Ship pipeline electric heating method and system

Abstract

The invention discloses a ship pipeline electric heating method and system, and belongs to the technical field of ship pipeline heating. The method comprises the following steps: training an initial neural network model through historical temperature data and historical heating power data to obtain a ship pipeline electric heating control prediction model; inputting the real-time temperature data and the real-time heating power data into a ship pipeline electric heating control prediction model to obtain electric heating control prediction data, and calculating an electric heating demand power prediction value by combining the real-time temperature data to obtain an electric heating demand power prediction value; and the electric heating process of the ship pipeline is adjusted based on the electric heating demand power predicted value, so that not only is the poor heating and heat preservation effect caused by only depending on constant power heating avoided, but also the electric heat tracing energy consumption can be reduced aiming at complex and changeable temperature fluctuation in polar navigation, and the ship pipeline electric heating efficiency is improved. The heating accuracy and reliability of the ship pipeline are improved, and normal operation of the ship in the polar region environment is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of ship pipeline heating, and in particular relates to a ship pipeline electric heating method and system. Background Art

[0002] With the continued warming of the global climate and the gradual reduction of extremely low ice, polar navigation has become an important development direction for shipping. However, the extremely low temperatures in the polar environment place higher demands on ships, especially the cold and frost protection of ship pipelines. Ship pipelines are key channels for transporting liquids such as fuel, hydraulic oil, fresh water, and wastewater. Their reliable operation in extremely low temperature environments is directly related to the functional stability of the ship's power system and life support systems. If the fluid in the pipeline freezes or its fluidity decreases, it may cause serious accidents such as pipeline rupture, valve failure, power outage, and even threaten the ship's navigation safety and mission execution capabilities in the polar regions. Therefore, heating and insulating ship pipelines during polar navigation has become key to ensuring polar navigation.

[0003] At present, for the heating and insulation of ship pipelines under extremely low navigation conditions, most methods are to wrap them with insulation materials, heat them with steam, or use electric heating. However, in polar environments, the external temperature varies greatly, and it is difficult to completely isolate the external cold source by wrapping them with insulation materials, and it is impossible to dynamically respond to temperature fluctuations. The use of steam heating can easily cause local overheating or ice blockage of the pipelines, resulting in unsatisfactory heating effect on the ship pipelines and inability to accurately heat the ship pipelines. In addition, the existing electric heating belongs to fixed-power heating, which can only achieve a good heating effect within the set temperature range. After exceeding the temperature range, the heating and insulation effect of the ship pipelines will be greatly reduced. In addition, the large temperature fluctuations also lead to excessively high energy consumption of the current electric heating. Therefore, there is an urgent need for an electric heating method and system for ship pipelines to solve the defects of the existing technology. Summary of the Invention

[0004] The present invention aims to provide a method and system for electrically heating ship pipelines to solve the above-mentioned technical problems. By using a ship pipeline electric heating control prediction model to perform heating control prediction, the electric heating process of the ship pipelines can be regulated, thereby improving the accuracy of the ship pipeline electric heating.

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for electrically heating a ship pipeline, comprising:

[0006] Acquiring historical temperature data, historical heating power data, and an initial neural network model, and training the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model;

[0007] Acquiring real-time temperature data and real-time heating power data, and inputting the real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model to obtain electric heating control prediction data;

[0008] An electric heating demand power prediction value is calculated according to the electric heating control prediction data and the real-time temperature data, and the electric heating process of the ship pipeline is adjusted according to the electric heating demand power prediction value.

[0009] It can be understood that, compared with the prior art, the present invention trains the initial neural network model using historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model. Thereafter, the ship pipeline electric heating control prediction model is input with real-time temperature data and real-time heating power data to obtain electric heating control prediction data. The electric heating demand power prediction value is calculated in combination with the real-time temperature data to obtain the electric heating demand power prediction value. Then, the electric heating process of the ship pipeline is adjusted based on the electric heating demand power prediction value, thereby achieving accurate electric heating of the ship pipeline.

[0010] The present invention trains an initial neural network model using historical temperature data and historical heating power data, so that the resulting ship pipeline electric heating control prediction model can fully exploit and couple the relationship between historical temperature data and historical heating power data, enabling the ship pipeline electric heating control prediction model to accurately predict ship pipeline electric heating control. Real-time temperature data and real-time heating power data are then input into the ship pipeline electric heating control prediction model, enabling the resulting electric heating control prediction data to dynamically identify and integrate the real-time temperature data and real-time heating power data, thereby improving the accuracy of the electric heating control prediction data. The real-time temperature data is then combined to calculate a predicted value of electric heating demand power, thereby achieving regulation of the ship pipeline electric heating process. This not only avoids the poor heating and insulation effect caused by existing reliance on constant power heating alone, but also addresses the complex and variable temperature fluctuations during polar navigation, reduces electric heating energy consumption, improves the accuracy and reliability of ship pipeline heating, and ensures the normal operation of ships in polar environments.

[0011] As a preferred solution, the acquiring of historical temperature data, historical heating power data, and an initial neural network model, and training the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model, includes:

[0012] Acquiring historical temperature data, historical heating power data, and an initial neural network model, wherein the historical temperature data includes historical ambient temperature data, historical pipeline external temperature data, and historical pipeline internal temperature data;

[0013] Processing the historical ambient temperature data, the historical pipeline external temperature data, the historical pipeline internal temperature data, and the historical heating power data according to a preset data processing method to obtain a ship pipeline heating control training sequence;

[0014] The ship pipeline heating control training sequence is input into the initial neural network model, and the initial neural network model is trained based on a preset neural network model training method to obtain a ship pipeline electric heating control prediction model.

[0015] This preferred solution integrates historical temperature data and historical heating power data from multiple dimensions and processes the data according to a preset data processing method to obtain a ship pipeline heating control training sequence. The initial neural network model is then trained based on the ship pipeline heating control training sequence. This allows the ship pipeline electric heating control prediction model to fully integrate the relationship between various temperature factors and heating power in the polar environment of the ship, thereby more closely resembling the complex temperature conditions of the ship pipeline in the actual polar environment and fully considering the impact of multiple factors on the heating effect. This enables the ship pipeline electric heating control prediction model to more accurately predict the ship pipeline electric heating control. Furthermore, using the ship pipeline electric heating control prediction model to perform electric heating control predictions can eliminate control delays caused by temperature lags, thereby further improving the accuracy and reliability of ship pipeline electric heating.

[0016] As a preferred solution, the historical ambient temperature data, historical pipeline external temperature data, historical pipeline internal temperature data, and historical heating power data are processed according to a preset data processing method to obtain a ship pipeline heating control training sequence, including:

[0017] Normalizing the historical ambient temperature data based on a preset data processing method to obtain a historical ambient temperature training set;

[0018] Normalizing the historical pipeline external temperature data based on a preset data processing method to obtain a historical pipeline external temperature training set;

[0019] Normalizing the historical pipeline internal temperature data based on a preset data processing method to obtain a historical pipeline internal temperature training set;

[0020] Normalizing the historical heating power data based on a preset data processing method to obtain a historical heating power training set;

[0021] A ship pipeline heating control training sequence is determined based on the historical ambient temperature training set, the historical pipeline external temperature training set, the historical pipeline internal temperature training set, and the historical heating power training set.

[0022] This preferred solution normalizes multiple different types of data, mapping historical ambient temperature data, historical pipeline external temperature data, historical pipeline internal temperature data, and historical heating power data into a unified dimensional space. This improves the accuracy of the subsequently constructed ship pipeline heating control training sequence, enhances the quality and efficiency of initial neural network model training, and avoids the adverse effects of excessive data differences on model training. This results in a trained ship pipeline electric heating control prediction model with greater generalization and adaptability when dealing with different temperature data, thereby improving the accuracy and reliability of ship pipeline electric heating.

[0023] As a preferred solution, the calculating of the electric heating demand power prediction value based on the electric heating control prediction data and the real-time temperature data, and adjusting the electric heating process of the ship pipeline based on the electric heating demand power prediction value, includes:

[0024] The electric heating control prediction data includes: PID controller proportional parameter, PID controller integral parameter and PID controller differential parameter;

[0025] Acquiring rated temperature data of the ship pipeline, and determining real-time temperature difference data based on the rated temperature data of the ship pipeline and the real-time temperature data;

[0026] An electric heating demand power prediction value is calculated based on the real-time temperature difference data, a PID controller proportional parameter, a PID controller integral parameter, and a PID controller differential parameter, and the electric heating process of the ship pipeline is adjusted according to the electric heating demand power prediction value.

[0027] This preferred solution introduces PID control, dynamically coupling PID control with real-time temperature difference data. The electric heating process of the ship's pipelines is adjusted by calculating the predicted value of the electric heating demand power. The adjustment method based on PID control can quickly and accurately respond to the temperature changes of the ship's pipelines, thereby realizing dynamic adjustment of the ship's pipeline electric heating. This not only avoids the poor heating and insulation effect caused by the existing reliance on fixed power heating, but also can address the complex and changeable temperature fluctuations during polar navigation, reduce the energy consumption of electric heating, improve the accuracy and reliability of ship pipeline heating, and ensure the normal operation of ships in polar environments.

[0028] As a preferred solution, the method of calculating a predicted electric heating power requirement value based on the real-time temperature difference data, a PID controller proportional parameter, a PID controller integral parameter, and a PID controller differential parameter, and adjusting the electric heating process of the ship pipeline according to the predicted electric heating power requirement value includes:

[0029] Input the real-time temperature difference data, the proportional parameter, the integral parameter and the differential parameter of the PID controller into a preset electric heating demand power calculation formula to obtain a predicted value of the electric heating demand power;

[0030] adjusting the electric heating process of the ship pipeline according to the predicted value of the electric heating demand power;

[0031] The formula for calculating the required power of electric heating is as follows:

[0032]

[0033] P heat (t) is the predicted value of electric heating power demand at time t, K p is the proportional parameter of the PID controller, K i is the integral parameter of the PID controller, K d is the differential parameter of the PID controller, e(t) is the real-time temperature difference data; is the integral of the real-time temperature difference data about time t.

[0034] This preferred solution calculates the electric heating demand power prediction value through real-time temperature difference data, PID controller proportional parameter, PID controller integral parameter and PID controller differential parameter, so that the electric heating demand power prediction value can be calculated in a timely and accurate manner. The preset electric heating demand power calculation formula realizes the intelligent solution of the electric heating demand power prediction value, thereby effectively regulating the heating of the ship pipeline by using PID control, thereby improving the accuracy and reliability of the heating of the ship pipeline.

[0035] As a preferred solution, after adjusting the electric heating process of the ship pipeline according to the predicted value of the electric heating demand power, the method further includes:

[0036] Acquiring pipeline length data and pipeline radius data of the ship pipeline;

[0037] The real-time temperature data includes: real-time ambient temperature data and real-time pipeline internal temperature data;

[0038] Calculating the heat loss power of the ship pipeline according to the real-time ambient temperature data, the real-time pipeline internal temperature data, the pipeline length data, and the pipeline radius data;

[0039] Calculating the energy saving rate of the ship pipeline according to the heat loss power;

[0040] The ship pipeline electric heating control prediction model is optimized according to the energy saving rate.

[0041] This preferred solution calculates the heat loss power of the ship's pipelines using real-time ambient temperature data, real-time pipeline internal temperature data, pipeline length data, and pipeline radius data, and then calculates the energy saving rate of the ship's pipelines. Based on the energy saving rate, the ship's pipeline electric heating control prediction model is optimized. This allows the ship's pipeline electric heating control prediction model to continuously adapt to the actual operating conditions and environmental changes of the ship's pipelines, further improving the model's prediction accuracy and applicability, thereby improving the accuracy and reliability of subsequent ship pipeline heating.

[0042] Accordingly, an embodiment of the present invention provides a ship pipeline electric heating system, comprising: a sensor module, a control cabinet, a heating cable, a ship pipeline, and a switch module;

[0043] The heating cable is used to electrically heat the ship pipeline;

[0044] The control cabinet is used to obtain historical temperature data, historical heating power data and an initial neural network model, and train the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model;

[0045] The control cabinet is further configured to obtain real-time temperature data and real-time heating power data collected by the sensor module, and input the real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model to obtain electric heating control prediction data;

[0046] The control cabinet is further configured to generate a switch drive instruction according to the electric heating control prediction data and the real-time temperature data, so that the switch module adjusts the electric heating process of the ship pipeline according to the switch drive instruction.

[0047] The system electrically heats the ship pipeline through a heating cable, the sensor module collects real-time temperature data and real-time heating power data, the control cabinet constructs a ship pipeline electric heating control prediction model, calculates the electric heating control prediction data, and generates a switch drive instruction to drive the switch module to adjust the electric heating process of the ship pipeline, thereby forming a ship pipeline electric heating system that can accurately control the electric heating of the ship pipeline; the initial neural network model is trained by historical temperature data and historical heating power data, so that the obtained ship pipeline electric heating control prediction model can fully explore and couple the relationship between historical temperature data and historical heating power data, so that the ship pipeline electric heating control prediction model can accurately The electric heating control of ship pipelines is predicted; then, real-time temperature data and real-time heating power data are input into the ship pipeline electric heating control prediction model, so that the obtained electric heating control prediction data can dynamically identify and integrate the real-time temperature data and real-time heating power data, thereby improving the accuracy of the electric heating control prediction data. Then, the electric heating demand power prediction value is calculated in combination with the real-time temperature data, thereby realizing the regulation of the ship pipeline electric heating process. This not only avoids the poor heating and insulation effect caused by the existing reliance on fixed power heating, but also can address the complex and changeable temperature fluctuations during polar navigation, reduce the energy consumption of electric heating, improve the accuracy and reliability of ship pipeline heating, and ensure the normal operation of ships in polar environments.

[0048] As a preferred solution, the ship pipeline electric heating system further includes: a power supply, a power cable and a power junction box;

[0049] The power junction boxes are evenly installed on the heating cables and are used to supply power to the heating cables;

[0050] The power supply is electrically connected to the power connection box via the power cable, and the power supply is used to supply power to the power connection box.

[0051] This preferred solution achieves uniform power distribution and redundant backup of the heating cables through a combined power supply solution of a distributed power junction box and power cables. It can avoid the problem of local overheating or insufficient heating of the pipeline caused by uneven power supply under traditional electric heating methods, and ensure the uniformity and accuracy of ship pipeline heating.

[0052] As a preferred solution, the heating cable is a self-limiting temperature heating cable.

[0053] This preferred solution uses heating cables with self-limiting temperature heating cables. The automatic temperature limiting characteristics of the self-limiting temperature heating cables can effectively avoid energy waste caused by overheating, thereby better adapting to the complex and changeable temperature fluctuations in the polar environment. It can also reduce the damage to ship pipelines caused by high temperatures and achieve reliable heating of ship pipelines.

[0054] As a preferred solution, the exteriors of the sensor module, heating cable, ship pipeline and power junction box are all wrapped with an insulating layer.

[0055] This preferred solution can effectively reduce the ineffective heat exchange between the pipeline and the environment by wrapping the sensor module, heating cable, ship pipeline and power junction box with an insulating layer, further reducing the heat loss of the ship pipeline electric heating system, improving the thermal efficiency of the ship pipeline electric heating process, ensuring that more heat generated by the heating cable is used to heat the ship pipeline, and improving the accuracy and efficiency of the ship pipeline electric heating. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A flowchart of the steps of a method for electrically heating a ship pipeline provided by an embodiment of the present invention;

[0057] Figure 2 A schematic structural diagram of a ship pipeline electric heating system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0058] 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0059] Example 1

[0060] Please refer to Figure 1 , Figure 1 A flowchart of a method for electrically heating a ship pipeline provided by an embodiment of the present invention includes steps S101 to S103.

[0061] Step S101: historical temperature data, historical heating power data and an initial neural network model are acquired, and the initial neural network model is trained based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model.

[0062] In this embodiment, the acquisition of historical temperature data, historical heating power data, and an initial neural network model, and training the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model includes:

[0063] Acquiring historical temperature data, historical heating power data, and an initial neural network model, wherein the historical temperature data includes historical ambient temperature data, historical pipeline external temperature data, and historical pipeline internal temperature data;

[0064] Processing the historical ambient temperature data, the historical pipeline external temperature data, the historical pipeline internal temperature data, and the historical heating power data according to a preset data processing method to obtain a ship pipeline heating control training sequence;

[0065] The ship pipeline heating control training sequence is input into the initial neural network model, and the initial neural network model is trained based on a preset neural network model training method to obtain a ship pipeline electric heating control prediction model.

[0066] This embodiment integrates historical temperature data and historical heating power data from multiple dimensions and processes the data according to a preset data processing method to obtain a ship pipeline heating control training sequence. The initial neural network model is then trained based on the ship pipeline heating control training sequence. This allows the ship pipeline electric heating control prediction model to fully integrate the relationship between various temperature factors and heating power in polar environments, thereby more closely resembling the complex temperature conditions of ship pipelines in actual polar environments. The model can fully consider the impact of multiple factors on the heating effect, enabling the model to more accurately predict ship pipeline electric heating control. Furthermore, using the ship pipeline electric heating control prediction model to perform electric heating control predictions can eliminate control delays caused by temperature lags, thereby further improving the accuracy and reliability of ship pipeline electric heating.

[0067] In this embodiment, the historical ambient temperature data, historical pipeline external temperature data, historical pipeline internal temperature data, and historical heating power data are processed according to a preset data processing method to obtain a ship pipeline heating control training sequence, including:

[0068] Normalizing the historical ambient temperature data based on a preset data processing method to obtain a historical ambient temperature training set;

[0069] Normalizing the historical pipeline external temperature data based on a preset data processing method to obtain a historical pipeline external temperature training set;

[0070] Normalizing the historical pipeline internal temperature data based on a preset data processing method to obtain a historical pipeline internal temperature training set;

[0071] Normalizing the historical heating power data based on a preset data processing method to obtain a historical heating power training set;

[0072] A ship pipeline heating control training sequence is determined based on the historical ambient temperature training set, the historical pipeline external temperature training set, the historical pipeline internal temperature training set, and the historical heating power training set.

[0073] This embodiment normalizes multiple different types of data to map historical ambient temperature data, historical pipeline external temperature data, historical pipeline internal temperature data, and historical heating power data into a unified dimensional space. This improves the accuracy of the subsequently constructed ship pipeline heating control training sequence, enhances the quality and efficiency of initial neural network model training, and avoids the adverse effects of excessive data variance on model training. This enables the trained ship pipeline electric heating control prediction model to have stronger generalization and adaptability when dealing with different temperature data, thereby improving the accuracy and reliability of ship pipeline electric heating.

[0074] It should be noted that, in this embodiment, the historical heating power data P is set heat,history The initial neural network model is the LSTM model. The historical temperature data includes: historical ambient temperature data T env,history , historical pipeline external temperature data T pipe,history and historical pipeline internal temperature data T in,history ; The preset data processing method is Min-Max normalization; Among them, Min-Max (Min-Max Normalization) normalization refers to a commonly used data preprocessing method used to linearly map data to a specific range (such as [0,1] or [-1,1]); The LSTM model refers to the Long Short-Term Memory (LSTM) network, which is a special recurrent neural network (RNN) that can effectively capture long-term dependencies in time series by introducing a gating mechanism and cell state, specifically a forget gate, input gate, candidate state, cell state update, output gate, and hidden state output; The expression of the forget gate is f t =σ(W f ·[h t；1 ,x t ]+b f ); the expression of the input gate is i t =σ(W i ·[h t；1 ,x t ]+b i ); the candidate state is expressed as The cell state update expression is The output gate expression is o t =σ(W o ·[h t；1 ,x t ]+b o ); the hidden state output expression is In the above expression, σ is the sigmoid function, tanh is the hyperbolic tangent function, and ° is the element-by-element multiplication (Hadamard product).

[0075] In an optional embodiment, specifically, the historical ambient temperature data T of the past sixty time steps (past ten minutes) is collected. env,history , historical pipeline external temperature data T pipe,history , historical pipeline internal temperature data T in,history And historical heating power data P heat,history ; Then use Min-Max normalization method to normalize the historical ambient temperature data T env,history Normalize to the interval [-1,1] to obtain the historical ambient temperature training set, and use the Min-Max normalization method to normalize the historical pipeline external temperature data T pipe,history Normalize to the interval [-1,1] to obtain the historical pipeline external temperature training set, and use the Min-Max normalization method to normalize the historical pipeline internal temperature data T in,history Normalize to the interval [-1,1] to obtain the historical pipeline internal temperature training set, and use the Min-Max normalization method to normalize the historical heating power data P heat,history Normalized to the interval [-1,1], the historical heating power training set is obtained. Then, according to the time dimension, the ship pipeline heating control training sequence [T env,history ,T in,history ,T pipe,history ,P heat,history ]; then the ship pipeline heating control training sequence [T env,history ,T in,history ,T pipe,history ,P heat,history ] Input LSTM model, LSTM model includes input layer, hidden layer and output layer, where the input layer is 4-dimensional input, that is, it is used to receive the ship pipeline heating control training sequence [T env,history ,T in,history ,T pipe,history ,P heat,history ], and the hidden layer includes two layers of LSTM, each layer of LSTM has 64 neurons, the activation function is tanh, and the output layer is the output PID controller proportional parameter optimization value ΔK p , PID controller integral parameter optimization value ΔK i and the optimal value of the PID controller differential parameter αK d; Then, the loss function is set to mean square error (MSE), the optimizer is set to Adam, the learning rate is 0.001, the batch size is 32, and the LSTM model is trained using the ship pipeline heating control training sequence. When the loss of the validation set (which can be obtained by dividing from the ship pipeline heating control training sequence) does not decrease for 5 consecutive rounds, the training is terminated, and the ship pipeline electric heating control prediction model is obtained.

[0076] Step S102: acquiring real-time temperature data and real-time heating power data, and inputting the real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model to obtain electric heating control prediction data.

[0077] In an optional embodiment, real-time temperature data and real-time heating power data are obtained, that is, real-time ambient temperature data T is obtained. env,now , real-time pipeline external temperature data T pipe,now , real-time pipeline internal temperature data T in,now And real-time heating power data P heat,now ; Then input the ship pipeline electric heating control prediction model to obtain the ship pipeline electric heating control prediction model output PID controller proportional parameter optimization value αK p , PID controller integral parameter optimization value αK i and the optimal value of the PID controller differential parameter ΔK d ; Then get the real-time PID controller proportional parameter K p,now , real-time PID controller integral parameter K i,now and the real-time PID controller differential parameter K d,now (i.e. the three control parameters of the current PID controller), the PID controller proportional parameter optimization value ΔK p and the real-time PID controller proportional parameter K p,now Add them together to get the PID controller proportional parameter K p ; Optimize the integral parameter value of PID controller ΔK i and the real-time PID controller integral parameter K i,now Add them together to get the PID controller integral parameter K i , optimize the differential parameter value ΔK of the PID controller d and the real-time PID controller differential parameter K d,now Add them together to get the PID controller differential parameter K d , thus according to the PID controller proportional parameter K p , PID controller integral parameter K i , PID controller differential parameter K d Get electric heating control prediction data.

[0078] It should be noted that the PID controller proportional parameter K p , PID controller integral parameter K i , PID controller differential parameter K d , refers to the three control parameters of the PID controller. The PID controller (Proportional-Integral-Derivative Controller) is a classic and widely used feedback controller, which controls through three links: proportional, integral and differential.

[0079] Step S103: Calculating an electric heating demand power prediction value according to the electric heating control prediction data and the real-time temperature data, and adjusting the electric heating process of the ship pipeline according to the electric heating demand power prediction value.

[0080] In this embodiment, the calculating of the electric heating demand power prediction value based on the electric heating control prediction data and the real-time temperature data, and adjusting the electric heating process of the ship pipeline based on the electric heating demand power prediction value, includes:

[0081] The electric heating control prediction data includes: PID controller proportional parameter, PID controller integral parameter and PID controller differential parameter;

[0082] Acquiring rated temperature data of the ship pipeline, and determining real-time temperature difference data based on the rated temperature data of the ship pipeline and the real-time temperature data;

[0083] An electric heating demand power prediction value is calculated based on the real-time temperature difference data, a PID controller proportional parameter, a PID controller integral parameter, and a PID controller differential parameter, and the electric heating process of the ship pipeline is adjusted according to the electric heating demand power prediction value.

[0084] This embodiment introduces PID control, dynamically coupling it with real-time temperature difference data. The electric heating process of the ship's pipelines is regulated by calculating a predicted value of the electric heating demand power. This PID control-based regulation method can quickly and accurately respond to temperature changes in the ship's pipelines, thereby achieving dynamic regulation of the ship's pipeline electric heating. This not only avoids the poor heating and insulation effects caused by existing reliance on constant power heating, but also addresses the complex and variable temperature fluctuations experienced during polar navigation, reducing electric heating energy consumption, improving the accuracy and reliability of heating of the ship's pipelines, and ensuring the normal operation of ships in polar environments.

[0085] In this embodiment, the step of calculating a predicted electric heating power requirement value based on the real-time temperature difference data, a proportional parameter of a PID controller, an integral parameter of a PID controller, and a differential parameter of a PID controller, and adjusting the electric heating process of the ship pipeline according to the predicted electric heating power requirement value includes:

[0086] Input the real-time temperature difference data, the proportional parameter, the integral parameter and the differential parameter of the PID controller into a preset electric heating demand power calculation formula to obtain a predicted value of the electric heating demand power;

[0087] adjusting the electric heating process of the ship pipeline according to the predicted value of the electric heating demand power;

[0088] The formula for calculating the required power of electric heating is as follows:

[0089]

[0090] P heat (t) is the predicted value of electric heating power demand at time t, K p is the proportional parameter of the PID controller, K i is the integral parameter of the PID controller, K d is the differential parameter of the PID controller, e(t) is the real-time temperature difference data; is the integral of the real-time temperature difference data about time t.

[0091] In an optional embodiment, the calculation formula for the real-time temperature difference data is e(t)=T set -T in (t), where T set is the rated temperature data of ship piping, T in (t) is the internal temperature data of the pipeline at time t; the real-time internal temperature data of the pipeline T in,now Substitute T in (t), and calculate the real-time temperature difference data e(t).

[0092] In an optional embodiment, after obtaining the predicted value of the electric heating demand power, the PID controller is used to adjust the electric heating process of the ship pipeline within the next five minutes based on the PID controller proportional parameter, the PID controller integral parameter and the PID controller differential parameter to ensure that the power value during the electric heating process of the ship pipeline is the predicted value of the electric heating demand power.

[0093] This embodiment calculates the electric heating demand power prediction value through real-time temperature difference data, PID controller proportional parameters, PID controller integral parameters, and PID controller differential parameters, enabling timely and accurate calculation of the electric heating demand power prediction value. Using a preset electric heating demand power calculation formula, the electric heating demand power prediction value is intelligently solved, thereby enabling effective regulation of ship pipeline heating using PID control, thereby improving the accuracy and reliability of ship pipeline heating.

[0094] In this embodiment, after adjusting the electric heating process of the ship pipeline according to the predicted value of the electric heating demand power, the method further includes:

[0095] Acquiring pipeline length data and pipeline radius data of the ship pipeline;

[0096] The real-time temperature data includes: real-time ambient temperature data and real-time pipeline internal temperature data;

[0097] Calculating the heat loss power of the ship pipeline according to the real-time ambient temperature data, the real-time pipeline internal temperature data, the pipeline length data, and the pipeline radius data;

[0098] Calculating the energy saving rate of the ship pipeline according to the heat loss power;

[0099] The ship pipeline electric heating control prediction model is optimized according to the energy saving rate.

[0100] In an optional embodiment, the calculation formula for the heat loss power of the ship pipeline is specifically:

[0101]

[0102] Among them, Q loss is the heat loss power, L is the length of the ship pipeline, T in is the internal temperature data of the pipeline; T env is the ambient temperature data, r in is the inner radius of the pipe; r out is the outer radius of the pipe, k is the thermal conductivity of the insulation material; h is the convection heat transfer coefficient.

[0103] It should be noted that overshoot refers to the situation where the control exceeds the target set value during the PID control process, which is usually caused by improper adjustment of the PID parameters.

[0104] In an optional embodiment, the pipe length data, pipe radius data (including the inner radius and outer radius of the pipe), real-time ambient temperature data, and real-time internal temperature data of the pipe of the ship are obtained, and then the thermal conductivity of the insulation material of the ship pipe is obtained (which can be found in the instructions of the ship pipe, for example, polyurethane foam k = 0.035 W / (m·K)), and the convection heat transfer coefficient can be directly obtained (for example, under forced convection conditions, h = 25 W / (m·K)). 2 ·K)); Substituting into the above calculation formula of heat loss power of ship pipelines, the heat loss power of ship pipelines can be obtained, and the energy saving rate of ship pipelines can be obtained based on the heat loss power;

[0105] Specifically, the ship pipeline length L is set to 20m, and the pipeline outer radius r out =0.12m, inner radius of the pipe r in =0.1m, the ambient temperature data at night is T env = -10℃, during the day it is T env =5℃; Rated temperature data of ship piping T set =40℃; then calculate the heat loss power of the ship's pipelines. Specifically, the heat loss power at night is: The heat loss power during the day is: When PID control is used, there is a 20% overshoot. At this time, the actual nighttime electric heating power is 3.53×1.2=4.24kW, and the actual daytime electric heating power is 2.47×1.2=2.96kW. Therefore, based on the heat loss power during the day and night, the average daily energy consumption using PID control can be obtained as W PID =12×4.24+12×2.96=86.4kWh; after using the ship pipeline electric heating control prediction model (LSTM model) to obtain electric heating control prediction data, combined with PID control, the overshoot can be reduced to 5%; at this time, the actual nighttime electric heating power is 3.53×1.05=3.71kW, and the actual daytime electric heating power is 2.47×1.05=2.59kW; the average daily energy consumption is W LSTM =12×3.71+12×2.59=75.6kWh; therefore, the energy saving rate is: When the energy saving rate does not meet the preset energy saving requirement (set as a threshold), the ship pipeline electric heating control prediction model (LSTM model) is optimized based on the difference between the energy saving rate and the preset energy saving requirement. In particular, there are currently many mature existing technologies for optimizing the ship pipeline electric heating control prediction model (LSTM model), so this embodiment will not be described in detail here.

[0106] This embodiment calculates the heat loss power of a ship's pipelines using real-time ambient temperature data, real-time pipeline internal temperature data, pipeline length data, and pipeline radius data, and further calculates the energy saving rate of the ship's pipelines. Based on the energy saving rate, the ship's pipeline electric heating control prediction model is optimized. This allows the model to continuously adapt to the actual operating conditions and environmental changes of the ship's pipelines, further improving the model's prediction accuracy and applicability, thereby increasing the accuracy and reliability of subsequent ship pipeline heating.

[0107] In this embodiment, the initial neural network model is trained using historical temperature data and historical heating power data, so that the resulting ship pipeline electric heating control prediction model can fully exploit and couple the relationship between historical temperature data and historical heating power data, enabling the ship pipeline electric heating control prediction model to accurately predict ship pipeline electric heating control. Real-time temperature data and real-time heating power data are then input into the ship pipeline electric heating control prediction model, enabling the resulting electric heating control prediction data to dynamically identify and integrate the real-time temperature data and real-time heating power data, thereby improving the accuracy of the electric heating control prediction data. The predicted electric heating demand power value is then calculated in combination with the real-time temperature data, thereby enabling regulation of the ship pipeline electric heating process. This not only avoids the poor heating and insulation effects caused by existing reliance on constant power heating alone, but also addresses the complex and variable temperature fluctuations experienced during polar navigation, reduces electric heating energy consumption, improves the accuracy and reliability of ship pipeline heating, and ensures the normal operation of ships in polar environments.

[0108] Example 2

[0109] Please refer to Figure 2 , Figure 2 This is a schematic structural diagram of a ship pipeline electric heating system provided by an embodiment of the present invention. The ship pipeline electric heating system is applicable to ships and includes: a sensor module 201, a control cabinet 202, a heating cable 203, a ship pipeline 204, and a switch module 205;

[0110] The heating cable 203 is used to electrically heat the ship pipeline 204;

[0111] The control cabinet 202 is used to obtain historical temperature data, historical heating power data and an initial neural network model, and train the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model;

[0112] The control cabinet 202 is further configured to obtain the real-time temperature data and real-time heating power data collected by the sensor module 201, and input the real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model to obtain electric heating control prediction data;

[0113] The control cabinet 202 is further configured to generate a switch driving instruction according to the electric heating control prediction data and the real-time temperature data, so that the switch module 205 adjusts the electric heating process of the ship pipeline 204 according to the switch driving instruction.

[0114] In this embodiment, the ship pipeline electric heating system further includes: a power supply 206, a power cable 207 and a power connection box 208;

[0115] The power junction boxes 208 are evenly installed on the heating cables 203 and are used to supply power to the heating cables 203;

[0116] The power supply 206 is electrically connected to the power connection box 208 via the power cable 207 , and the power supply 206 is used to supply power to the power connection box 208 .

[0117] In an optional embodiment, the power supply 206 can be powered by a ground distribution board connected to the ship's generator; the control cabinet 202 generates a switch drive instruction based on the electric heating control prediction data and the real-time temperature data, driving the switch module 205 to be turned on or off, thereby controlling the power supply to the power junction box, and then controlling the power supply to the heating cable by the power junction box, and then controlling the ship pipeline electric heating process based on controlling the power supply to the heating cable.

[0118] This embodiment achieves uniform power distribution and redundant backup for the heating cables through a combined power supply solution of a distributed power junction box and power cables. This can avoid the problem of local overheating or insufficient heating of the pipeline caused by uneven power supply in traditional electric heating methods, and ensure the uniformity and accuracy of ship pipeline heating.

[0119] In this embodiment, the sensor module 201 includes: a sensor junction box 2011, an ambient temperature sensor 2012, a cable limit temperature sensor 2013, a pipe temperature sensor 2014 and a heating power sensor 2015;

[0120] The sensor junction box 2011 is provided with a temperature data transmission interface for electrically connecting to the ambient temperature sensor 2012, the cable limit temperature sensor 2013, the pipeline temperature sensor 2014 and the heating power sensor 2015 respectively (i.e. Figure 2 2011, 2012, 2013, 2014, 2015 shown);

[0121] The ambient temperature sensor 2012 is used to monitor the ambient temperature of the ship pipeline 204; the cable limit temperature sensor 2013 is used to monitor the temperature of the heating cable 203; the pipeline temperature sensor 2014 is used to monitor the external temperature data and the internal temperature data of the ship pipeline 204; the heating power sensor 2015 is used to monitor the real-time heating power data of the heating cable 203;

[0122] The ambient temperature sensor 2012 can be installed on the deck of the ship, with a sampling interval of 10 seconds; the cable limit temperature sensor 2013 is installed inside the heating cable 203; the pipeline temperature sensor 2014 is installed above the ship pipeline 204; the heating power sensor 2015 is installed inside the heating cable 203.

[0123] In an optional embodiment, the ambient temperature sensor 2012 is specifically a PT100 platinum resistance with a range of -50°C to 150°C, an accuracy of ±0.1°C, and IP68 protection; the pipeline temperature sensor 2014 can adopt a DS18B20 digital sensor and a K-type thermocouple, wherein, when measuring the internal temperature data of the pipeline, the DS18B20 digital sensor is used, which has a range of -55°C to 125°C, an accuracy of ±0.1°C, and uses single bus communication. When using the DS18B20 digital sensor, it can be inserted into the medium flow channel of the ship pipeline after threaded sealing; when measuring the external temperature data of the pipeline, a K-type thermocouple is used, which has a range of -200°C to 1250°C and a response time of <1s. The K-type thermocouple can fit the pipe wall and use thermal conductive silicone to enhance thermal contact; the heating power sensor 2015 can adopt an ELDX-8.0 sensor with a power range of 3.6KVA to 24KVA.

[0124] In an optional embodiment, the ship pipeline electric heating system further includes: an intermediate connector 209 and a terminal connector 210; the heating cable 203 and the ship pipeline 204 are connected via the intermediate connector 209; the heating cable 203 and the ship pipeline 204 are also connected via the terminal connector 210.

[0125] In an optional embodiment, the ship pipeline electric heating system further includes: an isolation transformer 211; the isolation transformer 211 is used for electrical isolation, and the isolation transformer 211 prevents the heating cable 203 from causing leakage and low insulation due to moisture and other reasons, thereby affecting the normal operation of the ship's power grid system.

[0126] In this embodiment, the heating cable is a self-limiting temperature heating cable.

[0127] It should be noted that self-regulating trace heating tape is an intelligent electric heating device based on the PTC (positive temperature coefficient) effect. Its internal heating matrix and thermoplastic insulation material form an independent unit, providing additional moisture-proof protection. Its self-limiting temperature feature improves the safety and reliability of the product. The heating power output can also be automatically adjusted with changes in ambient temperature. Even if there is cross-or overlap during installation, it will not overheat or burn out.

[0128] This embodiment uses a heating cable with a self-limiting temperature heating tape. The automatic temperature limiting feature of the self-limiting temperature heating tape can effectively avoid energy waste caused by overheating, thereby better adapting to the complex and changeable temperature fluctuations in the polar environment. It can also reduce damage to ship pipelines caused by high temperatures and achieve reliable heating of ship pipelines.

[0129] In this embodiment, the sensor module, the heating cable, the ship pipeline and the power junction box are all wrapped with an insulating layer 212 .

[0130] By wrapping the sensor module, heating cable, ship pipeline and power junction box with an insulating layer, this embodiment can effectively reduce ineffective heat exchange between the pipeline and the environment, further reduce heat loss of the ship pipeline electric heating system, improve the thermal efficiency of the ship pipeline electric heating process, ensure that more heat generated by the heating cable is used to heat the ship pipeline, and improve the accuracy and efficiency of ship pipeline electric heating.

[0131] In this embodiment, the control cabinet includes: a ship pipeline electric heating control prediction model acquisition module, an electric heating control prediction data acquisition module and a ship pipeline electric heating adjustment module;

[0132] The ship pipeline electric heating control prediction model acquisition module is used to acquire historical temperature data, historical heating power data and an initial neural network model, and train the initial neural network model based on the historical temperature data and the historical heating power data to obtain the ship pipeline electric heating control prediction model.

[0133] The electric heating control prediction data acquisition module is used to acquire real-time temperature data and real-time heating power data, and input the real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model to obtain electric heating control prediction data.

[0134] The ship pipeline electric heating adjustment module is used to calculate the electric heating demand power prediction value according to the electric heating control prediction data and the real-time temperature data, and adjust the electric heating process of the ship pipeline according to the electric heating demand power prediction value.

[0135] In this embodiment, the ship pipeline electric heating control prediction model acquisition module includes: a ship pipeline electric heating control prediction model acquisition unit;

[0136] The ship pipeline electric heating control prediction model acquisition unit is used to acquire historical temperature data, historical heating power data and an initial neural network model, wherein the historical temperature data includes: historical ambient temperature data, historical pipeline external temperature data and historical pipeline internal temperature data;

[0137] Processing the historical ambient temperature data, the historical pipeline external temperature data, the historical pipeline internal temperature data, and the historical heating power data according to a preset data processing method to obtain a ship pipeline heating control training sequence;

[0138] The ship pipeline heating control training sequence is input into the initial neural network model, and the initial neural network model is trained based on a preset neural network model training method to obtain a ship pipeline electric heating control prediction model.

[0139] In this embodiment, the ship pipeline electric heating control prediction model acquisition unit includes: a ship pipeline heating control training sequence acquisition subunit;

[0140] The ship pipeline heating control training sequence acquisition subunit is used to normalize the historical ambient temperature data based on a preset data processing method to obtain a historical ambient temperature training set;

[0141] Normalizing the historical pipeline external temperature data based on a preset data processing method to obtain a historical pipeline external temperature training set;

[0142] Normalizing the historical pipeline internal temperature data based on a preset data processing method to obtain a historical pipeline internal temperature training set;

[0143] Normalizing the historical heating power data based on a preset data processing method to obtain a historical heating power training set;

[0144] A ship pipeline heating control training sequence is determined based on the historical ambient temperature training set, the historical pipeline external temperature training set, the historical pipeline internal temperature training set, and the historical heating power training set.

[0145] In this embodiment, the ship pipeline electric heating and regulating module includes: a ship pipeline electric heating and regulating unit;

[0146] In the ship pipeline electric heating adjustment unit, the electric heating control prediction data includes: a PID controller proportional parameter, a PID controller integral parameter and a PID controller differential parameter;

[0147] The ship pipeline electric heating adjustment unit is used to obtain the ship pipeline rated temperature data, and determine the real-time temperature difference data based on the ship pipeline rated temperature data and the real-time temperature data;

[0148] An electric heating demand power prediction value is calculated based on the real-time temperature difference data, a PID controller proportional parameter, a PID controller integral parameter, and a PID controller differential parameter, and the electric heating process of the ship pipeline is adjusted according to the electric heating demand power prediction value.

[0149] In this embodiment, the ship pipeline electric heating and regulating unit includes: a ship pipeline electric heating and regulating subunit;

[0150] The ship pipeline electric heating adjustment subunit is used to input the real-time temperature difference data, the PID controller proportional parameter, the PID controller integral parameter and the PID controller differential parameter into a preset electric heating demand power calculation formula to obtain a predicted value of the electric heating demand power;

[0151] adjusting the electric heating process of the ship pipeline according to the predicted value of the electric heating demand power;

[0152] The formula for calculating the required power of electric heating is as follows:

[0153]

[0154] P heat (t) is the predicted value of electric heating power demand at time t, K p is the proportional parameter of the PID controller, K i is the integral parameter of the PID controller, K d is the differential parameter of the PID controller, e(t) is the real-time temperature difference data; is the integral of the real-time temperature difference data about time t.

[0155] In this embodiment, the initial neural network model is trained using historical temperature data and historical heating power data, so that the resulting ship pipeline electric heating control prediction model can fully exploit and couple the relationship between historical temperature data and historical heating power data, enabling the ship pipeline electric heating control prediction model to accurately predict ship pipeline electric heating control. Real-time temperature data and real-time heating power data are then input into the ship pipeline electric heating control prediction model, enabling the resulting electric heating control prediction data to dynamically identify and integrate the real-time temperature data and real-time heating power data, thereby improving the accuracy of the electric heating control prediction data. The predicted electric heating demand power value is then calculated in combination with the real-time temperature data, thereby enabling regulation of the ship pipeline electric heating process. This not only avoids the poor heating and insulation effects caused by existing reliance on constant power heating alone, but also addresses the complex and variable temperature fluctuations experienced during polar navigation, reduces electric heating energy consumption, improves the accuracy and reliability of ship pipeline heating, and ensures the normal operation of ships in polar environments.

[0156] In summary, the embodiments of the present invention train the initial neural network model using historical temperature data and historical heating power data, so that the obtained ship pipeline electric heating control prediction model can fully explore and couple the relationship between historical temperature data and historical heating power data, so that the ship pipeline electric heating control prediction model can accurately predict the ship pipeline electric heating control. Then, by inputting real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model, the obtained electric heating control prediction data can dynamically identify and integrate the real-time temperature data and real-time heating power data, thereby improving the accuracy of the electric heating control prediction data. Then, the electric heating demand power prediction value is calculated in combination with the real-time temperature data, thereby achieving regulation of the ship pipeline electric heating process. This not only avoids the poor heating and insulation effect caused by the existing reliance on constant power heating, but also can address the complex and changeable temperature fluctuations during polar navigation, reduce the energy consumption of electric heating, improve the accuracy and reliability of ship pipeline heating, and ensure the normal operation of the ship in the polar environment.

[0157] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for electrically heating a ship pipeline, characterized in that: include: Acquiring historical temperature data, historical heating power data, and an initial neural network model, and training the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model; Acquiring real-time temperature data and real-time heating power data, and inputting the real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model to obtain electric heating control prediction data; An electric heating demand power prediction value is calculated according to the electric heating control prediction data and the real-time temperature data, and the electric heating process of the ship pipeline is adjusted according to the electric heating demand power prediction value.

2. A method for electrically heating a ship pipeline according to claim 1, characterized in that: The acquiring of historical temperature data, historical heating power data, and an initial neural network model, and training the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model, includes: Acquiring historical temperature data, historical heating power data, and an initial neural network model, wherein the historical temperature data includes historical ambient temperature data, historical pipeline external temperature data, and historical pipeline internal temperature data; Processing the historical ambient temperature data, the historical pipeline external temperature data, the historical pipeline internal temperature data, and the historical heating power data according to a preset data processing method to obtain a ship pipeline heating control training sequence; The ship pipeline heating control training sequence is input into the initial neural network model, and the initial neural network model is trained based on a preset neural network model training method to obtain a ship pipeline electric heating control prediction model.

3. A method for electrically heating a ship pipeline according to claim 2, characterized in that: The historical ambient temperature data, the historical pipeline external temperature data, the historical pipeline internal temperature data, and the historical heating power data are processed according to a preset data processing method to obtain a ship pipeline heating control training sequence, including: Normalizing the historical ambient temperature data based on a preset data processing method to obtain a historical ambient temperature training set; Normalizing the historical pipeline external temperature data based on a preset data processing method to obtain a historical pipeline external temperature training set; Normalizing the historical pipeline internal temperature data based on a preset data processing method to obtain a historical pipeline internal temperature training set; Normalizing the historical heating power data based on a preset data processing method to obtain a historical heating power training set; A ship pipeline heating control training sequence is determined based on the historical ambient temperature training set, the historical pipeline external temperature training set, the historical pipeline internal temperature training set, and the historical heating power training set.

4. The method for electrically heating a ship pipeline according to claim 1, wherein: The calculating of the electric heating demand power prediction value according to the electric heating control prediction data and the real-time temperature data, and adjusting the electric heating process of the ship pipeline according to the electric heating demand power prediction value, includes: The electric heating control prediction data includes: PID controller proportional parameter, PID controller integral parameter and PID controller differential parameter; Acquiring rated temperature data of the ship pipeline, and determining real-time temperature difference data based on the rated temperature data of the ship pipeline and the real-time temperature data; An electric heating demand power prediction value is calculated based on the real-time temperature difference data, a PID controller proportional parameter, a PID controller integral parameter, and a PID controller differential parameter, and the electric heating process of the ship pipeline is adjusted according to the electric heating demand power prediction value.

5. A method for electrically heating a ship pipeline according to claim 4, characterized in that: The method further comprises calculating a predicted electric heating power requirement value based on the real-time temperature difference data, a proportional parameter of a PID controller, an integral parameter of a PID controller, and a differential parameter of a PID controller, and adjusting the electric heating process of the ship pipeline according to the predicted electric heating power requirement value, including: Input the real-time temperature difference data, the proportional parameter, the integral parameter and the differential parameter of the PID controller into a preset electric heating demand power calculation formula to obtain a predicted value of the electric heating demand power; adjusting the electric heating process of the ship pipeline according to the predicted value of the electric heating demand power; The formula for calculating the required power of electric heating is as follows: P heat (t) is the predicted value of electric heating power demand at time t, K p is the proportional parameter of the PID controller, K i is the integral parameter of the PID controller, K d is the differential parameter of the PID controller, e(t) is the real-time temperature difference data; is the integral of the real-time temperature difference data about time t.

6. A method for electrically heating a ship pipeline according to claim 5, characterized in that: After adjusting the electric heating process of the ship pipeline according to the predicted value of the electric heating demand power, the method further includes: Acquiring pipeline length data and pipeline radius data of the ship pipeline; The real-time temperature data includes: real-time ambient temperature data and real-time pipeline internal temperature data; Calculating the heat loss power of the ship pipeline according to the real-time ambient temperature data, the real-time pipeline internal temperature data, the pipeline length data, and the pipeline radius data; Calculating the energy saving rate of the ship pipeline according to the heat loss power; The ship pipeline electric heating control prediction model is optimized according to the energy saving rate.

7. A ship pipeline electric heating system, characterized in that: include: Sensor modules, control cabinets, heating cables, ship piping and switch modules; The heating cable is used to electrically heat the ship pipeline; The control cabinet is used to obtain historical temperature data, historical heating power data and an initial neural network model, and train the initial neural network model based on the historical temperature data and the historical heating power data to obtain a ship pipeline electric heating control prediction model; The control cabinet is further configured to obtain real-time temperature data and real-time heating power data collected by the sensor module, and input the real-time temperature data and real-time heating power data into the ship pipeline electric heating control prediction model to obtain electric heating control prediction data; The control cabinet is further configured to generate a switch drive instruction according to the electric heating control prediction data and the real-time temperature data, so that the switch module adjusts the electric heating process of the ship pipeline according to the switch drive instruction.

8. The ship pipeline electric heating system according to claim 7, characterized in that: Also includes: Power supply, power cables and power junction box; The power junction boxes are evenly installed on the heating cables and are used to supply power to the heating cables; The power supply is electrically connected to the power connection box via the power cable, and the power supply is used to supply power to the power connection box.

9. The ship pipeline electric heating system according to claim 7, characterized in that: The heating cable is a self-limiting temperature heating cable.

10. The ship pipeline electric heating system according to claim 8, characterized in that: The sensor module, heating cable, ship pipeline and power junction box are all wrapped with an insulating layer.

Images