Fuzzy control method and system for ship power conversion device

Abstract

The invention provides a fuzzy control method and system for a ship power conversion device, and relates to the technical field of ship power plant control, and the method comprises the steps: building a hybrid model, obtaining a power relative deviation value according to a compensation relation, and superposing the power relative deviation value to a power control input end, the constant rotating speed control of the ship power conversion device is ensured by regulating and controlling the power control output end on line; the current opening value of a steam admission adjusting valve is adjusted on line according to the control parameters of the current power operation section to adjust the steam admission flow and the steam admission pressure, and therefore power tracking of the ship power conversion device is achieved; according to the method, high-precision self-adaptive tracking of the rotating speed and the power of the ship power conversion device is ensured, a constant-rotating-speed variable-power operation mode is ensured, the parameter optimization efficiency and effect are improved, the optimal performance of the system is ensured, and the variable working condition load response capability and the disturbance rejection performance of the ship power conversion device are improved to a great extent.

Description

Technical Field

[0001] The present invention relates to the technical field of ship power plant control, and in particular to a fuzzy control method and system for a ship power conversion device based on neural network identification. Background Art

[0002] The ship power conversion device mainly includes core equipment such as steam generator, steam turbine, generator, steam inlet regulating valve, steam pipeline, etc. Figure 1 As shown, the high-temperature and high-pressure steam generated by the steam generator is input to the inlet of the steam inlet regulating valve through the steam pipe. The pressure and flow of the high-temperature and high-pressure steam are regulated by changing the opening of the steam inlet regulating valve. After being regulated by the steam inlet regulating valve, the steam enters the steam turbine and is converted into mechanical energy. The mechanical energy is further converted into electrical energy and output by driving the coaxially connected generator, thereby providing an energy source for electrical equipment and meeting the energy requirements of the ship's power conversion device.

[0003] At present, ship power conversion devices usually adopt a constant speed and variable power operation mode; constant speed means that the speed of the power output equipment such as the main engine or engine of the ship power conversion device is maintained at a relatively stable value, while variable power means that the output power of the ship power conversion device can be changed according to the actual needs of the ship while the speed remains unchanged; this operation mode can flexibly meet the power requirements of the ship under various working conditions while ensuring the stable operation of the ship.

[0004] However, it's difficult to use the same set of controller parameters for control systems in different power ranges. In practical engineering, a trial-and-error approach is often used to adjust control parameters to meet the control performance requirements of different operating conditions. Therefore, when operating conditions change, the control parameters must be adjusted again using trial-and-error to adapt to the new conditions. This approach not only relies on personnel with extensive experience and extensive testing, but also leads to a time-consuming tuning process, complex commissioning, and long commissioning cycles. Furthermore, complex control systems require extensive adjustments and observations to achieve satisfactory parameters, resulting in a relatively low degree of parameter optimization, making it difficult to ensure optimal system performance. This results in poor variable load response and anti-disturbance performance for marine power conversion systems. Summary of the Invention

[0005] In view of the above problems, the present invention provides a fuzzy control method and system for a ship power conversion device, which is used to solve the problems of poor variable load response capability and anti-disturbance performance of the current ship power conversion device.

[0006] In a first aspect, the present invention provides a fuzzy control method for a ship power conversion device, the method comprising: A hybrid model is established based on neural networks and the mechanism model of ship power conversion devices; Based on the hybrid model, a relative speed deviation value of the current state is obtained to determine whether the current speed needs to be adjusted; if necessary, a compensation relationship between the relative speed change and the relative power change is obtained, and a relative power deviation value is obtained based on the compensation relationship; the relative power deviation value is added to the power control input end, and the constant speed control of the ship power conversion device is ensured by regulating the power control output end; Based on the hybrid model, the power deviation range and the power deviation differential range of the current state are obtained, and the power deviation range and the power deviation differential range are subjected to fuzzification processing, fuzzy rule mapping and defuzzification processing in sequence to obtain control parameters suitable for the current power operation section; the steam inlet flow rate and the steam inlet pressure are adjusted by adjusting the current opening value of the steam inlet regulating valve using the control parameters, thereby realizing power tracking of the ship power conversion device.

[0007] Furthermore, before establishing the hybrid model, it also includes: Real-time collection of state parameters of the ship's power conversion device to obtain the current speed tracking state and power tracking state of the ship's power conversion device; It is determined whether to adjust the current rotation speed and power based on the rotation speed tracking state and the power tracking state.

[0008] Furthermore, the establishment of the hybrid model includes: Obtaining a mechanism model of a ship power conversion device, and connecting the mechanism model and the neural network model in series to obtain a model structure of a hybrid model; The state parameters of the ship power conversion device collected in real time are input into the neural network, and the hybrid model is used to perform nonlinear fitting on the state parameters, thereby realizing parameter identification of the hybrid model.

[0009] Furthermore, the compensation relationship between the relative change in speed and the relative change in power is obtained according to piecewise linearity, including: When the relative change in speed is within the set range, the slope is adjusted to 20000%, indicating that the speed control dead zone has been entered, reducing the frequent operation of the turbine steam inlet regulating valve; Outside this range, the inclination is adjusted to 4%, indicating that it is necessary to quickly change the power transmitted by the ship's power conversion device to the outside world to compensate for the mismatch between the power of the power conversion device and the target load power, thereby ensuring that the current speed of the ship's power conversion device is always maintained at the target speed value.

[0010] Furthermore, the inclination is the negative value of the ratio of the relative change in the rotational speed of the ship power conversion device to the relative change in the output power.

[0011] Furthermore, the Gaussian membership function is used for fuzzy processing.

[0012] Furthermore, the defuzzification process includes: using a centroid defuzzification method to take the abscissa value of the centroid of the area covered by the Gaussian membership function as the defuzzification output.

[0013] Furthermore, the current power tracking state is obtained as follows: comparing a power conversion device speed with a target speed; When the speed of the power conversion device is greater than the target speed, it means that the output speed of the ship's power conversion device is too high and the power transmitted to the outside world by the power conversion device needs to be reduced; When the speed of the power conversion device is equal to the target speed, it means that the output power of the ship's power conversion device is appropriate and there is no need to adjust the power transmitted to the outside by the power conversion device; When the speed of the power conversion device is lower than the target speed, it indicates that the output speed of the ship's power conversion device is too low, and the power transmitted by the power conversion device to the outside world needs to be increased.

[0014] Furthermore, the current power tracking state is obtained as follows: Comparing the power conversion device power with the target load power; When the power conversion device power is greater than the target load power, it means that the output power of the ship's power conversion device is too large, and the steam inlet regulating valve needs to be adjusted to reduce the steam inlet flow rate; When the power conversion device power is equal to the target load power, it means that the output power of the ship's power conversion device is appropriate and there is no need to adjust the steam inlet regulating valve; When the power of the power conversion device is less than the target load power, it means that the output power of the ship's power conversion device is insufficient, and the steam inlet regulating valve needs to be adjusted to increase the steam inlet flow rate.

[0015] In a second aspect, the present invention provides a fuzzy control system for a ship power conversion device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any one of the above methods.

[0016] In general, the present invention provides a fuzzy control method and system for a ship power conversion device. The technical solution conceived by the present invention can achieve the following beneficial effects compared with the prior art: (1) The present invention establishes a hybrid model, obtains a power relative deviation value based on a compensation relationship, superimposes the power relative deviation value on a power control input terminal, and ensures constant speed control of a ship power conversion device by online regulating the power control output terminal; adjusts the current opening value of the steam inlet regulating valve online through the control parameters of the current power operation section to adjust the steam inlet flow rate and steam inlet pressure, thereby achieving power tracking of the ship power conversion device; ensures high-precision adaptive tracking of the speed and power of the ship power conversion device, ensures a constant speed and variable power operation mode, improves the parameter optimization efficiency and effect, ensures the optimal performance of the system, and greatly improves the variable load response capability and anti-disturbance performance of the ship power conversion device.

[0017] (2) The present invention can adjust various parameters such as the inclination index, proportional coefficient, integral coefficient, etc. online according to the power tracking state and speed tracking state of the ship power conversion device, thereby ensuring high-precision adaptive tracking of the speed and power of the ship power conversion device and improving the variable load response capability and anti-disturbance performance of the ship power conversion device.

[0018] (3) The present invention connects the mechanism model and the neural network model in series to obtain a hybrid model, and performs parameter identification on the hybrid models of the high power section and the low power section of the ship power conversion device respectively, and obtains design parameters that are difficult to obtain accurately, such as flow correction coefficient, stage efficiency, steam distribution parameters and other design parameters. By adjusting the design parameters to simulate the hybrid models of different power sections, hybrid models of different working conditions can be obtained, and state parameters such as the relative deviation value of the speed, power deviation range, and power deviation differential range of the corresponding working conditions can be obtained, thereby avoiding reliance on personnel with a large amount of experiments and accumulated experience, especially for complex control systems, and improving debugging efficiency and effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 This is a schematic structural diagram of a ship cooling system of a fuzzy control method and system for a ship power conversion device provided by the present invention; Figure 2 This is a schematic diagram of the steps of a fuzzy control method and system for a ship power conversion device provided by the present invention; Figure 3 This is a schematic diagram of a hybrid model of a fuzzy control method and system for a ship power conversion device provided by the present invention; Figure 4 This is a schematic diagram of the compensation relationship of a fuzzy control method and system for a ship power conversion device provided by the present invention; Figure 5 The present invention provides a fuzzy control method for a ship power conversion device and a schematic diagram of the fuzzy control principle of the system. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0022] It should be noted that, in the description of the embodiments of the present invention, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a method, step, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such method, step, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the method, step, or apparatus comprising the element.

[0023] In order to solve the problem of poor load response capability and anti-disturbance performance of current ship power conversion devices, the present invention proposes a fuzzy control method and system for ship power conversion devices. Specifically, Figure 2 As shown, the method includes: S101: Establish a hybrid model based on neural network and mechanism model of ship power conversion device; S102: Based on the hybrid model, a relative speed deviation value of the current state is obtained, and it is determined whether the current speed needs to be adjusted; if necessary, a compensation relationship between the relative speed change and the relative power change is obtained, and a relative power deviation value is obtained based on the compensation relationship; the relative power deviation value is added to the power control input end, and the constant speed control of the ship power conversion device is ensured by regulating the power control output end; S103: Based on the hybrid model, the power deviation range and the power deviation differential range of the current state are obtained, and the power deviation range and the power deviation differential range are subjected to fuzzification processing, fuzzy rule mapping and defuzzification processing in sequence to obtain control parameters suitable for the current power operation section; the steam inlet flow rate and the steam inlet pressure are adjusted by adjusting the current opening value of the steam inlet regulating valve using the control parameters, thereby realizing power tracking of the ship power conversion device.

[0024] As an embodiment, before establishing the hybrid model, the following steps are further included: Real-time collection of state parameters of the ship's power conversion device to obtain the current speed tracking state and power tracking state of the ship's power conversion device; Determine whether to adjust the speed and power of the current state based on the speed tracking state and the power tracking state; If there is a difference between the speed of the power conversion device and the target speed, or if there is a difference between the power of the power conversion device and the target load power, then the subsequent steps are entered to adjust the speed and power; otherwise, if there is no difference, then the current state can be maintained.

[0025] It should be noted that status parameters include measured parameters such as power conversion unit power, power change, power conversion unit speed, speed change, inlet steam flow, inlet steam pressure, and intake control valve opening. When these parameters exceed safety thresholds, an alarm will be triggered.

[0026] Furthermore, the current power tracking state is obtained as follows: comparing a power conversion device speed with a target speed; When the speed of the power conversion device is greater than the target speed, it means that the output speed of the ship's power conversion device is too high and the power transmitted to the outside world by the power conversion device needs to be reduced; When the speed of the power conversion device is equal to the target speed, it means that the output power of the ship's power conversion device is appropriate and there is no need to adjust the power transmitted to the outside by the power conversion device; When the speed of the power conversion device is lower than the target speed, it indicates that the output speed of the ship's power conversion device is too low, and the power transmitted by the power conversion device to the outside world needs to be increased.

[0027] The current power tracking status is obtained as follows: Comparing the power conversion device power with the target load power; When the power conversion device power is greater than the target load power, it means that the output power of the ship's power conversion device is too large, and the steam inlet regulating valve needs to be adjusted to reduce the steam inlet flow rate; When the power conversion device power is equal to the target load power, it means that the output power of the ship's power conversion device is appropriate and there is no need to adjust the steam inlet regulating valve; When the power of the power conversion device is less than the target load power, it means that the output power of the ship's power conversion device is insufficient, and the steam inlet regulating valve needs to be adjusted to increase the steam inlet flow rate.

[0028] S101: Establish a hybrid model based on the neural network and the mechanism model of the ship power conversion device.

[0029] Due to the complexity of the precise nonlinear model of the ship's power conversion device, the design parameters of the models in different power ranges are different, and it is difficult to obtain accurate design parameters of the power conversion device, such as flow correction coefficient, stage efficiency, steam distribution parameters, etc., which results in the characteristic curve of the steam inlet regulating valve opening and steam inlet flow needing to be obtained through trial and error, which is time-consuming, labor-intensive and has low accuracy.

[0030] Therefore, the present application establishes a hybrid model, connects the mechanism model and the neural network model in series to obtain a hybrid model, and performs parameter identification on the hybrid models of the high-power section and the low-power section of the ship power conversion device respectively, and obtains design parameters that are difficult to obtain accurately, such as flow correction coefficient, stage efficiency, steam distribution parameters and other design parameters. By adjusting the design parameters to simulate the hybrid models of different power sections, hybrid models of different working conditions can be obtained, and state parameters such as the relative deviation value of the speed, power deviation range, and power deviation differential range of the corresponding working conditions can be obtained, avoiding reliance on personnel with a large amount of experiments and accumulated experience, especially for complex control systems, and improving debugging efficiency and effect.

[0031] As an embodiment, the establishment of the hybrid model includes: Obtain the mechanism model of the ship power conversion device, and connect the mechanism model and the neural network model in series to obtain the model structure of the hybrid model; The state parameters of the ship power conversion device collected in real time are input into the neural network, and the hybrid model is used to perform nonlinear fitting on the state parameters, thereby realizing parameter identification of the hybrid model.

[0032] The mechanism model and the neural network model are connected in series to obtain a hybrid model; the model structure and the input and output information of the neural network are determined according to the mechanism model. Figure 3 As shown, the input information of the neural network is and , the output information is ; The input information of the mechanism model is and , the output information is .in, Indicates real-time collection of status parameters of ship power conversion device; Indicates real-time acquisition of control parameters of ship power conversion device; Represents the state parameters identified by the neural network; Indicates based on and Predicted state parameters for the next moment; Indicates a delay of one time step, that is, taking the prediction result of the previous step and feeding it back to the neural network; Represents the corrected state parameters; represents the design parameters; represents the target state parameter; Indicates time.

[0033] The state parameters and control parameters of the ship power conversion device are collected in real time and simultaneously input into a neural network to obtain identified state parameters. The identified state parameters and control parameters are then simultaneously input into a mechanism model to obtain predicted k+1 state parameters, which are then fed back into the neural network for prediction at time k+2. Corrected state parameters are then obtained based on the predicted k+1 state parameters and the target state parameters, and fed back into the neural network to obtain the corresponding design parameters. This iterative process is repeated to obtain a hybrid model. The hybrid model performs parameter identification for different power ranges to obtain accurate design parameters, such as flow correction coefficient, stage efficiency, and steam distribution parameters. By adjusting the design parameters and simulating the hybrid model for different power ranges, state parameters such as relative speed deviation, power deviation range, and power deviation differential range under different operating conditions are directly obtained. Preferably, the neural network is a BP neural network. Control parameters refer to variables used to adjust and optimize the performance of the ship power conversion device. These parameters can be proportional coefficients, integral coefficients, differential coefficients, gain coefficients, etc., and they affect the system's dynamic response, stability, and accuracy.

[0034] S102: Based on the hybrid model, a relative speed deviation value of the current state is obtained to determine whether the current speed needs to be adjusted; if necessary, a compensation relationship between the relative speed change and the relative power change is obtained, and a relative power deviation value is obtained based on the compensation relationship; the relative power deviation value is superimposed on the power control input end, and the constant speed control of the ship power conversion device is ensured by regulating the power control output end.

[0035] Specifically, an inclination index is designed based on the target speed, speed, speed change, power, and power change of the ship's power conversion device. Following a piecewise linear design approach, a compensation relationship is derived between the relative speed change (speed change / speed) and the relative power change (power change / power) of the power conversion device. Based on the inclination index, the power delivered to the external environment by the ship's power conversion device is altered to compensate for the mismatch between the power conversion device power and the target load power, ensuring that the speed of the ship's power conversion device remains constant at the rated parameter value.

[0036] It should be noted that the speed compensation capability depends on the inclination The inclination is the negative value of the ratio of the relative change in the speed of the ship's power conversion device to the relative change in the output power. That is: ; Indicates the speed change; Indicates the speed of the power conversion device; Indicates the power change; Indicates the power of the power conversion device.

[0037] When the ship power conversion device is put into the speed automatic control mode, the cassette compensation characteristics are used to adjust the mismatch between the power conversion device power and the target load power. According to the piecewise linear design idea, the following is obtained: Figure 4 The compensation relationship between the relative change in speed and the relative change in power of the ship power conversion device shown may specifically include: When the relative speed change is within the set range (for example, the set range is 0.05%), the inclination is adjusted to 20000%. At this time, it basically does not respond to the speed fluctuation of the ship's power conversion device, indicating that it has entered the speed control dead zone, reducing the frequent operation of the turbine steam inlet regulating valve; Outside this range, the inclination is adjusted to 4%, indicating that it is necessary to quickly change the power transmitted by the ship's power conversion device to the outside world to compensate for the mismatch between the power of the power conversion device and the target load power, thereby ensuring that the current speed of the ship's power conversion device is always maintained at the target speed value.

[0038] S103: Based on the hybrid model, the power deviation range and the power deviation differential range of the current state are obtained, and the power deviation range and the power deviation differential range are subjected to fuzzification processing, fuzzy rule mapping and defuzzification processing in sequence to obtain control parameters suitable for the current power operation section; the steam inlet flow rate and the steam inlet pressure are adjusted by adjusting the current opening value of the steam inlet regulating valve using the control parameters, thereby realizing power tracking of the ship power conversion device.

[0039] Specifically, if Figure 5 As shown, the method of obtaining the power deviation range and power deviation differential range of the current state based on the hybrid model is: The power relative deviation value is superimposed on the power control input end, and the target load power is obtained at the same time. The load setting value is obtained based on the power relative deviation value and the target load power. The load deviation is obtained based on the load setting value and the power of the power conversion device. The power deviation range and power deviation differential range of the target load power and the power conversion device power are obtained based on the load deviation.

[0040] The power deviation range (E) and the power deviation differential range (EC) are subjected to fuzzification processing, fuzzy rule mapping and defuzzification processing in sequence to obtain the proportional coefficient, integral coefficient and differential coefficient, etc. suitable for the current power operation section; the opening value of the steam inlet regulating valve can be calculated by the power PID controller, and the steam inlet flow and pressure can be adjusted by adjusting the opening value of the steam inlet regulating valve, thereby achieving the power tracking performance of the power conversion device.

[0041] It should be noted that using a power PID controller to calculate the opening value of the steam inlet regulating valve is a common control strategy. The PID controller adjusts the control output by calculating control parameters such as the proportional coefficient, integral coefficient, and differential coefficient to achieve the desired system performance. This will not be discussed in detail here.

[0042] As an embodiment, a Gaussian membership function may be used to perform fuzzy processing.

[0043] Among them, the Gaussian membership function is: .

[0044] For example, the power deviation range is [-6.8, 6.8] and the power deviation differential range is [-0.91, 0.91]. The fuzzification level of the power deviation range is shown in Table 1, and the fuzzification level of the power deviation differential range is shown in Table 2.

[0045] Table 1 Fuzzy classification of power deviation range

[0046] Table 2 Fuzzy classification of power deviation differential range

[0047] Among them, NB means negative large. If it means power deviation, it indicates that the power of the power conversion device is much smaller than the target load power. If it means power deviation differential, it indicates that the power deviation change rate is negative, and the power of the power conversion device deviates from the target load power in the negative direction at a larger rate; NS means negative small, which has the same meaning as negative large, but the change amplitude is smaller; Z means zero, that is, the power control is in the target state, and the power deviation or the power deviation differential is 0; PS has the opposite meaning to NS, but the amplitude is the same; PB has the opposite meaning to NB, but the amplitude is the same.

[0048] The fuzzy rule mapping may be a fuzzy rule table, as shown in Table 3.

[0049] Table 3 Fuzzy rule table

[0050] It should be noted that the actual control of a ship's power conversion system requires determining the opening of the steam inlet control valve. However, the output of the fuzzy rule mapping is a fuzzy value, making it difficult to directly use it to issue control instructions for the steam inlet control valve. Therefore, defuzzification is required to convert the resulting fuzzy rule mapping into a precise value.

[0051] As an embodiment of the present invention, the defuzzification process includes: using a centroid defuzzification method to output the abscissa value of the centroid of the area covered by the Gaussian membership function as a defuzzified output.

[0052] The calculation formula of the centroid defuzzification method is: ,in, Represents the output fuzzy set In the domain superior The membership value at .

[0053] It should be noted that if a satisfactory power conversion device speed and power control effect cannot be obtained, steps S101 to S103 are repeated continuously to adjust the neural network parameters, compensation relationship, and key parameters such as fuzzification, fuzzy rule mapping and defuzzification until a satisfactory power conversion device speed / power control effect is achieved.

[0054] On the other hand, the present invention also provides a fuzzy control system for a ship power conversion device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of any of the above methods.

[0055] Specifically, the pump-valve dynamic coordinated control system includes a system state monitoring module, a system model identification module, a power conversion device speed compensation control module, and a power conversion device power fuzzy control module.

[0056] The system status monitoring module is used to collect the status parameters of the ship's power conversion device in real time, obtain the current power tracking status and speed tracking status of the ship's power conversion device; and determine whether to adjust the power and speed of the current state based on the power tracking status and speed tracking status.

[0057] The system model identification module is used to establish a hybrid model based on the neural network and the mechanism model of the ship power conversion device.

[0058] The speed compensation control module of the power conversion device is used to obtain the relative speed deviation value of the current state based on the hybrid model to determine whether the current speed needs to be adjusted; if necessary, the compensation relationship between the relative change in speed and the relative change in power is obtained, and the relative power deviation value is obtained based on the compensation relationship; the relative power deviation value is superimposed on the power control input end, and the constant speed control of the ship power conversion device is ensured by regulating the power control output end.

[0059] The power fuzzy control module of the power conversion device is used to obtain the power deviation range and power deviation differential range of the current state based on the hybrid model, and perform fuzzification processing, fuzzy rule mapping and defuzzification processing on the power deviation range and power deviation differential range in sequence to obtain control parameters suitable for the current power operation section; by using the control parameters to adjust the current opening value of the steam inlet regulating valve to adjust the steam inlet flow and steam inlet pressure, thereby realizing power tracking of the ship power conversion device.

[0060] The technical features of the systems are consistent and will not be described in detail here.

[0061] In summary, the present invention can adjust the inclination index K of the speed compensation control module and the proportional coefficient and integral coefficient of the power fuzzy control module online according to the power tracking state and speed tracking state of the power conversion device, thereby ensuring high-precision adaptive tracking of the speed and power of the power conversion device and improving the variable load response capability and anti-disturbance performance of the power conversion device.

[0062] It should be noted that for the aforementioned embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0063] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0064] In the several embodiments provided in this application, it should be understood that the disclosed methods or systems can be implemented in other ways. For example, the embodiments described above are merely illustrative, and the division of the units described is merely a logical functional division. In actual implementation, other division methods may be used, such as combining or integrating multiple units or components into another system, or ignoring or not implementing certain features.

[0065] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0066] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0067] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A fuzzy control method for a ship power conversion device, characterized in that: The method comprises: A hybrid model is established based on neural networks and the mechanism model of ship power conversion devices; Based on the hybrid model, a relative speed deviation value of the current state is obtained to determine whether the current speed needs to be adjusted; if necessary, a compensation relationship between the relative speed change and the relative power change is obtained, and a relative power deviation value is obtained based on the compensation relationship; the relative power deviation value is added to the power control input end, and the constant speed control of the ship power conversion device is ensured by regulating the power control output end; Based on the hybrid model, the power deviation range and the power deviation differential range of the current state are obtained, and the power deviation range and the power deviation differential range are subjected to fuzzification processing, fuzzy rule mapping and defuzzification processing in sequence to obtain control parameters suitable for the current power operation section; the steam inlet flow rate and the steam inlet pressure are adjusted by adjusting the current opening value of the steam inlet regulating valve using the control parameters, thereby realizing power tracking of the ship power conversion device.

2. The fuzzy control method for a ship power conversion device according to claim 1, characterized in that: Before building the hybrid model, also include: Real-time collection of state parameters of the ship's power conversion device to obtain the current speed tracking state and power tracking state of the ship's power conversion device; It is determined whether to adjust the current rotation speed and power based on the rotation speed tracking state and the power tracking state.

3. The fuzzy control method for a ship power conversion device according to claim 1, characterized in that: The establishment of the hybrid model includes: Obtaining a mechanism model of a ship power conversion device, and connecting the mechanism model and the neural network model in series to obtain a model structure of a hybrid model; The state parameters of the ship power conversion device collected in real time are input into the neural network, and the hybrid model is used to perform nonlinear fitting on the state parameters, thereby realizing parameter identification of the hybrid model.

4. The fuzzy control method for a ship power conversion device according to claim 1, characterized in that: The compensation relationship between the relative change in speed and the relative change in power is obtained according to the piecewise linear method, including: When the relative change in speed is within the set range, the slope is adjusted to 20000%, indicating that the speed control dead zone has been entered, reducing the frequent operation of the turbine steam inlet regulating valve; Outside this range, the inclination is adjusted to 4%, indicating that it is necessary to quickly change the power transmitted by the ship's power conversion device to the outside world to compensate for the mismatch between the power of the power conversion device and the target load power, thereby ensuring that the current speed of the ship's power conversion device is always maintained at the target speed value.

5. The fuzzy control method for a ship power conversion device according to claim 4, characterized in that: The inclination is the negative value of the ratio of the relative change in the rotational speed of the ship power conversion device to the relative change in the output power.

6. The fuzzy control method for a ship power conversion device according to claim 1, characterized in that: The fuzzy processing is performed using Gaussian membership function.

7. The fuzzy control method for a ship power conversion device according to claim 6, characterized in that: The defuzzification process includes: using a centroid defuzzification method and taking the horizontal coordinate value of the centroid of the area covered by the Gaussian membership function as the defuzzification output.

8. The fuzzy control method for a ship power conversion device according to claim 2, characterized in that: The current power tracking status is obtained as follows: comparing a power conversion device speed with a target speed; When the speed of the power conversion device is greater than the target speed, it means that the output speed of the ship's power conversion device is too high and the power transmitted to the outside world by the power conversion device needs to be reduced; When the speed of the power conversion device is equal to the target speed, it means that the output power of the ship's power conversion device is appropriate and there is no need to adjust the power transmitted to the outside by the power conversion device; When the speed of the power conversion device is lower than the target speed, it indicates that the output speed of the ship's power conversion device is too low, and the power transmitted by the power conversion device to the outside world needs to be increased.

9. The fuzzy control method for a ship power conversion device according to claim 2, characterized in that: The current power tracking status is obtained as follows: Comparing the power conversion device power with the target load power; When the power conversion device power is greater than the target load power, it means that the output power of the ship's power conversion device is too large, and the steam inlet regulating valve needs to be adjusted to reduce the steam inlet flow rate; When the power conversion device power is equal to the target load power, it means that the output power of the ship's power conversion device is appropriate and there is no need to adjust the steam inlet regulating valve; When the power of the power conversion device is less than the target load power, it means that the output power of the ship's power conversion device is insufficient, and the steam inlet regulating valve needs to be adjusted to increase the steam inlet flow rate.

10. A fuzzy control system for a ship power conversion device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the method according to any one of claims 1 to 9.

Images