Automatic vibration isolation method and apparatus

Abstract

The present disclosure provides an automatic vibration isolation method and device, which can be applied to the technical field of vibration isolation. The method comprises: collecting a vibration signal by using a sensor, wherein the vibration signal is obtained by vibration interference of an external vibration interference source on a controlled platform; comparing the vibration signal and a pre-sampling signal to obtain a comparison result; in the case that the comparison result represents that the vibration signal and the pre-sampling signal are similar, determining a control parameter corresponding to the pre-sampling signal, wherein the control parameter is obtained by optimizing an initial control parameter corresponding to the pre-sampling signal by using an optimization model; generating a control signal according to the control parameter and a real-time vibration signal; and applying an isolation force to the controlled platform by using an actuator in response to the control signal, wherein the isolation force is used to suppress the vibration interference generated by the external vibration interference source on the controlled platform.

Description

Technical Field

[0001] This disclosure relates to the field of vibration isolation technology, and more specifically to an automatic vibration isolation method and apparatus. Background Technology

[0002] Active vibration isolation mainly consists of four parts: sensors, controllers, actuators, and controlled platforms. The vibration signals from the sensors are processed by the controller and then output to the actuators. The actuators then output a corresponding force to the controlled platforms to counteract the original vibrations on the platforms.

[0003] In related technologies, it is usually necessary to obtain the response function associated with the controlled platform in order to design a corresponding vibration isolation control algorithm. However, the above methods are overly simplified due to the complexity of the theoretical model compared to the actual response function associated with the controlled platform. As a result, the output of the theoretical model deviates from reality, leading to a difference between the designed vibration isolation control algorithm and the actual vibration isolation effect. Furthermore, when the number of parameters in the theoretical model is large, excessive manpower is required for parameter integration and processing. Moreover, the vibration isolation effect obtained based on the theoretical model is difficult to achieve optimal results, limiting the improvement of vibration isolation performance. Summary of the Invention

[0004] In view of the above problems, this disclosure provides an automatic vibration isolation method and device.

[0005] According to a first aspect of this disclosure, an automatic vibration isolation method is provided, comprising: acquiring a vibration signal using a sensor, wherein the vibration signal is obtained by an external vibration interference source vibrating a controlled platform; comparing the vibration signal and a pre-sampled signal to obtain a comparison result; determining a control parameter corresponding to a preset signal if the comparison result indicates that the vibration signal and the pre-sampled signal are similar, wherein the control parameter is obtained by optimizing an initial control parameter corresponding to the pre-sampled signal using an optimization model; generating a control signal based on the control parameter and the real-time vibration signal; and applying a vibration isolation force to the controlled platform using an actuator in response to the control signal, wherein the vibration isolation force is used to suppress vibration interference generated by an external vibration interference source on the controlled platform.

[0006] According to embodiments of this disclosure, the presampled control parameters are obtained by optimizing the initial control parameters using an optimization model, which is performed based on the following operations: a Gaussian distribution is constructed based on the initial control parameters, variable control parameters, and initial control effect, wherein the initial control effect is associated with the initial control parameters and the variable control parameters are associated with the initial control parameters; based on the Gaussian distribution, the variable control parameters are predicted to obtain the predicted control effect; and if the predicted control effect satisfies a first preset optimization condition, the variable control parameters are determined as the presampled control parameters.

[0007] According to embodiments of this disclosure, constructing a Gaussian distribution based on initial control parameters, variable control parameters, and initial control effect includes: acquiring an initial residual vibration signal of the platform corresponding to the initial control parameters, wherein the initial residual vibration signal is obtained by applying an initial vibration isolation force to the controlled platform based on the initial control parameters, and the initial vibration isolation force is generated based on the initial control parameters; determining the initial control effect corresponding to the initial control parameters based on the Allen deviation of the initial residual vibration signal; generating a kernel function associated with the Gaussian distribution based on the initial control parameters and variable control parameters; and constructing a Gaussian distribution based on the kernel function, variable control parameters, initial control parameters, and initial control effect.

[0008] According to embodiments of this disclosure, generating a kernel function associated with a Gaussian distribution based on initial control parameters and variable control parameters includes: constructing a correlation matrix between the variable control parameters and the initial control parameters to obtain a first kernel function; constructing an autocorrelation matrix of the variable control parameters to obtain a second kernel function, wherein the first kernel function and the second kernel function have the same hyperparameters; optimizing the hyperparameters to obtain target hyperparameters; updating the first kernel function and the second kernel function based on the target hyperparameters to obtain updated first kernel function and second kernel function; and determining the kernel function associated with the Gaussian distribution based on the updated first kernel function and second kernel function.

[0009] According to embodiments of this disclosure, optimizing hyperparameters to obtain target hyperparameters includes: constructing an autocorrelation matrix of initial control parameters to obtain a third kernel function; constructing a likelihood function based on the hyperparameters, the third kernel function, and the initial control effect; optimizing the hyperparameters to obtain optimized hyperparameters; calculating the likelihood function value based on the optimized hyperparameters; and determining the optimized hyperparameters as target hyperparameters if the likelihood function value satisfies a second preset optimization condition.

[0010] According to embodiments of this disclosure, when the predictive control effect meets a first preset optimization condition, the variable control parameter is determined as a presampled control parameter, including: analyzing the predictive control effect using an expected boost function to obtain an analysis result; and when the analysis result indicates that the predictive control effect meets a third preset optimization condition, the variable control parameter is determined as a presampled control parameter.

[0011] According to embodiments of this disclosure, generating a control signal based on pre-sampled control parameters and vibration signals includes: analyzing the pre-sampled control parameters and vibration signals using a controller to determine a control strategy; and generating a control signal suitable for the actuator based on the control strategy and vibration signals.

[0012] According to embodiments of this disclosure, the above method further includes: using a target identification model to perform parameter identification processing on the vibration signal to obtain a target vibration signal, wherein the parameters of the target identification model are obtained by optimizing the initial parameters of the target identification model using an optimization model; wherein comparing the vibration signal and the presampled signal to obtain a comparison result includes: comparing the target vibration signal and the presampled signal to obtain a comparison result.

[0013] According to embodiments of this disclosure, the above method further includes:

[0014] The residual vibration signal of the platform is collected using sensors. This residual vibration signal is obtained by applying vibration isolation force to the controlled platform. The residual vibration signal is analyzed to obtain the platform analysis results. If the platform analysis results indicate abnormal vibration isolation or the comparison results indicate that the vibration signal and the pre-sampled signal are dissimilar, the pre-sampled control parameters are optimized using an optimization model to obtain the target control parameters. Based on the target control parameters and the vibration signal, a target control signal is generated. The target vibration isolation force is applied to the controlled platform using an actuator, where the actuator responds to the target control signal and generates the target vibration isolation force.

[0015] A second aspect of this disclosure provides an automatic vibration isolation device, comprising: a controlled platform; a sensor for acquiring vibration signals, wherein the vibration signals are obtained by an external vibration interference source vibrating the controlled platform; a controller for comparing the vibration signals and a pre-sampled signal to obtain a comparison result; determining control parameters corresponding to the pre-sampled signal when the comparison result indicates that the vibration signals and the pre-sampled signal are similar, wherein the control parameters are obtained by optimizing initial control parameters corresponding to the pre-sampled signal using an optimization model; generating a control signal based on the pre-sampled control parameters and the vibration signal; and an actuator for responding to the control signal to generate... A vibration isolation force is applied to the controlled platform to suppress vibration interference caused by external vibration sources. The optimization of the initial control parameters to obtain pre-sampled control parameters using an optimization model is performed as follows: a Gaussian distribution is constructed based on the initial control parameters, variable control parameters, and initial control effect. The initial control effect is correlated with the initial control parameters, and the variable control parameters are correlated with the initial control parameters. Based on the Gaussian distribution, the variable control parameters are predicted to obtain the predicted control effect. If the predicted control effect meets the first preset optimization condition, the variable control parameters are determined as the pre-sampled control parameters.

[0016] According to embodiments of this disclosure, vibration signals are acquired using sensors; the vibration signals and pre-sampled signals are compared to obtain a comparison result; if the comparison result indicates that the vibration signals and pre-sampled signals are similar, control parameters corresponding to the pre-sampled signals are determined, wherein the control parameters are obtained by optimizing the initial control parameters corresponding to the pre-sampled signals using an optimization model; a control signal is generated based on the control parameters; and an actuator is used to apply vibration isolation force to the controlled platform in response to the control signal. Since the initial control parameters corresponding to the pre-sampled signals are optimized using an optimization model, there is no need to consider the difference in complexity between the theoretical model and the actual response function associated with the controlled platform, enabling automatic acquisition of the mapping relationship between control parameters and optimization effects based on training data. Furthermore, in practical use, the optimized preset control parameters can be directly invoked by comparing the vibration signals and pre-sampled signals, avoiding the resource waste caused by parameter debugging and achieving improved efficiency in automatic vibration isolation. Attached Figure Description

[0017] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0018] Figure 1 A flowchart illustrating an automatic vibration isolation method according to an embodiment of the present disclosure is shown schematically;

[0019] Figure 2 An optimization diagram based on a back-end sensor is illustrated schematically according to an embodiment of the present disclosure;

[0020] Figure 3 An optimization diagram based on a back-end sensor and a front-end sensor according to an embodiment of the present disclosure is illustrated schematically;

[0021] Figure 4 The diagram illustrates an optimized target identification model according to an embodiment of the present disclosure.

[0022] Figure 5 A schematic diagram of the structure of an automatic vibration isolation device according to an embodiment of the present disclosure is shown.

[0023] Figure 6 A schematic diagram of an automatic vibration isolation device according to an embodiment of the present disclosure is shown. Detailed Implementation

[0024] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0025] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0026] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0027] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0028] Embodiments of this disclosure provide an automatic vibration isolation method, comprising: acquiring vibration signals using sensors, wherein the vibration signals are obtained by external vibration interference sources vibrating a controlled platform; comparing the vibration signals and pre-sampled signals to obtain a comparison result; determining control parameters corresponding to the pre-sampled signals when the comparison result indicates that the vibration signals and pre-sampled signals are similar, wherein the control parameters are obtained by optimizing initial control parameters corresponding to the pre-sampled signals using an optimization model; generating a control signal based on the control parameters; and applying a vibration isolation force to the controlled platform using an actuator in response to the control signal, wherein the vibration isolation force is used to suppress vibration interference generated by external vibration interference sources on the controlled platform.

[0029] Figure 1 A flowchart illustrating an automatic vibration isolation method according to an embodiment of the present disclosure is shown schematically.

[0030] like Figure 1 As shown, the automatic vibration isolation method of this embodiment includes operations S110 to S150.

[0031] When operating S110, vibration signals are collected using sensors. These vibration signals are obtained by external vibration interference sources causing vibration interference to the controlled platform.

[0032] According to embodiments of this disclosure, the sensor can be a vibration sensor, such as a displacement gauge, velocity gauge, accelerometer, or other vibration measurement device, used to collect vibration signals generated by external vibration interference sources interfering with the controlled platform.

[0033] According to embodiments of this disclosure, the vibration interference from external vibration sources on the controlled platform can be caused by the natural environment or by human intervention on the controlled platform.

[0034] According to embodiments of this disclosure, the controlled platform can be a platform of any material and size, capable of being affected by external vibration interference sources and also capable of receiving forces applied by actuators.

[0035] During operation S120, the vibration signal and the pre-sampled signal are compared to obtain the comparison result.

[0036] According to embodiments of this disclosure, the presampled signal may be at least one training vibration signal selected and recorded during the training process.

[0037] According to embodiments of this disclosure, comparing the vibration signal and the presampled signal can be used to determine whether the currently acquired vibration signal has the same or similar spectral characteristics as the recorded presampled signal.

[0038] In operation S130, if the comparison results show that the vibration signal and the presampled signal are similar, the control parameters corresponding to the presampled signal are determined. The control parameters are obtained by optimizing the initial control parameters corresponding to the presampled signal using an optimization model.

[0039] According to embodiments of this disclosure, when the comparison results indicate that the vibration signal and the pre-sampled signal are similar, i.e., the currently acquired vibration signal can utilize the control parameters corresponding to the pre-sampled signal obtained during training. According to embodiments of this disclosure, the optimization model can be a Gaussian process regression model, used to leverage historical control parameters obtained during training based on a Bayesian optimization algorithm, achieving better optimization results with fewer optimization iterations.

[0040] In operation S140, a control signal is generated based on the pre-sampled control parameters.

[0041] According to embodiments of this disclosure, the pre-sampled control parameters can be obtained by training an optimization model, enabling the actuator to apply vibration isolation force to the controlled platform based on the control parameters, thereby suppressing vibration interference from external vibration sources.

[0042] According to embodiments of this disclosure, the initial control parameters may be control parameters randomly generated during training based on presampled signals.

[0043] According to embodiments of this disclosure, the pre-sampled control signal can be obtained based on pre-sampled control parameters, enabling the actuator to receive and acquire an output strategy for adjusting voltage or current corresponding to the pre-sampled control parameters.

[0044] In operation S150, the actuator applies a vibration isolation force to the controlled platform in response to the pre-sampled control signal. The vibration isolation force is used to suppress vibration interference generated by external vibration sources on the controlled platform.

[0045] According to embodiments of this disclosure, the actuator may be a voice coil motor, Lorentz motor, piezoelectric ceramic, hydraulic system, shape memory alloy, or other device that outputs a force or displacement controlled by voltage or current.

[0046] According to embodiments of this disclosure, the actuator applies a vibration isolation force to the controlled platform to suppress vibration interference from external vibration sources.

[0047] According to embodiments of this disclosure, vibration signals are acquired using sensors; the vibration signals and pre-sampled signals are compared to obtain a comparison result; if the comparison result indicates that the vibration signals and pre-sampled signals are similar, control parameters corresponding to the pre-sampled signals are determined, wherein the pre-sampled control parameters are obtained by optimizing the initial control parameters corresponding to the pre-sampled signals using an optimization model; a control signal is generated based on the pre-sampled control parameters; and an actuator is used to apply vibration isolation force to the controlled platform in response to the control signal. Since the initial control parameters corresponding to the pre-sampled signals are optimized using an optimization model, there is no need to consider the difference in complexity between the theoretical model and the actual response function associated with the controlled platform, enabling automatic acquisition of the mapping relationship between control parameters and optimization effects based on training data. Furthermore, in practical use, the optimized control parameters can be directly retrieved by comparing the vibration signals and pre-sampled signals, avoiding the waste of resources caused by parameter tuning and achieving improved efficiency in automatic vibration isolation.

[0048] According to embodiments of this disclosure, the presampled control parameters are obtained by optimizing the initial control parameters using an optimization model, which is performed based on the following operations: A Gaussian distribution is constructed based on the initial control parameters, variable control parameters, and initial control effect, wherein the initial control effect is correlated with the initial control parameters, and the variable control parameters are correlated with the initial control parameters; based on the Gaussian distribution, the variable control parameters are predicted to obtain the predicted control effect; if the predicted control effect satisfies a first preset optimization condition, the variable control parameters are determined as the presampled control parameters.

[0049] According to embodiments of this disclosure, the initial control parameters may be preset control parameters used to adjust the actuator.

[0050] According to embodiments of this disclosure, the variable control parameter can be at least one control parameter obtained by adjusting the initial control parameter.

[0051] According to embodiments of this disclosure, the initial control effect is the result obtained based on the vibration feedback of the controlled platform after adjusting the actuator with initial control parameters.

[0052] According to embodiments of this disclosure, a Gaussian distribution is constructed based on initial control parameters, variable control parameters, and initial control effects to obtain the distribution relationship between control parameters and control effects.

[0053] According to embodiments of this disclosure, the control effect of variable control parameters is derived based on Gaussian distribution to obtain the predicted control effect.

[0054] According to embodiments of this disclosure, the optimization model may perform multiple rounds of optimization, each round having an intermediate control parameter and an intermediate control effect corresponding to that intermediate control parameter.

[0055] According to an embodiment of this disclosure, the first preset optimization condition may be to compare the intermediate control effects of all rounds, select an optimal intermediate control effect, and determine the intermediate control parameters corresponding to the optimal intermediate control effect as pre-sampling control parameters.

[0056] According to embodiments of this disclosure, by optimizing the control parameters in advance during the training process, the obtained pre-sampled control parameters can be directly called in practical applications, thereby reducing the system response time and achieving a rapid vibration isolation effect.

[0057] According to embodiments of this disclosure, constructing a Gaussian distribution based on initial control parameters, variable control parameters, and initial control effect includes: acquiring an initial residual vibration signal of the platform corresponding to the initial control parameters, wherein the initial residual vibration signal is obtained by applying an initial vibration isolation force to the controlled platform based on the initial control parameters, and the initial vibration isolation force is generated based on the initial control parameters; determining the initial control effect corresponding to the initial control parameters based on the Allen deviation of the initial residual vibration signal of the platform; generating a kernel function associated with the Gaussian distribution based on the initial control parameters and variable control parameters; and constructing a Gaussian distribution based on the kernel function, variable control parameters, initial control parameters, and initial control effect.

[0058] According to embodiments of this disclosure, obtaining the initial feedback signal corresponding to the initial control parameters can be achieved by generating an initial control signal based on the initial control parameters, so that the actuator applies an initial vibration isolation force to the controlled platform based on the initial control signal. Under the action of the external interference source and the initial vibration isolation force, the controlled platform will generate a new vibration state, which is collected by the sensor to obtain the initial feedback signal.

[0059] According to embodiments of this disclosure, the Allen deviation can be calculated by measuring the deviation between the vibration signals of the controlled platform every second after applying the initial vibration isolation force to the controlled platform, and the deviation can be determined as the initial control effect corresponding to the initial control parameters.

[0060] According to embodiments of this disclosure, a Gaussian distribution is constructed based on the kernel function, variable control parameters, initial control parameters, and initial control effect. This can be achieved by denoting the initial control parameters as... And obtain the corresponding initial control effect. The Gaussian distribution is shown in formula (1).

[0061] (1);

[0062] in, Indicates a Gaussian distribution. Indicates variable control parameters, Indicates the predicted control effect. Both indicate that the parameters are controlled by variables. and initial control parameters The generated kernel function.

[0063] According to embodiments of this disclosure, generating a kernel function associated with a Gaussian distribution based on initial control parameters and variable control parameters includes: constructing a correlation matrix between the variable control parameters and the initial control parameters to obtain a first kernel function; constructing an autocorrelation matrix of the variable control parameters to obtain a second kernel function, wherein the first kernel function and the second kernel function have the same hyperparameters; optimizing the hyperparameters to obtain target hyperparameters; updating the first kernel function and the second kernel function based on the target hyperparameters to obtain updated first kernel function and second kernel function; and determining the kernel function associated with the Gaussian distribution based on the updated first kernel function and second kernel function.

[0064] According to embodiments of this disclosure, constructing the correlation matrix between the variable control parameters and the initial control parameters can be achieved by constructing a matrix using multiple variable sub-control parameters of the variable control parameters and multiple initial sub-control parameters of the initial control parameters to obtain the first kernel function. It is used to analyze the correlation between variable control parameters and initial control parameters.

[0065] According to embodiments of this disclosure, constructing the autocorrelation matrix of the variable control parameters can be achieved by using multiple sets of variable control parameters to construct the matrix, thereby obtaining the second kernel function. It is used to analyze the correlation between multiple sets of variable control parameters.

[0066] According to embodiments of this disclosure, the hyperparameters of the kernel function are used to control the size of the kernel function, and the Gaussian distribution can be adjusted by adjusting the hyperparameters.

[0067] For example, the second kernel function can be as shown in formula (2).

[0068] (2);

[0069] in, Indicates the second kernel function ,in, It is the i-th group of variable control parameters. It is the j-th group of variable control parameters. and Since both are hyperparameters, it can be seen that the size of the second kernel function depends on the size of the hyperparameters.

[0070] According to embodiments of this disclosure, hyperparameter optimization can be achieved by adjusting the values ​​of the hyperparameters to update the first kernel function and the second kernel function. The kernel function constructed based on the updated first and second kernel functions can output accurate predictive control effects through the aforementioned Gaussian distribution, thereby obtaining the optimal control parameters.

[0071] According to embodiments of this disclosure, optimizing hyperparameters to obtain target hyperparameters includes: constructing an autocorrelation matrix of initial control parameters to obtain a third kernel function; constructing a likelihood function based on the hyperparameters, the third kernel function, and the initial control effect; optimizing the hyperparameters to obtain optimized hyperparameters; calculating the likelihood function value based on the optimized hyperparameters; and determining the optimized hyperparameters as target hyperparameters if the likelihood function value satisfies a second preset optimization condition.

[0072] According to embodiments of this disclosure, constructing the autocorrelation matrix of the initial control parameters can be achieved by using multiple sets of initial control parameters to construct the matrix and obtain the third kernel function. It is used to analyze the autocorrelation between multiple sets of initial control parameters.

[0073] According to embodiments of this disclosure, a likelihood function is constructed based on hyperparameters, a third kernel function, and initial control effects. It can be as shown in formula (3).

[0074] (3);

[0075] Where N represents a normal distribution, and the hyperparameters are optimized to achieve the following: The hyperparameter corresponding to the maximum likelihood function value is determined as the target hyperparameter to satisfy the second preset optimization condition.

[0076] According to embodiments of this disclosure, by optimizing hyperparameters based on the likelihood function, the constructed kernel function can more accurately analyze the correlation between various parameters, thereby enabling the Gaussian distribution to obtain the optimal preset control parameters.

[0077] According to embodiments of this disclosure, when the predictive control effect meets a first preset optimization condition, the variable control parameter is determined as a presampled control parameter, including: analyzing the predictive control effect using an expected boost function to obtain an analysis result; and when the analysis result indicates that the predictive control effect meets a third preset optimization condition, the variable control parameter is determined as a presampled control parameter.

[0078] According to embodiments of this disclosure, multiple rounds of optimization can be performed before determining the predictive control parameters. In a new round, in order to obtain new intermediate control parameters, the control parameters can be collected using a collection function, which includes at least one of a random sampling function, an expectation boosting function, a probability improvement function, and a Thompson sampling function.

[0079] The Expected Improvement (EI) function can be represented by Equation (4).

[0080] (4);

[0081] in, Represents expectations, It represents the best predictive control performance in the current round and in all historical rounds. These are the variable control parameters corresponding to the best predictive control effect in the current round and in historical rounds.

[0082] Furthermore, based on the expected improvement Determine the new variable control parameters based on the maximum value of the variable control parameters. Based on the new variable control parameters, the new predictive control effect of the controlled platform as measured by the sensor is determined. .

[0083] The variable control dataset is composed of Expanded to Based on the expanded variable control dataset, the hyperparameters of the kernel function can be updated, thereby updating the Gaussian distribution. Then, based on the updated Gaussian distribution, a new round of variable control parameters can be obtained from the acquisition function, thus obtaining a new round of predictive control effect. This process continues until a variable control parameter that meets the preset optimization conditions is found and determined as the predictive control parameter. The third preset optimization condition can be that after completing a fixed number of optimization rounds, the variable control parameter corresponding to the optimal predictive control effect in all rounds is selected as the predictive control parameter.

[0084] Figure 2 An optimization diagram based on a back-end sensor is illustrated schematically according to an embodiment of the present disclosure; Figure 3 An optimized schematic diagram based on a back-end sensor and a front-end sensor according to an embodiment of the present disclosure is illustrated.

[0085] According to embodiments of this disclosure, the sensor may include a front-end sensor disposed at a front end and a rear-end sensor disposed at a rear end. Taking a rear-end sensor as an example, such as... Figure 2 As shown, the initial control parameters are generated by the controller into an initial control signal and input to the actuator. The actuator applies an initial vibration isolation force to the controlled platform, and the initial control effect is obtained by the back-end sensor. Subsequently, the initial control parameters in the controller are adjusted by the optimization model and the acquisition function to obtain the variable control parameters.

[0086] If front-end sensors are also included, then as follows Figure 3 As shown, vibration signals are collected by front-end sensors, and initial control signals are randomly generated based on the vibration signals and input to the actuator. The actuator applies initial vibration isolation force to the controlled platform, and the initial control effect is obtained by back-end sensors. Subsequently, the initial control parameters are optimized by the optimization model and the acquisition function to obtain variable control parameters.

[0087] According to embodiments of this disclosure, generating a corresponding control signal based on pre-sampled control parameters includes: analyzing the pre-sampled control parameters using a controller to determine a preset control strategy; and generating a control signal suitable for the actuator based on the preset control strategy.

[0088] According to embodiments of this disclosure, the controller analyzes the pre-sampled control parameters to determine the parameters that the actuator in the current state needs to adjust, or the current and voltage that need to be adjusted, and generates a control strategy for the actuator parameters.

[0089] According to embodiments of this disclosure, the control strategy is converted into a signal, namely a control signal, so as to be transmitted to the actuator, so that the actuator can adjust its own parameters or modify the state of current and voltage in response to the control signal, so as to suppress vibration interference from external interference sources.

[0090] According to embodiments of this disclosure, the above method further includes: using a target identification model to perform parameter identification processing on the vibration signal to obtain a target vibration signal, wherein the parameters of the target identification model are obtained by optimizing the initial parameters of the target identification model using an optimization model; wherein comparing the vibration signal with a pre-sampled preset signal to obtain a comparison result includes: comparing the target vibration signal with the pre-sampled preset signal to obtain a comparison result.

[0091] According to embodiments of this disclosure, different external interference sources result in different types of vibration signals.

[0092] According to embodiments of this disclosure, a target identification model is used to identify and process vibration signals. By determining the type of vibration signal, the comparison between the target vibration signal and the preset signal, or the construction of the Gaussian distribution during the training process, can be more accurate, reducing the errors caused by different types of vibration signals.

[0093] According to embodiments of this disclosure, when it is necessary to approximate the actual response of a system using a theoretical model, i.e., it is necessary to determine the transfer function (i.e., target identification model) corresponding to the vibration signal and / or pre-sampled signal to the sensor, but the parameters of this transfer function cannot be determined. Optimizing the initial parameters of the target identification model using an optimization model can automatically optimize the parameters of the transfer function, thereby obtaining the optimal parameters.

[0094] Figure 4 The diagram illustrates an optimized target identification model according to an embodiment of the present disclosure.

[0095] According to embodiments of this disclosure, such as Figure 4 As shown, optimizing the initial parameters of the target identification model using an optimization model can be achieved by using the predicted values ​​of the vibration signal after processing by the target identification model. The predicted value is compared with the actual output value y of the sensor. The value y is obtained from the target identification model, while the actual output value y is the signal collected by the sensor after applying vibration disturbance to the controlled platform. The difference between the two is used as the loss value, i.e. The initial parameters of the target recognition model are optimized based on the loss value. After multiple rounds of optimization, the parameters of the target recognition model are obtained.

[0096] According to embodiments of this disclosure, the method further includes: acquiring a feedback signal using a sensor, wherein the feedback signal is obtained by applying a vibration isolation force to the controlled platform; analyzing the feedback signal to obtain a feedback analysis result; if the feedback analysis result indicates an abnormal vibration isolation or the comparison result indicates that the vibration signal and the pre-sampled signal are dissimilar, optimizing the pre-sampled control parameters using an optimization model to obtain target control parameters; generating a target control signal based on the target control parameters; and applying the target vibration isolation force to the controlled platform using an actuator, wherein the actuator responds to the target control signal and generates the target vibration isolation force.

[0097] According to embodiments of this disclosure, after applying vibration isolation force to the controlled platform, sensors are used to detect the controlled platform, obtain the vibration signal under the current state, and use it as a feedback signal.

[0098] According to embodiments of this disclosure, if the feedback analysis results indicate vibration isolation abnormalities or the comparison results indicate that the vibration signal and the pre-sampled signal are dissimilar, it indicates that the preset control parameters obtained from the training process corresponding to the current external interference source environment are not applicable, and the control parameters need to be re-optimized using an optimization model to adapt to the current external interference source environment.

[0099] According to embodiments of this disclosure, optimized control parameters are used as target control parameters so that the actuator can apply a target vibration isolation force to the controlled platform based on the target control parameters, thereby suppressing vibration interference from external interference sources.

[0100] Figure 5 A schematic block diagram of an automatic vibration isolation device according to an embodiment of the present disclosure is shown.

[0101] A second aspect of this disclosure provides an automatic vibration isolation device, comprising: a controlled platform 510; a sensor 520 for acquiring vibration signals, wherein the vibration signals are obtained by superimposing the original vibration of the platform surface onto the controlled platform 510 due to vibration interference from an external vibration interference source; a controller 530 for comparing the vibration signals and a pre-sampled signal to obtain a comparison result; determining control parameters corresponding to the pre-sampled signal when the comparison result indicates that the vibration signals and the pre-sampled signals are similar, wherein the control parameters are obtained by optimizing the initial control parameters corresponding to the pre-sampled signal using an optimization model; generating a corresponding control signal based on the control parameters; and an actuator 540 for generating a vibration isolation force in response to the control signal and applying the vibration isolation force to the controlled platform 510, wherein the vibration isolation force is used to suppress vibration interference generated by an external vibration interference source on the controlled platform 510.

[0102] Figure 6 A schematic diagram of an automatic vibration isolation device according to an embodiment of the present disclosure is shown.

[0103] External interference source 1 causes vibration interference to the controlled platform 2. At this time, the front-end sensor 3 collects the vibration signal and compares it with the pre-sampled signal to obtain the comparison result. If the comparison result indicates that the vibration signal and the pre-sampled signal are similar, the controller 6 determines the control parameters corresponding to the pre-sampled signal and generates the corresponding control signal, which is transmitted to the actuator 7. The actuator 7 responds to the control signal and applies vibration isolation force to the controlled platform 2. After applying the vibration isolation force, the back-end sensor 5 collects the residual vibration signal. If the controller 6 analyzes the feedback signal and the feedback analysis result indicates that the vibration isolation is abnormal or the comparison result indicates that the vibration signal and the pre-sampled signal are not similar, the optimization model 4 is used to optimize the pre-sampled control parameters to obtain the target control parameters and input them to the controller 6.

[0104] Those skilled in the art will understand that the features described in the various embodiments of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0105] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. An automatic vibration isolation method, characterized in that, The method includes: Vibration signals are collected using sensors, wherein the vibration signals are obtained by external vibration interference sources vibrating the controlled platform. The vibration signal and the pre-sampled signal are compared to obtain the comparison result; If the comparison results indicate that the vibration signal and the presampled signal are similar, a presampled control parameter corresponding to the presampled signal is determined, wherein the presampled control parameter is obtained by optimizing the initial control parameter corresponding to the presampled signal using an optimization model; A control signal is generated based on the pre-sampled control parameters and the vibration signal; An actuator, in response to the control signal, applies a vibration isolation force to the controlled platform, wherein the vibration isolation force is used to suppress the vibration interference generated on the controlled platform by the external vibration interference source; The optimization of the initial control parameters using the optimization model to obtain the presampled control parameters is performed based on the following operations: A Gaussian distribution is constructed based on the initial control parameters, variable control parameters, and initial control effect. The initial control effect is associated with the initial control parameters, and the variable control parameters are associated with the initial control parameters. Based on the Gaussian distribution, the variable control parameters are predicted to obtain the predicted control effect; If the predictive control effect meets the first preset optimization condition, the variable control parameter is determined as the presampled control parameter.

2. The method according to claim 1, characterized in that, The step of constructing a Gaussian distribution based on initial control parameters, variable control parameters, and initial control effects includes: Acquire the initial residual vibration signal of the platform corresponding to the initial control parameters, wherein the initial residual vibration signal of the platform is obtained by applying an initial vibration isolation force to the controlled platform based on the initial control parameters, and the initial vibration isolation force is generated according to the initial control parameters; Based on the Allen deviation of the initial residual vibration signal of the initial platform, the initial control effect corresponding to the initial control parameters is determined; Based on the initial control parameters and the variable control parameters, a kernel function associated with the Gaussian distribution is generated; The Gaussian distribution is constructed based on the kernel function, the variable control parameters, the initial control parameters, and the initial control effect.

3. The method according to claim 2, characterized in that, The step of generating a kernel function associated with the Gaussian distribution based on the initial control parameters and the variable control parameters includes: Construct the correlation matrix between the variable control parameters and the initial control parameters to obtain the first kernel function; Construct the autocorrelation matrix of the control parameters of the variables to obtain the second kernel function, wherein the first kernel function and the second kernel function have the same hyperparameters; The hyperparameters are optimized to obtain the target hyperparameters; Based on the target hyperparameters, update the first kernel function and the second kernel function to obtain the updated first kernel function and second kernel function; Based on the updated first and second kernel functions, a kernel function associated with the Gaussian distribution is determined.

4. The method according to claim 3, characterized in that, The optimization of the hyperparameters to obtain the target hyperparameters includes: Construct the autocorrelation matrix of the initial control parameters to obtain the third kernel function; Based on the hyperparameters, the third kernel function, and the initial control effect, a likelihood function is constructed. The hyperparameters are optimized to obtain the optimized hyperparameters; Based on the optimized hyperparameters, the likelihood function value of the likelihood function is calculated; If the likelihood function value satisfies the second preset optimization condition, the optimized hyperparameter is determined as the target hyperparameter.

5. The method according to claim 1, characterized in that, When the predictive control effect meets the first preset optimization condition, determining the variable control parameter as the presampled control parameter includes: The predictive control effect is analyzed using the expected improvement function, and the analysis results are obtained. If the analysis results indicate that the predictive control effect meets the third preset optimization condition, the variable control parameter is determined as the presampled control parameter.

6. The method according to claim 1, characterized in that, The step of generating a control signal based on the pre-sampled control parameters and the vibration signal includes: The controller is used to analyze the pre-sampled control parameters and the vibration signal to determine the control strategy; Based on the control strategy and the vibration signal, a control signal suitable for the actuator is generated.

7. The method according to claim 1, further comprising: The vibration signal is processed by parameter identification using a target identification model to obtain the target vibration signal. The parameters of the target identification model are obtained by optimizing the initial parameters of the target identification model using the optimization model. The comparison of the vibration signal and the pre-sampled signal to obtain the comparison result includes: The target vibration signal and the pre-sampled signal are compared to obtain the comparison result.

8. The method according to claim 1, characterized in that, The method further includes: The sensor is used to collect residual vibration signals of the platform, which are obtained by applying the vibration isolation force to the controlled platform. The residual vibration signal of the platform is analyzed to obtain the platform analysis results; If the analysis results of the platform indicate abnormal vibration isolation, or if the comparison results indicate that the vibration signal and the pre-sampled signal are dissimilar, then... The pre-sampled control parameters are optimized using the optimization model to obtain the target control parameters; Based on the target control parameters and the vibration signal, a target control signal is generated; An actuator is used to apply a target vibration isolation force to the controlled platform, wherein the actuator generates the target vibration isolation force in response to the target control signal.

9. An automatic vibration isolation device, characterized in that, The device includes: Controlled platform; A sensor is used to collect vibration signals, wherein the vibration signals are obtained by an external vibration interference source vibrating the controlled platform. A controller is configured to compare the vibration signal and the presampled signal to obtain a comparison result; if the comparison result indicates that the vibration signal and the presampled signal are similar, a presampled control parameter corresponding to the presampled signal is determined, wherein the presampled control parameter is obtained by optimizing the initial control parameter corresponding to the presampled signal using an optimization model; and a control signal is generated based on the presampled control parameter and the vibration signal. An actuator is configured to generate a vibration isolation force in response to the control signal and apply the vibration isolation force to the controlled platform, the vibration isolation force being used to suppress the vibration interference generated by the external vibration interference source on the controlled platform; The optimization of the initial control parameters using the optimization model to obtain the presampled control parameters is performed based on the following operations: A Gaussian distribution is constructed based on the initial control parameters, variable control parameters, and initial control effect. The initial control effect is associated with the initial control parameters, and the variable control parameters are associated with the initial control parameters. Based on the Gaussian distribution, the variable control parameters are predicted to obtain the predicted control effect; If the predictive control effect meets the first preset optimization condition, the variable control parameter is determined as the presampled control parameter.

Images