Underwater ship water heater transient temperature control method and system

Abstract

The invention discloses a transient temperature control method and system for an underwater ship water heater. The method comprises the steps that temperature values Tcurrent, corresponding target temperature values Ttarget and real-time electrical loads Pshift of n monitoring points of the underwater ship water heater are obtained; based on the temperature value Tcurrent of the monitoring point, the corresponding target temperature value Ttarget and the real-time electrical load Pship, constructing a first state vector st; based on the first state vector st, defining a heating power adjustment amount delta Q as an action at; based on the action at, constructing a first segmentation award function coupling temperature error and energy consumption; on the basis of the above steps, an Actor-Critic network containing a space-time attention mechanism is constructed; and quantitatively deploying the trained Actor network to an embedded controller. The method has the advantages of high-precision temperature field control, dynamic load self-adaption, energy-saving efficiency improvement, system-level energy efficiency optimization, high engineering applicability and the like.

Description

Technical Field

[0001] The present invention belongs to the field of computer system engineering, and in particular relates to a transient temperature control method and system for an underwater ship water heater. Background Art

[0002] In the field of underwater ship water heater control, traditional temperature control methods mainly rely on PID (proportional-integral-differential) control or rule-based logic control. Although these methods are simple and easy to implement, they have significant technical limitations in the dynamic and complex underwater environment:

[0003] Underwater ship water heaters are typically large and multi-zoned. Traditional single-point temperature measurement combined with PID control cannot detect the spatial heterogeneity of the temperature field, resulting in localized overheating or insufficient heating. Experimental data shows that in systems using PID control, the standard deviation of the temperature field can reach over ±5°C, significantly affecting the life of the equipment.

[0004] Ship power systems need to power multiple loads, including propulsion, lighting, and communications. The power load P_ship can experience instantaneous fluctuations of more than 20%. Traditional fixed-threshold power allocation strategies often cause two problems:

[0005] When the load suddenly increases, the heating power is not reduced in time, causing the power system to overload and trip;

[0006] When the load drops suddenly, the heating power fails to increase quickly, resulting in a delay in temperature recovery (the measured delay is 3-5 minutes).

[0007] Existing methods ignore the nonlinear characteristics of thermodynamic processes:

[0008] The transfer function of heating power and temperature change varies with water flow velocity and ambient pressure;

[0009] Thermal inertia causes a lag in temperature response, making it difficult to adaptively adjust PID parameters. Tests on a certain deep-sea vessel showed that traditional methods overshoot by more than 8°C under variable operating conditions.

[0010] Marine energy systems require strict energy efficiency management, but traditional methods focus solely on temperature deviations, without considering energy consumption indicators. Statistics show that inefficient power consumption in existing systems during steady-state operation accounts for as much as 15%-20%.

[0011] The underwater environment places extremely high demands on equipment reliability, but traditional control lacks the ability to control temperature gradients. Real-time monitoring may cause thermal stress cracking of sealing materials (in one case causing flange leakage).

[0012] In recent years, although some studies have attempted to introduce fuzzy control and model predictive control (MPC) into this field, the following problems still exist:

[0013] Fuzzy rules rely on expert experience and are difficult to cover all working conditions;

[0014] MPC requires a high-precision thermodynamic model, but underwater environmental parameters (such as seawater permeability) are difficult to accurately model in real time;

[0015] None of the existing methods achieves multi-objective collaborative optimization of load, temperature and energy consumption. Summary of the Invention

[0016] In view of the above-mentioned defects in the prior art, the present invention provides a method for controlling the transient temperature of an underwater ship water heater, comprising the following steps:

[0017] Step 1: Obtain the temperature values ​​T of n monitoring points of the underwater ship water heater current , the corresponding target temperature value T target and real-time power load P ship ;

[0018] Step 2: Based on the temperature value T of the monitoring point current , the corresponding target temperature value T target and real-time power load P ship , construct the first state vector s t ;

[0019] Step 3: Based on the first state vector s t , define the heating power adjustment ΔQ as action a t ;

[0020] Step 4: Based on the action a t , construct the first piecewise reward function coupling temperature error and energy consumption;

[0021] Step 5: Based on the above steps, build an Actor-Critic network with spatiotemporal attention mechanism;

[0022] Step 6: Quantize and deploy the trained Actor network to the embedded controller.

[0023] Among them, the temperature values ​​T of the n monitoring points in step 1 are current The constructed n-dimensional spatial distribution features are used for the motion amplitude constraint in step three and the temperature gradient penalty calculation in step four.

[0024] The heating power adjustment amount ΔQ in step 3 is the t , ΔQ range is [-f(P ship ),f(P ship)], where f(P ship )=Q max *(1-P ship / P rated ) is the load adaptive limiting function, P rated Indicates the rated load power of the ship's power system, Q max Indicates the maximum allowable power change rate of the heater under rated load.

[0025] Among them, the load adaptive limit function f(P ship ) is determined by the following process:

[0026] Establish a ship load-heating power constraint database, including different real-time power loads P ship Maximum permissible heating power Q under allow ;

[0027] Use cubic spline interpolation to fit Q allow With P ship The relationship curve of

[0028] Introducing the safety margin coefficient η∈(0,1), we can finally determine f(P ship )=η·Q allow (P ship ).

[0029] The first segment reward function in step 4 is calculated using the following formula: Where λ is the dynamic weight coefficient.

[0030] The spatiotemporal attention mechanism of step 5 includes:

[0031] The spatial attention layer uses the following formula to calculate the attention weight of each temperature measurement point Where i represents the i-th temperature measurement point, v represents a trainable parameter vector used to map hidden features into scalar attention scores, and W represents a trainable weight matrix used to fuse the current temperature and target temperature features. Indicates the current temperature value of the i-th temperature measurement point; T target Indicates the global target temperature value;

[0032] Temporal convolution layer, which uses dilated convolution to extract multi-scale temporal features;

[0033] Action generation layer, which outputs Gaussian distributed actions with exploration noise.

[0034] Among them, the Actor network in step 5 takes the first state vector of step 2 as input and outputs the action a of step 3 t , with the action a tThe range of the relevant exploration noise is dynamically adjusted according to the cumulative reward calculated based on the first piecewise reward function in step 4.

[0035] The Critic network in step 5 is based on the first state vector in step 2 and the action a in step 3. t The output value function is used to evaluate the first segment reward function in step 4.

[0036] The step six specifically includes: performing the action a of step three at a fixed period Δt. t Generate, wherein Δt is adaptively adjusted according to the rate of change of the real-time power load in step 1.

[0037] The present invention also proposes a transient temperature control system for an underwater ship water heater, comprising:

[0038] The sensor module is used to obtain the temperature value T of n monitoring points of the underwater ship water heater. current , the corresponding target temperature value T target and real-time power load P ship ;

[0039] A state vector building module is used to construct a state vector based on the temperature value T of the monitoring point. current , the corresponding target temperature value T target and real-time power load P ship , construct the first state vector s t ;

[0040] A space definition module is used to define a state vector s based on the first state vector s t , define the heating power adjustment ΔQ as action a t ;

[0041] Reward function building module, which is used to t , construct the first piecewise reward function coupling temperature error and energy consumption;

[0042] The network construction module is used to build an Actor-Critic network with spatiotemporal attention mechanism based on the above steps;

[0043] An embedded controller, which is used to quantize and deploy the trained Actor network.

[0044] Compared with the prior art, the present invention has the following advantages:

[0045] High-precision temperature field control: the spatiotemporal attention mechanism can capture the spatial correlation of n temperature measurement points, reducing the standard deviation of the temperature field to within ±1.2°C (measured data);

[0046] Dynamic load adaptation, the load adaptive limiting function f(P_ship) realizes millisecond-level power adjustment. When the load suddenly changes:

[0047] The power response delay is shortened from 3s in traditional methods to 0.1s;

[0048] The power system stability index RI increased to 0.92 (out of 1).

[0049] The dynamic weight coefficient λ achieves a real-time trade-off between energy consumption and temperature control, improving energy efficiency by 18%.

[0050] exist When the limit is exceeded, power reduction is triggered within 2ms, and the failure rate is reduced to 0.01 times / 1,000 hours.

[0051] System-level energy efficiency optimization, λP_ship(ΔQ) in the reward function 2 The system suppresses ineffective power consumption, improving the overall energy efficiency ratio (COP) from 2.1 to 2.8; it maintains control continuity in the event of a sensor failure, with an availability of 99.99%.

[0052] The engineering applicability is enhanced. The technical effect of the present invention has been verified by sea trials. Compared with traditional PID control: temperature control accuracy is improved by 76%, energy consumption is reduced by 22%, and emergency condition response speed is increased by 40 times, which fully solves the technical difficulties in the background technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and other objects, features and advantages of the exemplary embodiments of the present disclosure will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present disclosure are shown in an illustrative and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0054] Figure 1 is a flow chart showing a method for controlling transient temperature of an underwater ship water heater according to an embodiment of the present invention;

[0055] Figure 2 is a schematic diagram showing the logical relationship of parameters in steps 2 to 5 according to an embodiment of the present invention; and

[0056] Figure 3 FIG. 4 is a diagram showing a network architecture of a Critic network according to an embodiment of the present invention. DETAILED DESCRIPTION

[0057] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0058] The terms used in the embodiments of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The singular forms "a," "an," "the," and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, and unless the context clearly indicates otherwise, "a plurality" generally includes at least two.

[0059] It should be understood that although the terms "first," "second," "third," etc. may be used to describe "...," these "..." should not be limited to these terms. These terms are merely used to distinguish "...." For example, "first..." could also be referred to as "second...", and similarly, "second..." could also be referred to as "first..." without departing from the scope of the present invention.

[0060] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0061] As used herein, the words "if" and "if" may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to the determination" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0062] It should also be noted that the terms "include," "comprises," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a product or device comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such product or device. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the product or device comprising the element.

[0063] The optional embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0064] Example 1

[0065] like Figure 1 As shown, the present invention discloses a method for transient temperature control of an underwater ship water heater, comprising the following steps:

[0066] Step 1: Obtain the temperature values ​​T of n monitoring points of the underwater ship water heater current , the corresponding target temperature value T target and real-time power load P ship ;

[0067] Step 2: Based on the temperature value T of the monitoring point current , the corresponding target temperature value T target and real-time power load P ship , construct the first state vector s t ;

[0068] Step 3: Based on the first state vector s t , define the heating power adjustment ΔQ as action a t ;

[0069] Step 4: Based on the action a t , construct the first piecewise reward function coupling temperature error and energy consumption;

[0070] Step 5: Based on the above steps, build an Actor-Critic network with spatiotemporal attention mechanism;

[0071] Step 6: Quantize and deploy the trained Actor network to the embedded controller.

[0072] Example 2

[0073] The present invention proposes a method for controlling the transient temperature of an underwater ship water heater, comprising the following steps:

[0074] Step 1: Obtain the temperature values ​​T of n monitoring points of the underwater ship water heater current , the corresponding target temperature value T target and real-time power load P ship ;

[0075] Step 2: Based on the temperature value T of the monitoring point current , the corresponding target temperature value T target and real-time power load P ship , construct the first state vector s t ;

[0076] Step 3: Based on the first state vector s t , define the heating power adjustment ΔQ as action a t ;

[0077] Step 4: Based on the action a t , construct the first piecewise reward function coupling temperature error and energy consumption;

[0078] Step 5: Based on the above steps, build an Actor-Critic network with spatiotemporal attention mechanism;

[0079] Step 6: Quantize and deploy the trained Actor network to the embedded controller.

[0080] Among them, the temperature values ​​T of the n monitoring points in step 1 are current The constructed n-dimensional spatial distribution features are used for the motion amplitude constraint in step three and the temperature gradient penalty calculation in step four.

[0081] Among them, T current 、T target and P ship Composed state vector s t =[T current ,T target ,P ship ], T current is the normalized n-dimensional temperature field vector.

[0082] The heating power adjustment amount ΔQ in step 3 is the t , ΔQ range is [-f(P ship ),f(P ship )], where f(P ship )=Q base *(1-P ship / P rated ) is the load adaptive limiting function, P rated Indicates the rated load power of the ship's power system, Q base Indicates the maximum adjustment of the heater at rated load.

[0083] Among them, the action a t The output of the standardized strategy is converted into the actual power adjustment through linear mapping, that is, ΔQ = a t ·f(P ship ).

[0084] Among them, the load adaptive limit function f(P ship ) is determined by the following process:

[0085] Establish a ship load-heating power constraint database, including different real-time power loads P ship Maximum permissible heating power Q under allow ;

[0086] Use cubic spline interpolation to fit Q allow With P ship The relationship curve of

[0087] Introducing the safety margin coefficient η∈(0,1), we can finally determine f(P ship )=η·Q allow (P ship ).

[0088] Among them, Q allow (P ship ) indicates the ship's current load P ship The theoretical maximum allowable heating power (unit: kW) under the condition of φ 100-1500 is the upper limit of heating power to ensure stable operation of ship power system.

[0089] Q allow (P ship )=min(P rated -P ship , Q thermal ), where P rated -P ship Indicates the remaining capacity of the power system, Q thermal Indicates the thermodynamic limit power of the water heater (determined by the heat dissipation capacity).

[0090] In order to prevent the overload risk caused by load fluctuation and measurement error, η∈(0.7,0.95) (engineering experience value) is set. η0 represents the basic safety factor (default is 0.9), k represents the load change rate sensitivity coefficient, Indicates the absolute value of the instantaneous rate of change of load.

[0091] like Figure 2 The figure shows the logical relationship diagram of the parameters in steps 2 to 5.

[0092] The first segment reward function in step 4 is calculated using the following formula: Where λ is the dynamic weight coefficient.

[0093] Among them, λ=λ0·xxp(-μt)+λ min , t is the number of training steps, μ is the decay coefficient, λ0 and λ min are the initial value and lower limit respectively.

[0094] The spatiotemporal attention mechanism of step 5 includes:

[0095] The spatial attention layer uses the following formula to calculate the attention weight of each temperature measurement point Where i represents the i-th temperature measurement point, v represents a trainable parameter vector used to map hidden features into scalar attention scores, and W represents a trainable weight matrix used to fuse the current temperature and target temperature features. Indicates the current temperature value of the i-th temperature measurement point; T target Indicates the global target temperature value;

[0096] Temporal convolution layer, which uses dilated convolution to extract multi-scale temporal features;

[0097] Action generation layer, which outputs Gaussian distributed actions with exploration noise.

[0098] Where v∈R d×1 is a trainable projection vector, W∈R d×2 is the trainable weight matrix, With T target The splicing operation realizes local-global feature fusion.

[0099] Among them, the Actor network in step 5 takes the first state vector of step 2 as input and outputs the action ΔQ of step 3, which is consistent with the action a t The range of the relevant exploration noise is dynamically adjusted according to the cumulative reward calculated based on the first piecewise reward function in step 4.

[0100] In simple terms, the Actor network outputs an action a t =π θ (s t )+ε, Critic network output state-action value function ε is the exploration noise, ε~N(0,σ 2 ),π θ For the strategic network.

[0101] The final power command must meet, Q t+1 =Q t +ΔQ∈[0,Q max ],(Q max is the absolute maximum power of the heater).

[0102] The Critic network in step 5 is based on the first state vector s in step 2. t and action a in step three t As input, the output value function is used to evaluate the first segment reward function of step 4. Figure 3 Shown is the network architecture diagram of the Critic network.

[0103] The mathematical expression of the above is:

[0104] The step six specifically includes: executing the action ΔQ generation of the step three at a fixed period Δt, wherein Δt is adaptively adjusted according to the rate of change of the real-time power load of the step one.

[0105] Example 3:

[0106] The present invention also proposes a transient temperature control system for an underwater ship water heater, comprising:

[0107] The sensor module is used to obtain the temperature value T of n monitoring points of the underwater ship water heater. current , the corresponding target temperature value T target and real-time power load P ship ;

[0108] A state vector building module is used to construct a state vector based on the temperature value T of the monitoring point. current , the corresponding target temperature value T target and real-time power load P ship , construct the first state vector s t ;

[0109] A space definition module is used to define a state vector s based on the first state vector s t , define the heating power adjustment ΔQ as action a t ;

[0110] Reward function building module, which is used to t , construct the first piecewise reward function coupling temperature error and energy consumption;

[0111] The network construction module is used to build an Actor-Critic network with spatiotemporal attention mechanism based on the above steps;

[0112] An embedded controller, which is used to quantize and deploy the trained Actor network.

[0113] The system also includes an exception handling module, which is used to use Kalman filtering to estimate missing temperature data when a sensor failure is detected; switch to a local cache control strategy when communication is interrupted; and force the energy system to enter a low-power mode when an abnormality occurs.

[0114] Example 4:

[0115] An embodiment of the present disclosure provides a non-volatile computer storage medium, wherein the computer storage medium stores computer-executable instructions, and the computer-executable instructions can execute the method steps described in the above embodiment.

[0116] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0117] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0118] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0119] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0121] The above introduces the preferred embodiments of the present invention, which is intended to make the spirit of the present invention clearer and easier to understand, and is not intended to limit the present invention. Any modifications, replacements, and improvements made within the spirit and principles of the present invention should be included in the scope of protection outlined by the claims attached to the present invention.

Claims

1. A method for controlling transient temperature of an underwater ship water heater, characterized in that: The following steps are involved: Step 1: Obtain the temperature values ​​T of n monitoring points of the underwater ship water heater current , the corresponding target temperature value T target and real-time power load P ship ; Step 2: Based on the temperature value T of the monitoring point current , the corresponding target temperature value T target and real-time power load P ship , construct the first state vector s t ; Step 3: Based on the first state vector s t , define the heating power adjustment ΔQ as action a t ; Step 4: Based on the action a t , construct the first piecewise reward function coupling temperature error and energy consumption; Step 5: Based on the above steps, build an Actor-Critic network with spatiotemporal attention mechanism; Step 6: Quantize and deploy the trained Actor network to the embedded controller.

2. The method according to claim 1, wherein The temperature values ​​T of the n monitoring points in step 1 current The constructed n-dimensional spatial distribution features are used for the motion amplitude constraint in step three and the temperature gradient penalty calculation in step four.

3. The method according to claim 1, wherein: The heating power adjustment amount ΔQ in step 3 is the action a t , ΔQ range is [-f(P ship ),f(P ship )], where f(P ship )=Q max *(1-P ship / {r ated ) is the load adaptive limiting function, P rated Indicates the rated load power of the ship's power system, Q max Indicates the maximum allowable power change rate of the heater under rated load.

4. The method according to claim 3, wherein: The load adaptive limit function f(P ship ) is determined by the following process: Establish a ship load-heating power constraint database, including different real-time power loads P ship Maximum permissible heating power Q under allow ; Use cubic spline interpolation to fit Q allow With P ship The relationship curve of Introducing the safety margin coefficient η∈(0,1), we can finally determine f(P ship )=η·Q allow (P ship ).

5. The method according to claim 1, wherein: The first segment reward function in step 4 is calculated using the following formula: Where λ is the dynamic weight coefficient.

6. The method according to claim 1, wherein: The spatiotemporal attention mechanism of step 5 includes: The spatial attention layer uses the following formula to calculate the attention weight of each temperature measurement point Where i represents the i-th temperature measurement point, v represents a trainable parameter vector used to map hidden features into scalar attention scores, and W represents a trainable weight matrix used to fuse the current temperature and target temperature features. Indicates the current temperature value of the i-th temperature measurement point; T target Indicates the global target temperature value; Temporal convolution layer, which uses dilated convolution to extract multi-scale temporal features; Action generation layer, which outputs Gaussian distributed actions with exploration noise.

7. The method according to claim 1, wherein: In step five, the Actor network uses the first state vector s in step two t As input, output action a in step three t , with the action a t The range of the relevant exploration noise is dynamically adjusted according to the cumulative reward calculated based on the first piecewise reward function in step 4.

8. The method according to claim 1, wherein: In step five, the critic network uses the first state vector in step two and the action a in step three t The output value function is used to evaluate the first segment reward function in step 4.

9. The method according to claim 1, wherein: The step six specifically includes: performing the action a of step three at a fixed period Δt. t Generate, wherein Δt is adaptively adjusted according to the rate of change of the real-time power load in step 1.

10. A transient temperature control system for an underwater ship water heater, comprising: The sensor module is used to obtain the temperature value T of n monitoring points of the underwater ship water heater. current , the corresponding target temperature value T target and real-time power load P ship ; A state vector building module is used to construct a state vector based on the temperature value T of the monitoring point. current , the corresponding target temperature value T target and real-time power load P ship , construct the first state vector s t ; A space definition module is used to define a state vector s based on the first state vector s t , define the heating power adjustment ΔQ as action a t ; Reward function building module, which is used to t , construct the first piecewise reward function coupling temperature error and energy consumption; The network construction module is used to build an Actor-Critic network with spatiotemporal attention mechanism based on the above steps; An embedded controller, which is used to quantize and deploy the trained Actor network.

Images