Method and device for calculating and displaying dredging object volume based on multi-source sensing, equipment and medium

Abstract

The application discloses a dredging object volume calculation and display method and device based on multi-source sensing, equipment and medium, relates to the technical field of data measurement, and comprises the following steps: collecting multi-source data of vibration, photoelectricity and water level, constructing a dynamic vibration reference model and a dredging object shape profile, combining the water level to complete reference surface correction and initial volume calculation; after Kalman filtering calibration, inputting a fusion measurement model containing three modules to obtain a reference volume, and then performing credibility verification, total amount accumulation and threshold early warning to output a measurement result, which can truly reflect the dredging object shape, eliminate water level and noise interference, realize accurate measurement of single-bucket dredging object volume in the chain bucket type dredging object ship floating operation scene, and meet the accurate measurement and compliance supervision requirements of dredging objects on water.

Description

Technical Field

[0001] This invention relates to the field of data measurement technology, and in particular to a method, apparatus, equipment and medium for calculating and displaying the volume of dredged material based on multi-source sensing. Background Technology

[0002] Currently, the measurement and supervision of dredged materials in rivers and lakes are mostly achieved by a combination of single sensor monitoring and manual statistics. This mainly relies on the vibration sensor of the chain bucket dredging vessel to determine the equipment's operating status, photoelectric sensors to count the number of chain buckets, and single-point ultrasonic sensors to measure the height of the dredged material. Then, a simple volume formula is used to estimate the dredged material in a single bucket, and the total dredged material is obtained by summing them up.

[0003] Existing methods for calculating dredged material volume rely solely on a single measuring point and a simple formula, failing to reflect the true shape of the dredged material within the bucket. This leads to significant measurement errors due to empty buckets, half-full buckets, and irregular material distribution. Furthermore, they fail to consider reference plane deviations caused by water level changes and ship draft shifts, resulting in insufficient noise reduction and deviation calibration of raw sensor data and inadequate data reliability. The lack of a deep multi-source data fusion mechanism, relying instead on simple combinations of various sensor data, prevents adaptive measurement based on equipment operating conditions and dredged material morphology. Finally, the absence of a reliability verification mechanism for measurement results means abnormal data cannot be automatically identified and corrected, resulting in low measurement accuracy, poor anti-interference capabilities, delayed over-extraction warnings, and an incomplete regulatory loop. These shortcomings make it difficult to meet the actual needs for accurate measurement and compliant supervision under complex maritime conditions.

[0004] Therefore, how to achieve deep fusion measurement of multi-source sensor data to improve the accuracy and reliability of dredged material calculation for chain bucket dredgers and realize closed-loop early warning and supervision has become an urgent problem to be solved. Summary of the Invention

[0005] The main purpose of this application is to provide a method, device, equipment and medium for calculating and displaying the volume of dredged material based on multi-source sensing, which aims to solve the technical problem of how to achieve accurate measurement and early warning monitoring of the volume of dredged material in a single bucket in the floating operation scenario of a chain bucket dredger.

[0006] To achieve the above objectives, this application proposes a method for calculating and displaying the volume of dredged material based on multi-source sensing, comprising: Acquire multi-source sensor data, wherein the multi-source sensor data includes chain bucket vibration data, photoelectric triggering data, and water level data; A dynamic vibration benchmark model that distinguishes between unloaded and loaded states is established based on the aforementioned chain bucket vibration data. A profile of the dredged material pile is constructed based on the photoelectric triggering data; The dredged material pile profile was corrected to a reference plane based on the water level data, and the initial volume of a single bucket was obtained by volume calculation. The Kalman filter algorithm is used to perform noise cancellation and bias calibration on the multi-source sensor data to obtain calibrated multi-source sensor data. The calibrated multi-source sensor data, dredged material pile shape profile and single bucket initial volume are input into the multi-source sensor fusion measurement model to obtain the single bucket dredged material reference volume. The multi-source sensor fusion measurement model includes a working condition perception coding module, a shape correction module and an adaptive weighted fusion module. The reliability of the single-bucket dredged material reference volume is verified based on the dynamic vibration reference model to obtain the verified single-bucket dredged material reference volume. The cumulative calculation of the verified single-bucket dredged material reference volume is used to obtain the real-time dredged material total volume data of a single vessel. The real-time dredged material volume data of a single vessel is compared with the preset dredged material quota data, a threshold early warning mechanism is executed, and the dredged material measurement results are output and displayed.

[0007] In one embodiment, the step of establishing a dynamic vibration reference model that distinguishes between unloaded and loaded states based on the chain bucket vibration data includes: The chain bucket vibration data is subjected to bandpass filtering to obtain filtered vibration data; The root mean square value, peak factor, and skewness index are extracted from the filtered vibration data as time-domain statistical features. The filtered vibration data were subjected to a fast Fourier transform, and the main frequency energy ratio and the spectral centroid were extracted as frequency domain energy features. Based on the time-domain statistical characteristics and frequency-domain energy characteristics, construct an unloaded state characteristic sample set and a loaded state characteristic sample set; The unloaded state feature sample set and the loaded state feature sample set are labeled to obtain the labeled training sample set. The labeled training sample set is input into a preset classifier for model training to obtain a dynamic vibration benchmark model, wherein the dynamic vibration benchmark model outputs an unloaded state determination result or a loaded state determination result.

[0008] In one embodiment, the step of constructing the dredged material pile profile based on the photoelectric triggering data includes: The level transition edge of the laser diffuse reflection signal is detected based on the photoelectric trigger data, and the time of the chain bucket passing the photoelectric sensor is identified based on the level transition edge. The chain bucket transmission cycle is compensated for the elapsed time to obtain the arrival time of the chain bucket at the unloading position; At the specified arrival time, a synchronous trigger command is sent to the multi-point ultrasonic sensor array so that the multi-point ultrasonic sensor array can synchronously measure the distance of the dredged material surface in the bucket and obtain multi-point ultrasonic ranging data. Based on the spatial installation coordinates of each sensor in the multi-point ultrasonic sensor array, the multi-point ultrasonic ranging data is mapped into three-dimensional point cloud data of the surface of the dredged material in the bucket. The 3D point cloud data is subjected to profile fitting to obtain the dredged material pile profile.

[0009] In one embodiment, the step of correcting the dredged material pile profile to a reference plane using the water level data and calculating the initial volume of a single bucket includes: Calculate the water level difference based on the water level data and the preset empty reference water level value; The change in hull draft is obtained by linear interpolation based on the water level difference and preset hull drainage characteristic parameters. Calculate the vertical offset of the ultrasonic sensor mounting reference plane based on the change in the ship's draft; Based on the vertical offset, the elevation of each ranging point of the dredged material pile profile is corrected using a reference plane to obtain the corrected dredged material pile profile. The modified dredged material pile profile is subjected to cross-sectional integration along the length of the bucket to obtain a sequence of single bucket cross-sectional areas; The initial volume of a single bucket is obtained by performing a volume accumulation calculation based on the single bucket cross-sectional area sequence and the bucket width parameter of the chain bucket.

[0010] In one embodiment, the step of inputting the calibrated multi-source sensor data, dredged material pile profile, and initial volume of a single bucket into the multi-source sensor fusion metrology model to obtain the reference volume of dredged material in a single bucket includes: The working condition sensing coding module is used to distinguish between the unloaded and loaded states of the chain bucket vibration data in the calibrated multi-source sensor data to obtain a single bucket effectiveness label. The working condition features are extracted from the chain bucket vibration data and water level data in the calibrated multi-source sensor data to obtain the current excavation working condition encoding vector. The edge integrity index and surface roughness index of the dredged material pile profile are calculated using the shape correction module to obtain the pile shape reliability coefficient. Based on the pile shape confidence coefficient, the initial volume of the single bucket is shaped and corrected to obtain the corrected volume of the single bucket. The single-bucket effectiveness label, the current excavation condition encoding vector, and the corrected single-bucket volume are input into the adaptive weighted fusion module. The start and stop status of the fusion calculation is controlled according to the single-bucket effectiveness label. The morphological correction weight coefficient and the condition adaptive weight coefficient are obtained by querying the preset condition weight mapping table according to the current excavation condition encoding vector. The corrected single-bucket volume is weighted and fused based on the morphological correction weight coefficient and the working condition adaptive weight coefficient to obtain the single-bucket dredged material reference volume.

[0011] In one embodiment, the step of verifying the reliability of the single-bucket dredged material reference volume based on the dynamic vibration reference model to obtain the verified single-bucket dredged material reference volume includes: Input the chain bucket vibration data of the current bucket into the dynamic vibration benchmark model to obtain the load state confidence of the current bucket. Perform time-series difference operation on the multi-point ultrasonic ranging data of the current round to obtain the ranging change sequence at adjacent ranging times, and extract the maximum jump variable in the ranging change sequence. When the confidence level of the loaded state is greater than the preset confidence threshold and the maximum jump variable is less than the preset jump tolerance condition, the single bucket dredged material reference volume is used as the verified single bucket dredged material reference volume. When the confidence level of the loaded state is less than or equal to the preset confidence threshold, or when the maximum jump variable is greater than or equal to the preset jump tolerance condition, the current bucket is marked as an abnormal bucket, and the single bucket dredged material reference volume is replaced and corrected by the sliding window mean to obtain the verified single bucket dredged material reference volume.

[0012] In one embodiment, the steps of comparing the real-time dredged material volume data of a single vessel with preset dredged material quota data, executing a threshold early warning mechanism, and outputting and displaying the dredged material measurement results include: The quota consumption ratio is calculated based on the real-time dredged material total data of a single vessel and the preset dredged material quota data, and the remaining quota ratio is obtained based on the quota consumption ratio. The remaining quota percentage is input into the multi-level threshold discrimination module to obtain the current warning level; Based on the current warning level, a preset warning action mapping table is queried to obtain a target warning action set, wherein the target warning action set includes at least one of local audio-visual prompt action, remote platform push action, and on-site evidence collection trigger action. Generate early warning control instructions based on the target early warning action set; The warning control command is sent to the shipborne audible and visual alarm, so that the shipborne audible and visual alarm performs a local audible and visual prompt action. The early warning control command is sent to the remote monitoring platform so that the remote monitoring platform can perform a remote platform push action and store the real-time total amount of dredged material of a single vessel. The warning control command is sent to the shipborne camera equipment so that the shipborne camera equipment can perform on-site evidence collection triggering action and transmit back evidence collection image data; Receive confirmation receipt information returned by the remote monitoring platform; The system integrates the real-time dredged material volume data of a single vessel, the current warning level, the target warning action set, and the confirmation receipt information to generate and display the dredged material measurement results.

[0013] Furthermore, to achieve the above objectives, this application also proposes a device for calculating and displaying the volume of dredged material based on multi-source sensing, the device comprising: The acquisition module is used to acquire multi-source sensor data, wherein the multi-source sensor data includes chain bucket vibration data, photoelectric triggering data, and water level data; The vibration modeling module is used to establish a dynamic vibration benchmark model that distinguishes between unloaded and loaded states based on the chain bucket vibration data. The profile construction module is used to construct a profile of the dredged material pile based on the photoelectric triggering data; The volume calculation module is used to correct the reference plane of the dredged material pile shape profile by combining the water level data, and obtain the initial volume of a single bucket through volume calculation. The calibration module is used to perform noise cancellation and bias calibration on the multi-source sensor data using a Kalman filter algorithm to obtain calibrated multi-source sensor data. The metering module is used to input the calibrated multi-source sensor data, dredged material pile shape profile and single bucket initial volume into the multi-source sensor fusion metering model to obtain the single bucket dredged material reference volume. The multi-source sensor fusion metering model includes a working condition perception coding module, a shape correction module and an adaptive weighted fusion module. The verification module is used to verify the reliability of the single-bucket dredged material reference volume based on the dynamic vibration reference model, and obtain the verified single-bucket dredged material reference volume. The calculation module is used to cumulatively calculate the verified single-bucket dredged material reference volume to obtain the real-time dredged material total volume data of a single vessel. The results module is used to compare the real-time total dredged material data of a single vessel with the preset dredged material quota data, execute the threshold early warning mechanism, and output the dredged material measurement results for display.

[0014] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the method for calculating and displaying the volume of dredged material based on multi-source sensing as described above.

[0015] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the method for calculating and displaying dredged material volume based on multi-source sensing as described above.

[0016] This application constructs a dynamic vibration benchmark model and a dredged material pile shape profile by collecting multi-source data of vibration, photoelectric, and water level. The benchmark surface is corrected and the initial volume is calculated by combining water level data. After Kalman filtering calibration, the benchmark volume is obtained by inputting the fusion measurement model containing three modules. The measurement results are then output and displayed after reliability verification, total accumulation, and threshold warning. This can accurately reflect the dredged material pile shape, eliminate water level and noise interference, and achieve accurate measurement of the volume of dredged material in a floating operation scenario of a chain bucket dredger, meeting the requirements for accurate measurement and compliant supervision of dredged materials on water. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the first embodiment of the method for calculating and displaying the volume of dredged material based on multi-source sensing in this application. Figure 2 This is a flowchart illustrating the second embodiment of the method for calculating and displaying the volume of dredged material based on multi-source sensing in this application; Figure 3 This is a schematic diagram of the module structure of the dredged material volume calculation and display device based on multi-source sensing in this application; Figure 4 This is a schematic diagram of the hardware operating environment involved in the method for calculating and displaying the volume of dredged material based on multi-source sensing in the embodiments of this application.

[0019] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0021] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0022] Currently, the measurement and supervision of dredged materials in rivers and lakes are mostly achieved by a combination of single sensor monitoring and manual statistics. This mainly relies on the vibration sensor of the chain bucket dredging vessel to determine the equipment's operating status, photoelectric sensors to count the number of chain buckets, and single-point ultrasonic sensors to measure the height of the dredged material. Then, a simple volume formula is used to estimate the dredged material in a single bucket, and the total dredged material is obtained by summing them up.

[0023] Current methods for calculating dredged material volume rely solely on single measuring points and simple formulas, failing to reflect the true shape of the dredged material within the bucket. This leads to significant measurement errors due to empty buckets, half-full buckets, and irregular material distribution. Furthermore, they neglect reference plane deviations caused by water level changes and hull draft shifts, resulting in insufficient noise reduction and deviation calibration of raw sensor data and inadequate data reliability. The lack of a deep multi-source data fusion mechanism, relying solely on simple combinations of various sensor data, fails to achieve adaptive measurement based on equipment operating conditions and dredged material morphology. The absence of a reliability verification mechanism for measurement results prevents automatic identification and correction of abnormal data, resulting in low dredged material measurement accuracy, poor anti-interference capabilities, delayed over-extraction warnings, and incomplete regulatory loops. These shortcomings make it difficult to meet the practical needs of accurate measurement and compliant supervision under complex maritime conditions. Therefore, achieving deep multi-source sensor data fusion measurement to improve the accuracy and reliability of dredged material calculations for bucket-type dredgers and to realize closed-loop early warning and supervision is an urgent problem to be solved.

[0024] Based on the above, this application also provides a method for calculating and displaying the volume of dredged material based on multi-source sensing, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the method for calculating and displaying the volume of dredged material based on multi-source sensing in this application.

[0025] In this embodiment, the method for calculating and displaying the volume of dredged material based on multi-source sensing includes steps S10 to S90: Step S10: Acquire multi-source sensor data.

[0026] It should be noted that the multi-source sensor data includes chain bucket vibration data, photoelectric trigger data, and water level data. Chain bucket vibration data refers to the vibration signal values ​​generated by the chain bucket during operation, which directly reflects whether the chain bucket is operating under no-load or load. Photoelectric trigger data refers to the level change signal generated when the photoelectric sensing device detects the passing of the chain bucket; this signal is used to mark the time point when the chain bucket reaches a designated position. Water level data refers to the real-time water level height value monitored within the operating area, which reflects changes in the on-site water environment.

[0027] Specifically, firstly, vibration sensors are installed on the chain bucket drive bearing housing of the dredger, photoelectric sensors are installed on the fixed brackets along the chain bucket's path, and water level sensors are installed near the waterline on the hull side. These three types of sensors are connected to the embedded microprocessor of the dredged material metering terminal via wired or wireless means. Secondly, synchronous data acquisition is performed according to a preset sampling frequency. The vibration sensors collect triaxial vibration signals of the chain bucket at a higher frequency, the photoelectric sensors detect level transition signals as the chain bucket passes by at a medium frequency, and the water level sensors monitor changes in the current water level elevation at a lower frequency, obtaining chain bucket vibration data, photoelectric trigger data, and water level data, respectively. Finally, the collected data is timestamped and managed in a cache queue, establishing a multi-source data set under a unified time-series coordinate system to ensure accurate retrieval of sensor data according to the time sequence during subsequent processing. This is done because the dredging vessel operates in a complex environment, and a single sensor cannot fully reflect the state of the dredged material. Vibration data is used to determine whether the bucket has dug up the dredged material, photoelectric data is used to lock the time when the bucket is in position, and water level data is used to compensate for the drift of the measurement reference caused by the floating of the hull. Only by working together can the three can key information such as "whether dredged material has been dug", "when to measure", and "where the reference is" be covered. Moreover, timestamp alignment is the basis for subsequent fusion calculations.

[0028] Step S20: Establish a dynamic vibration benchmark model that distinguishes between unloaded and loaded states based on the chain bucket vibration data.

[0029] It should be noted that step S20 includes: performing bandpass filtering on the chain bucket vibration data to obtain filtered vibration data; extracting the root mean square value, peak factor, and skewness index from the filtered vibration data as time-domain statistical features; performing fast Fourier transform on the filtered vibration data and extracting the main frequency energy ratio and spectral centroid as frequency-domain energy features; constructing an unloaded state feature sample set and a loaded state feature sample set based on the time-domain statistical features and frequency-domain energy features; labeling the unloaded state feature sample set and the loaded state feature sample set to obtain a labeled training sample set; inputting the labeled training sample set into a preset classifier for model training to obtain a dynamic vibration benchmark model, wherein the dynamic vibration benchmark model outputs an unloaded state determination result or a loaded state determination result.

[0030] It's important to understand that bandpass filtering refers to a process that retains signals within a specific frequency range while eliminating interference signals from other frequencies. This process can remove invalid vibration signals introduced by the environment and equipment. Time-domain statistical characteristics refer to quantitative indicators extracted from the temporal variation patterns of the signal. These indicators directly reflect the amplitude and distribution characteristics of the vibration signal. Frequency-domain energy characteristics refer to energy distribution indicators extracted after converting the signal to the frequency dimension. These indicators characterize the frequency composition and energy concentration of the vibration signal.

[0031] Specifically, firstly, vibration data of the dredging vessel is collected under two conditions: unloaded operation (the bucket is idling without contacting the riverbed) and loaded operation (the bucket is dredging dredged material). Preset durations (e.g., 30 minutes each) are extracted as the original unloaded and original loaded samples, respectively. Bandpass filtering is then applied to both types of original samples to retain the effective frequency band (e.g., 10Hz-500Hz) and remove high-frequency mechanical noise and low-frequency hull sway interference, resulting in filtered vibration data. Secondly, time-domain and frequency-domain features are extracted from the filtered vibration data: in the time domain, the root mean square value reflects the magnitude of vibration energy, the peak factor reflects the impact characteristics, and the skewness index reflects the asymmetry of distribution. In the frequency domain, the time-domain signal is converted into a spectrum using a fast Fourier transform. The proportion of dominant frequency energy reflects the degree of vibration energy concentration, and the centroid of the spectrum reflects the centroid of frequency distribution. The five-dimensional time-domain statistical features and frequency-domain energy features are combined into a feature vector, constructing feature sample sets for both unloaded and loaded states. Then, the unloaded state feature sample set is uniformly labeled as category 0, and the loaded state feature sample set is uniformly labeled as category 1, resulting in a labeled training sample set. Finally, the labeled training sample set is input into a preset classifier (such as support vector machine or random forest) for supervised training. The model hyperparameters are adjusted through cross-validation to obtain a dynamic vibration benchmark model. This model outputs the unloaded state determination result or the loaded state determination result after inputting new chain bucket vibration data. This is done because there is a fundamental difference in the vibration mode of the chain bucket when it is idling and when dredging—when idling, the vibration pattern is stable, the main frequency is concentrated, and there are few impacts. When dredging, the vibration is violent due to the impact and friction of the dredged material, the spectrum is dispersed, and there are frequent impacts. Simply relying on a fixed threshold cannot adapt to the changing working conditions of different ship types and different riverbed hardness. However, by establishing a dynamic benchmark model through machine learning, it can adaptively learn the vibration fingerprints of the two working conditions and achieve more accurate state discrimination.

[0032] Step S30: Construct a profile of the dredged material pile based on photoelectric triggering data.

[0033] It should be noted that step S30 includes: detecting the level transition edge of the laser diffuse reflection signal based on the photoelectric trigger data, and identifying the passing time of the bucket chain through the photoelectric sensor based on the level transition edge; performing bucket chain transmission cycle compensation on the passing time to obtain the arrival time of the bucket chain at the unloading position; sending a synchronous trigger command to the multi-point ultrasonic sensor array at the arrival time to enable the multi-point ultrasonic sensor array to synchronously measure the distance of the dredged material surface in the bucket, and obtaining multi-point ultrasonic ranging data; mapping the multi-point ultrasonic ranging data into three-dimensional point cloud data of the dredged material surface in the bucket based on the spatial installation coordinates of each sensor in the multi-point ultrasonic sensor array; and performing profile fitting on the three-dimensional point cloud data to obtain the dredged material pile profile.

[0034] It's important to understand that laser diffuse reflection signal refers to the light signal emitted by a photoelectric sensor and received after reflection from an object; the signal strength changes accordingly as the object approaches or moves away. A level transition edge refers to the instantaneous point when an electrical signal changes from low to high or vice versa; this point can be used to mark the accurate time elapsed by an object. Chain bucket drive cycle compensation refers to correcting time points based on the actual operating speed of the chain bucket, aiming to eliminate time deviations caused by the transmission mechanism. A multi-point ultrasonic sensor array refers to multiple ultrasonic ranging units arranged in fixed spatial positions; multiple units can simultaneously acquire ranging information from different locations. Three-dimensional point cloud data refers to a discrete set of points containing spatial coordinate information; this set of points can completely reflect the three-dimensional morphological distribution of an object's surface. Profile fitting refers to smoothing and constructing curves from discrete point data; the constructed result can visually present the morphological contour of a specified cross-section.

[0035] Specifically, firstly, a laser diffuse reflection photoelectric switch is installed on the fixed bracket of the bucket chain drive. When the bucket passes through the detection area of ​​the photoelectric switch, the switch outputs a level transition signal. The dredged material metering terminal detects this level transition edge and records the current time through interrupt capture, thus obtaining the passage time of the bucket passing the photoelectric sensor. Secondly, the passage time is compensated based on the preset transmission cycle of the bucket drive system (i.e., the time interval between two adjacent buckets passing the same position, such as 2.5 seconds). The compensation time required for the bucket to travel from the photoelectric sensor position to directly above the unloading position is calculated. The passage time is then added to the compensation time to obtain the arrival time of the bucket at the unloading position. Then, at the arrival time, a synchronous trigger command is sent to the multi-point ultrasonic sensor array, causing each sensor in the array to measure the distance to the surface of the dredged material in the bucket at the same time, obtaining multi-point ultrasonic ranging data reflecting the elevation distribution of the dredged material surface. Next, based on the preset spatial installation coordinates of each sensor in the multi-point ultrasonic sensor array (e.g., a grid layout with a horizontal spacing of 10 cm and a vertical spacing of 15 cm), the ranging data are mapped into three-dimensional point cloud data with the center of the bucket as the origin through geometric transformation, with each ranging value corresponding to a three-dimensional spatial coordinate. Finally, the least squares method or spline interpolation is used to perform profile fitting on the three-dimensional point cloud data to obtain a smooth and continuous dredged material pile profile. This is done because the chain bucket experiences position drift and speed fluctuations during transmission. Directly using the photoelectric trigger moment as the measurement moment would miss the optimal measurement window (the bucket may not have reached or has already left the unloading position). Transmission cycle compensation can accurately lock the unloading position moment. Compared with single-point ranging, multi-point synchronous ranging can completely depict the natural accumulation morphology of the dredged material in the bucket (e.g., central bulge, edge collapse, or off-center load distribution), avoiding volume estimation errors caused by simply treating irregular piles as cuboids. Profile fitting transforms discrete ranging points into continuous surfaces that can be used for subsequent integration calculations.

[0036] Step S40: Based on the water level data, the dredged material pile profile is corrected to a reference plane, and the initial volume of a single bucket is obtained through volume calculation.

[0037] It should be noted that step S40 includes: calculating the water level difference based on the water level data and the preset empty reference water level value; performing linear interpolation calculation based on the water level difference and preset hull drainage characteristic parameters to obtain the hull draft change; calculating the vertical offset of the ultrasonic sensor installation reference plane based on the hull draft change; correcting the elevation of each ranging point of the dredged material pile profile based on the vertical offset to obtain the corrected dredged material pile profile; performing cross-sectional integration calculation along the length of the bucket to obtain the single bucket cross-sectional area sequence; and performing volume accumulation calculation based on the single bucket cross-sectional area sequence and the bucket width parameter to obtain the initial volume of the single bucket.

[0038] It's important to understand that the hull displacement characteristic parameters refer to fixed parameters that characterize the relationship between the volume of dredged material entering the water and its draft. These parameters are stable and unchanging, adapted to the ship's structural characteristics. Vertical offset refers to the vertical displacement of the ultrasonic sensor's mounting reference plane as the ship floats and sinks; this offset directly changes the initial reference height for distance measurement. Cross-sectional integration calculation refers to the calculation method of integrating along a fixed direction over a continuous cross-sectional profile. This calculation can accurately obtain the actual area of ​​irregular cross-sections. Volumetric summation calculation combines cross-sectional area and lateral span to perform spatial volume conversion; this conversion method is suitable for solving volume problems involving irregular materials.

[0039] Specifically, firstly, the current water level elevation data output by the water level sensor is read and compared with a preset no-load reference water level value (such as the water level elevation corresponding to the ship's design draft) to obtain the water level difference. Secondly, linear interpolation is performed based on the water level difference and preset hull displacement characteristic parameters (such as the draft change in centimeters corresponding to each ton of displacement) to obtain the hull draft change; for example, if a 10 cm rise in water level causes the hull to sink by 5 cm, the draft change is 5 cm. Then, based on the fixed installation height of the ultrasonic sensor array on the hull and the hull draft change, the vertical offset of the sensor installation reference plane relative to the water surface is calculated, i.e., the installation height minus the draft change to obtain the actual measurement reference height. Next, based on the vertical offset, the elevation of each ranging point in the dredged material pile profile is uniformly compensated and corrected. The actual elevation of each ranging point is equal to the original ranging value plus the vertical offset, resulting in the corrected dredged material pile profile, restoring all ranging data to a unified reference under the design draft state. Then, cross-sectional integration is performed on the corrected dredged material pile profile along the length of the bucket. The profile curve is divided into multiple transverse sections at a preset step size (e.g., per centimeter), and the area value of each section is calculated to obtain a single bucket cross-sectional area sequence. Finally, volume accumulation is performed based on the single bucket cross-sectional area sequence and the bucket width parameter. The area of ​​each section is multiplied by the bucket width and then accumulated along the length to obtain the initial volume of the single bucket. This is done because the dredger is a floating platform, and fluctuations in water level and changes in ship load will cause the hull to heave and trim. If the ultrasonic ranging reference plane is not corrected, the same bucket will measure different heights under different water level conditions, introducing systematic errors. Real-time compensation using water level data can uniformly restore the measurement reference to the design draft, ensuring the consistency of volume calculation. Compared with simple height multiplication by bottom area, cross-sectional integration can more accurately reflect the irregular accumulation shape of the dredged material in the bucket.

[0040] Step S50: The Kalman filter algorithm is used to perform noise cancellation and bias calibration on the multi-source sensor data to obtain calibrated multi-source sensor data.

[0041] It should be noted that the Kalman filter algorithm is a data processing algorithm with recursive optimization capabilities, which can continuously correct random interference components in monitoring data. Noise cancellation refers to removing irregular and chaotic interference information from multi-source sensor data, as this chaotic interference information can interfere with the calculation of normal measurement results. Deviation calibration refers to correcting the fixed measurement errors that exist between different sensing devices, thereby unifying the measurement standards of various types of collected data.

[0042] Specifically, firstly, the vibration data, photoelectric triggering data, multi-point ultrasonic ranging data, and water level data of the bucket were time-stamped and aligned. Using the high-frequency sampling time of the vibration data as a reference, the other three types of low-frequency data were resampled to a unified time-series coordinate system through nearest-neighbor interpolation or linear interpolation to establish a multi-source observation sequence. Secondly, a state-space model of a Kalman filter was constructed: the state variables were set as the estimated volume of dredged material in a single bucket and its first-order rate of change, and the observation variables were set as the volume calculated by ultrasonic ranging, the volume indirectly estimated by vibration energy, and the geometric volume corrected by water level. The filter parameters were initialized based on the preset measurement noise covariance matrix of each sensor (e.g., ultrasonic noise variance 0.001, vibration noise variance 0.05) and the preset state transition matrix (e.g., the volume change rate follows a Markov process). Then, using the prediction-update recursive mechanism of Kalman filtering, the multi-source observation sequence is estimated time-by-time optimally: the prediction step calculates the prior volume estimate for the next time step based on the state transition matrix; the update step calculates the Kalman gain based on the deviation between the actual observation and the prior estimate; and the prior estimate and observation information are fused to obtain the posterior optimal estimate. Finally, the original data of each sensor are compensated for deviations based on the filtered state estimates (e.g., when there is a fixed installation angle deviation in ultrasonic ranging, the compensation amount is inferred from the state estimate), and the calibrated multi-source sensor data is output. This is done because the sampling frequency, dimensions, and noise characteristics of the four types of sensors differ significantly (vibration is acceleration, photoelectric is switching, ultrasound is distance, and water level is elevation). Direct fusion would lead to dimensional conflicts and noise amplification; Kalman filtering, through unified state-space modeling, can achieve optimal weighted fusion in the time dimension, suppressing random noise and calibrating system biases, providing clean and reliable input for subsequent fusion metrology models.

[0043] Step S60: Input the calibrated multi-source sensor data, dredged material pile profile and single bucket initial volume into the multi-source sensor fusion metrology model to obtain the single bucket dredged material reference volume.

[0044] It should be noted that the multi-source sensor fusion metrology model includes a condition-aware encoding module, a morphology correction module, and an adaptive weighted fusion module. The condition-aware encoding module is the core input processing module of the multi-source sensor fusion metrology model, used to extract and encode features from the calibrated multi-source sensor data, transforming the data into condition feature vectors that can be used for subsequent calculations. The morphology correction module is an intermediate correction module of the multi-source sensor fusion metrology model, used to specifically correct the initial volume of a single bucket based on the morphological characteristics of the dredged material's pile shape profile, conforming to the actual pile shape of the dredged material. The adaptive weighted fusion module is the output calculation module of the multi-source sensor fusion metrology model, used to complete the fusion calculation through dynamic weight allocation based on the condition characteristics and the corrected volume data, outputting the final reference volume.

[0045] Specifically, firstly, the calibrated multi-source sensor data, dredged material pile profile, and initial single-bucket volume are input into the multi-source sensor fusion metrology model. The working condition perception coding module analyzes the current bucket vibration data and water level data to reflect the excavation conditions (such as riverbed hardness and dredged material compaction), generating a current excavation condition coding vector and outputting a single-bucket validity label to determine whether the current bucket operation is in an effective loading state. Secondly, the integrity of the dredged material pile profile is evaluated by the morphology correction module. A pile shape reliability coefficient is calculated based on edge coverage integrity and surface smoothness. Based on this coefficient, the initial single-bucket volume is reliably corrected to obtain the corrected single-bucket volume. Finally, the adaptive weighted fusion module dynamically allocates the weight ratios of each data source according to the current excavation condition coding vector. Based on these weight ratios, a weighted fusion calculation is performed on the corrected single-bucket volume, outputting the single-bucket dredged material reference volume. This is done because dredging operations face complex and ever-changing riverbed environments, and the reliability of various sensors varies significantly under different working conditions. By using a three-module hierarchical fusion, the effectiveness of each dredging operation can be determined first, then the morphological deviation can be corrected, and finally adaptive weighting can be performed to achieve a layer-by-layer purification from raw data to reliable volume, thus avoiding the risk of failure of a single data source under specific working conditions.

[0046] Step S70: Verify the reliability of the single-bucket dredged material reference volume based on the dynamic vibration reference model to obtain the verified single-bucket dredged material reference volume.

[0047] It should be noted that step S70 includes: inputting the chain bucket vibration data of the current bucket cycle into the dynamic vibration benchmark model to obtain the load state confidence of the current bucket cycle; performing time-series difference operation on the multi-point ultrasonic ranging data of the current bucket cycle to obtain the ranging change sequence at adjacent ranging times, and extracting the maximum jump variable in the ranging change sequence; when the load state confidence is greater than the preset confidence threshold and the maximum jump variable is less than the preset jump tolerance condition, the single bucket dredged material benchmark volume is used as the verified single bucket dredged material benchmark volume; when the load state confidence is less than or equal to the preset confidence threshold, or the maximum jump variable is greater than or equal to the preset jump tolerance condition, the current bucket cycle is marked as an abnormal bucket cycle, and the single bucket dredged material benchmark volume is replaced and corrected by using the sliding window mean to obtain the verified single bucket dredged material benchmark volume.

[0048] It's important to understand that the load-bearing state confidence level refers to the degree of confidence that the dynamic vibration benchmark model determines the current bucket chain is under load; this value quantifies the reliability of the state identification result. Time-series difference calculation refers to the operation of calculating the difference between monitoring data from consecutive time points; this operation can quickly capture sudden data changes within a short period. The distance change sequence refers to an ordered set of difference data calculated from adjacent distance measurement times; this set can comprehensively reflect the dynamic fluctuations of the distance measurement values ​​on the dredged material surface. The sliding window mean refers to the calculation method of selecting multiple consecutive sets of normal measurement data to obtain the average value; this method can smoothly replace abnormal values, thus weakening the interference of sudden errors.

[0049] Specifically, firstly, the chain bucket vibration data of the current bucketing cycle is input into a pre-trained dynamic vibration benchmark model. The model performs pattern matching based on the time-domain statistical characteristics and frequency-domain energy characteristics of this bucketing cycle, outputting a confidence score indicating that the current bucketing cycle belongs to the loaded state. The higher the score, the greater the probability that the current bucketing cycle has dredged material. Secondly, time-series difference operations are performed on the multi-point ultrasonic ranging data of the current bucketing cycle. The ranging values ​​at adjacent ranging times are subtracted to obtain a series of ranging changes. From this series, the jump variable with the largest absolute value is identified. This jump variable reflects whether there are any abnormal abrupt changes during the ranging process (such as a sudden increase in the ranging value at a certain moment due to water surface splash interference). Then, the confidence level of the loaded state is compared with the preset confidence threshold, and the maximum jump variable is compared with the preset jump tolerance condition. When the confidence level of the loaded state is greater than the preset confidence threshold and the maximum jump variable is less than the preset jump tolerance condition, both conditions are met, indicating that the vibration mode of the current bucket cycle conforms to the characteristics of the loaded state and the ultrasonic ranging is stable without sudden changes. The data is deemed reliable, and the single bucket dredged material reference volume is directly output as the verified single bucket dredged material reference volume. Finally, when the confidence level of the loaded state is less than or equal to the preset confidence threshold, or the maximum jump variable is greater than or equal to the preset jump tolerance condition, the failure of either condition indicates an anomaly (e.g., low confidence level may be due to an empty bucket colliding with rocks, and a large jump variable may be due to ultrasonic waves encountering water splash). The current bucket cycle is marked as an abnormal bucket cycle, and the historical normal bucket cycle volume data of the most recent preset window number (e.g., 5 buckets) is retrieved to calculate the sliding window mean. This mean is used to replace the single bucket dredged material reference volume of the current bucket cycle to obtain the verified single bucket dredged material reference volume. This is done because the on-site environment of dredged materials is harsh, and a single verification condition is easily breached (for example, the vibration characteristics when the hull is shaking violently may be misjudged as being under load). Dual-condition joint verification can cross-verify from two independent dimensions, vibration mode and distance measurement stability, which greatly reduces the probability of misjudgment. The sliding window mean substitution mechanism avoids abnormal data from directly entering the accumulation process, which would cause the total amount to be distorted, thus ensuring the continuity and reliability of the total amount of dredged materials statistics.

[0050] Step S80: The cumulative volume of dredged material in a single bucket after verification is calculated to obtain the total amount of dredged material in real time for a single vessel.

[0051] Specifically, a single-vessel dredged material total accumulator is established in the memory of the dredged material metering terminal, initialized to zero. After each bucket's reliability verification is completed, the baseline volume of dredged material in that bucket is read and added to the current stored value of the accumulator, updating the real-time dredged material total data for the single vessel in the accumulator. Secondly, according to a preset visualization update cycle (e.g., every 5 minutes), the current total data is read from the accumulator to generate time-series visualization charts (e.g., a line graph of dredged material for the day, a bar chart of bucket efficiency for each time period, and a dashboard of current dredged material rate), and the chart data is encoded into a preset network transmission format (e.g., JSON or binary stream). Finally, the visualization chart data is sent to the web server of the remote monitoring platform via a wireless communication module, allowing monitoring personnel to view the dredged material progress in real time through a browser. This is done because regulatory authorities need to know the real-time operational intensity of dredgers. Cumulative calculation is the final aggregation of measurement results. Only by adding up the dredged material from each bucket to the total can the actual scale of mining be reflected. Visualization is a necessary part of human-computer interaction. Transforming dry numbers into intuitive charts helps to detect anomalies in dredged material in a timely manner (such as a sudden drop in efficiency at a certain time, which may indicate equipment failure or changes in the riverbed), making it easier for regulatory personnel to make quick decisions.

[0052] Step S90: Compare the real-time total dredged material data of a single vessel with the preset dredged material quota data, execute the threshold early warning mechanism, and output the dredged material measurement results for display.

[0053] It should be noted that step S90 includes: calculating the quota consumption ratio based on the real-time dredged material volume data of a single vessel and the preset dredged material quota data, and obtaining the remaining quota ratio based on the quota consumption ratio; inputting the remaining quota ratio into the multi-level threshold discrimination module to obtain the current warning level; querying the preset warning action mapping table according to the current warning level to obtain the target warning action set, wherein the target warning action set includes at least one of the following: local audio-visual prompt action, remote platform push action, and on-site evidence collection trigger action; generating a warning control command based on the target warning action set; and sending the warning control command. The system sends data to the shipboard audible and visual alarm to trigger local audio and visual alerts; it also sends warning control commands to the remote monitoring platform to push remote information and store real-time dredged material volume data for the single vessel; it sends warning control commands to the shipboard camera to trigger on-site evidence collection and transmit evidence-collected image data; it receives confirmation receipts from the remote monitoring platform; and it integrates real-time dredged material volume data, current warning level, target warning action set, and confirmation receipts to generate and display dredged material measurement results.

[0054] It's important to understand that the quota consumption ratio refers to the percentage of the total real-time dredged material used to occupy the preset dredged material quota. This value directly reflects the progress of quota usage. The remaining quota ratio refers to the percentage of the remaining exploitable quota in the total quota. This value directly reflects the remaining compliant exploitation space for dredged material operations. The multi-level threshold discrimination module is a judgment unit that divides multiple levels of numerical critical conditions. This unit can output corresponding warning levels based on the proportional values. The warning action mapping table is a pre-established table that maps levels to corresponding actions. The table can be fixed to match the control execution logic under different scenarios. Confirmation receipt information refers to the response information fed back by the remote monitoring platform after receiving the instruction. This information is used to verify the effective transmission and normal execution of the warning instruction.

[0055] Specifically, firstly, the system reads the real-time dredged material volume data of a single vessel and the preset dredged material quota data. The real-time dredged material volume data is divided by the preset dredged material quota data to obtain the quota consumption ratio. Then, the remaining quota ratio is obtained by subtracting the remaining quota ratio from the value of 1. This ratio reflects the current dredged material progress relative to the remaining quota. Secondly, the remaining quota ratio is input into a multi-level threshold discrimination module, which queries a preset grading threshold table to determine the level: when the remaining quota ratio is greater than the preset first threshold (e.g., 20%), a green normal level is output; when it is between the preset second threshold (e.g., 10%) and the first threshold, a yellow alert level is output; when it is between the preset third threshold (e.g., 5%) and the second threshold, an orange warning level is output; and when it is less than the preset third threshold, a red over-limit level is output, thus obtaining the current warning level. Then, based on the current warning level, a preset warning action mapping table is queried: green level corresponds to an empty action set (only logging is recorded), yellow level corresponds to a local audio-visual prompt action, orange level adds a remote platform push action, and red level adds an on-site evidence collection trigger action, resulting in a target warning action set containing at least one action. Next, based on the target warning action set, corresponding warning control commands are generated and sent to the shipborne audible and visual alarm, the remote monitoring platform, and the shipborne camera equipment. This causes the shipborne audible and visual alarm to issue local audible and visual alerts (beeping and flashing), the remote monitoring platform to send push notifications via SMS or pop-up and store the real-time dredged material volume data for the single vessel, and the shipborne camera equipment to trigger on-site evidence collection by taking photos or videos and transmitting the collected image data back. Finally, the system receives confirmation information from the remote monitoring platform, encapsulates and integrates the real-time dredged material volume data for the single vessel, the current warning level, the target warning action set, and the confirmation information according to a preset structured format, generating and displaying the dredged material measurement results. Specifically, a multi-region visualization interface is constructed based on a preset display template. In the total quantity display area, real-time dredged material volume data for a single vessel and preset dredged material quota data are displayed in the form of a digital dashboard, accompanied by a dynamic progress bar reflecting the quota consumption ratio. In the warning level area, the current warning level is displayed with a background color fill, along with the remaining quota ratio. In the action execution area, the execution status (executed / not executed / in progress) of each action in the target warning action set is displayed in an icon list format. In the confirmation area, the confirmation information returned by the remote monitoring platform and its corresponding timestamp are displayed in a timeline format. Then, the constructed visualization interface data is sent to the shipboard display screen and the remote monitoring platform's web interface via a display driver, achieving synchronous display on both local and remote ends. The shipboard display screen allows crew members to view the operation status in real time, while the remote web interface allows supervisors to centrally monitor the status of multiple vessels. Finally, the display content is automatically updated according to a preset refresh cycle (e.g., every 30 seconds). When new metering data or changes in warning levels are received, the interface is redrawn to ensure the real-time nature and accuracy of the displayed information.This approach is necessary because dredging operations involve two user groups: crew members and regulatory personnel. Crew members need a clear understanding of the current total amount extracted and remaining quotas to adjust operational intensity, while regulatory personnel need a holistic perspective to monitor the early warning situation of multiple vessels and allocate enforcement resources. The multi-area, segmented display, similar to a car dashboard layout—speed gauge, fuel gauge, and warning lights—clearly distinguishes different information levels, preventing critical warning information from being buried in large amounts of data. Simultaneous dual-end display enables collaboration between on-site perception and remote supervision, forming a transparent management structure where "data is visible on board and available on shore." This approach is also necessary because dredged material supervision requires a tiered response mechanism—early warnings when quotas are approaching give ship owners room to adjust, while mandatory intervention and evidence collection are required when over-extraction is imminent, avoiding enforcement conflicts caused by a "one-size-fits-all" approach. The multi-level threshold design, similar to traffic light tiers—green for clear passage, yellow for caution, orange for slowing down, and red for stopping—makes warning information intuitive and easy to understand. The structured results facilitate subsequent auditing and traceability, forming a complete regulatory closed loop of "data collection-calculation-early warning-evidence collection-confirmation."

[0056] This embodiment collects multi-source data on vibration, photoelectricity, and water level to construct a dynamic vibration benchmark model and a dredged material pile shape profile. Combined with water level, it completes benchmark surface correction and initial volume calculation. After Kalman filtering calibration, the benchmark volume is obtained by inputting a fusion measurement model containing three modules. Then, after reliability verification, total accumulation, and threshold warning, the measurement result is output, which can truly reflect the dredged material pile shape and eliminate water level and noise interference. It can achieve accurate measurement of the volume of dredged material in a floating operation scenario of a chain bucket dredger, meeting the requirements for accurate measurement and compliant supervision of dredged materials on water.

[0057] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 The method for calculating and displaying the volume of dredged material based on multi-source sensing, step S60, further includes steps S201 to S206: Step S201: The working condition sensing coding module performs no-load and loaded state discrimination on the chain bucket vibration data in the calibrated multi-source sensor data to obtain the single bucket effectiveness label.

[0058] It should be noted that the single-bucket validity label is an identifier representing whether a single bucket dredging operation is effective. This label can distinguish between invalid empty bucket operations and valid loaded operations. Specifically, firstly, the calibrated multi-source sensor data is input into the working condition sensing encoding module. The bucket vibration data component is separated from the calibrated multi-source sensor data and sent to the inference interface of the dynamic vibration benchmark model. The model performs pattern matching calculations based on the time-domain statistical characteristics and frequency-domain energy characteristics of this bucket operation, and outputs the empty-load state determination result or the loaded state determination result. Secondly, a single-bucket validity label is generated based on the model's output determination result: when the output is a loaded state determination result, the single-bucket validity label is assigned a valid identifier (e.g., value 1), indicating that the current bucket operation dredged material and should be included in the measurement statistics; when the output is an empty-load state determination result, the single-bucket validity label is assigned an invalid identifier (e.g., value 0), indicating that the current bucket operation did not dredge material and should skip the measurement process. Finally, the single-bucket validity label and the working condition feature encoding vector from the chain bucket vibration data are output to the next-level module as control switches and weighting bases for subsequent fusion calculations. This is done because there are a large number of empty bucket runs during chain bucket operation (such as when the chain bucket does not contact the riverbed, or when it contacts but slips and does not dredge the dredged material). If all bucket runs are included in the total, it will lead to a serious overestimation. By using a dynamic vibration benchmark model to identify each bucket in real time, it is possible to accurately distinguish between effective dredged material buckets and ineffective empty buckets. Only bucket runs with valid labels will trigger the subsequent volume calculation and accumulation process, ensuring the authenticity of the measurement data from the source.

[0059] Step S202: Extract working condition features from the chain bucket vibration data and water level data in the calibrated multi-source sensor data to obtain the current excavation working condition coding vector.

[0060] It should be noted that operating condition feature extraction refers to the processing method of filtering key and effective information from raw monitoring data. This method can eliminate redundant content and retain core parameters that fit the operational scenario. Mining operating condition encoding vectors refers to a set of operating environment and equipment operation features presented in a standardized vector form. This set can unify the calling format of operating condition data.

[0061] Specifically, firstly, the chain bucket vibration data component and water level data component are extracted from the calibrated multi-source sensor data. Secondary feature processing is performed on the chain bucket vibration data to calculate the spectral entropy and main frequency band energy concentration of the vibration signal, obtaining the dredging hardness index, which reflects the hardness of the riverbed texture. The water level data is differentially calculated to obtain the water level change rate, and combined with the ship's draft change, the riverbed density index, reflecting the compactness of the dredged material accumulation, is obtained. Secondly, the dredging hardness index and riverbed density index are normalized and mapped to a preset coding range (e.g., between 0 and 1). They are then combined according to a preset coding rule: the dredging hardness index is used as the high 4 bits, and the riverbed density index as the low 4 bits, concatenating them to generate an 8-bit binary code, resulting in the current dredging condition coding vector. Finally, the current dredging condition coding vector is output to the adaptive weighted fusion module as the index key for querying the preset condition weight mapping table. This is done because the reliability of various sensors varies significantly under different riverbed environments—ultrasonic ranging is stable but the vibration signal is weak in soft mud riverbeds, while the vibration signal is strong but the ultrasonic reflection clutter is high in hard rock riverbeds. By inferring the current working condition characteristics from the chain bucket vibration and water level data, the complex field environment can be abstracted into a standardized coded identifier, realizing accurate measurement from "blind integration" to "on-demand integration".

[0062] Step S203: The edge integrity index and surface roughness index of the dredged material pile profile are calculated by the shape correction module to obtain the pile shape confidence coefficient.

[0063] It should be noted that the edge integrity index is an evaluation index that quantifies the integrity of the dredged material pile profile outline. This index can reflect whether there are missing or broken defects in the measured profile. The surface roughness index is a quantitative parameter that characterizes the degree of undulation and irregularity on the surface of the dredged material in the bucket. This parameter can reflect the regularity of the dredged material's accumulation shape. The pile shape reliability coefficient is a quantitative evaluation result obtained by combining the two morphological indicators. This result is used to measure the validity and reliability of the dredged material pile profile data.

[0064] Specifically, firstly, the dredged material pile shape profile is input into the morphology correction module. Boundary detection is performed on the profile curve, and the proportion of the distance measuring points at the profile edge covering the preset boundary range of the bucket is statistically analyzed to obtain the edge integrity index. This index reflects whether the ultrasonic ranging has completely scanned the entire area of ​​the dredged material inside the bucket. Secondly, the sum of squared residuals between each distance measuring point on the profile curve and the fitted surface is calculated. The sum of squared residuals is divided by the total number of distance measuring points to obtain the surface roughness index. This index reflects the smoothness or abnormal fluctuation of the dredged material pile surface. Then, the edge integrity index and surface roughness index are input into a preset reliability mapping function. The higher the edge integrity index and the lower the surface roughness index, the higher the pile shape reliability coefficient. When the edge integrity index is lower than the preset integrity threshold or the surface roughness index is higher than the preset roughness threshold, the pile shape reliability coefficient decreases significantly. Finally, the pile shape reliability coefficient is output to the next-level module as the basis for reliability correction of the initial volume of a single bucket. This is done because the morphology of dredged material accumulation in the bucket directly affects the accuracy of volume calculation—missing edge distance measurements may lead to an underestimation of volume (e.g., the bucket corner was not scanned), and abnormal surface roughness may indicate distance measurement errors (e.g., water splashing interference at a certain point). By using a dual-index joint evaluation, the quality level of the dredging shape data can be quantified, similar to a quality inspector assessing the product grade based on the product's appearance integrity and surface smoothness. This provides a clear numerical basis for subsequent volume correction and avoids using low-quality distance measurement data directly for measurement.

[0065] Step S204: Based on the stack shape confidence coefficient, the initial volume of the single bucket is shaped and corrected to obtain the corrected volume of the single bucket.

[0066] It should be noted that morphological correction is a process of adjusting the volume value based on the actual shape of the dredged material accumulation. This process can compensate for the numerical deviation between the rule calculation and the actual accumulation state. The corrected single-bucket volume refers to the volume result after correction based on the actual characteristics of the pile shape, which is closer to the actual filling volume of dredged material inside the chain bucket.

[0067] Specifically, firstly, the pile shape confidence coefficient is compared with a preset confidence level threshold to determine the quality level of the current pile shape data: when the pile shape confidence coefficient is greater than or equal to the preset high confidence threshold, the pile shape data is judged to be of excellent quality, and the initial volume of a single bucket is directly output as the corrected volume of a single bucket without any additional correction; when the pile shape confidence coefficient is between the preset medium confidence threshold and the preset high confidence threshold, the pile shape data is judged to have slight defects, and the initial volume of a single bucket is conservatively reduced by multiplying it by a preset first correction coefficient (e.g., 0.95) to obtain the corrected volume of a single bucket; when the pile shape confidence coefficient is less than the preset medium confidence threshold, the pile shape data is judged to be of poor quality, and the initial volume of a single bucket is significantly reduced by multiplying it by a preset second correction coefficient (e.g., 0.8), and the bucket is marked as suspicious data. Secondly, for buckets marked as suspicious, the original multi-point ultrasonic ranging data corresponding to those buckets is retrieved for retrospective analysis to identify the specific ranging points that led to the reduced reliability of the pile shape. This location information is then added to the corrected single-bucket volume metadata for subsequent manual verification or model iteration optimization. Finally, the corrected single-bucket volume is output to the adaptive weighted fusion module for subsequent weighted fusion calculations. This is done because ultrasonic ranging is greatly affected by the field environment; missing edges or local jumps can directly lead to volume overestimation. Reliability-level correction allows for differentiated processing of pile shape data of different qualities: high-quality data retains its original value, slightly defective data is conservatively reduced, and severely defective data is significantly reduced and recorded. This is similar to weighting exam scores based on the completeness of the test paper: full marks for complete answers, partial marks for missing questions, and low marks for large blank areas marked for retakes. This ensures the overall robustness of the measurement and provides a quality traceability basis for data traceability.

[0068] Step S205: Input the single-bucket validity label, the current excavation condition coding vector, and the corrected single-bucket volume into the adaptive weighted fusion module. Control the start and stop status of the fusion calculation according to the single-bucket validity label. Query the preset condition weight mapping table according to the current excavation condition coding vector to obtain the morphological correction weight coefficient and the condition adaptive weight coefficient.

[0069] It should be noted that the preset working condition weight mapping table is a reference form that pre-stores the weight parameters corresponding to different excavation working conditions. This form can quickly match the appropriate weight values ​​for various working scenarios. The weight coefficient is a quantitative parameter used to adjust the proportion of different measurement data. This parameter can balance the influence of morphological correction results and real-time working conditions on volume calculation.

[0070] Specifically, firstly, the single-bucket validity label, the current excavation condition coding vector, and the corrected single-bucket volume are input into the adaptive weighted fusion module. The identifier value of the single-bucket validity label is read. When the identifier value is invalid, zero volume is directly output and the fusion calculation process is skipped. When the identifier value is valid, the fusion calculation process is started, and the corrected single-bucket volume is used as the base value to be fused. Secondly, the current excavation condition coding vector is used as the index key to query a preset condition weight mapping table. This mapping table pre-stores the morphological correction weight coefficient and condition adaptive weight coefficient combination corresponding to different condition codes. For example, the morphological correction weight coefficient for soft mud riverbed is 0.3, and the condition adaptive weight coefficient is 0.7; the morphological correction weight coefficient for hard rock riverbed is 0.5, and the condition adaptive weight coefficient is 0.5. The morphological correction weight coefficient and condition adaptive weight coefficient corresponding to the current bucket are obtained by matching the coding vector and looking up the table. Finally, the morphological correction weight coefficient and condition adaptive weight coefficient are output to the weighted calculation unit as weight parameters for subsequent weighted fusion calculation of the corrected single-bucket volume. This is done because the reliability of data sources varies significantly under different working conditions. Filtering out invalid buckets by using single-bucket validity labels can avoid polluting the total amount of idle data. The working condition coding lookup mechanism realizes the transformation from "one-size-fits-all fixed weights" to "dynamic weighting on demand". Soft mud riverbeds rely more on ultrasound, while hard rock riverbeds rely more on vibration, making the fusion results more consistent with the actual situation on site.

[0071] Step S206: The corrected single-bucket volume is weighted and fused based on the morphology correction weight coefficient and the working condition adaptive weight coefficient to obtain the single-bucket dredged material reference volume.

[0072] It should be noted that the morphology correction weighting coefficient is a quantitative parameter used to measure the influence of the dredged material's pile shape on volume calculation. This parameter can constrain measurement interference caused by shape deviations. The working condition adaptive weighting coefficient is a dynamically adjusted parameter that matches the real-time excavation environment. This parameter can adapt to the differences in working conditions caused by water level fluctuations and equipment vibrations. Weighted fusion calculation refers to a processing method that uses multiple weighting coefficients to comprehensively calculate the basic volume data. This processing can balance the influence ratio of multiple dimension correction factors.

[0073] Specifically, firstly, the corrected single-bucket volume, morphology correction weight coefficient, and operating condition adaptation weight coefficient are read. The corrected single-bucket volume is then multiplied by both the morphology correction weight coefficient and the operating condition adaptation weight coefficient to obtain the first weighted volume component and the second weighted volume component. The morphology correction weight coefficient reflects the influence of pile shape data quality on volume reliability, while the operating condition adaptation weight coefficient reflects the adaptability of the multi-source data fusion strategy under the current operating condition. Secondly, the first and second weighted volume components are summed to obtain the weighted fused volume value. This weighted fused volume value is then normalized to ensure that the fusion result is within a reasonable volume value range. Finally, the normalized weighted fused volume value is output as the single-bucket dredged material baseline volume. This volume value comprehensively reflects the dual correction of the initial volume by pile shape quality and the operating condition adaptation strategy, and serves as the final result of the single-bucket measurement in the subsequent reliability verification stage. This is done because a single weight cannot simultaneously cover the impact of both data quality and working condition adaptation. By weighting and then fusing the two weights separately, the reliability of the form and the characteristics of the working condition can be explicitly included in the calculation. This is similar to how a student's overall grade is composed of regular grades and final grades weighted in different proportions. It examines both the process performance and the final result, making the single-bucket volume measurement more comprehensive and robust.

[0074] This embodiment relies on the collaborative operation of multiple modules in the model to achieve accurate volume calculation. First, the working condition perception and coding module determines the load status of the bucket chain and extracts working condition features. Then, the morphology correction module quantifies the mass of the dredged material pile shape and corrects the initial volume. Combined with validity tag control for calculation start and stop, and matching the working condition to dynamically retrieve weight coefficients, adaptive weighted fusion calculation is completed. This effectively combines equipment operation and environmental conditions to correct for errors caused by dredged material morphology and scene interference, improving the rationality of dredged material volume calculation and overall measurement accuracy.

[0075] Based on the first embodiment of this application, this application also provides a device for calculating and displaying the volume of dredged material based on multi-source sensing. Please refer to... Figure 3 The device includes: The acquisition module 10 is used to acquire multi-source sensor data, including chain bucket vibration data, photoelectric triggering data, multi-point ultrasonic ranging data, and water level data.

[0076] Vibration modeling module 20 is used to establish a dynamic vibration benchmark model that distinguishes between unloaded and loaded states based on chain bucket vibration data.

[0077] The profile construction module 30 is used to construct the dredged material pile profile based on photoelectric triggering data.

[0078] The volume calculation module 40 is used to correct the dredged material pile profile based on the water level data, and obtain the initial volume of a single bucket through volume calculation.

[0079] The calibration module 50 is used to perform noise cancellation and bias calibration on multi-source sensor data using the Kalman filter algorithm to obtain calibrated multi-source sensor data.

[0080] The metering module 60 is used to input the calibrated multi-source sensor data, dredged material pile shape profile and single bucket initial volume into the multi-source sensor fusion metering model to obtain the single bucket dredged material reference volume. The multi-source sensor fusion metering model includes a working condition perception coding module, a shape correction module and an adaptive weighted fusion module.

[0081] The verification module 70 is used to verify the reliability of the single-bucket dredged material reference volume based on the dynamic vibration reference model, and obtain the verified single-bucket dredged material reference volume.

[0082] The calculation module 80 is used to cumulatively calculate the base volume of dredged material in a single bucket after verification, so as to obtain the real-time total dredged material data of a single vessel.

[0083] The results module 90 is used to compare the real-time total dredged material data of a single vessel with the preset dredged material quota data, execute the threshold early warning mechanism, and output the dredged material measurement results.

[0084] The dredged material volume calculation and display device based on multi-source sensing provided in this application, employing the dredged material volume calculation and display method based on multi-source sensing in the above embodiments, can solve the technical problem of how to achieve accurate measurement and early warning monitoring of the volume of dredged material in a single bucket in a floating operation scenario of a chain bucket dredger. Compared with the prior art, the beneficial effects of the dredged material volume calculation and display device based on multi-source sensing provided in this application are the same as those of the dredged material volume calculation and display method based on multi-source sensing provided in the above embodiments, and other technical features in the dredged material volume calculation and display device based on multi-source sensing are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0085] This application provides a dredged material volume calculation and display device based on multi-source sensing. The dredged material volume calculation and display device based on multi-source sensing includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the dredged material volume calculation and display method based on multi-source sensing in the above embodiment 1.

[0086] The following is for reference. Figure 4This document illustrates a structural schematic diagram of a dredged material volume calculation and display device suitable for implementing embodiments of this application. The dredged material volume calculation and display device in this application embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The illustrated device for calculating and displaying the volume of dredged material based on multi-source sensing is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0087] like Figure 4 As shown, the dredged material volume calculation and display device based on multi-source sensing may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 1002 or a program loaded from storage device 1003 into random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the dredged material volume calculation and display device based on multi-source sensing. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the multi-source sensing-based dredged material volume calculation and display device to exchange data wirelessly or via wired communication with other devices. Although various multi-source sensing-based dredged material volume calculation and display devices are shown in the figures, it should be understood that it is not required to implement or possess all of them. More or fewer may be implemented alternatively.

[0088] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0089] The dredged material volume calculation and display device based on multi-source sensing provided in this application, employing the dredged material volume calculation and display method based on multi-source sensing in the above embodiments, can solve the technical problem of how to achieve accurate measurement and early warning monitoring of the volume of dredged material in a single bucket in a floating operation scenario of a chain bucket dredger. Compared with the prior art, the beneficial effects of the dredged material volume calculation and display device based on multi-source sensing provided in this application are the same as those of the dredged material volume calculation and display method based on multi-source sensing provided in the above embodiments, and other technical features in this dredged material volume calculation and display device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0090] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0091] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0092] This application provides a computer-readable medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the method for calculating and displaying dredged material volume based on multi-source sensing in the above embodiments.

[0093] The computer-readable medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor devices, or any combination thereof. More specific examples of computer-readable media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable medium may be any tangible medium containing or storing a program that can be executed by instructions, used by a device, or used in conjunction with it. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0094] The aforementioned computer-readable medium may be included in a multi-source sensing-based dredged material volume calculation and display device; or it may exist independently and not be assembled into a multi-source sensing-based dredged material volume calculation and display device.

[0095] The aforementioned computer-readable medium carries one or more programs that, when executed by a multi-source sensing-based dredged material volume calculation and display device, enable the device to write computer program code for performing the operations of this application in one or more programming languages ​​or combinations thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—and conventional procedural programming languages—such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of this application. In this regard, all blocks in the flowcharts or block diagrams may represent a module, segment, or portion of code containing one or more executable instructions for implementing the 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 all blocks in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using dedicated hardware-based implementations that perform the specified functions or operations, or using a combination of dedicated hardware and computer instructions.

[0097] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0098] The readable medium provided in this application is a computer-readable medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-described method for calculating and displaying dredged material volume based on multi-source sensing. This solves the technical problem of accurately measuring and monitoring the volume of dredged material in a single bucket in a floating operation scenario using a chain bucket dredger. Compared with the prior art, the beneficial effects of the computer-readable medium provided in this application are the same as those of the method for calculating and displaying dredged material volume based on multi-source sensing provided in the above embodiments, and will not be elaborated upon here.

[0099] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for calculating and displaying the volume of dredged material based on multi-source sensing.

[0100] The computer program product provided in this application can solve the technical problem of how to accurately measure and monitor the volume of dredged material in a single bucket in a floating operation scenario of a chain bucket dredger. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the dredged material volume calculation and display method based on multi-source sensing provided in the above embodiments, and will not be repeated here.

[0101] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for calculating and displaying the volume of dredged material based on multi-source sensing, characterized in that, The method includes: Acquire multi-source sensor data, wherein the multi-source sensor data includes chain bucket vibration data, photoelectric triggering data, and water level data; A dynamic vibration benchmark model that distinguishes between unloaded and loaded states is established based on the aforementioned chain bucket vibration data. A profile of the dredged material pile is constructed based on the photoelectric triggering data; The dredged material pile profile was corrected to a reference plane based on the water level data, and the initial volume of a single bucket was obtained by volume calculation. The Kalman filter algorithm is used to perform noise cancellation and bias calibration on the multi-source sensor data to obtain calibrated multi-source sensor data. The calibrated multi-source sensor data, dredged material pile shape profile and single bucket initial volume are input into the multi-source sensor fusion measurement model to obtain the single bucket dredged material reference volume. The multi-source sensor fusion measurement model includes a working condition perception coding module, a shape correction module and an adaptive weighted fusion module. The reliability of the single-bucket dredged material reference volume is verified based on the dynamic vibration reference model to obtain the verified single-bucket dredged material reference volume. The cumulative calculation of the verified single-bucket dredged material reference volume is used to obtain the real-time dredged material total volume data of a single vessel. The real-time dredged material total data of a single vessel is compared with the preset dredged material quota data, a threshold early warning mechanism is executed, and the dredged material measurement results are output and displayed. The step of constructing the dredged material pile profile based on the photoelectric triggering data includes: The level transition edge of the laser diffuse reflection signal is detected based on the photoelectric trigger data, and the time of the chain bucket passing the photoelectric sensor is identified based on the level transition edge. The chain bucket transmission cycle is compensated for the elapsed time to obtain the arrival time of the chain bucket at the unloading position; At the specified arrival time, a synchronous trigger command is sent to the multi-point ultrasonic sensor array so that the multi-point ultrasonic sensor array can synchronously measure the distance of the dredged material surface in the bucket and obtain multi-point ultrasonic ranging data. Based on the spatial installation coordinates of each sensor in the multi-point ultrasonic sensor array, the multi-point ultrasonic ranging data is mapped into three-dimensional point cloud data of the surface of the dredged material in the bucket. The 3D point cloud data is subjected to profile fitting to obtain the dredged material pile profile; The step of inputting the calibrated multi-source sensor data, dredged material pile profile, and initial volume of a single bucket into the multi-source sensor fusion metrology model to obtain the reference volume of dredged material in a single bucket includes: The working condition sensing coding module is used to distinguish between the unloaded and loaded states of the chain bucket vibration data in the calibrated multi-source sensor data to obtain a single bucket effectiveness label. The working condition features of the bucket chain vibration data and water level data in the calibrated multi-source sensor data are extracted to obtain the current excavation working condition coding vector. Specifically, the bucket chain vibration data component and the water level data component are extracted from the calibrated multi-source sensor data respectively. The bucket chain vibration data is subjected to secondary feature processing to calculate the spectral entropy value and the energy concentration of the main frequency band of the vibration signal to obtain the excavation hardness index. The water level data is differentially calculated to obtain the water level change rate, and the riverbed density index is obtained by combining it with the hull draft change. The excavation hardness index and the riverbed density index are normalized and mapped to a preset coding interval. They are then combined according to a preset coding rule to obtain the current excavation working condition coding vector. The edge integrity index and surface roughness index of the dredged material pile profile are calculated using the shape correction module to obtain the pile shape reliability coefficient. Based on the pile shape confidence coefficient, the initial volume of the single bucket is shaped and corrected to obtain the corrected volume of the single bucket. The single-bucket effectiveness label, the current excavation condition encoding vector, and the corrected single-bucket volume are input into the adaptive weighted fusion module. The start and stop status of the fusion calculation is controlled according to the single-bucket effectiveness label. The morphological correction weight coefficient and the condition adaptive weight coefficient are obtained by querying the preset condition weight mapping table according to the current excavation condition encoding vector. The corrected single-bucket volume is weighted and fused based on the morphological correction weight coefficient and the working condition adaptive weight coefficient to obtain the single-bucket dredged material reference volume.

2. The method as described in claim 1, characterized in that, The steps for establishing a dynamic vibration benchmark model that distinguishes between unloaded and loaded states based on the chain bucket vibration data include: The chain bucket vibration data is subjected to bandpass filtering to obtain filtered vibration data; The root mean square value, peak factor, and skewness index are extracted from the filtered vibration data as time-domain statistical features. The filtered vibration data were subjected to a fast Fourier transform, and the main frequency energy ratio and the spectral centroid were extracted as frequency domain energy features. Based on the time-domain statistical characteristics and frequency-domain energy characteristics, construct an unloaded state characteristic sample set and a loaded state characteristic sample set; The unloaded state feature sample set and the loaded state feature sample set are labeled to obtain the labeled training sample set. The labeled training sample set is input into a preset classifier for model training to obtain a dynamic vibration benchmark model, wherein the dynamic vibration benchmark model outputs an unloaded state determination result or a loaded state determination result.

3. The method as described in claim 1, characterized in that, The step of correcting the dredged material pile profile to a reference plane based on the water level data and calculating the initial volume of a single bucket includes: Calculate the water level difference based on the water level data and the preset empty reference water level value; The change in hull draft is obtained by linear interpolation based on the water level difference and preset hull drainage characteristic parameters. Calculate the vertical offset of the ultrasonic sensor mounting reference plane based on the change in the ship's draft; Based on the vertical offset, the elevation of each ranging point of the dredged material pile profile is corrected using a reference plane to obtain the corrected dredged material pile profile. The modified dredged material pile profile is subjected to cross-sectional integration along the length of the bucket to obtain a sequence of single bucket cross-sectional areas; The initial volume of a single bucket is obtained by performing a volume accumulation calculation based on the single bucket cross-sectional area sequence and the bucket width parameter of the chain bucket.

4. The method as described in claim 1, characterized in that, The step of verifying the reliability of the single-bucket dredged material reference volume based on the dynamic vibration reference model to obtain the verified single-bucket dredged material reference volume includes: Input the chain bucket vibration data of the current bucket into the dynamic vibration benchmark model to obtain the load state confidence of the current bucket. Perform time-series difference operation on the multi-point ultrasonic ranging data of the current round to obtain the ranging change sequence at adjacent ranging times, and extract the maximum jump variable in the ranging change sequence. When the confidence level of the loaded state is greater than the preset confidence threshold and the maximum jump variable is less than the preset jump tolerance condition, the single bucket dredged material reference volume is used as the verified single bucket dredged material reference volume. When the confidence level of the loaded state is less than or equal to the preset confidence threshold, or when the maximum jump variable is greater than or equal to the preset jump tolerance condition, the current bucket is marked as an abnormal bucket, and the single bucket dredged material reference volume is replaced and corrected by the sliding window mean to obtain the verified single bucket dredged material reference volume.

5. The method as described in claim 1, characterized in that, The steps of comparing the real-time dredged material total data of a single vessel with the preset dredged material quota data, executing a threshold early warning mechanism, and outputting the dredged material measurement results for display include: The quota consumption ratio is calculated based on the real-time dredged material total data of a single vessel and the preset dredged material quota data, and the remaining quota ratio is obtained based on the quota consumption ratio. The remaining quota percentage is input into the multi-level threshold discrimination module to obtain the current warning level; Based on the current warning level, a preset warning action mapping table is queried to obtain a target warning action set, wherein the target warning action set includes at least one of local audio-visual prompt action, remote platform push action, and on-site evidence collection trigger action. Generate early warning control instructions based on the target early warning action set; The warning control command is sent to the shipborne audible and visual alarm, so that the shipborne audible and visual alarm performs a local audible and visual prompt action. The early warning control command is sent to the remote monitoring platform so that the remote monitoring platform can perform a remote platform push action and store the real-time total amount of dredged material of a single vessel. The warning control command is sent to the shipborne camera equipment so that the shipborne camera equipment can perform on-site evidence collection triggering action and transmit back evidence collection image data; Receive confirmation receipt information returned by the remote monitoring platform; The system integrates the real-time dredged material volume data of a single vessel, the current warning level, the target warning action set, and the confirmation receipt information to generate and display the dredged material measurement results.

6. A device for calculating and displaying the volume of dredged material based on multi-source sensing, characterized in that, The device is applied to the method for calculating and displaying dredged material volume based on multi-source sensing as described in any one of claims 1-5, and the device comprises: The acquisition module is used to acquire multi-source sensor data, wherein the multi-source sensor data includes chain bucket vibration data, photoelectric triggering data, and water level data; The vibration modeling module is used to establish a dynamic vibration benchmark model that distinguishes between unloaded and loaded states based on the chain bucket vibration data. The profile construction module is used to construct a profile of the dredged material pile based on the photoelectric triggering data; The volume calculation module is used to correct the reference plane of the dredged material pile shape profile by combining the water level data, and obtain the initial volume of a single bucket through volume calculation. The calibration module is used to perform noise cancellation and bias calibration on the multi-source sensor data using a Kalman filter algorithm to obtain calibrated multi-source sensor data. The metering module is used to input the calibrated multi-source sensor data, dredged material pile shape profile and single bucket initial volume into the multi-source sensor fusion metering model to obtain the single bucket dredged material reference volume. The multi-source sensor fusion metering model includes a working condition perception coding module, a shape correction module and an adaptive weighted fusion module. The verification module is used to verify the reliability of the single-bucket dredged material reference volume based on the dynamic vibration reference model, and obtain the verified single-bucket dredged material reference volume. The calculation module is used to cumulatively calculate the verified single-bucket dredged material reference volume to obtain the real-time dredged material total volume data of a single vessel. The results module is used to compare the real-time total dredged material data of a single vessel with the preset dredged material quota data, execute the threshold early warning mechanism, and output the dredged material measurement results for display.

7. A device for calculating and displaying the volume of dredged material based on multi-source sensing, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the method for calculating and displaying dredged material volume based on multi-source sensing as described in any one of claims 1 to 5.

8. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the method for calculating and displaying the volume of dredged material based on multi-source sensing as described in any one of claims 1 to 5.

Images