A method for predicting the rotation speed of a gas-electric hybrid power system of a ship

Abstract

The present application belongs to the technical field of ship working condition prediction, and discloses a rotating speed prediction method for a ship gas-electric hybrid power system. A ship gas-electric hybrid power propeller rotating speed prediction model is constructed based on an adaptive neuro-fuzzy inference system (ANFIS); a difference between the obtained predicted rotating speed and the actual rotating speed is obtained; an improved rotating speed prediction model is constructed using the obtained difference and the used rotating speed information; and future rotating speed prediction is performed through the constructed improved rotating speed prediction model. The present application uses the initially constructed rotating speed prediction model to obtain the first-step predicted rotating speed, and provides the difference between the predicted rotating speed and the actual rotating speed for the improved prediction model; the improved rotating speed prediction model is constructed according to the obtained difference and the initial rotating speed information, so as to improve the rotating speed prediction accuracy and achieve the real-time prediction effect within a given time step.

Description

Technical Field

[0001] This invention belongs to the field of ship operating condition prediction technology, and particularly relates to a method for predicting the rotational speed of a ship's gas-electric hybrid power system. Background Technology

[0002] The development of new power forms for ships, such as ammonia and hydrogen-powered ships, is still in its early stages. Natural gas engines have better nitrogen oxide emission characteristics than diesel engines, so gas-electric hybrid ships can effectively meet the needs of the development transition period. Gas-electric hybrid ships include multiple propulsion methods, requiring solutions to energy allocation optimization and scheduling problems. To address these issues, energy management strategies often employ model predictive control (MPC), but this requires advance knowledge of the operating load for a certain period. If the prediction is not timely, the MPC solution will not meet the ship's operational requirements. Based on the above analysis, ship operating condition prediction is essential.

[0003] Based on the above analysis, the problems and defects of the existing technology are as follows: the existing general speed prediction method based on ANFIS often requires multiple sets of parameters to achieve many-to-one prediction, which makes it difficult to obtain navigation parameters under actual working conditions, and some parameters have little effect on speed prediction; speed prediction with only speed information often adopts neural network-based speed prediction methods, which are difficult to meet the accuracy requirements. Summary of the Invention

[0004] To overcome the problems existing in related technologies, this invention discloses an embodiment of a method for predicting the rotational speed of a ship's gas-electric hybrid power system. The purpose of this invention is to propose a novel ANFIS-based method for predicting the propeller rotational speed of a gas-electric hybrid power ship, enabling advanced optimized scheduling and significantly improving response speed to cope with complex and changing actual operating conditions. It also improves the accuracy of rotational speed prediction, providing real-time rotational speed prediction information within a given prediction interval based on actual conditions.

[0005] The technical solution is as follows: A method for predicting the rotational speed of a marine gas-electric hybrid power system, comprising the following steps:

[0006] S1. Based on the ANFIS toolbox of the adaptive neural fuzzy prediction system, a prediction model for the propeller speed of a ship's gas-electric hybrid power system is constructed to predict the propeller speed of the gas-electric hybrid power system.

[0007] S2, calculate the difference between the predicted rotational speed in step S1 and the actual rotational speed of the ship's gas-electric hybrid power system;

[0008] S3. Based on the speed difference obtained in step S2 and the speed information obtained from the ship gas-electric hybrid propeller speed prediction model in step S1, an improved ANFIS speed prediction model is constructed.

[0009] S4. Predict future speed using the improved ANFIS speed prediction model constructed in step S3.

[0010] In one embodiment, constructing a ship gas-electric hybrid propeller speed prediction model in step S1 includes:

[0011] (a) Typical speed information under two identical operating conditions provided by the ship's gas-electric hybrid power system is used as the input information and actual information of the adaptive neural fuzzy prediction system ANFIS, respectively.

[0012] (b) Using the speed information obtained in step (a), construct a speed prediction model for the ship's gas-electric hybrid power system with the help of the Adaptive Neural Fuzzy Prediction System (ANFIS) toolbox.

[0013] In one embodiment, the propeller speed prediction model for ship gas-electric hybrid power constructed in step (b) is a single-input speed prediction model. The speed information input into the adaptive neural fuzzy prediction system (ANFIS) for training is the propeller speed obtained under the actual operating conditions of the ship under two identical conditions, which are used as the input speed and the actual speed for training, respectively.

[0014] In one embodiment, in step S1, the Adaptive Neural Fuzzy Prediction System (ANFIS) comprises a five-layer structure:

[0015] The required first-order Sugeno model consists of one input and one output, using the Takagi-Sugeno IF-THEN rule:

[0016] If x is A, then f1 = p1x + r1(1)

[0017] The first layer structure consists of an input variable member function MFs and an input, which is the rotational speed information under typical ship operating conditions.

[0018] The second layer structure examines the weights of the member functions MFs for each input variable, receives the input values ​​from the first layer and uses them as member functions to represent the fuzzy set of the input variables, and the output of the node represents the strength of the rule.

[0019] The third layer is the rule layer, where each node performs precondition matching for fuzzy rules, specifically calculating the activation level of each rule and calculating the normalized weights for each node.

[0020] The fourth layer provides the output value after rule inference for the defuzzification layer, and each node is an adaptive node;

[0021] The fifth layer is the output layer, which calculates the sum of all incoming signals as the total output and outputs the speed prediction result.

[0022] In one embodiment, in step S2, the difference between the predicted rotational speed and the actual rotational speed is the difference between the input rotational speed in step S1 and the predicted rotational speed obtained by establishing a prediction model for the rotational speed of a ship's gas-electric hybrid propeller.

[0023] The predicted speed value V obtained by establishing a propeller speed prediction model for ship gas-electric hybrid power generation * and the input speed V in Calculate the difference between the two:

[0024] ΔV=V in -V * (2)

[0025] In one embodiment, in step S3, the improved speed prediction model is trained using the difference between the speed prediction result obtained in step S1 and the input speed, and the same input speed as in step S1. The actual speed used for training is the same as in step S1.

[0026] The improved speed prediction model is a dual-input speed prediction model, specifically including:

[0027] The required first-order Sugeno model consists of two inputs and one output, using the Takagi-Sugeno IF-THEN rule:

[0028] If x is A and y is C then f1=p1x+r1 (3)

[0029] The first layer structure consists of input variable member functions, input 1, and input 2. Input 1 is the rotational speed information under the same typical ship operating conditions as in step 1, and input 2 is the difference between the predicted rotational speed obtained in step 2 and the actual rotational speed. Each node in the first layer is an adaptive node, and the node function is:

[0030] O = μ AB (x) (4)

[0031] O = μ CD (x) (5)

[0032] Where, μ AB (x) and μ CD (x) represents MFs;

[0033] The second layer is a member layer that checks the weights of each MFs and receives the input values ​​from the first layer as member functions to represent the fuzzy set of input variables. Each node is non-adaptive. This layer multiplies the signals passed from the first layer and sends the product to the next layer, as shown in formula (6). The output of each node represents the strength of a rule.

[0034] ωi =μ AB (x)*μ CD (y)(6)

[0035] The third layer is the rule layer. Each node in this layer performs fuzzy rule precondition matching. This layer is non-adaptive. The ratio of the fitness strength of the rule to the activation strength of all rules is calculated as shown in Equation (7).

[0036]

[0037] The fourth layer provides the output value after rule inference for the defuzzification layer. Each node is an adaptive node, and the node function is:

[0038]

[0039] Among them, {p i ,q i ,r i} represents the result parameter set;

[0040] The fifth layer is the output layer, which outputs the improved speed prediction results.

[0041] In one embodiment, in step S4, predicting future engine speed using the improved ANFIS speed prediction model constructed in step S3 includes:

[0042] (1) Input the initial input speed and the difference to pre-train the improved ANFIS speed prediction model constructed in step S3 to obtain the advanced speed prediction value.

[0043] (2) Determine the prediction step size based on actual needs and the prediction value trained by the prediction model to ensure real-time performance. Use the advanced speed prediction value obtained in step S1 as the initial feedback signal to complete the speed prediction.

[0044] Another object of the present invention is to provide a speed prediction device for a marine gas-electric hybrid power system, comprising:

[0045] The module for predicting the propeller speed of a ship's gas-electric hybrid propeller is used to build a prediction model for the propeller speed of a ship's gas-electric hybrid propeller based on the Adaptive Neural Fuzzy Prediction System (ANFIS) toolbox, and to predict the propeller speed of the gas-electric hybrid system.

[0046] The difference acquisition module is used to calculate the difference between the predicted rotational speed and the actual rotational speed of the ship's gas-electric hybrid power system.

[0047] An improved speed prediction model acquisition module is used to construct an improved ANFIS speed prediction model based on the obtained speed difference and the speed information obtained from the ship gas-electric hybrid propeller speed prediction model.

[0048] The future speed prediction module is used to predict future speeds using the improved ANFIS speed prediction model.

[0049] Another object of the present invention is to provide a storage medium for receiving user input programs, wherein the stored computer programs enable electronic devices to execute the speed prediction method of the ship's gas-electric hybrid power system.

[0050] Another objective of this invention is to provide an application of the aforementioned method for predicting the rotational speed of a marine gas-electric hybrid power system in predicting the operating load of a natural gas engine.

[0051] Combining all the above technical solutions, the advantages and positive effects of this invention are as follows:

[0052] First, addressing the technical problems and difficulties in solving the aforementioned existing technologies, and closely combining the technical solution to be protected by this invention with the results and data from the research and development process, this paper provides a detailed and in-depth analysis of how the technical solution of this invention solves the technical problems and the creative technical effects brought about after solving the problems. The specific description is as follows: The speed prediction method for a ship's gas-electric hybrid power system provided by this invention utilizes the theoretical logic of the Adaptive Neuro-Fuzzy System (ANFIS) to establish a propeller speed prediction model for the ship's gas-electric hybrid power system based on system theoretical principles and logical rules. Furthermore, it uses the deviation between this prediction result and the input speed to improve the speed prediction model, constructing an improved dual-input ANFIS speed prediction model. This achieves high-precision prediction of the ship's future speed even with only propeller speed information, and enables flexible speed prediction within a time step. Using this invention, the accuracy of speed prediction can be improved, providing advanced speed information for the energy management strategy of the ship's gas-electric hybrid power system, and improving the optimization accuracy of the hybrid power system's energy management strategy.

[0053] Secondly, considering the technical solution as a whole or from the perspective of the product, the technical effects and advantages of the technical solution to be protected by this invention are specifically described as follows: Based on the theoretical support of the adaptive neural fuzzy prediction system, this invention constructs a speed prediction model using the propeller speed information provided by the ship's gas-electric hybrid power system; using the initially constructed speed prediction model, the first predicted speed is obtained, and at the same time, the actual operating speed of the gas-electric hybrid power system is measured, providing the difference between the predicted speed and the actual speed for improving the prediction model; based on the obtained difference and the initial speed information, an improved speed prediction model is constructed to improve the speed prediction accuracy and achieve real-time prediction within a given time step.

[0054] Third, as supplementary evidence of the inventive step of the claims of this invention, it is also reflected in the following important aspects: This invention can provide a tool for predicting the rotational speed of a real marine gas-electric hybrid power system. This invention is based on the Adaptive Neuro-Fuzzy Prediction System (ANFIS) for predicting the propeller rotational speed of a marine gas-electric hybrid power system. Attached Figure Description

[0055] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure;

[0056] Figure 1 This is a flowchart illustrating the logical principle of the ship gas-electric hybrid power system speed prediction method provided in this embodiment of the invention.

[0057] Figure 2 This is a flowchart of the speed prediction method for a ship gas-electric hybrid power system provided in an embodiment of the present invention;

[0058] Figure 3 This is a diagram of the single-input ANFIS structure provided in the embodiments of the present invention;

[0059] Figure 4 This is a structural diagram of the dual-input ANFIS provided in an embodiment of the present invention;

[0060] Figure 5 This is a diagram of the ANFIS structure using a two-input five-member function provided in an embodiment of the present invention; in the diagram, white circles represent logical operations and black circles represent "AND".

[0061] Figure 6 This is a schematic diagram of the speed prediction device for a ship gas-electric hybrid power system provided in an embodiment of the present invention;

[0062] In the figure: 1. Ship gas-electric hybrid propeller speed prediction model construction module; 2. Difference acquisition module; 3. Improved speed prediction model acquisition module; 4. Future speed prediction module. Detailed Implementation

[0063] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Many specific details are set forth in the following description to provide a thorough understanding of the present invention. However, the present invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0064] I. Explanation of the Implementation Example:

[0065] Example 1

[0066] like Figure 1 As shown, this invention provides a method for predicting the rotational speed of a ship's gas-electric hybrid power system. Based on the theoretical logic of Adaptive Neural Fuzzy Systems (ANFIS), it uses the propeller rotational speed information under actual operating conditions of the gas-electric hybrid ship as the input speed and the actual speed to establish a single-input ANFIS-based rotational speed prediction model. Furthermore, it uses the established model to obtain the deviation between the output result and the input speed, and uses this deviation, the input speed, and the actual speed to establish an improved dual-input ANFIS rotational speed prediction model, thereby improving the propeller rotational speed prediction effect. The improved model can achieve ship propeller rotational speed prediction with feedback dual inputs by providing a set of rotational speed information within a given time step, given an initial deviation amount set according to actual conditions, thus achieving accurate future rotational speed prediction even with only historical rotational speed information.

[0067] Specifically, such as Figure 2 As shown, this embodiment of the invention provides a method for predicting the rotational speed of a ship's gas-electric hybrid power system, comprising the following steps:

[0068] S1. Based on the ANFIS toolbox of the adaptive neural fuzzy prediction system, a propeller speed prediction model for ship gas-electric hybrid power system is constructed to predict the propeller speed of the gas-electric hybrid power system.

[0069] S2, calculate the difference between the predicted rotational speed in step S1 and the actual rotational speed of the ship's gas-electric hybrid power system;

[0070] S3. Based on the speed difference obtained in step S2 and the speed information obtained from the ship gas-electric hybrid propeller speed prediction model in step S1, construct an improved ANFIS speed prediction model.

[0071] S4. Predict future speed using the improved ANFIS speed prediction model constructed in step S3.

[0072] The single-input rotational speed prediction model established in step S1 uses the rotational speed information input into ANFIS for training. This information is obtained from the actual propeller rotational speed under two identical operating conditions of the ship, and is used as the input rotational speed and the actual rotational speed for training.

[0073] For example, the construction of the ship's gas-electric hybrid power system speed prediction model in step 1 specifically includes:

[0074] (a) Typical speed information under two identical operating conditions is provided by the ship's gas-electric hybrid power system, and used as the input information and actual information for ANFIS respectively;

[0075] (b) Using the speed information obtained in step (a), construct a speed prediction model for the ship's gas-electric hybrid power system with the help of the ANFIS toolbox.

[0076] The difference between the predicted rotational speed and the actual rotational speed obtained in step S2 is the difference between the input rotational speed in step S1 and the predicted rotational speed obtained by establishing the model in step S1.

[0077] The improved speed prediction model established in step S3 uses the difference between the speed prediction result obtained in step S1 and the input speed, and the same input speed as in step S1, as input quantities for training. The actual speed used for training is the same as in step S1.

[0078] The use of the model in step S4 specifically includes:

[0079] (1) First, input the initial speed and the difference to pre-train the model built in step S3 to obtain the advanced speed prediction value;

[0080] (2) Determine the prediction step size based on actual needs and the prediction value trained by the prediction model to ensure real-time performance. Use the advanced speed prediction value obtained in step (1) as the initial feedback signal to complete the speed prediction.

[0081] Example 2

[0082] This invention provides a method for predicting the rotational speed of a ship's gas-electric hybrid power system. Within the theoretical framework of fuzzy logic rules, and based on the principle of adaptive neural networks, the method adjusts the rules using a backpropagation algorithm after collecting input-output data to adapt to the fuzzy logic environment and establish a rotational speed prediction model. Furthermore, the method improves the rotational speed prediction model by utilizing the difference between the prediction model's output and input. To meet the needs of different multi-objective optimization models, the method proposes to achieve rotational speed prediction within a given time step. The method includes the following steps:

[0083] Step 1: Construct a prediction model for the rotational speed of a ship's gas-electric hybrid propeller based on an adaptive neural fuzzy prediction system;

[0084] Step 2: Obtain the difference between the predicted speed obtained in Step 1 and the actual speed;

[0085] Step 3: Construct an improved speed prediction model using the difference obtained in Step 2 and the speed information used in Step 1;

[0086] Step 4: Achieve higher accuracy in speed prediction using the model built in Step 3.

[0087] The construction of the speed-adaptive neural fuzzy prediction system in step 1 specifically includes:

[0088] The adaptive neural fuzzy prediction system consists of a five-layer structure:

[0089] This step requires a first-order Sugeno model with one input and one output, using the Takagi-Sugeno IF-THEN rule:

[0090] If x is A then f1=p1x+r1 (1)

[0091] The first layer structure consists of input variable member functions (MFs) and an input, which is the rotational speed information under typical ship operating conditions;

[0092] The second layer structure examines the weights of each MFs, receives input values ​​from the first layer and uses them as member functions to represent the fuzzy set of input variables, and the output of the node represents the strength of the rule.

[0093] The third layer is the rule layer, where each node performs precondition matching of fuzzy rules, that is, calculates the activation level of each rule, and each node calculates the normalized weight.

[0094] The fourth layer provides the output value after rule reasoning for the defuzzification layer, and each node is an adaptive node;

[0095] The fifth layer is the output layer, which calculates the sum of all incoming signals as the total output and outputs the speed prediction result.

[0096] The structure of the single-input ANFIS model established based on the above content is as follows: Figure 3 As shown.

[0097] The difference calculation method in step 2 specifically includes:

[0098] Using the predicted rotational speed V obtained in step 1 * And the input speed V in step 1 in Calculate the difference between the two:

[0099] ΔV=V in -V * (2)

[0100] The improved speed prediction model in step 3 specifically includes:

[0101] The first-order Sugeno model required for this step consists of two inputs and one output, using the Takagi-Sugeno IF-THEN rule:

[0102] If x is A and y is C then f1=p1x+r1 (3)

[0103] The first layer structure consists of input variable member functions, input 1, and input 2. Input 1 is the rotational speed information under the same typical ship operating conditions as in step 1, and input 2 is the difference between the predicted rotational speed obtained in step 2 and the actual rotational speed. Each node in the first layer is an adaptive node, and its node function is:

[0104] O = μ AB (x) (4)

[0105] O = μ CD (x) (5)

[0106] Where μ AB (x) and μ CD (x) represents MFs;

[0107] The second layer is a member layer that checks the weights of each MFs and receives the input values ​​from the first layer as member functions representing the fuzzy set of input variables. Each node is non-adaptive, and this layer multiplies the signals passed from the first layer and sends the product to the next layer, as shown in Equation (6). The output of each node represents the strength of a rule.

[0108] ω i =μ AB (x)*μ CD (y) (6)

[0109] The third layer is the rule layer. Each node in this layer performs fuzzy rule precondition matching. This layer is also non-adaptive. The ratio of the adaptive strength of the calculated rule to the activation strength of all rules is shown in Equation (7).

[0110]

[0111] The fourth layer provides the output value after rule inference for the defuzzification layer. Each node is an adaptive node, and the node function is:

[0112]

[0113] Among them, {p i ,q i ,r i} represents the result parameter set;

[0114] The fifth layer is the output layer, which outputs the improved speed prediction results.

[0115] The structure of the two-input ANFIS model established based on the above content is as follows: Figure 4 As shown, Figure 5 This shows the two-input ANFIS structure and five member functions for each input. White circles represent logical operations, and black circles represent AND operations.

[0116] The use of the model in step 4 specifically includes:

[0117] First, the initial rotational speed V0 and the initial deviation ΔV0 are input for training to obtain the advanced rotational speed prediction result V. p0 The initial feedback quantity is used to obtain the input deviation during actual use of the model; the input speed step size of the improved speed prediction model is reasonably adjusted according to the needs of the optimized scheduling model to further improve the speed prediction accuracy.

[0118] Example 3

[0119] like Figure 6 As shown, an embodiment of the present invention provides a speed prediction device for a marine gas-electric hybrid power system, comprising:

[0120] Module 1 for predicting the propeller speed of a ship's gas-electric hybrid propeller is used to build a predictive model of the propeller speed of a ship's gas-electric hybrid propeller based on the Adaptive Neural Fuzzy Prediction System (ANFIS) toolbox, and to predict the propeller speed of the gas-electric hybrid system.

[0121] The difference acquisition module 2 is used to calculate the difference between the predicted rotational speed and the actual rotational speed of the ship's gas-electric hybrid power system.

[0122] The improved speed prediction model acquisition module 3 is used to construct an improved ANFIS speed prediction model based on the obtained speed difference and the speed information obtained from the ship gas-electric hybrid propeller speed prediction model.

[0123] Future speed prediction module 4 is used to predict future speeds using the improved ANFIS speed prediction model.

[0124] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0125] The information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of the present invention. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.

[0126] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this invention. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments.

[0127] II. Application Examples:

[0128] Application examples

[0129] This invention also provides a computer device comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.

[0130] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps described in the various method embodiments above.

[0131] This invention also provides an information data processing terminal, which, when executed on an electronic device, provides a user input interface to implement the steps described in the above method embodiments. The information data processing terminal is not limited to mobile phones, computers, or switches.

[0132] This invention also provides a server that, when executed on an electronic device, provides a user input interface to implement the steps described in the above method embodiments.

[0133] This invention provides a computer program product that, when run on an electronic device, enables the electronic device to implement the steps described in the various method embodiments above.

[0134] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of this application can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying the computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0135] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0136] III. Evidence of the relevant effects of the embodiments:

[0137] This study aims to predict the rotational speed of a ship's gas-electric hybrid power system throughout its entire operation. A propeller rotational speed prediction model is constructed, and future rotational speeds are predicted based on interpolation with actual rotational speeds. This allows for the prediction of propeller rotational speed at the next moment during ship navigation, thus clarifying the operational status of the ship's gas-electric hybrid power system. The rotational speed prediction of the ship's gas-electric hybrid power system can further improve the application of intelligent ship control and intelligent engine room technology.

[0138] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention and within the spirit and principles of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A method for predicting the rotational speed of a marine gas-electric hybrid power system, characterized in that, The method includes the following steps: S1. Based on the ANFIS toolbox of the adaptive neural fuzzy prediction system, a propeller speed prediction model for ship gas-electric hybrid power system is constructed to predict the propeller speed of the gas-electric hybrid power system. S2, calculate the difference between the predicted rotational speed in step S1 and the propeller rotational speed obtained under the actual operating conditions of the ship's gas-electric hybrid power system. S3. Based on the speed difference obtained in step S2 and the speed information obtained from the ship gas-electric hybrid propeller speed prediction model in step S1, an improved speed prediction model is constructed. S4. Predict future speed using the improved speed prediction model constructed in step S3. The construction of the ship's gas-electric hybrid propeller speed prediction model in step S1 includes: (a) Typical rotational speed information under two identical operating conditions provided by the ship's gas-electric hybrid power system is used as the input information and actual information of the adaptive neural fuzzy prediction system (ANFIS), respectively. (b) Using the rotational speed information obtained in step (a), construct a rotational speed prediction model for the ship's gas-electric hybrid power system with the help of the Adaptive Neural Fuzzy Prediction System (ANFIS) toolbox. The propeller speed prediction model for the ship's gas-electric hybrid power system constructed in step (b) is a single-input speed prediction model. The speed information input into the adaptive neural fuzzy prediction system ANFIS for training is the propeller speed obtained under the actual operating conditions of the ship under two identical conditions, which are used as the input speed and the actual speed for training, respectively. In step S3, the improved speed prediction model is a dual-input speed prediction model. The inputs used for training are the difference between the speed prediction result obtained in step S1 and the input speed, and the same input speed as in step S1. The actual speed used for training is the same as in step S1.

2. The method for predicting the rotational speed of a ship's gas-electric hybrid power system according to claim 1, characterized in that, In step S1, the Adaptive Neural Fuzzy Prediction System (ANFIS) comprises a five-layer structure: The required first-order Sugeno model consists of one input and one output, using the Takagi-Sugeno IF-THEN rule: （1） The first layer structure consists of an input variable member function MFs and an input, which is the rotational speed information under typical ship operating conditions. The second layer structure examines the weights of the member functions MFs for each input variable, receives the input values ​​from the first layer and uses them as member functions to represent the fuzzy set of the input variables, and the output of the node represents the strength of the rule. The third layer is the rule layer, where each node performs precondition matching for fuzzy rules, specifically calculating the activation level of each rule and calculating the normalized weights for each node. The fourth layer provides the output value after rule inference for the defuzzification layer, and each node is an adaptive node; The fifth layer is the output layer, which calculates the sum of all incoming signals as the total output and outputs the speed prediction result.

3. The method for predicting the rotational speed of a ship's gas-electric hybrid power system according to claim 1, characterized in that, In step S2, the difference between the predicted rotational speed and the propeller rotational speed obtained under the actual operating conditions of the ship's gas-electric hybrid power system is the difference between the input rotational speed in step S1 and the predicted rotational speed obtained by establishing the ship's gas-electric hybrid power propeller rotational speed prediction model. Predicted speed values ​​obtained by establishing a propeller speed prediction model for ship gas-electric hybrid power generation and input speed Calculate the difference between the two: （2）。 4. The method for predicting the rotational speed of a ship's gas-electric hybrid power system according to claim 1, characterized in that, In step S3, the improved speed prediction model specifically includes: The required first-order Sugeno model consists of two inputs and one output, using the Takagi-Sugeno IF-THEN rule: （3） The first layer structure consists of input variable member functions, input 1, and input 2. Input 1 is the rotational speed information under the same typical ship operating conditions as in step 1, and input 2 is the difference between the predicted rotational speed obtained in step 2 and the actual rotational speed. Each node in the first layer is an adaptive node, and the node function is: （4） （5） in, and For MFs; The second layer is a member layer that checks the weights of each MFs and receives the input values ​​from the first layer as member functions to represent the fuzzy set of input variables. Each node is non-adaptive. This layer multiplies the signals passed from the first layer and sends the product to the next layer, as shown in formula (6). The output of each node represents the strength of a rule. （6） The third layer is the rule layer. Each node in this layer performs fuzzy rule precondition matching. This layer is non-adaptive. The ratio of the fitness strength of the rule to the activation strength of all rules is calculated as shown in Equation (7). （7） The fourth layer provides the output value after rule inference for the defuzzification layer. Each node is an adaptive node, and the node function is: （8） in, For the result parameter set; The fifth layer is the output layer, which outputs the improved speed prediction results.

5. The method for predicting the rotational speed of a ship's gas-electric hybrid power system according to claim 1, characterized in that, In step S4, predicting future engine speed using the improved engine speed prediction model constructed in step S3 includes: (1) Input the initial input speed and the difference to pre-train the improved speed prediction model constructed in step S3 to obtain the advanced speed prediction value; (2) Determine the prediction step size based on actual needs and the prediction model training prediction value, and use the advanced speed prediction value obtained in step S1 as the initial feedback signal to complete the speed prediction.

6. An apparatus for predicting the rotational speed of a marine gas-electric hybrid power system according to any one of claims 1 to 5, characterized in that, The device includes: The module for predicting the rotational speed of a ship's gas-electric hybrid propeller (1) is used to build a prediction model for the rotational speed of a ship's gas-electric hybrid propeller based on the ANFIS toolbox of the adaptive neural fuzzy prediction system, and to predict the rotational speed of the propeller in the gas-electric hybrid system. The difference acquisition module (2) is used to calculate the difference between the predicted rotational speed and the propeller speed obtained under the actual operating conditions of the ship's gas-electric hybrid power system. An improved speed prediction model acquisition module (3) is used to construct an improved speed prediction model based on the obtained speed difference and the speed information obtained from the ship gas-electric hybrid propeller speed prediction model. The future speed prediction module (4) is used to predict future speeds using the improved speed prediction model that has been constructed.

7. A user input program storage medium, wherein the stored computer program causes an electronic device to execute the speed prediction method for a marine gas-electric hybrid power system according to any one of claims 1-5.

8. The application of the speed prediction method for a marine gas-electric hybrid power system as described in any one of claims 1-5 to the prediction of operating load of a natural gas engine.

Images