Intelligent linkage control method for avionics hub flood discharge gate

Abstract

The invention provides an intelligent linkage control method for a flood discharge gate of an avionics hub, and the method comprises the steps: collecting and preprocessing hydrological, meteorological and shipping multi-source data through a sensor, and eliminating data noise and scale difference. And constructing a multi-factor evaluation model by utilizing machine learning or fuzzy mathematics, and calculating a flood discharge risk and shipping influence evaluation value by taking the preprocessed data as input. A control strategy is made according to the evaluation value and a preset rule, the gates are grouped and sorted, and the opening sequence, height and time are determined through an intelligent linkage algorithm. In flood discharge, key parameters are monitored in real time, actual and expected targets are compared, control strategies and parameters are adjusted, and historical data are collected regularly to optimize a model and an algorithm. According to the method, the flood discharge efficiency and accuracy are improved, the operation safety is enhanced, the shipping demand is considered, and the system adaptability and stability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation and power hub engineering, and in particular to an intelligent linkage control method for flood discharge gates of a navigation and power hub. Background Art

[0002] As a multifunctional water conservancy project integrating navigation, power generation, and flood control, navigation and power hubs play a vital role in the comprehensive utilization of water resources and regional economic development. The precise and efficient control of flood discharge gates, a core component of navigation and power hubs, is directly related to the safe operation of the hubs, as well as flood control safety, smooth navigation, and ecological stability in downstream areas. However, current control technology for flood discharge gates in navigation and power hubs still has numerous shortcomings, making it difficult to meet the increasingly complex and changing needs of the environment.

[0003] Traditional floodgate control at navigation and power hubs relies heavily on manual experience. This approach relies heavily on the operator's personal experience and subjective judgment. When a flood approaches, operators must use their own experience and limited observational data to determine the number, height, and timing of floodgate openings.

[0004] However, under complex flood conditions, the onset, scale, and dynamics of floods are often highly uncertain, making it difficult for human experience to fully and accurately grasp their dynamic characteristics. Operators may misjudge the flood situation, resulting in untimely or excessive flood releases. Failure to release water in a timely manner will cause reservoir water levels to continue to rise, increasing safety risks at the hub and potentially even causing a serious dam failure. Excessive flood releases can cause unnecessary impacts on the downstream ecological environment, shipping, and residents, such as causing a sharp rise in water levels and inundating farmland and residential areas.

[0005] Furthermore, manual control is subject to the operator's expertise, work status, and psychological factors, making it difficult to ensure the consistency and stability of control decisions. Furthermore, manual control is relatively slow, and in the event of a rapidly developing flood, effective response measures may not be implemented in a timely manner, thus delaying the release of floodwaters.

[0006] With the development of automation technology, some navigation and power hubs have adopted simple automated control methods. This control method typically opens or closes a single gate based on a preset water level threshold. When the reservoir water level reaches a certain threshold, the corresponding flood discharge gate automatically opens; when the water level drops to a certain level, the gate closes.

[0007] While this simple automated control approach has improved the efficiency and accuracy of flood gate control to a certain extent, it still has significant limitations. It only considers the reservoir water level, ignoring numerous other factors crucial to flood release decisions, such as inflow, downstream water levels, rainfall, and shipping demand. In reality, these factors are interconnected and mutually influential, collectively determining the optimal timing and method of flood release.

[0008] Existing flood gate control systems are unable to achieve intelligent linkage between multiple flood gates. Each gate opens and closes independently, lacking overall coordination and cooperation. This fails to fully utilize the overall efficiency of the flood discharge system, resulting in an unstable and inefficient flood discharge process.

[0009] Most existing flood gate control methods lack the comprehensive analysis and utilization of real-time hydrological and meteorological information, as well as upstream and downstream shipping demand. Hydrological data on inflow and outflow can reflect the dynamic trends of floods, while meteorological data on rainfall, wind speed, and direction can be used to predict flood development. Upstream and downstream shipping demand influences the impact of flood discharge operations on shipping.

[0010] However, current control methods often process this information in isolation, failing to integrate it for comprehensive analysis. This results in a lack of comprehensiveness and foresight in control decisions, making it impossible to dynamically adjust flood discharge strategies based on actual conditions. Faced with complex and changing flood scenarios and shipping demands, existing control methods are insufficient to achieve optimal operation of navigation and power hubs. Therefore, we address this issue by proposing an intelligent linkage control method for flood discharge gates in navigation and power hubs. Summary of the Invention

[0011] The purpose of the present invention is to address the problems raised by the existing background technology. In order to achieve the above-mentioned invention purpose, the present invention provides the following technical solutions: a method for intelligent linkage control of flood discharge gates of a navigation and power hub, comprising the following steps:

[0012] Step 1: Data collection and preprocessing: Sensors installed in and around the navigation and power hub collect hydrological data, meteorological data, and upstream and downstream shipping information in real time, and clean, filter, and normalize the collected data.

[0013] Step 2: Establish a multi-factor evaluation model: Determine the main factors affecting flood gate control as evaluation indicators, and use machine learning algorithms or fuzzy mathematics methods to construct a multi-factor evaluation model with pre-processed multi-source data as input and flood discharge risk assessment values ​​and shipping impact assessment values ​​as output;

[0014] Step 3: Real-time assessment and decision-making: Input the real-time collected and pre-processed data into the multi-factor assessment model to calculate the current flood discharge risk assessment value and shipping impact assessment value. Based on these values ​​and preset decision-making rules, the flood discharge gate control strategy is formulated;

[0015] Step 4: Intelligent linkage control: The gates are grouped and sorted according to their layout and functions. Based on the flood discharge gate control strategy, an intelligent linkage control algorithm is used to determine the opening sequence, opening height, and opening time of each group of gates.

[0016] Step 5. Feedback and optimization: Monitor changes in key parameters in real time during the flood discharge process, compare actual data with expected targets, adjust flood discharge gate control strategies and linkage parameters based on deviations, and regularly collect historical data to optimize the multi-factor evaluation model and linkage control algorithm.

[0017] As a preferred technical solution of the present invention, the hydrological data includes reservoir water level, inflow and outflow, the meteorological data includes rainfall, wind speed and wind direction, and the upstream and downstream shipping information includes ship flow and ship tonnage.

[0018] As a preferred technical solution of the present invention, the main factors affecting the control of the flood discharge gate are determined as evaluation indicators, specifically including reservoir water level, inflow flow, downstream water level, rainfall and shipping demand.

[0019] As a preferred technical solution of the present invention, the machine learning algorithm is a neural network algorithm or a support vector machine algorithm.

[0020] As a preferred technical solution of the present invention, the preset decision rules are adjusted according to different flood scenarios and operation objectives, giving priority to ensuring hub safety when the flood discharge risk is high, and taking into account shipping needs when the flood discharge risk is low.

[0021] As a preferred technical solution of the present invention, the principle of grouping the gates takes into account the location of the gates, flood discharge capacity and impact on upstream and downstream water levels.

[0022] As a preferred technical solution of the present invention, the intelligent linkage control algorithm is dynamically adjusted according to real-time data.

[0023] As a preferred technical solution of the present invention, the key parameters include reservoir water level, outflow flow and downstream water level.

[0024] As a preferred technical solution of the present invention, the data cleaning is to remove erroneous data and noise data in the collected data.

[0025] As a preferred technical solution of the present invention, the data preprocessing includes filtering, outlier removal, and data normalization operations.

[0026] Compared with existing technologies, the present invention offers the following advantages: The intelligent linkage control method of the present invention, by scientifically grouping and sequencing flood discharge gates and applying an intelligent linkage control algorithm, can dynamically adjust the opening sequence, height, and timing of each group of gates based on real-time hydrological, meteorological, and shipping information. This enables multiple flood discharge gates to coordinate and operate together, forming an organic whole, greatly improving flood discharge efficiency. For example, in the face of a large flood, multiple appropriate gates can be opened quickly and orderly, allowing floodwater to be discharged quickly and smoothly, avoiding flood discharge delays caused by improper operation of a single gate or uncoordinated operation of multiple gates.

[0027] This invention utilizes a multi-factor assessment model that comprehensively considers factors such as reservoir water level, inflow, downstream water level, and rainfall, enabling accurate assessment of flood discharge risk. This allows for the development of precise flood discharge strategies tailored to different flood scenarios and risk levels. During minor floods, the discharge flow can be precisely controlled to avoid unnecessary downstream impacts caused by excessive discharge. During major floods, flood discharge can be promptly increased to ensure the safety of the hub. This precise control approach effectively improves the hub's ability to respond to diverse flood situations and reduces flood losses.

[0028] This system monitors key parameters such as reservoir water level, outflow rate, and downstream water level in real time and compares them with expected targets. If deviations between actual data and expectations are detected, the control strategy and linkage parameters of the flood discharge gates can be adjusted promptly, achieving closed-loop control of the flood discharge process. This real-time, dynamic monitoring and adjustment mechanism can promptly identify and resolve problems that arise during the flood discharge process, such as abnormal water level rise and unstable flow rate. This effectively avoids safety incidents caused by improper flood discharge and ensures the safe and stable operation of the navigation and power hub.

[0029] The intelligent linkage control method of this invention is based on scientific models and algorithms, and uses large amounts of real-time data for analysis and decision-making, reducing human interference. The system can objectively and accurately assess flood discharge risks and formulate control strategies, significantly reducing safety hazards caused by human decision-making errors.

[0030] Through intelligent linkage control, this invention makes the flood discharge process smoother and more controllable, reducing the dramatic impact of flood discharge on downstream water levels and flow velocities. This provides a relatively stable water environment for navigation, reduces navigation risks, and ensures the continuity and safety of shipping. It also reduces the economic losses to shipping caused by flood discharge, promoting the healthy development of the shipping industry.

[0031] Historical data is regularly collected to optimize and update the multi-factor assessment model and linkage control algorithm. With the continuous accumulation of data and feedback from actual operations, the model learns more patterns and characteristics, and the algorithm is continuously improved and refined. This enables the system to better adapt to different flood scenarios and complex and changing environmental conditions, improving its adaptability and stability.

[0032] The control method of this invention can cope with a variety of complex and changing operating conditions. Whether it's a sudden rainstorm or flood, or long-term water level fluctuations, the system can make accurate judgments and decisions based on real-time data, ensuring the normal operation of the navigation and power hub in all situations, demonstrating strong anti-interference capabilities and the ability to cope with complex situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 The present invention provides a flow chart of the method. DETAILED DESCRIPTION

[0034] To make the purpose, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0035] Therefore, the following detailed description of the embodiments of the present invention is not intended to limit the scope of the invention claimed for protection, but merely represents some embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions in the embodiments can be combined with each other. It should be noted that similar numbers and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0036] Example 1: A method for intelligent linkage control of flood discharge gates of a navigation and power hub, comprising the following steps: Step 1, data collection and preprocessing: real-time collection of hydrological data, meteorological data, and upstream and downstream shipping information through sensors installed in and around the navigation and power hub, and cleaning, filtering, and normalization of the collected data;

[0037] Step 2: Establish a multi-factor evaluation model: Determine the main factors affecting flood gate control as evaluation indicators, and use machine learning algorithms or fuzzy mathematics methods to construct a multi-factor evaluation model with pre-processed multi-source data as input and flood discharge risk assessment values ​​and shipping impact assessment values ​​as output;

[0038] Step 3: Real-time assessment and decision-making: Input the real-time collected and pre-processed data into the multi-factor assessment model to calculate the current flood discharge risk assessment value and shipping impact assessment value. Based on these values ​​and preset decision-making rules, the flood discharge gate control strategy is formulated;

[0039] Step 4: Intelligent linkage control: The gates are grouped and sorted according to their layout and functions. Based on the flood discharge gate control strategy, an intelligent linkage control algorithm is used to determine the opening sequence, opening height, and opening time of each group of gates.

[0040] Step 5. Feedback and optimization: Monitor changes in key parameters in real time during the flood discharge process, compare actual data with expected targets, adjust flood discharge gate control strategies and linkage parameters based on deviations, and regularly collect historical data to optimize the multi-factor evaluation model and linkage control algorithm.

[0041] Hydrological data includes reservoir water level, inflow and outflow; meteorological data includes rainfall, wind speed and wind direction; upstream and downstream shipping information includes ship flow and ship tonnage.

[0042] Key factors influencing floodgate control are identified as evaluation indicators, including reservoir water level, inflow, downstream water level, rainfall, and shipping demand. Machine learning algorithms are either neural networks or support vector machines. Pre-set decision rules are adjusted based on different flood scenarios and operational objectives, prioritizing hub safety when flood risk is high and balancing shipping demand when risk is low. Gate grouping is based on gate location, flood discharge capacity, and impact on upstream and downstream water levels.

[0043] Intelligent linkage control algorithms dynamically adjust based on real-time data. Key parameters include reservoir water level, outflow, and downstream water level. Data cleaning removes erroneous and noisy data from collected data. Data preprocessing includes filtering, outlier removal, and data normalization.

[0044] The Python algorithm code for the intelligent linkage control method of the flood discharge gates of the navigation and power hub is as follows:

[0045]

[0046]

[0047]

[0048]

[0049]

[0050]

[0051] Code Explanation:

[0052] Data collection and preprocessing: simulate the collection of hydrological data, meteorological data and upstream and downstream shipping information, and perform data cleaning and normalization.

[0053] Establish a multi-factor assessment model: Use a neural network algorithm to construct a multi-factor assessment model with pre-processed multi-source data as input and flood discharge risk assessment values ​​and shipping impact assessment values ​​as output.

[0054] Real-time evaluation and decision-making: The real-time collected and pre-processed data is input into the multi-factor evaluation model, and the flood discharge gate control strategy is formulated based on the calculation results and preset decision rules.

[0055] Intelligent linkage control: Determine the opening sequence, opening height and opening time of each group of gates based on the flood discharge gate control strategy.

[0056] Feedback and optimization: Real-time monitoring of key parameter changes during the flood discharge process, and adjustment of flood discharge gate control strategies and linkage parameters based on deviations.

[0057] Working Principle of the Intelligent Linkage Control Method for Floodgates at Navigation and Power Hubs: This intelligent linkage control method for floodgates at navigation and power hubs aims to achieve efficient and precise control of floodgates, taking into account multiple factors to ensure the safe operation of the hub and address upstream and downstream shipping needs. Its core working principle is to build a scientific evaluation model for real-time decision-making through comprehensive data collection and processing, utilize intelligent linkage algorithms to control gate movement, and continuously optimize the control process through feedback mechanisms. The following is a detailed explanation of the working principles of each link:

[0058] Data Collection and Preprocessing Principles: Data Collection: Various sensors, such as water level sensors, flow sensors, weather station equipment, and shipping monitoring devices, are strategically placed in and around the navigation and power hub. These sensors utilize their respective physical principles to collect different types of data in real time. For example, water level sensors, based on the principle of pressure sensing, convert water pressure into an electrical signal, which is then converted into water level height. Flow sensors calculate flow by measuring water velocity based on the relationship between flow velocity and cross-sectional area. Weather stations utilize various meteorological sensors to measure meteorological parameters such as rainfall, wind speed, and wind direction. Shipping monitoring equipment utilizes radar and camera technology to obtain information on the flow and tonnage of upstream and downstream vessels.

[0059] The data collected by the present invention may contain noise, erroneous values, or have different scale ranges due to different data sources. The data cleaning process uses preset rules and algorithms to identify and remove obviously erroneous or abnormal data points to ensure data accuracy. Filtering operations, such as Kalman filtering, smooth the data, reduce the interference of random noise, and make the data more stable. Normalization processing uniformly maps data of different types and ranges to the interval [0, 1], eliminating the impact of data scale differences on subsequent analysis and facilitating subsequent model processing and calculation.

[0060] The multi-factor evaluation model establishes principles for determining evaluation indicators. Key factors influencing the flood discharge process at a navigation and hydropower hub are comprehensively considered. For example, reservoir water levels reflect the current state of the reservoir's water storage; inflows determine the rate of reservoir water growth; downstream water levels influence the downstream impact of flood discharges; rainfall is an important indicator for predicting future inflows; and shipping demand reflects the impact of flood discharges on upstream and downstream shipping. Using these factors as evaluation indicators can comprehensively and objectively reflect the actual situation during the flood discharge process.

[0061] The present invention adopts machine learning algorithms, including neural networks, support vector machines or fuzzy mathematics methods to construct a multi-factor evaluation model. Taking neural networks as an example, its working principle is to simulate the working mode of neurons in the human brain, train through a large amount of historical data, and adjust the connection weights and thresholds between each neuron in the network. During the training process, the model continuously learns the mapping relationship between input data (pre-processed multi-source data) and output results (flood risk assessment value and shipping impact assessment value), so that the corresponding assessment value can be accurately calculated based on the real-time input data. The fuzzy mathematics method is based on fuzzy sets and fuzzy logic, which fuzzifies the boundaries of influencing factors and obtains evaluation results through fuzzy rules and reasoning mechanisms. It is more suitable for dealing with practical problems with uncertainty and ambiguity.

[0062] This method feeds real-time, pre-processed data into a trained multi-factor assessment model. Based on the learned mapping relationships, the model assesses the current flood discharge risk and navigation impact. The flood discharge risk assessment reflects the current flood discharge pressure and potential danger faced by the reservoir, while the navigation impact assessment reflects the degree of disruption to upstream and downstream navigation caused by the flood discharge.

[0063] The preset decision rules of the present invention are formulated according to different flood scenarios and operational objectives. In actual applications, the flood discharge risk assessment value and the shipping impact assessment value obtained based on real-time assessment are compared with the preset thresholds. When the flood discharge risk assessment value exceeds the high-risk threshold, it means that the reservoir is facing a greater security threat. At this time, priority is given to ensuring the safety of the hub, and the decision rule will tend to open a sufficient number of flood discharge gates to quickly lower the reservoir water level; when the flood discharge risk assessment value is between the low-risk threshold and the high-risk threshold, while ensuring the safety of the hub, the flood discharge flow is reasonably adjusted taking into account the shipping needs; when the flood discharge risk assessment value is lower than the low-risk threshold, it means that the reservoir is in good safety condition. At this time, the flood discharge flow is appropriately reduced to meet the maximum demand of shipping.

[0064] This invention divides flood discharge gates at navigation and power hubs into different groups based on their layout and functional characteristics. This grouping primarily considers gate location, flood discharge capacity, and impact on upstream and downstream water levels. For example, gates with similar geographical locations and functions are grouped together. Within each group, gates are prioritized, with gates with high flood discharge capacity and minimal impact on upstream and downstream water levels being prioritized for opening. This ensures effective flood discharge while minimizing drastic fluctuations in upstream and downstream water levels.

[0065] This invention utilizes intelligent linkage control algorithms, such as fuzzy control algorithms, to dynamically calculate the opening sequence, height, and time for each gate group based on the flood discharge gate control strategy and real-time hydrological data and shipping information. The fuzzy control algorithm fuzzifies the input real-time data by setting a series of fuzzy rules and membership functions. It then uses fuzzy inference to derive appropriate control decisions. Finally, the decision results are defuzzified to determine the specific gate control parameters. During the control process, the algorithm continuously adjusts the control parameters based on changes in real-time data to ensure a smooth and efficient flood discharge process.

[0066] During the flood discharge process, the present invention uses sensors installed in the reservoir and river channel to monitor changes in key parameters such as reservoir water level, outflow rate, and downstream water level in real time. These sensors continuously transmit monitoring data to the control center, providing a basis for subsequent feedback adjustments.

[0067] The control center of the present invention compares the actual data monitored in real time with the expected target and calculates the deviation. If the deviation exceeds the allowable range, it indicates that the current flood discharge control strategy may be unreasonable and requires timely adjustment. For example, if the reservoir water level drops too slowly, the gate opening height may need to be increased or more gates may need to be opened; if the downstream water level rises too quickly, the flood discharge flow rate may need to be appropriately reduced. Through continuous comparison and adjustment, closed-loop control of the flood discharge process is achieved, ensuring that the flood discharge operation meets the expected goals.

[0068] This invention regularly collects historical data, including hydrological data, meteorological data, shipping information, and flood gate control parameters. This new historical data is used to retrain and optimize the multi-factor assessment model and linkage control algorithm. During the retraining process, the model learns more about actual operating conditions and changing patterns, adjusts its structure and parameters, and improves its accuracy and algorithm adaptability, thereby better responding to different future flood scenarios and operational requirements.

[0069] The intelligent linkage control method for flood discharge gates at the navigation and power hub works as follows: Various sensors are installed in and around the hub for data collection. Water level sensors are located at various locations within the reservoir and at key locations in the downstream river. They measure water pressure and convert it into electrical signals to accurately obtain reservoir and downstream water level data. Flow sensors are installed at key inlet and outlet channels. Based on the relationship between flow velocity and cross-sectional area, they use electromagnetic induction or ultrasonic principles to measure water flow velocity and calculate inlet and outlet flows. A meteorological station is equipped with rain gauges, anemometers, and wind vanes to collect real-time meteorological information on rainfall, wind speed, and wind direction. Furthermore, shipping monitoring equipment is installed in upstream and downstream waterways, using radar and cameras to monitor and count vessel traffic and tonnage. All of these sensors and equipment transmit the collected data to a data collection center in real time.

[0070] The present invention first performs data cleaning at the data collection center. Pre-set rules, such as determining whether the data exceeds a reasonable range or whether there are significant mutations, are used to identify and eliminate erroneous and noisy data from the collected data. Next, the data is filtered using a Kalman filter algorithm. Kalman filtering predicts and estimates the true value of the data based on its historical state and current measurements, effectively reducing random fluctuations in the data and making it smoother and more stable. Finally, different types of data are normalized. Water level, flow, and rainfall data are uniformly mapped to the interval [0, 1], eliminating data scale differences and providing a unified standard for subsequent analysis and processing.

[0071] Taking into account the actual flood discharge situation and needs of the navigation and power hub, reservoir water level, inflow, downstream water level, rainfall, and shipping demand are identified as the main evaluation indicators affecting flood discharge gate control. These indicators can comprehensively reflect the operating status of the navigation and power hub, flood situation, and shipping demand.

[0072] A multi-factor assessment model was constructed using a neural network algorithm. First, preprocessed multi-source data was fed into the neural network as neurons in the input layer. The network then had several hidden layers, each containing multiple neurons, which were used to extract features and perform nonlinear mapping on the input data. The output layer contained two neurons, one corresponding to the flood risk assessment value and the other to the shipping impact assessment value. The neural network was trained using a large amount of historical data. By continuously adjusting the connection weights and thresholds between the neurons in the network, the model was able to accurately calculate the flood risk assessment value and the shipping impact assessment value based on the input data.

[0073] Real-time, pre-processed data is fed into a trained multi-factor assessment model. Based on the learned mapping relationships, the model assesses the current flood risk and shipping impact. Through comprehensive analysis and calculation of multiple assessment indicators, it derives flood risk and shipping impact assessments, providing a basis for subsequent decision-making.

[0074] Different decision-making rules are pre-set, with decisions made based on comparisons of the flood discharge risk assessment and navigation impact assessment with pre-set thresholds. When the flood discharge risk assessment exceeds the high-risk threshold, indicating a significant reservoir safety threat, the safety of the reservoir is prioritized, with the decision to open a sufficient number of flood discharge gates to rapidly lower the reservoir water level. When the flood discharge risk assessment falls between the low-risk and high-risk thresholds, the flood discharge flow rate is appropriately adjusted, while ensuring the safety of the reservoir and taking into account navigation needs. When the flood discharge risk assessment falls below the low-risk threshold, indicating a good reservoir safety, the flood discharge flow rate is appropriately reduced to meet the maximum shipping demand.

[0075] The flood discharge gates at the navigation and power hub are divided into different groups based on their layout and functional characteristics. They are geographically divided into upstream, midstream, and downstream groups. The gates in each group are ranked based on their discharge capacity and impact on upstream and downstream water levels. Gates with high discharge capacity and minimal impact on upstream and downstream water levels are prioritized for opening to improve discharge efficiency and minimize impact on the surrounding environment.

[0076] This invention uses a fuzzy control algorithm to achieve intelligent linkage control of gates. Based on the flood discharge gate control strategy and real-time hydrological data and shipping information, the input data is fuzzified and mapped into different fuzzy sets. Then, reasoning is performed based on preset fuzzy rules to arrive at the corresponding control decisions. Finally, the fuzzy decision results are defuzzified to determine the specific opening sequence, opening height, and opening time for each group of gates. During the control process, the algorithm continuously adjusts the control parameters based on changes in real-time data to ensure a smooth and efficient flood discharge process.

[0077] During the flood discharge process, the present invention continuously monitors changes in key parameters such as reservoir water level, outflow rate, and downstream water level in real time through sensors installed in the reservoir and river channel. The sensors transmit the monitoring data to the control center in real time, allowing the actual status of the flood discharge process to be monitored in a timely manner.

[0078] The control center of the present invention compares the actual data monitored in real time with the expected target and calculates the deviation. If the deviation exceeds the allowable range, the current flood discharge control strategy may need to be adjusted. For example, if the reservoir water level drops too slowly, the gate opening height may need to be increased or more gates may need to be opened; if the downstream water level rises too quickly, the flood discharge flow rate may need to be appropriately reduced. Based on the deviation, the control strategy and linkage parameters of the flood discharge gates are adjusted in a timely manner to achieve closed-loop control of the flood discharge process.

[0079] This method regularly collects historical data, including hydrological and meteorological data, shipping information, and flood gate control parameters. This new historical data is used to retrain and optimize the multi-factor assessment model and linkage control algorithm. By adjusting the model's structure and parameters, the model can better adapt to different flood scenarios and operational requirements, improving the model's accuracy and the algorithm's adaptability.

[0080] The above embodiments are only used to illustrate the present invention and are not intended to limit the technical solutions described in the present invention. Although this specification has described the present invention in detail with reference to the above embodiments, the present invention is not limited to the above specific implementation methods. Therefore, any modification or replacement of the present invention; and all technical solutions and improvements thereof that do not depart from the spirit and scope of the invention are included in the scope of the claims of the present invention.

Claims

1. An intelligent linkage control method for flood discharge gates of a navigation and power hub, characterized in that: The following steps are involved: Step 1: Data collection and preprocessing: Sensors installed in and around the navigation and power hub collect hydrological data, meteorological data, and upstream and downstream shipping information in real time, and clean, filter, and normalize the collected data. Step 2: Establish a multi-factor evaluation model: Determine the main factors affecting flood gate control as evaluation indicators, and use machine learning algorithms or fuzzy mathematics methods to construct a multi-factor evaluation model with pre-processed multi-source data as input and flood discharge risk assessment values ​​and shipping impact assessment values ​​as output; Step 3: Real-time assessment and decision-making: Input the real-time collected and pre-processed data into the multi-factor assessment model to calculate the current flood discharge risk assessment value and shipping impact assessment value. Based on these values ​​and preset decision-making rules, the flood discharge gate control strategy is formulated; Step 4: Intelligent linkage control: The gates are grouped and sorted according to their layout and functions. Based on the flood discharge gate control strategy, an intelligent linkage control algorithm is used to determine the opening sequence, opening height, and opening time of each group of gates. Step 5. Feedback and optimization: Monitor changes in key parameters in real time during the flood discharge process, compare actual data with expected targets, adjust flood discharge gate control strategies and linkage parameters based on deviations, and regularly collect historical data to optimize the multi-factor evaluation model and linkage control algorithm.

2. The intelligent linkage control method for flood discharge gates of a navigation and power hub according to claim 1 is characterized in that: The hydrological data includes reservoir water level, inflow and outflow; the meteorological data includes rainfall, wind speed and wind direction; and the upstream and downstream shipping information includes ship flow and ship tonnage.

3. The intelligent linkage control method for flood discharge gates of a navigation and power hub according to claim 1 is characterized in that: The main factors affecting flood discharge gate control are determined as evaluation indicators, specifically including reservoir water level, inflow flow, downstream water level, rainfall and shipping demand.

4. The intelligent linkage control method for flood discharge gates of a navigation and power hub according to claim 1 is characterized in that: The machine learning algorithm is a neural network algorithm or a support vector machine algorithm.

5. The intelligent linkage control method for flood discharge gates of a navigation and power hub according to claim 1 is characterized in that: The preset decision rules are adjusted according to different flood scenarios and operational objectives, giving priority to hub safety when the flood discharge risk is high, and taking into account shipping needs when the flood discharge risk is low.

6. The intelligent linkage control method for flood discharge gates of a navigation and power hub according to claim 1 is characterized in that: The principle of grouping gates takes into account the location of the gates, flood discharge capacity and impact on upstream and downstream water levels.

7. The intelligent linkage control method for flood discharge gates of a navigation and power hub according to claim 1 is characterized in that: The intelligent linkage control algorithm is dynamically adjusted according to real-time data.

8. The intelligent linkage control method for flood discharge gates of a navigation and power hub according to claim 1 is characterized in that: The key parameters include reservoir water level, outflow and downstream water level.

9. The method for intelligent linkage control of flood discharge gates of a navigation and power hub according to claim 1, characterized in that: The data cleaning is to remove erroneous data and noise data from the collected data.

10. The method for intelligent linkage control of flood discharge gates of a navigation and power hub according to claim 1, characterized in that: The data preprocessing includes filtering, outlier removal, and data normalization operations.

Images