A synergistic control method for filtration and ultraviolet sterilization in a purely physical ballast water management system

Abstract

This invention discloses a synergistic control method for filtration and ultraviolet sterilization in a purely physical ballast water management system. Based on real-time monitoring of water flow characteristics, filter status, water quality parameters, and ultraviolet sterilization effect, this method achieves efficient operation of the ballast water treatment system through intelligent feedback regulation, machine learning optimization, adaptive flow rate adjustment, and dynamic energy consumption optimization. The method of this invention can improve ballast water treatment efficiency by 20%, reduce energy consumption by 15%, and enhance system stability and adaptability. It is applicable to ballast water management of various types of ships and complies with international environmental standards.

Description

Technical Field

[0001] This invention relates to the field of ballast water treatment technology, and in particular to a synergistic control method for filtration and ultraviolet sterilization in a purely physical ballast water management system. Background Technology

[0002] Currently, ballast water treatment technologies are mainly divided into physical, chemical, and biological methods. Among them, physical methods, due to their lack of chemical residues and environmental safety, have become the focus of research and application. Physical methods mainly include mechanical filtration, ultraviolet sterilization, high-pressure sterilization, and ultrasonic treatment, with the combination of mechanical filtration and ultraviolet sterilization being the most widely used. Mechanical filtration can remove larger suspended solids and organisms, while ultraviolet sterilization uses high-intensity ultraviolet light to destroy the DNA of microorganisms, achieving an inactivation effect. Although these two methods have relatively mature technologies in practical applications, their independent control modes often lead to a decrease in the overall system operating efficiency. For example, the degree of clogging in the filtration system directly affects the treatment efficiency of the ultraviolet sterilization unit, and the operating status of the ultraviolet sterilization unit also affects the maintenance requirements of the filtration system. However, existing technologies have limited research on the coordinated control of these two methods, and the system operation still faces the following problems:

[0003] 1. The filtration system and the UV sterilization unit failed to work together effectively. Traditional systems often operate the filtration and UV sterilization units as two independent modules, failing to dynamically adjust the power and flow rate of UV sterilization based on changes in filtration performance, resulting in increased energy consumption or incomplete sterilization.

[0004] 2. Clogged filtration system affects sterilization efficiency. After prolonged operation, the filter element may become clogged, causing a decrease in water flow rate. Since UV sterilization units are typically designed for a fixed flow rate, changes in flow rate may result in insufficient or excessive sterilization time, affecting the overall stability of the system.

[0005] 3. High energy consumption and maintenance costs. Due to the lack of effective coordinated control, the system often requires high-intensity ultraviolet irradiation to compensate for the instability of the filtration system, which leads to a shortened lifespan of the ultraviolet lamps and increases maintenance and replacement costs. Summary of the Invention

[0006] In view of this, the purpose of this invention is to provide a coordinated control method for filtration and ultraviolet sterilization in a purely physical ballast water management system. Through an intelligent monitoring and feedback mechanism, the method enables adaptive adjustment of the filtration and ultraviolet sterilization units, thereby improving sterilization efficiency, reducing energy consumption, and reducing equipment maintenance costs, ensuring that the system can operate stably and efficiently under different operating conditions.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a synergistic control method for filtration and ultraviolet sterilization in a purely physical ballast water management system, comprising the following steps:

[0008] Step 1: Monitor the suspended particle concentration, turbidity, ultraviolet transmittance and water flow velocity of ballast water in real time using sensors, and establish a water quality analysis model.

[0009] Step 2: Employ an intelligent feedback control mechanism to dynamically adjust filtration accuracy, backwashing frequency, and UV dosage requirements based on real-time water quality data;

[0010] Step 3: Employ a machine learning-based optimization model, utilizing support vector regression and long short-term memory networks to predict the optimal filtration accuracy and UV sterilization parameters, and optimize the processing strategy based on historical data;

[0011] Step 4: Adopt an adaptive flow rate regulation mechanism, and combine quantitative control PID control, fuzzy control and genetic algorithm to optimize the flow control valve and variable frequency pump, so that the water flow rate is kept within the optimal working range of ultraviolet sterilization;

[0012] Step 5: Adopt a dynamic energy consumption optimization strategy, combine water quality monitoring data, adjust the power of ultraviolet lamps and filtration energy consumption, and reduce overall energy consumption while ensuring treatment effect.

[0013] In a preferred embodiment, step 2 specifically includes:

[0014] Step 21: Real-time water quality monitoring and data acquisition:

[0015] A turbidity sensor is used to monitor the turbidity of the ballast water in real time, and a particulate matter concentration sensor is used to monitor the suspended particulate matter concentration of the ballast water in real time.

[0016] The ultraviolet light transmittance is measured using an ultraviolet transmittance sensor, and the ultraviolet light dose is calculated. in, Ultraviolet light dose, Ultraviolet light intensity, This refers to the irradiation time;

[0017] Water flow velocity is detected using a flow velocity sensor. Ensure the water stays in the UV sterilization unit for the required time. The following conditions must be met: in, The effective length of the ultraviolet sterilization unit;

[0018] Step 22: Dynamically adjust filter parameters:

[0019] When the concentration of suspended particles is higher than the threshold It will automatically improve the filtration accuracy. Level or increase backwash frequency ;

[0020] When the turbidity after filtration If the water flow rate is still higher than the set value, reduce the water flow rate. To improve filtration efficiency;

[0021] Step 23: Adjust UV sterilization power

[0022] Calculate UV dose requirements in, This is an empirical coefficient, adjusted according to different water qualities;

[0023] According to ultraviolet dose requirements Adjust UV lamp power in, For maximum ultraviolet power, The target UV dose;

[0024] Step 24: Adaptive Flow Control

[0025] Calculate the optimal flow velocity range in, This is the optimal UV sterilization dwell time;

[0026] The water flow rate is automatically adjusted by a variable frequency pump and a flow control valve. To match the optimal UV sterilization dwell time;

[0027] Step 25: Exception Handling Mechanism

[0028] When the turbidity after filtration Continuously higher than the turbidity set value If so, an alarm will be triggered and the filtering mode will be adjusted;

[0029] When the survival rate of the ultraviolet sterilization unit organisms Exceeding the survival rate setting value Increase the power of the ultraviolet lamp. Or reduce the flow rate.

[0030] In a preferred embodiment, step 3 specifically includes:

[0031] Step 31: Data Acquisition and Feature Engineering

[0032] Collect water quality data before and after filtration, including the concentration of suspended particles before filtration. Concentration of suspended particles after filtration Turbidity before filtration (NTU), turbidity after filtration UV transmittance (UVT) after filtration, water flow velocity UV lamp power and sterilization rate after filtration ;

[0033] Principal component analysis (PCA) was used for dimensionality reduction to extract key influencing factors. : ,in The dimension reduction transformation matrix is The original data feature matrix;

[0034] Step 32: Model Training and Optimization

[0035] Support Vector Regression (SVR) is used to predict the optimal filtering accuracy. and UV dose requirements ;

[0036] Training objectives: ,in The sterilization rate predicted by the model. Sterilization is performed after filtration; N represents a summary of historical data samples, and i represents the sample index;

[0037] Cross-validation is used to improve the model's generalization ability;

[0038] Step 33: Real-time forecasting and dynamic adjustment:

[0039] Calculate the current water quality state vector :

[0040] LSTM network is used to predict the optimal filtering accuracy at the next time step. And the optimal UV dose requirement at the next moment : Where f is the LSTM network mapping function, For model parameters; determine the optimal filtering accuracy at the next time step. Applied to the filtration module, adjusting precision; optimal UV dose requirement at the next moment. Adjust UV lamp power ;

[0041] Step 34: Reinforcement learning optimizes the control strategy:

[0042] Deep reinforcement learning (DQN) is used to optimize the filtering and UV sterilization strategies;

[0043] Reward function design : ,in, The total energy consumption of the ballast water management system. For weight coefficients; during training, the agent learns the optimal control strategy through trial and error to maximize the sterilization rate and minimize energy consumption;

[0044] Step 35: Ballast Water Management System Deployment and Adaptive Optimization

[0045] We continuously update our machine learning models through online learning to adapt to different water quality environments.

[0046] By combining historical ballast water data of ships, a personalized optimization model is established to improve the adaptability to different routes.

[0047] In a preferred embodiment, step 4 specifically includes:

[0048] Step 41: Flow rate monitoring and data acquisition;

[0049] Step 42: Adaptive flow velocity calculation:

[0050] Optimal flow rate calculate: ; Indicates the optimal UV sterilization dwell time;

[0051] When the residence time in the ultraviolet sterilization unit At this time, the water flow rate needs to be increased. To avoid excessive energy consumption due to excessive radiation;

[0052] When the residence time in the ultraviolet sterilization unit At that time, reduce the water flow speed To ensure sterilization effectiveness;

[0053] Step 43: Flow rate regulation and control strategy:

[0054] Adaptive adjustment is achieved using fuzzy control.

[0055] Set the fuzzy control input variable: current flow rate UV transmittance (UVT) after filtration and NTU turbidity before filtration; set control rules:

[0056] If the UV transmittance (UVT) is low after filtration and the NTU (turbidity) is high before filtration, then reduce the water flow rate. ;

[0057] If the UV transmittance (UVT) is high after filtration and the NTU (turbidity) is low before filtration, then increase the water flow rate. ;

[0058] Adjustment range is calculated using fuzzy inference. in, It is the target flow rate;

[0059] Step 44: Closed-loop control and optimization

[0060] Set up an error feedback mechanism: in, Indicates the current flow rate. These are the PID control parameters; if the error If the error is too large, the controller will adaptively and quickly adjust the flow rate; if the error is small, it will adjust slowly to ensure a stable flow rate.

[0061] Step 45: Ballast water management system optimization and dynamic adjustment.

[0062] In a preferred embodiment, step 5 specifically includes:

[0063] Step 51: Energy consumption modeling and objective function:

[0064] The total energy consumption of the ballast water management system mainly consists of the energy consumption of the filtration unit. Energy consumption of UV sterilization unit composition: ;

[0065] Filter unit energy consumption Water flow velocity and backwash frequency Influence: ,in, For flow velocity correlation coefficient, This refers to the backwashing energy consumption coefficient.

[0066] Energy consumption of UV sterilization unit Power of ultraviolet lamp Influence of UV transmittance (UVT): ;

[0067] The goal is to minimize the total energy consumption of the ballast water management system. At the same time, it meets the sterilization rate after filtration. constraint: s. t. , Indicates the minimum sterilization rate;

[0068] Step 52: Energy optimization strategy based on reinforcement learning:

[0069] A deep reinforcement learning (DQN) approach is adopted to optimize the synergistic energy consumption control strategy of filtering and ultraviolet sterilization.

[0070] State variables Water quality parameters (NTU, UVT, C), current flow rate UV lamp power ;

[0071] Action space Adjust V, F and ;

[0072] reward function : ,in, As a penalty factor;

[0073] During training, the agent learns the optimal strategy based on historical data and continuously updates it online;

[0074] Step 53: Dynamically adjust the UV lamp power:

[0075] Calculate the optimal UV lamp power ;

[0076] When the UV transmittance (UVT) is high, reduce the UV lamp power. To reduce energy consumption;

[0077] Sterilization rate after filtration Increase the UV lamp power as it descends. To ensure sterilization effectiveness;

[0078] Step 54: Collaborative Optimization Strategy:

[0079] Optimization using a genetic algorithm (GA) Parameter combinations;

[0080] Fitness function: ;

[0081] The optimal energy consumption scheme is searched using selection, crossover, and mutation operations.

[0082] Step 55: System Online Adaptive Optimization:

[0083] By combining reinforcement learning and genetic algorithms, the energy consumption optimization strategy is dynamically updated.

[0084] Predictive maintenance is employed to prevent performance degradation caused by long-term system operation.

[0085] Compared with the prior art, the present invention has the following beneficial effects:

[0086] This invention achieves intelligent, energy-saving, and efficient ballast water treatment systems through the coordinated control of filtration and ultraviolet sterilization processes, meeting the emission requirements of international conventions and improving the overall level of ship ballast water management. Attached Figure Description

[0087] Figure 1 This is a flowchart illustrating a preferred embodiment of the present invention. Detailed Implementation

[0088] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0089] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0090] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations according to this application; as used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise; furthermore, it should be understood that when the terms “comprising” and / or “including” are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0091] A method for coordinated control of filtration and ultraviolet sterilization in a purely physical ballast water management system, with reference to... Figure 1 This includes the following steps:

[0092] Step 1. System Initialization and Data Acquisition

[0093] (1) Start the ballast water management system and perform a self-check to ensure that the filtration unit, ultraviolet sterilization unit, sensor network and control system are all in normal working condition.

[0094] (2) The water quality sensor begins to collect raw water quality data in real time, including suspended particulate concentration. Turbidity (NTU), ultraviolet transmittance (UVT), and water flow rate .

[0095] (3) The system sets the target water quality standard ( Target value, (Minimum sterilization rate requirement), and calculate the initial filtration accuracy. UV dose requirements and flow rate .

[0096] Step 2. Intelligent Feedback Control

[0097] (1) Monitor water quality parameters before and after filtration, and calculate filtration efficiency: .

[0098] (2) If If the value is below the set threshold, the filtration accuracy will be automatically adjusted. Or increase the backwashing frequency .

[0099] (3) By comparing ultraviolet transmittance (UVT) with biological survival rate Feedback and dynamic adjustment of UV dose:

[0100] Step 3. Optimization Model Based on Machine Learning

[0101] (1) Support vector regression (SVR) was used to predict the optimal filtration accuracy and UV dose.

[0102] (2) Calculate the error and optimize the parameters to achieve the target sterilization rate:

[0103] .

[0104] (3) Water quality prediction is performed using a long short-term memory (LSTM) network to adjust filtration and UV sterilization strategies in advance.

[0105] Step 4. Adaptive Flow Rate Adjustment

[0106] (1) Calculate the current stay time: .

[0107] (2) Ensure At the optimal sterilization time Adjust the flow rate nearby.

[0108] (3) Introduce a fuzzy control strategy and adjust the flow rate through fuzzy logic decision-making to improve the control accuracy.

[0109] (4) Use genetic algorithms to optimize PID control parameters to make flow rate regulation more precise and efficient.

[0110] Step 5. Dynamic Energy Consumption Optimization

[0111] (1) Reinforcement learning is used to optimize the synergistic energy consumption control of filtration and ultraviolet sterilization.

[0112] (2) Calculate the total energy consumption of the system:

[0113] (3) Objective function: s. t.

[0114] (4) Optimization using a genetic algorithm (GA) Combined, it improves system energy efficiency.

[0115] Step 6. System Fault Early Warning and Maintenance

[0116] (1) Set an abnormal detection threshold and alarm when the water quality parameters exceed the range.

[0117] (2) Use remote monitoring and data analysis to predictively maintain key components and reduce unplanned downtime.

[0118] This invention achieves intelligent, energy-saving, and efficient ballast water treatment systems through the coordinated control of filtration and ultraviolet sterilization processes, meeting the emission requirements of international conventions and improving the overall level of ship ballast water management.

Claims

1. A method for the coordinated control of filtration and ultraviolet sterilization in a purely physical ballast water management system, characterized in that, Includes the following steps: Step 1: Monitor the suspended particle concentration, turbidity, ultraviolet transmittance and water flow velocity of ballast water in real time using sensors, and establish a water quality analysis model. Step 2: Employ an intelligent feedback control mechanism to dynamically adjust filtration accuracy, backwashing frequency, and UV dosage requirements based on real-time water quality data; Step 3: Employ a machine learning-based optimization model, utilizing support vector regression and long short-term memory networks to predict the optimal filtration accuracy and UV sterilization parameters, and optimize the processing strategy based on historical data; Step 4: Adopt an adaptive flow rate regulation mechanism, and combine quantitative control PID control, fuzzy control and genetic algorithm to optimize the flow control valve and variable frequency pump, so that the water flow rate is kept within the optimal working range of ultraviolet sterilization; Step 5: Adopt a dynamic energy consumption optimization strategy, combine water quality monitoring data, adjust the power of ultraviolet lamps and filtration energy consumption, and reduce overall energy consumption while ensuring treatment effect.

2. The method for coordinated control of filtration and ultraviolet sterilization in a purely physical ballast water management system according to claim 1, characterized in that, Step 2 specifically includes: Step 21: Real-time water quality monitoring and data acquisition: A turbidity sensor is used to monitor the turbidity of the ballast water in real time, and a particulate matter concentration sensor is used to monitor the suspended particulate matter concentration of the ballast water in real time. The ultraviolet light transmittance is measured using an ultraviolet transmittance sensor, and the ultraviolet light dose is calculated. in, Ultraviolet light dose, Ultraviolet light intensity, This refers to the irradiation time; Water flow velocity is detected using a flow velocity sensor. Ensure the water stays in the UV sterilization unit for the required time. The following conditions must be met: in, The effective length of the ultraviolet sterilization unit; Step 22: Dynamically adjust filter parameters: When the concentration of suspended particles is higher than the threshold It will automatically improve the filtration accuracy. Level or increase backwash frequency ; When the turbidity after filtration If the water flow rate is still higher than the set value, reduce the water flow rate. To improve filtration efficiency; Step 23: Adjust UV sterilization power Calculate UV dose requirements in, This is an empirical coefficient, adjusted according to different water qualities; According to ultraviolet dose requirements Adjust UV lamp power in, For maximum ultraviolet power, The target UV dose; Step 24: Adaptive Flow Control Calculate the optimal flow velocity range in, This is the optimal UV sterilization dwell time; The water flow rate is automatically adjusted by a variable frequency pump and a flow control valve. To match the optimal UV sterilization dwell time; Step 25: Abnormal handling mechanism When the turbidity after filtration Continuously higher than the turbidity set value If so, an alarm will be triggered and the filtering mode will be adjusted; When the survival rate of the ultraviolet sterilization unit organisms Exceeding the survival rate setting value Increase the power of the ultraviolet lamp. Or reduce the flow rate.

3. The method for coordinated control of filtration and ultraviolet sterilization in a purely physical ballast water management system according to claim 1, characterized in that, Step 3 specifically includes: Step 31: Data Acquisition and Feature Engineering Collect water quality data before and after filtration, including the concentration of suspended particles before filtration. Concentration of suspended particles after filtration Turbidity before filtration (NTU), turbidity after filtration UV transmittance (UVT) after filtration, water flow velocity UV lamp power and sterilization rate after filtration ; Principal component analysis (PCA) was used for dimensionality reduction to extract key influencing factors. : ,in The dimension reduction transformation matrix is The original data feature matrix; Step 32: Model Training and Optimization Support Vector Regression (SVR) is used to predict the optimal filtering accuracy. and UV dose requirements ; Training objectives: ,in The sterilization rate predicted by the model. Sterilization is performed after filtration; N represents a summary of historical data samples, and i represents the sample index; Cross-validation is used to improve the model's generalization ability; Step 33: Real-time forecasting and dynamic adjustment: Calculate the current water quality state vector : LSTM network is used to predict the optimal filtering accuracy at the next time step. And the optimal UV dose requirement at the next moment : Where f is the LSTM network mapping function, For model parameters; determine the optimal filtering accuracy at the next time step. Applied to the filtration module, adjusting precision; optimal UV dose requirement at the next moment. Adjust UV lamp power ; Step 34: Reinforcement learning optimizes the control strategy: Deep reinforcement learning (DQN) is used to optimize the filtering and UV sterilization strategies; Reward function design : ,in, The total energy consumption of the ballast water management system. For weight coefficients; during training, the agent learns the optimal control strategy through trial and error to maximize the sterilization rate and minimize energy consumption; Step 35: Ballast Water Management System Deployment and Adaptive Optimization We continuously update our machine learning models through online learning to adapt to different water quality environments. By combining historical ballast water data of ships, a personalized optimization model is established to improve the adaptability to different routes.

4. The method for coordinated control of filtration and ultraviolet sterilization in a purely physical ballast water management system according to claim 1, characterized in that, Step 4 specifically includes: Step 41: Flow rate monitoring and data acquisition; Step 42: Adaptive flow velocity calculation: Optimal flow rate calculate: ; Indicates the optimal UV sterilization dwell time; When the residence time in the ultraviolet sterilization unit At this time, the water flow rate needs to be increased. To avoid excessive energy consumption due to excessive radiation; When the residence time in the ultraviolet sterilization unit At that time, reduce the water flow speed To ensure sterilization effectiveness; Step 43: Flow rate regulation and control strategy: Adaptive adjustment is achieved using fuzzy control. Set the fuzzy control input variable: current flow rate UV transmittance (UVT) after filtration and NTU turbidity before filtration; set control rules: If the UV transmittance (UVT) is low after filtration and the NTU (turbidity) is high before filtration, then reduce the water flow rate. ; If the UV transmittance (UVT) is high after filtration and the NTU (turbidity) is low before filtration, then increase the water flow rate. ; Adjustment range is calculated using fuzzy inference. in, It is the target flow rate; Step 44: Closed-loop control and optimization Set up an error feedback mechanism: in, Indicates the current flow rate. These are the PID control parameters; if the error If the error is too large, the controller will adaptively and quickly adjust the flow rate; if the error is small, it will adjust slowly to ensure a stable flow rate. Step 45: Ballast water management system optimization and dynamic adjustment.

5. The method for coordinated control of filtration and ultraviolet sterilization in a purely physical ballast water management system according to claim 1, characterized in that, Step 5 specifically includes: Step 51: Energy consumption modeling and objective function: The total energy consumption of the ballast water management system mainly consists of the energy consumption of the filtration unit. Energy consumption of UV sterilization unit composition: ; Filter unit energy consumption Water flow velocity and backwash frequency Influence: ,in, For flow velocity correlation coefficient, This refers to the backwashing energy consumption coefficient. Energy consumption of UV sterilization unit Power of ultraviolet lamp Influence of UV transmittance (UVT): ; The goal is to minimize the total energy consumption of the ballast water management system. At the same time, it meets the sterilization rate after filtration. constraint: s. t. , Indicates the minimum sterilization rate; Step 52: Energy optimization strategy based on reinforcement learning: A deep reinforcement learning (DQN) approach is adopted to optimize the synergistic energy consumption control strategy of filtering and ultraviolet sterilization. State variables Water quality parameters (NTU, UVT, C), current flow rate UV lamp power ; Action space Adjust V, F and ; reward function : ,in, As a penalty factor; During training, the agent learns the optimal strategy based on historical data and continuously updates it online; Step 53: Dynamically adjust the UV lamp power: Calculate the optimal UV lamp power ; When the UV transmittance (UVT) is high, reduce the UV lamp power. To reduce energy consumption; Sterilization rate after filtration Increase the UV lamp power as it descends. To ensure sterilization effectiveness; Step 54: Collaborative Optimization Strategy: Optimization using a genetic algorithm (GA) Parameter combinations; Fitness function: ; The optimal energy consumption scheme is searched using selection, crossover, and mutation operations. Step 55: System Online Adaptive Optimization: By combining reinforcement learning and genetic algorithms, the energy consumption optimization strategy is dynamically updated. Predictive maintenance is employed to prevent performance degradation caused by long-term system operation.

Images