Intelligent control method and system for marine ultraviolet disinfection device

Abstract

The application discloses a marine ultraviolet disinfection device intelligent control method and system, relates to the technical field of marine disinfection, and comprises the following steps: performing ship environment information collection, establishing an environment state vector including a ship-in and ship-out environment state vector; performing modular modeling on a cabin, calling the environment state vector to calculate a cabin risk factor, and constructing an initial task queue; acquiring the importance level and personnel activity data of the cabin, performing priority compensation on the initial task queue according to the importance level and personnel activity data, and generating a corrected task queue; performing load state identification of power equipment in the ship, establishing task constraints according to the identification result and the schedulable power capacity; performing start control optimization of the ultraviolet disinfection device according to the corrected task queue and the task constraints, and implementing ship cabin disinfection management based on the optimization result. In this way, the technical effects of environment perception precision, task queue optimization and disinfection efficiency improvement are achieved.

Description

Technical Field

[0001] This invention relates to the field of marine disinfection technology, and in particular to an intelligent control method and system for marine ultraviolet disinfection devices. Background Technology

[0002] Current ship disinfection management technologies suffer from insufficient and unsystematic collection of ship environmental information. They typically only monitor basic environmental parameters such as temperature and humidity, neglecting crucial information like harmful gas concentrations and the status of the previous disinfection round. Furthermore, external environmental factors such as ship positioning and weather information are rarely considered. This makes it impossible to accurately construct a complete state vector of the ship's internal and external environments, thus affecting a comprehensive assessment of the ship's environmental condition. Simultaneously, the impact of cabin importance levels and personnel activity data on disinfection task priority is not adequately considered. The initial task queue cannot be reasonably prioritized based on actual conditions, potentially leading to a disinfection task execution order that does not meet the ship's actual operational needs, impacting the efficiency and quality of overall ship cabin disinfection management. Summary of the Invention

[0003] This invention provides an intelligent control method and system for marine ultraviolet disinfection devices to solve the technical problems of incomplete environmental perception and inaccurate task queues in the prior art, which affect disinfection efficiency, and to achieve the technical effects of more precise environmental perception, optimized task queues, and improved disinfection efficiency.

[0004] In a first aspect, the present invention provides an intelligent control method for a marine ultraviolet disinfection device, wherein the intelligent control method for the marine ultraviolet disinfection device includes:

[0005] The system collects environmental information about the ship and establishes an environmental state vector, which includes an internal environmental state vector and an external environmental state vector.

[0006] After modularly modeling the cabin, the environmental state vector is called, and the cabin risk factor is calculated based on the modular modeling results. The initial task queue is then constructed using the cabin risk factor.

[0007] Acquire the importance level of the compartment and personnel activity data, and perform priority compensation of the initial task queue based on the importance level and personnel activity data to generate a correction task queue.

[0008] Perform load status identification of the ship's electrical equipment, and establish task constraints based on the load status identification results and dispatchable power capacity.

[0009] The startup control optimization of the ultraviolet disinfection device is performed based on the correction task queue and the task constraints, and the disinfection management of the ship's cabins is carried out based on the startup control optimization results.

[0010] In one feasible implementation, the process of collecting environmental information from the vessel and establishing an environmental state vector includes:

[0011] Obtain the ship's location, perform port correlation analysis based on the ship's location, and establish port correlation environmental data.

[0012] Based on the ship's positioning, external meteorological information is read to establish meteorological environment data.

[0013] Activate the sensor array inside the cabin to collect environmental data and establish an environmental dataset. The environmental dataset includes temperature data, humidity data, carbon dioxide concentration, organic pollutant concentration, and cabin status after the previous round of disinfection.

[0014] An external environmental state vector is established using the port-related environmental data and meteorological environmental data, and an internal environmental state vector is established using the environmental dataset.

[0015] In one feasible implementation, after modularly modeling the compartment, the environmental state vector is invoked, and the compartment risk factor is calculated based on the modular modeling results, including:

[0016] Based on the modular modeling results, the connectivity features of the cabin structure and the associated features of the ventilation system are extracted to establish a graph structure.

[0017] The graph structure is used to perform inter-cabin interaction clustering, and the inter-cabin interaction clustering results are established.

[0018] Based on the environmental state vector, an independent risk calculation is performed for each compartment, and an independent risk calculation result is established.

[0019] Based on the clustering results of mutual influence, risk impact compensation is performed on the independent risk calculation results to generate cabin risk factors.

[0020] In one feasible implementation, the step of prioritizing the initial task queue based on the importance level and the personnel activity data to generate a corrected task queue includes:

[0021] The activity logs of the personnel activity data are extracted to establish predicted activity trajectories.

[0022] Based on the predicted activity trajectory, perform temporal adaptation analysis on each task in the initial task queue to establish task temporal adaptation fitness.

[0023] Perform functional analysis on the compartments and construct an importance level based on the results of the functional analysis.

[0024] The initial task queue is compensated for priority using the task timing adaptation fitness and importance level to generate a corrected task queue.

[0025] In one feasible implementation, the step of optimizing the start-up control of the ultraviolet disinfection device based on the correction task queue and the task constraints, and using the optimization result to manage the disinfection of ship cabins, includes:

[0026] After configuring the parameter control space, an initial solution is established.

[0027] An evaluation objective function is established, and the evaluation features in the evaluation objective function include maximum power load characteristics, equipment conflict penalty characteristics, average delay characteristics of critical compartments, and overall disinfection quality characteristics.

[0028] Based on the objective function, the initial solution, and the task constraints, perform iterative optimization of the startup control to establish the startup control optimization result.

[0029] In one feasible implementation, the step of performing iterative optimization of startup control based on the objective function, the initial solution, and the task constraints, and establishing the startup control optimization result, includes:

[0030] Establish time disturbances, task replacement disturbances, start / stop switching disturbances, and equipment adjustment disturbances.

[0031] In each round of iterative optimization, historical perturbation data is called, and the change value of the objective function under the corresponding perturbation feature is calculated based on the historical perturbation data. The perturbation weight list is then reconstructed based on the change value of the objective function.

[0032] The random selection factors for time disturbance, task replacement disturbance, start-stop switching disturbance, and equipment adjustment disturbance are configured using the disturbance weight list to perform startup control iterative optimization.

[0033] In one feasible implementation, the step of calculating the change value of the objective function under the corresponding perturbation feature based on the perturbation historical data, and reconstructing the perturbation weight list based on the change value of the objective function, includes:

[0034] Obtain the time sequence identifier of historical disturbance data.

[0035] After establishing the mapping between the time sequence identifier and the change value, configure the key points of the iterative optimization stage.

[0036] The time-weighted calculation of the perturbation criticality is performed by using the mapping between the time sequence identifier and the change value, and the time-weighted calculation result is generated.

[0037] After compensating for the time-weighted calculation results based on the key points of the aforementioned stages, the disturbance weight list is reconstructed.

[0038] In one feasible implementation, the disinfection management of ship cabins based on the optimization results of the initiation control includes:

[0039] Configure the cabin disinfection parameters for the ship's cabins based on the optimization results of the startup control.

[0040] Using the disinfection parameters of the cabin as a reference parameter, adaptive zonal control decisions are made within the cabin.

[0041] Disinfection management of ship cabins is carried out based on the results of adaptive zone control decisions.

[0042] In one feasible implementation, the disinfection management of ship cabins based on adaptive zone control decision results includes:

[0043] The disinfection test standards are mapped according to the disinfection parameters of the cabin.

[0044] The aforementioned mapping disinfection inspection standards are used to test and verify the cabins, and test and verification feedback is generated.

[0045] Based on the detection and verification feedback, a correction compensation is generated, and the correction compensation is used to optimize the adaptive region control decision results.

[0046] Secondly, the present invention also provides an intelligent control system for a marine ultraviolet disinfection device, wherein the intelligent control system for the marine ultraviolet disinfection device includes:

[0047] The environmental state vectorization module is used to collect environmental information of the ship and establish environmental state vectors, which include internal environmental state vectors and external environmental state vectors.

[0048] The risk factor calculation module is used to perform modular modeling of the cabin, call the environmental state vector, calculate the cabin risk factor based on the modular modeling result, and construct the initial task queue with the cabin risk factor.

[0049] The priority compensation module is used to acquire the importance level of the compartment and personnel activity data, and to perform priority compensation of the initial task queue based on the importance level and personnel activity data to generate a corrected task queue.

[0050] The task constraint module is used to perform load status identification of the ship's electrical equipment and establish task constraints based on the load status identification results and the dispatchable power capacity.

[0051] The disinfection execution and management module is used to optimize the start-up control of the ultraviolet disinfection device based on the calibration task queue and the task constraints, and to manage the disinfection of the ship's cabins based on the start-up control optimization results.

[0052] This invention discloses an intelligent control method and system for marine ultraviolet disinfection devices, comprising: collecting multi-source information about the ship's environment to construct an environmental state vector containing characteristics of both the ship's internal and external environments; performing modular modeling of the ship's compartments and, based on the environmental state vector, assessing the environmental risk level of each compartment based on the modeling results, thereby generating an initial task queue; acquiring the importance level and personnel activity-related data corresponding to each compartment, dynamically adjusting the task priority of the initial task queue based on the above data, and constructing a corrected task queue; identifying the current load status of the ship's internal electrical equipment and, based on the identified load status and available power capacity, constructing a resource constraint model for disinfection task execution; optimizing the start-stop control strategy for the ultraviolet disinfection device according to the corrected task queue and resource constraint model, and scheduling and executing compartment disinfection tasks based on the optimization results. The intelligent control method and system for marine ultraviolet disinfection devices disclosed in this invention solves the technical problems of incomplete environmental perception and inaccurate task queues affecting disinfection efficiency, achieving the technical effects of precise environmental perception, optimized task queues, and improved disinfection efficiency. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating the intelligent control method for the marine ultraviolet disinfection device of the present invention.

[0054] Figure 2 This is a schematic diagram of the intelligent control system of the marine ultraviolet disinfection device of the present invention.

[0055] Figure labeling: Environmental state vectorization module 11, risk factor calculation module 12, priority compensation module 13, task constraint module 14, disinfection execution and management module 15. Detailed Implementation

[0056] The above technical solutions will now be described in detail with reference to the accompanying drawings and specific embodiments to provide a better understanding of them. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be understood that the present invention is not limited to the exemplary embodiments used only to explain the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention. Furthermore, it should be noted that, for ease of description, only the parts related to the present invention are shown in the drawings, not all of them.

[0057] Example 1, as Figure 1 This is a flowchart illustrating the intelligent control method for a marine ultraviolet disinfection device according to the present invention, wherein the intelligent control method for the marine ultraviolet disinfection device includes:

[0058] S100: Perform environmental information collection for the ship and establish an environmental state vector, which includes an internal environmental state vector and an external environmental state vector.

[0059] Specifically, the environmental information of the target vessel's environment is first determined, and the collected environmental information is vectorized to obtain a structured representation of the environmental state vector, thereby improving the representation level of the environmental information and facilitating subsequent retrieval and analysis.

[0060] Specifically, environmental information collection refers to the collection of relevant data on the ship's internal and external environment through various sensors and data acquisition methods. Examples include cabin environmental data such as internal temperature, humidity, harmful gas concentration, and previous disinfection status, as well as external environmental data such as ship positioning and meteorological information. Environmental state vectors are used to integrate and represent the collected multi-dimensional environmental information in vector form. The internal environmental state vector describes the characteristics of the ship's internal cabin environment, while the external environmental state vector focuses on depicting the external environmental conditions in which the ship is located.

[0061] By collecting environmental information from ships and establishing environmental state vectors, precise environmental perception can be achieved. Compared with traditional disinfection management technologies, this method not only collects basic environmental parameters inside the ship but also fully considers the ship's positioning and meteorological information outside the ship, making the assessment of the ship's environmental condition more comprehensive, detailed, and accurate.

[0062] In some embodiments, the process of collecting environmental information from the ship and establishing an environmental state vector includes:

[0063] The system acquires the ship's location and performs port-related analysis based on the ship's location to establish port-related environmental data. It also reads external meteorological information based on the ship's location to establish meteorological environmental data. The system activates the sensor group inside the cabin to collect environmental data from the cabin and establishes an environmental dataset, which includes temperature data, humidity data, carbon dioxide concentration, organic matter pollution concentration, and cabin status after disinfection on the previous vessel. The system uses the port-related environmental data and meteorological environmental data to establish an external environmental state vector and uses the environmental dataset to establish an internal environmental state vector.

[0064] Specifically, port-related environmental data refers to environmental parameters related to the ship's current berthing or proximity to the port, obtained based on the ship's current location information and combined with historical or real-time port environmental databases. These parameters include port air quality, epidemic information, and port pollutant emission levels. Meteorological environmental data consists of meteorological parameters obtained in real-time from weather stations or sensors based on the ship's location, such as temperature, humidity, wind speed, and wind direction. Environmental datasets refer to a collection of multiple data points reflecting the cabin environment, collected by sensor arrays within the ship's cabins. These include temperature, humidity, carbon dioxide concentration, organic pollutant concentration, and cabin conditions after the last disinfection.

[0065] Specifically, firstly, the system acquires the ship's current geographical location information, such as latitude and longitude, through a GNSS system. Then, based on the ship's location, it retrieves and analyzes environmental databases related to the current port (such as API-based online databases) to obtain parameters such as port air quality, epidemic information, and pollutant emissions, establishing port-related environmental data. Simultaneously, based on the location information, the interactive meteorological service platform reads real-time meteorological data of the ship's location, including temperature, humidity, wind speed, and air pressure, forming meteorological environmental data.

[0066] Next, the sensor groups in each cabin are activated to collect environmental parameters such as temperature, humidity, carbon dioxide concentration, and organic pollution concentration. Based on the disinfection records, the microorganisms and disinfectant residues after the previous round of disinfection are extracted. After correlation, the data is output as an environmental dataset.

[0067] Furthermore, a multidimensional data space is constructed using multiple data dimensions of port-related environmental data and meteorological environmental data as multidimensional coordinate axes. The port-related environmental data and meteorological environmental data are then mapped to this multidimensional data space to form an external environmental state vector. Simultaneously, another multidimensional data space is established using multiple data dimensions of the environmental dataset as another set of multidimensional coordinate axes. Spatial mapping of the environmental dataset is then performed, and the mapping result is output as an internal environmental state vector.

[0068] Through the above process, it is possible to achieve multi-dimensional and dynamic perception and quantitative expression of the ship's environment, providing comprehensive and real-time data support for the intelligent control of ultraviolet disinfection devices, making the disinfection process more scientific and precise, and effectively improving the level of ship environmental safety and hygiene management.

[0069] S200: After modularly modeling the compartment, call the environmental state vector, calculate the compartment risk factor based on the modular modeling results, and construct the initial task queue with the compartment risk factor.

[0070] Optionally, the ship's compartments can be modularized according to factors such as structure, function, and ventilation, and the structural connectivity and ventilation system correlation between compartments can be modeled using mathematical or graph theory methods. The compartment risk factor is a scalar indicator that quantifies the current environmental risk level of each compartment based on multi-dimensional data such as compartment structure, environmental conditions, and inter-compartmental interactions. The initial task queue is a preliminary disinfection task execution sequence arranged according to the order of the compartment risk factors, providing a basis for subsequent priority adjustments to disinfection tasks.

[0071] This step, through scientific modeling and risk assessment, ensures that disinfection tasks can be prioritized for high-risk cabins, initially achieving a reasonable allocation of disinfection resources and laying the foundation for further optimization of the task queue.

[0072] In some embodiments, after modularly modeling the cabin, calling the environmental state vector and calculating the cabin risk factor based on the modular modeling results includes:

[0073] Based on the modular modeling results, the connectivity features of the cabin structure and the correlation features of the ventilation system are extracted to establish a graph structure; the mutual influence clustering of the cabins is performed using the graph structure to establish mutual influence clustering results; the independent risk calculation of each cabin is performed based on the environmental state vector to establish independent risk calculation results; the risk impact compensation of the independent risk calculation results is performed based on the mutual influence clustering results to generate cabin risk factors.

[0074] Specifically, the connectivity characteristics of the compartment structure refer to the physical connections between compartments, such as the connection methods of doors and passageways, which determine the flow path of personnel or air between compartments. The connectivity characteristics of the ventilation system refer to the connection relationship between ventilation ducts in different compartments, affecting air exchange and pollutant transmission between compartments.

[0075] Specifically, firstly, modular modeling is performed on each compartment of the ship. Based on the modular modeling results, structural connectivity features (such as doors, passageways, and adjacency relationships) and ventilation system association features (such as air ducts, air exchange vents, and fan distribution) of each compartment are extracted. A compartment graph structure is then established in the form of nodes and edges. Nodes correspond to multiple compartment modules and key locations of multiple ventilation systems, while edges represent the connection relationships between different compartments and ventilation system locations. Preferably, the edges in the graph structure are labeled with weights to represent the direction, attributes, or performance of connectivity.

[0076] Then, graph clustering algorithms (such as community detection algorithms) are used to cluster the nodes (cabins) in the graph structure based on their mutual influence, grouping those cabins that are structurally closely connected or interconnected by the ventilation system into the same category. For example, in the crew living area module, by analyzing connectivity and ventilation correlation, the cabins, corridors, and public bathrooms are clustered into a subclass with greater mutual influence.

[0077] Then, based on the data in the environmental state vector, such as the concentration of harmful gases in each cabin (assuming that exceeding the harmful gas concentration standard would increase the disinfection risk), an independent risk calculation is performed for each cabin. For example, if the concentration of harmful gases in a cabin reaches 120% of the threshold, its independent risk is initially calculated as "high". The independent risk calculation is based on a preset mathematical model or calculation rules.

[0078] Finally, the independent risks are compensated and adjusted based on the clustering results of mutual influence. For example, for the cabin, corridor, and public bathroom clustered together, since there may be risk propagation between them, if the independent risk of the public bathroom is "medium" and that of the corridor is "low", the independent risk calculation result of the cabin can be compensated according to the risk propagation weight within the cluster (e.g., setting the risk propagation weight of the public bathroom to the cabin to 0.3 and that of the corridor to 0.2).

[0079] Through the above process, the coupling effect of the structural connectivity of the compartments and the ventilation system can be fully considered, enabling dynamic and refined assessment of the risks of each compartment. This provides a scientific basis for the zonal control strategy of the ultraviolet disinfection device, thereby improving the pertinence and effectiveness of disinfection work and reducing safety hazards in the ship's internal environment.

[0080] S300: Obtain the importance level of the compartment and personnel activity data, and perform priority compensation of the initial task queue based on the importance level and personnel activity data to generate a correction task queue.

[0081] Specifically, the importance level of a compartment refers to the result of classifying each compartment based on pre-defined assessment dimensions such as functional positioning, system criticality, and safety level. For example, control compartments and life support compartments usually have higher levels. Personnel activity data includes the distribution density of personnel in the compartment, their stay time, and their behavioral status (such as resting, operating, and moving).

[0082] Specifically, based on the actual cabin level and personnel status, task priorities can be adjusted and optimized, i.e., priority compensation. The task list that has completed compensation sorting is the corrected task queue, which serves as the basis for subsequent task scheduling or dispatch. For example, if the initial task queue includes a ventilation equipment maintenance task, the area of ​​operation of which is the control cabin, and there are currently two operators in the control cabin working continuously, then the priority of this task can be raised to the top of the queue to ensure the stable operation of the ventilation system and personnel safety.

[0083] By performing the above steps, the initial tasks generated by static rules can be integrated with dynamic cabin status and human factors data, effectively compensating for the shortcomings of traditional scheduling that ignores the actual operational context, enhancing the support capabilities of key areas, and improving overall safety and mission completion quality.

[0084] In some embodiments, the step of prioritizing the initial task queue based on the importance level and the personnel activity data to generate a corrected task queue includes:

[0085] The activity data of the personnel is used to extract activity logs and establish predicted activity trajectories; based on the predicted activity trajectories, the temporal adaptation analysis of each task in the initial task queue is performed to establish task temporal adaptation fitness; the execution functions of the cabins are analyzed, and the importance level is constructed based on the execution function analysis results; the priority compensation of the initial task queue is performed using the task temporal adaptation fitness and importance level to generate a corrected task queue.

[0086] Specifically, activity logs refer to time-space sequence data extracted from raw personnel activity records obtained from sensors, cameras, or wearable devices to reflect the behavioral paths of personnel within the cabin; predicted activity trajectories are based on historical behavioral sequences and combined with short-term trend modeling (such as sliding windows and time series networks) to infer the movement and behavioral trends of personnel over a future period of time.

[0087] Specifically, task timing adaptation is used to reflect the degree of matching between the expected execution time window of a task and the future behavioral trajectory of personnel, that is, to measure the degree of execution interference and time coordination.

[0088] Specifically, the execution function analysis is the classification of the importance of a cabin based on its functional settings, equipment type, and key business roles.

[0089] Specifically, firstly, by reading sensor network records (such as access control, location tags, and operation action recognition), the activity log for the current period is extracted, including timestamps, cabin locations, and behavior tags. Then, time series analysis algorithms and machine learning models, such as Markov chain models, are used to predict the cabin where personnel may move next, or Long Short-Term Memory (LSTM) networks in deep learning are used to predict personnel activity trajectories, thus establishing predicted activity trajectories for a future period (such as the next 24 hours).

[0090] Specifically, for each initial task, the analysis examines whether the spatial location (i.e., the compartment) upon which the task execution depends conflicts with or complements the personnel's predicted trajectory, and assigns a temporal fit fitness score based on the degree of fit. For example, if the compartment will be in a period of high-density activity during the task execution, it is assessed as low fit; if the task happens to occur during the compartment's idle period or is synchronized with personnel behavior (such as assisting in operations), it is assessed as high fit.

[0091] Furthermore, the functions of each compartment are analyzed by reviewing the ship's design documents and operations manual to clarify their roles. For example, key areas such as the command center and communications room are identified as compartments performing special functions, which play a crucial role in the safe operation of the ship. Then, based on the importance of the function and its impact on personnel health and safety, a functional characteristic vector for each compartment (such as the key equipment it contains, system independence, and business influence) is obtained, and a corresponding importance level is calculated.

[0092] Furthermore, by combining the task timing adaptation adaptability with the cabin importance level, a compensation value is calculated through a weighted model to adjust the initial task priority, and finally a corrected task queue is generated, so that tasks with high adaptability and high importance are executed first.

[0093] For example, at a certain moment, the cockpit (high importance) predicts frequent personnel activity within the next 10 minutes, while the medical pod (high importance) predicts no activity within the next 30 minutes. The initial task queue is [cockpit, medical pod]. After time-series adaptation analysis, the medical pod has a higher fitness rate than the cockpit; therefore, the task queue is adjusted to [medical pod, cockpit], prioritizing disinfection of the medical pod.

[0094] Through the above process, the actual usage of each compartment on the ship can be dynamically sensed and predicted. Combining the functional importance of each compartment with future personnel activity trends, intelligent priority compensation and timing optimization are applied to task queues such as disinfection. This helps improve the disinfection efficiency of critical compartments and high-risk periods, while reducing interference with normal personnel activities, significantly enhancing the scientific and intelligent level of ship environmental hygiene management.

[0095] S400: Performs load status identification of shipboard electrical equipment and establishes task constraints based on the load status identification results and dispatchable power capacity.

[0096] Specifically, the operational status of various electrical devices within the ship is monitored and classified to obtain information such as whether the equipment is in operation, standby, or off, and its current power consumption level. The dispatchable power capacity refers to the remaining power resources available for dynamic allocation by non-critical tasks (such as disinfection equipment operation) without affecting the normal operation of the ship's core systems. Task constraints are the resource boundary conditions that need to be considered during task scheduling based on the dispatchable power capacity definition, ensuring that task execution does not cause power system overload or interfere with the stable operation of critical systems.

[0097] For example, firstly, operating data of various electrical equipment is collected in real time using current, voltage, and power sensors installed in the ship's power distribution system. Combined with load identification algorithms (such as non-intrusive load monitoring and cluster analysis), the current operating status and load level of the equipment are identified. Then, the total load and power supply capacity of the current power system are assessed. After deducting the reserve capacity required for critical equipment (such as navigation, communication, and life support systems) (ensuring a safety margin, such as 15% main bus redundancy), the available power capacity for scheduling tasks is calculated. Finally, based on the above load status identification results and the available power capacity, and considering the load balancing and safe operation requirements of the electrical equipment, power limits are set for disinfection tasks in different areas of the ship according to the power supply conditions in different areas, generating task constraints.

[0098] Through the above process, real-time perception and intelligent identification of the operating status of the ship's internal electrical equipment are achieved, and resource constraints for task execution are dynamically constructed based on the current system's power load. This effectively avoids the risk of power system overload during task execution and ensures the continuous and stable operation of the ship's critical systems.

[0099] S500: Optimize the start-up control of the ultraviolet disinfection device based on the correction task queue and the task constraints, and manage the disinfection of the ship's cabins based on the start-up control optimization results.

[0100] Specifically, under the premise of meeting task constraints, an optimization algorithm is used to find the optimal start-up control scheme for the ultraviolet disinfection device to achieve multiple objectives such as maximizing disinfection effect and rationally allocating power load. Finally, the ship's cabins are disinfected and managed based on the optimization results. That is, according to the optimized start-up control scheme, the start-up and shutdown times and sequence of the ultraviolet disinfection device are rationally arranged to effectively disinfect each cabin.

[0101] The above steps, by comprehensively considering various factors, seek the optimal start-up control scheme for the disinfection device, which can maximize disinfection efficiency and quality while meeting power constraints.

[0102] In some embodiments, the step of optimizing the start-up control of the ultraviolet disinfection device based on the correction task queue and the task constraints, and then managing the disinfection of ship cabins based on the optimization result, includes:

[0103] After configuring the parameter control space, an initial solution is established; an evaluation objective function is established, the evaluation features of which include maximum power load characteristics, equipment conflict penalty characteristics, average delay characteristics of critical compartments, and overall disinfection quality characteristics; based on the objective function, the initial solution, and the task constraints, iterative optimization of startup control is performed, and startup control optimization results are established.

[0104] Specifically, firstly, based on the corrected task queue and task execution constraints, an adjustable control parameter space is defined, including the start time, maximum number of concurrent tasks, and duration of each disinfection task; then, a heuristic method (such as earliest feasible time and task priority sorting) is used to randomly select parameters in the control space to generate an initial solution as the starting point of the optimization algorithm.

[0105] Specifically, an objective function incorporating multiple evaluation features is established to optimize startup control. For example, the maximum power load feature ensures that the power load does not exceed the dispatchable capacity; the equipment conflict penalty feature avoids operational conflicts between different disinfection devices in time or space; the average delay feature of critical compartments minimizes the disinfection waiting time of high-priority compartments; and the overall disinfection quality feature ensures that all compartments meet the prescribed disinfection standards.

[0106] Furthermore, based on the objective function mentioned above and combined with the initial solution, intelligent optimization algorithms such as genetic algorithms, simulated annealing, particle swarm optimization, or improved ant colony optimization are used to perform multiple rounds of iterative optimization.

[0107] For example, using a genetic algorithm, multiple possible start-up control schemes for the disinfection devices are initially generated randomly (i.e., the initial population). Each scheme corresponds to a set of start-up and shutdown times and sequences for the disinfection devices. Then, the objective function value of each scheme is calculated, its merits are evaluated, and the schemes in the population are continuously optimized through genetic operations such as selection, crossover, and mutation. Finally, the optimal individual in the population is selected as the start-up control optimization result. For example, this start-up control optimization result includes scheduling information such as the specific start time, duration, and execution sequence of each ultraviolet disinfection task.

[0108] Through the above process, while ensuring the safe operation of the power system and the rationality of task scheduling, the system load, task conflicts, cabin importance, and overall disinfection quality can be comprehensively considered to achieve intelligent start-up control optimization of the ultraviolet disinfection device. This improves the execution efficiency and resource utilization of ship cabin disinfection tasks, reduces the risk of interference to critical systems, and enhances the automation and intelligence level of ship environmental management.

[0109] In some implementations, the step of performing iterative optimization of startup control based on the objective function, the initial solution, and the task constraints, and establishing the startup control optimization result, includes:

[0110] Establish time perturbations, task replacement perturbations, start-stop switching perturbations, and equipment adjustment perturbations; during each round of iterative optimization, call the historical perturbation data, calculate the change value of the objective function under the corresponding perturbation feature based on the historical perturbation data, and reconstruct the perturbation weight list based on the change value of the objective function; use the perturbation weight list to configure the random selection factors of time perturbations, task replacement perturbations, start-stop switching perturbations, and equipment adjustment perturbations to perform startup control iterative optimization.

[0111] Specifically, time perturbations are used to fine-tune the time window for task execution; task replacement perturbations are used to replace a task in the scheduling sequence to adjust compartment coverage or priority; start-stop switching perturbations are used to modify the start-stop strategy of the ultraviolet device, such as starting earlier or stopping later; and equipment adjustment perturbations are used to adjust load distribution or task binding relationships among multiple devices.

[0112] Specifically, historical perturbation data refers to the feedback data recording the impact of various perturbation operations on the objective function during multiple iterations. By analyzing historical perturbation data, the selection probability of subsequent perturbation types (i.e., a perturbation weight list) can be defined based on the changes in the objective function.

[0113] Specifically, in each iteration, the change in the objective function (i.e., objective function gain or loss) caused by each type of perturbation in the current scheduling solution is recorded, and the change value is used as a performance index of the perturbation to reflect the effectiveness of each type of perturbation in the current search stage. Then, methods such as weighted averaging, exponential decay, or Bayesian update are used to dynamically adjust the selection weights of each type of perturbation to ensure that the perturbation types with better performance receive a higher selection probability, thereby improving optimization efficiency.

[0114] For example, in 10 iterations, the objective function improvement brought by time perturbation is +5%, task replacement perturbation is +2%, start-stop switching perturbation is +1%, and equipment adjustment perturbation is +3%. The list of updatable perturbation weights is: time perturbation (0.4), equipment adjustment perturbation (0.3), task replacement perturbation (0.2), and start-stop switching perturbation (0.1).

[0115] Furthermore, based on the perturbation weight list, a probability distribution for perturbation selection is constructed. Then, a random selection factor (such as roulette wheel selection or a greedy-random strategy) is used to select one of the four types of perturbations, and the perturbation operation is performed on the current solution. Specifically, if the objective function improves after perturbation, the new solution is accepted.

[0116] Through the above process, an adaptive optimization strategy based on perturbation effect feedback is realized, which helps to improve the search efficiency and solution quality in the ultraviolet disinfection task scheduling process.

[0117] In some implementations, the step of calculating the change value of the objective function under the corresponding perturbation feature based on the historical perturbation data, and reconstructing the perturbation weight list based on the change value of the objective function, includes:

[0118] Obtain the time-series identifier of the historical disturbance data; after establishing the mapping between the time-series identifier and the change value, configure the key points of the iterative optimization stage; use the mapping between the time-series identifier and the change value to perform time-weighted calculation of the disturbance criticality and generate the time-weighted calculation result; after compensating the time-weighted calculation result based on the key points of the stage, reconstruct the disturbance weight list.

[0119] Specifically, the time sequence identifier is used to mark the iteration round or time point of each perturbation, so as to track the evolution of the perturbation effect over time; the perturbation criticality is used to quantify the degree of influence of a certain type of perturbation on the optimization objective function at a specific stage; the stage key point refers to the representative stage nodes (such as the initial stage, convergence stage, local optimum stage, etc.) divided in the optimization process, which are used to guide the stage compensation of the weight adjustment strategy.

[0120] Specifically, firstly, in each optimization iteration, the system records the iteration number t for each perturbation operation as a time sequence identifier, and simultaneously records the change in the objective function Δf caused by the perturbation in that iteration, forming a perturbation record pair (t, Δf). Then, all perturbation record pairs are classified according to perturbation type, establishing a time-series evolution sequence for each type of perturbation, and dividing the optimization process into several stages based on the total number of iterations, determining the key points of each stage.

[0121] Furthermore, to reflect the priority of recent perturbation effects, time-weighted calculations are performed on historical perturbation data. Weighting functions (such as exponential decay and linear decay) are used to assign time weights to each perturbation record to calculate the perturbation criticality. Finally, a stage compensation factor is set according to the current iteration stage to compensate the weighted calculation results, so as to strengthen the guiding role of certain perturbation types in specific stages (for example, encouraging exploratory perturbations in the early stage and strengthening convergent perturbations in the later stage).

[0122] Through the above process, dynamic perturbation strategy optimization based on historical perturbation feedback is achieved. It not only considers the absolute performance of the perturbation effect, but also introduces time decay and phased compensation mechanisms, which enhances the timeliness and pertinence of perturbation selection.

[0123] In some embodiments, the disinfection management of ship cabins based on the results of the initiation control optimization includes:

[0124] Configure cabin disinfection parameters for the ship's cabins based on the optimization results of the start-up control; use the cabin disinfection parameters as a reference parameter to execute adaptive area control decisions within the cabins; and manage the disinfection of the ship's cabins based on the results of the adaptive area control decisions.

[0125] Specifically, cabin disinfection parameters refer to a set of standard configuration parameters used to guide ultraviolet disinfection devices in performing their tasks within ship cabins. These parameters may include disinfection duration, disinfection intensity, equipment start-up and shutdown sequence, and disinfection frequency. Based on these cabin disinfection parameters, disinfection resources can be dynamically allocated and optimized according to the risk factors, frequency of personnel activity, and spatial structure of each area, while ensuring that the total amount of disinfection resources remains constant. This improves resource efficiency and ensures disinfection effectiveness.

[0126] Specifically, firstly, based on the optimization results of the startup control (including task scheduling, equipment start-up and shutdown, and available power capacity), an initial set of disinfection parameters is generated for each compartment. This includes: the total disinfection resource budget (e.g., available disinfection time / energy per unit time); the availability and limitations of various ultraviolet devices; and the priority and timing of disinfection tasks. Then, each compartment is further divided into several functional areas (e.g., rest areas, work areas, and passageways), and the total resources are adaptively allocated based on predetermined factors, such as:

[0127] Risk level of each area (e.g., population density, air circulation, historical pollution records); usage frequency of the area (e.g., frequency of human activity detected by sensors); spatial structure parameters (e.g., degree of enclosure, volume, surface area); current power availability and equipment status.

[0128] Optionally, under the constraint of a constant total value (i.e., a fixed total disinfection resource), a weighted allocation, linear programming, or heuristic algorithm can be used to allocate disinfection resources to each region to generate regional-level control decision results.

[0129] Furthermore, based on the regional control decision results, the ultraviolet disinfection devices are scheduled to perform tasks in regional order, and the task execution status and power load are monitored in real time to ensure that the tasks are completed as planned. Preferably, regional parameters are readjusted when necessary to adapt to emergencies (such as personnel entry, equipment failure, etc.).

[0130] Through the above process, a multi-level collaborative mechanism from global scheduling optimization (start-up control optimization) to local execution control (regional adaptive allocation) is realized, ensuring that ultraviolet disinfection tasks can be executed efficiently and accurately in ship environments with limited power resources and complex task constraints, achieving multi-objective optimization of disinfection effect, safety and energy utilization.

[0131] In some implementations, the disinfection management of ship cabins based on adaptive zone control decision results includes:

[0132] Configure a mapping disinfection inspection standard based on the cabin disinfection parameters; use the mapping disinfection inspection standard to test and verify the cabin, and generate test and verification feedback; generate correction compensation based on the test and verification feedback, and use the correction compensation to optimize the adaptive area control decision results.

[0133] Specifically, the mapping disinfection inspection standard is a disinfection effectiveness evaluation benchmark established based on the disinfection parameters of the cabin (such as duration, intensity, frequency, etc.) and the regional characteristics (such as risk level, structural parameters), used to determine whether the disinfection task has met the standards. By comparing the environmental status data after disinfection (such as ultraviolet radiation coverage, residual microbial indicators, air quality parameters, etc.) collected by sensors or detection equipment with the above-mentioned mapping disinfection inspection standard, defects in the actual disinfection operation can be identified, thereby generating detection and verification feedback, and adjusting the original control strategy corresponding to the adaptive regional control decision results accordingly, optimizing the subsequent disinfection resource allocation and execution strategy.

[0134] Specifically, after the disinfection task is completed, the disinfection effect of each area is detected by deploying environmental sensors, rapid microbial detection equipment, ultraviolet dose monitors, etc., generating detection verification data and comparing it with preset standards to obtain feedback results.

[0135] Furthermore, if the feedback results exceed the tolerance range, they are marked as non-compliant areas. Based on the degree of deviation and regional characteristics, correction and compensation strategies are generated for non-compliant areas, including: increasing the disinfection time or intensity of the area; optimizing equipment layout or irradiation angle; and increasing the resource allocation weight of the area in the next round of tasks. Finally, the correction and compensation results are fed back to the adaptive area control decision module to update the area allocation strategy to achieve closed-loop optimization.

[0136] Through the above process, a closed-loop control mechanism was constructed, encompassing parameter setting, disinfection execution, effect detection, and calibration optimization. This mechanism enables dynamic adaptive control of cabin disinfection tasks, from strategy configuration to effect verification. It helps improve the accuracy and reliability of disinfection tasks, enhances the ability to respond to environmental disturbances and task deviations, and ensures efficient, safe, and compliant intelligent disinfection management in complex ship environments.

[0137] In summary, the intelligent control method for marine ultraviolet disinfection devices provided by this invention has the following technical effects:

[0138] By collecting multi-source information about the ship's environment, an environmental state vector containing characteristics of both the internal and external environments is constructed. Modular modeling of ship compartments is implemented, and based on the environmental state vector, the environmental risk level of each compartment is assessed, generating an initial task queue. Importance levels and personnel activity data for each compartment are acquired, and the task priorities of the initial task queue are dynamically adjusted based on this data to construct a corrected task queue. The current load status of the ship's internal electrical equipment is identified, and a resource constraint model for disinfection task execution is constructed based on the identified load status and available power capacity. According to the corrected task queue and resource constraint model, the start-stop control strategy for the ultraviolet disinfection device is optimized, and the scheduling and execution of compartment disinfection tasks are carried out based on the optimization results. This achieves the technical effects of more precise environmental perception, optimized task queues, and improved disinfection efficiency.

[0139] Example 2, as Figure 2 This is a schematic diagram of the intelligent control system for the marine ultraviolet disinfection device of the present invention. For example, Figure 1 The flowchart of the intelligent control method for the marine ultraviolet disinfection device of the present invention can be seen as follows: Figure 2 The structure shown is implemented.

[0140] Based on the same concept as the intelligent control method for marine ultraviolet disinfection devices described in the embodiments, the present invention also provides an intelligent control system for marine ultraviolet disinfection devices, comprising:

[0141] The environmental state vectorization module 11 is used to collect environmental information of the ship and establish an environmental state vector, which includes an internal environmental state vector and an external environmental state vector.

[0142] The risk factor calculation module 12 is used to perform modular modeling of the cabin, call the environmental state vector, calculate the cabin risk factor based on the modular modeling result, and construct the initial task queue with the cabin risk factor.

[0143] The priority compensation module 13 is used to acquire the importance level of the compartment and personnel activity data, and to perform priority compensation of the initial task queue based on the importance level and personnel activity data to generate a corrected task queue.

[0144] Task constraint module 14 is used to perform load status identification of the ship's electrical equipment and establish task constraints based on the load status identification results and the dispatchable power capacity.

[0145] The disinfection execution and management module 15 is used to optimize the start-up control of the ultraviolet disinfection device based on the calibration task queue and the task constraints, and to manage the disinfection of the ship's cabins based on the start-up control optimization results.

[0146] In some embodiments, the environment state vectorization module 11 includes:

[0147] The ship positioning and port correlation analysis unit is used to obtain ship positioning, perform port correlation analysis based on the ship positioning, and establish port correlation environment data.

[0148] The external meteorological information reading and meteorological environment data establishment unit is used to read external meteorological information and establish meteorological environment data based on the ship's positioning.

[0149] The cabin environment data acquisition and environmental dataset establishment unit is used to activate the sensor group in the cabin, perform environmental data acquisition in the cabin, and establish an environmental dataset. The environmental dataset includes temperature data, humidity data, carbon dioxide concentration, organic matter pollution concentration, and cabin status after the previous round of disinfection.

[0150] The environmental state vector establishment unit is used to establish an external environmental state vector based on the port-related environmental data and meteorological environmental data, and to establish an internal environmental state vector based on the environmental dataset.

[0151] In some embodiments, the risk factor calculation module 12 includes:

[0152] The cabin structure and ventilation system feature extraction unit is used to extract cabin structure connectivity features and ventilation system association features based on the modular modeling results, and establish a graph structure.

[0153] The mutual influence clustering unit is used to perform mutual influence clustering of compartments using the graph structure and establish mutual influence clustering results.

[0154] An independent risk calculation unit is used to perform independent risk calculations for each compartment based on the environmental state vector and to establish independent risk calculation results.

[0155] The risk impact compensation and cabin risk factor generation unit is used to compensate for the risk impact of independent risk calculation results based on the mutual influence clustering results, and generate cabin risk factors.

[0156] In some embodiments, the priority compensation module 13 includes:

[0157] The activity log extraction and activity trajectory prediction unit is used to extract activity logs from the personnel activity data and establish predicted activity trajectories.

[0158] The task timing adaptation analysis and fitness establishment unit is used to perform timing adaptation analysis on each task in the initial task queue based on the predicted activity trajectory, and to establish task timing adaptation fitness.

[0159] The compartment execution function analysis and importance level construction unit is used to analyze the execution functions of the compartment and construct an importance level based on the results of the execution function analysis.

[0160] The priority compensation and correction task queue generation unit is used to perform priority compensation of the initial task queue and generate a correction task queue by utilizing the task timing adaptation fitness and importance level.

[0161] In some embodiments, the disinfection execution and management module 15 includes:

[0162] The initial solution establishment unit is used to establish an initial solution after configuring the parameter control space.

[0163] The evaluation objective function establishment unit is used to establish the evaluation objective function, wherein the evaluation features in the evaluation objective function include the maximum power load feature, the equipment conflict penalty feature, the average delay feature of the critical compartment, and the overall disinfection quality feature.

[0164] The unit for initiating control iterative optimization and establishing results is used to perform initiation control iterative optimization based on the objective function, the initial solution, and the task constraints, and to establish the initiation control optimization results.

[0165] In some implementations, the execution steps of the control iteration optimization and result establishment unit in the disinfection execution and management module 15 include:

[0166] Establish time perturbations, task replacement perturbations, start-stop switching perturbations, and equipment adjustment perturbations; during each round of iterative optimization, call the historical perturbation data, calculate the change value of the objective function under the corresponding perturbation feature based on the historical perturbation data, and reconstruct the perturbation weight list based on the change value of the objective function; use the perturbation weight list to configure the random selection factors of time perturbations, task replacement perturbations, start-stop switching perturbations, and equipment adjustment perturbations to perform startup control iterative optimization.

[0167] In some implementations, the execution steps of initiating the control iterative optimization and result establishment unit also include:

[0168] Obtain the time-series identifier of the historical disturbance data; after establishing the mapping between the time-series identifier and the change value, configure the key points of the iterative optimization stage; use the mapping between the time-series identifier and the change value to perform time-weighted calculation of the disturbance criticality and generate the time-weighted calculation result; after compensating the time-weighted calculation result based on the key points of the stage, reconstruct the disturbance weight list.

[0169] In some embodiments, the disinfection execution and management module 15 further includes:

[0170] The cabin disinfection parameter configuration unit is used to configure the cabin disinfection parameters of the ship's cabins based on the startup control optimization results.

[0171] An adaptive zone control decision execution unit is used to execute adaptive zone control decisions within the cabin, using the cabin disinfection parameters as a reference parameter.

[0172] The disinfection management unit is used to manage the disinfection of ship cabins based on the results of adaptive zone control decisions.

[0173] In some implementations, the execution steps of the disinfection management unit in the disinfection execution and management module 15 include:

[0174] Configure a mapping disinfection inspection standard based on the cabin disinfection parameters; use the mapping disinfection inspection standard to test and verify the cabin, and generate test and verification feedback; generate correction compensation based on the test and verification feedback, and use the correction compensation to optimize the adaptive area control decision results.

[0175] It should be understood that the focus of the embodiments mentioned in this specification is their difference from other embodiments. The specific embodiments in the aforementioned Embodiment 1 are also applicable to the intelligent control system of the marine ultraviolet disinfection device described in Embodiment 2. For the sake of brevity, they will not be further elaborated here.

[0176] It should be understood that the embodiments disclosed in this invention and the above description enable those skilled in the art to implement this invention. However, this invention is not limited to the embodiments mentioned above. It should be understood that those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this invention, and should all be included within the protection scope of this invention.

Claims

1. An intelligent control method for marine ultraviolet disinfection devices, characterized in that, include: Perform environmental information collection on the ship and establish an environmental state vector, which includes an internal environmental state vector and an external environmental state vector. After modularly modeling the cabin, the environmental state vector is called, and the cabin risk factor is calculated based on the modular modeling results. The initial task queue is then constructed using the cabin risk factor. Acquire the importance level of the compartment and personnel activity data, and perform priority compensation of the initial task queue based on the importance level and personnel activity data to generate a correction task queue; Perform load status identification of shipboard electrical equipment, and establish task constraints based on the load status identification results and dispatchable power capacity; The startup control optimization of the ultraviolet disinfection device is performed based on the correction task queue and the task constraints, and the disinfection management of the ship's cabins is carried out based on the startup control optimization results.

2. The intelligent control method for the marine ultraviolet disinfection device as described in claim 1, characterized in that, The process of collecting environmental information from the vessel and establishing an environmental state vector includes: Obtain the ship's location, perform port correlation analysis based on the ship's location, and establish port correlation environmental data; Based on the ship's positioning, external meteorological information is read to establish meteorological environment data; Activate the sensor group inside the cabin to collect environmental data and establish an environmental dataset, which includes temperature data, humidity data, carbon dioxide concentration, organic pollution concentration, and cabin status after the previous round of disinfection. An external environmental state vector is established using the port-related environmental data and meteorological environmental data, and an internal environmental state vector is established using the environmental dataset.

3. The intelligent control method for the marine ultraviolet disinfection device as described in claim 1, characterized in that, After modularly modeling the cabin, the environmental state vector is invoked, and cabin risk factors are calculated based on the modular modeling results, including: Based on the modular modeling results, extract the connectivity features of the cabin structure and the correlation features of the ventilation system, and establish a graph structure; The graph structure is used to perform inter-cabin interaction clustering, and the inter-cabin interaction clustering results are established. Based on the environmental state vector, perform independent risk calculations for each compartment and establish independent risk calculation results; Based on the clustering results of mutual influence, risk impact compensation is performed on the independent risk calculation results to generate cabin risk factors.

4. The intelligent control method for the marine ultraviolet disinfection device as described in claim 1, characterized in that, The step of prioritizing the initial task queue based on the importance level and the personnel activity data to generate a corrected task queue includes: The activity data of the personnel is used to extract activity logs and establish predicted activity trajectories; Based on the predicted activity trajectory, perform temporal adaptation analysis on each task in the initial task queue and establish task temporal adaptation fitness. Perform functional analysis on the compartments and construct an importance level based on the results of the functional analysis; The initial task queue is compensated for priority using the task timing adaptation fitness and importance level to generate a corrected task queue.

5. The intelligent control method for the marine ultraviolet disinfection device as described in claim 1, characterized in that, The step of optimizing the start-up control of the ultraviolet disinfection device based on the calibration task queue and the task constraints, and using the optimization result to manage the disinfection of ship cabins, includes: After configuring the parameter control space, an initial solution is established; An evaluation objective function is established, and the evaluation features in the evaluation objective function include maximum power load characteristics, equipment conflict penalty characteristics, average delay characteristics of critical compartments, and overall disinfection quality characteristics. Based on the objective function, the initial solution, and the task constraints, perform iterative optimization of the startup control to establish the startup control optimization result.

6. The intelligent control method for the marine ultraviolet disinfection device as described in claim 5, characterized in that, The step of performing iterative optimization of startup control based on the objective function, the initial solution, and the task constraints, and establishing the startup control optimization result, includes: Establish time disturbances, task replacement disturbances, start / stop switching disturbances, and equipment adjustment disturbances; In each round of iterative optimization, historical perturbation data is called, and the change value of the objective function under the corresponding perturbation feature is calculated based on the historical perturbation data. The perturbation weight list is then reconstructed based on the change value of the objective function. The random selection factors for time disturbance, task replacement disturbance, start-stop switching disturbance, and equipment adjustment disturbance are configured using the disturbance weight list to perform startup control iterative optimization.

7. The intelligent control method for the marine ultraviolet disinfection device as described in claim 6, characterized in that, The step of calculating the change value of the objective function under the corresponding perturbation feature based on the historical perturbation data, and reconstructing the perturbation weight list based on the change value of the objective function, includes: Obtain the time sequence identifier of historical disturbance data; After establishing the mapping between the time sequence identifier and the change value, configure the key points of the iterative optimization stage; The time-weighted calculation of the perturbation criticality is performed by using the mapping between the time sequence identifier and the change value, and a time-weighted calculation result is generated. After compensating for the time-weighted calculation results based on the key points of the aforementioned stages, the disturbance weight list is reconstructed.

8. The intelligent control method for the marine ultraviolet disinfection device as described in claim 1, characterized in that, The disinfection management of ship cabins based on the optimization results of the initiation control includes: Configure the cabin disinfection parameters of the ship's cabins based on the optimization results of the start-up control; Using the disinfection parameters of the cabin as a reference parameter, an adaptive area control decision is made within the cabin. Disinfection management of ship cabins is carried out based on the results of adaptive zone control decisions.

9. The intelligent control method for the marine ultraviolet disinfection device as described in claim 8, characterized in that, The disinfection management of ship cabins based on adaptive zone control decision results includes: Configure and map disinfection inspection standards according to the aforementioned cabin disinfection parameters; The aforementioned mapping disinfection inspection standards are used to test and verify the cabin, and test and verification feedback is generated; Based on the detection and verification feedback, a correction compensation is generated, and the correction compensation is used to optimize the adaptive region control decision results.

10. An intelligent control system for marine ultraviolet disinfection devices, characterized in that: The intelligent control method for implementing the marine ultraviolet disinfection device according to any one of claims 1 to 9 includes: The environmental state vectorization module is used to collect environmental information of the ship and establish environmental state vectors, which include internal environmental state vectors and external environmental state vectors. The risk factor calculation module is used to perform modular modeling of the cabin, call the environmental state vector, calculate the cabin risk factor based on the modular modeling result, and construct the initial task queue with the cabin risk factor. The priority compensation module is used to acquire the importance level of the compartment and personnel activity data, and to perform priority compensation of the initial task queue based on the importance level and personnel activity data to generate a corrected task queue. The task constraint module is used to perform load status identification of the ship's electrical equipment and establish task constraints based on the load status identification results and the dispatchable power capacity. The disinfection execution and management module is used to optimize the start-up control of the ultraviolet disinfection device based on the calibration task queue and the task constraints, and to manage the disinfection of the ship's cabins based on the start-up control optimization results.

Images