Inland river splicing cutter suction dredger control system

Abstract

The present application relates to the technical field of soil migration, and more particularly to a control system for an assembled cutter suction dredger for inland rivers. The system comprises a multi-source data acquisition module, an operating environment data construction module, a closed-loop control module and an optimization module. The ship body sensor data and water body sensor data are obtained. The ship body sensor data and water body sensor data are time-labeled to construct first operating unit data and second operating unit data, respectively. The first operating unit data is associated with a three-dimensional space to obtain river construction track data. Load identification is performed on the first operating unit data to generate equipment load state data. Therefore, the present application establishes a technical path combining multi-source data fusion, three-dimensional construction environment reconstruction, closed-loop instruction generation and dynamic optimization, solves the problems of data fragmentation, feedback lag and control rigidity in traditional dredging operations, and improves the precision, energy efficiency and stability of river dredging construction.

Description

Technical Field

[0001] This invention relates to the field of soil migration technology, and in particular to a dredging control system for an inland waterway assembled cutter suction dredger. Background Technology

[0002] Existing inland waterway prefabricated cutter suction dredging control systems have revealed several shortcomings in engineering practice. Firstly, the acquisition frequencies of source sensors (pressure, rotational speed, mud sample, current, positioning, and sonar, etc.) are out of sync with clocks and their labels are incomplete, leading to missing time-series information and difficulty in accurately tracing events. Secondly, sensor drift and inconsistent calibration introduce systematic biases, resulting in poor robustness of observation-based operational condition judgments. Thirdly, the accuracy of vessel motion positioning and relative position estimation of the suction head in three-dimensional water is insufficient. Positioning noise and echo interference cause fluctuations in trajectory tracking and dredging depth control, failing to guarantee real-time closed-loop coordination between cutting actions and terrain changes. Fourthly, the online characterization capability of mud quality and sand content is weak; the acquisition of mud and sand physical parameters is delayed or relies on offline chemical analysis, inhibiting real-time optimization of cutting resistance and dredging pump power. Finally, control strategies are mostly based on empirical rules or static thresholds, lacking adaptive adjustment mechanisms when facing sudden changes in the riverbed, obstacles, or unexpected hydrological conditions, making them prone to overload, empty suction, or delayed responses. Fifth, the communication and computing power layout between systems is unreasonable: insufficient shipboard edge computing power and bandwidth constraints on data interaction with shore-based monitoring platforms lead to high latency, frequent redundant data transmission, and a lack of data integrity and traceability. Sixth, the fault diagnosis and predictive maintenance capabilities are inadequate; potential damage to critical components (such as cutterhead bearings and sludge pump impellers) is often only discovered after significant performance degradation, increasing maintenance costs and project time risks. Seventh, the information in the human-machine interface is fragmented, and alarms and suggestions lack interpretability, making it difficult for on-site operators to quickly and correctly handle complex operating conditions. Finally, the existing solution lacks continuous monitoring and constraint of environmental impact, failing to effectively limit the spread of turbidity and ecological disturbance while ensuring operational efficiency. Summary of the Invention

[0003] Therefore, it is necessary to provide a dredging control system for an inland waterway assembled cutter suction dredger to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a dredging control system for an inland waterway assembled cutter suction dredger is provided, the method comprising the following modules:

[0005] The multi-source data acquisition module acquires ship hull sensor data and water body sensor data; it timestamps the ship hull sensor data and water body sensor data to construct the first operation unit data and the second operation unit data, respectively.

[0006] The operational environment data construction module associates the data of the first operational unit with the three-dimensional space to obtain the river construction trajectory data; it performs load identification on the data of the first operational unit to generate equipment load status data; and it performs water depth and flow velocity conversion on the data of the second operational unit to generate real-time hydraulic condition data.

[0007] The closed-loop control module generates construction operation instructions based on river construction trajectory data, equipment load status data, and real-time hydraulic condition data, and sends them to the execution unit; it also collects dredging feedback data to obtain dredging construction efficiency verification data.

[0008] The optimization module updates the parameter mapping relationship of the construction operation instructions based on the dredging construction efficiency review data.

[0009] The beneficial effects of this invention are as follows: By using a multi-source data acquisition module to uniformly time-stamp ship hull sensor data and water body sensor data, the consistency of information from different sources in terms of time sequence is ensured, avoiding alignment errors caused by data at different acquisition frequencies. This makes the constructed data of the first and second work units comparable and fusionable. Secondly, the work environment data construction module not only maps the data of the first work unit to three-dimensional space to obtain intuitive river channel construction trajectory data, but also converts complex signals such as mud pump pressure, bridge attitude, and trolley travel into measurable equipment load status data through load identification. Combined with the water depth and flow velocity data from the second work unit, it generates real-time hydraulic condition data. This process achieves bidirectional quantification and real-time expression of the construction environment and equipment operating status. Based on this, the closed-loop control module uses three core data types—construction trajectory data, load status data, and hydraulic condition data—to construct construction operation instructions. By comparing feedback data with target instructions, it generates dredging construction efficiency verification data, thereby achieving data-driven dynamic closed-loop control at the execution level. Finally, the optimization module uses the efficiency review data as the evaluation basis to update and correct the parameter mapping relationship, forming an adaptive optimization mechanism based on historical and real-time data. This allows the system to continuously accumulate experience and correct control strategies, avoiding the insufficient accuracy and efficiency fluctuations caused by relying on manual experience or static rules in traditional methods. Through this data-driven, end-to-end closed-loop system, the system not only ensures the uniformity of data in spatial, temporal, and semantic dimensions, but also ensures the logical coherence and traceability of instruction generation, execution, and optimization. Therefore, this invention, by establishing a technical path that combines multi-source data fusion, three-dimensional construction environment reconstruction, closed-loop instruction generation, and dynamic optimization, solves the problems of data fragmentation, feedback lag, and control rigidity in traditional dredging operations, improving the accuracy, energy efficiency, and stability of river dredging construction. Attached Figure Description

[0010] Figure 1 A schematic diagram of the module flow of a dredging control system for an inland waterway assembled cutter suction dredger;

[0011] Figure 2 A schematic diagram of the river channel construction trajectory;

[0012] Figure 3 This is a schematic diagram of the construction process;

[0013] Figure 4 A visual diagram of the construction curve;

[0014] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0015] The technical method of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.

[0016] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0017] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0018] To achieve the above objectives, please refer to Figures 1 to 4 A dredging control system for an inland waterway assembled cutter suction dredger, the method comprising the following modules:

[0019] S1: Multi-source data acquisition module, acquires ship hull sensor data and water body sensor data; timestamps the ship hull sensor data and water body sensor data, and constructs the first operation unit data and the second operation unit data respectively;

[0020] S2: Operational environment data construction module, which associates the data of the first operational unit with the three-dimensional space to obtain the river construction trajectory data; performs load identification on the data of the first operational unit to generate equipment load status data; and performs water depth and flow velocity conversion on the data of the second operational unit to generate real-time hydraulic condition data.

[0021] S3: Closed-loop control module, which generates construction operation instructions based on river construction trajectory data, equipment load status data and real-time hydraulic condition data, and sends them to the execution unit; collects dredging feedback data to obtain dredging construction efficiency verification data;

[0022] S4: Optimization module, updates the parameter mapping relationship of construction operation instructions based on dredging construction efficiency review data.

[0023] In this embodiment of the invention, reference Figure 1 The diagram shown is a schematic flowchart of the module flow of a dredging control system for an inland waterway assembled cutter suction dredger according to the present invention. In this example, the dredging control system for the inland waterway assembled cutter suction dredger includes the following modules:

[0024] The multi-source data acquisition module acquires ship hull sensor data and water body sensor data; it timestamps the ship hull sensor data and water body sensor data to construct the first operation unit data and the second operation unit data, respectively.

[0025] Preferably, the data of the first working unit includes bridge attitude data, trolley travel data, and mud pump pressure data; the data of the second working unit includes positioning and heading data, water level and depth data, and sediment transport data.

[0026] In embodiments of the present invention, the multi-source data acquisition module synchronously accesses ship hull sensor data and water body sensor data through a standardized interface, establishes a unified time axis based on differential positioning and timing, writes millisecond-level time stamps to all raw data and records the sampling sequence number and measurement point number; subsequently, it performs time alignment, sensor calibration, unit normalization, outlier removal and missing measurement interpolation: the bridge angle and bridge trunnion draft are corrected using static zero point and temperature drift coefficient and spatially correlated according to the equipment coordinate system; the trolley stroke is constrained for climbing and speed consistency is checked based on displacement encoder or hydraulic cylinder stroke sensor; the mud pump suction vacuum, discharge pressure and sealing pressure are subject to upper and lower limit threshold discrimination and sliding window smoothing; differential positioning and gyrocompass heading are resampled at the same epoch and heading jump suppression is performed; tide level and water depth measurements are corrected for tide level according to the operation period and output standard water level surface; the production flow rate and sediment concentration are aggregated at the same time particle size and concentration drift correction is performed.

[0027] After completing the above processing, two types of operational data are constructed according to their intended use: The first operational unit data consists of bridge attitude data (a spatiotemporal correlation sequence of bridge angle and bridge trunnion draft), trolley travel data, and mud pump pressure data (a consistency verification sequence of three pressure measurements), used to characterize equipment movement and load status; the second operational unit data consists of positioning and heading data (a synchronization sequence of differential positioning position and gyrocompass heading), water level and depth data (operating water depth after tidal correction and standard water level), and sediment transport data (a window aggregation of flow rate and concentration), used to characterize the operating environment and mud transport channel status; both types of data are output with a unified time granularity and retain the original measurement reference relationships.

[0028] In one implementation of the present invention, during a continuous ten-second operation of a dredger, the bridge angle is between -25 degrees and -27 degrees, the draft of the bridge trunnion is between 3.8 and 4.0 meters, the trolley travels a cumulative forward thrust of 0.6 meters, the mud pump suction vacuum stabilizes between -0.50 and -0.55 bar, the discharge pressure is between 8 and 9 bar, the sealing pressure is between 9.5 and 10.0 bar, the differential positioning trajectory moves downstream at a speed of 0.4 meters per second, the gyrocompass heading is 180 degrees, the operating water depth after tide level correction is 4.5 meters, and the production flow rate is... The flow rate is approximately 7,000 cubic meters per hour (based on the rated flow rate of the mud pump), and the sediment concentration in the water area is between 1,100 and 1,200 kilograms per cubic meter. Based on this, the first operating unit data output synchronously is as follows: "Bridge attitude data: angle approximately -26 degrees and draft 4 meters, trolley travels forward 0.6 meters within ten seconds, mud pump pressure data is stable and does not exceed limits". The second operating unit data is as follows: "Positioning and heading data: continuous downstream navigation with stable heading, water level and depth data: 4.5-meter standardized water depth, sediment transport data: high concentration and high flow window value".

[0029] The operational environment data construction module associates the data of the first operational unit with the three-dimensional space to obtain the river construction trajectory data; it performs load identification on the data of the first operational unit to generate equipment load status data; and it performs water depth and flow velocity conversion on the data of the second operational unit to generate real-time hydraulic condition data.

[0030] Preferably, the working environment data construction module includes the following functions:

[0031] Align the positioning heading data and combine it with the bridge attitude data to generate terrain point cloud data; mark the construction trajectory points of the terrain point cloud data and perform 3D point cloud rasterization to construct river channel construction trajectory data.

[0032] The load is identified from the data of the first work unit to generate equipment load status data;

[0033] The water depth and velocity are converted from the data of the second working unit to generate real-time hydraulic condition data.

[0034] In this embodiment of the invention, the operational environment data construction module uses a unified time axis as a basis to synchronize and spatially register the data of the first operational unit and the data of the second operational unit: First, based on the positioning and heading data, a correspondence between the shipborne coordinate system and the river reference coordinate system is established, and the bridge attitude data (angle, trunnion draft) is converted into the temporal position of the cutter tip in the river reference coordinate system; then, the displacement of the hull along the construction axis is compensated with the trolley travel data to form a continuous cutter movement trajectory. After alignment according to the time window, the "cutter tip position sequence" and water level and depth data are fused into a three-dimensional scatter set, and the joint state of the mud pump pressure data and the trolley travel (stable suction vacuum, stable discharge pressure and trolley forward propulsion) is used as the "cutting contact" criterion. The construction trajectory points are marked in the scatter set, and then three-dimensional point cloud rasterization (unified grid resolution and time granularity) is performed to output the river construction trajectory data.

[0035] For load identification, the consistency of the mud pump pressure data is first checked (coordinated changes in suction vacuum, discharge pressure, and sealing water pressure). This data is then combined with the bridge attitude data and trolley travel data to distinguish between four states: underload, stable, overload, and abnormal, generating equipment load status data with timestamps and operating section indexes. For water depth and velocity conversion, the standardized water depth at the time of operation is reconstructed based on the water level and depth data. Combined with the flow rate and sediment concentration from the sediment transport data, the volumetric flow rate is converted into the pipe velocity according to the DN700 mud conveying pipe inner diameter and pump set settings, and synchronized with the concentration to form real-time hydraulic condition data (including operating water depth, pipe velocity, mud volume concentration, and their time series markers).

[0036] It is particularly important to note that the gridding uses a fixed resolution (default 0.5m × 0.5m grid), and each grid is associated with a time window (default 10 seconds). The "cutting contact" criterion must simultaneously meet the following: suction vacuum fluctuation range ≤ 0.05 bar; discharge pressure fluctuation range ≤ 0.5 bar; trolley propulsion speed > 0.01m / s.

[0037] like Figure 2 The image shows the construction trajectory of the river channel.

[0038] In one implementation of the present invention, within a 10-minute window in an inland river operation area, the positioning and heading data show that the hull is advancing downstream at a rate of 0.35 m / s and maintaining a stable heading of 185 degrees; the bridge attitude data records that the cutter head angle is approximately -24 degrees, the trunnion draft is 3.7 to 3.9 meters, and the trolley travels a cumulative forward distance of 3.2 meters; the mud pump pressure data shows an intake vacuum of approximately -0.53 bar, an discharge pressure of 8.6 bar, and a sealing pressure of 9.3 bar with minimal fluctuations; the water level and depth data, after tide correction, show an operating water depth of 4.3 meters; and the sediment transport data shows a flow rate of approximately 7000 cubic meters per hour and a sediment concentration of approximately 1100 kg per cubic meter.

[0039] Based on this, the module integrates the timing position of the cutterhead endpoint with the operating water depth to generate topographic point cloud data, and marks the construction trajectory points with a time slice of "vacuum and pressure relief are stable and the trolley is advancing". After rasterization, it forms the river construction trajectory data (grid resolution of 0.5 meters, trajectory continuously covering 120 grid cells). Combined pressure-attitude-stroke three-source data determine that the load is mostly in the stable-slight overload switching range, generating equipment load status data (stable section accounts for about 70%, light overload accounts for about 30%, and is located in the second half of the advancement). The volumetric flow rate is converted to the inner diameter of the DN700 mud conveying pipe to obtain the pipe velocity of about 2.0 m / s, and output in real time hydraulic condition data (operating water depth 4.3 meters, pipe velocity 5.1 m / s, mud volume concentration corresponding to 1100 kg / m³). The three types of data are aligned on the same time axis and under the operating section index, for subsequent generation of bridge control commands, trolley advancement commands, mud pump power distribution commands, and mud conveying flow rate adjustment commands.

[0040] It should be noted that the performance parameters of the mud pump used in this embodiment need to be supplemented as follows:

[0041] Flow rate: 7000m 3 / h;

[0042] Head: 42m;

[0043] Shaft power: 1680kW.

[0044] Preferably, load identification of the data in the first work unit includes:

[0045] The operating status of the pressure equipment is analyzed based on the ultimate pressure value of the mud pump pressure data to obtain the pressure equipment status data.

[0046] By combining the bridge angle data and trolley travel data, the load level of the pressure equipment is determined, and the load is divided based on the preset load threshold to obtain the equipment load status data.

[0047] In embodiments of this invention, the pressure data of the mud pump (including suction vacuum, discharge pressure, and sealing pressure) and the bridge angle and trolley stroke are synchronously sampled and calibrated. Time-series resampling, noise reduction (median filtering and low-pass filtering), baseline drift correction, and missing data interpolation are performed to ensure signal integrity. Pressure features (short-term mean, short-term variance, peak-to-peak value, rise / fall rate, and pulsation count) and mechanical features (bridge angular velocity, trolley instantaneous velocity, and cumulative displacement) are extracted within a sliding time window, and sensor anomalies are eliminated through consistency checks. Subsequently, the pressure and mechanical features are correlated and determined according to a rule set or lightweight classifier: when the pressure feature shows a high amplitude, the positive pressure difference increases, the bridge angle points to the deep incision zone, and the trolley speed decreases, it is marked as an overload state; when both pressure and mechanical features are within the calibration range and the trolley speed is stable, it is marked as a stable load; when the suction vacuum amplitude decreases significantly, the discharge pressure fluctuation increases, and the trolley stroke suddenly increases, it is marked as an empty suction or blockage anomaly. The load threshold can be determined by the device nameplate limit, historical operating percentile, or online adaptive baseline; finally, the device load status record with segment index is output in time series, including load category, load score, and trigger threshold reference.

[0048] In one implementation of this invention, taking a ten-second sliding window as an example, the average vacuum of the mud pump inside the sliding window is -0.53 bar, with a short-term variance of 0.02 bar and a peak value of 0.06 bar; the average discharge pressure is 8.6 bar, with a variance of 0.3 bar; the sealing water pressure is 9.6 bar with minimal fluctuation; the bridge angle is stable at -26°; and the trolley advances 0.6 meters within ten seconds (average speed 0.06 m / s). The threshold values ​​are set as follows: an absolute vacuum value greater than 0.65 bar or a discharge pressure greater than 9.5 bar is considered a heavy load; an absolute vacuum value between 0.50 and 0.65 bar and a discharge pressure between 0.08 and 9.5 bar are considered a light overload; and a pressure below 50 kPa and a discharge pressure below 0.8 MPa are considered stable. Based on the above characteristics and thresholds, this sliding window is determined to be the "stable to light overload switching range" and marked on the time axis as 70% stable segment and 30% light overload segment; if the vacuum drawn in instantly drops to -0.15 kPa and the discharge pressure suddenly drops or rises within the same window, the air suction / blockage abnormality flag will be triggered and the abnormal operating condition will be reported.

[0049] Preferably, the conversion of water depth and velocity for the data from the second operating unit includes:

[0050] Water level and depth data are corrected for depth to obtain corrected inland river water level data;

[0051] The flow velocity distribution data is obtained by statistically analyzing the sediment transport data.

[0052] Real-time hydraulic condition data is obtained by weighting inland river water level correction data and water flow velocity distribution data according to preset proportional weights.

[0053] In embodiments of the present invention, observational calibration and tidal correction are performed on water level and depth data: the original tidal level measurement is baseline-corrected according to the elevation of the measuring point and the reference water level surface, and the water level value is converted into a standardized operating water depth using the local riverbed elevation profile given by the construction trajectory; secondly, time window aggregation and concentration drift correction are performed on sediment transport data, and the median and variance of the flow rate and sediment concentration within the same time particle size are calculated according to the window length to obtain a steady-state representative value; subsequently, the effective sediment transport cross-sectional area or pipeline transmission cross-sectional area is calculated based on the cross-sectional geometry of the operating section (obtained by interpolation of the river channel cross-section or construction trajectory). The aggregated volumetric flow rate is converted into an average reference velocity based on the cross-sectional area. For the velocity distribution within the cross-section, a hierarchical discretization method is used to distribute the average velocity to each grid cell according to a preset or historically calibrated velocity weight to obtain the water flow velocity distribution. Finally, the standardized operating water depth, grid cell velocity, and mud concentration are fused according to preset weights and supplemented with pipe resistance or discharge correction. The output includes real-time hydraulic condition data containing operating water depth, average reference velocity, grid cell velocity, mud volumetric concentration, and corresponding timestamps. All results retain the original measurement references and are recorded for subsequent closed-loop control calls and historical backtracking.

[0054] In one implementation of the present invention, for example, if the original tide level measured on site is 5.20 meters and the reference water level correction value is -0.30 meters, then the working water level obtained after correcting the tide level is 4.90 meters; combined with the riverbed elevation of 0.40 meters given by the construction trajectory, the standardized working water depth is 4.90-0.40=4.50 meters.

[0055] For example, if the flow meter shows an instantaneous flow rate of 7000 cubic meters per hour, converting it to seconds is 7000 ÷ 3600 ≈ 1.944 cubic meters per second. If the inner diameter of the sludge conveying pipe is 0.70 meters, then the cross-sectional area inside the pipe is approximately 0.385 square meters. Using the formula "average flow velocity equals volumetric flow rate divided by cross-sectional area" (flow velocity = volumetric flow rate ÷ cross-sectional area, where volumetric flow rate represents the volume passing through per unit time, and cross-sectional area represents the pipe's cross-sectional area), substituting the values, we get an average flow velocity of approximately 5.05 meters per second. The average flow velocity is then weighted according to the five vertical grid units (e.g., by...). By assigning weights of 0.8, 1.0, 1.1, 1.0, and 0.9 after standardization, the local flow velocity of each cell can be obtained. Then, the local flow velocity is paired with the sediment concentration measured within the corresponding time window (e.g., 1100 kg / m³). The final output real-time hydraulic condition data is "operating water depth 4.50 m, average reference flow velocity in the pipe approximately 5.05 m / s, velocity of each cell approximately 4.04, 5.05, 5.56, 5.05, and 4.55 m / s, mud concentration 1100 kg / m³". This timestamped data is used for closed-loop control and threshold determination.

[0056] It is particularly important to note that flow velocity calculations must take into account the pump's water clearing efficiency, soil yield, and mud concentration; it is not advisable to simply convert the water flow velocity formula directly.

[0057] The closed-loop control module generates construction operation instructions based on river construction trajectory data, equipment load status data, and real-time hydraulic condition data, and sends them to the execution unit; it also collects dredging feedback data to obtain dredging construction efficiency verification data.

[0058] Preferably, the closed-loop control module includes the following functions:

[0059] Acquire design cross-section data; compare the river channel construction trajectory data with the design cross-section data to generate unexcavated and excavated sections respectively; calculate the cutter head deviation in the unexcavated and excavated sections, and determine the bridge frame angle and depth based on the deviation data; determine the target travel of the trolley based on the bridge frame angle and depth; generate bridge frame control commands and trolley propulsion commands according to the bridge frame angle and depth and the trolley target travel.

[0060] Based on equipment load status data and real-time hydraulic condition data, mud pump power allocation commands and mud conveying flow rate adjustment commands are constructed respectively.

[0061] The construction operation instructions include bridge control instructions, trolley propulsion instructions, mud pump power allocation instructions, and mud conveying flow rate adjustment instructions. The construction operation instructions are issued to the execution unit to carry out dredging operations, and dredging feedback data is collected based on hull sensors and water sensors to obtain dredging construction efficiency verification data.

[0062] In this embodiment of the invention, the river construction trajectory data is spatially projected onto the design cross-section data. The trajectory is divided into unexcavated and excavated sections using interpolation and a vertical difference threshold. For each unexcavated section, a three-dimensional deviation vector (including longitudinal projection and vertical depth difference) between the cutterhead endpoint and the design cross-section is calculated. Subsequently, inverse kinematic mapping is performed on the deviation vector using device geometric parameters (bridge pivot position, link length from the bridge to the cutterhead endpoint, etc.) to obtain the bridge angle and bridge extension (depth) adjustment. The inverse kinematics can be approximately expressed as the bridge angle change Δθ≈arcsin(Δd / L) (where Δθ represents the increment of the bridge angle, Δd represents the vertical difference between the cutterhead endpoint and the design depth, and L represents the link length from the pivot to the cutterhead endpoint; this approximation holds when the ratio of Δd to L is small). The obtained angle and extension target are then converted into a bridge angle through amplitude limiting and rate constraints. The system sets the values ​​for the bridge and depth; it projects these values ​​onto the working axis to determine the target travel and motion curve of the trolley (using a segmented velocity profile to meet the requirements for maximum acceleration / deceleration and displacement accuracy); it also determines the pump set's carrying capacity and critical vacuum / discharge threshold based on equipment load status data, and combines real-time hydraulic condition data (working water depth, average reference flow velocity in the pipe, mud volume concentration) to generate mud pump power allocation and valve opening settings through table lookup or characteristic curve mapping—the mapping table uses the target mud conveying volume flow rate and the current equipment carrying capacity as indexes to avoid dry suction or overpressure; finally, it constructs a timestamped construction operation instruction package containing the bridge angle, bridge extension / retraction, trolley displacement and speed, pump speed percentage, and valve opening, etc. The instruction includes priority, rate limit, and safety interlock conditions and is sent to the execution unit for execution, while feedback monitoring is activated to complete closed-loop correction.

[0063] It is particularly important to note that the three-dimensional deviation vector between the cutter tip and the design section is calculated by projecting the positioning data onto the normal of the design section.

[0064] In one implementation of this invention, the target depth of the cutterhead in an unexcavated section is designed to be 6.00 meters, the current cutterhead depth is 5.50 meters (i.e., another 0.50 meters needs to be excavated), and the length of the connecting rod from the pivot to the cutterhead end is 12.0 meters. Therefore, the approximate calculation of the required bridge angle increment Δθ≈arcsin(0.50 / 12.0)≈0.0417 radians, approximately 2.4 degrees. If the current bridge angle is -26 degrees, then the bridge angle setting value is -28.4 degrees (which can be taken as -28.0 degrees after amplitude limiting). The corresponding trolley target travel is calculated based on the cutterhead's lateral projection as a forward movement of 0.5 meters, with a velocity profile set to 0.06 m / s and a maximum acceleration of 0.01 m / s². The real-time hydraulic condition display shows an operating water depth of 4.50 meters and an average reference flow rate within the pipe. With a flow rate of approximately 5.1 m / s and a mud concentration of 1100 kg / m³, according to the mapping table, this flow rate corresponds to a main pump power allocation of 85%, an auxiliary pump of 60%, and a valve opening of 60%. The above values ​​are encapsulated into commands: bridge angle setting -28.0 degrees (slope 0.5 degrees / s), trolley advance 0.5 meters (speed 0.06 m / s), main pump power 85%, auxiliary pump power 60%, valve 60%, and the command includes a safety interlock with a vacuum threshold of -0.65 bar and a pressure relief threshold of 9.5 bar. The execution unit acts according to the command and judges the action completion status based on feedback such as bridge attitude, trolley stroke, suction vacuum, pressure relief, and flow rate. If the feedback shows that the vacuum is close to the threshold or the pressure relief exceeds the limit, the rate limit or retreat strategy is triggered and a correction request is sent back.

[0065] Preferably, the step of constructing the mud pump power allocation command and the mud conveying flow rate adjustment command based on equipment load status data and real-time hydraulic condition data includes:

[0066] Based on the equipment load status data, determine whether the equipment is overloaded, and combine the analysis of the changes in the trolley stroke and bridge angle. If it is determined that the equipment has entered a high-resistance soil layer, reduce the main pump speed and increase the auxiliary pump speed; otherwise, do the opposite, thereby generating a mud pump power distribution command.

[0067] Obtain the design output and real-time mud flow rate; compare the design output and real-time mud flow rate, and combine them with real-time hydraulic condition data to determine whether the mud conveying pipeline is too large, so as to adjust the valve opening and generate a mud conveying flow rate adjustment command.

[0068] In embodiments of the present invention, the equipment load status data (including time-series signals of suction vacuum, discharge pressure, sealing pressure, trolley travel speed, and bridge angle) and real-time hydraulic condition data (including operating water depth, average reference flow velocity in the pipe, mud volume concentration, and instantaneous volumetric flow rate) are smoothed and subjected to short-term statistics (mean, variance, and rate of increase) within a unified time window, and the recent data is compared with historical baselines using a sliding window to determine the trend; when the absolute value of suction vacuum continues to increase and the discharge pressure approaches or exceeds a preset critical value, while the trolley propulsion speed decreases significantly or the bridge angle decreases, the system will perform a short-term statistical analysis. When the frame angle points to a deeper cutting range, the rule set determines this working condition as a signal of high-resistance soil layer entry. The determination result is used as an index to look up the recommended power allocation strategy in the pump set characteristic mapping table and pump-pipeline safety curve. The mapping table uses the current pump set load capacity, NPSH margin and target sludge volume flow rate as indexes, and outputs the target speed percentage of the main pump and auxiliary pump, along with the rate upper limit and priority. To avoid control jitter, hysteresis and maximum rate limits are applied to the output of the mapping table, and safety interlock conditions are embedded in the output (such as immediately reducing the load or stopping the pump if the instantaneous vacuum exceeds the limit). For sludge flow rate regulation, the design output is first compared with the real-time sludge flow rate. Then, the average reference flow velocity in the pipe under real-time hydraulic conditions and the maximum allowable velocity / pressure threshold of the pipeline are used to determine whether the pipeline has reached or is close to the capacity limit. If there is a risk of insufficient capacity or overpressure, the valve opening or pump speed is adjusted by looking up a table or by proportional adjustment to change the flow target. At the same time, the influence of sludge concentration on pipe resistance is considered and the flow target is compensated according to the concentration correction coefficient. All issued power and valve settings are packaged in the format of "target value + rate constraint + interlock threshold" and recorded for subsequent review and optimization.

[0069] In one implementation of this invention, assuming on-site monitoring shows the suction vacuum gradually increasing from -0.50 bar to -0.62 bar, the discharge pressure stabilizing at 0.90 bar, the trolley speed decreasing from 0.06 m / s to 0.03 m / s, and the bridge angle changing from -25° to -28°, these signals together indicate that the excavator has entered a soil layer with greater resistance. After consulting the mapping table, the system decides to reduce the main pump speed from 90% to 70% and increase the auxiliary pump speed from 60% to 85%, stipulating that the speed change per second should not exceed 5% (to prevent impact). Simultaneously, a vacuum threshold of -0.70 bar and a discharge pressure threshold of 9.5 bar are set as interlocks. Regarding mud transport... If the designed output is 7000 cubic meters per hour but the real-time measured output is 6500 cubic meters per hour, and the pipe diameter is 0.70 meters, based on a simple conversion (reference flow velocity ≈ volumetric flow rate ÷ pipe cross-sectional area), the current average reference flow velocity in the pipe is approximately 4.6 meters per second. If the target is to increase the flow velocity to avoid settling, the valve opening is adjusted from 55% to 65%. However, if the discharge pressure approaches 9.5 bar after adjustment, the system will revert and prompt for load reduction. All these adjustments will be issued to the execution unit with the instruction package "main pump 70%, auxiliary pump 85%, valve 65%, rate limit 5% / s, interlock threshold -0.70 bar / 9.5 bar", and will continue to be corrected based on subsequent feedback.

[0070] Of particular importance is that the process of issuing work instructions to the execution unit for dredging operations includes:

[0071] The cable tray adjusts its angle and draft according to the cable tray control commands;

[0072] The trolley moves forward or backward according to the trolley's advance command;

[0073] The mud pump is allocated its speed according to the mud pump power distribution command;

[0074] The mud conveying flow rate adjustment command adjusts the amount of mud and sand discharged through valve or pump speed control.

[0075] In the embodiments of this invention, the issuance and execution of work instructions is a "command packet - actuator - closed-loop feedback" process at the data level: the control module encapsulates target values ​​such as bridge angle and draft, trolley displacement and speed, target speed percentage of each pump, and valve opening into a construction work instruction packet. The instruction includes the target value, speed limit, priority identifier, and safety interlock threshold, and is sent to the corresponding driver through the ship's fieldbus or PLC channel; the bridge execution adopts position / force hybrid control (with angle sensor and trunnion draft sensor as feedback), and uses a proportional-integral-derivative closed loop with feedforward and acceleration limit and dead zone processing to prevent overshoot; the trolley execution adopts position tracking (encoder / displacement sensor feedback) and uses a trapezoidal speed profile or segmented speed... The angle curve is executed to meet acceleration and deceleration constraints, and synchronous interpolation is performed with the bridge angle command to ensure the cutting point trajectory; the mud pump speed is adjusted by frequency converter or excitation speed controller according to power distribution command, and the pump speed control uses current / speed / suction vacuum as closed loop quantities and adds NPSH and discharge pressure safety judgment; the valve uses proportional actuator or pump speed linkage to realize mud conveying flow regulation, and the flow rate is given by flow meter and mud concentration feedback and used for closed loop correction; all key quantities after execution (bridge angle, draft, trolley stroke, pump suction vacuum, discharge pressure, flow rate, mud density, etc.) are synchronously transmitted back according to timestamp, and the control module performs rate adjustment, load reduction or emergency shutdown according to priority based on real-time feedback, and records the original commands and feedback in the log for efficiency review and parameter optimization call.

[0076] like Figure 3 The diagram shown illustrates the construction process after receiving instructions.

[0077] In one implementation of the present invention, it is assumed that a specific command package issued on site includes: adjusting the target angle of the cable tray from -26° to -28° (maximum speed 0.5° / s), increasing the target draft of the cable tray by 0.5 meters, advancing the trolley by 0.5 meters (target speed 0.06 m / s, maximum acceleration 0.01 m / s²), setting the main pump speed to 70%, the auxiliary pump speed to 85%, the valve opening to 65%, and the interlock thresholds being suction vacuum -0.70 bar and discharge pressure 9.5 bar. During execution, the angle sensor and draft sensor transmit angle and depth data in real time, the encoder transmits trolley displacement data, and the pump pressure and flow sensor transmit air pressure and discharge pressure data, as well as production meter data. For example, if the production meter displays 7000 cubic meters per hour (i.e., 7000 ÷ 3600 ≈ 1.944 cubic meters per second), and the sludge conveying pipe has an inner diameter of 0.70 meters, the cross-sectional area is approximately 0.385 square meters, and the average flow velocity inside the pipe is approximately 1.944 ÷ 0.385 ≈ 5.05 meters per second. The control module uses this flow velocity and sludge concentration (e.g., 1100 kg / m³) to determine the sludge conveying safety margin: if the discharge pressure approaches the interlock threshold or the suction vacuum approaches the limit, the controller first reduces the main pump speed according to the rate limit and notifies the operator or executes a load reduction strategy. All actions and feedback are archived in time sequence for subsequent efficiency verification and parameter mapping updates.

[0078] Preferably, the dredging feedback data collected based on hull sensors and water sensors includes:

[0079] Dredging feedback data is collected based on hull sensors and water body sensors;

[0080] The dredging feedback data is compared with the construction operation instructions item by item to obtain the dredging construction efficiency verification data. The item-by-item comparison includes the production completion rate generated by comparing the feedback production curve with the target production; the comparison between pump power consumption and production to generate unit volume energy consumption; the comparison between the actual actions of the bridge frame and trolley and the bridge frame control instructions and the trolley propulsion instructions to construct the deviation curve; and the abnormal statistics formed by the exceedance of vacuum, pressure and sediment concentration.

[0081] The system will create a visual statistical report that includes production completion rate, unit energy consumption, deviation curves, and anomaly statistics, and output dredging construction efficiency verification data.

[0082] In embodiments of the present invention, the dredging feedback data from the hull sensor and the water sensor, along with the corresponding construction operation instructions, are resampled to a unified sampling frequency by timestamp, and noise reduction and outlier removal are performed. Then, each item is compared, and several efficiency indicators are calculated: for production completion rate, the completion rate is obtained by integrating the feedback production curve within the same statistical window and calculating the ratio with the designed production within that window; for unit energy consumption, the unit energy consumption indicator is obtained by integrating the pump power measurement value within the same time window and converting it into energy, then dividing this energy by the dredging volume during the same period; for position / trajectory deviation, the difference between the actual bridge angle and the bridge control command angle, and the difference between the actual trolley displacement and the trolley propulsion command are calculated at each time step. The difference is used to obtain the error time series, and the mean, root mean square, maximum deviation, and lag (estimated by cross-correlation) are calculated from it. For anomaly statistics, the real-time values ​​of vacuum, discharge pressure, and sediment concentration are compared with preset thresholds to determine the threshold. The number of times the limit is exceeded, the cumulative duration of the limit exceeding, and the maximum amplitude of the limit exceeding are counted by event segment, and instantaneous pulse and continuous limit exceeding are distinguished. Finally, the above indicators are aggregated into tabular KPIs, error curves, and alarm event tables according to the operation segment and time window. The statistical report is constructed with visualization components such as time series diagrams, bar charts, and segment heat maps. At the same time, the original measurement references and time segment indexes are retained in the report for backtracking and optimization calls. All results are output as structured records for optimization modules and operation and maintenance to keep track.

[0083] like Figure 4 The image shown is a visualization of the construction curve.

[0084] In one implementation of this invention, within a 10-minute statistical window, the designed output is 7000 cubic meters per hour (corresponding to a 10-minute target volume of 1166.67 cubic meters). After integrating the feedback output curve, the measured output is 1050 cubic meters, indicating an output completion rate of 90%. Simultaneously, the average power of the pump unit is approximately 1800 kW, and the energy consumption within 10 minutes is approximately 300 kWh. Dividing this by the dredging volume of 1050 cubic meters yields an energy consumption of approximately 0.286 kWh / cubic meter. The bridge control command requires an angle of -28.0 degrees, while the actual angle sequence average is... At 27.2 degrees, the mean deviation sequence is approximately 0.8 degrees, the root mean square is approximately 0.9 degrees, and a control lag of approximately 0.6 seconds is estimated through cross-correlation. The vacuum threshold is set to -0.70 bar and the discharge pressure threshold to 9.5 bar. The discharge pressure was measured to briefly surge to 9.8 bar for 15 seconds (counted as one sustained exceedance, with a cumulative exceedance duration of 15 seconds and a maximum exceedance of 0.3 bar). The sediment concentration remained around 1100 kg / m³ for most of the time without exceeding the limit. Based on this, the system reported a production completion rate of 90% and an energy consumption of 0.286 kWh / m³. 3The deviation curve (mean / RMS / maximum / hysteresis) and a record of a pressure relief abnormality event are saved together with the relevant time period and the original sensor data index for subsequent parameter adjustment or accountability review.

[0085] The optimization module updates the parameter mapping relationship of the construction operation instructions based on the dredging construction efficiency review data.

[0086] Preferably, the optimization module includes the following functions:

[0087] The output completion rate, unit energy consumption, deviation curves, and anomaly statistics are categorized to obtain index classification data;

[0088] The parameter adjustment status of the indicator classification data is determined to obtain the parameter data to be adjusted.

[0089] The parameter mapping relationship of the construction operation command is corrected based on the parameter data to be adjusted, thereby completing the dredging control operation of the inland waterway assembled cutter suction dredger.

[0090] In embodiments of this invention, dredging construction efficiency verification data (production completion rate, unit volume energy consumption, deviation curve, anomaly statistics) are used as input. The data is then segmented, summarized, denoised, and smoothed according to the work section and time window. The deviation of each indicator from the baseline or design target is calculated and standardized to a uniform scale. Next, the standardized deviations are categorized and prioritized. A rule set and lightweight classifier are used to classify the deviations into performance (low production), energy consumption (high unit volume energy consumption), accuracy (significant trajectory deviation), or safety (vacuum / pressure release / concentration exceeding limits), etc., and index classification results are generated accordingly. Subsequently, a parameter mapping table is retrieved based on the index classification results to obtain a set of candidate parameter adjustments. The parameter mapping table will then... Deviations from control parameters (such as pump speed parameters, power distribution coefficients, thresholds, bridge angle and trolley stroke control parameters, valve opening and rate limits) are correlated through empirical mapping, characteristic curves, or pre-trained mapping functions. Feasibility assessment and constraint optimization are performed on candidate adjustment sets. Linear / convex approximations with safety constraints or finite-step grid search are used to obtain limited parameter update amounts within allowable power, vacuum, and pressure limits. Hysteresis, rate limits, and minimum significant step sizes are applied to avoid control oscillations. Finally, the versioned parameter mapping updates with trigger reasons are written back to the parameter library. Small-step experimental adjustments are issued to the closed-loop control module according to a hierarchical strategy, and the adjustment effect is verified with similar indicators in the subsequent efficiency review window.

[0091] In one implementation of the present invention, the system calculates a production completion rate of 75% (target 100%) and a unit energy consumption of 0.40 kWh / m³ within a ten-minute window. 3 (Target 0.28kWh / m) 3The cable tray deviation averaged approximately 1.2 degrees with a maximum deviation of 3.5 degrees, and two short-term pressure exceeding limits were recorded, totaling 30 seconds. The optimization module first classified this window as "low production + high energy consumption + moderate trajectory error + safety event," and after searching the mapping table, obtained candidate strategies (prioritizing safety and energy consumption mitigation before pursuing production): It is recommended to slightly increase the main pump speed by 4% to supplement production, while increasing the valve opening by 3% to reduce pump head and improve energy efficiency; slightly increase the auxiliary pump power by 6% to share the load; adopt a tighter speed limit for cable tray position control and fine-tune the position closed-loop gain to reduce the average deviation by 0.5 degrees; all adjustments are issued with a rate limit of "no more than 2% speed change every 10 seconds and no more than 1% valve opening change every 10 seconds," and a safety interlock is set for vacuum -0.70 bar and pressure discharge 9.5 bar; if production recovers to approximately 82% and unit energy consumption drops to approximately 0.32 kWh / m³ in the next ten-minute window after issuance, the optimization strategy is considered successful. 3 If there are no records of pressure exceeding the limit, then confirm the mapping update and persist it; otherwise, restore the previous parameters according to the rollback rules and record the failure cases for subsequent mapping table correction.

[0092] Preferably, the determination of parameter tuning status for the indicator classification data includes the following:

[0093] The parameter adjustment status is determined by classifying the index data. If the output completion rate exceeds the limit, the pump speed parameter needs to be adjusted. If the unit energy consumption exceeds the limit, the power distribution coefficient needs to be adjusted. If the deviation curve and abnormal statistics exceed the limit, the bridge angle and trolley stroke control parameters need to be adjusted. The parameter adjustment data is obtained.

[0094] In this embodiment of the invention, a unified time window is used to aggregate production completion rate, unit energy consumption, trajectory deviation sequence, and abnormal event statistics, and compare them with historical baselines. Percentile or standard deviation methods are used to convert each indicator into a comparable deviation score. Then, the scores are mapped to the indicator classification results according to preset categories (performance, energy consumption, accuracy, and safety), and a priority score is calculated for each category. The priority score considers deviation magnitude, persistence (number of consecutive out-of-limit windows), and event severity. At the mapping level, rule tables and mapping tables are used to map each category of indicators to a set of candidate control parameters (such as pump speed, power distribution coefficient, bridge angle closed-loop gain, trolley displacement correction). The parameters (such as positive values, threshold settings, valve opening, etc.) are assigned a permissible range of variation, minimum step size, and rate limit. A feasibility assessment is performed on the candidate parameter set. Based on the equipment capacity curve (pump characteristics, NPSH margin), safety threshold, and constraint relationships, rapid constraint solving or grid search is used to eliminate adjustments that would lead to exceeding limits. The remaining feasible candidates are sorted by impact score (expected contribution to output / energy consumption / safety) and assigned a confidence level. The final output parameter adjustment data is a structured record, including parameter identifier, current value, suggested variation amount, variation boundary, expected effect, confidence level, and rollback strategy, for updating parameter mapping relationships and issuing small-step experiments.

[0095] It is particularly important to note that the parameter mapping table takes the deviation score as input and outputs the parameter adjustment amount. For example, when the production completion rate is less than 80%, the deviation score is increased by one point and the main pump speed is increased by 3%; when the unit energy consumption is greater than 0.35, the deviation score is increased by one point and the valve opening is increased by 5%; when the bridge deviation is greater than 1°, the deviation score is increased by two points and the angle closed-loop gain coefficient is increased by 1.2 times.

[0096] In one implementation of the present invention, within a ten-minute window, the system calculates the production completion rate as 65% (target 100%), the unit energy consumption as 0.42 kWh / m³ (target 0.28), the average trajectory deviation as 1.6 degrees, and the maximum deviation as 4.0 degrees. At the same time, it records two instances of pressure exceeding the limit for a total of 45 seconds. After standardized scoring, the scores show that "safety category" and "energy consumption category" take precedence over "production category". The mapping table retrieved candidate adjustments: fine-tuning of the closed-loop gain of the bridge angle and a slight retraction of the trolley travel to alleviate cutting resistance (it is recommended to raise the bridge angle by 0.8 degrees and retract the trolley by 0.15 meters, both within the single action rate limit); power distribution is recommended to reduce the main pump from 90% to 84% and increase the auxiliary pump from 60% to 70% to share the load; all candidates were checked for pump characteristics and vacuum / pressure relief constraints to confirm that they would not trigger the interlock threshold and were packaged as parameter adjustment items (including "main pump -6% / auxiliary pump +10% / bridge +0.8° / trolley -0.15m", rate limit "no more than 2% speed change or 0.5° angle change every 10 seconds", and retraction condition "if the pressure relief does not drop within 10 minutes and the output is still below 70%, then retract"). The parameter to be adjusted data not only records the reasons for adjustment (excessive pressure discharge and high energy consumption), but also includes the confidence level and rollback strategy. Then, it is sent to the closed-loop control in small-step tests to verify the actual effect.

[0097] Most importantly, when the data from the ship's hull sensors and the water sensors are abnormal, the system automatically switches to a conservative mode: fixing the bridge angle and trolley travel; reducing the mud pump power to 70% of the safety threshold; triggering a real-time alarm and waiting for manual intervention.

[0098] Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0099] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A dredging control system for an inland waterway assembled cutter suction dredger, characterized in that, Includes the following modules: The multi-source data acquisition module acquires data from ship hull sensors and water body sensors; it timestamps the data from the ship hull sensors and water body sensors to construct data for the first and second work units, respectively. The first work unit data includes bridge attitude data, trolley travel data, and mud pump pressure data; the second work unit data includes positioning and heading data, water level and depth data, and sediment transport data. The operational environment data construction module associates the data of the first operational unit with the three-dimensional space to obtain the river channel construction trajectory data; The load is identified from the data of the first work unit to generate equipment load status data, including: The operating status of the pressure equipment is analyzed based on the ultimate pressure value of the mud pump pressure data to obtain the pressure equipment status data. By combining the bridge angle data and trolley travel data, the load level of the pressure equipment is determined, and the load is divided based on the preset load threshold to obtain the equipment load status data. The data from the second operating unit are converted from water depth to velocity to generate real-time hydraulic condition data, including: Water level and depth data are corrected for depth to obtain corrected inland river water level data; The flow velocity distribution data is obtained by statistically analyzing the sediment transport data. Real-time hydraulic condition data is obtained by weighting inland river water level correction data and water flow velocity distribution data according to preset proportional weights; The closed-loop control module generates construction operation instructions based on river channel construction trajectory data, equipment load status data, and real-time hydraulic condition data, and sends them to the execution unit; it also collects dredging feedback data to obtain dredging construction efficiency verification data. The closed-loop control module includes the following functions: Acquire design cross-section data; compare the river channel construction trajectory data with the design cross-section data to generate unexcavated and excavated sections respectively; calculate the cutter head deviation in the unexcavated and excavated sections, and determine the bridge frame angle and depth based on the deviation data; determine the target travel of the trolley based on the bridge frame angle and depth; generate bridge frame control commands and trolley propulsion commands according to the bridge frame angle and depth and the trolley target travel. Based on equipment load status data and real-time hydraulic condition data, mud pump power allocation commands and mud conveying flow rate adjustment commands are constructed respectively. The construction operation instructions include bridge control instructions, trolley propulsion instructions, mud pump power allocation instructions, and mud conveying flow rate adjustment instructions. The construction operation instructions are issued to the execution unit to carry out dredging operations, and dredging feedback data is collected based on the ship's hull sensors and water sensors to obtain dredging construction efficiency verification data. The optimization module updates the parameter mapping relationship of the construction operation instructions based on the dredging construction efficiency review data.

2. The inland waterway assembled cutter suction dredger dredging control system according to claim 1, characterized in that, The operational environment data construction module includes the following functions: Align the positioning heading data and combine it with the bridge attitude data to generate terrain point cloud data; mark the construction trajectory points of the terrain point cloud data and perform 3D point cloud rasterization to construct river channel construction trajectory data. The load is identified from the data of the first work unit to generate equipment load status data; The water depth and velocity are converted from the data of the second working unit to generate real-time hydraulic condition data.

3. The inland waterway assembled cutter suction dredger dredging control system according to claim 1, characterized in that, The construction of mud pump power allocation commands and mud conveying flow rate adjustment commands based on equipment load status data and real-time hydraulic condition data includes: Based on the equipment load status data, determine whether the equipment is overloaded, and combine the analysis of the changes in the trolley stroke and bridge angle. If it is determined that the equipment has entered a high-resistance soil layer, reduce the main pump speed and increase the auxiliary pump speed; otherwise, do the opposite, thereby generating a mud pump power distribution command. Obtain the design output and real-time mud flow rate; compare the design output and real-time mud flow rate, and combine them with real-time hydraulic condition data to determine whether the mud conveying pipeline is too large, so as to adjust the valve opening and generate a mud conveying flow rate adjustment command.

4. The inland waterway assembled cutter suction dredger dredging control system according to claim 1, characterized in that, The dredging feedback data collected based on hull sensors and water sensors includes: Dredging feedback data is collected based on hull sensors and water body sensors; The dredging feedback data is compared with the construction operation instructions item by item to obtain the dredging construction efficiency verification data. The item-by-item comparison includes the production completion rate generated by comparing the feedback production curve with the target production; the comparison between pump power consumption and production to generate unit volume energy consumption; the comparison between the actual actions of the bridge frame and trolley and the bridge frame control instructions and the trolley propulsion instructions to construct the deviation curve; and the abnormal statistics formed by the exceedance of vacuum, pressure and sediment concentration. The system will create a visual statistical report that includes production completion rate, unit energy consumption, deviation curves, and anomaly statistics, and output dredging construction efficiency verification data.

5. The inland waterway assembled cutter suction dredger dredging control system according to claim 1, characterized in that, The optimization module includes the following functions: The output completion rate, unit energy consumption, deviation curves, and anomaly statistics are categorized to obtain index classification data; The parameter adjustment status of the indicator classification data is determined to obtain the parameter data to be adjusted. The parameter mapping relationship of the construction operation command is corrected based on the parameter data to be adjusted, thereby completing the dredging control operation of the inland waterway assembled cutter suction dredger.

6. The inland waterway assembled cutter suction dredger dredging control system according to claim 5, characterized in that, The determination of parameter adjustment status for indicator classification data includes: the following: The parameter adjustment status is determined by classifying the index data. If the output completion rate exceeds the limit, the pump speed parameter needs to be adjusted. If the unit energy consumption exceeds the limit, the power distribution coefficient needs to be adjusted. If the deviation curve and abnormal statistics exceed the limit, the bridge angle and trolley stroke control parameters need to be adjusted. The parameter adjustment data is obtained.

Images