on Soft-PLC provided in the embodiment of the present invention;

[0024] Figure 5 This is a schematic diagram of a dredging vessel control device based on Soft-PLC provided in an embodiment of the present invention;

[0025] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Figure 1 This is a flowchart illustrating a Soft-PLC-based dredging vessel control method provided in an embodiment of the present invention. This method can be executed by a Soft-PLC-based dredging vessel control device provided in this embodiment, which can be implemented using software and / or hardware. In a specific embodiment, this device can be integrated into an electronic device, such as a computer or server. The following embodiments will illustrate this using the integration of the device into an electronic device as an example. (Reference) Figure 1 The method may specifically include the following steps:

[0029] Step 101: Obtain the latest policy network of the dredging operation reinforcement learning model based on the reward function. The reward function includes an expert experience term, which is a piecewise decision function of action conditions with the optimal action of the sample as the independent variable. The decision triggering conditions and branch action conditions of the piecewise decision function of action conditions are obtained based on historical expert experience. This step can help integrate expert experience into the decision-making process of the reinforcement learning model and solidify implicit operational experience knowledge.

[0030] Specifically, the dredging vessel in this embodiment of the invention can be a cutter suction dredger or a trailing suction dredger.

[0031] Specifically, the aforementioned reinforcement learning model for dredging operations can be a Deep Deterministic Policy Gradient (DDPG) algorithm model or a Soft Actor-Critic (SAC) algorithm model, etc.

[0032] Specifically, the process of obtaining the latest policy network of the dredging operation reinforcement learning model based on the reward function may include: obtaining the reward of the best action of the sample based on the reward function; evaluating the action value of the best action of the sample through the value network of the dredging operation reinforcement learning model based on the reward of the best action of the sample; and optimizing and updating the policy network based on the action value of the best action of the sample to obtain the latest policy network.

[0033] Specifically, embodiments of the present invention can also optimize and update the value network to obtain the latest value network, which is beneficial for further optimization of the policy network.

[0034] Specifically, the optimal action of the above sample can be the historical optimal action taken by the dredging operation reinforcement learning model during the dredging operation, or the simulated optimal action taken by the dredging operation reinforcement learning model during the simulated dredging operation.

[0035] Specifically, the process of optimizing and updating the policy network based on the action value of the best action in the sample to obtain the latest policy network can include: performing multi-step optimization training on the network parameters of the policy network based on the action value of the best actions in multiple samples to obtain optimized policy network parameters, and copying the optimized policy network parameters to the policy network once to obtain the latest policy network; or copying the optimized policy network parameters to the policy network multiple times to obtain the latest policy network.

[0036] Specifically, the aforementioned expert experience term can be understood as: a component of the reward function used to provide immediate, high rewards for actions performed by the reinforcement learning model for dredging operations that conform to expert experience.

[0037] Specifically, the reward function mentioned above may also include: output revenue, energy consumption penalty, and / or failure penalty.

[0038] Specifically, the aforementioned output benefit can be understood as a component of the reward function that is a quantitative indicator that directly measures the actual value obtained by the reinforcement learning model for dredging operations after performing specific actions to achieve the core objective of the task.

[0039] Specifically, the aforementioned energy consumption penalty term can be understood as a negative feedback applied after quantifying the energy consumption generated by the reinforcement learning model of dredging operations performing specific actions, in order to guide it to reduce unnecessary energy consumption.

[0040] Specifically, the aforementioned fault penalty term can be understood as a component of the reward function that quantifies and applies negative feedback to the reinforcement learning model of dredging operations, which may lead to abnormal states that do not meet safety / performance requirements when performing specific actions, in order to constrain it to avoid faults and ensure operational stability.

[0041] In a specific example, the dredging vessel is a cutter suction dredger, and the reward function can be expressed as:

[0042]

[0043] in, , and The corresponding weighting coefficients for output benefit items, energy consumption penalty items, and failure penalty items can be set based on empirical data or based on the results of multiple experiments. The actual benefit coefficient per unit lateral distance; Indicates the actual lateral speed; This indicates the real-time operating current of the auger. Indicates the rated current of the auger; Indicates an indicator function; This represents the first real-time state parameter; Threshold represents the state parameter threshold.

[0044] In a specific instance, the expert experience item can be represented as:

[0045]

[0046] Where A represents the specific action performed by the reinforcement learning model for dredging operations; S represents the environmental state when the reinforcement learning model for dredging operations performs the specific action. This represents the environmental state corresponding to the expert's experience; Action represents the action corresponding to the expert's experience. This indicates outdated actions that have not drawn on the experience of experts. and This indicates a high-weighting coefficient that is significantly greater than the normal reward value; for example, it could be 100 times. This is to ensure that the model can quickly perceive the importance of the expert's experience.

[0047] Step 102: Obtain the real-time state space of the dredging operation reinforcement learning model based on the real-time first state parameters of the dredging vessel. This step can further obtain the current optimal action of the dredging operation reinforcement learning model based on the real-time state space.

[0048] Specifically, when the dredging vessel is a cutter suction dredger, the aforementioned real-time first state parameter may include: the cutter current of the cutter suction dredger ( ), mud concentration ( ), mud pump suction vacuum ( ), lateral pressure ( ).

[0049] Specifically, when the dredging vessel is a trailing suction hopper dredger, the aforementioned real-time first state parameter may include: the vacuum degree of the dredging head suction (…). ), hull heave amplitude ( ) and mud concentration ( ).

[0050] Specifically, the process of obtaining the real-time state space of the dredging operation reinforcement learning model based on the real-time first state parameters of the dredging vessel includes: preprocessing the real-time first state parameters, specifically by cleaning and standardizing them to obtain preprocessed real-time first state parameters; and mapping the preprocessed real-time first state parameters to the input space of the dredging operation reinforcement learning model to obtain a real-time state space including the state space parameters corresponding to the real-time first state parameters.

[0051] Step 103: Obtain the real-time action space of the dredging operation reinforcement learning model based on the historical and real-time first state parameters of the dredging vessel. This step accurately determines the real-time action space of the dredging operation reinforcement learning model and facilitates obtaining the current optimal action of the dredging operation reinforcement learning model based on the real-time action space.

[0052] Specifically, the aforementioned historical first state parameters can include the latest historical first state parameters, which can be historical first state parameters within a certain period of time. This certain period of time can be set based on empirical data or based on the results of multiple trials.

[0053] Specifically, in order to maintain the stability of the state parameters, the process of obtaining the real-time action space of the dredging operation reinforcement learning model based on the historical first state parameters and the real-time first state parameters of the dredging vessel may include: determining the range of possible values ​​for the operation parameters based on the change of the real-time first state parameters of the dredging vessel relative to the latest historical first state parameters, and mapping the range of possible values ​​for the operation parameters to the output action space of the dredging operation reinforcement learning model to obtain the aforementioned real-time action space.

[0054] Specifically, the process of determining the selectable value range of the operation parameters based on the change of the real-time first state parameter of the dredging vessel relative to the latest historical first state parameter may include, for example, setting the selectable value range of the corresponding operation parameter to a range of values ​​that can increase the real-time first state parameter when the real-time first state parameter decreases relative to the latest historical first state parameter; and setting the selectable value range of the corresponding operation parameter to a range of values ​​that can decrease the real-time first state parameter when the real-time first state parameter increases relative to the latest historical first state parameter.

[0055] Step 104: Based on the real-time state space and real-time action space, the current optimal operating parameters of the dredging vessel are obtained through the latest policy network of the dredging operation reinforcement learning model, which serves as the current optimal action of the dredging operation reinforcement learning model. This step can efficiently and accurately obtain the current optimal operating parameters of the dredging vessel.

[0056] Specifically, the aforementioned current optimal job parameters can be understood as the current optimal job parameters.

[0057] Specifically, when the dredging vessel is a cutter suction dredger, the operating parameters may include the vessel's lateral speed, as well as the mud pump speed and / or cutter speed.

[0058] Specifically, when the dredging vessel is a trailing suction hopper dredger, the operating parameters may include the vessel's towing speed and the mud pump speed.

[0059] Specifically, the process of obtaining the current optimal action of the dredging operation reinforcement learning model through the latest policy network based on the real-time state space and the real-time action space includes: obtaining the current state features corresponding to the state space parameters in the real-time state space, inputting the current state features into the policy network, and the policy network outputting the current optimal action within the constraint boundary of the real-time action space based on the current state features.

[0060] Step 105: Based on the current optimal operating parameters, the dredging vessel is controlled in real time via Soft-PLC. Building upon steps 101 to 104, this step automatically adjusts the data operating parameters without relying on manual intervention, avoiding the lag in manual response and improving the accuracy of judgment. This allows for timely and precise adjustments to dredging operating parameters. Furthermore, the automatic control process integrates expert experience, effectively learning and solidifying the implicit operational experience accumulated by experts, preventing the loss of operational knowledge with personnel turnover. This enables automatic, precise, and efficient control of the dredging vessel's dredging operations, improving dredging efficiency.

[0061] Specifically, the process of real-time control of the dredging vessel by Soft-PLC based on the current optimal operating parameters may include real-time control of the dredging vessel by Soft-PLC based solely on the current optimal operating parameters, or it may include real-time control of the dredging vessel by Soft-PLC based on the current operating parameters and other types of control parameters, such as attitude adjustment parameters.

[0062] Specifically, the process of real-time control of the dredging vessel using Soft-PLC based on the current optimal operating parameters may include: converting the current optimal operating parameters into equipment control parameters based on a pre-set operating equipment parameter mapping table or a proportional-integral-derivative (PID) control algorithm, and controlling the operating control equipment of the dredging vessel based on the equipment control parameters.

[0063] In a specific example, the current optimal operation parameter is "lateral movement speed 1.2 m / min", and the above operation parameter mapping table is shown in Table 1:

[0064]

[0065] Then, look up Table 1 to obtain the target frequency of the drive motor and the opening degree of the hydraulic valve corresponding to the lateral speed of 1.2m / min, and obtain the equipment control parameters.

[0066] Specifically, the process of real-time control of the dredging vessel using Soft-PLC based on the current optimal operating parameters can include directly updating the corresponding control parameters to the current optimal operating parameters in real time using Soft-PLC, and then controlling the dredging vessel in real time based on the current optimal operating parameters; or it can involve verifying the current optimal operating parameters, and after successful verification, updating the corresponding control parameters to the current optimal operating parameters in real time using Soft-PLC, and then controlling the dredging vessel in real time based on the current optimal operating parameters.

[0067] Specifically, dredging vessels can also be controlled in real time based on edge controllers.

[0068] The following further describes the dredging vessel control method based on Soft-PLC provided by embodiments of the present invention, such as... Figure 2 As shown, that is Figure 1 Step 103 may include the following steps:

[0069] Step 1031: Predict the normal range value of the real-time first state parameter based on the historical first state parameter.

[0070] Specifically, the normal range value of a real-time first state parameter can be one value or multiple values.

[0071] Optionally, the process of predicting the normal range value of the real-time first state parameter based on the historical first state parameter includes: obtaining the normal range value of the real-time first state parameter through a state parameter normal value range prediction model based on the time series of the latest historical first state parameter.

[0072] Specifically, the above-mentioned normal value range prediction model for state parameters can be obtained by training the time series model based on multiple sets of sample training data. Each set of sample training data can include the sample state parameters and the normal value range of the state parameters at the nearest future time corresponding to the sample state parameters.

[0073] Specifically, the aforementioned time series models can be, for example, Long Short-Term Memory (LSTM) networks or Autoregressive Integrated Moving Average (ARIMA) models.

[0074] Specifically, the network structure of the aforementioned time series model can adopt the network structure in the existing technology, or it can be set according to needs.

[0075] In a specific instance, the dredging vessel is a cutter suction dredger, and the time series of the latest historical first state parameters can be represented as follows: in Predictive model based on normal range of state parameters The process of predicting the normal range values ​​of the real-time first state parameters can be represented as: ,in This indicates the normal range value of the real-time first state parameter.

[0076] Specifically, the process of predicting the normal range value of the real-time first state parameter based on the historical first state parameter may also include: obtaining the historical first state parameter under the same or similar historical operating conditions as the real-time operating conditions, and using it as the normal range value of the real-time operating parameter.

[0077] Step 1032: If the real-time first state parameter does not deviate from the normal range value, then obtain the real-time action space based on the real-time operation parameter.

[0078] Optionally, before step 1032, it can be determined whether the real-time first state parameter deviates from the normal value range based on the Mahalanobis distance or mean square error between the real-time state parameter vector corresponding to each real-time first state parameter and the normal range value vector corresponding to the normal range value.

[0079] Specifically, when the Mahalanobis distance is greater than a preset Mahalanobis distance threshold, or the mean square error is greater than a preset mean square error threshold, it can be determined that the real-time first state parameter deviates from the normal range.

[0080] Specifically, before step 1032, it can be determined whether the first state parameter deviates from the normal value range in the following way: for each real-time first state parameter, determine the normal value range of the current real-time first state parameter based on the corresponding normal range value; if the current real-time first state parameter is within the corresponding normal value range, it is determined that the current real-time first state parameter has not deviated from the normal range value; if the current real-time first state parameter is not within the corresponding normal value range, it is determined that the current real-time first state parameter deviates from the normal range value; when all real-time first state parameters deviate from the normal range value, it is determined that the first state parameter deviates from the normal range value; when all or some real-time first state parameters do not deviate from the normal range value, it is determined that the first state parameter deviates from the normal range value.

[0081] Step 1033: If the real-time first status parameter deviates from the normal range, query the status job parameter mapping table to obtain the first possible value range of the job parameter corresponding to the real-time first status parameter.

[0082] Specifically, the state operation parameter mapping table can store the first possible value range corresponding to the first state parameter in different ranges.

[0083] In a specific example, the dredging vessel is a cutter suction dredger, and the state operation parameter mapping table is shown in Table 2:

[0084]

[0085] In a specific example, the dredging vessel is a cutter suction dredger, and the state operation parameter mapping table is shown in Table 3:

[0086]

[0087] Step 1034: Obtain the real-time motion space based on the first possible value range of the job parameters.

[0088] Specifically, the process of obtaining the real-time action space based on the first possible value range of the operation parameters includes: directly determining the first possible value range as the optional value range of the operation parameters, and obtaining the real-time action space based on the optional value range of the operation parameters.

[0089] Specifically, before obtaining the real-time action space based on the first possible value range of the operation parameters, a second possible value range can be determined based on the range of operation parameters determined during ship design. The process of obtaining the real-time action space based on the first possible value range of the operation parameters includes: taking the intersection of the first possible value range and the second possible value range to obtain the above-mentioned selectable value range.

[0090] In a specific instance, the first possible range of values ​​for the ship's lateral speed. The second possible value range is Then, taking the intersection of the above two values ​​yields the possible range of values ​​for the ship's lateral speed. .

[0091] It is understandable that existing technologies typically rely on hard thresholds of ship status parameters for anomaly diagnosis and fault alarms. However, most equipment anomalies evolve gradually, but hard thresholds are usually set at the critical value of the fault, making it impossible to capture early minor anomalies and execute corresponding control strategies. This leads to a high rate of unplanned downtime of dredging equipment and severe wear and tear. This embodiment predicts the normal range value of the first status parameter based on its historical value, and then identifies anomalies and adjusts operating parameters based on the normal range value. This enables the capture of early minor anomalies and the execution of corresponding control strategies, thereby reducing the rate of unplanned downtime of dredging equipment and mitigating wear and tear.

[0092] The following further describes the dredging vessel control method based on Soft-PLC provided by the embodiments of the present invention, such as... Figure 3 As shown, it may include the following steps:

[0093] Step 301: Obtain the latest policy network of the dredging operation reinforcement learning model based on the reward function.

[0094] Step 302: Obtain the real-time state space of the dredging operation reinforcement learning model based on the real-time first state parameters of the dredging vessel.

[0095] Step 303: Obtain the real-time action space of the dredging operation reinforcement learning model based on the historical first state parameters and real-time first state parameters of the dredging vessel.

[0096] Step 304: Based on the real-time state space and real-time action space, obtain the current optimal operation parameters of the dredging vessel through the latest policy network of the dredging operation reinforcement learning model as the current optimal action of the dredging operation reinforcement learning model.

[0097] Step 305: Obtain the latest expert control instructions and convert them into structured text language through a code generation model to obtain the latest expert suggestion control code.

[0098] Specifically, the aforementioned latest expert control commands can be either voice commands or text commands.

[0099] In a specific instance, the latest expert instruction stated that "if the cutter current is greater than 80% and the mud concentration is less than 150 g / L, increase the cutter speed by 15% within 1 second."

[0100] Specifically, before converting the latest expert control instructions into structured text language through a code generation model, a natural language processing parser can be used to decompose the instructions into structured rules that include intent, condition, action, and priority items. Intent, condition, action, and priority items can be represented by Intent, Content, Action, and Priority, respectively.

[0101] In a specific instance, structured rules The intent is: strategy update; the condition is: cutter current greater than 80% and mud concentration less than 150g / L; the action is: cutter speed increased by 15%; and the priority is: high priority (1s response). Specifically, this can be represented as:

[0102] .

[0103] Specifically, the process of converting the latest expert control instructions into a structured text language through a code generation model can include: generating the latest expert-recommended control code based on structured rules and the structured language specification of the soft programmable logic controller through a code generation model.

[0104] Specifically, the aforementioned natural speech processor can be a natural language processor in the prior art, such as a natural speech processor based on the Transformer / BERT architecture, specifically a bidirectional and auto-regressive Transformer (BART) or a text-to-text transfer Transformer (T5).

[0105] Specifically, the code generation model mentioned above can be a code generation model in the prior art, such as the T5-Industrial-PLC model and the BART-PLC model.

[0106] Step 306: Obtain the review results of the reviewers on the latest expert recommendations for controlling the code through the code review channel.

[0107] Specifically, the process of obtaining the review results of the latest expert-recommended control code through the code review channel includes: verifying whether the latest expert-recommended control code will introduce new security risks or conflict with existing hard interlocks.

[0108] Step 307: When the review result of the latest expert-recommended control code is approved, the dredging vessel is controlled in real time via Soft-PLC based on the latest expert-recommended control code and the current optimal operating parameters.

[0109] Specifically, when the latest expert recommendation for the control code is rejected, the dredging vessel will be controlled in real time via Soft-PLC based solely on the current optimal operating parameters.

[0110] Specifically, the process of real-time control of the dredging vessel using Soft-PLC based on the latest expert-recommended control code and the current optimal operating parameters includes: compiling the latest expert-recommended control code and inserting it into the real-time control loop of the dredging vessel.

[0111] Specifically, the steps described above, which compile the latest expert advice control code and insert it into the real-time control loop of the dredging vessel, can be performed through high-priority tasks or function blocks.

[0112] The embodiments of the present invention can structure rules Recorded in the system knowledge base of the dredging vessel.

[0113] Optionally, the dredging vessel control method based on Soft-PLC provided in this embodiment of the invention further includes: updating the decision triggering conditions and branch action conditions based on the latest expert control instructions.

[0114] Specifically, the process of updating the decision triggering conditions and branch action conditions based on the latest expert control instructions includes: obtaining structured rules from the system knowledge base, and generating the latest decision triggering conditions and branch action conditions based on the structured rules.

[0115] Specifically, the process of generating the latest decision triggering conditions and branch action conditions based on structured rules includes: determining the latest decision triggering conditions based on the condition items in the structured rules, and determining the latest branch action conditions based on the action items in the structured rules.

[0116] The embodiments of the present invention can facilitate the timely integration of the latest expert experience into the control of dredging vessels, thereby further improving the accuracy of subsequent control of dredging vessels.

[0117] The following further illustrates the Soft-PLC-based dredging vessel control method provided by the embodiments of the present invention, such as... Figure 4 As shown, it may include the following steps:

[0118] Step 401: Obtain the latest policy network of the dredging operation reinforcement learning model based on the reward function.

[0119] Step 402: Obtain the real-time state space of the dredging operation reinforcement learning model based on the real-time first state parameters of the dredging vessel.

[0120] Step 403: Obtain the real-time action space of the dredging operation reinforcement learning model based on the historical first state parameters and real-time first state parameters of the dredging vessel.

[0121] Step 404: Based on the real-time state space and real-time action space, obtain the current optimal operation parameters of the dredging vessel through the latest policy network of the dredging operation reinforcement learning model as the current optimal action of the dredging operation reinforcement learning model.

[0122] Step 405: Determine the adaptive attitude control parameters of the dredging vessel based on the real-time second state parameters of the dredging vessel.

[0123] Optionally, when the dredging vessel is a cutter suction dredger, the second state parameters include water depth and the dredging vessel's draft, roll angle, pitch angle, heave amplitude, and suspension wire rope length. The adaptive attitude control parameters include bridge depth adjustment parameters and suspension wire rope length adjustment parameters.

[0124] Specifically, roll angle, pitch angle, and heave amplitude can be represented as: Roll, Pitch, and Heave.

[0125] Optionally, the process of determining the adaptive attitude control parameters of the dredging vessel based on its real-time second state parameters includes:

[0126] The real-time cable tray end depth is calculated based on the real-time draft; the distance from the cable tray to the mud resting surface is calculated based on the real-time water depth and the real-time cable tray end depth; and the cable tray depth adjustment parameters are determined based on the distance from the cable tray to the mud resting surface and the critical distance of the cable tray to the mud resting surface. The target cable tray end depth is determined based on the real-time cable tray end depth and the cable tray depth adjustment parameters. The appropriate suspension wire rope length is calculated based on the target cable tray end depth, real-time roll angle, real-time pitch angle, and real-time heave amplitude. And the suspension wire rope length adjustment parameters are calculated based on the appropriate suspension wire rope length and the real-time suspension wire rope length.

[0127] Specifically, when the distance from the cable tray to the mud rest surface is greater than the critical distance of the cable tray mud rest, the cable tray depth adjustment parameter can be set to 0; when the distance from the cable tray to the mud rest surface is not greater than the critical distance of the cable tray mud rest, the cable tray depth adjustment parameter can be determined based on the difference between the critical distance of the cable tray mud rest and the distance from the cable tray to the mud rest surface. Specifically, the cable tray depth adjustment parameter can be set to be greater than the difference between the critical distance of the cable tray mud rest and the distance from the cable tray to the mud rest surface.

[0128] Specifically, the process of calculating the appropriate suspension wire rope length based on the target cable tray end depth, real-time roll angle, real-time pitch angle, and real-time heave amplitude can be determined based on the cable tray kinematic model, where the model function of the cable tray kinematic model is the real-time cable tray end depth. Regarding the ship's attitude and the length of the suspension wire rope The function can be specifically represented as:

[0129]

[0130] in, That is, the hull attitude can be determined based on the real-time roll angle, real-time pitch angle and real-time heave amplitude, and LadderAngle represents the bridge tilt angle.

[0131] Specifically, the appropriate suspension wire rope length can be obtained by inversely solving the kinematic model of the cable tray based on the target cable tray end depth, real-time roll angle, real-time pitch angle, and real-time heave amplitude.

[0132] Specifically, the difference between the adapted suspension wire rope length and the real-time suspension wire rope length can be calculated to obtain the suspension wire rope length adjustment parameter.

[0133] Optionally, when the dredging vessel is a trailing suction hopper dredger, the second state parameters include: hull attitude parameters, drag arm angle, drag head ground pressure, and wave displacement; the adaptive attitude control parameters include the drag arm floating system compensation force.

[0134] Specifically, the aforementioned hull attitude parameters may include: the dredging vessel's roll angle (Roll), pitch angle (Pitch), heave amplitude (Heave), and roll rate. Pitch speed hull heave speed .

[0135] Specifically, real-time hull attitude parameters can be acquired through sensors such as satellite positioning sensors, inertial measurement units, and / or gyroscopes.

[0136] Specifically, real-time ship attitude parameters can also be obtained by fusing the raw attitude data collected in real time by satellite positioning sensors, inertial measurement units, and gyroscopes using a Kalman filter.

[0137] Optionally, the process of determining the adaptive attitude control parameters of the dredging vessel based on its real-time second state parameters includes:

[0138] The compensating force of the rake arm floating system is obtained through a dynamic model of the rake arm floating system based on real-time hull attitude parameters, real-time rake arm angle, target rake head ground pressure, and real-time wave displacement. The model function of the dynamic model of the rake arm floating system is a function of the rake head ground pressure with respect to the hull attitude parameters, rake arm angle, compensating force of the rake arm floating system, and wave displacement.

[0139] Specifically, the dynamic model of the above-mentioned rake arm floating system can be represented as:

[0140]

[0141]

[0142] Among them, Indicates the ground pressure of the rake head. This represents a time step within a preset duration T. Indicates the ship's attitude parameters. Indicates the angle of the rake arm. This represents the compensating force of the floating system. Indicates wave displacement.

[0143] Specifically, the aforementioned preset duration T can be set based on empirical data or specific scenario requirements.

[0144] Specifically, the process of obtaining the compensating force of the rake arm floating system based on the dynamic model of the rake arm floating system using real-time hull attitude parameters, real-time rake arm angle, target rake head ground pressure, and real-time wave displacement includes:

[0145] Based on real-time hull attitude parameters, real-time rake arm angle, target rake head ground pressure, and real-time wave displacement, the dynamic model of the rake arm floating system is solved by an objective function that aims to minimize the pressure error and the change in the compensating force of the rake arm floating system within a future preset time period T, and the aforementioned compensating force of the rake arm floating system is obtained.

[0146] Specifically, the above objective function can be expressed as:

[0147]

[0148] in, The weighting coefficient representing the pressure tracking error is used to emphasize control accuracy; Indicates the ground pressure of the target rake head; Weighting coefficients represent the smoothness of control actions and are used to penalize drastic changes in the control signal; This represents the change in compensating force. .

[0149] Specifically, the process of solving the dynamic model of the rake arm floating system based on real-time hull attitude parameters, real-time rake arm angle, target rake head ground pressure, and real-time wave displacement, using an objective function that minimizes the pressure error and the change in the compensating force of the rake arm floating system within a time period T, must be solved under the following set of constraints:

[0150] Geometric safety constraints (rake arm angle):

[0151] .

[0152] Actuator constraints (compensation force output):

[0153] .

[0154] Attitude stability constraints (speed limit):

[0155] .

[0156] in, and The corresponding values ​​represent the minimum and maximum rake arm angles determined based on the corresponding structure. and The corresponding values ​​represent the minimum and maximum compensation forces of the floating system, determined based on the physical limits of the hydraulic system. This indicates the maximum speed of the dredging vessel.

[0157] Step 406: Based on the current optimal operating parameters and the adapted pose control parameters, the dredging vessel is controlled in real time via Soft-PLC.

[0158] Specifically, the process of real-time control of the dredging vessel using Soft-PLC based on the current optimal operating parameters and adapted pose control parameters may include: converting the current optimal operating parameters and adapted pose control parameters into equipment control parameters, and controlling the operating control equipment of the dredging vessel based on the equipment control parameters.

[0159] Figure 5 This is a structural diagram of a dredging vessel control system provided in an embodiment of the present invention. This device is suitable for executing the dredging vessel control method based on Soft-PLC provided in an embodiment of the present invention. Figure 5 As shown, the device may specifically include:

[0160] The network update module 501 is used to obtain the latest policy network of the dredging operation reinforcement learning model based on the reward function. The reward function includes an expert experience term, which is a piecewise decision function of action conditions with the optimal action of the sample as the independent variable. The decision triggering conditions and branch action conditions of the piecewise decision function of action conditions are obtained based on historical expert experience.

[0161] The real-time state space acquisition module 502 is used to acquire the real-time state space of the dredging operation reinforcement learning model based on the real-time first state parameters of the dredging vessel.

[0162] The real-time action space acquisition module 503 is used to acquire the real-time action space of the dredging operation reinforcement learning model based on the historical first state parameters and real-time first state parameters of the dredging vessel.

[0163] The optimal operation parameter acquisition module 504 is used to obtain the current optimal operation parameters of the dredging vessel as the current optimal action of the dredging operation reinforcement learning model through the latest policy network of the dredging operation reinforcement learning model based on the real-time state space and real-time action space.

[0164] The real-time control module 505 is used to control the dredging vessel in real time using a Soft-PLC based on the current optimal operating parameters.

[0165] This invention, through a reinforcement learning model, determines the optimal parameters of dredging vessels, enabling automatic adjustment of data operation parameters without relying on manual intervention. This avoids the lag in manual responses and improves the accuracy of judgment, allowing for timely and precise adjustments to dredging operation parameters. Furthermore, by incorporating expert experience into the reward function of the reinforcement learning model, this invention integrates expert experience into the automatic control process. This effectively learns and solidifies the implicit operational experience accumulated by experts, preventing the loss of operational knowledge due to personnel turnover. Consequently, it enables automatic, precise, and efficient control of the dredging vessel's dredging operation, thereby improving dredging efficiency.

[0166] Optionally, the dredging vessel control device based on Soft-PLC provided in this embodiment of the invention further includes: an expert control instruction processing module, used to obtain the latest expert control instructions, and convert the latest expert control instructions into structured text language through a code generation model to obtain the latest expert suggested control code; and to obtain the review results of the reviewers on the latest expert suggested control code through a code review channel.

[0167] Optionally, the aforementioned real-time control module 505 can be specifically used to control the dredging vessel in real time via Soft-PLC based on the latest expert-recommended control code and the current optimal operating parameters when the review result of the latest expert-recommended control code is approved.

[0168] Optionally, the dredging vessel control device based on Soft-PLC provided in this embodiment of the invention further includes: a condition update module, used to update the decision triggering conditions and branch action conditions based on the latest expert control instructions.

[0169] Optionally, the aforementioned real-time action space acquisition module 503 can be specifically used to: predict and obtain the normal range value of the real-time operation parameter based on the historical first state parameter; if the real-time first state parameter does not deviate from the normal range value, then acquire the real-time action space based on the real-time operation parameter; if the real-time first state parameter deviates from the normal range value, then query the state operation parameter mapping table to obtain the first possible value range of the operation parameter corresponding to the real-time first state parameter; and acquire the real-time action space based on the first possible value range of the operation parameter.

[0170] Optionally, the dredging vessel control device based on Soft-PLC provided in this embodiment of the invention further includes an adaptive posture control parameter acquisition module, which is used to determine the adaptive posture control parameters of the dredging vessel based on the real-time second state parameters of the dredging vessel before real-time control of the dredging vessel by Soft-PLC based on the current optimal operating parameters.

[0171] Optionally, the aforementioned real-time motion space acquisition module 503 can be specifically used to control the dredging vessel in real time via Soft-PLC based on the current optimal operating parameters and adapted pose control parameters.

[0172] Optionally, the dredging vessel is a cutter suction dredger. The second state parameters include water depth and the dredging vessel's draft, roll angle, pitch angle, heave amplitude, and suspension wire rope length. The adaptive attitude control parameters include bridge depth adjustment parameters and suspension wire rope length adjustment parameters.

[0173] Optionally, the aforementioned adaptive pose control parameter acquisition module can be specifically used to: calculate the real-time bridge end depth based on the real-time draft; calculate the distance from the bridge to the mud resting surface based on the real-time water depth and the real-time bridge end depth; and determine the bridge depth adjustment parameters based on the distance from the bridge to the mud resting surface and the bridge's critical mud resting distance; determine the target bridge end depth based on the real-time bridge end depth and the bridge depth adjustment parameters; calculate the adaptive suspension wire rope length based on the target bridge end depth, real-time roll angle, real-time pitch angle, and real-time heave amplitude; and calculate and determine the suspension wire rope length adjustment parameters based on the adaptive suspension wire rope length and the real-time suspension wire rope length.

[0174] Optionally, the dredging vessel is a trailing suction hopper dredger, and the second state parameters include: hull attitude parameters, drag arm angle, drag head ground pressure, and wave displacement; the adaptive attitude control parameters include the compensating force of the drag arm floating system.

[0175] Optionally, the aforementioned adaptive posture control parameter acquisition module can be specifically used to obtain the rake arm floating system compensation force based on the real-time hull attitude parameters, real-time rake arm angle, target rake head ground pressure, and real-time wave displacement through the rake arm floating system dynamic model; wherein, the model function of the rake arm floating system dynamic model is a function of the rake head ground pressure with respect to the real-time hull attitude parameters, real-time rake arm angle, rake arm floating system compensation force, and wave displacement.

[0176] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional modules is merely an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the functional modules described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0177] This invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the Soft-PLC-based dredging vessel control method provided in any of the above embodiments.

[0178] This invention also provides a computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the dredging vessel control method based on Soft-PLC provided in any of the above embodiments.

[0179] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the dredging vessel control method based on Soft-PLC as described in any of the embodiments of this invention.

[0180] The following is for reference. Figure 6 It shows a schematic diagram of the structure of a computer system 600 suitable for implementing an electronic device according to embodiments of the present invention. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0181] like Figure 6As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the system 600. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0182] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0183] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this invention 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 communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs the functions defined above in the system of this invention.

[0184] It should be noted that the computer-readable medium shown in this invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0185] 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 the present invention. 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 a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may 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.

[0186] The modules and / or units described in the embodiments of this invention can be implemented in software or hardware. The described modules and / or units can also be housed in a processor; for example, a processor may be described as including a network update module, a real-time state space acquisition module, a real-time action space acquisition module, an optimal job parameter acquisition module, and a real-time control module. The names of these modules do not necessarily limit the module itself.

[0187] In another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiments; or it may exist independently and not assembled into the device. The computer-readable medium carries one or more programs, which, when executed by the device, cause the device to include: obtaining a latest policy network for a dredging operation reinforcement learning model based on a reward function, the reward function including an expert experience term, the expert experience term being an action condition piecewise decision function with the optimal action of a sample as the independent variable, the decision triggering condition and branch action condition of the action condition piecewise decision function being obtained based on historical expert experience; obtaining a real-time state space of the dredging operation reinforcement learning model based on real-time first state parameters of the dredging vessel; obtaining a real-time action space of the dredging operation reinforcement learning model based on historical first state parameters and real-time first state parameters of the dredging vessel; obtaining the current optimal operating parameters of the dredging vessel as the current optimal action of the dredging operation reinforcement learning model through the latest policy network of the dredging operation reinforcement learning model based on the real-time state space and real-time action space; and performing real-time control of the dredging vessel through a Soft-PLC based on the current optimal operating parameters.

[0188] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A dredging vessel control method based on Soft-PLC, characterized in that, include: The latest policy network of the reinforcement learning model for dredging operations is obtained based on the reward function. The reward function includes an expert experience term, which is a piecewise decision function of action conditions with the optimal action of the sample as the independent variable. The decision triggering conditions and branch action conditions of the piecewise decision function of action conditions are obtained based on historical expert experience. The real-time state space of the reinforcement learning model for dredging operations is obtained based on the real-time first state parameters of the dredging vessel. The real-time action space of the dredging operation reinforcement learning model is obtained based on the historical first state parameters and real-time first state parameters of the dredging vessel. Based on the real-time state space and real-time action space, the current optimal operating parameters of the dredging vessel are obtained through the state-of-the-art policy network of the dredging operation reinforcement learning model, which serves as the current optimal action of the dredging operation reinforcement learning model; and The dredging vessel is controlled in real time using a Soft-PLC based on the current optimal operating parameters.

2. The dredging vessel control method based on Soft-PLC according to claim 1, characterized in that, Also includes: Obtain the latest expert control instructions and convert them into structured text language using a code generation model to obtain the latest expert-recommended control code; Obtain the review results from reviewers regarding the latest expert recommendations for controlling the code through the code review channel; The real-time control of the dredging vessel using Soft-PLC based on the current optimal operating parameters includes: When the latest expert-recommended control code is approved, the dredging vessel is controlled in real time via Soft-PLC based on the latest expert-recommended control code and the current optimal operating parameters.

3. The dredging vessel control method based on Soft-PLC according to claim 2, characterized in that, Also includes: The decision triggering conditions and branch action conditions are updated based on the latest expert control instructions.

4. The dredging vessel control method based on Soft-PLC according to claim 1, characterized in that, The method of obtaining the real-time action space of the dredging operation reinforcement learning model based on the historical first state parameters and real-time first state parameters of the dredging vessel includes: The normal range values ​​of real-time operation parameters are obtained based on the prediction of historical first state parameters; If the real-time first state parameter does not deviate from the normal range value, then the real-time action space is obtained based on the real-time operation parameter; If the real-time first status parameter deviates from the normal range, the status job parameter mapping table is queried to obtain the first possible value range of the job parameter corresponding to the real-time first status parameter; and The real-time action space is obtained based on the first possible value range of the task parameters.

5. The dredging vessel control method based on Soft-PLC according to claim 1, characterized in that, Before the real-time control of the dredging vessel via Soft-PLC based on the current optimal operating parameters, the method further includes: The adaptive attitude control parameters of the dredging vessel are determined based on the real-time second state parameters of the dredging vessel. The real-time control of the dredging vessel using Soft-PLC based on the current optimal operating parameters includes: Based on the current optimal operating parameters and the adapted pose control parameters, the dredging vessel is controlled in real time using a Soft-PLC.

6. The dredging vessel control method based on Soft-PLC according to claim 5, characterized in that, The dredging vessel is a cutter suction dredger. The second state parameters include water depth and the dredging vessel's draft, roll angle, pitch angle, heave amplitude, and suspension wire rope length. The adaptive posture control parameters include bridge depth adjustment parameters and suspension wire rope length adjustment parameters. The determination of the adaptive attitude control parameters of the dredging vessel based on the real-time second state parameters of the dredging vessel includes: The real-time draft depth is used to calculate the real-time cable tray end depth. The distance from the cable tray to the mud resting surface is calculated based on the real-time water depth and the real-time cable tray end depth. The cable tray depth adjustment parameters are determined based on the distance from the cable tray to the mud resting surface and the critical distance of the cable tray to the mud resting surface. The target cable tray end depth is determined based on the real-time cable tray end depth and cable tray depth adjustment parameters; The appropriate suspension wire rope length is calculated based on the target cable tray end depth, real-time roll angle, real-time pitch angle, and real-time heave amplitude; and The adjustment parameters for the length of the suspension wire rope are determined based on the adapted length of the suspension wire rope and the real-time length of the suspension wire rope.

7. The dredging vessel control method based on Soft-PLC according to claim 5, characterized in that, The dredging vessel is a trailing suction hopper dredger. The second state parameters include: hull attitude parameters, drag arm angle, drag head ground pressure, and wave displacement. The adaptive attitude control parameters include the compensating force of the drag arm floating system. The determination of the adaptive attitude control parameters of the dredging vessel based on the real-time second state parameters of the dredging vessel includes: The compensating force of the rake arm floating system is obtained by using a dynamic model of the rake arm floating system based on real-time hull attitude parameters, real-time rake arm angle, target rake head ground pressure and real-time wave displacement. The model function of the dynamic model of the rake arm floating system is a function of the rake head ground pressure with respect to the real-time hull attitude parameters, the real-time rake arm angle, the rake arm floating system compensation force, and the wave displacement.

8. A dredging vessel control device based on Soft-PLC, characterized in that, include: The network update module is used to obtain the latest policy network of the dredging operation reinforcement learning model based on the reward function. The reward function includes an expert experience term, which is an action condition piecewise decision function with the optimal action of the sample as the independent variable. The decision triggering conditions and branch action conditions of the action condition piecewise decision function are obtained based on historical expert experience. The real-time state space acquisition module is used to acquire the real-time state space of the dredging operation reinforcement learning model based on the real-time first state parameters of the dredging vessel. The real-time action space acquisition module is used to acquire the real-time action space of the dredging operation reinforcement learning model based on the historical first state parameters and real-time first state parameters of the dredging vessel. The optimal operation parameter acquisition module is used to obtain the current optimal operation parameters of the dredging vessel as the current optimal action of the dredging operation reinforcement learning model through the latest policy network of the dredging operation reinforcement learning model based on the real-time state space and real-time action space. as well as The real-time control module is used to control the dredging vessel in real time using a Soft-PLC based on the current optimal operating parameters.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the dredging vessel control method based on Soft-PLC as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the Soft-PLC-based dredging vessel control method as described in any one of claims 1 to 7.

Images