Channel construction safety intelligent monitoring and automatic early warning system and method

Abstract

The invention discloses a channel construction safety intelligent monitoring and automatic early warning system and method, and the system comprises a multi-mode sensing module which is used for collecting the real-time monitoring data of a channel construction region; the data quality evaluation module is used for calculating data quality evaluation scores of various sensors in the multi-modal sensing module in real time; the dynamic risk assessment module is used for adjusting a data fusion weight based on the data quality assessment score and processing real-time monitoring data to generate a regional comprehensive risk value; the intelligent early warning module is used for comparing the regional comprehensive risk value with a dynamic risk threshold value and triggering an early warning signal; and the resource scheduling module is used for evaluating the score according to the early warning signal grade and the data quality. According to the invention, the monitoring precision is obviously improved; through multi-modal data fusion and quality evaluation, the target identification accuracy is improved; system parameters can be automatically adjusted according to environment changes and sensor states, and the optimal working state is kept.

Description

Technical Field

[0001] This invention relates to the technical field of waterway construction safety, and in particular to an intelligent monitoring and automatic early warning system and method for waterway construction safety. Background Technology

[0002] Waterway construction areas are characterized by complex and dynamically changing environments, and traditional monitoring systems mainly suffer from the following technical shortcomings: Low data utilization efficiency: Although the existing system uses multiple sensors, each sensor works independently and lacks an effective data fusion mechanism, resulting in low utilization of monitoring data.

[0003] Static risk assessment: Traditional risk assessment models often use fixed thresholds, which cannot adapt to the dynamic environmental changes in the waterway construction area, resulting in high false alarm and false negative rates.

[0004] System response lag: The entire process from data collection to early warning issuance lacks optimization, resulting in excessively long response times that fail to meet the needs of real-time security monitoring.

[0005] Inappropriate resource allocation: The fixed sensor resource allocation strategy cannot be dynamically adjusted according to the actual risk situation, resulting in resource waste or insufficient monitoring.

[0006] To address these issues, we propose an intelligent monitoring and automatic early warning system and method for waterway construction safety. Summary of the Invention

[0007] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0008] In view of the problems existing in the above-mentioned intelligent monitoring and automatic early warning systems and methods for waterway construction safety, this invention is proposed.

[0009] Therefore, the purpose of this invention is to provide an intelligent monitoring and automatic early warning system and method for waterway construction safety, which significantly improves monitoring accuracy: through multimodal data fusion and quality assessment, the target recognition accuracy is improved; the system has strong self-adaptability: it can automatically adjust system parameters according to environmental changes and sensor status to maintain optimal working condition.

[0010] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an intelligent monitoring and automatic early warning system for waterway construction safety, comprising: The multimodal sensing module is used to collect real-time monitoring data of the waterway construction area; The data quality assessment module is used to calculate the data quality assessment scores of various sensors in the multimodal sensing module in real time. The dynamic risk assessment module is used to adjust the data fusion weights based on the data quality assessment score and process real-time monitoring data to generate a regional comprehensive risk value. The intelligent early warning module is used to compare the comprehensive risk value of the area with the dynamic risk threshold and trigger an early warning signal; The resource scheduling module is used to generate scheduling instructions for the multimodal perception module based on the warning signal level and data quality evaluation score.

[0011] As a preferred embodiment of the intelligent monitoring and automatic early warning system for waterway construction safety described in this invention, the multimodal sensing module adopts a timestamp synchronization mechanism to keep the data acquisition of microwave radar, optical camera equipment and AIS receiving equipment synchronized at all times; the system also includes a data fusion center for spatiotemporal alignment and correlation processing of the synchronized multi-source data.

[0012] As a preferred embodiment of the intelligent monitoring and automatic early warning system for waterway construction safety described in this invention, the dynamic risk assessment module has a built-in feedback learning unit; the feedback learning unit is configured to receive manual feedback or automatic confirmation information of the early warning handling result, and compare the information with historical risk assessment data to iteratively optimize the internal parameters of the dynamic risk assessment model and the curve shape of the weight mapping function.

[0013] As a preferred embodiment of the intelligent monitoring and automatic early warning system for waterway construction safety described in this invention, the system adopts an edge-cloud collaborative computing architecture; the data quality assessment module and the intelligent early warning module for triggering low-level early warnings are deployed on edge computing nodes; the dynamic risk assessment module and the intelligent early warning module for triggering medium- and high-level early warnings are deployed in the cloud computing center; and the edge computing nodes and the cloud computing center interact with each other and synchronize instructions through a communication network.

[0014] A method for intelligent monitoring and automatic early warning of waterway construction safety includes the following steps: S1. Real-time monitoring data of the waterway construction area is collected through a multimodal sensing network; the multimodal sensing network includes at least a microwave radar, an optical camera, and an AIS receiving device; S2. Calculate the data quality assessment scores of various sensors in the multimodal sensing network in real time; the data quality assessment scores are calculated based on the sensor's signal-to-noise ratio, data integrity, and coverage indicators. S3. Based on the data quality assessment score, dynamically adjust the data fusion weights corresponding to various sensors in the dynamic risk assessment model, and use the adjusted dynamic risk assessment model to process the real-time monitoring data to generate a regional comprehensive risk value. S4. Compare the comprehensive risk value of the area with the preset dynamic risk threshold, and trigger the corresponding level of early warning signal according to the comparison result; S5. Based on the level of the triggered warning signal and the data quality assessment score, generate sensor resource scheduling instructions and feed them back to the multimodal sensing network to adjust the working status of the corresponding sensors.

[0015] As a preferred embodiment of the intelligent monitoring and automatic early warning method for waterway construction safety described in this invention, the specific process of calculating the data quality assessment score in step S2 includes: S21. Assign weight coefficients to the three indicators: signal-to-noise ratio, data integrity, and coverage. S22. Normalize each indicator to obtain a standardized score; S23. Based on the weighting coefficients and standardized scores, the data quality assessment score is obtained by weighted summation. The data quality assessment score is used to quantitatively characterize the reliability and usability of sensor data.

[0016] As a preferred embodiment of the intelligent monitoring and automatic early warning method for waterway construction safety described in this invention, wherein: in step S3, the specific method for dynamically adjusting the data fusion weights is as follows: The data quality assessment score is input into a preset weight mapping function, and the output value of the weight mapping function is the data fusion weight of this type of sensor at the current moment; The weight mapping function is configured such that the higher the data quality assessment score, the greater the corresponding data fusion weight.

[0017] As a preferred embodiment of the intelligent monitoring and automatic early warning method for waterway construction safety described in this invention, in step S3, the dynamic risk assessment model generates a regional comprehensive risk value through the following steps: S31. Extract spatiotemporal features, behavioral features, and environmental features from the real-time monitoring data; S32. Based on the adjusted data fusion weights, the spatiotemporal features, behavioral features, and environmental features are weighted and fused to form a fused feature vector; S33. Input the fused feature vector into a trained risk assessment neural network, and output the comprehensive risk value of the region by the risk assessment neural network.

[0018] As a preferred embodiment of the intelligent monitoring and automatic early warning method for waterway construction safety described in this invention, the dynamic risk threshold in step S4 is not a fixed value, but is dynamically adjusted according to the real-time environmental conditions of the waterway construction area; when the visibility is lower than the preset standard or the water flow speed is higher than the preset standard, the system automatically lowers the dynamic risk threshold to trigger the sensitivity of the early warning.

[0019] As a preferred embodiment of the intelligent monitoring and automatic early warning method for waterway construction safety described in this invention, wherein: the sensor resource scheduling instruction in step S5 is specifically used to control the working mode of the multimodal sensing network, the working mode including: Energy-saving mode: When the overall risk value of the area is low and the data quality assessment score is high, the sampling frequency of some sensors is reduced; Standard mode: Maintains the sensor's normal operating state under multiple array conditions; Enhanced Mode: When the overall risk value of the area is high or the critical sensor data quality assessment score is low, all available sensors are activated and operate at maximum performance.

[0020] The beneficial effects of this invention are as follows: The monitoring accuracy is significantly improved: through multimodal data fusion and quality assessment, the target recognition accuracy is improved; the system has strong self-adaptability: it can automatically adjust system parameters according to environmental changes and sensor status to maintain the best working state; and resource utilization efficiency is optimized: through intelligent resource scheduling, the energy consumption of the sensor network is reduced. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of the method steps of the intelligent monitoring and automatic early warning system and method for waterway construction safety of the present invention. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0025] Secondly, the present invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not according to the usual scale. Furthermore, the schematic diagrams are merely examples and should not limit the scope of protection of the present invention. In addition, actual fabrication should include three-dimensional spatial dimensions of length, width, and depth.

[0026] Reference Figure 1 A smart monitoring and automatic early warning system for waterway construction safety is provided, including: The multimodal sensing module is used to collect real-time monitoring data of the waterway construction area; The data quality assessment module is used to calculate the data quality assessment scores of various sensors in the multimodal sensing module in real time. The dynamic risk assessment module is used to adjust the data fusion weights based on the data quality assessment score and process real-time monitoring data to generate a regional comprehensive risk value. The intelligent early warning module is used to compare the comprehensive risk value of the area with the dynamic risk threshold and trigger an early warning signal; The resource scheduling module is used to generate scheduling instructions for the multimodal perception module based on the warning signal level and data quality evaluation score.

[0027] Specifically, the multimodal perception module includes: Microwave radar subsystem: used for ship trajectory tracking and speed detection; Optical imaging equipment: including visible light and infrared cameras, used for target recognition and behavior analysis; AIS receiving equipment: receives information on vessel identity, location, speed, and heading; Hydrometeorological sensors: collect data on water flow velocity, wind speed, and visibility; Data synchronization unit: Employs hardware-level timestamp synchronization to ensure spatiotemporal consistency of multi-source data; The dynamic risk assessment module employs a deep learning-based risk assessment network, and its innovation lies in using sensor data quality as the basis for adjusting model input weights. Feature extraction layer: Extracts spatiotemporal features, behavioral features, and environmental features from multi-source data; Weighted adaptive layer: dynamically adjusts feature weights based on data quality assessment scores; Risk prediction layer: Outputs the overall risk value and risk propagation trend of the region; The intelligent early warning module adopts a multi-level early warning mechanism, and the early warning threshold is dynamically adjusted according to environmental conditions: Blue alert (risk value < 30): Logged, no proactive warning; Yellow alert (30≤risk value<60): On-site audio and visual warning; Orange alert (60≤risk value<80): Remote platform alarm; Red Alert (Risk Value ≥ 80): Emergency warnings issued through multiple channels and coordinated emergency response; The multimodal sensing module employs a timestamp synchronization mechanism to ensure that the data acquisition from the microwave radar, optical camera equipment, and AIS receiving equipment remains synchronized. The system also includes a data fusion center for spatiotemporal alignment and correlation processing of the synchronized multi-source data.

[0028] The dynamic risk assessment module has a built-in feedback learning unit. The feedback learning unit is configured to receive manual feedback or automatic confirmation information of the early warning handling results, and compare the information with historical risk assessment data to iteratively optimize the internal parameters of the dynamic risk assessment model and the curve shape of the weight mapping function.

[0029] The system adopts an edge-cloud collaborative computing architecture; the data quality assessment module and the intelligent early warning module for triggering low-level early warnings are deployed on edge computing nodes; the dynamic risk assessment module and the intelligent early warning module for triggering medium- and high-level early warnings are deployed in the cloud computing center; the edge computing nodes and the cloud computing center interact with each other and synchronize instructions through a communication network.

[0030] Furthermore, a method for intelligent monitoring and automatic early warning of waterway construction safety includes the following steps: S1. Real-time monitoring data of the waterway construction area is collected through a multimodal sensing network; the multimodal sensing network includes at least a microwave radar, an optical camera, and an AIS receiving device; S2. Calculate the data quality assessment scores of various sensors in the multimodal sensing network in real time; the data quality assessment scores are calculated based on the sensor's signal-to-noise ratio, data integrity, and coverage indicators. S3. Based on the data quality assessment score, dynamically adjust the data fusion weights corresponding to various sensors in the dynamic risk assessment model, and use the adjusted dynamic risk assessment model to process the real-time monitoring data to generate a regional comprehensive risk value. S4. Compare the comprehensive risk value of the area with the preset dynamic risk threshold, and trigger the corresponding level of early warning signal according to the comparison result; S5. Based on the level of the triggered warning signal and the data quality assessment score, generate sensor resource scheduling instructions and feed them back to the multimodal sensing network to adjust the working status of the corresponding sensors.

[0031] In step S2, the specific process of calculating the data quality assessment score includes: S21. Assign weight coefficients to the three indicators: signal-to-noise ratio, data integrity, and coverage. S22. Normalize each indicator to obtain a standardized score; S23. Based on the weighting coefficients and standardized scores, the data quality assessment score is obtained by weighted summation. The data quality assessment score is used to quantitatively characterize the reliability and usability of sensor data.

[0032] Specifically, the data quality assessment score in step S2 adopts a multi-dimensional weighted comprehensive evaluation model, and the specific calculation formula is as follows: Data quality assessment score ; in: , , These are the weighting coefficients, and + + =1; SNR_score is the normalized score for signal-to-noise ratio; Integrity_score is the standardized score for data integrity. Coverage_score is the standardized score for coverage. Specifically, the methods for calculating signal power and noise power are as follows: For radar signals: Signal power = the square mean of the echo signal amplitude; For video signals: Signal power = Image sharpness index × Contrast index; Noise power = power spectral density of background noise in the signal acquisition system; Data integrity standardized score calculation: Integrity_score = (1 - data loss rate) × (1 - data anomaly rate); Data loss rate = (expected number of data points - actual number of data points received) / expected number of data points; Data anomaly rate = number of abnormal data points / actual number of data points received; Criteria for identifying abnormal data: The value exceeds the sensor's measurement range; The rate of change of data exceeds physical limits (e.g., ship speed > 50 knots); The data timestamp is severely off (>1 second); Standardized score calculation for coverage: Coverage_score = Actual effective coverage area / Theoretical maximum coverage area; Weighting coefficient settings: Based on extensive experimental data optimization, the weighting coefficients are set as follows: (Signal-to-noise ratio weight) = 0.5; (Data integrity weight) = 0.3; (Coverage weight) = 0.2; Weighting coefficient adjustment mechanism: Under special environmental conditions, the system can automatically adjust the weights: During severe weather: Increase Weight reduced to 0.6, decrease Up to 0.1; When the network is abnormal: Improve Weight reduced to 0.4, decrease Up to 0.4; The following is an example: Radar sensor data quality assessment Given parameters: Radar signal-to-noise ratio (SNR) = 18 dB During the data collection period: 100 data points were expected, and 95 were actually received, of which 3 were abnormal. Theoretical radar coverage area: 5km 2 Actual effective coverage: 4.2km 2 Calculation process: Signal-to-noise ratio score calculation SNR_score=(18-10) / (30-10)=8 / 20=0.4 Data integrity score calculation Data loss rate = (100-95) / 100 = 0.05 Data anomaly rate = 3 / 95 ≈ 0.0316 Integrity_score=(1-0.05)×(1-0.0316)=0.95×0.9684≈0.92 Coverage score calculation Coverage_score=4.2 / 5=0.84 Overall quality score calculation Q=0.5×0.4+0.3×0.92+0.2×0.84 =0.2 + 0.276 + 0.168 = 0.644 Result: The data quality assessment score of this radar sensor is 0.644 (out of 1.0). In step S3, the specific method for dynamically adjusting the data fusion weights is as follows: The data quality assessment score is input into a preset weight mapping function, and the output value of the weight mapping function is the data fusion weight of this type of sensor at the current moment; The weight mapping function is configured such that the higher the data quality assessment score, the greater the corresponding data fusion weight.

[0033] Furthermore, in step S3, the dynamic risk assessment model generates a regional comprehensive risk value through the following steps: S31. Extract spatiotemporal features, behavioral features, and environmental features from the real-time monitoring data; S32. Based on the adjusted data fusion weights, the spatiotemporal features, behavioral features, and environmental features are weighted and fused to form a fused feature vector; S33. Input the fused feature vector into a trained risk assessment neural network, and output the comprehensive risk value of the region by the risk assessment neural network.

[0034] In step S4, the dynamic risk threshold is not a fixed value, but is dynamically adjusted according to the real-time environmental conditions of the waterway construction area. When the visibility is lower than the preset standard or the water flow speed is higher than the preset standard, the system automatically lowers the dynamic risk threshold to trigger the sensitivity of the warning.

[0035] Specifically, the sensor resource scheduling instruction in step S5 is used to control the operating mode of the multimodal sensing network, and the operating mode includes: Energy-saving mode: When the overall risk value of the area is low and the data quality assessment score is high, the sampling frequency of some sensors is reduced; Standard mode: Maintains the sensor's normal operating state under multiple array conditions; Enhanced Mode: When the overall risk value of the area is high or the critical sensor data quality assessment score is low, all available sensors are activated and operate at maximum performance.

[0036] The specific implementation examples are as follows: Scene description: During the dredging of the waterway, the water depth of the temporary waterway changes frequently, and it is necessary to prevent ships from running aground due to insufficient water depth.

[0037] System configuration and sensor deployment: The multibeam echo sounder system monitors the water depth in the construction area in real time. Tide monitoring stations provide benchmark water level data; AIS receives ship draft depth information; Weather stations collect wind speed and direction data; Work process Multi-source data fusion; Integrates real-time water depth, tide level prediction, and ship draft data; Calculate the real-time effective water depth for each channel segment; Assess data quality and determine fusion weights; Tiered warning trigger Safety margin > 1.0 meter: No risk (risk value < 30) 0.5 meters < safety margin ≤ 1.0 meter: Yellow alert; 0.3 meters < safety margin ≤ 0.5 meters: Orange alert; Safety margin ≤ 0.3 meters: Red alert; Implementation results: The system successfully issued two warnings of grounding risk during the test, reducing the false alarm rate and significantly minimizing unnecessary construction interruptions.

[0038] This invention significantly improves monitoring accuracy: target identification accuracy is improved through multimodal data fusion and quality assessment; the system has strong adaptability: it can automatically adjust system parameters according to environmental changes and sensor status to maintain optimal working condition; and resource utilization efficiency is optimized: energy consumption of the sensor network is reduced through intelligent resource scheduling.

[0039] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A smart monitoring and automatic early warning system for waterway construction safety, characterized in that, include: The multimodal sensing module is used to collect real-time monitoring data of the waterway construction area; The data quality assessment module is used to calculate the data quality assessment scores of various sensors in the multimodal sensing module in real time. The dynamic risk assessment module is used to adjust the data fusion weights based on the data quality assessment score and process real-time monitoring data to generate a regional comprehensive risk value. The intelligent early warning module is used to compare the comprehensive risk value of the area with the dynamic risk threshold and trigger an early warning signal; The resource scheduling module is used to generate scheduling instructions for the multimodal perception module based on the warning signal level and data quality evaluation score.

2. The intelligent monitoring and automatic early warning system for waterway construction safety according to claim 1, characterized in that: The multimodal sensing module employs a timestamp synchronization mechanism to ensure that the data acquisition from the microwave radar, optical camera equipment, and AIS receiving equipment remains synchronized at all times. The system also includes a data fusion center for spatiotemporal alignment and correlation processing of the synchronized multi-source data.

3. The intelligent monitoring and automatic early warning system for waterway construction safety according to claim 2, characterized in that: The dynamic risk assessment module has a built-in feedback learning unit; the feedback learning unit is configured to receive manual feedback or automatic confirmation information of the early warning handling results, and compare the information with historical risk assessment data to iteratively optimize the internal parameters of the dynamic risk assessment model and the curve shape of the weight mapping function.

4. The intelligent monitoring and automatic early warning system for waterway construction safety according to claim 3, characterized in that: The system adopts an edge-cloud collaborative computing architecture; the data quality assessment module and the intelligent early warning module for triggering low-level early warnings are deployed on edge computing nodes; the dynamic risk assessment module and the intelligent early warning module for triggering medium- and high-level early warnings are deployed in the cloud computing center; the edge computing nodes and the cloud computing center interact with each other and synchronize instructions through a communication network.

5. A method for intelligent monitoring and automatic early warning of waterway construction safety based on the intelligent monitoring and automatic early warning system for waterway construction safety according to any one of claims 1-4, characterized in that: Includes the following steps: S1. Real-time monitoring data of the waterway construction area is collected through a multimodal sensing network; the multimodal sensing network includes at least a microwave radar, an optical camera, and an AIS receiving device; S2. Calculate the data quality assessment scores of various sensors in the multimodal sensing network in real time; the data quality assessment scores are calculated based on the sensor's signal-to-noise ratio, data integrity, and coverage indicators. S3. Based on the data quality assessment score, dynamically adjust the data fusion weights corresponding to various sensors in the dynamic risk assessment model, and use the adjusted dynamic risk assessment model to process the real-time monitoring data to generate a regional comprehensive risk value. S4. Compare the comprehensive risk value of the area with the preset dynamic risk threshold, and trigger the corresponding level of early warning signal according to the comparison result; S5. Based on the level of the triggered warning signal and the data quality assessment score, generate sensor resource scheduling instructions and feed them back to the multimodal sensing network to adjust the working status of the corresponding sensors.

6. The intelligent monitoring and automatic early warning method for waterway construction safety according to claim 5, characterized in that: In step S2, the specific process of calculating the data quality assessment score includes: S21. Assign weight coefficients to the three indicators: signal-to-noise ratio, data integrity, and coverage. S22. Normalize each indicator to obtain a standardized score; S23. Based on the weighting coefficients and standardized scores, the data quality assessment score is obtained by weighted summation. The data quality assessment score is used to quantitatively characterize the reliability and usability of sensor data.

7. The intelligent monitoring and automatic early warning method for waterway construction safety according to claim 5, characterized in that: In step S3, the specific method for dynamically adjusting the data fusion weights is as follows: The data quality assessment score is input into a preset weight mapping function, and the output value of the weight mapping function is the data fusion weight of this type of sensor at the current moment; The weight mapping function is configured such that the higher the data quality assessment score, the greater the corresponding data fusion weight.

8. The intelligent monitoring and automatic early warning method for waterway construction safety according to claim 7, characterized in that: In step S3, the dynamic risk assessment model generates a regional comprehensive risk value through the following steps: S31. Extract spatiotemporal features, behavioral features, and environmental features from the real-time monitoring data; S32. Based on the adjusted data fusion weights, the spatiotemporal features, behavioral features, and environmental features are weighted and fused to form a fused feature vector; S33. Input the fused feature vector into a trained risk assessment neural network, and output the comprehensive risk value of the region by the risk assessment neural network.

9. The intelligent monitoring and automatic early warning method for waterway construction safety according to claim 5, characterized in that: The dynamic risk threshold in step S4 is not a fixed value, but is dynamically adjusted according to the real-time environmental conditions of the waterway construction area. When the visibility is lower than the preset standard or the water flow speed is higher than the preset standard, the system automatically lowers the dynamic risk threshold to trigger the sensitivity of the warning.

10. The intelligent monitoring and automatic early warning method for waterway construction safety according to claim 5, characterized in that: The sensor resource scheduling command in step S5 is specifically used to control the operating mode of the multimodal sensing network, and the operating mode includes: Energy-saving mode: When the overall risk value of the area is low and the data quality assessment score is high, the sampling frequency of some sensors is reduced; Standard mode: Maintains the sensor's normal operating state under multiple array conditions; Enhanced Mode: When the overall risk value of the area is high or the critical sensor data quality assessment score is low, all available sensors are activated and operate at maximum performance.

Images