Intelligent vibration isolation control method and system based on vibration monitoring

Abstract

The invention discloses an intelligent vibration isolation control method and system based on vibration monitoring, and the method comprises the steps: collecting vibration data, carrying out the preprocessing, carrying out the fuzzy conversion according to the preprocessed data, and calculating a preliminary control quantity; constructing an optimization model and defining a target function, using a locust optimization algorithm to iteratively optimize the population position until the target function value converges, and using the initial control quantity as the final optimization model input to obtain the final control quantity; driving force signals are calculated based on the final control quantity, a difference equation is further constructed based on accumulation of the driving force signals, then a predicted value is output, conversion is carried out according to the obtained predicted value, and instantaneous data are obtained. According to the method, efficient adaptive control over a complex nonlinear vibration system is achieved, the optimization process is rapidly converged, the target function optimization result is directly used for dynamic adjustment of the control quantity, the time for calculation of the control quantity is remarkably shortened, the future vibration trend is predicted through a difference equation, and the calculation efficiency is improved. And the dynamic response capability is further improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent vibration isolation control, and particularly relates to an intelligent vibration isolation control method and system based on vibration monitoring. Background Art

[0002] In recent years, with the rapid development of sensor technology, signal processing technology, and intelligent control algorithms, active vibration isolation technology based on vibration monitoring has gradually become a research hotspot. The active vibration isolation technology realizes adaptive isolation in a complex vibration environment by monitoring the vibration signals of the system in real time, calculating the optimal control quantity through an intelligent algorithm, and driving the actuator to generate a reverse force to offset the vibration.

[0003] However, the existing vibration isolation control methods usually have difficulty in achieving efficient control in multi-variable and complex non-linear systems, and it is difficult to complete the calculation of complex control quantities in a short time, which affects the real-time performance and dynamic response ability of the vibration isolation control system. Summary of the Invention

[0004] Aiming at the above technical problems, the present invention provides an intelligent vibration isolation control method and system based on vibration monitoring, which solves the problems that the existing vibration isolation control methods usually have difficulty in achieving efficient control in multi-variable and complex non-linear systems, and it is difficult to complete the calculation of complex control quantities in a short time, which affects the real-time performance and dynamic response ability of the vibration isolation control system.

[0005] The technical solution adopted by the present invention to solve its technical problems is as follows: An intelligent vibration isolation control method based on vibration monitoring, the method comprising the following steps: S100: Collect vibration data, preprocess the vibration data to obtain preprocessed data; S200: Calculate the target signal and vibration deviation according to the preprocessed data, analyze the change rate of the vibration deviation, perform fuzzy conversion on the vibration deviation and the change rate and integrate the membership values, infer and merge the control quantity fuzzy sets through the Mamdani fuzzy inference method, divide the discrete points and calculate the membership values, screen the discrete points and calculate the preliminary control quantity; S300: Construct an optimization model and define an objective function, randomly initialize the membership values and generate an initial population, use the locust optimization algorithm to iteratively optimize the population position until the objective function value converges, output the final optimization model, use the preliminary control quantity as the input of the final optimization model to obtain the final control quantity; S400: Calculate the driving force signal based on the final control quantity, and further construct a difference equation based on the accumulation of the driving force signal and output a predicted value, and perform conversion according to the obtained predicted value to obtain instantaneous data; S500: Calculate the control error based on the instantaneous data, perform control adjustment based on the control error, and store the adjustment result in a database.

[0006] Preferably, S100 includes: S110: Collect vibration data by deploying an acceleration sensor; S120: Decompose and reconstruct the collected data using wavelet decomposition technology to obtain denoised data; S130: Based on the denoised data, perform a normalization operation on the denoised data using a normalization method to obtain normalized data.

[0007] Preferably, S200 includes: S210: Based on the denoised data, calculate the mean using the mean formula, define the obtained mean as the target signal, subtract the normalized data from the target signal to obtain the vibration deviation; S220: Calculate the vibration deviation at the previous time using time series analysis, and subtract the vibration deviation at the previous time from the vibration deviation to obtain the vibration deviation change rate; S230: Define the vibration deviation and the vibration deviation change rate as input variables. Based on the obtained input variables, perform a fuzzy conversion using a triangular membership function to obtain the converted membership values. Integrate the obtained membership values to obtain the fuzzy value set of the vibration deviation and the fuzzy value set of the vibration deviation change rate; S240: Define a fuzzy control rule table, use the fuzzy value set of the vibration deviation and the fuzzy value set of the vibration deviation change rate as the input of the Mamdani fuzzy inference method, and use the Mamdani fuzzy inference method to combine the rule activation strength and the fuzzy set truncation formula to infer the fuzzy control rule table to obtain the inferred fuzzy set of the control quantity. Based on the inferred fuzzy set of the control quantity, use the maximum membership degree method to merge the fuzzy sets of the control quantities of all rules to obtain the merged fuzzy set; S250: Divide the merged fuzzy set into M discrete points through an equidistant discretization method, and calculate the membership value of each discrete point using a triangular membership function; S260: Set a selection threshold, compare the membership value corresponding to the discrete point with the threshold. When the membership value corresponding to the discrete point is greater than or equal to the threshold, retain the discrete point; otherwise, eliminate it. Based on the retained discrete points, calculate the preliminary control quantity using the discretization formula.

[0008] Preferably, in S230, based on the obtained input variables, perform a fuzzy conversion using a triangular membership function to obtain the converted membership values. Specifically: The fuzzy formula for the vibration deviation is: ; In the formula, represents the input variable vibration deviation The membership value belonging to the fuzzy value set of vibration deviation represents the vibration deviation represents the maximum absolute value of the vibration deviation; The fuzzy value set of the vibration deviation is expressed as: ; In the formula, represents negative large, represents negative small, represents the central value, represents positive small, represents positive large; The fuzzification formula of the vibration deviation change rate is: ; In the formula, represents the input variable of the vibration deviation change rate The membership value belonging to the fuzzy value set of the vibration deviation change rate represents the vibration deviation change rate, represents the maximum absolute value of the vibration deviation change rate; The fuzzy value set of the vibration deviation change rate is expressed as: ; In the formula, represents negative speed, represents zero speed, represents positive speed; The rule activation formula in the Mamdani fuzzy inference method in S240 is: ; In the formula, represents the rule activation intensity, represents taking the minimum value of the membership value; The truncation formula of the rule output fuzzy set is: ; In the formula, represents the membership function of the fuzzy set after being truncated by the activation intensity represents the output variable obtained through Mamdani fuzzy inference, represents the original membership function of the fuzzy set output by the fuzzy rule; Based on the inferred fuzzy set of the control quantity, the maximum membership degree method is used to merge the fuzzy sets of the control quantities of all rules to obtain the merged fuzzy set, specifically: ; In the formula, represents the merged fuzzy set, denotes taking the maximum membership value, denotes the fuzzy set output by the nth rule; In S250, the preliminary control quantity is calculated using the discretization formula as follows: ; In the formula, denotes the preliminary control quantity at time t, denotes the weight of the discrete point, denotes the ith discrete point 's membership value, and S denotes the total number of discrete points retained.

[0009] Preferably, S300 includes: S310: Based on the obtained preliminary control quantity, use the recursive estimation method to calculate the preliminary control quantity of the previous state, subtract the preliminary control quantity of the previous state from the preliminary control quantity to obtain the change rate of the control quantity; S320: Randomly initialize the membership values of all retained discrete points, generate multiple groups of initial membership value combinations as the initial population, and perform offset adjustment on the total parameter value of the initial population according to the preliminary control quantity; S330: Construct an optimization model, and define the objective function of the optimization model based on the change rate of the control quantity: ; In the formula, denotes the objective function value, denotes the change rate of the control quantity at time t, denotes the vibration deviation at time t, denotes the weight factor of the control quantity change, denotes the total number of time steps; S340: Use the locust optimization algorithm to calculate the interaction forces of the individuals in the population, calculate the objective function value corresponding to the individual after updating the positions of the individuals in the population. During the iteration process, continuously update the population positions, and stop the iteration when the objective function value converges, and output the final optimization model; S350: Input the preliminary control quantity into the final optimization model and output the final control quantity.

[0010] Preferably, S400 includes: S410: Calculate the driving force signal according to the final control quantity. Based on the normalized vibration data and the driving force signal, use the sliding window method to obtain the vibration data and the driving force signal of the previous moment; S420: Construct a time series set for each time point according to the driving force signal of the previous moment and the corresponding vibration data of the previous moment, accumulate the driving force signal and the vibration data in the time series set to obtain the accumulated driving force signal and the accumulated vibration data; S430: Construct a rectangular matrix based on the obtained cumulative driving force signal and cumulative vibration data. Based on the cumulative vibration data, construct a target vector. Use the transpose operation to transpose the rectangular matrix and the target vector to obtain a parameter vector. Then further decompose it using matrix decomposition technology to obtain the coefficients of the vibration data. The coefficients of the driving force signal And the static offset ; S440: Construct a difference equation based on the obtained cumulative driving force signal, cumulative vibration data, coefficients of the vibration data, coefficients of the driving force signal, and static offset, and then output the cumulative value at a future time. Use the cumulative subtraction generation method to convert the obtained cumulative value at the future time to obtain instantaneous data.

[0011] Preferably, in S410, the driving force signal is calculated according to the final control amount, specifically: ; In the formula, Represents the driving force signal, Represents the stiffness parameter, which is set through experiments, Is the final control amount; In S430, constructing a rectangular matrix based on the obtained cumulative driving force signal and cumulative vibration data is specifically: ; In the formula, Represents the rectangular matrix, Represents the total number of data points in the time series, Represents the cumulative vibration data, Represents the cumulative driving force signal; In S430, constructing a target vector based on the cumulative vibration data is specifically: ; In the formula, Represents the target vector, Represents the total length of the time series; In S430, using the transpose operation to transpose the rectangular matrix and the target vector to obtain a parameter vector, and then further decompose it using matrix decomposition technology to obtain the coefficients of the vibration data, the coefficients of the driving force signal, and the static offset, specifically: ; ; In the formula, Represents the transpose operation, Represents the parameter vector, Represents the coefficients of the vibration data, Represents the coefficient of the driving force signal, Represents the static offset; In S440, based on the obtained cumulative driving force signal, cumulative vibration data, coefficient of vibration data, coefficient of driving force signal, and static offset, a difference equation is constructed and the cumulative value at a future time is output, specifically: ; In the formula, Represents the cumulative value at a future time ; In S440, the cumulative value at a future time obtained is converted using the subtraction generation method to obtain instantaneous data, specifically: ; In the formula, Represents the instantaneous data, Represents the cumulative value at the current time t.

[0012] Preferably, in S500, the control error is calculated based on the instantaneous data, and the control adjustment based on the control error includes: S510: Subtract the instantaneous data from the normalized vibration data to obtain the control error; S520: Set an optimization threshold, compare the control error with the threshold. When the control error is greater than or equal to the threshold, the control quantity is re-optimized through the final optimization model. When the control error is less than the threshold, the control error is used as the basis for vibration isolation control.

[0013] Preferably, in S500, a database is used to store the adjustment results, including: Based on the obtained control error, use the database for storage. During the storage process, record the control error in time series, and associate and store the vibration data and time series set corresponding to the error. Classify and organize the historical error data through the database, and generate trend analysis data.

[0014] An intelligent vibration isolation control system based on vibration monitoring, including a data preprocessing module, a preliminary control quantity calculation module, a model optimization module, an integration and transformation module, and an adjustment and storage module; The data preprocessing module is used to collect vibration data, preprocess the vibration data, and obtain the preprocessed data; The preliminary control quantity calculation module is used to calculate the target signal and vibration deviation according to the preprocessed data, analyze the change rate of the vibration deviation, perform fuzzy conversion on the vibration deviation and the change rate and integrate the membership values, infer and merge the control quantity fuzzy sets through the Mamdani fuzzy inference method, divide discrete points and calculate the membership values, screen discrete points and calculate the preliminary control quantity; The model optimization module is used to construct an optimization model and define an objective function, randomly initialize membership values and generate an initial population, and use the locust optimization algorithm to iteratively optimize the population position until the objective function value converges, output the final optimization model, take the preliminary control quantity as the input of the final optimization model, and obtain the final control quantity; The integration and transformation module is used to calculate a driving force signal based on the final control quantity, further construct a difference equation based on the accumulation of the driving force signal and then output a predicted value, and perform a transformation according to the obtained predicted value to obtain instantaneous data; The adjustment and storage module is used to calculate a control error based on the instantaneous data, perform control adjustment based on the control error, and store the adjustment result using a database.

[0015] The above intelligent vibration isolation control method and system based on vibration monitoring activate rules through the Mamdani fuzzy inference method, generate a preliminary control quantity and further optimize it, realizing efficient adaptive control of a complex nonlinear vibration system. By combining the locust optimization algorithm to randomly initialize the membership value combination as a population and adjusting the parameter range of the initial population based on the preliminary control quantity, the optimization process converges quickly, and the optimization result of the objective function is directly used for the dynamic adjustment of the control quantity, significantly shortening the calculation time of the control quantity. And by predicting the future vibration trend through a difference equation, the dynamic response ability of the present invention is further improved. Description of the Drawings

[0016] Figure 1 is a flowchart of an intelligent vibration isolation control method based on vibration monitoring in an embodiment of the present invention; Figure 2 is a schematic diagram of the principle of an intelligent vibration isolation control system based on vibration monitoring in an embodiment of the present invention. Detailed Embodiments

[0017] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below with reference to the drawings.

[0018] In one embodiment, as Figure 1 shown, an intelligent vibration isolation control method based on vibration monitoring, the method includes the following steps: S100: Collect vibration data, preprocess the vibration data, and obtain the preprocessed data; S200: Calculate a target signal and a vibration deviation based on the preprocessed data, analyze the change rate of the vibration deviation, perform a fuzzy conversion on the vibration deviation and the change rate and integrate the membership values, infer and merge the control quantity fuzzy sets through the Mamdani fuzzy inference method, divide discrete points and calculate the membership values, and screen discrete points and calculate the preliminary control quantity; S300: Build an optimization model and define the objective function, randomly initialize the membership values and generate the initial population, use the locust optimization algorithm to iteratively optimize the population position until the objective function value converges, output the final optimization model, take the preliminary control quantity as the input of the final optimization model, and obtain the final control quantity; S400: Calculate the driving force signal based on the final control quantity, further construct a difference equation based on the accumulation of the driving force signal and then output the prediction value, and perform conversion according to the obtained prediction value to obtain the instantaneous data; S500: Calculate the control error based on the instantaneous data, perform control adjustment based on the control error, and use the database to store the adjustment result.

[0019] In one embodiment, S100 includes: S110: Collect vibration data by deploying an acceleration sensor; S120: Use wavelet decomposition technology to decompose and reconstruct the collected data to obtain the denoised data; S130: Based on the denoised data, perform normalization operation on the denoised data using the normalization method to obtain the normalized data.

[0020] Specifically, by collecting vibration data through an acceleration sensor and combining wavelet decomposition technology and the normalization method, an efficient process for vibration signal acquisition and preprocessing is realized. Using wavelet decomposition technology to decompose and reconstruct the signal can effectively remove noise and retain key features, improving the accuracy of the data. The normalization operation unifies the data scale, enhancing the stability and efficiency of subsequent fuzzy control and optimization algorithm calculations.

[0021] In one embodiment, S200 includes: S210: Based on the denoised data, calculate the mean value using the mean formula, define the obtained mean value as the target signal, subtract the normalized data from the target signal to obtain the vibration deviation; S220: Use time series analysis method to calculate the vibration deviation of the previous time, and subtract the vibration deviation of the previous time from the vibration deviation to obtain the vibration deviation change rate; S230: Define the vibration deviation and the vibration deviation change rate as input variables. Based on the obtained input variables, perform fuzzy conversion using the triangular membership function to obtain the converted membership values, and integrate the obtained membership values to obtain the fuzzy value set of the vibration deviation and the fuzzy value set of the vibration deviation change rate; S240: Define the fuzzy control rule table. Take the fuzzy value set of the vibration deviation and the fuzzy value set of the vibration deviation change rate as the inputs of the Mamdani fuzzy inference method, and use the Mamdani fuzzy inference method to combine the rule activation strength and the fuzzy set truncation formula to infer the fuzzy control rule table, obtaining the inferred fuzzy set of the control quantity. Based on the inferred fuzzy set of the control quantity, use the maximum membership degree method to merge the fuzzy sets of the control quantity of all rules to obtain the merged fuzzy set; S250: Divide the merged fuzzy set into M discrete points by the equal-interval discretization method, and calculate the membership value of each discrete point using the triangular membership function; S260: Set the selection threshold according to domain knowledge, compare the membership value corresponding to the discrete point with the threshold. When the membership value corresponding to the discrete point is greater than or equal to the threshold, retain the discrete point; otherwise, eliminate it. Based on the retained discrete points, calculate the preliminary control quantity using the discretization formula.

[0022] In one embodiment, in S230, based on the obtained input variables, use the triangular membership function for fuzzy conversion to obtain the converted membership value, specifically: The fuzzy formula for the vibration deviation is: ; In the formula, represents the membership value of the input variable vibration deviation belonging to the fuzzy value set of the vibration deviation, represents the vibration deviation, represents the maximum absolute value of the vibration deviation; The fuzzy value set of the vibration deviation is expressed as: ; In the formula, represents negative large, represents negative small, represents the center value, represents positive small, represents positive large; The fuzzy formula for the vibration deviation change rate is: ; In the formula, represents the membership value of the input variable vibration deviation change rate belonging to the fuzzy value set of the vibration deviation change rate, represents the vibration deviation change rate, represents the maximum absolute value of the vibration deviation change rate; The fuzzy value set of the vibration deviation change rate is expressed as: ; Wherein, represents negative speed, represents zero speed, represents positive speed; The rule activation formula in the Mamdani fuzzy inference method in S240 is: ; Wherein, represents the rule activation strength, represents taking the minimum value of the membership value; The truncation formula for the output fuzzy set of the rule is: ; Wherein, represents the membership function of the fuzzy set after being truncated by the activation strength , represents the output variable obtained through Mamdani fuzzy inference, represents the original membership function of the fuzzy set output by the fuzzy rule; Based on the inferred fuzzy set of the control quantity, the maximum membership degree method is used to merge the fuzzy sets of the control quantities of all rules to obtain a merged fuzzy set, specifically: ; Wherein, represents the merged fuzzy set, represents taking the maximum value of the membership value, represents the fuzzy set output by the nth rule; In S250, the preliminary control quantity is calculated using the discretization formula, specifically: ; Wherein, represents the preliminary control quantity at time t, represents the weight of the discrete point, represents the ith discrete point of the membership value, and S represents the total number of discrete points retained.

[0023] Specifically, by calculating the vibration deviation and its change rate, the deviation amplitude and change trend of the vibration system are reflected in real time, providing high-precision input data for subsequent fuzzy conversion. Moreover, the calculation of the vibration deviation is based on the difference between the normalized data and the target signal, and the change rate of the vibration deviation is obtained through the difference between the deviations at adjacent time points. This can ensure that the present invention is sensitive to dynamic vibration signals and adapts to complex vibration environments. The introduction of fuzzy conversion greatly improves the processing ability of the present invention for uncertainty and complexity. Using triangular membership functions, the vibration deviation and its change rate are converted into membership values, effectively simplifying the modeling process and laying the foundation for the inference of the fuzzy control rule table. The Mamdani fuzzy inference method combines the rule activation strength and the fuzzy set truncation formula to infer and adjust the fuzzy set, enabling the control quantity to be dynamically generated according to the real-time change of the vibration deviation. Moreover, by combining the fuzzy sets through the maximum membership degree method, a clear control quantity is quickly generated, improving the dynamic response speed and real-time performance of the present invention. Secondly, by optimizing the fuzzy set through equal-interval discretization and threshold screening, the computational complexity is significantly reduced, and the key discrete points with the greatest impact on the control effect are retained. This not only improves the real-time performance of the system but also ensures the accuracy and stability of the calculation results. By combining the calculation formula of the preliminary control quantity, the present invention realizes the tight coupling from the vibration signal input to the preliminary control quantity output, laying a solid foundation for subsequent optimization and execution.

[0024] In one embodiment, S300 includes: S310: Based on the obtained preliminary control quantity, use the recursive estimation method to calculate the preliminary control quantity of the previous state, subtract the preliminary control quantity of the previous state from the preliminary control quantity to obtain the change rate of the control quantity; S320: Randomly initialize the membership values of all retained discrete points, generate multiple groups of initial membership value combinations as the initial population, and perform offset adjustment on the total parameter value of the initial population according to the preliminary control quantity; S330: Construct an optimization model, and define the objective function of the optimization model based on the change rate of the control quantity: ; In the formula, represents the objective function value, represents the change rate of the control quantity at time t, represents the vibration deviation at time t, represents the weight factor of the control quantity change, represents the total number of time steps; S340: Use the locust optimization algorithm to calculate the interaction forces of the individuals in the population, calculate the objective function values corresponding to the individuals after updating the positions of the individuals in the population. During the iteration process, continuously update the population positions, and stop the iteration when the objective function value converges, and output the final optimization model; S350: Input the preliminary control quantity into the final optimization model and output the final control quantity.

[0025] Specifically, by introducing a recursive estimation method and a calculation mechanism for the change rate of the control quantity, the present invention can capture the dynamic change trend of the control quantity in real time, ensure a quick response in a complex vibration environment, and by quantifying the difference between the current control quantity and the previous state, can dynamically adjust the control strategy to achieve more accurate vibration suppression. By combining the vibration deviation and the change rate of the control quantity through an objective function and dynamically balancing the importance of the two through a weight factor, the optimization result not only has a high-precision vibration control ability but also ensures the smoothness of the control quantity. Secondly, the locust optimization algorithm is used to optimize the control quantity. By simulating the interaction forces of the population to achieve global search, it can effectively avoid falling into local optima and meet the requirements of complex nonlinear vibration systems. Through random initialization of the population, dynamic adjustment of the parameter range, and fast iterative optimization based on the objective function, the present invention can output the final control quantity in a short time to meet the real-time control requirements in a high-frequency vibration environment.

[0026] In one embodiment, S400 includes: S410: Calculate the driving force signal according to the final control quantity. Based on the normalized vibration data and the driving force signal, use the sliding window method to obtain the vibration data and the driving force signal at the previous moment. S420: Construct a time series set for each time point according to the driving force signal and the corresponding vibration data at the previous moment, and accumulate the driving force signal and the vibration data in the time series set to obtain the accumulated driving force signal and the accumulated vibration data. S430: Construct a rectangular matrix according to the obtained accumulated driving force signal and accumulated vibration data, construct a target vector based on the accumulated vibration data, and perform a transpose operation on the rectangular matrix and the target vector using the transpose operation to obtain a parameter vector and further decompose it using matrix decomposition technology to obtain the coefficient of the vibration data , the coefficient of the driving force signal and the static offset ; S440: Construct a difference equation according to the obtained accumulated driving force signal, accumulated vibration data, coefficient of the vibration data, coefficient of the driving force signal, and static offset, and output the accumulated value at a future moment. Use the cumulative subtraction generation method to convert the obtained accumulated value at the future moment to obtain instantaneous data.

[0027] In one embodiment, when calculating the driving force signal according to the final control quantity in S410, specifically: ; In the formula, represents the driving force signal, represents the stiffness parameter, which is set by experiment, is the final control variable; In S430, according to the obtained cumulative driving force signal and cumulative vibration data, constructing a rectangular matrix is specifically as follows: ; In the formula, represents the rectangular matrix, represents the total number of data points in the time series, represents the cumulative vibration data, represents the cumulative driving force signal; In S430, based on the cumulative vibration data, constructing a target vector is specifically as follows: ; In the formula, represents the target vector, represents the total length of the time series; In S430, using the transpose operation to transpose the rectangular matrix and the target vector, after obtaining the parameter vector, further using the matrix decomposition technique for decomposition to obtain the coefficient of the vibration data, the coefficient of the driving force signal, and the static offset, specifically as follows: ; ; In the formula, represents the transpose operation, represents the parameter vector, represents the coefficient of the vibration data, represents the coefficient of the driving force signal, represents the static offset; In S440, according to the obtained cumulative driving force signal, cumulative vibration data, coefficient of the vibration data, coefficient of the driving force signal, and static offset, constructing a difference equation and then outputting the cumulative value at the future moment, specifically as follows: ; In the formula, represents the future moment of the cumulative value; In S440, using the cumulative subtraction generation method to convert the obtained cumulative value at the future moment to obtain the instantaneous data, specifically as follows: ; In the formula, represents the instantaneous data, represents the cumulative value at the current moment t.

[0028] Specifically, by adopting an accurate calculation method for the driving force signal, combining the final control quantity with the stiffness parameter, a driving force signal is dynamically generated. By using the sliding window method to extract the vibration data and driving force signal at the previous moment, it is ensured that the input data has high timeliness and accuracy, providing a reliable basis for the construction of the subsequent time series set. The cumulative driving force signal and cumulative vibration data are calculated respectively using the cumulative formula to extract the global features of the time series, analyze the long-term change trend of the data, and the rectangular matrix and target vector constructed based on the cumulative signal can comprehensively express the multi-dimensional correlation between the vibration data and the driving force signal, providing an accurate mathematical model for the solution of the parameter vector. Secondly, through the transpose operation of the rectangular matrix and the target vector, the present invention calculates and decomposes the parameter vector using linear algebra methods to obtain the vibration data coefficient, the driving force signal coefficient, and the static offset. These parameters serve as core factors when constructing the difference equation, and the dynamic prediction ability of the difference equation further enhances the control accuracy of the system and the response ability to future vibration trends. The instantaneous data is restored from the cumulative value at the future moment through the cumulative subtraction generation method, providing an efficient and accurate basis for real-time calculation. The instantaneous data directly reflects the vibration state at the current moment, providing an important reference for the error correction and optimization adjustment of vibration isolation control. Combining dynamic prediction and real-time adjustment, the present invention realizes efficient and precise vibration isolation control of the vibration system.

[0029] In one embodiment, calculating the control error based on the instantaneous data and performing control adjustment based on the control error includes: S510: Subtract the instantaneous data from the normalized vibration data to obtain the control error; S520: Set an optimization threshold according to the accuracy requirement and personal experience, compare the control error with the threshold. When the control error is greater than or equal to the threshold, re-optimize the control quantity through the final optimization model. When the control error is less than the threshold, use the control error as the basis for vibration isolation control.

[0030] Specifically, through the calculation of the instantaneous data, the vibration state of the system can be quickly captured, and an accurate control error is generated after comparison with the normalized vibration data. By setting the optimization threshold, the adaptive adjustment of the control strategy is realized, avoiding the waste of resources caused by frequent optimization, and at the same time ensuring the fast correction ability in the case of large errors.

[0031] In one embodiment, the database is used to store the adjustment results in S500, including: Based on the obtained control error, use the database for storage. During the storage process, record the control error in time series, and associate and store the vibration data and time series set corresponding to the error. Classify and organize the historical error data through the database and generate trend analysis data.

[0032] Specifically, through time - series recording and associated storage, it provides accurate data support for real - time optimization, and predicts future vibration behavior through trend - analysis data, dynamically adjusting control strategies to adapt to complex non - linear vibration environments.

[0033] This embodiment also provides an intelligent vibration isolation control system based on vibration monitoring, as Figure 2 shown, including a data pre - processing module, a preliminary control quantity calculation module, a model optimization module, an integration and transformation module, and an adjustment and storage module; The data pre - processing module is used to collect vibration data, pre - process the vibration data, and obtain the pre - processed data; The preliminary control quantity calculation module is used to calculate the target signal and vibration deviation according to the pre - processed data, analyze the change rate of the vibration deviation, perform fuzzy conversion on the vibration deviation and the change rate and integrate membership values, infer and merge the control quantity fuzzy sets through the Mamdani fuzzy inference method, divide discrete points and calculate membership values, screen discrete points and calculate the preliminary control quantity; The model optimization module is used to construct an optimization model and define an objective function, randomly initialize membership values and generate an initial population, use the locust optimization algorithm to iteratively optimize the population position until the objective function value converges, output the final optimization model, take the preliminary control quantity as the input of the final optimization model, and obtain the final control quantity; The integration and transformation module is used to calculate the driving force signal based on the final control quantity, further construct a difference equation based on the accumulation of the driving force signal and then output a prediction value, and perform conversion according to the obtained prediction value to obtain instantaneous data; The adjustment and storage module is used to calculate the control error based on the instantaneous data, perform control adjustment based on the control error, and store the adjustment result using a database.

[0034] For the specific limitations of an intelligent vibration isolation control system based on vibration monitoring, reference can be made to the limitations of an intelligent vibration isolation control method based on vibration monitoring in the above text, which will not be elaborated here. Each module in the above - mentioned intelligent vibration isolation control system based on vibration monitoring can be implemented in whole or in part by software, hardware, and their combinations. The above - mentioned modules can be embedded in the processor of a computer device in hardware form or be independent of it, or can be stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to the above - mentioned modules.

[0035] This embodiment also provides a computer device applicable to the case of an intelligent vibration isolation control method based on vibration monitoring, including: a memory and a processor; the memory is used to store computer - executable instructions, and the processor is used to execute the computer - executable instructions to implement the intelligent vibration isolation control method based on vibration monitoring proposed in the above - mentioned embodiment.

[0036] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or may also be a button, a trackball, or a touchpad provided on the outer shell of the computer device, or may also be an external keyboard, touchpad, or mouse, etc.

[0037] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the intelligent vibration isolation control method based on vibration monitoring proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), Erasable Programmable Read-Only Memory (EPROM for short), Programmable Read-Only Memory (PROM for short), Read-Only Memory (ROM for short), magnetic memory, flash memory, a magnetic disk, or an optical disc.

[0038] The above has introduced in detail a kind of intelligent vibration isolation control method and system based on vibration monitoring provided by the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the core idea of the present invention. It should be noted that for those of ordinary skill in the art in the technical field, without departing from the principle of the present invention, several improvements and modifications can still be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

Claims

1. An intelligent vibration isolation control method based on vibration monitoring, characterized in that, The method includes the following steps: S100: Collect vibration data, preprocess the vibration data to obtain preprocessed data; S200: Calculate the target signal and vibration deviation based on the preprocessed data, analyze the change rate of the vibration deviation, perform fuzzy conversion on the vibration deviation and the change rate and integrate the membership values, infer and merge the fuzzy set of control quantities through the Mamdani fuzzy inference method, divide discrete points and calculate the membership values, screen discrete points and calculate the preliminary control quantity; S300: Construct an optimization model and define the objective function, randomly initialize the membership values and generate the initial population, use the grasshopper optimization algorithm to iteratively optimize the population position until the objective function value converges, output the final optimization model, use the preliminary control quantity as the input of the final optimization model to obtain the final control quantity; S400: Calculate the driving force signal based on the final control quantity, further construct a difference equation based on the accumulation of the driving force signal and output the predicted value, and perform conversion according to the obtained predicted value to obtain instantaneous data; S500: Calculate the control error based on the instantaneous data, perform control adjustment based on the control error, and store the adjustment result using the database.

2. The method according to claim 1, wherein S100 includes: S110: Collect vibration data by deploying an acceleration sensor; S120: Use the wavelet decomposition technique to decompose and reconstruct the collected data to obtain denoised data; S130: Based on the denoised data, perform normalization operation on the denoised data using the normalization method to obtain normalized data.

3. The method according to claim 2, wherein S200 includes: S210: Based on the denoised data, calculate the mean using the mean formula, define the obtained mean as the target signal, subtract the normalized data from the target signal to obtain the vibration deviation; S220: Use the time series analysis method to calculate the vibration deviation at the previous time, and subtract the vibration deviation at the previous time from the vibration deviation to obtain the change rate of the vibration deviation; S230: Define the vibration deviation and the change rate of the vibration deviation as input variables, based on the obtained input variables, perform fuzzy conversion using the triangular membership function to obtain the converted membership values, and integrate the obtained membership values to obtain the fuzzy value set of the vibration deviation and the fuzzy value set of the change rate of the vibration deviation; S240: Define the fuzzy control rule table, use the fuzzy value set of the vibration deviation and the fuzzy value set of the change rate of the vibration deviation as the input of the Mamdani fuzzy inference method, and use the Mamdani fuzzy inference method to infer the fuzzy control rule table in combination with the rule activation intensity and the fuzzy set truncation formula to obtain the inferred fuzzy set of control quantities, based on the inferred fuzzy set of control quantities, use the maximum membership degree method to merge the fuzzy sets of control quantities of all rules to obtain the merged fuzzy set; S250: Divide the merged fuzzy set into M discrete points by the equal interval discretization method, and calculate the membership value of each discrete point using the triangular membership function; S260: Set the selection threshold, compare the membership value corresponding to the discrete point with the threshold. When the membership value corresponding to the discrete point is greater than or equal to the threshold, retain the discrete point; otherwise, eliminate it. Based on the retained discrete points, calculate the preliminary control quantity using the discretization formula.

4. The method according to claim 3, wherein In S230, based on the obtained input variables, perform fuzzy conversion using the triangular membership function to obtain the converted membership values, specifically: The fuzzy formula for vibration deviation is: ； In the formula, represents the vibration deviation of the input variable which belongs to the membership value of the fuzzy value set of the vibration deviation, represents the vibration deviation, represents the maximum absolute value of the vibration deviation; The fuzzy value set of vibration deviation is expressed as: ； In the formula, represents large negative, represents small negative, represents the central value, represents small positive, represents large positive; The fuzzy formula for the rate of change of vibration deviation is: ； In the formula, represents the rate of change of the vibration deviation of the input variable which is the membership value belonging to the fuzzy value set of the rate of change of the vibration deviation, represents the rate of change of the vibration deviation, represents the maximum absolute value of the rate of change of the vibration deviation; The fuzzy value set of the rate of change of vibration deviation is expressed as: ； In the formula, represents negative speed, represents zero speed, represents positive speed; In S240, the rule activation formula in the Mamdani fuzzy inference method is: ； wherein, represents the rule activation strength, represents taking the minimum value of the membership value; The truncation formula for the output fuzzy set of rules is: ； In the formula, represents the membership function of the fuzzy set after truncation by the activation intensity , represents the output variable obtained through Mamdani fuzzy inference, represents the original membership function of the fuzzy set output by the fuzzy rule; Based on the inferred control quantity fuzzy set, use the maximum membership degree method to merge the control quantity fuzzy sets of all rules to obtain the merged fuzzy set, specifically: ； In the formula, represents the combined fuzzy set, represents taking the maximum membership value, represents the fuzzy set output by the nth rule; In S250, the calculation of the preliminary control quantity using the discretization formula is specifically: ； In the formula, represents the preliminary control quantity at time t, represents the weight of the discrete point, represents the i-th discrete point 's membership value, and S represents the total number of reserved discrete points.

5. The method according to claim 4, characterized in that S300 includes: S310: Based on the obtained preliminary control quantity, use the recursive estimation method to calculate the preliminary control quantity of the previous state, subtract the preliminary control quantity of the previous state from the preliminary control quantity to obtain the rate of change of the control quantity; S320: Randomly initialize the membership values of all retained discrete points, generate multiple groups of initial membership value combinations as the initial population, and perform offset adjustment on the total parameter value of the initial population according to the preliminary control quantity; S330: Construct an optimization model, and define the objective function of the optimization model based on the rate of change of the control quantity: ； In the formula, represents the objective function value, represents the change rate of the control quantity at time t, represents the vibration deviation at time t, represents the weight factor of the change of the control quantity, represents the total number of time steps; S340: Use the locust optimization algorithm to calculate the interaction forces of individuals in the population, calculate the objective function value corresponding to the individual after updating the positions of individuals in the population. During the iteration process, continuously update the population position, and stop the iteration when the objective function value converges, and output the final optimization model; S350: Input the preliminary control quantity into the final optimization model and output the final control quantity.

6. The method according to claim 5, wherein S400 includes: S410: Calculate the driving force signal according to the final control quantity. Based on the normalized vibration data and the driving force signal, use the sliding window method to obtain the vibration data and the driving force signal of the previous moment; S420: Construct a time series set for each time point according to the driving force signal of the previous moment and the corresponding vibration data of the previous moment, and accumulate the driving force signal and the vibration data in the time series set to obtain the accumulated driving force signal and the accumulated vibration data; S430: Construct a rectangular matrix based on the obtained cumulative driving force signal and cumulative vibration data, construct a target vector based on the cumulative vibration data, and perform a transpose operation on the rectangular matrix and the target vector using the transpose operation to obtain a parameter vector Then further decompose using matrix decomposition technology to obtain the coefficients of the vibration data , the coefficients of the driving force signal and the static offset ; S440: According to the obtained accumulated driving force signal, accumulated vibration data, the coefficient of vibration data, the coefficient of driving force signal, and the static offset, construct a difference equation and output the accumulated value of the future moment, and use the cumulative subtraction generation method to convert the obtained accumulated value of the future moment to obtain the instantaneous data.

7. The method according to claim 6, wherein In S410, the calculation of the driving force signal according to the final control quantity is specifically: ； In the formula, represents the driving force signal, represents the stiffness parameter, which is set through experiments, is the final control quantity; In S430, the construction of the rectangular matrix according to the obtained accumulated driving force signal and accumulated vibration data is specifically: ； In the formula, represents a rectangular matrix, represents the total number of data points in the time series, represents the accumulated vibration data, represents the accumulated driving force signal; In S430, the construction of the target vector based on the accumulated vibration data is specifically: ； In the formula, represents the target vector, represents the total length of the time series; In S430, a transpose operation is performed on the rectangular matrix and the target vector using the transpose operation. After obtaining the parameter vector, matrix decomposition technology is further used for decomposition to obtain the coefficients of the vibration data, the coefficients of the driving force signal, and the static offset. Specifically: ； ； In the formula, represents the transpose operation, represents the parameter vector, represents the coefficient of the vibration data, represents the coefficient of the driving force signal, represents the static offset; In S440, based on the obtained cumulative driving force signal, cumulative vibration data, coefficients of the vibration data, coefficients of the driving force signal, and static offset, a difference equation is constructed and the cumulative value at a future time is output. Specifically: ； wherein, represents the cumulative value at a future time . In S440, the cumulative value at the obtained future time is converted using the subtraction generation method to obtain the instantaneous data. Specifically: ； In the formula, represents instantaneous data, represents the cumulative value at the current moment t.

8. The method according to claim 7, characterized in that, In S500, the control error is calculated based on the instantaneous data, and the control adjustment based on the control error includes: S510: Subtract the instantaneous data from the normalized vibration data to obtain the control error; S520: Set an optimization threshold, compare the control error with the threshold. When the control error is greater than or equal to the threshold, the control quantity is re-optimized through the final optimization model. When the control error is less than the threshold, the control error is used as the basis for vibration isolation control.

9. The method according to claim 8, wherein In S500, the database is used to store the adjustment results, including: Based on the obtained control error, it is stored using the database. During the storage process, the control error is recorded in time series, and the vibration data and time series set corresponding to the error are associated and stored. The historical error data is classified and sorted through the database, and trend analysis data is generated.

10. An intelligent vibration isolation control system based on vibration monitoring, characterized in that, Including a data preprocessing module, a preliminary control quantity calculation module, a model optimization module, an integration and conversion module, and an adjustment and storage module; The data preprocessing module is used to collect vibration data, preprocess the vibration data, and obtain the preprocessed data; The preliminary control quantity calculation module is used to calculate the target signal and vibration deviation based on the preprocessed data, analyze the change rate of the vibration deviation, perform fuzzy conversion on the vibration deviation and the change rate and integrate the membership values, infer and merge the control quantity fuzzy sets through the Mamdani fuzzy inference method, divide the discrete points and calculate the membership values, screen the discrete points and calculate the preliminary control quantity; The model optimization module is used to construct an optimization model and define the objective function, randomly initialize the membership values and generate the initial population, use the locust optimization algorithm to iteratively optimize the population position until the objective function value converges, output the final optimization model, and use the preliminary control quantity as the input of the final optimization model to obtain the final control quantity; The integration and conversion module is used to calculate the driving force signal based on the final control quantity, further construct a difference equation based on the accumulation of the driving force signal and output the predicted value, and perform conversion based on the obtained predicted value to obtain the instantaneous data; The adjustment and storage module is used to calculate the control error based on the instantaneous data, perform control adjustment based on the control error, and use the database to store the adjustment results.

Images