Ship ballast water treatment method, system and electronic device
By deploying a sensor cluster to acquire raw indicators of ballast water, constructing a multi-source parameter dataset and calculating the sub-difficulty coefficient, and generating processing instructions, the problem of poor adaptability and high cost in existing ballast water treatment technologies is solved, achieving a more reliable and economical water quality treatment effect.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN OCEAN UNIV
- Filing Date
- 2025-11-03
- Publication Date
- 2026-07-14
Smart Images
Figure CN121365300B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of ship ballast water technology, and in particular to ship ballast water treatment methods, systems and electronic equipment. Background Technology
[0002] With the booming development of global maritime trade and the flourishing shipping industry, the total discharge of ballast water from ships has continued to rise, becoming one of the main ways to introduce invasive alien species and disrupt the regional marine ecological balance. The International Maritime Organization and environmental protection agencies in various countries have successively introduced strict regulations, mandating the treatment of ballast water to eliminate its potential threat to the marine environment. The installation and efficient operation of ballast water treatment systems have become essential requirements for modern ships.
[0003] Currently, mainstream ballast water treatment technologies mainly include physicochemical methods such as ultraviolet disinfection and electrolytic chlorination, which are widely used in practical engineering. However, most existing technologies still rely on single or fixed treatment logic, such as controlling the power of ultraviolet lamps solely based on flow rate or simply switching treatment modes based on salinity thresholds. This has significant drawbacks: First, ship systems lack the ability to perceive and integrate multiple water quality parameters in real time, making it impossible to accurately quantify the comprehensive treatment difficulty of the water body, resulting in blind, redundant, or insufficient treatment processes. Second, control strategies are rigid and cannot adaptively adjust treatment intensity and modes according to dynamic changes in water quality. Third, ship systems generally lack foresight, relying solely on feedback from the final outlet for control, which is a passive response. Once treatment fails, a costly recycling and reprocessing mode must be initiated, resulting in unsatisfactory economic efficiency and reliability.
[0004] In summary, existing ballast water treatment technologies suffer from a series of problems, including poor adaptability, unstable treatment efficiency, weak compliance assurance, and high operating costs, due to the failure to achieve deep fusion and intelligent analysis of multi-source water quality parameters and the lack of a feedforward optimization mechanism based on real-time prediction. There is an urgent need for an intelligent treatment method capable of real-time assessment of treatment difficulty, dynamic optimization of treatment strategies, and predictive control capabilities to comprehensively improve the reliability, economy, and environmental safety of ballast water treatment. Summary of the Invention
[0005] This disclosure provides a method, system, and electronic equipment for treating ship ballast water, in order to solve the technical problems of poor adaptability, unstable treatment efficiency, weak compliance assurance and high operating costs in the prior art.
[0006] According to a first aspect of this disclosure, a method for treating ship ballast water is provided, comprising:
[0007] A sensor cluster is deployed in the key ballast water pipeline of the ship to acquire raw ballast water indicators in real time. The raw ballast water indicators are preprocessed to construct a multi-source parameter dataset, which includes physical parameters, chemical parameters, and biological parameters.
[0008] The sub-difficulty coefficients are calculated hierarchically based on multi-source parameter datasets, and the sub-difficulty coefficients include physical sub-difficulty coefficients, chemical sub-difficulty coefficients, and biological sub-difficulty coefficients.
[0009] Obtain the sub-difficulty coefficients and combine them with dynamic weights to calculate the comprehensive processing difficulty coefficient;
[0010] Ship ballast water treatment instructions are generated based on sub-difficulty coefficients and comprehensive treatment difficulty coefficients. These instructions include physical treatment instructions, chemical treatment instructions, biological treatment instructions, and coordinated optimization instructions.
[0011] Real-time simulation prediction based on ship ballast water treatment instructions is used to obtain an estimated effluent water quality. The estimated effluent water quality is compared with the water quality compliance threshold to determine whether to generate a secondary ship ballast water treatment instruction.
[0012] If a secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the secondary ballast water treatment instruction.
[0013] If no secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the ballast water treatment instruction.
[0014] Based on the treated ballast water, the sub-difficulty coefficient is recalculated and compared with the biological sub-difficulty coefficient and the biosafety threshold. If the biological sub-difficulty coefficient is lower than the compliance threshold, discharge is authorized; otherwise, iterative processing is carried out until the biological sub-difficulty coefficient meets the standard.
[0015] According to a second aspect of this disclosure, a ship ballast water treatment system is provided, comprising:
[0016] A multi-source sensing module is used to deploy a sensor cluster on the key ballast water pipeline of a ship to acquire raw ballast water indicators in real time, preprocess the raw ballast water indicators, and construct a multi-source parameter dataset, which includes physical parameters, chemical parameters, and biological parameters.
[0017] The sub-difficulty coefficient hierarchical calculation module is used to calculate the sub-difficulty coefficient hierarchically based on a multi-source parameter dataset. The sub-difficulty coefficients include physical sub-difficulty coefficients, chemical sub-difficulty coefficients, and biological sub-difficulty coefficients.
[0018] A comprehensive processing difficulty coefficient acquisition module is used to acquire sub-difficulty coefficients and calculate the comprehensive processing difficulty coefficient in combination with dynamic weights.
[0019] The instruction generation module is used to generate ship ballast water treatment instructions based on the sub-difficulty coefficient and the comprehensive processing difficulty coefficient. The ship ballast water treatment instructions include physical treatment instructions, chemical treatment instructions, biological treatment instructions and coordinated optimization instructions.
[0020] The predictive optimization module is used to perform real-time simulation prediction based on the ship ballast water treatment command, obtain the estimated effluent water quality, compare the estimated effluent water quality with the water quality compliance threshold, and determine whether to generate a secondary ship ballast water treatment command.
[0021] If a secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the secondary ballast water treatment instruction.
[0022] If no secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the ballast water treatment instruction.
[0023] The final compliance decision module is used to recalculate the sub-difficulty coefficient based on the treated ballast water, compare the biological sub-difficulty coefficient with the biosafety threshold, and authorize discharge if the biological sub-difficulty coefficient is lower than the compliance threshold; otherwise, iterative processing is performed until the biological sub-difficulty coefficient meets the standard.
[0024] According to a third aspect of this disclosure, embodiments of this application also provide an electronic device, including: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor communicates with the memory via the bus, and when the machine-readable instructions are executed by the processor, the steps of the ship ballast water treatment method described above are performed.
[0025] One or more technical solutions provided in this disclosure have at least the following technical effects or advantages: Deploying a sensor cluster in key ballast water pipelines of ships to acquire raw ballast water indicators in real time; preprocessing the raw ballast water indicators to construct a multi-source parameter dataset, which includes physical parameters, chemical parameters, and biological parameters; calculating sub-difficulty coefficients hierarchically based on the multi-source parameter dataset, which includes physical sub-difficulty coefficients, chemical sub-difficulty coefficients, and biological sub-difficulty coefficients; acquiring the sub-difficulty coefficients and calculating the comprehensive processing difficulty coefficient based on dynamic weights; generating ship ballast water treatment instructions based on the sub-difficulty coefficients and the comprehensive processing difficulty coefficient, which includes physical processing instructions. The system includes commands for ballast water treatment, chemical treatment, biological treatment, and coordinated optimization. Based on real-time simulation prediction of the ballast water treatment commands, it obtains an estimated effluent water quality, compares this estimated effluent water quality with compliance thresholds, and determines whether to generate a secondary ballast water treatment command. If a secondary ballast water treatment command is generated, the ship treats the ballast water according to the command. If no secondary ballast water treatment command is generated, the ship treats the ballast water according to the command. Based on the treated ballast water, the sub-difficulty coefficient is recalculated, and compared with the biological sub-difficulty coefficient and biosafety threshold. If the biological sub-difficulty coefficient is lower than the compliance threshold, discharge is authorized; otherwise, iterative processing continues until the biological sub-difficulty coefficient meets the standard. This system solves the technical problems of poor adaptability, unstable treatment efficiency, weak compliance assurance, and high operating costs in existing technologies. It achieves a comprehensive improvement in the reliability, economy, and environmental safety of ballast water treatment.
[0026] The above description is merely an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description
[0027] To more clearly illustrate the technical solutions in this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.
[0028] Figure 1 A schematic flowchart of a ship ballast water treatment method provided in an embodiment of this application;
[0029] Figure 2 This is a schematic diagram of the structure of a ship ballast water treatment system provided in an embodiment of this application.
[0030] Figure labeling: Multi-source perception module 11, Sub-difficulty coefficient hierarchical calculation module 12, Comprehensive processing difficulty coefficient acquisition module 13, Instruction generation module 14, Predictive optimization module 15, Final compliance adjudication module 16. Detailed Implementation
[0031] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.
[0032] Example 1, the ship ballast water treatment method provided in this disclosure, is referred to below. Figure 1 The methods include:
[0033] S1: Deploy a sensor cluster on the key ballast water pipeline of the ship to obtain the raw ballast water indicators in real time, preprocess the raw ballast water indicators, and construct a multi-source parameter dataset, which includes physical parameters, chemical parameters, and biological parameters;
[0034] Furthermore, step S1 also includes:
[0035] Select key ballast water pipelines for ships, install sensor clusters, and collect raw ballast water indicators. The key ballast water pipelines include inlet monitoring pipelines and outlet verification pipelines. The sensor clusters include physical indicator sensors, chemical indicator sensors, and biological indicator sensors.
[0036] The raw indicators of ballast water are pretreated to obtain physical, chemical and biological parameters. The three types of parameters are integrated to construct a multi-source parameter dataset. The pretreatment includes data transformation, validity verification, data smoothing and time alignment. The physical parameters include turbidity and particulate matter size distribution. The chemical parameters include ultraviolet transmittance and salinity. The biological parameters include real-time fluorescence intensity and chlorophyll a concentration.
[0037] Specifically, key ballast water pipelines were selected, including the inlet monitoring pipeline section and the outlet verification pipeline section. The inlet monitoring pipeline section is the main pipeline section from the seawater suction pump to the coarse filter, and the outlet verification pipeline section is the main pipeline section from the outlet flange of the ultraviolet reactor to the discharge valve. A sensor cluster was constructed by integrating physical, chemical, and biological indicator sensors. Based on the processing logic and sensor installation principles, the sensor cluster was deployed on the two key ballast water pipeline sections to collect raw ballast water indicators in real time.
[0038] Material index sensors include online turbidity meters and online particle size analyzers. The online turbidity meter uses the HachTU5 series, installed in a flow-through cell. Turbidity is measured by diverting the water sample to an independent small chamber with an observation window to isolate air bubble interference. It also integrates an automatic cleaning brush to prevent biofouling. The online particle size analyzer is installed in a bypass configuration, allowing the water sample to flow through its laser measurement chamber at a reduced flow rate to obtain particle size distribution data and assess clogging risk. Chemical index sensors include online UVT sensors and industrial conductivity and salinity sensors. The online UVT sensor uses the ATi T90 series, also installed in a flow-through cell and equipped with an ultrasonic or mechanical automatic cleaning device to accurately measure the transmittance of 254nm ultraviolet light. The industrial conductivity and salinity sensors are directly inserted into the main pipeline through a sleeve with a ball valve to obtain practical salinity values in PSU units. Biological index sensors include an online ATP monitor and an online fluorometer. The online ATP monitor, installed as a bypass sampling unit on a nearby bulkhead, continuously samples and automatically injects reagents. It accurately measures the total amount of all surviving microorganisms using bioluminescence to assess bioburden. The online fluorometer is a direct insertion type, inserted into the main pipeline through a sheath to acquire chlorophyll a concentration data. Data from all sensors are integrated to obtain the raw ballast water indicators. It is important to note that because the online turbidity meter, online UVT sensor, industrial conductivity and salinity sensor, and online fluorometer transmit data via 4–20 mA analog signals, the data obtained from these four sensors in the raw ballast water indicators are current values and have not yet been converted to engineering values. In contrast, the online particle size analyzer and online ATP monitor transmit data via digital communication protocols; therefore, these two types of data are engineering values that do not require conversion.
[0039] Sensor installation must meet four core principles: Representativeness of measurement data: The sensor must be installed in a straight pipe section with stable flow and sufficient mixing, away from sources of turbulence or bubbles such as pumps, valves, and elbows. Typically, the upstream straight pipe section length should be no less than 10 times the pipe diameter, and the downstream no less than 5 times the pipe diameter, to ensure that the collected water sample accurately reflects the overall water quality of the main pipeline. Maintainability of location: The sensor location must provide sufficient operating space for technicians to perform routine calibration, cleaning, disassembly, and replacement. Operational safety: The installation method must allow for sensor insertion and removal without shutting down the system or draining the pipeline. Environmental adaptability: Due to the high vibration, humidity, and salt spray corrosiveness of the marine environment, industrial-grade products with classification society certification must be selected, equipped with robust and shock-resistant mounting brackets to ensure long-term operational reliability.
[0040] Data preprocessing was performed based on the collected raw ballast water parameters. First, data conversion was performed by reading data transmitted via 4–20 mA analog signals. Using the slope and intercept parameters provided in the corresponding sensor's factory calibration certificate, a linear transformation formula was used to convert the current values back to physically meaningful engineering values, obtaining turbidity, UV transmittance, salinity, and chlorophyll a concentration, representing their actual physical significance. Subsequently, the validity of each data point in the raw ballast water parameters was verified, including range checks to ensure it was within the sensor's range and physical limits, and rate of change checks. If a parameter value changed abruptly beyond its reasonable physical change threshold during adjacent sampling periods, the data was marked as abnormal. For example, a sudden change in turbidity exceeding 100 NTU might be due to transient sensor interference or bubble erosion.
[0041] After validity verification, the data smoothing stage begins. This step aims to suppress random noise and transient interference, extracting the true signal trend. For valid data that passes verification, a first-order low-pass filter is applied, with the specific formula as follows: Here, x represents the current filtered value, indicating the smoothed data; y represents the actual measured value; z represents the filtered value at the previous moment; and α represents the filtering coefficient, with a value between 0 and 1. Its value depends on the parameter characteristics. For water quality parameters that change relatively slowly, such as salinity, a smaller α can be chosen to enhance the smoothing effect; for parameters that may change rapidly, a larger α is chosen to retain more dynamic characteristics. Data marked as abnormal and invalid is discarded and replaced with the valid filtered value from the previous moment to ensure the continuity of the data stream.
[0042] To achieve fusion analysis of multi-source data and perform time alignment, since there may be slight differences in the response time and sampling frequency of different sensors, it is necessary to use a high-precision clock as a reference to stamp the data with a unified timestamp and interpolate and align all data to the same equally spaced time series, thereby ensuring that all parameter values in the data frame at the same moment represent the characteristics of the same water sample.
[0043] Finally, all the data, after the aforementioned transformation, validity verification, smoothing, and time alignment, are integrated frame by frame to construct a structured multi-source parameter dataset. This dataset is indexed by timestamps, and each row contains physical, chemical, and biological parameters at the same moment. As the sole reliable data source for the entire intelligent processing system, this dataset directly serves subsequent hierarchical difficulty coefficient calculations and adaptive control decisions; its quality directly determines the accuracy and reliability of the entire system's intelligent judgments.
[0044] S2: Calculate sub-difficulty coefficients hierarchically based on multi-source parameter datasets, including physical sub-difficulty coefficients, chemical sub-difficulty coefficients, and biological sub-difficulty coefficients;
[0045] Furthermore, step S2 also includes:
[0046] The turbidity difficulty coefficient and particulate matter size difficulty coefficient are calculated based on the physical parameters in the multi-source parameter dataset. The specific formula for calculating the turbidity difficulty coefficient is as follows:
[0047] ;
[0048] in, The turbidity difficulty coefficient is represented by 'min', which represents the function that selects the minimum value, and 'TUR' represents the turbidity value. This represents the maximum turbidity design threshold;
[0049] The specific formula for calculating the particle size difficulty coefficient is as follows:
[0050] ;
[0051] in, D90 represents the particle size distribution, while D90 represents the particle size distribution. This represents the preset maximum allowed D90 threshold.
[0052] Using the shortest board principle, the maximum value between the turbidity difficulty coefficient and the particulate matter size difficulty coefficient is selected as the physical sub-difficulty coefficient.
[0053] The difficulty coefficients for calculating ultraviolet transmittance and salinity are derived from chemical parameters in a multi-source parameter dataset. The specific formula for calculating the ultraviolet transmittance difficulty coefficient is as follows:
[0054] ;
[0055] in, The difficulty coefficient represents ultraviolet transmittance, while UVT represents ultraviolet transmittance.
[0056] The specific formula for calculating the salinity difficulty coefficient is as follows:
[0057] ;
[0058] in, The value represents the salinity difficulty coefficient, min represents the function that selects the minimum value, and SAL represents the salinity value. This represents the optimal salinity point for the technology. The radius representing the effective operating range;
[0059] The weighted fusion method is used to calculate the chemical component difficulty coefficient. The specific formula is as follows: Where kc represents the chemical difficulty coefficient, The difficulty level of ultraviolet transmittance is represented by the coefficient of measurement. Represents the salinity difficulty level. and These are the weights of the two coefficients;
[0060] The difficulty coefficients for calculating total bioactivity and algal concentration are derived from biological parameters in a multi-source parameter dataset. The specific formula for calculating the total bioactivity difficulty coefficient is as follows:
[0061] ;
[0062] in, The total biological activity difficulty coefficient is represented by _min_, which represents the function for selecting the minimum value, and ATP represents the real-time fluorescence intensity value. Represents maximum bioburden capacity;
[0063] The specific formula for calculating the difficulty coefficient of algae concentration is as follows:
[0064] ;
[0065] in, The difficulty coefficient represents the algae concentration; min represents the function that selects the minimum value; chla represents the chlorophyll a concentration value. This represents the maximum algal concentration threshold;
[0066] Using the shortest board principle, the maximum value between the total biological activity difficulty coefficient and the algal concentration difficulty coefficient is selected as the biological sub-difficulty coefficient.
[0067] Specifically, a multi-source parameter dataset is obtained, and the physical, chemical, and biological sub-difficulty coefficients are calculated based on the physical, chemical, and biological parameters in the multi-source parameter dataset.
[0068] The physical difficulty coefficient quantifies the physical challenge posed by suspended particulate matter in ballast water to the treatment system, and is used to assess the risk of equipment blockage, mechanical wear, and fluid flow. The physical difficulty coefficient is calculated based on sensor data acquisition. An online turbidity meter measures the turbidity of the water sample in real time, obtaining a turbidity value in NTU units. A higher value indicates more suspended particles scattering light in the water. Simultaneously, an online particle size analyzer provides particle size distribution data and outputs the key statistical indicator D90, which indicates that 90% of particles are smaller than this value, effectively characterizing the presence of large particles.
[0069] After obtaining the physical parameters, the calculation process begins. The physical difficulty coefficient consists of two independent dimensions: turbidity difficulty coefficient and particulate matter size difficulty coefficient. The calculation formulas for these two coefficients are as follows:
[0070] Turbidity difficulty level: ;
[0071] in, TUR represents the turbidity difficulty coefficient, TUR represents the turbidity value obtained from the online turbidity meter, and min represents the function that selects the minimum value. The actual meaning of this function is to set an upper limit for the difficulty coefficient, ensuring that no matter how large the calculated value is, the maximum value of the final output will not exceed 1. All subsequent formulas using the min function aim to ensure that the final sub-difficulty coefficient is within the interval [0,1]. The maximum turbidity design threshold is the preset value, which is mainly determined based on the design capacity of the filter, pump, and pipeline. Here it is set to 1000 NTU, representing the upper limit of the system's processing capacity. The square term in the formula is the key to the calculation, as it reflects the non-linear increase in difficulty in actual engineering. For example, if the turbidity increases from 100 NTU to 200 NTU, the difficulty does not increase by 2 times, but by 4 times. This is because at high turbidity, particulate matter will clog the filter pores more quickly, forming a filter cake, which will cause the pressure difference to rise sharply, and the cleaning frequency must be increased exponentially.
[0072] Difficulty level of particulate matter particle size: ;
[0073] in, The difficulty coefficient for particle size analysis is represented by D90, which represents the particle size distribution data provided by the online particle size analyzer. The maximum permissible D90 threshold is determined based on the filter's precision and structural strength, and is set to 150μm here. The principle behind this calculation formula is to obtain the proportion of large particles, because large particles are the main cause of filter clogging, pump impeller wear, and pipeline corrosion. The destructive potential of a 150μm particle is far greater than that of 100 10μm particles. The closer the particle size difficulty coefficient is to 1, the higher the potential physical damage risk of large particles to the hull.
[0074] Using the shortest plank principle, the maximum value of the two coefficients is selected as the final physics sub-difficulty coefficient, with the formula: kp = max(kp tur , kp psd ), where Kp represents the difficulty level of the physics sub-sub ... Represents the difficulty level of turbidity. The physical sub-difficulty coefficient, representing the particle size distribution difficulty, is a dimensionless number between 0 and 1 that comprehensively reflects the stress exerted by the water sample on the system's physical units. This value will be directly and preferentially used to control the ship's filtration function settings. For example, when Kp exceeds 0.7, the algorithm will command the filter to initiate automatic backwashing at a higher frequency; if Kp remains extremely high, it may activate the secondary backup filtration system or issue a pre-filter check alarm, thereby achieving critical protection for the equipment.
[0075] The purpose of obtaining the chemical difficulty coefficient is to assess the inhibitory effect of the water body's chemical properties on the efficiency of the core disinfection process; essentially, it determines the compatibility of the water sample with the treatment technology. The calculation of the chemical difficulty coefficient relies on data from chemical sensors, including an online UVT sensor measuring the transmittance of 254nm wavelength ultraviolet light. This value directly reflects the water's clarity; dissolved organic matter, color, and fine particles strongly absorb ultraviolet light, leading to its attenuation. Simultaneously, industrial conductivity and salinity sensors provide practical salinity values in PSU units, a core parameter for electrolytic treatment technology.
[0076] The chemical difficulty coefficient is also composed of two independent dimensions: ultraviolet transmittance difficulty coefficient and salinity difficulty coefficient. The formulas for calculating the two coefficients are as follows:
[0077] Ultraviolet transmittance difficulty level: ;
[0078] in, The UV transmittance coefficient represents the difficulty level of ultraviolet (UV) disinfection. UVT represents the UV transmittance obtained by an online UVT sensor. This formula mainly characterizes the clarity of the water. The closer the value is to 1, the greater the obstruction of UV penetration by the water, and the higher the difficulty of disinfection. When the water is perfectly clear, UVT = 100%, then kc uvt =0 indicates no difficulty. When UVT=50%, it means that half of the ultraviolet light intensity has been absorbed in the water, greatly increasing the difficulty of disinfection. uvt =0.5, if UVT is lower, the difficulty approaches 1.
[0079] Salinity difficulty level: ;
[0080] in, The value represents the salinity difficulty coefficient, min represents the function that selects the minimum value, and SAL represents the salinity value obtained by the sensor. The optimal salinity point for the technology is represented, such as 32 PSU for electrolysis. The radius representing the effective operating range is set to 10 PSU here. This formula measures how much the current salinity deviates from the ideal value. If the salinity is too low, the efficiency of the electrolytic generation of disinfectant will decrease significantly; if the salinity is too high, it may cause scaling or overcurrent in the equipment. The formula ensures that the difficulty only reaches its maximum value of 1 when the salinity deviates significantly from the optimal range.
[0081] The difficulty coefficients for obtaining ultraviolet transmittance and salinity were calculated using a weighted fusion method, taking into account the varying sensitivities of different technologies to chemical parameters. The specific formula is as follows: Where kc represents the chemical difficulty coefficient, The difficulty level of ultraviolet transmittance is represented by the coefficient of measurement. Represents the salinity difficulty level. and These are the weights of two coefficients, which are added together to equal 1. The specific value is determined by the system's technical approach. For the UV-first mode, It can be set to 0.9; for electrolysis priority mode, It can be set to 0.8. The final chemical difficulty coefficient directly guides the operation of the disinfection unit.
[0082] The primary function of the biomass difficulty coefficient is to assess the total biomass load of surviving microorganisms in ballast water, i.e., the amount of inactivation work required. It is the most direct indicator of the difficulty of the treatment task. The data comes from a cluster of deployed sensors. Among them, the online ATP monitor measures the concentration of adenosine triphosphate (ATP) using bioluminescence. Since ATP is the universal energy carrier for all living cells, its value directly and rapidly reflects the total biomass of all surviving microorganisms and is an internationally recognized activity indicator. The online fluorometer measures the concentration of chlorophyll a using induced fluorescence, an indicator that specifically reflects the abundance of phytoplankton.
[0083] The biodiversity difficulty coefficient is mainly obtained by comparing the total bioactivity difficulty coefficient and the algal concentration difficulty coefficient. The calculation formulas for the two coefficients are as follows:
[0084] Overall biological activity difficulty level: ;
[0085] in, The total bioactivity difficulty coefficient is represented by , min represents the function for selecting the minimum value, and ATP represents the real-time fluorescence intensity value measured by the online ATP monitor. The ATP value represents the maximum bioburden capacity that the system is designed to handle. The formula linearly converts real-time bioburden into a difficulty value. The higher the ATP value, the more microorganisms need to be inactivated, and the greater the required UV dose or chemical agent dose.
[0086] Algae Concentration Difficulty Level: ;
[0087] in, The difficulty coefficient represents the algae concentration; min represents the function for selecting the minimum value; and chla represents the chlorophyll a concentration value obtained by the sensor. This represents the maximum algae concentration threshold that the system is designed to handle. High algae levels are not only a biological problem, but also a physical and chemical one. Algae cells can clog filters, algal colonies can block ultraviolet light, and some algae even exhibit strong resistance to disinfectants. Therefore, high algae concentrations require special attention from the system.
[0088] The final calculation of the difficulty coefficient of the biological component also adopts the shortest board principle, and the formula is as follows: Where kb represents the difficulty coefficient of the biological sub-sub ... Represents the overall bioactivity difficulty coefficient. The biodiversity difficulty coefficient represents the difficulty level of algae concentration. This formula means that even if the total biomass is low, but algae blooms are extreme, or the total biomass is extremely high but algae are scarce, the system will respond at the highest difficulty level. The biodiversity difficulty coefficient is the final arbiter of control decisions. It directly determines the amount of disinfectant added, because inactivating a certain number of microorganisms requires a specific amount of chemical reaction. When the biodiversity difficulty coefficient exceeds a certain extremely high threshold, it means that a single treatment may not guarantee compliance. The system will automatically trigger a circulation treatment mode, returning the water to the treatment system inlet for secondary treatment to ensure success. Simultaneously, the biodiversity difficulty coefficient is also the final verification indicator for whether the final effluent water quality meets standards. If the ATP value measured at the discharge port fails to drop below the standard after treatment, the system will automatically stop discharge by triggering the valve.
[0089] S3: Obtain the sub-difficulty coefficient and combine it with dynamic weights to calculate the comprehensive processing difficulty coefficient;
[0090] Furthermore, step S3 also includes:
[0091] Based on the sub-difficulty coefficient and the set static weight, the dynamic weight is calculated using the following formula:
[0092] ;
[0093] Where i represents the index value. The dynamic weights represent the updated sub-difficulty coefficients. The basic static weights representing the original settings of the sub-difficulty coefficients. w represents the specific numerical value of the sub-difficulty level. p w c w b These are the basic static weights corresponding to the difficulty coefficients of the physics, chemistry, and biology sub-sub ...
[0094] The difficulty coefficient is calculated by comprehensively processing dynamic weights and sub-difficulty coefficients. The specific formula is as follows:
[0095] ;
[0096] Where k represents the overall processing difficulty coefficient. , , , respectively, represent the dynamic weights corresponding to the difficulty coefficients of the physics, chemistry, and biology sub-sub ...
[0097] Specifically, the calculation yields three sub-difficulty coefficients: physics, chemistry, and biology. Based on these sub-difficulty coefficients and the established static weights, the dynamic weights are calculated using the following formula:
[0098] ;
[0099] Here, 'i' represents the index value, used to distinguish the three types of sub-difficulty coefficients. The dynamic weights represent the updated sub-difficulty coefficients. The basic static weights representing the original settings of the sub-difficulty coefficients. w represents the specific numerical value of the sub-difficulty level. p w c w b Here, kp, kc, and kb represent the basic static weights corresponding to the difficulty coefficients of the physics, chemistry, and biology sub-difficulty dimensions, respectively. The physical meaning of this formula is to achieve intelligent weight allocation driven by difficulty; the higher the real-time difficulty of a certain sub-dimension, the higher its weight ratio in the final comprehensive score. The setting of the basic static weights in the formula is based on the ship's operating mode. If the ship's operating mode is electrolysis-priority mode, the preset basic static weights will be biased towards the chemical and biological dimensions, with a specific value of w. p =0.1, w c =0.5, w b =0.4, if the ship's operating mode is UV priority mode, the preset basic static weights are biased towards the chemical and physical dimensions, with a specific value of w. p =0.3, w c =0.6, w b =0.1.
[0100] The difficulty coefficient is calculated by comprehensively processing the obtained dynamic weights and sub-difficulty coefficients. The specific formula is as follows:
[0101] ;
[0102] Where k represents the overall processing difficulty coefficient. , , These represent the dynamic weights corresponding to the physical, chemical, and biological sub-difficulty coefficients, respectively, while kp, kc, and kb are the specific values of the physical, chemical, and biological sub-difficulty coefficients, respectively. The final calculated comprehensive processing difficulty coefficient serves as a global, dimensionless decision indicator used to determine the overall state of the ship's ballast water and generate coordinated optimization instructions.
[0103] S4: Generate ballast water treatment instructions based on the sub-difficulty coefficient and the overall treatment difficulty coefficient. The ballast water treatment instructions include physical treatment instructions, chemical treatment instructions, biological treatment instructions, and coordination optimization instructions.
[0104] Furthermore, step S4 also includes:
[0105] Data is processed with priority based on the physical sub-difficulty coefficient. It is then determined whether to generate a physical processing instruction. A physical safety threshold for the ship is set. When the physical sub-difficulty coefficient exceeds the physical safety threshold, the highest priority physical processing instruction is generated.
[0106] Based on the data source of the chemical difficulty coefficient, the ship's technical processing mode is determined, and chemical processing instructions are generated under the corresponding mode. The ship's technical processing modes are divided into ultraviolet priority mode and electrolysis priority mode.
[0107] Set a biosafety threshold for the ship; when the biosafety difficulty coefficient exceeds the biosafety threshold, generate a biosafety treatment command.
[0108] Based on the overall processing difficulty coefficient, query the preset control strategy table and generate coordination and optimization instructions;
[0109] Integrate physical treatment instructions, chemical treatment instructions, biological treatment instructions, and coordination optimization instructions to generate ship ballast water treatment instructions.
[0110] Specifically, the process of generating ship ballast water treatment instructions based on the overall processing difficulty coefficient and its sub-difficulty coefficients is a complex logical operation involving hierarchical decision-making and prioritization. Its core lies in first responding to the highest priority safety and compliance alerts, and then performing economic optimization within the safety boundaries.
[0111] First, the physical difficulty coefficient is prioritized for processing to determine whether to generate a physical processing command. This is because the physical difficulty coefficient reflects the operational risk of the ship's physical equipment, which is the fundamental boundary determining whether the ship can operate normally. A physical safety threshold Kp is then set for the ship. safe This threshold is not a fixed value, but needs to be determined based on the specific ship's ballast water treatment system model, the equipment manufacturer's technical specifications, and the ship's actual operating history data. Based on engineering experience, in order to reduce unnecessary maintenance and improve the ship's continuous treatment capacity, Kpsafe The value is typically set within a high range, such as 0.8. When the real-time calculated physical difficulty coefficient exceeds this threshold, it indicates that the ship's filtration system is facing an immediate risk of clogging or wear. At this point, the ship needs to immediately interrupt any optimization procedures and generate the highest priority physical treatment command. This command includes, but is not limited to: forcibly initiating the emergency backwashing procedure of the filter, ordering a reduction in the influent flow rate to reduce particulate load, or activating parallel standby filter units. The sole objective of this command is to protect the hardware and prevent system failure due to mechanical malfunction.
[0112] The generation of chemical treatment commands differs from that of physical treatment commands. Chemical commands do not require threshold-based generation; they are generated regardless of the situation, and their generation logic is strongly correlated with the ship's operating mode. The ship's technical treatment mode is determined by the source of the chemical difficulty coefficient. When the UV transmittance difficulty coefficient is significantly greater than the salinity difficulty coefficient, the source of the chemical difficulty coefficient is the UV transmittance difficulty coefficient, therefore the ship's technical treatment mode is UV priority mode; otherwise, it is electrolysis priority mode. In electrolysis priority mode, the chemical command aims to produce disinfectant efficiently and stably: the output current of the electrolysis unit is adjusted according to the chemical difficulty coefficient, which is determined by the degree of salinity deviation; the higher the chemical difficulty coefficient, the greater the current. Simultaneously, the UV unit is set to dechlorination mode, with neutralizing residual chlorine as the primary task. In UV priority mode, the chemical command fully guarantees the penetration and sterilization efficiency of ultraviolet light: the output power of the ultraviolet lamp is directly adjusted according to the chemical difficulty coefficient. At this time, the chemical difficulty coefficient is determined by UVT. The higher the chemical difficulty coefficient, the greater the power. If the chemical difficulty coefficient is extremely high, the metering pump is started to add hydrogen peroxide and start the advanced ultraviolet oxidation process to enhance the processing capacity.
[0113] Whether to generate a biological treatment command is determined based on the difficulty coefficient of the biological component, and the ship's biosafety threshold (kb) is set. safeThis threshold, similar to the physical safety threshold, can be dynamically adjusted. However, since biosafety is not equipment safety and must strictly adhere to the microbial concentration limits stipulated by the International Maritime Organization and port state control regulations, the biosafety threshold must be set at an extremely low level, even approaching zero, for example, 0.2. When the real-time calculated bioburden difficulty coefficient exceeds this threshold, it indicates that the ship's ballast water is accompanied by high algae or zooplankton concentrations, at which point the ship needs to generate a biological treatment command. High algae or zooplankton concentrations easily cause filter clogging. Therefore, the biological treatment command will also invoke the ship's filtration unit, ordering the filter to start the highest frequency backwashing mode, and may also activate additional pretreatment units, such as activating a centrifugal cyclone separator specifically for removing most large organisms. In addition, in electrolysis priority mode, upon detecting a high bioburden difficulty coefficient, the system will order the electrolysis unit to operate at the maximum allowable current to generate far more active chlorine than usual, ensuring sufficient disinfectant to cope with the large bioburden. Simultaneously, the ultraviolet unit needs to prepare for an even heavier chlorine removal task. In UV priority mode, the high bio-difficulty coefficient will command the UV lamp to directly increase its power to 100%, and it is very likely that hydrogen peroxide will be added immediately to start the most efficient but also most energy-consuming advanced UV oxidation mode, rather than ordinary UV disinfection.
[0114] The coordinated optimization command is generated by the overall processing difficulty coefficient. This coefficient is a smoothed indicator reflecting the overall system load. It doesn't directly trigger a single action, but rather queries a large "intensity-mode" control strategy table to output a coordinated intensity command. For example, when the overall processing difficulty coefficient is in the range of 0.6-0.8, the ship will generate the command: "Increase the electrolysis unit's rated current to 90%, increase the UV unit's power to 95%, and increase the backwashing frequency by 30%." The purpose of this command is to find an optimal operating intensity within the operational framework defined by physical and biological safety boundaries, matching the current overall difficulty and achieving a dynamic balance between energy consumption and treatment effectiveness.
[0115] Ultimately, all instructions are integrated into a complete control command set and issued to each actuator. It's important to note that regardless of ballast water conditions, chemical treatment and coordination optimization instructions will always be generated, while physical treatment and biological treatment instructions are determined based on thresholds. The essence of the entire decision-making process lies in its strict prioritization: if a physical treatment instruction exists, it takes priority, and the ship will implement it first. Chemical, biological, and coordination instructions are issued and implemented sequentially after the physical instruction. This allows the ship to respond decisively to extreme conditions while maintaining high efficiency and economy in daily operations.
[0116] S5: Based on the ship ballast water treatment command, perform real-time simulation prediction to obtain the estimated effluent water quality, compare the estimated effluent water quality with the water quality compliance threshold, and determine whether to generate a secondary ship ballast water treatment command.
[0117] If a secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the secondary ballast water treatment instruction.
[0118] If no secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the ballast water treatment instruction.
[0119] Furthermore, step S5 also includes:
[0120] Based on the currently generated ship ballast water treatment instructions, real-time simulation prediction is performed, and effluent water quality prediction based on microbial inactivation dynamics is executed. The specific formula is as follows:
[0121] ;
[0122] in, The effluent quality estimate is represented by kb, which represents the currently measured biological difficulty coefficient, and S represents the treatment intensity factor. For the UV-preferred mode... ,in Represents ultraviolet power, for electrolysis-preferred mode ,in Represents the electrolysis current value. Represents the maximum current value, kc represents the chemical difficulty coefficient, and the exponential decay term. Represents the microbial inactivation rate;
[0123] Set a water quality compliance threshold, compare the estimated effluent water quality with the water quality compliance threshold. If the effluent water quality meets the standard, confirm that the ship ballast water treatment command is the final command and issue it to the physical actuator. If the estimated effluent water quality does not meet the standard, immediately trigger the command dynamic adjustment cycle, automatically increase the treatment intensity and re-perform simulation calculation until the prediction result is confirmed to meet the standard. In this way, a secondary ship ballast water treatment command that has been strengthened and verified is generated and then issued.
[0124] Specifically, based on the currently generated ship ballast water treatment instructions, real-time simulation prediction is performed to predict the effluent water quality based on the biomechanics of microbial inactivation. The specific formula is as follows:
[0125] ;
[0126] in, The effluent quality estimate is represented by KB, which represents the currently measured biological difficulty coefficient. This is a quantitative representation of the total initial microbial load requiring inactivation; a higher value indicates a more challenging initial treatment task. S represents the treatment intensity factor, a key parameter for quantifying chemical and biological treatment instructions in ship ballast water treatment commands. For UV-preferred mode... ,in Represents ultraviolet power, for electrolysis-preferred mode ,in Represents the electrolysis current value. The maximum current value is represented by , which directly reflects the magnitude of the applied disinfection energy. kc represents the chemical difficulty coefficient, characterizing the inhibitory effect component of the ballast water on the treatment command. In the formula... The effective treatment efficiency factor represents the degree of ballast water suppression, which translates into the system's effective operating efficiency. A factor closer to 1 indicates 100% treatment efficiency, while a factor closer to 0 indicates significantly reduced efficiency. Represents the effective treatment intensity, which indicates the net treatment intensity actually applied to microorganisms after discounting by water quality conditions. For example, in clear seawater with high ultraviolet transmittance, When the value is close to 1, the treatment intensity is fully utilized. However, in turbid waters, this value decreases sharply, resulting in a significant reduction in treatment effectiveness, leading to an exponential decay term. The output of the entire formula represents the microbial inactivation rate. This is the estimated value of the predicted effluent water quality, which is equal to the product of the initial load and the inactivation ratio, and directly represents the expected water quality after the execution of the command.
[0127] The water quality compliance threshold is set to 0.1 kb. The estimated effluent water quality is compared with the preset water quality compliance threshold. When the value is less than 0.1kb, the effluent water quality meets the standards and discharge requirements. The ship can confirm that the ballast water treatment instruction is the final instruction and issue it to the actuator. If the estimated effluent water quality shows a risk of exceeding the standard, the instruction dynamic adjustment cycle is immediately triggered, the treatment intensity is automatically increased and the simulation calculation is re-performed until the prediction result is confirmed to meet the standard. Thus, a secondary ballast water treatment instruction that has been strengthened and verified is generated and then issued.
[0128] Specifically, assuming the effective treatment intensity in the formula... The value is 0, at which point the microbial inactivation rate is 0. The value is 1. This indicates that the ballast water was completely untreated, and its quality is the same as untreated water. Therefore, it cannot be discharged in compliance with regulations and a secondary ballast water treatment order needs to be generated for further calculation and judgment. If the effective treatment intensity... The value is 3, at which point the microbial inactivation rate is 3. The value is approximately 0.05. This indicates that 95% of the microorganisms have been killed, the ballast water meets the standards, and the ship's ballast water treatment order is issued as the final order. And when... When the value is very large, the microbial inactivation rate When the value is infinitely close to 0, it indicates that the ballast water quality has reached the highest level, and the ship ballast water treatment instruction is also issued as the final instruction.
[0129] S6: Based on the treated ballast water, recalculate the sub-difficulty coefficient, compare the biological sub-difficulty coefficient with the biosafety threshold. If the biological sub-difficulty coefficient is lower than the compliance threshold, discharge is authorized; otherwise, iterative processing is performed until the biological sub-difficulty coefficient meets the standard.
[0130] Specifically, after executing a ballast water treatment order or a secondary ballast water treatment order, the ship's system does not immediately discharge ballast water. Instead, it initiates a rigorous final compliance verification closed loop. First, the sensor cluster performs real-time data acquisition again to obtain the physical, chemical, and biological parameters of the treated water sample. After preprocessing, a new multi-source parameter dataset is constructed. Based on this dataset, the current sub-difficulty coefficients are calculated, including physical, chemical, and biological sub-difficulty coefficients.
[0131] The core basis for the final discharge decision is the biological difficulty coefficient, which is directly compared with the legally mandated discharge compliance threshold. If the biological difficulty coefficient is lower than the biosafety threshold, the water quality is deemed compliant, and the discharge valve is authorized for discharge. If the biological difficulty coefficient is still higher than the biosafety threshold, it indicates that the treatment has failed to achieve the expected results, and a new round of optimization treatment cycle is automatically triggered. In this cycle, the ship system will run the dynamic weighted fusion decision algorithm again based on the latest measured sub-difficulty coefficients to calculate a new comprehensive treatment difficulty coefficient, and generate a new round of intensity-optimized ship ballast water treatment instructions. Next, the estimated effluent water quality is predicted based on the ship ballast water treatment instructions, and the determination of whether to generate a second ship ballast water treatment instruction is made based on the effluent water quality estimate, and the ship system is adjusted again. This iterative process will continue until the final collected and calculated biological difficulty coefficient confirms that it meets all regulatory requirements and is within the biosafety threshold range, only then will the ship system execute the discharge operation, thus forming a closed-loop adaptive intelligent treatment process that ensures absolute compliance.
[0132] Example 2: Based on the same inventive concept as the ship ballast water treatment method in the foregoing examples, this application also provides a ship ballast water treatment system. Please refer to the appendix. Figure 2 The system includes:
[0133] The multi-source sensing module 11 is used to deploy a sensor cluster on the key pipeline of ship ballast water, acquire raw ballast water indicators in real time, preprocess the raw ballast water indicators, and construct a multi-source parameter dataset, which includes physical parameters, chemical parameters, and biological parameters.
[0134] The sub-difficulty coefficient hierarchical calculation module 12 is used to calculate the sub-difficulty coefficient hierarchically based on a multi-source parameter dataset. The sub-difficulty coefficient includes physical sub-difficulty coefficient, chemical sub-difficulty coefficient, and biological sub-difficulty coefficient.
[0135] The comprehensive processing difficulty coefficient acquisition module 13 is used to acquire sub-difficulty coefficients and calculate the comprehensive processing difficulty coefficient in combination with dynamic weights.
[0136] The instruction generation module 14 is used to generate ship ballast water treatment instructions based on the sub-difficulty coefficient and the comprehensive processing difficulty coefficient. The ship ballast water treatment instructions include physical treatment instructions, chemical treatment instructions, biological treatment instructions and coordinated optimization instructions.
[0137] The predictive optimization module 15 is used to perform real-time simulation prediction based on the ship ballast water treatment command, obtain the estimated effluent water quality, compare the estimated effluent water quality with the water quality compliance threshold, and determine whether to generate a secondary ship ballast water treatment command.
[0138] If a secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the secondary ballast water treatment instruction.
[0139] If no secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the ballast water treatment instruction.
[0140] The final compliance decision module 16 is used to recalculate the sub-difficulty coefficient based on the treated ballast water, compare the biological sub-difficulty coefficient with the biosafety threshold, and authorize discharge if the biological sub-difficulty coefficient is lower than the compliance threshold; otherwise, iterative processing is performed until the biological sub-difficulty coefficient meets the standard.
[0141] Based on the same inventive concept, an electronic device is also provided in the embodiment, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the storage medium via the bus. When the machine-readable instructions are executed by the processor, they can perform the operations described above. Figure 1 The steps of the ship ballast water treatment method in the illustrated method embodiment can be found in the method embodiment for specific implementation, and will not be repeated here.
[0142] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0143] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for treating ship ballast water, characterized in that, The method includes: A sensor cluster is deployed in the key ballast water pipeline of the ship to acquire raw ballast water indicators in real time. The raw ballast water indicators are preprocessed to construct a multi-source parameter dataset, which includes physical parameters, chemical parameters, and biological parameters. The sub-difficulty coefficients are calculated hierarchically based on multi-source parameter datasets, and the sub-difficulty coefficients include physical sub-difficulty coefficients, chemical sub-difficulty coefficients, and biological sub-difficulty coefficients. The sub-difficulty coefficients are obtained, and a comprehensive processing difficulty coefficient is calculated by combining them with dynamic weights. This includes: Based on the sub-difficulty coefficient and the set static weight, the dynamic weight is calculated using the following formula: ； Where i represents the index value. The dynamic weights represent the updated sub-difficulty coefficients. The basic static weights representing the original settings of the sub-difficulty coefficients. w represents the specific numerical value of the sub-difficulty level. p w c w b These are the basic static weights corresponding to the difficulty coefficients of the physics, chemistry, and biology sub-sub ... The difficulty coefficient is calculated by comprehensively processing dynamic weights and sub-difficulty coefficients. The specific formula is as follows: ； Where k represents the overall processing difficulty coefficient. , , , respectively represent the dynamic weights corresponding to the difficulty coefficients of the physics, chemistry, and biology sub-sub ... Ship ballast water treatment instructions are generated based on sub-difficulty coefficients and comprehensive treatment difficulty coefficients. These instructions include physical treatment instructions, chemical treatment instructions, biological treatment instructions, and coordinated optimization instructions. Based on real-time simulation prediction of ship ballast water treatment instructions, an estimated effluent water quality is obtained. This estimated effluent water quality is compared with water quality compliance thresholds to determine whether a secondary ship ballast water treatment instruction should be generated. This includes: Based on the currently generated ship ballast water treatment instructions, real-time simulation prediction is performed, and effluent water quality prediction based on microbial inactivation dynamics is executed. The specific formula is as follows: ； in, The effluent quality estimate is represented by kb, which represents the currently measured biological difficulty coefficient, and S represents the treatment intensity factor. For the UV-preferred mode... ,in Represents ultraviolet power, for electrolysis-preferred mode ,in Represents the electrolysis current value. Represents the maximum current value, kc represents the chemical difficulty coefficient, and the exponential decay term. Represents the microbial inactivation rate; Set a water quality compliance threshold, compare the estimated effluent water quality with the water quality compliance threshold. If the effluent water quality meets the standard, confirm that the ship ballast water treatment command is the final command and issue it to the physical actuator. If the estimated effluent water quality does not meet the standard, immediately trigger the command dynamic adjustment cycle, automatically increase the treatment intensity and re-perform simulation calculation until the prediction result is confirmed to meet the standard. In this way, a secondary ship ballast water treatment command that has been strengthened and verified is generated and then issued. If a secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the secondary ballast water treatment instruction. If no secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the ballast water treatment instruction. Based on the treated ballast water, the sub-difficulty coefficient is recalculated and compared with the biological sub-difficulty coefficient and the biosafety threshold. If the biological sub-difficulty coefficient is lower than the compliance threshold, discharge is authorized; otherwise, iterative processing is carried out until the biological sub-difficulty coefficient meets the standard.
2. The ship ballast water treatment method as described in claim 1, characterized in that, Construct a multi-source parameter dataset, including: Select key ballast water pipelines for ships, install sensor clusters, and collect raw ballast water indicators. The key ballast water pipelines include inlet monitoring pipelines and outlet verification pipelines. The sensor clusters include physical indicator sensors, chemical indicator sensors, and biological indicator sensors. The raw indicators of ballast water are pretreated to obtain physical, chemical and biological parameters. The three types of parameters are integrated to construct a multi-source parameter dataset. The pretreatment includes data transformation, validity verification, data smoothing and time alignment. The physical parameters include turbidity and particulate matter size distribution. The chemical parameters include ultraviolet transmittance and salinity. The biological parameters include real-time fluorescence intensity and chlorophyll a concentration.
3. The ship ballast water treatment method as described in claim 1, characterized in that, The sub-difficulty coefficient is calculated hierarchically based on a multi-source parameter dataset, including: The turbidity difficulty coefficient and particulate matter size difficulty coefficient are calculated based on the physical parameters in the multi-source parameter dataset. The specific formula for calculating the turbidity difficulty coefficient is as follows: ； in, The turbidity difficulty coefficient is represented by 'min', which represents the function that selects the minimum value, and 'TUR' represents the turbidity value. This represents the maximum turbidity design threshold; The specific formula for calculating the particle size difficulty coefficient is as follows: ； in, D90 represents the particle size distribution, while D90 represents the particle size distribution. This represents the preset maximum allowed D90 threshold. Using the shortest board principle, the maximum value between the turbidity difficulty coefficient and the particulate matter size difficulty coefficient is selected as the physical sub-difficulty coefficient. The difficulty coefficients for calculating ultraviolet transmittance and salinity are derived from chemical parameters in a multi-source parameter dataset. The specific formula for calculating the ultraviolet transmittance difficulty coefficient is as follows: ； in, The difficulty coefficient represents ultraviolet transmittance, while UVT represents ultraviolet transmittance. The specific formula for calculating the salinity difficulty coefficient is as follows: ； in, The value represents the salinity difficulty coefficient, min represents the function that selects the minimum value, and SAL represents the salinity value. This represents the optimal salinity point for the technology. The radius representing the effective operating range; The weighted fusion method is used to calculate the chemical component difficulty coefficient. The specific formula is as follows: Where kc represents the chemical difficulty coefficient, The difficulty level of ultraviolet transmittance is represented by the coefficient of measurement. Represents the salinity difficulty level. and These are the weights of the two coefficients; The difficulty coefficients for calculating total bioactivity and algal concentration are derived from biological parameters in a multi-source parameter dataset. The specific formula for calculating the total bioactivity difficulty coefficient is as follows: ； in, The total biological activity difficulty coefficient is represented by _min_, which represents the function for selecting the minimum value, and ATP represents the real-time fluorescence intensity value. Represents maximum bioburden capacity; The specific formula for calculating the difficulty coefficient of algae concentration is as follows: ； in, The difficulty coefficient represents the algae concentration; min represents the function that selects the minimum value; chla represents the chlorophyll a concentration value. This represents the maximum algal concentration threshold; Using the shortest board principle, the maximum value between the total biological activity difficulty coefficient and the algal concentration difficulty coefficient is selected as the biological sub-difficulty coefficient.
4. The ship ballast water treatment method as described in claim 1, characterized in that, Based on the sub-difficulty coefficient and the overall processing difficulty coefficient, a ship ballast water treatment instruction is generated, including: Data is processed with priority based on the physical sub-difficulty coefficient. It is then determined whether to generate a physical processing instruction. A physical safety threshold for the ship is set. When the physical sub-difficulty coefficient exceeds the physical safety threshold, the highest priority physical processing instruction is generated. Based on the data source of the chemical difficulty coefficient, the ship's technical processing mode is determined, and chemical processing instructions are generated under the corresponding mode. The ship's technical processing modes are divided into ultraviolet priority mode and electrolysis priority mode. Set a biosafety threshold for the ship; when the biosafety difficulty coefficient exceeds the biosafety threshold, generate a biosafety treatment command. Based on the overall processing difficulty coefficient, query the preset control strategy table and generate coordination and optimization instructions; Integrate physical treatment instructions, chemical treatment instructions, biological treatment instructions, and coordination optimization instructions to generate ship ballast water treatment instructions.
5. A ship ballast water treatment system, characterized in that, The system is used to implement the ship ballast water treatment method according to any one of claims 1-4, the system comprising: A multi-source sensing module is used to deploy a sensor cluster on the key ballast water pipeline of a ship to acquire raw ballast water indicators in real time, preprocess the raw ballast water indicators, and construct a multi-source parameter dataset, which includes physical parameters, chemical parameters, and biological parameters. The sub-difficulty coefficient hierarchical calculation module is used to calculate the sub-difficulty coefficient hierarchically based on a multi-source parameter dataset. The sub-difficulty coefficients include physical sub-difficulty coefficients, chemical sub-difficulty coefficients, and biological sub-difficulty coefficients. A comprehensive processing difficulty coefficient acquisition module is used to acquire sub-difficulty coefficients and calculate the comprehensive processing difficulty coefficient in combination with dynamic weights. The instruction generation module is used to generate ship ballast water treatment instructions based on the sub-difficulty coefficient and the comprehensive processing difficulty coefficient. The ship ballast water treatment instructions include physical treatment instructions, chemical treatment instructions, biological treatment instructions and coordinated optimization instructions. The predictive optimization module is used to perform real-time simulation prediction based on the ship ballast water treatment command, obtain the estimated effluent water quality, compare the estimated effluent water quality with the water quality compliance threshold, and determine whether to generate a secondary ship ballast water treatment command. If a secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the secondary ballast water treatment instruction. If no secondary ballast water treatment instruction is generated, the ship will treat the ballast water according to the ballast water treatment instruction. The final compliance decision module is used to recalculate the sub-difficulty coefficient based on the treated ballast water, compare the biological sub-difficulty coefficient with the biosafety threshold, and authorize discharge if the biological sub-difficulty coefficient is lower than the compliance threshold; otherwise, iterative processing is performed until the biological sub-difficulty coefficient meets the standard.
6. An electronic device, characterized in that, include: The device includes a processor, a storage medium, and a bus, wherein the storage medium stores machine-readable instructions executable by the processor, and when the electronic device is in operation, the processor communicates with the storage medium via the bus, and the processor executes the machine-readable instructions to perform the steps of the ship ballast water treatment method as described in any one of claims 1 to 4.