Intelligent collaborative control method for ship lock water delivery based on hydraulic simulation

Abstract

The application discloses a ship lock water delivery intelligent collaborative control method based on a hydraulic simulation and relates to the technical field of ship lock hydrodynamics. The application collects hydraulic data such as speed, acceleration and blockage ratio in the ship water delivery process, constructs discrete hydraulic states and calculates attribution coefficients; in combination with historical transfer frequency and physical conservation law verification, a state transfer matrix reflecting state evolution law is established; the future hydraulic state probability distribution is deduced by using a Markov chain model, and then a mooring force threat coefficient is calculated to quantify the risk. The method dynamically adjusts the valve opening degree based on the prediction result, realizes intelligent collaborative control with prediction ability, changes passive response into active prevention, and improves the operation safety and efficiency of the ship lock.

Description

Technical Field

[0001] This application relates to the field of ship lock hydrodynamics technology, and in particular to a smart collaborative control method for ship lock water conveyance based on hydrodynamic simulation. Background Technology

[0002] The lock water conveyance system refers to a complete set of facilities that realize the filling and emptying of the lock chamber. It mainly includes components such as the inlet, water conveyance corridor, valve section, outlet and energy dissipation facilities. The core task of the lock water conveyance system is to complete the filling and emptying of the lock chamber in a short time and safely so as to enable ships to pass.

[0003] Mooring force refers to the tension exerted by a ship on the mooring system via cables, and is a key indicator of ship berthing safety. During the water conveyance process in a lock, the non-constant movement of water flow within the lock chamber exerts a pushing and pulling effect on the ship, which is transmitted to the mooring system via cables to form mooring force.

[0004] One of the core constraints of intelligent water conveyance control in ship locks is to keep the mooring force within a safe threshold. By predicting the flow field under different valve opening schemes through hydraulic simulation, the mooring force can be estimated, and the valve opening and closing can be dynamically adjusted to achieve "stable water conveyance".

[0005] The existing emergency protection system based on mooring force monitoring during the water conveyance process of the lock usually adopts a reactive response mode of "over-limit alarm - emergency shutdown". This passive response mode lacks the ability to predict and actively control the trend of mooring force changes in advance, and cannot achieve the prevention of risks in advance. The resulting response lag may affect the safety of the ship. Summary of the Invention

[0006] Therefore, it is necessary to provide a smart collaborative control method for water conveyance in ship locks based on hydraulic simulation to address the aforementioned technical problems.

[0007] The following technical solution is adopted in this specification: This manual provides a method for intelligent collaborative control of water conveyance in ship locks based on hydraulic simulation, including: The system acquires hydraulic data of the vessel at each moment during multiple historical water conveyance processes and the current water conveyance process. The hydraulic data includes the lock chamber water level difference, water conveyance velocity, water flow acceleration, and blockage ratio. Based on the hydraulic data, multiple hydraulic states are constructed. The hydraulic states are used to characterize the different risks faced by the ship's mooring forces under different hydraulic data states. The attribution coefficients of the state data at each time moment with each hydraulic state are calculated. The hydraulic state at each time moment with the maximum value of the attribution coefficients of all hydraulic states is taken as the hydraulic state at each time moment. Based on whether the change in water conveyance velocity between hydraulic states can meet the required flow increment and whether the water level difference in the gate chamber can meet the hydraulic acceleration requirements, the physical feasibility of the transfer between hydraulic states is judged; by analyzing the transfer frequency between hydraulic states and the physical feasibility of the transfer between hydraulic states during historical water conveyance, the transfer factor between hydraulic states is obtained and a state transfer matrix is ​​constructed. Using the attribution coefficients of all hydraulic states at the current moment as the initial probability vector, the probability distribution of hydraulic states at several future time steps is derived using the Markov chain model and the state transition matrix, and the mooring force threat coefficient at each future moment is calculated. The risk of mooring force is determined by the mooring force threat coefficient, and the opening of the lock water conveyance valve is dynamically adjusted to achieve intelligent and coordinated control of lock water conveyance.

[0008] Furthermore, the construction of the state transition matrix specifically includes: Preset boundary thresholds for determining the stability of water delivery velocity and water flow acceleration. and 1. Determine the boundary threshold for a large positive water flow acceleration. 1. Determine the boundary threshold for high water delivery rate Boundary threshold for large negative water flow acceleration Determine the boundary threshold of a specific interval of vortex-induced vibration. and 1. Determine the boundary threshold for a high blocking ratio ; When the water delivery rate is within the range The water flow acceleration is within the range When the water flow acceleration is within the range, it is in the s1 static steady state; when the water flow acceleration is within the range... When the water flow acceleration is within the range, it is in the s2 gradient impact state; when the water flow acceleration is within the range And the water delivery rate is within the range Within this timeframe, further determine whether the blocking ratio is greater than [a certain value]. If the blocking ratio is in the range The inner state is s6 jet penetration state; otherwise, it is s3 drag-dominated state. When the water flow acceleration is within the range... When the water flow rate is within the range, it is in the s4 water hammer backflow state; when the water conveyance velocity is within the range Inside, it is in the s5 vortex-induced resonance state.

[0009] Furthermore, the calculation of the attribution coefficients between the state data at each moment and each hydraulic state specifically includes: The three types of hydraulic data, namely water delivery velocity, water flow acceleration, and blockage ratio, are recorded as state data. The assignment coefficient between time t and hydraulic state i The calculation method is as follows:

[0010] In the formula: This represents the total number of categories in the state data. This represents the dominant weight of the k-th state data at time t. This represents the comparison factor for the i-th hydraulic state at time t in the k-th state data. This represents an exponential function with the natural constant as its base.

[0011] Furthermore, the specific method for obtaining the comparison factor is as follows: The comparison factor for the i-th hydraulic state at time t with the k-th state data. The calculation method is as follows:

[0012] In the formula: This represents the value of the k-th state data at time t. This represents the value of the i-th hydraulic state that is closest to the k-th state data at time t within the interval corresponding to the k-th state data.

[0013] Furthermore, the specific method for obtaining the dominant weight is as follows: The maximum absolute value of all boundary thresholds involved in each type of state data is recorded as the dominant threshold of that type of state data. The dominant weight of the k-th class of state data at time t The calculation method is as follows:

[0014] In the formula: This represents the value of the k-th state data at time t. This represents the value of the k-th class of state data at time t, adjacent to the previous time. This represents the dominant threshold associated with the k-th class of state data; This represents a user-defined function, and the expression for this user-defined function is: ,in This represents the argument of the user-defined function; This represents the function that takes the minimum value. This represents the function that takes the absolute value.

[0015] Furthermore, the determination of the physical feasibility of the transition between hydraulic states specifically includes: When the change in water conveyance velocity between hydraulic states cannot meet the required flow increment, the law of conservation of mass is violated, and it is physically impossible; when the water level difference in the gate chamber cannot meet the hydraulic acceleration requirement of the next hydraulic state, the law of conservation of momentum is violated, and it is physically impossible.

[0016] Furthermore, the step of obtaining the transition factors between hydraulic states and constructing the state transition matrix specifically includes: The transfer factor from the i-th hydraulic state to the j-th hydraulic state The calculation method is as follows:

[0017] In the formula: This represents the total number of moments in the i-th hydraulic state. This represents the total number of times the hydraulic state i transitions to the hydraulic state j. This represents the attribution coefficient between the t-th time point and the j-th hydraulic state. It represents the average of the attribution coefficients for all hydraulic states other than the i-th hydraulic state at time t; When the transition between hydraulic states is physically impossible, its transition factor is denoted as the preset smoothing probability. ; A matrix is ​​constructed based on the transfer factors between all hydraulic states. The matrix is ​​then normalized and corrected, and the normalized and corrected matrix is ​​denoted as the state transition matrix.

[0018] Furthermore, the calculation of the mooring force threat coefficient at future times specifically includes: Mooring force threat coefficient at the r-th time in the i-th hydraulic state The calculation method is as follows:

[0019] In the formula: This represents the preset risk weight for the i-th hydraulic state. This indicates the duration of the dominant hydraulic state at time r in the future. This represents the probability that the system is in the i-th hydraulic state at the r-th time in the future.

[0020] Furthermore, the duration of sustained dominance specifically includes: If the probability of being in the i-th hydraulic state at the r-th time in the future is the highest, then the i-th hydraulic state will dominate at the r-th time in the future. The total number of all adjacent times before the r-th time that are dominated by the i-th hydraulic state is recorded as the duration of the i-th hydraulic state's dominance at the r-th time in the future.

[0021] Furthermore, the determination of mooring force risk based on the mooring force threat coefficient specifically includes: The system presets the observation duration and threat threshold, and obtains the mooring force threat coefficient for each hydraulic state at all times within the observation duration. When the mooring force threat coefficient exceeds the threat threshold in any hydraulic state, it is considered that there is a mooring force risk corresponding to that hydraulic state in the current lock. When the mooring force threat coefficient does not exceed the threat threshold at all times within the observation duration, the current lock water conveyance state is stable.

[0022] The above-mentioned technical solutions adopted in this specification can achieve the following beneficial effects: The intelligent collaborative control method for water conveyance in locks based on hydraulic simulation provided in this specification constructs a discrete hydraulic state and calculates the attribution coefficient by acquiring data such as the speed, acceleration, and blockage ratio of the ship during water conveyance; a state transition matrix is ​​established by combining historical transition frequencies with physical conservation laws for verification; a Markov chain model is used to deduce the probability distribution of future hydraulic states and quantify the mooring force threat coefficient; finally, the valve opening is dynamically adjusted based on the predicted risk to achieve intelligent collaborative control of water conveyance in locks from passive response to active prevention.

[0023] This invention breaks through the limitations of traditional post-event response alarm modes, mapping continuous and complex hydraulic processes into discrete state spaces, significantly reducing computational costs and improving response speed. By introducing physical verification, it enhances the interpretability and reliability of the model, while realizing pre-event prevention and proactive control of accidents, thereby improving the safety and passage efficiency of water conveyance in locks. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This document presents a schematic diagram of the intelligent collaborative control method for water conveyance in a ship lock based on hydraulic simulation, as provided in this manual. Figure 2 This specification provides a schematic diagram of the hydraulic state plane based on velocity-acceleration. Figure 3 This is a schematic diagram illustrating the difference between the dominant weight control state data and the hydraulic state, as provided in this specification. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of this specification clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments in this specification without creative effort are within the scope of protection of this application.

[0026] Existing emergency protection systems based on mooring force monitoring during water conveyance in locks primarily employ a reactive "over-limit alarm - emergency shutdown" response mode. These systems typically consist of a signal input terminal, a signal processing terminal, a status analysis terminal, an anomaly alarm terminal, and an emergency protection terminal. After preprocessing, the status analysis terminal determines whether the ship's mooring status and the floating bollard's operational status are abnormal. The core judgment logic is based on a preset mooring force threshold. Throughout the lock's water conveyance process, the system compares the absolute value of the mooring force with the preset threshold in real time, triggering alarm messages or emergency valve closure confirmation prompts based on the comparison results. This reactive response mode only issues an alarm or executes an emergency shutdown after the mooring force has reached or exceeded the danger threshold, failing to proactively control the situation before the mooring force exceeds the limit and thus making it difficult to fundamentally prevent cable breakage or bollard damage caused by hydraulic impact.

[0027] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0028] Figure 1 This is a schematic diagram of the intelligent collaborative control method for water conveyance in a ship lock based on hydraulic simulation, as described in this specification. The method specifically includes the following steps: S101: Acquire hydraulic data of the ship at each moment during multiple historical water conveyance processes and the current water conveyance process.

[0029] The purpose of this invention is to dynamically control the lock's water delivery valves by predicting future changes in ship mooring force based on a Markov chain model using monitored ship hydraulic data. Therefore, this step first obtains several historical water delivery processes and the ship's hydraulic data during the current water delivery process. The hydraulic data includes, but is not limited to: water level data at the bow and stern of the lock chamber at each moment, average water level of the lock chamber at each moment, water delivery speed at each moment, water flow acceleration at each moment, ship's length, width, and draft, blockage ratio at each moment, and tension of each mooring rope at each moment.

[0030] Specifically, the preset time step is 0.1 seconds, and a moment is taken at every time step; the water level data of the bow and stern of the lock chamber at each moment during the water conveyance process is collected by the submersible level gauge, and the average of the water level data of the bow and stern of the lock chamber at each moment is recorded as the average water level of the lock chamber at each moment; the average cross-sectional velocity of the water conveyance channel outlet at each moment is obtained by the electromagnetic flowmeter, and it is recorded as the water conveyance velocity at each moment; the water conveyance velocity at each moment is processed by the center difference to obtain the water flow acceleration at each moment; the length, width and draft of the ship are obtained by the Automatic Identification System (AIS) data, and the blockage ratio at each moment is calculated by combining it with the average water level of the lock chamber at each moment; the tension of each mooring rope at each moment is collected by the tension sensor.

[0031] Thus far, this step has obtained several historical water conveyance processes and hydraulic parameters related to water conveyance control during the current water conveyance process, providing a data foundation with clear physical meaning for the intelligent real-time control of water conveyance in the lock.

[0032] S102: Construct multiple hydraulic states to characterize the different risks faced by ship mooring forces under different hydraulic data states.

[0033] It should be noted that the computational load required for high-precision modeling and simulation of continuous and complex physical processes is enormous, resulting in significant time costs. During the water conveyance process at the lock, rapid response and measures are needed to address changes in the hydraulic state. This step uses three types of hydraulic data—water conveyance velocity, water flow acceleration, and blockage ratio—to reflect the real-time energy state of the water flow during the water conveyance process.

[0034] The three types of hydraulic data—water conveyance velocity, water flow acceleration, and blockage ratio—are recorded as state data. Different hydraulic states are constructed based on the state data during the water conveyance process and the hydraulic principles involved in ship mooring. Different hydraulic states are used to distinguish the different risks faced by the ship's mooring force under different hydraulic characteristics, as well as the different strategies corresponding to the lock's water conveyance control.

[0035] Specifically, boundary thresholds for different hydraulic states are set, and the hydraulic states of ship water delivery are divided into the following based on the water delivery speed, water flow acceleration and blockage ratio at each moment: s1 still water steady state, s2 gradient impact state, s3 towing-dominated state, s4 water hammer backflow state, s5 vortex-induced resonance state, and s6 jet penetration state.

[0036] Under the aforementioned still water steady state, both the water conveyance velocity and the water flow acceleration are small, resulting in low mooring force risk. The lock's water conveyance strategy is to increase the water conveyance velocity. By acquiring the water conveyance velocity and water flow acceleration noise values ​​in the ship's static state before water conveyance, three times the standard deviation of the water conveyance velocity and water flow acceleration noise values ​​are used as the boundary thresholds for judging the stability of the water conveyance velocity and the stability of the water flow acceleration. and .

[0037] Under the aforementioned gradient impact state, the forward water flow acceleration is large, and the mooring force is in a state of high static tension, posing a risk of mooring breakage. The lock's water conveyance strategy is to reduce the water flow acceleration. Based on the lock's maximum allowable water surface gradient and the linear relationship between acceleration and gradient in the Saint-Venant equation, the maximum water flow acceleration that will not cause the mooring force to exceed the limit is calculated and used as the boundary threshold for judging whether the forward water flow acceleration is large. .

[0038] Under the towing-dominated state, the water conveyance velocity is high while the water flow acceleration is low, resulting in a high and continuous load on the mooring lines, which poses a risk of cable fatigue. Therefore, the lock's water conveyance strategy is to limit further increases in water conveyance velocity. Based on the towing force coefficient curve of a typical vessel and the safe breaking tensile force of the mooring lines, the corresponding safe limit velocity is calculated using the square of resistance formula, serving as the boundary threshold for judging high water conveyance velocities. .

[0039] Under the aforementioned water hammer backflow condition, the negative water flow acceleration is large, and the mooring force is in a state of sudden directional impact, posing a risk of mooring breakage. The lock's water conveyance strategy is to limit the water flow acceleration. Based on the maximum allowable negative pressure value of the water conveyance channel and the water hammer pressure calculation formula, the maximum negative acceleration to avoid generating destructive water hammer waves is calculated and used as the boundary threshold for judging large negative water flow acceleration. .

[0040] Under the vortex-induced resonance state, the water conveyance velocity is within a specific range of vortex-induced vibration. At this point, the mooring force exhibits alternating stress, which significantly accelerates cable fatigue. The lock's water conveyance strategy aims to rapidly traverse the specific range of vortex-induced vibration. Based on the energy dissipation structure dimensions and the Strouhal number, combined with the ship's mooring system's natural frequencies, the velocity range where vortex-induced resonance lock-in occurs is calculated. Reference values ​​for the upper and lower thresholds of the critical vortex-induced velocity are obtained as indicators to determine if the water conveyance velocity is within the specific range of vortex-induced vibration. Boundary threshold and .

[0041] In the jet penetration state, the water conveyance velocity is high and the blockage ratio is high. The mooring force is uneven and the tension is high, posing a risk of mooring breakage. The lock's water conveyance strategy is to reduce the flow velocity to alleviate the high blockage ratio effect. Based on the influence of the reduction ratio of the effective water passage cross-section of the lock chamber on the amplification factor of the gap flow velocity, a blockage ratio value is set when the gap flow velocity exceeds a certain multiple (e.g., 2 times) of the average flow velocity as a boundary threshold for judging a high blockage ratio. .

[0042] The methods for obtaining the above boundary thresholds are merely illustrative; the boundary thresholds can be adjusted according to specific implementation conditions, and this invention does not impose specific limitations. The hydraulic state is divided based on the above boundary thresholds: when the water conveyance velocity is within the interval... The water flow acceleration is within the range When the water flow acceleration is within the range, it is in the s1 static steady state; when the water flow acceleration is within the range... When the water flow acceleration is within the range, it is in the s2 gradient impact state; when the water flow acceleration is within the range And the water delivery rate is within the range Within this timeframe, further determine whether the blocking ratio is greater than [a certain value]. If the blocking ratio is in the range The inner state is s6 jet penetration state; otherwise, it is s3 drag-dominated state. When the water flow acceleration is within the range... When the water flow rate is within the range, it is in the s4 water hammer backflow state; when the water conveyance velocity is within the range Inside, it is in the s5 vortex-induced resonance state.

[0043] When constructing a rectangular coordinate system with water conveyance velocity as the horizontal axis and water flow acceleration as the vertical axis, the first and fourth quadrants of this rectangular coordinate system are denoted as the velocity-acceleration-based hydraulic state plane. The velocity-acceleration-based hydraulic state plane can be divided into several regions based on all boundary thresholds related to determining water conveyance velocity and water flow acceleration; for example... Figure 2 The figure shown is a schematic diagram of a hydraulic state plane based on velocity-acceleration.

[0044] Thus, multiple hydraulic states were constructed; by mapping the continuous water conveyance state to a discrete physical state space, the simulation model of the lock water conveyance process was simplified, and the control efficiency of the water conveyance process was improved.

[0045] S103: Calculate the state data and the assignment coefficients of each hydraulic state at each time point to determine the hydraulic state at each time point.

[0046] It should be noted that, since the above-mentioned division of hydraulic states is a discrete region, the magnitude of the water conveyance velocity and the water flow acceleration are continuously changing during the water conveyance process. It is not necessarily that every moment completely conforms to a certain hydraulic state mentioned above. Therefore, this step calculates the degree of conformity between the magnitude of the state data at each moment and the hydraulic states of different locks, obtains the division coefficient between each moment and each hydraulic state, and thus determines the hydraulic state at each moment.

[0047] Specifically, firstly, the difference between the real-time status data of the lock water conveyance and each hydraulic state is obtained and denoted as the comparison factor; taking the comparison factor of the i-th hydraulic state in the interval of the k-th state data at time t as an example, the comparison factor of the i-th hydraulic state in the k-th state data at time t is... The calculation method is as follows:

[0048] In the formula: This represents the value of the k-th state data at time t. This represents the value of the i-th hydraulic state that is closest to the k-th state data at time t within the interval corresponding to the k-th state data.

[0049] It should be noted that when the i-th hydraulic state has no boundary threshold in the k-th state data, the interval corresponding to the i-th hydraulic state in the k-th state data is: When the value of the k-th state data at time t is within the interval corresponding to the k-th state data for the i-th hydraulic state, .

[0050] Furthermore, the maximum absolute value of all boundary thresholds involved in each type of state data is recorded as the dominant threshold of that type of state data. Based on the dominance of data in the state data at each time step, and the magnitude of the comparison factor between each time step and each hydraulic state in each type of state data, the partitioning coefficient between each time step and each hydraulic state is obtained. Taking the current time step as the t-th time step as an example, the dominant weight of the k-th type of state data at the t-th time step... The calculation method is as follows:

[0051] In the formula: This represents the value of the k-th state data at time t. This represents the value of the k-th class of state data at time t, adjacent to the previous time. This represents the dominant threshold associated with the k-th class of state data; This represents a user-defined function, and the expression for this user-defined function is: ,in This represents the argument of the user-defined function, used to express the sign state of the argument; This represents the function that takes the minimum value. This represents the function that takes the absolute value.

[0052] It should be noted that the dominant weight represents the overall dominant state of the k-th class of state data at time t. It represents the direction of change of the k-th state data at time t relative to its adjacent previous time. When this value is non-negative, it is considered to show an increasing trend; otherwise, it is considered to show a decreasing trend. This represents the ratio of the value of the k-th state data at time t to the dominant threshold, and... By using a ratio to eliminate the influence of dimensions, a larger value indicates a larger absolute value of the k-th state data at time t, and thus a greater degree of dominance of the k-th state data over the hydraulic state at time t. In order to limit the results to Within the range; specifically, when t=1, take .

[0053] Furthermore, the attribution coefficient between time t and hydraulic state i. The calculation method is as follows:

[0054] In the formula: This represents the total number of categories of state data, in this embodiment. , This represents the dominant weight of the k-th state data at time t. This represents the comparison factor for the i-th hydraulic state at time t in the k-th state data. This represents an exponential function with the natural constant as its base, here expressed as... The model implements inverse proportional normalization.

[0055] It should be noted that This represents the difference between the value of the hydraulic state at time t and the value of the hydraulic state at time ith in the k-th state data. This indicates that the dominant trend of the state data reflected by the dominant weight is used to adjust the difference between the state data at time t and the hydraulic state i. When the dominant trend of the state data at time t is consistent with the direction of reducing the contrast factor, for example, if the contrast factor is negative, the corresponding state data is less than the boundary threshold of the hydraulic state. Conversely, if the dominant weight is positive, the corresponding state data shows an increasing trend, indicating that the state data is currently too small but may increase. The calculation reduces the difference between the state data at time t and the hydraulic state at time i, such as... Figure 3 The diagram shows the difference between the dominant weight control state data and the hydraulic state. This represents the Euclidean distance calculated based on the differences in state data across all classes, reflecting the overall level of difference between the state data at time t and the hydraulic state of class i.

[0056] Furthermore, obtain the attribution coefficients of the hydraulic states at time t, and record the hydraulic state at time t when the attribution coefficients of the hydraulic states at time t are at their maximum values; similarly, obtain the water conveyance states at all times in all historical water conveyance processes and the current water conveyance process.

[0057] At this point, the hydraulic state at each moment has been determined. Based on the dominant situation of the state data, the degree of conformity between the state data and all hydraulic states is optimized and compared, so as to more accurately determine the hydraulic state at each moment, so that different states can directly reflect the characteristics of water flow energy performance in the water conveyance process.

[0058] S104: Analyze the frequency of hydraulic state transitions during historical water conveyance processes and construct a state transition matrix based on physical realizability.

[0059] Since different hydraulic states are discretely distributed, the hydraulic states obtained in the above steps may exhibit state transitions that do not conform to physical rules. This step examines the rationality of different state transitions and, by combining the probability distribution of the successor states of each state in historical data, obtains the transition probability matrix between different hydraulic states.

[0060] Specifically, based on the hydraulic state at all times during all historical water conveyance processes and the attribution coefficient to each state, the frequency distribution of hydraulic state transitions is analyzed to obtain the transition factors between hydraulic states; the transition factor from the i-th hydraulic state to the j-th hydraulic state is also analyzed. The calculation method is as follows:

[0061] In the formula: This represents the total number of moments in the i-th hydraulic state. This represents the total number of times the hydraulic state i transitions to the hydraulic state j. This represents the attribution coefficient between the t-th time point and the j-th hydraulic state. This represents the average of the attribution coefficients for all hydraulic states other than the i-th hydraulic state at time t. This represents the Sigmoid function, used here for proportional normalization.

[0062] It should be noted that the i-th hydraulic state and the j-th hydraulic state can be the same hydraulic state; This represents the difference in the average attribution coefficient between the i-th hydraulic state and other hydraulic states at time t. A larger value indicates that the i-th hydraulic state is more prominent at time t, thus reducing the likelihood that the transition from the i-th to the j-th hydraulic state at time t is an intermediate state fluctuation, and making the process more reliable. The weighted average of all times from the i-th to the j-th hydraulic state is then considered. The cumulative sum, combined with the reliability of each transfer, reflects the frequency of the transfer from the i-th hydraulic state to the j-th hydraulic state; similarly, the transfer factor between all hydraulic states is obtained.

[0063] Furthermore, a physical verification is performed on the transitions between all hydraulic states. If the physical verification fails, the transition factor is recorded as a preset smoothing probability. The physical verification specifically includes mass conservation verification and momentum conservation verification, and the specific verification process is as follows: Mass conservation verification: The required flow increment is calculated by back-calculating the change in water conveyance velocity corresponding to the hydraulic state after the transfer, and compared with the cumulative amount of the theoretical maximum flow capacity under the current water conveyance velocity within the time step; if the required flow increment exceeds the maximum flow capacity, the transfer process is deemed to violate the law of conservation of mass and is physically impossible.

[0064] Momentum conservation check: Calculate the water flow acceleration and corresponding inertial force required to achieve the water conveyance velocity after the transfer, and compare it with the maximum driving hydraulic force that can be provided by the current water level difference between the head and tail of the gate chamber; if the required inertial force significantly exceeds the driving hydraulic limit, the transfer process is deemed to violate the law of conservation of momentum and is physically impossible to achieve.

[0065] Physical verification is performed on the transfer process between all hydraulic states to update the transfer factor, thus obtaining the transfer factor between all hydraulic states.

[0066] Furthermore, a matrix is ​​constructed based on the transfer factors between all hydraulic states. Each row of the matrix represents the transfer factor from one hydraulic state to all hydraulic states. The matrix is ​​then normalized to ensure that the distribution of elements in each row of the normalized matrix satisfies the probability axiom (non-negative and summing to 1). The normalized matrix is ​​denoted as the state transition matrix.

[0067] Thus, based on the frequency and reliability of state transitions combined with physical verification, a state transition matrix reflecting the probability of transitions between different hydraulic states was constructed; physical verification avoids state jumps that violate the basic laws of fluid mechanics, thereby enhancing the reliability and interpretability of the model.

[0068] S105: Deduce the probability distribution of hydraulic state over several future time steps and calculate the mooring force threat coefficient at each future time.

[0069] Existing emergency protection systems based on mooring force monitoring during water conveyance in ship locks typically employ a reactive "over-limit alarm - emergency shutdown" response mode. These systems compare the absolute value of the mooring force with a preset mooring force threshold in real time throughout the entire water conveyance process, triggering alarms or emergency valve closure confirmations based on the comparison results. This can lead to a delayed response and prevent proactive control before the mooring force exceeds the limit. This new approach, based on a state transition matrix and using a Markov chain model, extrapolates the probability distribution of the hydraulic state at various future moments in real time, reflecting future mooring force risks. This allows for intelligent control of water conveyance in the ship lock based on these risks.

[0070] Specifically, the current time is denoted as the t-th moment of the current water conveyance process, and the initial probability vector is the association coefficient between the current time and each hydraulic state. Using the initial probability vector and state transition matrix as input, the state probability distribution for several future time steps is calculated iteratively through matrix multiplication based on the Markov chain model to obtain the probability of being in each hydraulic state at each time step in the future; based on the probability of being in each hydraulic state at each future time step, the risk coefficient for each future time step is obtained. Taking the r-th future time as an example, if the probability of being in the i-th hydraulic state at the r-th future time is the highest, then the i-th hydraulic state dominates at the r-th future time. The total number of all adjacent times before the r-th future time dominated by the i-th hydraulic state is recorded as the duration of the i-th hydraulic state's dominance at the r-th future time. The mooring force threat coefficient in the i-th hydraulic state at the r-th future time is... The calculation method is as follows:

[0071] In the formula: This represents the preset risk weight for the i-th hydraulic state. This indicates the duration of the dominant hydraulic state at time r in the future. This represents the probability that the system is in the i-th hydraulic state at the r-th time in the future.

[0072] It should be noted that different hydraulic conditions correspond to different mooring force risk states. Strong impact hydraulic conditions may lead to rapid mooring breakage, while hydraulic conditions that accelerate cable fatigue may only cause breakage after a longer duration. Therefore, different settings are applied to different hydraulic conditions. In this embodiment, the risk weight of the s1 static steady state is set to 0, the risk weight of the s2 gradient impact state, the s4 water hammer backflow state, and the s6 jet penetration state is set to 0.08, and the risk weight of the s3 drag-dominated state and the s5 vortex-induced resonance state is set to 0.03. The preset values ​​of the risk weights here are only examples and can be adjusted according to the specific implementation. This embodiment does not impose any specific limitations.

[0073] Thus, by obtaining the threat coefficient based on probability extrapolation, quantitative risk assessment and proactive intervention have been achieved.

[0074] S106: Based on the mooring force threat coefficient, assess the mooring force risk to achieve intelligent and coordinated control of water conveyance in the lock.

[0075] Furthermore, the system acquires the mooring force threat coefficient for each hydraulic state at every future time after the current moment; a preset threat threshold of 0.8 is used. When the mooring force threat coefficient exceeds the threshold in any hydraulic state, the lock is considered to have a mooring force risk corresponding to that hydraulic state. Based on the lock's water conveyance strategy corresponding to the specific hydraulic state where the mooring force threat coefficient is greater than the threshold, such as adjusting the lock valve opening to control the water conveyance speed, intelligent control of the lock's water conveyance is achieved. The preset observation period is 300 time steps after the current moment. The system acquires the mooring force threat coefficient for each hydraulic state at all times within the observation period. When the mooring force threat coefficient for each hydraulic state at all times within the observation period does not exceed the threat threshold, the current lock's water conveyance state is stable. This achieves intelligent control of the lock's water conveyance.

[0076] This concludes the embodiment.

[0077] based on Figure 1 The intelligent collaborative control method for water conveyance in locks based on hydraulic simulation shown here breaks through the limitations of the traditional post-event response alarm mode. It maps the continuous and complex hydraulic process into a discrete state space, which greatly reduces the computational cost and improves the response speed. By introducing physical verification, it enhances the interpretability and reliability of the model, while realizing the prevention and active control of accidents in advance, and improving the safety and passage efficiency of water conveyance in locks.

[0078] When applying the intelligent collaborative control method for lock water conveyance based on hydraulic simulation provided in this manual, it is not necessary to consider... Figure 1 The steps shown are executed in sequence. The specific execution order of each step can be determined as needed, and this manual does not impose any restrictions on it.

[0079] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for intelligent collaborative control of water conveyance in ship locks based on hydraulic simulation, characterized in that, include: The system acquires hydraulic data of the vessel at each moment during multiple historical water conveyance processes and the current water conveyance process. The hydraulic data includes the lock chamber water level difference, water conveyance velocity, water flow acceleration, and blockage ratio. Based on the hydraulic data, multiple hydraulic states are constructed. The hydraulic states are used to characterize the different risks faced by the ship's mooring forces under different hydraulic data states. The attribution coefficients of the state data at each time moment with each hydraulic state are calculated. The hydraulic state at each time moment with the maximum value of the attribution coefficients of all hydraulic states is taken as the hydraulic state at each time moment. Based on whether the change in water conveyance velocity between hydraulic states can meet the required flow increment and whether the water level difference in the gate chamber can meet the hydraulic acceleration requirements, the physical feasibility of the transfer between hydraulic states is judged; by analyzing the transfer frequency between hydraulic states and the physical feasibility of the transfer between hydraulic states during historical water conveyance, the transfer factor between hydraulic states is obtained and a state transfer matrix is ​​constructed. Using the attribution coefficients of all hydraulic states at the current moment as the initial probability vector, the probability distribution of hydraulic states at several future time steps is derived using the Markov chain model and the state transition matrix, and the mooring force threat coefficient at each future moment is calculated. The risk of mooring force is determined by the mooring force threat coefficient, and the opening of the lock water conveyance valve is dynamically adjusted to achieve intelligent and coordinated control of lock water conveyance.

2. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 1, characterized in that, The construction of the state transition matrix specifically includes: Preset boundary thresholds for determining the stability of water delivery velocity and water flow acceleration. and 1. Determine the boundary threshold for a large positive water flow acceleration.

1. Determine the boundary threshold for high water delivery rate Boundary threshold for large negative water flow acceleration Determine the boundary threshold of a specific interval of vortex-induced vibration. and 1. Determine the boundary threshold for a high blocking ratio ; When the water delivery rate is within the range The water flow acceleration is within the range When the water flow acceleration is within the range, it is in the s1 static steady state; when the water flow acceleration is within the range... When the water flow acceleration is within the range, it is in the s2 gradient impact state; when the water flow acceleration is within the range And the water delivery rate is within the range Within this timeframe, further determine whether the blocking ratio is greater than [a certain value]. If the blocking ratio is in the range The inner state is s6 jet penetration state; otherwise, it is s3 drag-dominated state. When the water flow acceleration is within the range... When the water flow rate is within the range, it is in the s4 water hammer backflow state; when the water conveyance velocity is within the range Inside, it is in the s5 vortex-induced resonance state.

3. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 1, characterized in that, The calculation of the attribution coefficients between the state data at each moment and each hydraulic state specifically includes: The three types of hydraulic data, namely water delivery velocity, water flow acceleration, and blockage ratio, are recorded as state data. The assignment coefficient between time t and hydraulic state i The calculation method is as follows: In the formula: This represents the total number of categories in the state data. This represents the dominant weight of the k-th state data at time t. This represents the comparison factor for the i-th hydraulic state at time t in the k-th state data. This represents an exponential function with the natural constant as its base.

4. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 3, characterized in that, The specific method for obtaining the contrast factor is as follows: The comparison factor for the i-th hydraulic state at time t with the k-th state data. The calculation method is as follows: In the formula: This represents the value of the k-th state data at time t. This represents the value of the i-th hydraulic state that is closest to the k-th state data at time t within the interval corresponding to the k-th state data.

5. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 3, characterized in that, The specific method for obtaining the dominant weight is as follows: The maximum absolute value of all boundary thresholds involved in each type of state data is recorded as the dominant threshold of that type of state data. The dominant weight of the k-th class of state data at time t The calculation method is as follows: In the formula: This represents the value of the k-th state data at time t. This represents the value of the k-th class of state data at time t, adjacent to the previous time. This represents the dominant threshold associated with the k-th class of state data; This represents a user-defined function, and the expression for this user-defined function is: ,in This represents the argument of the user-defined function; This represents the function that takes the minimum value. This represents the function that takes the absolute value.

6. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 1, characterized in that, The determination of the physical feasibility of the transition between hydraulic states specifically includes: When the change in water conveyance velocity between hydraulic states cannot meet the required flow increment, the law of conservation of mass is violated, and it is physically impossible; when the water level difference in the gate chamber cannot meet the hydraulic acceleration requirement of the next hydraulic state, the law of conservation of momentum is violated, and it is physically impossible.

7. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 1, characterized in that, The process of obtaining the transition factors between hydraulic states and constructing the state transition matrix specifically includes: The transfer factor from the i-th hydraulic state to the j-th hydraulic state The calculation method is as follows: In the formula: This represents the total number of moments in the i-th hydraulic state. This represents the total number of times the hydraulic state i transitions to the hydraulic state j. This represents the attribution coefficient between the t-th time point and the j-th hydraulic state. It represents the average of the attribution coefficients for all hydraulic states other than the i-th hydraulic state at time t; When the transition between hydraulic states is physically impossible, its transition factor is denoted as the preset smoothing probability. ; A matrix is ​​constructed based on the transfer factors between all hydraulic states. The matrix is ​​then normalized and corrected, and the normalized and corrected matrix is ​​denoted as the state transition matrix.

8. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 1, characterized in that, The calculation of the mooring force threat coefficient at future times specifically includes: Mooring force threat coefficient at the r-th time in the i-th hydraulic state The calculation method is as follows: In the formula: This represents the preset risk weight for the i-th hydraulic state. This indicates the duration of the dominant hydraulic state at time r in the future. This represents the probability that the system is in the i-th hydraulic state at the r-th time in the future.

9. The intelligent collaborative control method for water conveyance in ship locks based on hydraulic simulation as described in claim 8, characterized in that, The duration of sustained dominance specifically includes: If the probability of being in the i-th hydraulic state at the r-th time in the future is the highest, then the i-th hydraulic state will dominate at the r-th time in the future. The total number of all adjacent times before the r-th time that are dominated by the i-th hydraulic state is recorded as the duration of the i-th hydraulic state's dominance at the r-th time in the future.

10. The intelligent collaborative control method for water conveyance in a ship lock based on hydraulic simulation as described in claim 1, characterized in that, The method of determining mooring force risk based on the mooring force threat coefficient specifically includes: The system presets the observation duration and threat threshold, and obtains the mooring force threat coefficient for each hydraulic state at all times within the observation duration. When the mooring force threat coefficient exceeds the threat threshold in any hydraulic state, it is considered that there is a mooring force risk corresponding to that hydraulic state in the current lock. When the mooring force threat coefficient does not exceed the threat threshold at all times within the observation duration, the current lock water conveyance state is stable.

Images