A method and system for active damping of a vibration-isolating adapter

Abstract

This invention proposes an active vibration reduction method for vibration-damping nozzles, comprising the following steps: acquiring historical vibration information of the vibration-damping nozzle; constructing an active vibration reduction control model based on adaptive fuzzy inference, inputting the historical vibration information of the vibration-damping nozzle into the active vibration reduction control model for training, and obtaining the trained active vibration reduction control model; collecting real-time vibration information of the vibration-damping nozzle, inputting the real-time vibration information into the active vibration reduction control model, and the active vibration reduction control model outputting vibration compensation force; sending the vibration compensation force to the action unit to execute action compensation to offset external vibration. This method has high control accuracy, effectively suppresses low-frequency vibration of ship pipelines, and can adapt to the vibration reduction and isolation requirements under multiple working conditions and complex stress states, thereby improving the vibration isolation effect of existing ship vibration-damping nozzles.

Description

Technical Field

[0001] This invention relates to the field of ship vibration reduction technology, and in particular to an active vibration reduction method and system using a vibration reduction manipulator. Background Technology

[0002] Vibration damping nozzles are widely used in ship piping connections to reduce rigid connections, thereby weakening and absorbing vibrations at the nozzles, protecting ship piping and reducing vibrations transmitted to the outside, ensuring the ship's safety, reliability, and stealth performance.

[0003] The medium-temperature vibration damping nozzle with announcement number CN103398253B maintains an elongation length of less than 2% of the total nozzle length under internal medium pressure. Its main functions are to isolate the transmission of mechanical vibration and compensate for displacement caused by temperature differences in the pipeline. The flanges at both ends of the nozzle are connected to the outer flange of the pipeline, and anti-loosening rings are provided between the flanges and the outer flanges. When the connecting bolts are tightened, the anti-loosening rings limit the compression deformation of the nozzle sealing surface, protect the sealing surface, and effectively maintain the specific pressure of the sealing surface. A curtain is provided between the inner and outer rubber layers of the nozzle to provide the required strength for the nozzle. The inner lining is made of polytetrafluoroethylene and is vulcanized and bonded to the inner rubber layer to keep the medium clean and provide a sealing function at the ends. Steel rings are embedded inside both ends to fix the curtain together with the flanges.

[0004] Currently, existing vibration damping nozzles have poor low-frequency vibration damping effect, making it difficult to meet the vibration reduction and isolation requirements under multiple working conditions and complex stress states. Furthermore, their vibration control accuracy is low, thus reducing the vibration isolation effect of existing ship vibration damping nozzles. Summary of the Invention

[0005] In view of this, the present invention proposes an active vibration reduction method and system for vibration reduction pipes, which has high control precision, effectively suppresses low-frequency vibration of ship pipelines, and can adapt to the vibration reduction and isolation requirements under multiple working conditions and complex stress states, thereby improving the vibration isolation effect of existing ship vibration reduction pipes.

[0006] The technical solution of this invention is implemented as follows: On one hand, this invention provides an active vibration reduction method for vibration-damping pipes, comprising the following steps:

[0007] S1, obtain historical vibration information of the vibration damping pipe;

[0008] S2, construct an active vibration damping control model based on adaptive fuzzy inference, input the historical vibration information of the vibration damping nozzle into the active vibration damping control model for training, and obtain the trained active vibration damping control model;

[0009] S3 collects real-time vibration information of the vibration damping pipe and inputs the real-time vibration information into the active vibration damping control model. The active vibration damping control model outputs vibration compensation force.

[0010] S4 sends the vibration compensation force to the action unit to perform action compensation to counteract external vibration.

[0011] Based on the above technical solutions, preferably, the step S1 of obtaining historical vibration information of the vibration damping pipe includes constructing a vibration information database, which stores historical vibration information of the vibration damping pipe, including displacement, velocity, acceleration, mass, stiffness, damping, external load and nonlinear element force.

[0012] Based on the above technical solution, preferably, step S1 further includes establishing a vibration equilibrium equation based on the historical vibration information of the vibration damping pipe, with the expression as follows:

[0013]

[0014] In the formula, R NL ( t ) is the global nodal force vector of the sum of nonlinear element forces. R ( t ) is an externally applied load. Forces generated by mass and acceleration, The force generated by damping and acceleration, The force generated by stiffness and displacement.

[0015] Based on the above technical solutions, preferably, step S2, which involves constructing an active vibration damping control model based on adaptive fuzzy inference, inputting historical vibration information of the vibration damping nozzle into the active vibration damping control model for training, and obtaining the trained active vibration damping control model, includes the following sub-steps:

[0016] S21, Preprocess the historical vibration information of the acquired vibration damping pipe;

[0017] S22, an active vibration reduction control model is constructed based on adaptive fuzzy inference, a fuzzy rule base is built, and the membership function is used to fuzzify the input variables to obtain the membership values;

[0018] S23, for each rule in the fuzzy rule base, multiply the membership values ​​corresponding to the input variables to obtain the trigger strength of the corresponding rule. The calculation expression is as follows:

[0019]

[0020] In the formula, y n Indicates the first n The trigger strength of the rule, x k Indicates the first k Individual variables, ik express x k The corresponding membership degree;

[0021] S24, normalize the trigger intensity of all rules to obtain the trigger weight of each rule in the entire rule base;

[0022] S25, Substitute the input variables and calculate the preliminary vibration compensation force estimate based on the mapping relationship;

[0023] S26 uses the normalized trigger intensity as a weight to perform a weighted average on the preliminary vibration compensation force estimate, and outputs the final vibration compensation force after defuzzification.

[0024] Based on the above technical solutions, preferably, the preprocessing includes cleaning, denoising, filtering and normalizing the data, and determining the extracted displacement, velocity and acceleration information features as input variables of the active vibration reduction control model, and the vibration compensation force as output variable of the active vibration reduction control model.

[0025] Based on the above technical solutions, preferably, step S22, which involves constructing an active vibration reduction control model based on adaptive fuzzy inference, building a fuzzy rule base, and using a membership function to fuzzify the input variables to obtain membership values, includes the following sub-steps:

[0026] Define a fuzzy set for each variable, and use fuzzy rules to map the fuzzy set of the input variable to the fuzzy set of the output variable, and combine all the rules to form a fuzzy rule library;

[0027] Select the triangular membership function, initialize the parameters of the membership function, use the triangular membership function to fuzzify the input variables, and calculate the membership values ​​of each fuzzy set.

[0028] Based on the above technical solution, preferably, the mapping relationship in step S25 is a linear combination of the input variables, expressed as:

[0029] f = C 0 + C 1 x 1+ C 2 x 2+ C 3 x 3

[0030] In the formula, f This is a preliminary estimate of the vibration compensation force. C 0 For the bias constant term, C 1. C 2 andC 3 represents the linear coefficients for different input features. x 1. x 2 and x 3 represent input features of different dimensions.

[0031] Based on the above technical solutions, preferably, step S2 further includes dividing the preprocessed data into a training set and a validation set. During the forward propagation process, the least squares method is used to optimize and update the linear parameters of the output layer. During the backpropagation process, only the parameters of the membership function are updated, keeping the linear parameters of the output layer unchanged. During iterative training, if the loss function reaches a preset convergence threshold, the iterative training is stopped.

[0032] Secondly, the present invention also provides an active vibration damping system for a vibration damping nozzle, employing the active vibration damping method for a vibration damping nozzle as described above, the system comprising:

[0033] The acquisition unit is used to acquire historical vibration information of the vibration damping nozzle;

[0034] The model building unit is used to build an active vibration damping control model based on adaptive fuzzy inference. The historical vibration information of the vibration damping nozzle is input into the active vibration damping control model for training, and the trained active vibration damping control model is obtained.

[0035] The acquisition unit collects real-time vibration information of the vibration damping pipe and inputs the real-time vibration information into the active vibration damping control model. The active vibration damping control model outputs vibration compensation force.

[0036] The action unit is used to send the vibration compensation force to the adjustment execution unit to perform the action compensation to counteract the external vibration.

[0037] Thirdly, the present invention also provides an electronic device, comprising: at least one processor, at least one memory, a communication bus, a user interface, and a network interface;

[0038] The processor, memory, user interface, and network interface communicate with each other through the bus.

[0039] The memory stores program instructions that can be executed by the processor, which calls the program instructions to implement the active vibration reduction method of the vibration damping pipe as described above.

[0040] The vibration damping pipe active vibration reduction method and system of the present invention have the following advantages over the prior art:

[0041] (1) By collecting and analyzing historical vibration data of the vibration damping nozzle, an active vibration control model is constructed and optimized using adaptive fuzzy inference. After real-time monitoring of the nozzle vibration state, the model can quickly calculate the required vibration compensation force and accurately guide the action unit to perform the corresponding compensation action, thereby effectively offsetting external vibration. The compensation output is calculated accurately, the control precision is high, and the low-frequency vibration of the ship's pipeline is effectively suppressed. It can adapt to the vibration reduction and isolation requirements under multiple working conditions and complex stress states, thereby improving the vibration isolation effect of the existing ship vibration damping nozzle.

[0042] (2) Set the preprocessed historical vibration data to be input into the active vibration reduction control model. During the forward propagation process, the least squares method is used to optimize and update the linear parameters of the output layer. During the backward propagation process, only the parameters of the membership function are updated, and the linear parameters of the output layer remain unchanged. The training stability can be improved through hybrid learning. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a schematic diagram of the hardware operating environment of the device involved in the embodiments of the present invention;

[0045] Figure 2 This is a flowchart of the active vibration reduction method for the vibration-damping pipe of the present invention;

[0046] Figure 3 This is a schematic diagram of the functional modules of the active vibration reduction system of the vibration reduction pipe of the present invention. Detailed Implementation

[0047] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0048] like Figure 1As shown, the device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0049] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the device. In practical applications, the device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0050] like Figure 1 As shown, the memory 1005, which serves as a medium, may include an operating system, a network communication module, a user interface module, and a vibration damping pipe active vibration damping method program.

[0051] exist Figure 1 In the device shown, the network interface 1004 is mainly used to establish a communication connection between the device and the server that stores all the data required in the active vibration damping method system of the vibration damping pipe; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the active vibration damping method device of the present invention can be set in the active vibration damping method device of the vibration damping pipe, and the active vibration damping method device of the vibration damping pipe calls the active vibration damping method program of the vibration damping pipe stored in the memory 1005 through the processor 1001 and executes the active vibration damping method of the vibration damping pipe provided by the present invention.

[0052] like Figure 2 As shown, the present invention provides an active vibration reduction method for a vibration-damping pipe, comprising the following steps:

[0053] S1, obtain historical vibration information of the vibration damping nozzle.

[0054] In this embodiment, step S1 includes constructing a vibration information database, which stores historical vibration information of the vibration damping pipe. The vibration information includes displacement, velocity, acceleration, mass, stiffness, damping, external load, and nonlinear element force.

[0055] It should be noted that the vibration information database is used to store historical vibration information of the vibration damping nozzle under various working conditions. Obtaining historical vibration information of the vibration damping nozzle provides a necessary data foundation for subsequent construction and training of active vibration damping control models. Among them, displacement is the offset of the vibration damping nozzle from its equilibrium position during vibration; velocity is the change in velocity of the vibration damping nozzle during vibration; acceleration is the change in acceleration of the vibration damping nozzle during vibration; mass is the mass distribution of the vibration damping nozzle and its connecting components; stiffness is the stiffness of the vibration damping nozzle and its supporting structure. Stiffness determines the system's ability to resist deformation when subjected to external forces and has a direct impact on the vibration frequency; damping is the mechanism used in the system to dissipate vibration energy. Damping can reduce the amplitude and duration of vibration; external load is the external force or torque acting on the vibration damping nozzle. External load is the main cause of vibration, and its magnitude, direction, and frequency characteristics directly affect vibration behavior; nonlinear element force is the force generated during vibration due to factors such as material nonlinearity, contact nonlinearity, or geometric nonlinearity.

[0056] In this embodiment, step S1 further includes establishing a vibration equilibrium equation based on the historical vibration information of the vibration damping pipe, the expression of which is:

[0057]

[0058] In the formula, R NL ( t ) is the global nodal force vector of the sum of nonlinear element forces. R ( t ) is an externally applied load. Forces generated by mass and acceleration, The force generated by damping and acceleration, The force generated by stiffness and displacement.

[0059] It should be noted that, M For the quality matrix, displacement vector U ( t The second derivative of ), where C is the damping matrix. displacement vector U ( t The first derivative of ) K It is the stiffness matrix. U ( t ) is a displacement vector. RNL ( t ) is the global nodal force vector of the sum of nonlinear element forces, which includes forces generated by factors such as material nonlinearity, geometric nonlinearity, or contact nonlinearity.

[0060] Understandably, this vibration equilibrium equation describes the vibration behavior of the damping nozzle under dynamic load. The left side of the equation represents the inertial force, damping force, elastic force, and nonlinear force inside the system, while the right side represents the externally applied load. When the system is in equilibrium, the internal force is equal to the external load, providing a theoretical basis for the subsequent active vibration control model.

[0061] S2. An active vibration damping control model is constructed based on adaptive fuzzy inference. The historical vibration information of the vibration damping nozzle is input into the active vibration damping control model for training, and the trained active vibration damping control model is obtained.

[0062] Step S2 includes the following sub-steps:

[0063] S21, preprocess the historical vibration information of the acquired vibration damping nozzle; the preprocessing includes cleaning, denoising, filtering and normalizing the data, and determining the displacement, velocity and acceleration information features as input variables of the active vibration damping control model, and the vibration compensation force as output variable of the active vibration damping control model.

[0064] Understandably, data cleaning identifies and removes outliers. By using statistical methods or threshold settings based on physical principles, abnormal data points caused by sensor malfunctions, measurement errors, or extreme operating conditions can be identified and removed. For missing data points, interpolation or statistical model-based methods can be used to fill in the gaps, ensuring the integrity and continuity of the data. Through preprocessing steps such as data cleaning, denoising, and filtering, the quality and reliability of vibration data can be significantly improved. Furthermore, selecting displacement, velocity, and acceleration features as input variables for the active vibration damping control model can more accurately reflect the vibration state of the vibrating pipe, thereby improving the model's prediction accuracy and control effect.

[0065] S22, an active vibration reduction control model is constructed based on adaptive fuzzy inference, a fuzzy rule base is built, and the membership function is used to fuzzify the input variables to obtain the membership values;

[0066] This includes the following sub-steps:

[0067] Define a fuzzy set for each variable, and use fuzzy rules to map the fuzzy set of the input variable to the fuzzy set of the output variable, and combine all the rules to form a fuzzy rule library;

[0068] Select the triangular membership function, initialize the parameters of the membership function, use the triangular membership function to fuzzify the input variables, and calculate the membership values ​​of each fuzzy set.

[0069] Specifically, fuzzy sets of input and output variables are defined, which typically reflect different states of the variables; the fuzzy set for the input variable displacement D is {small (S), medium (M), large (L)}, the fuzzy set for the input variable velocity V is {slow (S), medium (M), fast (F)}, the fuzzy set for the input variable acceleration A is {negative large (NL), negative small (NS), zero (Z), positive small (PS), positive large (PL)}, and the fuzzy set for the input variable vibration compensation force F is {weak (W), medium (M), strong (S)}.

[0070] In addition, based on the vibration equilibrium equation, fuzzy rules are constructed as follows:

[0071] Rule 1: If the displacement is small (S), the velocity is medium (M), and the acceleration is zero (Z), then the vibration compensation force is weak (W).

[0072] Rule 2: If the displacement is medium (M), the velocity is medium (M), and the acceleration is positive small (PS), then the vibration compensation force is medium (M).

[0073] Rule 3: If the displacement is large (L), the velocity is fast (F), and the acceleration is positive (PL), then the vibration compensation force is strong (S).

[0074] Rule 4: If the displacement is small (S), the velocity is medium (M), and the acceleration is negative small (NS), then the vibration compensation force is weak (W).

[0075] Rule 5: If the displacement is medium (M), the velocity is slow (S), and the acceleration is zero (Z), then the vibration compensation force is the lower value of medium (M).

[0076] Rule 6: If the displacement is medium (M), the velocity is fast (F), and the acceleration is negative large (NL), then the vibration compensation force is the higher value of medium (M) to the lower value of strong (S).

[0077] Rule 7: If the displacement is large (L), the velocity is slow (S), and the acceleration is small (PS), then the vibration compensation force is a higher value of medium (M).

[0078] Rule 8: If the displacement is large (L), the velocity is medium (M), and the acceleration is zero (Z), then the vibration compensation force is strong (S).

[0079] Rule 9: If the displacement is extremely large (VL), the velocity is extremely fast (VF), and the acceleration is any value (regardless of sign or magnitude), then the vibration compensation force is extremely strong (VS).

[0080] Rule 10: If displacement, velocity, and acceleration are all at the boundary values ​​of their fuzzy sets, then a higher compensation force level should be selected.

[0081] All the above rules are combined to form a fuzzy rule base.

[0082] In this embodiment, by defining fuzzy sets and fuzzy rules, the complex dynamic characteristics of the system can be simplified into a series of fuzzy relationships that are easy to understand and process, thereby reducing the complexity of the model. Furthermore, the fuzzy rule base is built based on expert knowledge, which allows experts' experience and intuition to be easily incorporated into the model, thereby improving the accuracy and reliability of the model.

[0083] S23, for each rule in the fuzzy rule base, multiply the membership values ​​corresponding to the input variables to obtain the trigger strength of the corresponding rule. The calculation expression is as follows:

[0084]

[0085] In the formula, y n Indicates the first n The trigger strength of the rule, x k Indicates the first k Individual variables, i k express x k The corresponding membership degree;

[0086] S24, normalize the trigger intensity of all rules to obtain the trigger weight of each rule in the entire rule base;

[0087] S25, Substitute the input variables and calculate the preliminary vibration compensation force estimate based on the mapping relationship;

[0088] In step S25, the mapping relationship is a linear combination of the input variables, expressed as:

[0089] f = C 0 + C 1 x 1+ C 2 x 2+ C 3 x 3

[0090] In the formula, f This is a preliminary estimate of the vibration compensation force.C 0 For the bias constant term, C 1. C 2 and C 3 represents the linear coefficients for different input features. x 1. x 2 and x 3 represent input features of different dimensions.

[0091] S26 uses the normalized trigger intensity as a weight to perform a weighted average on the preliminary vibration compensation force estimate, and outputs the final vibration compensation force after defuzzification.

[0092] Step S2 further includes dividing the preprocessed data into a training set and a validation set, using the preprocessed historical vibration data as input to the active vibration reduction control model, and continuously adjusting the membership function parameters of the fuzzy set and the weights in the rule base through iteration, so that the model output can better fit the target control signal. During the training process, the model parameters can be automatically adjusted according to the error feedback to improve the model's adaptability and accuracy.

[0093] In this embodiment, during the forward propagation process, the least squares method is used to optimize and update the linear parameters of the output layer. During the backward propagation process, only the parameters of the membership function are updated, while keeping the linear parameters of the output layer unchanged.

[0094] It's important to note that in each iteration, the model calculates the output based on the current parameters. For the fuzzy logic part, this typically involves mapping the input data to a fuzzy set and calculating the output according to rules in the rule base. For the output layer, least squares or other optimization algorithms are used to update the linear parameters (C0, C1, C2, and C3) to minimize the error between the output and the target control signal. During backpropagation, the model parameters are adjusted based on the output error. In this example, only the membership function parameters are updated to keep the linear parameters of the output layer unchanged. This can be achieved using gradient descent or other optimization algorithms, where the gradient is calculated using the chain rule. During training, the model parameters are automatically adjusted based on error feedback. Iterative training continues until a preset convergence threshold is reached, at which point the training process stops. Hybrid learning enhances training stability.

[0095] S3 collects real-time vibration information of the vibration damping pipe and inputs the real-time vibration information into the active vibration damping control model. The active vibration damping control model outputs vibration compensation force.

[0096] S4 sends the vibration compensation force to the action unit to perform action compensation to counteract external vibration.

[0097] like Figure 3As shown, the present invention also provides an active vibration damping system for a vibration damping nozzle, employing the active vibration damping method for a vibration damping nozzle as described above. The system includes:

[0098] The acquisition unit is used to acquire historical vibration information of the vibration damping nozzle;

[0099] The model building unit is used to build an active vibration damping control model based on adaptive fuzzy inference. The historical vibration information of the vibration damping nozzle is input into the active vibration damping control model for training, and the trained active vibration damping control model is obtained.

[0100] The acquisition unit collects real-time vibration information of the vibration damping pipe and inputs the real-time vibration information into the active vibration damping control model. The active vibration damping control model outputs vibration compensation force.

[0101] The action unit is used to send the vibration compensation force to the adjustment execution unit to perform the action compensation to counteract the external vibration.

[0102] The present invention also discloses a computer-readable storage medium that stores computer instructions, which cause the computer to implement all or part of the steps of the method described in the embodiments of the present invention. The storage medium includes various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0103] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, meaning they can be distributed across multiple network units. Those skilled in the art can select some or all of the modules to achieve the purpose of this embodiment without any inventive effort, based on actual needs.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for active vibration reduction via a vibration damping pipe, characterized in that, Includes the following steps: S1, Obtain historical vibration information of the vibration damping nozzle. Obtaining historical vibration information of the vibration damping nozzle includes constructing a vibration information database. The vibration information database stores historical vibration information of the vibration damping nozzle. The vibration information includes displacement, velocity, acceleration, mass, stiffness, damping, external load, and nonlinear element force. Step S1 also includes establishing a vibration equilibrium equation based on the historical vibration information of the vibration damping nozzle, with the following expression: ； In the formula, R NL ( t ) is the global nodal force vector of the sum of nonlinear element forces. R ( t ) is an externally applied load. Forces generated by mass and acceleration, The force generated by damping and acceleration, Forces generated by stiffness and displacement; S2, construct an active vibration damping control model based on adaptive fuzzy inference, input the historical vibration information of the vibration damping nozzle into the active vibration damping control model for training, and obtain the trained active vibration damping control model; Step S2 also includes dividing the preprocessed data into a training set and a validation set. During the forward propagation, the least squares method is used to optimize and update the linear parameters of the output layer. During the back propagation, only the parameters of the membership function are updated, while keeping the linear parameters of the output layer unchanged. During iterative training, if the loss function reaches the preset convergence threshold, the iterative training is stopped. S3 collects real-time vibration information of the vibration damping pipe and inputs the real-time vibration information into the active vibration damping control model. The active vibration damping control model outputs vibration compensation force. S4 sends the vibration compensation force to the action unit to perform action compensation to counteract external vibration.

2. The active vibration reduction method for the vibration-damping pipe as described in claim 1, characterized in that: Step S2, which involves constructing an active vibration damping control model based on adaptive fuzzy inference, inputs historical vibration information of the damping nozzle into the active vibration damping control model for training, thereby obtaining the trained active vibration damping control model. This includes the following sub-steps: S21, Preprocess the historical vibration information of the acquired vibration damping pipe; S22, an active vibration reduction control model is constructed based on adaptive fuzzy inference, a fuzzy rule base is built, and the membership function is used to fuzzify the input variables to obtain the membership values; S23, for each rule in the fuzzy rule base, multiply the membership values ​​corresponding to the input variables to obtain the trigger strength of the corresponding rule. The calculation expression is as follows: ； In the formula, y n Indicates the first n The trigger strength of the rule, x k Indicates the first k Individual variables, i k express x k The corresponding membership degree; S24, normalize the trigger intensity of all rules to obtain the trigger weight of each rule in the entire rule base; S25, Substitute the input variables and calculate the preliminary vibration compensation force estimate based on the mapping relationship; S26 uses the normalized trigger intensity as a weight to perform a weighted average on the preliminary vibration compensation force estimate, and outputs the final vibration compensation force after defuzzification.

3. The active vibration reduction method for the vibration-damping pipe as described in claim 1, characterized in that: The preprocessing includes cleaning, denoising, filtering, and normalizing the data, and determining the displacement, velocity, and acceleration information features as input variables of the active vibration reduction control model, and the vibration compensation force as output variable of the active vibration reduction control model.

4. The active vibration reduction method for the vibration-damping pipe as described in claim 2, characterized in that: Step S22, which involves constructing an active vibration reduction control model based on adaptive fuzzy inference, building a fuzzy rule base, and using a membership function to fuzzify the input variables to obtain membership values, includes the following sub-steps: Define a fuzzy set for each variable, and use fuzzy rules to map the fuzzy set of the input variable to the fuzzy set of the output variable, and combine all the rules to form a fuzzy rule library; Select the triangular membership function, initialize the parameters of the membership function, use the triangular membership function to fuzzify the input variables, and calculate the membership values ​​of each fuzzy set.

5. The active vibration reduction method for the vibration-damping pipe as described in claim 4, characterized in that: In step S25, the mapping relationship is a linear combination of the input variables, expressed as: f = C 0 + C 1 x 1+ C 2 x 2+ C 3 x 3 In the formula, f This is a preliminary estimate of the vibration compensation force. C 0 For the bias constant term, C 1. C 2 and C 3 represents the linear coefficients for different input features. x 1. x 2 and x 3 represent input features of different dimensions.

6. A vibration damping pipe active vibration damping system, employing the vibration damping pipe active vibration damping method as described in any one of claims 1 to 5, characterized in that, The system includes: The acquisition unit is used to acquire historical vibration information of the vibration damping nozzle; The model building unit is used to build an active vibration damping control model based on adaptive fuzzy inference. The historical vibration information of the vibration damping nozzle is input into the active vibration damping control model for training, and the trained active vibration damping control model is obtained. The acquisition unit collects real-time vibration information of the vibration damping pipe and inputs the real-time vibration information into the active vibration damping control model. The active vibration damping control model outputs vibration compensation force. The action unit is used to send the vibration compensation force to the adjustment execution unit to perform the action compensation to counteract the external vibration.

7. An electronic device, characterized in that, include: At least one processor, at least one memory, a communication bus, a user interface, and a network interface; The processor, memory, user interface, and network interface communicate with each other through the bus. The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the active vibration reduction method of the vibration damping pipe as described in any one of claims 1 to 5.

Images