A method and device for protecting the safety of a water injection process in a special-purpose cavity of a ship

Abstract

The application discloses a kind of special-purpose cavity of ship injection water process safety protection control method and device, it is related to ship intelligent control technical field.The method includes: constructing the nonlinear mathematical model of special-purpose cavity of ship injection water system;Parameter identification module based on swarm intelligence algorithm is constructed, the dynamic parameter vector of nonlinear mathematical model is carried out rolling optimization identification, and the updated nonlinear mathematical model is obtained;Multi-objective optimization function is constructed, and constraint condition is set;Based on the updated nonlinear mathematical model, the multi-objective optimization function is solved using swarm intelligence algorithm, and the optimal control amount of current time is obtained, and the injection water regulating valve of special-purpose cavity of ship injection water system is driven to execute;Real-time monitoring parameter identification module in execution process, if the identification parameter of dynamic parameter vector exceeds physical feasible region or prediction error diverges, then trigger safety protection logic.The application solves the problem of low control precision and poor safety caused by parameter time-varying in the prior art.

Description

Technical Field

[0001] This invention relates to the field of ship intelligent control technology, and in particular to a safety protection and control method and device for the water injection process of a ship-specific cavity. Background Technology

[0002] The water injection process into specialized ship cavities (such as ballast tanks and cargo tanks) is a critical operation in ship maintenance. During water injection, the system's hydrodynamic characteristics change significantly due to factors such as pipe aging, biofouling, valve wear, and vent blockage. This manifests as time-varying parameters such as the pipe friction coefficient and local resistance coefficient. Traditional water injection control methods, typically based on fixed PID control or simple open-loop control, are ill-suited to this dynamically changing parameter environment. This can easily lead to low water injection efficiency, excessive pipe pressure fluctuations, and even safety incidents such as overpressure overflow.

[0003] Furthermore, existing water injection systems lack real-time monitoring and adaptive capabilities for model parameter drift. When sensors malfunction or critical components (such as vents) become severely blocked, traditional systems often fail to identify and implement protective measures in a timely manner, posing significant safety hazards.

[0004] Therefore, there is an urgent need for a water injection control method that can identify dynamic parameters in real time, optimize control strategies, and have active safety protection functions. Summary of the Invention

[0005] This invention provides a safety protection and control method and device for the water injection process of a ship-specific cavity. This invention solves the problems of low control accuracy and poor safety caused by time-varying parameters in existing technologies.

[0006] In a first aspect, embodiments of the present invention provide a safety protection and control method for the water injection process of a ship-specific cavity, the method comprising: A nonlinear mathematical model of a ship-specific cavity water injection system is constructed. The model takes the opening degree of the water injection valve as input, the cavity liquid level and the water injection pipeline pressure as output, and includes a dynamic parameter vector to be identified. The parameter identification module, built on the swarm intelligence algorithm, uses the sample dataset collected in real time during the water injection process to perform rolling optimization identification of the dynamic parameter vector of the nonlinear mathematical model, thereby obtaining an updated nonlinear mathematical model. A multi-objective optimization function for safety protection and control is constructed, with the objectives of maximizing water injection efficiency and minimizing pipeline pressure fluctuation, and the constraints being the liquid level safety threshold and the pipeline pressure resistance value. Based on the updated nonlinear mathematical model, the multi-objective optimization function is solved using a swarm intelligence algorithm to obtain the optimal control quantity at the current moment, and to drive the water injection regulating valve of the ship's special cavity water injection system to execute. During execution, the parameter identification module is monitored in real time. If the identified parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible region or the prediction error diverges, the safety protection logic is triggered.

[0007] The technical solution provided in this application has at least the following beneficial effects: By constructing a nonlinear mathematical model containing dynamic parameter vectors and using an improved Black-winged Kite algorithm for real-time rolling identification, the model can accurately reflect changes in system characteristics caused by pipeline aging, biological attachment, etc., thus improving the model's prediction accuracy. A control strategy based on multi-objective optimization is adopted to effectively suppress pipeline pressure fluctuations while ensuring water injection efficiency. An improved Grey Wolf algorithm is used to solve for the optimal control quantity, achieving intelligent control of the water injection process. Safety monitoring and protection logic is introduced. By analyzing the changing trends and fitness values ​​of the identification parameters, abnormal states such as vent blockage and sensor malfunctions can be proactively identified, triggering graded protection measures, significantly improving safety and reliability.

[0008] In one alternative implementation, the formula for the nonlinear mathematical model is:

[0009] In the formula, For time l Predicted injection flow rate; In order to keep pace with time l Valve opening Relevant flow coefficients; The flow area of ​​the valve port; This refers to the pump outlet pressure. For time l The cabin air pressure; For fluid density; For time l The liquid level height; g It is the gravitational constant; For time l The cross-sectional area of ​​the cavity at the liquid level height; For time l The exhaust flow rate of the vent holes; For time l liquid level height right l The first derivative; For time l The valve opening degree; l For time indication; The dynamic parameter vector The identification parameters include the pipeline friction coefficient. Local drag coefficient and the flow coefficient of the vent. ,in, This is the transpose symbol.

[0010] In one alternative implementation, a parameter identification module based on a swarm intelligence algorithm uses a sample dataset collected in real time during the water injection process to perform rolling optimization identification on the dynamic parameter vector of the nonlinear mathematical model, resulting in an updated nonlinear mathematical model, including: Using the improved Black-winged Kite algorithm, a parameter identification module is constructed, and the fitness function of the parameter identification module is defined. A sample dataset collected in real time during the water injection process using a sensor network; Based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is identified by rolling optimization using the sample dataset to obtain the optimal dynamic parameter vector. The nonlinear mathematical model is updated based on the optimal dynamic parameter vector to obtain an updated nonlinear mathematical model.

[0011] In one optional implementation, the fitness function of the parameter identification module is formulated as follows:

[0012] In the formula, Individual Black-winged Kite X The corresponding fitness value; For time j Individual Black-winged Kite X The parameters are substituted into the nonlinear mathematical model and the sample data is input to obtain the predicted water injection flow rate; For time j The filtered measured water injection flow rate; For time j Individual Black-winged Kite X The parameters are substituted into the nonlinear mathematical model and the sample data is input to obtain the predicted pipeline pressure; For time j The filtered measured pipeline pressure; j For time indication; X Let be the position vector of an individual Black-winged Kite; N The total number of samples in the dataset; For fitness weights.

[0013] In one alternative implementation, a sensor network is used to collect a sample dataset in real time during the water injection process, including: A sensor network is used to collect sensor data at fixed intervals; the sensor data includes measured valve opening. Actual water injection flow rate Actual pipeline pressure and the liquid level in the cavity ; The sensor data is preprocessed to obtain preprocessed sensor data; the preprocessed sensor data includes the normalized measured valve opening. Measured injection flow rate after filtering Measured pipeline pressure after filtering and the liquid level in the cavity after tilt compensation ; Maintain a memory with a length of N A data queue that stores the most recent data. N Preprocessed sensor data over consecutive time intervals yields a sample dataset. ,in, For time k Preprocessed sensor data, k For time indication, N This represents the total number of samples in the dataset.

[0014] In one optional implementation, based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is identified through rolling optimization using a sample dataset to obtain the optimal dynamic parameter vector, including: Based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is encoded into the individual vector of the improved Black-winged Kite algorithm; The initial population of black-winged kites is obtained by initialization using a Logistic chaotic mapping sequence; each individual black-winged kite in the population corresponds to a candidate dynamic parameter vector. Based on the candidate dynamic parameter vectors corresponding to the initial black-winged kite individuals in the initial black-winged kite population, a candidate nonlinear mathematical model is constructed. The sample dataset is input, the fitness function is used to calculate the corresponding fitness value, and the initial black-winged kite individual with the best fitness value is taken as the optimal solution. By introducing the Levy flight mechanism and the PSO algorithm, and based on the hovering and diving behaviors of the improved black-winged kite algorithm, the initial black-winged kite population is iteratively updated to obtain the updated black-winged kite population. Using the fitness function, calculate the fitness value of each updated black-winged kite individual in the updated black-winged kite population, and update the updated black-winged kite individual with the best fitness value as the optimal solution. When the number of iterations reaches the maximum number of iterations or the fitness value of the optimal solution meets the requirements, the iterative update of the black-winged kite population is terminated, and the optimal solution of the current iteration is output. The individual vectors of the black-winged kites corresponding to the optimal solution are decoded to obtain the optimal dynamic parameter vector.

[0015] In one alternative implementation, the formula for the multi-objective optimization function is:

[0016] In the formula, For individual gray wolves Y The corresponding comprehensive target value; For individual gray wolves Y The corresponding efficiency target value; For individual gray wolves Y The corresponding safety target value; The target weight;

[0017] In the formula, For time individual gray wolf Y The parameters are substituted into the updated nonlinear mathematical model to obtain the predicted water injection flow rate from the input sample data; For prediction in the time domain; It is a time variable;

[0018] In the formula, For time individual gray wolf Y The parameters are substituted into the nonlinear mathematical model to obtain the predicted pipeline pressure from the input sample data.

[0019] In one alternative implementation, based on an updated nonlinear mathematical model, a swarm intelligence algorithm is used to solve the multi-objective optimization function to obtain the optimal control quantity at the current moment, and to drive the water injection regulating valve of the ship's dedicated cavity water injection system to execute, including: The valve opening control sequence is encoded into individual vectors of the improved Grey Wolf algorithm; The initial gray wolf population is obtained by initialization using a Logistic chaotic mapping sequence; each gray wolf in the population corresponds to an alternative valve opening control sequence. The candidate valve opening control sequences corresponding to the initial gray wolf individuals in the initial gray wolf population are input into the updated nonlinear mathematical model for prediction, and the corresponding comprehensive objective value is calculated using a multi-objective optimization function. Based on the comprehensive objective value, an initial non-dominated ranking of the gray wolf population is performed, and the three best-performing non-dominated solutions in the non-dominated layer are taken as Alpha. α Grey Wolf, Beta β Grey Wolf and Delta δ Grey wolf; Store all non-dominated solutions in an external archive and maintain the archive capacity limit using a grid mechanism or crowding distance. The initial gray wolf population is updated in location to obtain an updated gray wolf population; Based on the multi-objective optimization function, the comprehensive objective value for each updated gray wolf individual in the updated gray wolf population is calculated, and the Alpha in the external archive is updated based on the comprehensive objective value. α Grey Wolf, Beta β Grey Wolf and Delta δ Grey wolf; The iterative update of the gray wolf population is terminated when the maximum number of iterations is reached or the fitness value of the optimal solution meets the requirements, and the Alpha value in the external archive is updated. α The gray wolf is output as the optimal solution; Decode the individual vector of the gray wolf corresponding to the optimal solution to obtain the optimal valve opening control sequence, and take the valve opening control quantity at the first position of the valve opening control sequence as the optimal control quantity. Based on the optimal control quantity, the water injection regulating valve of the ship's special cavity water injection system is driven to execute, and the parameter identification step and safety protection control optimization are returned to generate the dynamic parameter vector and optimal control quantity for the next moment.

[0020] In one optional implementation, the parameter identification module is monitored in real time during execution. If the identified parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible region or the prediction error diverges, the safety protection logic is triggered, including: During execution, the safety anomaly characteristics of the parameter identification module are monitored in real time; the safety anomaly characteristics include the dynamic parameter vector and the corresponding fitness value output periodically by the parameter identification module; If the vent flow coefficient is among the identification parameters of the dynamic parameter vector in the safety anomaly characteristics... If the rate of descent exceeds the preset rate threshold, the safety anomaly identification result is determined to be frost and dust accumulation in the vent holes; If the vent flow coefficient If the value is below the physically feasible region, the safety anomaly identification result is determined to be severe blockage of the vent. If the fitness value corresponding to the dynamic parameter vector in the safety anomaly feature is higher than the maximum fitness threshold, then the prediction error diverges, and the safety anomaly identification result is determined to be a sensor failure. Based on the security anomaly identification results, the corresponding level of security protection logic is triggered.

[0021] Secondly, embodiments of the present invention provide a safety protection and control device for the water injection process of a ship-specific cavity, used to implement a safety protection and control method for the water injection process of a ship-specific cavity, the device comprising: The mathematical model building unit is used to build a nonlinear mathematical model of a ship-specific cavity water injection system. The model takes the opening degree of the water injection valve as input, the cavity liquid level and the water injection pipeline pressure as output, and includes a dynamic parameter vector to be identified. The parameter identification unit is used to construct a parameter identification module based on swarm intelligence algorithm. It uses the sample dataset collected in real time during the water injection process to perform rolling optimization identification on the dynamic parameter vector of the nonlinear mathematical model to obtain an updated nonlinear mathematical model. The optimization function construction unit is used to construct a multi-objective optimization function for safety protection and control, with the objectives of maximizing water injection efficiency and minimizing pipeline pressure fluctuation, and with the liquid level safety threshold and pipeline pressure resistance value as constraints. The control quantity optimization unit is used to solve the multi-objective optimization function based on the updated nonlinear mathematical model using a swarm intelligence algorithm, obtain the optimal control quantity at the current moment, and drive the water injection regulating valve of the ship's special cavity water injection system to execute. The safety anomaly identification unit is used to monitor the parameter identification module in real time during execution. If the identification parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible domain or the prediction error diverges, the safety protection logic is triggered.

[0022] A third aspect of this invention provides an electronic device, which includes: At least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by at least one processor, such that the at least one processor can perform the method proposed in the first aspect of the present invention.

[0023] A fourth aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in the first aspect of the present invention. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of the present invention; Figure 2 This is a flowchart illustrating the steps of a safety protection and control method for water injection into a ship-specific cavity, as provided in an embodiment of the present invention. Figure 3 This is a functional unit schematic diagram of a safety protection and control device for the water injection process of a ship-specific cavity, provided in an embodiment of the present invention. Detailed Implementation

[0025] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0026] The present invention will be further described below with reference to the accompanying drawings.

[0027] Reference Figure 1 , Figure 1 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of the present invention.

[0028] like Figure 1 As shown, the electronic device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0029] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0030] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and an electronic program for a safety protection and control device for the water injection process of a ship-specific cavity.

[0031] exist Figure 1In the electronic device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the electronic device of the present invention can be set in the electronic device. The electronic device calls the electronic program of the ship-specific cavity water injection process safety protection control device stored in the memory 1005 through the processor 1001, and executes the ship-specific cavity water injection process safety protection control method provided in the embodiment of the present invention.

[0032] Reference Figure 2 The present invention provides a safety protection and control method for the water injection process of a ship-specific cavity, the method comprising: S201: Construct a nonlinear mathematical model of a ship-specific cavity water injection system. The model takes the opening degree of the water injection valve as input, the cavity liquid level and the water injection pipeline pressure as output, and includes a dynamic parameter vector to be identified. The formula for the nonlinear mathematical model is:

[0033] In the formula, For time l Predicted injection flow rate; In order to keep pace with time l Valve opening Relevant flow coefficients; The flow area of ​​the valve port; This refers to the pump outlet pressure. For time l The cabin air pressure; For fluid density; For time l The liquid level height; g It is the gravitational constant; For time l The cross-sectional area of ​​the cavity at the liquid level height; For time l The exhaust flow rate of the vent holes; For time l liquid level height right l The first derivative; For time l The valve opening degree; l For time indication; Due to factors such as pipe aging and biofouling, the parameters in the model are unknown time-varying variables. The dynamic parameter vector is defined as follows: The dynamic parameter vector The identification parameters include the pipeline friction coefficient. (Affected by pipe wall roughness), local resistance coefficient (Affected by elbows, valve status) and vent flow coefficient (Affected by the degree of congestion), among which, It is the transpose symbol; S202: A parameter identification module based on a swarm intelligence algorithm, which uses a sample dataset collected in real time during the water injection process to perform rolling optimization identification on the dynamic parameter vector of the nonlinear mathematical model, thereby obtaining an updated nonlinear mathematical model. S203: Construct a multi-objective optimization function for safety protection and control, with the objectives of maximizing water injection efficiency and minimizing pipeline pressure fluctuations, and with the liquid level safety threshold and pipeline pressure resistance value as constraints. S204: Based on the updated nonlinear mathematical model, the multi-objective optimization function is solved using a swarm intelligence algorithm to obtain the optimal control quantity at the current moment, and to drive the water injection regulating valve of the ship's special cavity water injection system to execute. S205: During execution, the parameter identification module is monitored in real time. If the identification parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible region or the prediction error diverges, the safety protection logic is triggered.

[0034] The technical solution provided in this application has at least the following beneficial effects: By constructing a nonlinear mathematical model containing dynamic parameter vectors and using an improved Black-winged Kite algorithm for real-time rolling identification, the model can accurately reflect changes in system characteristics caused by pipeline aging, biological attachment, etc., thus improving the model's prediction accuracy. A control strategy based on multi-objective optimization is adopted to effectively suppress pipeline pressure fluctuations while ensuring water injection efficiency. An improved Grey Wolf algorithm is used to solve for the optimal control quantity, achieving intelligent control of the water injection process. Safety monitoring and protection logic is introduced. By analyzing the changing trends and fitness values ​​of the identification parameters, abnormal states such as vent blockage and sensor malfunctions can be proactively identified, triggering graded protection measures, significantly improving safety and reliability.

[0035] In one alternative implementation, a parameter identification module based on a swarm intelligence algorithm uses a sample dataset collected in real time during the water injection process to perform rolling optimization identification on the dynamic parameter vector of the nonlinear mathematical model, resulting in an updated nonlinear mathematical model, including: S2021: Using the improved Blackwing Kite algorithm, construct a parameter identification module and define the fitness function of the parameter identification module; The fitness function of the parameter identification module is formulated as follows:

[0036] In the formula, Individual Black-winged Kite X The corresponding fitness value; For time j Individual Black-winged Kite X The parameters are substituted into the nonlinear mathematical model and the sample data is input to obtain the predicted water injection flow rate; For time j The filtered measured water injection flow rate; For time j Individual Black-winged Kite X The parameters are substituted into the nonlinear mathematical model and the sample data is input to obtain the predicted pipeline pressure; For time j The filtered measured pipeline pressure; j For time indication; X Let be the position vector of an individual Black-winged Kite; N The total number of samples in the dataset; For fitness weights; S2022: Sample datasets collected in real time during the water injection process using a sensor network; S2023: Based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is identified by rolling optimization using the sample dataset to obtain the optimal dynamic parameter vector. S2024: Update the nonlinear mathematical model based on the optimal dynamic parameter vector to obtain an updated nonlinear mathematical model.

[0037] In one alternative implementation, a sensor network is used to collect a sample dataset in real time during the water injection process, including: S20221: Use a sensor network to collect sensor data at fixed intervals; the sensor data includes measured valve opening. Actual water injection flow rate Actual pipeline pressure and the liquid level in the cavity ; S20222: Perform data preprocessing on the sensor data to obtain preprocessed sensor data; the preprocessed sensor data includes the normalized measured valve opening. Measured injection flow rate after filtering Measured pipeline pressure after filtering and the liquid level in the cavity after tilt compensation ; In this embodiment, data preprocessing includes: Normalization: For the measured valve opening Normalization is performed to eliminate the magnitude differences between different valves; Filtering: This involves processing the collected measured water injection flow rate. and measured pipeline pressure First-order hysteresis filtering is performed to remove high-frequency electromagnetic noise; Attitude compensation: Read the tiltmeter data and adjust the liquid level in the cavity. Preliminary tilt compensation is performed to eliminate measurement geometric errors caused by the ship's roll and trim. S20223: Maintain a memory array of length... N A data queue that stores the most recent data. N Preprocessed sensor data over consecutive time intervals yields a sample dataset. ,in, For time k Preprocessed sensor data, k For time indication, N This represents the total number of samples in the dataset.

[0038] In one optional implementation, based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is identified through rolling optimization using a sample dataset to obtain the optimal dynamic parameter vector, including: S20231: Based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is encoded into the individual vector of the improved Black-winged Kite algorithm; S20232: Initialize using a Logistic chaotic mapping sequence to obtain an initial black-winged kite population; each black-winged kite individual in the black-winged kite population corresponds to a candidate dynamic parameter vector; The formula is:

[0039] In the formula, For the first n+ 1. n One chaotic variable; The stability coefficient is typically 4. This sequence is ergodic and random, ensuring that the initial population is uniformly distributed in the solution space, avoiding getting trapped in local optima, which is superior to traditional random initialization. n For chaotic variable indicators;

[0040] In the formula, The first in the initial black-winged kite population i The initial individual Black-winged Kite; For the first i One chaotic variable; These are the upper and lower bounds of the search space; For individual indicators; S20233: Based on the candidate dynamic parameter vectors corresponding to the initial black-winged kite individuals in the initial black-winged kite population, construct candidate nonlinear mathematical models, input sample datasets, use fitness functions to calculate the corresponding fitness values, and take the initial black-winged kite individual with the best fitness value as the optimal solution. S20234: Introducing the Levy flight mechanism and Particle Swarm Optimization (PSO) algorithm, the initial black-winged kite population is iteratively updated based on the hovering and diving behaviors of the improved black-winged kite algorithm to obtain an updated black-winged kite population. The formula for the hovering behavior introduced by the PSO algorithm is:

[0041] In the formula, Number of iterations t+ The hovering behavior of 1 yielded the first i One new individual Blackwing Kite; Number of iterations t The optimal solution; Number of iterations t The i The historical optimal solution for an individual black-winged kite; Number of iterations t The i One updated Blackwing Kite individual, the initial Blackwing Kite individual during the initial iteration; Number of iterations t The convergence factor improves the inertia weight; The cooperation coefficient; A random number between (0, 1); t This is an indicator of the number of iterations.

[0042] In the formula, These represent the maximum and minimum values ​​of the inertia weight; This is the threshold for the number of iterations; , To adjust the parameters; It is the hyperbolic tangent function; Randomly generate a dive selection parameter ,like <threshold p (Generally 0.5), to perform soft dive behavior, the formula is:

[0043] In the formula, Number of iterations t+ The soft dive behavior of 1 yielded the first iOne new individual Blackwing Kite; A random number between [0, 1]; For flight factors; for Levy The random numbers are distributed as follows: b for Levy Step length, and b ∈[1,2]; Soft dive is an exploration-oriented behavior that guides an individual toward the currently found optimal solution. It approaches the optimal solution, but it is not entirely equivalent to flying directly to the optimal solution. Instead, it incorporates some random perturbations based on the Levy flight mechanism to avoid premature convergence. like ≥threshold p To perform a hard dive, the formula is:

[0044] In the formula, Number of iterations t+ The hard dive behavior of 1 yielded the first i One new individual Blackwing Kite; Number of iterations t Two random individuals of black-winged kites; S20235: Using the fitness function, calculate the fitness value of each updated black-winged kite individual in the updated black-winged kite population, and update the updated black-winged kite individual with the best fitness value as the optimal solution. S20236: When the number of iterations reaches the maximum number of iterations or the fitness value of the optimal solution meets the requirements, terminate the iterative update of the black-winged kite population and output the optimal solution of the current iteration; S20237: Decode the individual vector of the Black-winged Kite corresponding to the optimal solution to obtain the optimal dynamic parameter vector.

[0045] In one alternative implementation, the formula for the multi-objective optimization function is:

[0046] In the formula, For individual gray wolves Y The corresponding comprehensive target value; For individual gray wolves Y The corresponding efficiency target value; For individual gray wolves Y The corresponding safety target value; The target weight;

[0047] In the formula, For time individual gray wolf Y The parameters are substituted into the updated nonlinear mathematical model to obtain the predicted water injection flow rate from the input sample data; For prediction in the time domain; It is a time variable;

[0048] In the formula, For time individual gray wolf Y The parameters are substituted into the nonlinear mathematical model and the sample data is input to obtain the predicted pipeline pressure; The constraints include: Liquid level constraint: The liquid level must not exceed the dynamic safety limit during the prediction time domain; Pressure constraint: The pipeline pressure must not exceed the rated pressure of the pipeline; Actuator constraints: Valve opening degree ∈[0,100%], and the rate of change of opening degree at adjacent time points (To prevent mechanical shock caused by excessively rapid valve operation).

[0049] In one alternative implementation, based on an updated nonlinear mathematical model, a swarm intelligence algorithm is used to solve the multi-objective optimization function to obtain the optimal control quantity at the current moment, and to drive the water injection regulating valve of the ship's dedicated cavity water injection system to execute, including: S2041: Encode the valve opening control sequence into individual vectors of the improved Grey Wolf algorithm; Valve opening control sequence for the future Valve opening control quantity within a time period. ; S2042: Initialize using a Logistic chaotic mapping sequence to obtain an initial gray wolf population; each gray wolf in the gray wolf population corresponds to an alternative valve opening control sequence; S2043: Input the candidate valve opening control sequence corresponding to the initial gray wolf individuals in the initial gray wolf population into the updated nonlinear mathematical model for prediction, and use a multi-objective optimization function to calculate the corresponding comprehensive objective value; S2044: Based on the comprehensive objective value, perform an initial non-dominated ranking of the gray wolf population, and select the three best-performing non-dominated solutions in the non-dominated layer as Alpha. α Grey Wolf, Beta β Grey Wolf and Delta δ Grey wolf; S2045: Store all non-dominated solutions in an external archive and maintain the archive capacity limit using a grid mechanism or congestion distance; S2046: Update the position of the initial gray wolf population to obtain the updated gray wolf population; The formula is:

[0050] In the formula, For the first t+ 1, t In the population of the second iteration i Each updated individual, in the initial iteration, For the initial individual; For the first t+ 1, t The first, second, and third potential movement vectors of the next iteration; For the first t The current individual in the next iteration and Distance vector between wolves; This represents the vector of the first, second, and third control coefficients; These are the first, second, and third oscillation coefficients; A random number between [0, 1]; For control coefficients and oscillation coefficients; As a control factor; t This is an indicator of the number of iterations. For the first t Alpha in the next iteration ( α Grey Wolf, Beta β Grey Wolf and Delta δ Grey wolf; S2047: Based on the multi-objective optimization function, calculate the comprehensive objective value for each updated gray wolf individual in the updated gray wolf population, and update the Alpha in the external archive based on the comprehensive objective value. α Grey Wolf, Beta β Grey Wolf and Delta δ Grey wolf; S2048: When the number of iterations reaches the maximum number of iterations or the fitness value of the optimal solution meets the requirements, terminate the iterative update of the gray wolf population and update the Alpha value in the external archive. α The gray wolf is output as the optimal solution; S2049: Decode the individual vector of the gray wolf corresponding to the optimal solution to obtain the optimal valve opening control sequence, and set the valve opening control quantity at the beginning of the valve opening control sequence as the optimal valve opening control quantity. As the optimal control quantity; S20410: Based on the optimal control quantity, drive the water injection regulating valve of the ship's special cavity water injection system to execute, and return the parameter identification steps and safety protection control optimization to generate the dynamic parameter vector and optimal control quantity for the next moment.

[0051] In one optional implementation, the parameter identification module is monitored in real time during execution. If the identified parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible region or the prediction error diverges, the safety protection logic is triggered, including: S2051: Real-time monitoring of security anomaly characteristics of the parameter identification module during execution; the security anomaly characteristics include dynamic parameter vectors and corresponding fitness values ​​periodically output by the parameter identification module; S2052: If the vent flow coefficient is among the identification parameters of the dynamic parameter vector in the safety anomaly characteristics... If the rate of descent exceeds the preset rate threshold, the safety anomaly identification result is determined to be frost and dust accumulation in the vent holes; S2053: If the vent flow coefficient If the value is below the physically feasible region, the safety anomaly identification result is determined to be severe blockage of the vent. S2054: If the fitness value corresponding to the dynamic parameter vector in the safety anomaly feature is higher than the maximum fitness threshold, then the prediction error diverges, and the safety anomaly identification result is determined to be a sensor failure, that is, the flow meter or pressure gauge has drifted or failed. S2055: Based on the security anomaly identification result, trigger the corresponding level of security protection logic; In this embodiment, the security protection logic includes: Level 1: Detected The pressure decreases, triggering a "high air resistance" alarm, and the pressure is reduced in the optimization function. (Efficiency) weight Reduce the water injection speed; Level 2: Predicted injection flow rate detected. If the predicted liquid level will overflow in the future, or if the sensor malfunctions, or if the vent is severely blocked, immediately cut off the optimized algorithm control and switch to safety mode: force the valve to close, or operate at a fixed minimum safe opening, and switch to manual intervention.

[0052] This invention also provides a safety protection and control device for the process of filling a ship's dedicated cavity with water, as described in the following embodiments. Figure 3 The device may include the following units: The mathematical model building unit 301 is used to build a nonlinear mathematical model of a ship-specific cavity water injection system. The model takes the opening degree of the water injection valve as input, the cavity liquid level and the water injection pipeline pressure as output, and includes a dynamic parameter vector to be identified. The parameter identification unit 302 is used to construct a parameter identification module based on a swarm intelligence algorithm. It uses a sample dataset collected in real time during the water injection process to perform rolling optimization identification on the dynamic parameter vector of the nonlinear mathematical model, thereby obtaining an updated nonlinear mathematical model. The optimization function construction unit 303 is used to construct a multi-objective optimization function for safety protection control, with the objectives of maximizing water injection efficiency and minimizing pipeline pressure fluctuation, and with the liquid level safety threshold and pipeline pressure resistance value as constraints. The control quantity optimization unit 304 is used to solve the multi-objective optimization function based on the updated nonlinear mathematical model using a swarm intelligence algorithm, obtain the optimal control quantity at the current moment, and drive the water injection regulating valve of the ship's special cavity water injection system to execute. The safety anomaly identification unit 305 is used to monitor the parameter identification module in real time during execution. If the identification parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible domain or the prediction error diverges, the safety protection logic is triggered.

[0053] Based on the same inventive concept, another embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. Memory, used to store computer programs; The processor, when executing the program stored in the memory, implements the safety protection and control method for the water injection process of the ship-specific cavity of the present invention.

[0054] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EI) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. The communication interface is used for communication between the aforementioned terminal and other devices. The memory can include Random Access Memory (RAM), or non-volatile memory, such as at least one disk storage device. Optionally, the memory can also be at least one storage device located remotely from the aforementioned processor.

[0055] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0056] Furthermore, to achieve the above objectives, embodiments of the present invention also propose a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the safety protection and control method for the water injection process of a ship-specific cavity according to embodiments of the present invention.

[0057] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable hardware devices (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] The embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. "And / or" indicates that either one or both can be chosen. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes the element.

[0062] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A safety protection and control method for the water injection process of a ship-specific cavity, characterized in that, The method includes: A nonlinear mathematical model of a ship-specific cavity water injection system is constructed. The model takes the opening degree of the water injection valve as input, the cavity liquid level and the water injection pipeline pressure as output, and includes a dynamic parameter vector to be identified. The parameter identification module, built on the swarm intelligence algorithm, uses the sample dataset collected in real time during the water injection process to perform rolling optimization identification of the dynamic parameter vector of the nonlinear mathematical model, thereby obtaining an updated nonlinear mathematical model. A multi-objective optimization function for safety protection and control is constructed, with the objectives of maximizing water injection efficiency and minimizing pipeline pressure fluctuation, and the constraints being the liquid level safety threshold and the pipeline pressure resistance value. Based on the updated nonlinear mathematical model, the multi-objective optimization function is solved using a swarm intelligence algorithm to obtain the optimal control quantity at the current moment, and to drive the water injection regulating valve of the ship's special cavity water injection system to execute. During execution, the parameter identification module is monitored in real time. If the identified parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible region or the prediction error diverges, the safety protection logic is triggered.

2. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 1, characterized in that, The formula for the nonlinear mathematical model is: In the formula, For time l Predicted injection flow rate; In order to keep pace with time l Valve opening Relevant flow coefficients; The flow area of ​​the valve port; This refers to the pump outlet pressure. For time l The cabin air pressure; For fluid density; For time l The liquid level height; g It is the gravitational constant; For time l The cross-sectional area of ​​the cavity at the liquid level height; For time l The exhaust flow rate of the vent holes; For time l liquid level height right l The first derivative; For time l The valve opening degree; l For time indication; The dynamic parameter vector The identification parameters include the pipeline friction coefficient. Local drag coefficient and the flow coefficient of the vent. ,in, This is the transpose symbol.

3. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 2, characterized in that, A parameter identification module based on a swarm intelligence algorithm uses a real-time sample dataset collected during the water injection process to perform rolling optimization identification on the dynamic parameter vectors of the nonlinear mathematical model, resulting in an updated nonlinear mathematical model, including: Using the improved Black-winged Kite algorithm, a parameter identification module is constructed, and the fitness function of the parameter identification module is defined. A sample dataset collected in real time during the water injection process using a sensor network; Based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is identified by rolling optimization using the sample dataset to obtain the optimal dynamic parameter vector. The nonlinear mathematical model is updated based on the optimal dynamic parameter vector to obtain an updated nonlinear mathematical model.

4. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 3, characterized in that, The fitness function of the parameter identification module is formulated as follows: In the formula, Individual Black-winged Kite X The corresponding fitness value; For time j Individual Black-winged Kite X The parameters are substituted into the nonlinear mathematical model and the sample data is input to obtain the predicted water injection flow rate; For time j The filtered measured water injection flow rate; For time j Individual Black-winged Kite X The parameters are substituted into the nonlinear mathematical model to obtain the predicted pipeline pressure from the input sample data; For time j The filtered measured pipeline pressure; j For time indication; X Let be the position vector of an individual Black-winged Kite; N The total number of samples in the dataset; For fitness weights.

5. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 4, characterized in that, The sample dataset collected in real time during the water injection process using a sensor network includes: A sensor network is used to collect sensor data at fixed intervals; the sensor data includes measured valve opening. Actual water injection flow rate Actual pipeline pressure and the liquid level in the cavity ; The sensor data is preprocessed to obtain preprocessed sensor data; the preprocessed sensor data includes the normalized measured valve opening. Measured injection flow rate after filtering Measured pipeline pressure after filtering and the liquid level in the cavity after tilt compensation ; Maintain a memory with a length of N A data queue that stores the most recent data. N Preprocessed sensor data over consecutive time intervals yields a sample dataset. ,in, For time k Preprocessed sensor data, k For time indication, N This represents the total number of samples in the dataset.

6. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 5, characterized in that, Based on the parameter identification module, the dynamic parameter vectors of the nonlinear mathematical model are identified through rolling optimization using a sample dataset to obtain the optimal dynamic parameter vectors, including: Based on the parameter identification module, the dynamic parameter vector of the nonlinear mathematical model is encoded into the individual vector of the improved Black-winged Kite algorithm; The initial population of black-winged kites is obtained by initialization using a Logistic chaotic mapping sequence; each individual black-winged kite in the population corresponds to a candidate dynamic parameter vector. Based on the candidate dynamic parameter vectors corresponding to the initial black-winged kite individuals in the initial black-winged kite population, a candidate nonlinear mathematical model is constructed. The sample dataset is input, the fitness function is used to calculate the corresponding fitness value, and the initial black-winged kite individual with the best fitness value is taken as the optimal solution. By introducing the Levy flight mechanism and the PSO algorithm, and based on the hovering and diving behaviors of the improved black-winged kite algorithm, the initial black-winged kite population is iteratively updated to obtain the updated black-winged kite population. Using the fitness function, calculate the fitness value of each updated black-winged kite individual in the updated black-winged kite population, and update the updated black-winged kite individual with the best fitness value as the optimal solution. When the number of iterations reaches the maximum number of iterations or the fitness value of the optimal solution meets the requirements, the iterative update of the black-winged kite population is terminated, and the optimal solution of the current iteration is output. The individual vectors of the black-winged kites corresponding to the optimal solution are decoded to obtain the optimal dynamic parameter vector.

7. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 6, characterized in that, The formula for the multi-objective optimization function is: In the formula, For individual gray wolves Y The corresponding comprehensive target value; For individual gray wolves Y The corresponding efficiency target value; For individual gray wolves Y The corresponding safety target value; The target weight; In the formula, For time individual gray wolf Y The parameters are substituted into the updated nonlinear mathematical model to obtain the predicted water injection flow rate from the input sample data; For prediction in the time domain; It is a time variable; In the formula, For time individual gray wolf Y The parameters are substituted into the nonlinear mathematical model to obtain the predicted pipeline pressure from the input sample data.

8. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 7, characterized in that, Based on the updated nonlinear mathematical model, a swarm intelligence algorithm is used to solve the multi-objective optimization function to obtain the optimal control quantity at the current moment, and to drive the water injection regulating valve of the ship's special cavity water injection system to execute, including: The valve opening control sequence is encoded into individual vectors of the improved Grey Wolf algorithm; The initial gray wolf population is obtained by initialization using a Logistic chaotic mapping sequence; each gray wolf in the population corresponds to an alternative valve opening control sequence. The candidate valve opening control sequences corresponding to the initial gray wolf individuals in the initial gray wolf population are input into the updated nonlinear mathematical model for prediction, and the corresponding comprehensive objective value is calculated using a multi-objective optimization function. Based on the comprehensive objective value, an initial non-dominated ranking of the gray wolf population is performed, and the three best-performing non-dominated solutions in the non-dominated layer are taken as Alpha. α Grey Wolf, Beta β Grey Wolf and Delta δ Grey wolf; Store all non-dominated solutions in an external archive and maintain the archive capacity limit using a grid mechanism or crowding distance. The initial gray wolf population is updated in location to obtain an updated gray wolf population; Based on the multi-objective optimization function, the comprehensive objective value for each updated gray wolf individual in the updated gray wolf population is calculated, and the Alpha in the external archive is updated based on the comprehensive objective value. α Grey Wolf, Beta β Grey Wolf and Delta δ Grey wolf; The iterative update of the gray wolf population is terminated when the maximum number of iterations is reached or the fitness value of the optimal solution meets the requirements, and the Alpha value in the external archive is updated. α The gray wolf is output as the optimal solution; Decode the individual vector of the gray wolf corresponding to the optimal solution to obtain the optimal valve opening control sequence, and take the valve opening control quantity at the first position of the valve opening control sequence as the optimal control quantity. Based on the optimal control quantity, the water injection regulating valve of the ship's special cavity water injection system is driven to execute, and the parameter identification step and safety protection control optimization are returned to generate the dynamic parameter vector and optimal control quantity for the next moment.

9. The safety protection and control method for the water injection process of a ship-specific cavity according to claim 8, characterized in that, During execution, the parameter identification module is monitored in real time. If the identified parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible region or the prediction error diverges, the safety protection logic is triggered, including: During execution, the safety anomaly characteristics of the parameter identification module are monitored in real time; the safety anomaly characteristics include the dynamic parameter vector and the corresponding fitness value output periodically by the parameter identification module; If the vent flow coefficient is one of the identification parameters in the dynamic parameter vector of the safety anomaly characteristics. If the rate of descent exceeds the preset rate threshold, the safety anomaly identification result is determined to be frost and dust accumulation in the vent holes; If the vent flow coefficient If the value is below the physically feasible region, the safety anomaly identification result is determined to be severe blockage of the vent. If the fitness value corresponding to the dynamic parameter vector in the safety anomaly feature is higher than the maximum fitness threshold, then the prediction error diverges, and the safety anomaly identification result is determined to be a sensor failure. Based on the security anomaly identification results, the corresponding level of security protection logic is triggered.

10. A safety protection and control device for the water injection process of a ship-specific cavity, used to implement the safety protection and control method for the water injection process of a ship-specific cavity as described in any one of claims 1-9, characterized in that, The device includes: The mathematical model building unit is used to build a nonlinear mathematical model of a ship-specific cavity water injection system. The model takes the opening degree of the water injection valve as input, the cavity liquid level and the water injection pipeline pressure as output, and includes a dynamic parameter vector to be identified. The parameter identification unit is used to construct a parameter identification module based on swarm intelligence algorithm. It uses the sample dataset collected in real time during the water injection process to perform rolling optimization identification on the dynamic parameter vector of the nonlinear mathematical model to obtain an updated nonlinear mathematical model. The optimization function construction unit is used to construct a multi-objective optimization function for safety protection and control, with the objectives of maximizing water injection efficiency and minimizing pipeline pressure fluctuation, and with the liquid level safety threshold and pipeline pressure resistance value as constraints. The control quantity optimization unit is used to solve the multi-objective optimization function based on the updated nonlinear mathematical model using a swarm intelligence algorithm, obtain the optimal control quantity at the current moment, and drive the water injection regulating valve of the ship's special cavity water injection system to execute. The safety anomaly identification unit is used to monitor the parameter identification module in real time during execution. If the identification parameters of the dynamic parameter vector dynamically output by the parameter identification module exceed the physical feasible domain or the prediction error diverges, the safety protection logic is triggered.

Images