Ship heat exchanger control optimization method

Abstract

The invention discloses a ship heat exchanger control optimization method, and particularly relates to the technical field of ship heat exchange.The ship heat exchanger control optimization method comprises the steps that firstly, a ship heat exchanger control management database is built, then data generated in the ship heat exchange process is collected, then a multi-physics field coupling model is built, the physics field coupling model is analyzed, and the ship heat exchanger control management database is obtained; triggering a control mechanism according to an exception analysis result, performing control optimization through an optimization model, evaluating an obtained result after control optimization, and feeding back an exception evaluation result to the administrator terminal for human-computer interaction; the multi-physics coupling module is controlled through the heat exchanger, the operation of the heat exchanger and the mutual influence among the power system, the air conditioning system and the cooling system are comprehensively considered, then the control parameters of the heat exchanger can be accurately adjusted according to different working conditions, the heat exchanger is always in the optimal operation state, and the operation stability of the heat exchanger is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ship heat exchange, and in particular to a ship heat exchanger control optimization method. Background Art

[0002] In the field of ship engineering, ship heat exchangers play a vital role in ship systems. They are responsible for achieving heat transfer between different media to ensure the stable operation of ship power systems, cooling systems and other thermal management-related systems. Their performance optimization is crucial.

[0003] Existing control methods often only focus on the operating parameters of the heat exchanger itself, such as inlet and outlet temperatures and pressures. A ship is a complex system, and the operation of the heat exchanger is closely related to the power system, air conditioning system, cooling system, etc. For example, changes in the load of the power system will directly affect the thermal load of the heat exchanger. In addition, in terms of dealing with the mutual influence between systems, each system often operates independently and lacks an effective coordination mechanism, making it difficult to make reasonable parameter adjustments according to actual needs, resulting in unreasonable energy consumption and reduced equipment performance.

[0004] However, the existing ship heat exchanger control methods can no longer meet the needs of efficient, energy-saving and safe operation of ships. For example, the existing control methods only focus on the operating parameters of the heat exchanger itself, but ignore the coordination with other systems of the ship. If the control method cannot comprehensively consider the mutual influence between these systems, it will be difficult to achieve the optimized operation of the entire ship thermal management system; each system operates independently and lacks an effective coordination mechanism, and the coordinated optimization between the systems cannot be achieved, resulting in energy waste and increased equipment loss; therefore, a ship heat exchanger control optimization method based on in-depth research on the above-mentioned coordinated control is needed to improve the overall performance of the ship thermal management system. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a ship heat exchanger control optimization method to solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for optimizing control of a ship heat exchanger, comprising:

[0007] S1: Using big data technology, collect and store standard data on ship heat exchanger control, receive data generated during the ship heat exchanger control process, and build a ship heat exchanger control management database;

[0008] S2: Through sensor technology, the data generated during the ship's heat exchange process is collected to obtain and analyze various parameters of heat exchange control;

[0009] S3: Using big data analysis technology, a multi-physics coupling model is constructed for the various heat exchange control parameters obtained in S2, resulting in a power system-heat exchanger coupling model, an air conditioning system-heat exchanger coupling model, and a cooling system-heat exchanger coupling model.

[0010] S4: Analyze the multi-physics field coupling model obtained in S3 through big data analysis technology, trigger the control mechanism based on the abnormal analysis results, and optimize the control through the optimization model to obtain the optimized control results;

[0011] S5: Use big data analysis technology to evaluate the results of control optimization, and feed back abnormal evaluation results to the administrator terminal for human-computer interaction.

[0012] Technical effects and advantages of the present invention:

[0013] 1. The present invention uses various sensor technologies to collect data generated during the ship's heat exchange process, analyze various heat exchange control parameters, and accurately adjust the subsequent ship's heat exchanger control parameters. By continuously optimizing these control parameters, the heat exchanger can maintain a high heat exchange efficiency under different operating conditions, reducing energy consumption.

[0014] 2. The present invention uses a heat exchanger control multi-physics field coupling module to comprehensively consider the mutual influence between the operation of the heat exchanger and the power system, air conditioning system, and cooling system. It can then accurately adjust the control parameters of the heat exchanger according to different working conditions, so that it is always in the optimal operating state and improve the stability of the heat exchanger operation;

[0015] 3. The present invention analyzes the multi-physics field coupling model through the heat exchanger control optimization module. Once the big data analysis technology detects an abnormal result and triggers the control mechanism, the system can quickly take emergency measures; at the same time, the Lagrangian function optimization model can avoid falling into the local optimal solution, ensuring that the control strategy found is the optimal solution in the entire feasible domain, thereby realizing the control optimization of the ship heat exchanger. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the overall process of the present invention.

[0017] Figure 2 Schematic diagram of the method of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0019] See also Figure 1 As shown, the present invention provides a ship heat exchanger control optimization system, including a ship heat exchanger control management database, a heat exchanger control multi-parameter acquisition module, a heat exchanger control multi-physical field coupling module, a heat exchanger control optimization module and a heat exchanger control optimization feedback module.

[0020] The ship heat exchanger control management database is connected to all other modules, the heat exchanger control multi-parameter acquisition module is connected to the heat exchanger control multi-physical field coupling module, and the heat exchanger control optimization module is connected to the heat exchanger control multi-physical field coupling module and the heat exchanger control optimization feedback module respectively.

[0021] Ship heat exchanger control and management database: This database uses big data technology to collect and store standard control data for ship heat exchangers, while also receiving data generated during the ship heat exchanger control process to build a ship heat exchanger control and management database.

[0022] Heat exchanger control multi-parameter acquisition module: This module uses sensor technology to collect data generated during the ship's heat exchange process, analyze various heat exchange control parameters, and transmit them to the heat exchanger control multi-physics field coupling module.

[0023] Heat exchanger control multi-physics coupling module: This module uses big data analysis technology to construct a multi-physics coupling model for the various heat exchange control parameters obtained by the multi-parameter acquisition module and transmits the model to the heat exchanger control optimization module.

[0024] What needs to be specifically explained in this embodiment is that the heat exchanger control multi-physics field coupling module includes a power system-heat exchanger coupling unit, an air-conditioning system-heat exchanger coupling unit and a cooling system-heat exchanger coupling unit. The power system-heat exchanger coupling unit is used to analyze the power system-heat exchanger coupling parameters, the air-conditioning system-heat exchanger coupling unit is used to analyze the air-conditioning system-heat exchanger coupling parameters, and the cooling system-heat exchanger coupling is used to analyze the cooling system-heat exchanger coupling parameters.

[0025] Heat exchanger control optimization module: This module uses big data analysis technology to analyze the multi-physics field coupling model, triggers the control mechanism based on the abnormal analysis results, and optimizes the control through the optimization model. The control optimization results are then transmitted to the heat exchanger control optimization feedback module.

[0026] Heat exchanger control optimization feedback module: Through big data analysis technology, the results of control optimization are evaluated, and abnormal evaluation results are fed back to the administrator terminal for human-computer interaction.

[0027] See also Figure 2 As shown, a ship heat exchanger control optimization method includes: S1: using big data technology to collect and store ship heat exchanger control standard data, and at the same time receive data generated by the ship heat exchanger control process to build a ship heat exchanger control management database; S2: using sensor technology to collect data generated in the ship heat exchange process to obtain and analyze various parameters of heat exchange control; S3: using big data analysis technology to construct a multi-physical field coupling model for the various parameters of heat exchange control obtained in S2, and respectively obtain a power system-heat exchanger coupling model, an air-conditioning system-heat exchanger coupling model and a cooling system-heat exchanger coupling model; S4: using big data analysis technology to analyze the multi-physical field coupling model obtained in S3, triggering a control mechanism according to the abnormal analysis results, and at the same time performing control optimization through the optimization model to obtain the control optimization result; S5: using big data analysis technology to evaluate the control optimization result, and feeding back the abnormal evaluation result to the administrator terminal for human-computer interaction.

[0028] S1: Using big data technology, collect and store standard data on ship heat exchanger control, receive data generated during the ship heat exchanger control process, and build a ship heat exchanger control management database;

[0029] What needs to be specifically explained in this embodiment is that the standard data for the control of the ship heat exchanger includes but is not limited to the design operating status parameters of the heat exchanger in the ship heat exchanger control system, the inlet and outlet temperature ranges of the hot fluid and the cooling medium, the heat transfer efficiency range that the heat exchanger should achieve under specific working conditions, etc.; the control variables required in the control process of the ship heat exchanger, etc., for example, the control variables include the opening of the heat exchanger medium flow regulating valve, the cooling pump frequency, and the opening of the air-conditioning system expansion valve; the data generated by the ship heat exchanger control process includes but is not limited to real-time monitoring of the inlet and outlet temperatures of the hot fluid and the cooling medium, the real-time flow of the cooling medium and the hot fluid, etc.

[0030] S2: Using sensor technology, data generated during the heat exchange process of the ship is collected to obtain and analyze various parameters for heat exchange control, including power system-heat exchanger coupling parameters, air conditioning system-heat exchanger coupling parameters, and cooling system-heat exchanger coupling parameters. The power system-heat exchanger coupling parameters include the output power of the ship's main engine, the amount of heat that the heat exchanger can dissipate under the maximum design operating conditions, and the amount of heat that the heat exchanger can dissipate under the maximum design operating conditions. The air conditioning system-heat exchanger coupling parameters include the heat exchanger outlet temperature, the air conditioning system benchmark efficiency, the reference temperature for cooling efficiency attenuation under standard operating conditions, and the cooling water temperature. The cooling system-heat exchanger coupling parameters include the hot fluid inlet temperature, the hot fluid outlet temperature, the cold fluid inlet temperature, and the cold fluid outlet temperature.

[0031] S3: Using big data analysis technology, a multi-physics coupling model is constructed for the various parameters of heat exchange control obtained in S2. The power system-heat exchanger coupling model, the air conditioning system-heat exchanger coupling model, and the cooling system-heat exchanger coupling model are obtained respectively. The model includes the following steps:

[0032] S3.1: Power system-heat exchanger coupling model: First, the power sensor installed on the ship's main engine measures the main engine's output power P in real time. eng ; Then, through sensors and data acquisition systems, record the host load P eng and heat exchanger heat load Q HX The historical data of the power system are fitted with a linear regression model to obtain the intercept term β0, which represents the basic heat load of the heat exchanger when the host load is zero. The slope β1, that is, the coupling coefficient, represents the change in the heat load of the heat exchanger when the host load increases by 1MW (for example, the value is 0.85kW / MW). Secondly, the power system-heat exchanger coupling model Q is obtained through big data analysis technology: HX =β0+β1×P eng +ε, ε represents the error term; finally, the heat exchanger heat dissipation redundancy index R is obtained HX , R HX =(Q HX,max -Q HX ) / Q HX,max , Q HX,max Indicates the amount of heat that the heat exchanger can dissipate under the maximum design conditions;

[0033] It should be specifically explained in this embodiment that in a ship heat exchanger system, the main engine load generally refers to the load of the ship's main propulsion engine. The ship's main propulsion engine is the core equipment that provides the ship's forward power, usually a diesel engine, a gas turbine or a steam turbine. The main engine load represents the mechanical power currently output by the main engine, and the unit is usually megawatt (MW) or kilowatt (kW); the difference between the error term model prediction value and the actual value is called the residual, which is expressed in the linear regression model by ε=Q HX -(β0+β1×P eng ) get; Q HX,max Indicates the maximum heat dissipation capacity of the heat exchanger, that is, the amount of heat that the heat exchanger can dissipate under the maximum design conditions (unit: kW or MW).

[0034] It should be specifically explained in this embodiment that the ship's heat exchangers (such as coolers, condensers, etc.) are used to manage the heat of the main engine and other equipment to ensure that the system operates within an appropriate temperature range; the operation of the main engine generates a large amount of heat, which needs to be dissipated to the environment (such as seawater or air) through the heat exchanger; the main engine's cooling system is the main source of the heat load of the heat exchanger, so there is a direct relationship between the main engine load and the heat load of the heat exchanger.

[0035] S3.2: Air conditioning system-heat exchanger coupling model: First, use sensor technology to obtain the heat exchanger outlet temperature T HX,out ; Then, the air conditioning system benchmark efficiency η is obtained through the ship heat exchanger control standard data AC,0 And the reference temperature T of cooling efficiency decay under standard working conditions base Finally, through big data analysis technology, the air conditioning system-heat exchanger coupling model was obtained: η AC It represents the actual cooling efficiency of the air conditioning system in decimal form. λ represents the cooling efficiency attenuation coefficient (such as 0.03 / ℃), that is, for every 1℃ increase in temperature, the cooling efficiency decreases by 0.03. The cooling water temperature T is recorded through sensors and data acquisition systems. water and the cooling efficiency of the air conditioning system η AC The historical data is input into the cooling efficiency attenuation coefficient λ model:

[0036] The present embodiment needs to specifically explain that the cooling efficiency of the air-conditioning system and the heat dissipation capacity of the heat exchanger are predicted in real time based on parameters such as the cooling water temperature and flow rate. HX,out Control in the optimal range (such as 30℃≤T HX,out ≤35℃), dynamically adjust the heat exchanger operating parameters (such as cooling water flow, temperature), and balance η by increasing the cooling water flow. AC and cooling water pump energy consumption.

[0037] S3.3: Cooling system-heat exchanger coupling model: First, the hot fluid inlet temperature T is obtained at the inlet and outlet of the heat exchanger through sensor technology. h,in , hot fluid outlet temperature T h,out , cold fluid inlet temperature T c,in and the cold fluid outlet temperature T c,out ; Through the ship heat exchanger control standard data, the number of ship heat exchanger partitions n is obtained, and the cooling system-heat exchanger coupling model is obtained: H coup represents the heat exchanger capacity transfer matching degree, i represents the i-th partition, ΔT LM Indicates the actual logarithmic mean temperature difference, ΔT des Indicates the temperature difference under standard working conditions, ΔT LM Including the logarithmic mean temperature difference ΔT of the countercurrent flow of hot and cold fluids LM n The logarithmic mean temperature difference ΔT between the cold and hot fluids in countercurrent LM b ,

[0038]

[0039] In this embodiment, it is necessary to specifically explain that H coup By comparing the actual temperature difference ΔT LM The temperature difference ΔT under standard working conditions des , real-time quantification of the degree of deviation in the energy transfer efficiency of the heat exchanger; in the field of ship engineering, when the main engine load suddenly changes or the seawater temperature suddenly changes, H coup Heat transfer imbalances can be detected, triggering control compensation.

[0040] S4: Analyze the multi-physics field coupling model obtained in S3 through big data analysis technology, trigger the control mechanism based on the abnormal analysis results, and optimize the control through the optimization model to obtain the optimized control results, including the following steps:

[0041] S4.1: During the preset monitoring period of the ship heat exchanger, firstly, the multi-physics field coupling model is analyzed by big data analysis technology, and the heat exchanger heat dissipation redundancy abnormality index AR (R HX ), air conditioning system cooling efficiency abnormality index AR(η AC ) and heat exchanger capacity transfer matching abnormality index AR(H coup ), AR(R HX )=(R HX,0 -R HX ) / R HX,0 , R HX and R HX,0 represents the heat exchanger heat dissipation redundancy index and the corresponding threshold, AR(ηAC )=(η AC,0 -η AC ) / η AC,0 , η AC,0 represents the base efficiency of the air conditioning system, η AC Indicates the actual cooling efficiency of the air conditioning system, AR(H coup )=|H coup -H coup,0 | / H coup,0 , H coup Indicates the heat exchanger capacity transfer matching degree, H coup,0 Indicates the corresponding set value; then AR(R HX ), AR(η AC ) and AR(H coup ) are compared with the corresponding thresholds. If any abnormal result occurs, the control mechanism is triggered. The abnormal results include AR(R HX ) is greater than the corresponding threshold AR(R HX ) 0 (e.g. 10%), AR(η AC ) is greater than the corresponding threshold AR(η AC ) 0 (e.g. 10%) and AR(H coup ) is greater than the corresponding threshold AR(H coup ) 0 (e.g. deviation of ±15%);

[0042] S4.2: Based on the abnormal result trigger control mechanism of S4.1, the Lagrangian function is used to build the optimization model L for optimization. w1, w2 and w3 represent the corresponding weights, which are dynamically adjusted based on the actual ship operating conditions according to historical data. For example, when operating at high speed, priority is given to ensuring the cooling of the main engine w1 = 0.7, and when mooring in the port, priority is given to maintaining air conditioning comfort w2 = 0.6, etc. j (X) represents the constraint function, g1(X)=T out -T max ≤0, T out Indicates the outlet temperature of the heat exchanger, T max Indicates the maximum allowable temperature, g2(X)=f in -f max ≤0,f in Indicates the inlet pressure of the heat exchanger, f max Indicates the maximum allowable pressure, g3(X)=m c -m max ≤0,m c Indicates cooling water flow rate, m max Indicates the maximum flow allowed, γ j represents the Lagrange multiplier of the j-th constraint function;

[0043] It should be specifically explained in this embodiment that the Lagrangian function is an important tool in the field of mathematical optimization for solving constrained optimization problems. By combining constraints with the objective function, it transforms the originally complex constrained optimization problem into an unconstrained optimization problem. Different constraints correspond to different physical limitations, resulting in different Lagrangian multipliers. In the field of ship engineering, the Lagrangian function can be used to balance multiple objectives such as cooling efficiency, energy matching, and heat dissipation redundancy, while satisfying constraints such as flow rate and temperature.

[0044] S4.3: Obtain the required control variables through the ship heat exchanger control management database, and use the sequential quadratic programming (such as SQP) algorithm to iteratively solve the optimization model L obtained in S4.2, so that L is the largest control variable data set U opt , U opt =[U1,U2,...,U N ],U N Represents the Nth control variable, N represents the number of control variables, and the optimal control parameter is obtained by the gradient of the optimization model L being 0. For example, the control variables include the opening of the heat exchanger medium flow regulating valve, the cooling pump frequency, and the opening of the air conditioning system expansion valve; then according to U opt And the corresponding current state, the calculated adjustment amount, generates the corresponding control instructions, such as U opt The opening of the heat exchanger medium flow regulating valve should be set to 85%, but it is currently 70%, so it needs to be increased by 15%;

[0045] It is important to note that Sequential Quadratic Programming (SQP) is an iterative algorithm for solving nonlinear constrained optimization problems. It approaches the optimal solution to the original problem by solving a quadratic programming (QP) subproblem in each iteration. The SQP algorithm performs well in solving optimization problems with complex constraints and is therefore widely used in solving optimal control parameters in control systems.

[0046] S5: Through big data analysis technology, the results of control optimization are evaluated, and the abnormal evaluation results are fed back to the administrator terminal for human-computer interaction. Through data monitoring technology, the heat exchanger heat dissipation redundancy abnormality index AR (R HX ), air conditioning system cooling efficiency abnormality index AR(η AC ) and heat exchanger capacity transfer matching abnormality index AR(H coup ), if abnormal results occur within M consecutive preset control cycles, the optimization model L calibration feedback mechanism is triggered to the administrator terminal.

[0047] What needs to be specifically explained in this embodiment is that the abnormal evaluation results are fed back to the administrator terminal in real time, so that the administrator can promptly understand the system operation status. According to the feedback results, the parameters or structure of the optimization model L are automatically adjusted to improve the accuracy and adaptability of the model, forming a closed-loop control system of "control-evaluation-feedback-calibration", so that the control strategy of the ship heat exchanger can be continuously optimized.

[0048] Secondly: The drawings of the embodiments disclosed in the present invention only involve structures related to the embodiments disclosed in the present invention. Other structures may refer to conventional designs. The same embodiment and different embodiments of the present invention may be combined with each other without conflict.

[0049] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling and optimizing a ship heat exchanger, characterized in that: include: S1: Using big data technology, collect and store standard data on ship heat exchanger control, receive data generated during the ship heat exchanger control process, and build a ship heat exchanger control management database; S2: Through sensor technology, the data generated during the ship's heat exchange process is collected to obtain and analyze various parameters of heat exchange control; S3: Using big data analysis technology, a multi-physics coupling model is constructed for the various heat exchange control parameters obtained in S2, resulting in a power system-heat exchanger coupling model, an air conditioning system-heat exchanger coupling model, and a cooling system-heat exchanger coupling model. S4: Analyze the multi-physics field coupling model obtained in S3 through big data analysis technology, trigger the control mechanism based on the abnormal analysis results, and optimize the control through the optimization model to obtain the optimized control results; S5: Use big data analysis technology to evaluate the results of control optimization, and feed back abnormal evaluation results to the administrator terminal for human-computer interaction.

2. A ship heat exchanger control optimization method according to claim 1, characterized in that: The parameters in S2 include power system-heat exchanger coupling parameters, air conditioning system-heat exchanger coupling parameters and cooling system-heat exchanger coupling parameters, wherein the power system-heat exchanger coupling parameters include the output power of the ship's main engine, the amount of heat that the heat exchanger can dissipate under the maximum design operating conditions, and the amount of heat that the heat exchanger can dissipate under the maximum design operating conditions; the air conditioning system-heat exchanger coupling parameters include the heat exchanger outlet temperature, the air conditioning system benchmark efficiency, the reference temperature for cooling efficiency attenuation under standard operating conditions, and the cooling water temperature; the cooling system-heat exchanger coupling parameters include the hot fluid inlet temperature, the hot fluid outlet temperature, the cold fluid inlet temperature, and the cold fluid outlet temperature.

3. The ship heat exchanger control optimization method according to claim 1, characterized in that: The power system-heat exchanger coupling model is obtained in S3: First, the output power P of the main engine is measured in real time by the power sensor installed on the main engine of the ship. eng ; Then, through sensors and data acquisition systems, record the host load P eng and heat exchanger heat load Q HX The historical data of the power system are used to fit the linear regression model to obtain the intercept term β0, which represents the basic heat load of the heat exchanger when the host load is zero, and the slope β1, which is the coupling coefficient; secondly, the power system-heat exchanger coupling model is obtained through big data analysis technology: Q HX =β0+β1×P eng +ε, ε represents the error term; finally, the heat exchanger heat dissipation redundancy index R is obtained HX , R HX =(Q HX,max -Q HX ) / Q HX,max , Q HX,max Indicates the amount of heat that a heat exchanger can dissipate under maximum design conditions.

4. The ship heat exchanger control optimization method according to claim 1, characterized in that: The air conditioning system-heat exchanger coupling model is obtained in S3: First, the heat exchanger outlet temperature T is obtained through sensor technology. HX,out ; Then, the air conditioning system benchmark efficiency η is obtained through the ship heat exchanger control standard data AC,0 And the reference temperature T of cooling efficiency decay under standard working conditions base Finally, through big data analysis technology, the air conditioning system-heat exchanger coupling model was obtained: η AC It represents the actual cooling efficiency of the air conditioning system in decimal form, and λ represents the cooling efficiency attenuation coefficient; the cooling water temperature T is recorded through sensors and data acquisition systems. water and the cooling efficiency of the air conditioning system η AC The historical data is input into the cooling efficiency attenuation coefficient λ model:

5. The ship heat exchanger control optimization method according to claim 1, characterized in that: The cooling system-heat exchanger coupling model is obtained in S3: First, the hot fluid inlet temperature T is obtained at the hot and cold fluid inlets and outlets of the heat exchanger through sensor technology. h,in , hot fluid outlet temperature T h,out , cold fluid inlet temperature T c,in and the cold fluid outlet temperature T c,out ; Through the ship heat exchanger control standard data, the number of ship heat exchanger partitions n is obtained, and the cooling system-heat exchanger coupling model is obtained: H coup represents the heat exchanger capacity transfer matching degree, i represents the i-th partition, ΔT LM Indicates the actual logarithmic mean temperature difference, ΔT des Indicates the temperature difference under standard working conditions, ΔT LM Including the logarithmic mean temperature difference ΔT of the countercurrent flow of hot and cold fluids LM n The logarithmic mean temperature difference ΔT between the cold and hot fluids in countercurrent LM b .

6. A ship heat exchanger control optimization method according to claim 1, characterized in that: Said S4 includes: S4.1: During the preset monitoring period of the ship heat exchanger, firstly, the multi-physics field coupling model is analyzed by big data analysis technology, and the heat exchanger heat dissipation redundancy abnormality index AR (R HX ), air conditioning system cooling efficiency abnormality index AR(η AC ) and heat exchanger capacity transfer matching abnormality index AR(H coup ); then AR(R HX ), AR(η AC ) and AR(H coup ) are compared with the corresponding thresholds. If any abnormal result occurs, the control mechanism is triggered. The abnormal results include AR(R HX ) is greater than the corresponding threshold AR(R HX ) 0 、AR(η AC ) is greater than the corresponding threshold AR(η AC ) 0 and AR(H coup ) is greater than the corresponding threshold AR(H coup ) 0 ; S4.2: Based on the abnormal result trigger control mechanism of S4.1, the Lagrangian function is used to build the optimization model L for optimization. w1, w2 and w3 represent the corresponding weights, g j (X) represents the constraint function, g1(X)=T out -T max ≤0, T out Indicates the outlet temperature of the heat exchanger, T max Indicates the maximum allowable temperature, g2(X)=f in -f max ≤0,f in Indicates the inlet pressure of the heat exchanger, f max Indicates the maximum allowable pressure, g3(X)=m c -m max ≤0,m c Indicates cooling water flow rate, m max Indicates the maximum flow allowed, γ j represents the Lagrange multiplier of the j-th constraint function.

7. The ship heat exchanger control optimization method according to claim 1, characterized in that: Said S4 also includes: S4.3: Obtain the required control variables through the ship heat exchanger control management database, and use the sequential quadratic programming algorithm to iteratively solve the optimization model L obtained in S4.2 to obtain the control variable data set U that maximizes L. opt , U opt =[U1,U2,...,U N ],U N Represents the Nth control variable, N represents the number of control variables, and the optimal control parameter is obtained by the gradient of the optimization model L being 0; then according to U opt And the corresponding current state, calculate the adjustment amount, and generate the corresponding control instructions.

8. The ship heat exchanger control optimization method according to claim 1, characterized in that: The S5 includes: using data monitoring technology to monitor the heat exchanger heat dissipation redundancy abnormality index AR (R HX ), air conditioning system cooling efficiency abnormality index AR(η AC ) and heat exchanger capacity transfer matching abnormality index AR(H coup ), if abnormal results occur within M consecutive preset control cycles, the optimization model L calibration feedback mechanism is triggered to the administrator terminal.

Images