A Ship Intelligent Monitoring System and Method Based on the Internet of Things

Abstract

This application relates to an IoT-based intelligent ship monitoring system and method, comprising a sensor layer including a biofouling composite monitoring unit, a ballast water correlation monitoring unit, and a corrosion monitoring unit, for collecting biofouling data of the hull surface, characteristic parameters of the ballast water system, and hull corrosion data; an IoT transmission layer including a multi-mode communication gateway and edge computing nodes for remote transmission and preprocessing of sensor data; a data processing and analysis layer constructing a ballast water-fouling dynamic coupling model and an interference correction module for analyzing the correlation between biofouling and ballast water parameters and compensating for environmental interference; and an application layer including a 3D visualization monitoring platform and an intelligent report generation system for visualizing the hull status and generating adaptive maintenance strategies. This application effectively improves the accuracy and efficiency of ship monitoring.

Description

Technical Field

[0001] This application relates to the field of intelligent ship monitoring, and in particular to an Internet of Things-based intelligent ship monitoring system and method. Background Technology

[0002] Ships that are submerged in seawater for extended periods face the dual threats of biofouling and seawater corrosion: biofouling increases navigation resistance by 15%-30% and fuel consumption increases; corrosion weakens the hull structure and affects navigation safety.

[0003] Traditional monitoring technologies often focus on a single parameter, such as using cameras to monitor biofouling on the hull surface or using electrochemical sensors to monitor corrosion. This single-parameter monitoring method cannot comprehensively and accurately reflect the actual condition of the hull because biofouling and seawater corrosion are complex processes that are interconnected and influence each other. Single-parameter monitoring cannot capture the complex relationship between them, which can easily lead to biased assessments of the hull's condition.

[0004] Secondly, traditional monitoring technologies do not fully consider the impact of the ship's own systems on biofouling and corrosion, especially the ballast water system. Ballast water is seawater loaded and unloaded by ships at different ports to adjust their center of gravity and ensure navigational safety. During cross-ocean transport, ballast water carries a large number of foreign microorganisms and biological species. When this ballast water is discharged into a new sea area, these foreign microorganisms may adhere to the ship's surface, exacerbating the degree of biofouling. At the same time, the water flow impact generated during ballast water discharge may also have a certain stripping effect on the fouling organisms on the ship's surface, affecting the distribution and development of biofouling. However, traditional monitoring technologies ignore this dynamic relationship between the ballast water system and biofouling, and cannot accurately predict the changing trend of biofouling.

[0005] In conclusion, in order to more effectively address the problems of biofouling and seawater corrosion on ships and improve the accuracy and reliability of ship monitoring, there is an urgent need for an IoT-based intelligent ship monitoring system and method to achieve accurate assessment of ship condition and intelligent decision-making. Summary of the Invention

[0006] To address the aforementioned issues, this application provides an Internet of Things-based intelligent ship monitoring system and method.

[0007] Firstly, this application provides a ship intelligent monitoring system based on the Internet of Things, which adopts the following technical solution:

[0008] An Internet of Things (IoT) based intelligent ship monitoring system includes:

[0009] The sensor layer includes a biofouling composite monitoring unit, a ballast water correlation monitoring unit, and a corrosion monitoring unit, which are used to collect biofouling data on the hull surface, characteristic parameters of the ballast water system, and hull corrosion data.

[0010] The Internet of Things (IoT) transmission layer, which includes multimode communication gateways and edge computing nodes, is used to realize the remote transmission and preprocessing of sensor data.

[0011] The data processing and analysis layer constructs a dynamic coupling model of ballast water and fouling, and an interference correction module, used to analyze the correlation between biofouling and ballast water parameters and compensate for environmental disturbances; and,

[0012] The application layer includes a 3D visualization monitoring platform and an intelligent report generation system, which are used to visualize the hull status and generate adaptive maintenance strategies.

[0013] Preferably, the biofouling composite monitoring unit includes a high-resolution infrared camera, a spectral sensor array, and a microelectrode array sensor, used to acquire biofouling data on the hull surface. The biofouling data on the hull surface includes image information of biofouling on the hull surface, spectral reflectance data, and bio-metabolic electrical signals.

[0014] The ballast water correlation monitoring unit includes a water quality multi-parameter sensor and a miniature flow velocity and pressure sensor, which are used to monitor and collect characteristic parameters of the ballast water system. The characteristic parameters of the ballast water system include ballast water quality parameters and discharge flow shear force parameters.

[0015] The corrosion monitoring unit includes an array-type fiber Bragg grating sensor and a galvanic corrosion monitor, used to monitor and collect ship hull corrosion data. The ship hull corrosion data includes corrosion depth data of the ship hull metal structure and potential difference data of different metal contacts on the ship hull.

[0016] Preferably, the water quality multi-parameter sensor integrates turbidity, dissolved oxygen, pH sensors and a microbial fluorescent labeling probe, which is used to detect exogenous bacterial DNA fragments using surface plasmon resonance technology.

[0017] Preferably, the mathematical expression of the ballast water-fouling dynamic coupling model is:

[0018]

[0019] in, C represents the growth rate of biofouling. bC is the microbial concentration in the ballast water, V is the flow rate of ballast water discharge, f(V) is the water flow shear force function, the positive term represents the peeling effect, the negative term represents the attachment promotion, and S(t) is the intensity of the antifouling treatment measure; k1 represents the influence coefficient of the microbial concentration in the ballast water on the growth rate of biofouling; k2 represents the influence coefficient of the ballast water discharge flow rate on the growth rate of biofouling; k3 represents the influence coefficient of the intensity of the antifouling treatment measure on the growth rate of biofouling, where k1, k2, and k3 are all dynamically adjusted through a pre-set weight dynamic adjustment model, and the weight dynamic adjustment model is an iterative training obtained by a machine learning model based on the LSTM algorithm through historical voyage data.

[0020] Preferably, in the ballast water-biofouling dynamic coupling model, the specific expression of the water flow shear force function is:

[0021] f(V) = τ = j * ρ * V n ;

[0022] where, V is the ballast water discharge flow rate, τ is the ballast water flow shear force, ρ is the density of the seawater body, j is the ship coefficient, n is the hull power number, and both j and n are determined by the management personnel according to the actual measured data of the hull or determined by simulation through a pre-set CFD simulation model according to the hull parameters.

[0023] Preferably, in the ballast water-biofouling dynamic coupling model, the specific calculation formula for the intensity of the antifouling treatment measure is:

[0024]

[0025] where, λ is the antifouling treatment reference intensity, α is the dynamic weight coefficient of the fouled area, β is the dynamic weight coefficient of the microbial concentration, and both λ, α, and β are dynamically adjusted through a pre-set weight dynamic adjustment model; A(t) is the real-time fouled coverage area of the hull, A0 is the reference value of the hull surface area, which is pre-set by the management personnel according to the ship type; C <000000​​​​​​​​​​​​​

[0029] A piezoelectric energy harvester is placed near the vibration source of the ship's main engine.

[0030] A seawater temperature difference power generation module, used to generate electricity by utilizing the temperature difference between the seawater inside and outside the ballast tank; and,

[0031] The power management unit is used to dynamically allocate power to the sensor layer and the IoT transmission layer.

[0032] Secondly, this application provides a ship intelligent monitoring method based on the Internet of Things, which adopts the following technical solution:

[0033] A ship intelligent monitoring method based on the Internet of Things includes the following steps:

[0034] S1. Routine Data Acquisition: Biofouling data of the hull surface, characteristic parameters of the ballast water system, and hull corrosion data are simultaneously acquired through the biofouling composite monitoring unit, ballast water correlation monitoring unit, and corrosion monitoring unit. The biofouling data of the hull surface includes image information, spectral reflectance data, and biological metabolic electrical signals of the biofouling. The characteristic parameters of the ballast water system include ballast water quality parameters and discharge flow shear force parameters. The ballast water quality parameters include turbidity, dissolved oxygen, pH, plankton concentration, exogenous bacterial DNA fragments, and nutrient content parameters of the ballast water. The hull corrosion data includes corrosion depth data of the hull metal structure and potential difference data of different metal contacts on the hull.

[0035] S2, High-frequency acquisition trigger: When a ballast water discharge event is detected, the high-frequency acquisition mode is triggered, and the sensor layer is controlled to acquire the characteristic parameters of the ballast water system at a high frequency according to the acquisition frequency preset in the high-frequency acquisition mode, until 30 minutes after the discharge is completed;

[0036] S3. Edge Preprocessing and Transmission: Data collected by the sensor layer is preprocessed through edge computing nodes and transmitted to the data processing and analysis layer through a multi-mode communication gateway;

[0037] S4. Dynamic Model Calculation: In the data processing and analysis layer, based on the biofouling data of the hull surface and the characteristic parameters of the ballast water system, the correlation between biofouling and ballast water parameters is analyzed using the dynamic coupling model of ballast water and fouling. The environmental interference factors are compensated through the interference correction module, and the growth rate of biofouling is output.

[0038] S5 Corrosion Status Assessment: Calculate and assess the hull corrosion rate based on hull corrosion data, and compensate for environmental interference factors through the interference correction module to output the hull corrosion rate.

[0039] S5. Strategy Generation and State Visualization: The real-time state of the hull is dynamically displayed through a digital twin model at the application layer. By combining the growth rate of biofouling and the hull corrosion rate with the collected biofouling data on the hull surface, ballast water system characteristic parameters, and hull corrosion data, a pre-set adaptive response mechanism is executed.

[0040] In summary, this application includes at least one of the following beneficial technical effects:

[0041] 1. This system achieves deep integration of IoT multimodal sensing, ballast water dynamic coupling analysis, and intelligent response mechanisms, enabling multi-parameter collaborative monitoring of biofouling, corrosion, and ballast water systems. It introduces a ballast water-fouling dynamic coupling model, incorporating the correlation between ballast water parameters and biofouling into the model analysis. This quantifies the dynamic correlation between ballast water system parameters (microbial concentration, discharge velocity) and the growth / stripping process of biofouling on the ship's hull, addressing the problem of traditional ship monitoring technologies neglecting the impact of the ship's own systems. It accurately predicts the development trend of biofouling, effectively improving the accuracy and efficiency of ship monitoring.

[0042] 2. By establishing a dynamic coupling model of ballast water and fouling, the dynamic correlation between ballast water system parameters and the growth / stripping process of biofouling on the hull is quantified, and the development trend of biofouling is accurately predicted, providing data support for antifouling maintenance strategies. Attached Figure Description

[0043] Figure 1 This is a system block diagram of an IoT-based intelligent ship monitoring system according to an embodiment of this application;

[0044] Figure 2 This is a system block diagram of the self-powered unit in the embodiments of this application;

[0045] Figure 3 This is a flowchart of a ship intelligent monitoring method based on the Internet of Things in an embodiment of this application.

[0046] Figure labeling: 1. Sensor layer; 11. Biofouling composite monitoring unit; 12. Ballast water correlation monitoring unit; 13. Corrosion monitoring unit; 2. Internet of Things transmission layer; 21. Multimode communication gateway; 22. Edge computing node; 3. Data processing and analysis layer; 31. Ballast water-fouling dynamic coupling model; 32. Interference correction module; 4. Application layer; 41. 3D visualization monitoring platform; 42. Intelligent report generation system; 5. Self-powered unit; 51. Piezoelectric energy harvester; 52. Seawater temperature difference power generation module; 53. Power management unit. Detailed Implementation

[0047] The following is in conjunction with the appendix Figure 1-3 This application will be described in further detail.

[0048] This application discloses an intelligent ship monitoring system based on the Internet of Things (IoT). (Refer to...) Figure 1 An IoT-based intelligent ship monitoring system includes:

[0049] The sensor layer includes a biofouling composite monitoring unit, a ballast water correlation monitoring unit, and a corrosion monitoring unit, which are used to collect biofouling data on the hull surface, characteristic parameters of the ballast water system, and hull corrosion data.

[0050] The Internet of Things (IoT) transmission layer, which includes multimode communication gateways and edge computing nodes, is used to realize the remote transmission and preprocessing of sensor data.

[0051] The data processing and analysis layer constructs a dynamic coupling model of ballast water and fouling, and an interference correction module, used to analyze the correlation between biofouling and ballast water parameters and compensate for environmental disturbances; and,

[0052] The application layer includes a 3D visualization monitoring platform and an intelligent report generation system, used to visualize hull status and generate adaptive maintenance strategies. This system achieves deep integration of IoT multimodal sensing, ballast water dynamic coupling analysis, and intelligent response mechanisms. It enables multi-parameter collaborative monitoring of biofouling, corrosion, and the ballast water system. A ballast water-fouling dynamic coupling model is introduced, incorporating the correlation between ballast water parameters and biofouling into the model analysis. This quantifies the dynamic correlation between ballast water system parameters (microbial concentration, discharge velocity) and the growth / stripping process of biofouling on the hull, addressing the problem of traditional ship monitoring technologies neglecting the impact of the ship's own systems. It accurately predicts the development trend of biofouling, effectively improving the accuracy and efficiency of ship monitoring.

[0053] The aforementioned biofouling monitoring unit includes a high-resolution infrared camera, a spectral sensor array, and a microelectrode array sensor, used to acquire biofouling data on the ship's hull surface. This biofouling data includes image information of the biofouling, spectral reflectance data, and biochemical metabolic electrical signals. The infrared camera captures high-definition images of the hull surface around the clock, identifying the types, distribution, and coverage area of ​​fouling organisms. The spectral sensor array collects spectral reflectance data in the 400-1000 nm wavelength band, accurately identifying different fouling organisms based on their spectral characteristics. The microelectrode array sensor monitors biochemical metabolic electrical signals, quantifying the activity of fouling organisms. These sensors work together to achieve integrated monitoring of the types, distribution, and activity of fouling organisms.

[0054] The aforementioned ballast water monitoring unit includes a multi-parameter water quality sensor and a miniature flow velocity and pressure sensor, used to monitor and collect characteristic parameters of the ballast water system. These characteristic parameters include ballast water quality parameters and discharge flow shear force parameters. The multi-parameter water quality sensor integrates turbidity, dissolved oxygen, and pH sensors, as well as a microbial fluorescently labeled probe. The microbial fluorescently labeled probe is used to detect exogenous bacterial DNA fragments using surface plasmon resonance technology, assessing the risk of ballast water carrying exogenous organisms and providing data support for fouling source tracing. The miniature flow velocity and pressure sensor measures the flow velocity and shear force during ballast water discharge, facilitating the quantification of the water flow's effect on fouling removal. The multi-parameter water quality sensor, in conjunction with the miniature flow velocity and pressure sensor, facilitates the quantification of the dual effects of ballast water discharge on fouling removal and promotion.

[0055] The aforementioned corrosion monitoring unit includes an array-type fiber Bragg grating sensor and a galvanic corrosion monitor, used to monitor and collect hull corrosion data. This data includes corrosion depth data of the hull's metal structure and potential difference data of different metal contacts within the hull. The array-type fiber Bragg grating sensor covers the hull surface with a 10cm × 10cm grid and uses wavelength shift (1pm resolution) to invert localized corrosion depth (accuracy ±5μm), achieving refined monitoring of the corrosion state and avoiding the blind spots of traditional point sensors. The galvanic corrosion monitor utilizes the potential difference between different metal contacts within the hull to provide early warning of galvanic corrosion risks, helping to address localized corrosion problems caused by the multi-material structure of ships.

[0056] The multi-mode communication gateway in the IoT transmission layer supports dynamic switching between 5G networks, BeiDou satellites, and LoRa communication methods. Specific switching strategies include:

[0057] Near-shore communication mode: 5G slicing technology is used to transmit high-definition image data with low latency (≤10ms) and large bandwidth (≥100Mbps);

[0058] Ocean-going communication mode: Switch to BeiDou satellite communication, with bandwidth sufficient for critical data transmission (≥1Mbps) and low packet loss rate (≤0.1%).

[0059] Based on the two communication modes, either of the following conditions must be met:

[0060] a. Sensor battery level ≤ 20%

[0061] b. Data packets ≤ 10KB and transmission intervals ≥ 5 minutes

[0062] c. Electromagnetic interference intensity ≥ 30 dBμV / m

[0063] d. Node density ≥ 50 nodes / 100㎡, LoRa communication is selected to assist communication, reduce the overall energy consumption of the sensor network, divert small data transmissions to the LoRa channel, reduce satellite communication costs, and ensure stable delivery of data packets even when 5G / BeiDou signals are interrupted.

[0064] In addition, the edge computing node integrates a real-time data caching module for caching sensor data. In this embodiment, the real-time data caching module is preferably configured to cache sensor data from the ship's hull for at least 72 hours.

[0065] The mathematical expression for the above dynamic coupling model of ballast water and fouling is:

[0066]

[0067] in, C represents the growth rate of biofouling. b Let V be the concentration of microorganisms in the ballast water, f(V) be the flow velocity of the ballast water discharge, f(V) be the shear force function of the water flow (positive terms represent peeling, negative terms represent adhesion promotion), and S(t) be the intensity of antifouling treatment measures. k1 represents the influence coefficient of microbial concentration in the ballast water on the biofouling growth rate; k2 represents the influence coefficient of ballast water discharge velocity on the biofouling growth rate; and k3 represents the influence coefficient of the intensity of antifouling treatment measures on the biofouling growth rate. k1, k2, and k3 are all dynamically adjusted using a pre-set weighted dynamic adjustment model. This weighted dynamic adjustment model is a machine learning model based on the LSTM algorithm, iteratively trained using historical cruise data. It should be noted that the specific training steps of the weighted dynamic adjustment model are existing technology and will not be elaborated here. The historical cruise data includes multi-dimensional information such as ballast water-related data and corresponding fouling conditions under different sea areas and environmental conditions. The LSTM algorithm can effectively process and extract features from these complex time series data, uncovering hidden patterns and features in the data, such as the potential relationship between factors like different seasons, different routes, different ship types, and the pollution growth rate.

[0068] The core function of the ballast water-fouling dynamic coupling model is to quantify the dynamic correlation between the parameters of the ballast water system (microbial concentration, discharge flow rate) and the hull biofouling growth / stripping process. Through mathematical modeling and machine learning, it accurately predicts the development trend of biofouling and provides data support for anti-fouling maintenance strategies. Specifically, first, a dynamic equilibrium equation is established by comprehensively considering the microbial concentration in the ballast water (the attached pollution source), the discharge flow rate (the shear force stripping effect), and the anti-fouling treatment measures (such as the anti-fouling agent released by the coating). Secondly, through the weight model (LSTM algorithm) trained with historical data, the influence of environmental variables (such as seawater temperature, salinity) on fouling growth is automatically calibrated, and the weight coefficient is dynamically set to improve the prediction accuracy (the growth rate of biofouling). Finally, the output fouling growth rate combined with the corrosion situation directly drives various anti-fouling measures to prevent problems before they occur. Before the biofouling grows rapidly, its growth possibility is destroyed, and the hidden danger of the damage caused by biofouling to the hull is eliminated in advance, extending the hull life and reducing the hull maintenance cost.

[0069] In the above ballast water-fouling dynamic coupling model, the specific expression of the water flow shear force function is:

[0070] f(V) = τ = j * ρ * V n ;

[0071] where, V is the ballast water discharge flow rate, τ is the ballast water flow shear force, ρ is the seawater density, j is the ship coefficient, n is the hull power number, and both j and n are determined by the management personnel according to the actual measured data of the hull or determined by simulating through the pre-set CFD simulation model according to the hull parameters.

[0072] In the above ballast water-fouling dynamic coupling model, the specific calculation formula for the intensity of the anti-fouling treatment measures is:

[0073]

[0074] where, λ is the anti-fouling treatment reference intensity, α is the dynamic weight coefficient of the fouling area, β is the dynamic weight coefficient of the microbial concentration, and both λ, α, and β are dynamically adjusted and set through the pre-set weight dynamic adjustment model; A(t) is the real-time fouling coverage area of the hull, A0 is the reference value of the hull surface area, which is pre-set by the management personnel according to the ship type; C b (t) is the microbial concentration of the ballast water, C bth micro is the pre-set biological concentration threshold; τ(t) is the ballast water shear force. Among them it grows exponentially when the microbial concentration exceeds the threshold, enhancing the response to high-pollution scenarios; This is a smooth transition function for the influence of shear force, effectively avoiding threshold abrupt changes. By using specific calculation formulas for the intensity of antifouling treatment measures, not only can the equivalent amount of antifouling agent per unit area of ​​the hull be accurately calculated, but the operation of actuators can also be directly guided through a ballast water-fouling dynamic coupling model. For example, based on actual conditions, the growth rate of biofouling can be set to 0, and the baseline intensity λ of the antifouling treatment can be derived in reverse, further guiding the operation of the antifouling actuators to achieve more targeted defouling.

[0075] The above interference correction module is a Bayesian network model that dynamically compensates for the following interference factors:

[0076] Ballast water discharge interference: During ballast water discharge, air bubbles and sediment carried by the water flow can interfere with camera image recognition (mistakenly identifying air bubbles as contamination). Bayesian networks adjust the background model of the biofouling image recognition algorithm during the discharge process to eliminate false detections caused by water flow disturbance. In addition, the image-based biofouling image recognition algorithm is an existing technology that can be selected according to actual needs. In this embodiment, the preferred biofouling image recognition algorithm is the YOLOv8 algorithm.

[0077] The corrosion rate is calculated by adding a correction factor of 15%-20% based on the nutrient concentration of the ballast water (nitrate > 0.1 mg / L). The specific correction formula is as follows:

[0078]

[0079] Among them, CR 修正 The data presented here represents the corrected corrosion data. CR represents the original corrosion data measured by the corrosion monitoring unit, and NO represents the nitrate concentration. By configuring the interference correction module, the impact of environmental interference factors on data analysis can be significantly reduced, thereby improving the accuracy of the data analysis.

[0080] The aforementioned 3D visualization monitoring platform uses the Unity 3D engine to build a digital twin model, accurately presenting the ship's structure, equipment operating status, and the location and extent of biofouling and corrosion changes in a 3D visualization format. It also connects to AR devices for AR visualization. Building a digital twin model based on the Unity 3D engine to achieve AR visualization of the ship's condition helps staff intuitively understand the ship's status and improves decision-making efficiency.

[0081] Reference Figure 2 In addition, the system is equipped with a self-powered unit, which specifically includes:

[0082] A piezoelectric energy harvester is placed near the vibration source of the ship's main engine.

[0083] A seawater temperature difference power generation module, used to generate electricity by utilizing the temperature difference between the seawater inside and outside the ballast tank; and,

[0084] The power management unit dynamically distributes electrical energy to the sensor layer and the IoT transmission layer. It utilizes piezoelectric energy harvesting (vibration energy) and seawater temperature difference power generation (thermal energy) to achieve energy self-sufficiency for the sensor network.

[0085] This application also discloses an IoT-based intelligent ship monitoring method. Referring to Figure 3, an IoT-based intelligent ship monitoring method includes the following steps:

[0086] S1. Routine Data Acquisition: Biofouling data of the hull surface, characteristic parameters of the ballast water system, and hull corrosion data are simultaneously acquired through a biofouling composite monitoring unit, a ballast water correlation monitoring unit, and a corrosion monitoring unit. The hull surface biofouling data includes image information, spectral reflectance data, and biological metabolic electrical signals. The ballast water system characteristic parameters include ballast water quality parameters and discharge flow shear force parameters. Ballast water quality parameters include turbidity, dissolved oxygen, pH, plankton concentration, exogenous bacterial DNA fragments, and nutrient content parameters. The hull corrosion data includes corrosion depth data of the hull's metal structure and potential difference data at different metal junctions. Under normal conditions, various data are stably acquired through the biofouling composite monitoring unit, ballast water correlation monitoring unit, and corrosion monitoring unit.

[0087] S2, High-frequency acquisition trigger: When a ballast water discharge event is detected, the high-frequency acquisition mode is triggered, and the sensor layer is controlled to acquire the characteristic parameters of the ballast water system at a high frequency according to the acquisition frequency preset in the high-frequency acquisition mode, until 30 minutes after the discharge is completed;

[0088] S3. Edge Preprocessing and Transmission: Data collected by the sensor layer is preprocessed through edge computing nodes and transmitted to the data processing and analysis layer through a multi-mode communication gateway;

[0089] S4. Dynamic Model Calculation: In the data processing and analysis layer, based on the biofouling data of the hull surface and the characteristic parameters of the ballast water system, the correlation between biofouling and ballast water parameters is analyzed using the ballast water-fouling dynamic coupling model. The environmental interference factors are compensated by the interference correction module, and the growth rate of biofouling is output. The Bayesian network adjusts the background model of the biofouling image recognition algorithm during the discharge process to eliminate false detections caused by water flow disturbances and accurately and efficiently determine the fouling area.

[0090] S5. Corrosion Status Assessment: The corrosion rate of the hull is calculated and assessed based on the hull corrosion data, and environmental interference factors are compensated through the interference correction module to output the hull corrosion rate; the corrosion rate is corrected by the Bayesian network based on the ballast water nutrient concentration.

[0091] S5. Strategy Generation and Status Visualization: The system dynamically displays the real-time status of the hull through a digital twin model at the application layer. It combines the growth rate of biofouling and the hull corrosion rate with collected biofouling data from the hull surface, ballast water system characteristic parameters, and hull corrosion data to execute a pre-set adaptive response mechanism. This adaptive response mechanism is set by the administrator based on the actual situation of the decontamination methods available on board. Through these steps, the system achieves deep integration of IoT multimodal sensing, ballast water dynamic coupling analysis, and intelligent response mechanisms. It enables multi-parameter collaborative monitoring of biofouling, corrosion, and the ballast water system. By introducing a ballast water-fouling dynamic coupling model, the system incorporates the correlation between ballast water parameters and biofouling into the model analysis, quantifying the dynamic correlation between ballast water system parameters (microbial concentration, discharge flow rate) and the biofouling growth / stripping process on the hull. This addresses the problem of traditional ship monitoring technologies neglecting the impact of the ship's own systems, accurately predicts the development trend of biofouling, and effectively improves the accuracy and efficiency of ship monitoring.

[0092] This application also discloses a computer-readable storage medium that stores a computer program that can be loaded by a processor and executed as described above. The computer-readable storage medium includes, for example, various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0093] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on these embodiments, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art can still combine, add, delete, or otherwise adjust the features of the various embodiments of the present invention according to the circumstances without conflict or creative effort, thereby obtaining different technical solutions that do not fundamentally depart from the concept of the present invention. These technical solutions also fall within the scope of protection of the present invention.

Claims

1. An Internet of Things based intelligent monitoring system for a ship, characterized in that, The application relates to a ship hull biofouling monitoring system, which comprises the following steps: a sensor layer, which comprises a biofouling composite monitoring unit, a ballast water correlation monitoring unit and a corrosion monitoring unit, is used for collecting ship hull surface biofouling data, ballast water system characteristic parameters and ship hull corrosion data, wherein the ballast water system characteristic parameters comprise ballast water quality parameters and discharge water flow shear force parameters; an Internet of Things transmission layer, which comprises a multi-mode communication gateway and an edge computing node, is used for realizing remote transmission and preprocessing of sensor data; a data processing and analysis layer, which constructs a ballast water-fouling dynamic coupling model and an interference correction module, is used for analyzing the correlation between biofouling and ballast water parameters and compensating environmental interference; and an application layer, which comprises a three-dimensional visual monitoring platform and an intelligent report generation system, is used for visualizing the ship hull state and generating an adaptive maintenance strategy; the ballast water-fouling dynamic coupling model has a mathematical expression as follows: the biofouling composite monitoring unit comprises a high-resolution infrared camera, a spectrum sensor array and a microelectrode array sensor, and is used for acquiring ship hull surface biofouling data, wherein the ship hull surface biofouling data comprises image information, spectrum reflectivity data and biological metabolic electric signals of the ship hull surface biofouling; ； wherein, is the growth rate of biofouling, is the concentration of microorganisms in the ballast water, V is the flow rate of the ballast water discharge, is the water flow shear force function, the positive term represents the peeling effect, and the negative term represents the adhesion promotion, is the strength of the antifouling treatment measure; represents the influence coefficient of the concentration of microorganisms in the ballast water on the growth rate of biofouling; represents the influence coefficient of the flow rate of the ballast water discharge on the growth rate of biofouling; represents the influence coefficient of the strength of the antifouling treatment measure on the growth rate of biofouling, wherein and are dynamically adjusted by a pre-set weight dynamic adjustment model, and the weight dynamic adjustment model is obtained by iterative training of historical voyage data based on an LSTM algorithm.​ 2. The ship intelligent monitoring system based on the Internet of Things according to claim 1, characterized in that: the ballast water correlation monitoring unit comprises a water quality multi-parameter sensor and a micro flow velocity and pressure sensor, and is used for monitoring and collecting ballast water system characteristic parameters; the corrosion monitoring unit comprises an array type fiber Bragg grating sensor and a galvanic corrosion monitor, and is used for monitoring and collecting ship hull corrosion data, wherein the ship hull corrosion data comprises ship hull metal structure corrosion depth data and potential difference data of different ship hull metal junctions. The water quality multi-parameter sensor is integrated with a turbidity sensor, a dissolved oxygen sensor, a pH sensor and a microorganism fluorescence marking probe, and the microorganism fluorescence marking probe is used for detecting foreign bacterial group DNA fragments through a surface plasmon resonance technology.

3. The ship intelligent monitoring system based on the Internet of Things according to claim 2, characterized in that: In the ballast water-fouling dynamic coupling model, the specific expression of a water flow shear force function is as follows:

4. The ship intelligent monitoring system based on the Internet of Things according to claim 1, characterized in that: wherein V is a ballast water discharge flow rate, tau is a ballast water flow shear force, rho is a seawater body density, j is a ship body coefficient and n is a ship body power, and j and n are determined by an administrator according to ship hull measured data or simulated through a pre-set CFD simulation model according to ship hull parameters. ； In the ballast water-fouling dynamic coupling model, the specific calculation formula of the strength of an antifouling treatment measure is as follows:

5. The ship intelligent monitoring system based on the Internet of Things according to claim 1, characterized in that, The edge computing node is integrated with a real-time data caching module and is used for caching sensor data. ； Wherein, λ is the anti-fouling treatment reference strength, α is the dynamic weight coefficient of the fouling area, β is the dynamic weight coefficient of the microbial concentration, and λ, α, β are dynamically adjusted and set through the pre-set weight dynamic adjustment model; is the real-time fouling coverage area of the ship body, is the ship body surface area reference value, which is pre-set by the management personnel according to the ship model; is the microbial concentration of the ballast water, μ is the pre-set biological concentration threshold value; is the shear force of the ballast water.

6. The ship intelligent monitoring system based on the Internet of Things according to claim 1, characterized in that: The three-dimensional visual monitoring platform constructs a digital twin model based on a Unity 3D engine, accurately presents the ship hull structure, equipment running state and the position and degree change of biofouling and corrosion in a three-dimensional visual form, and realizes AR visualization through connection with an AR device.

7. The ship intelligent monitoring system based on the Internet of Things according to claim 1, characterized in that: The application further comprises a self-powered unit, which specifically comprises: 8.The ship intelligent monitoring system based on Internet of Things according to claim 1, characterized in that, a piezoelectric energy collector arranged near a ship main engine vibration source; a seawater temperature difference power generation module used for generating power by using the seawater temperature difference between the inside and outside of a ballast tank; and a power management unit used for dynamically distributing electric energy to the sensor layer and the Internet of Things transmission layer. The application further comprises the following steps:

9. An intelligent monitoring method for a ship based on an Internet of Things, applied to the intelligent monitoring system for a ship based on an Internet of Things in any one of claims 1-8, characterized in that, ​ S1, normal data acquisition: through the biological fouling composite monitoring unit, the ballast water associated monitoring unit and the corrosion monitoring unit, the ship surface biological fouling data, the ballast water system characteristic parameters and the ship corrosion data are synchronously collected; the ship surface biological fouling data includes the image information, the spectral reflectance data and the biological metabolism electric signal of the ship surface biological fouling; the ballast water system characteristic parameters include the ballast water quality parameters and the discharge water flow shear force parameters, the ballast water quality parameters include the turbidity, the dissolved oxygen, the pH, the plankton concentration, the alien bacteria group DNA fragment and the nutrient salt content parameters of the ballast water; the ship corrosion data includes the ship metal structure corrosion depth data and the potential difference data of the different metal joints of the ship; S2, high-frequency acquisition trigger: when the ballast water discharge event is detected, the high-frequency acquisition mode is triggered, the sensor layer controls the acquisition frequency of the ballast water system characteristic parameters according to the high-frequency acquisition mode preset, and the acquisition is carried out frequently until 30 minutes after the discharge is finished; S3, edge preprocessing and transmission: the data collected by the sensor layer is preprocessed through the edge computing node, and is transmitted to the data processing and analysis layer through the multi-mode communication gateway; S4, dynamic model calculation: in the data processing and analysis layer, according to the ship surface biological fouling data and the ballast water system characteristic parameters, the ballast water-fouling dynamic coupling model is used to analyze the correlation between the biological fouling and the ballast water parameters, and the environmental interference factors are compensated through the interference correction module, and the growth rate of the biological fouling is output; S5, corrosion state evaluation: according to the ship corrosion data, the ship corrosion speed is calculated and evaluated, and the environmental interference factors are compensated through the interference correction module, and the ship corrosion rate is output; S5, strategy generation and state visualization: through the digital twin model of the application layer, the real-time state of the ship is dynamically displayed, the growth rate of the biological fouling and the ship corrosion rate are combined with the collected ship surface biological fouling data, ballast water system characteristic parameters and ship corrosion data, and the pre-set adaptive response mechanism is executed.

Images