A dynamic balance device control system and method

Abstract

The present invention relates to the technical field of numerical control machine tools, and specifically to a dynamic balance device control system and method. The method includes: obtaining displacement data of the working part of the numerical control machine tool in the vertical direction, calculating the force on the working part, adjusting the deformation amount of the spring connected to the working part, and controlling the spring to apply a reaction force; constructing a bounce threshold of the working part and an adaptive spring elastic force calculation model, and inversely solving the telescopic amount of the electric cylinder; introducing a spring elastic force loss factor, constructing a spring elastic force loss balance model, calculating the spring elastic force loss and compensating it; using a machine learning algorithm to train a support vector regression model, predicting the spring elastic force loss factor, and calculating the real-time balance reaction force provided by the spring in combination with the displacement amount of the working part to achieve adaptive active control of the vibration of the working part. This method can effectively improve the machining accuracy and stability of the numerical control machine tool and extend the service life of the equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of numerical control machine tools, and specifically to a control system and method for a dynamic balancing device. Background Art

[0002] Numerical control machine tools are important equipment in modern manufacturing and are widely used in the processing of various workpieces. During the operation of a numerical control machine tool, due to the influence of factors such as cutting force and vibration, the working part of the numerical control machine tool will produce certain displacements and deformations; such displacements and deformations will affect the machining accuracy and quality, and long-term displacements will cause irreversible damage to the motors of the numerical control machine tool. Therefore, it is necessary to monitor the force state of the working part of the numerical control machine tool in real time and perform balance control to ensure machining performance and maintain the normal operation of the numerical control machine tool.

[0003] Currently, the method of traditional technical solutions is to install an airbag or a hydraulic device on the working part of the numerical control machine tool and use the acting force of air pressure or hydraulic pressure to balance the external acting force. However, the traditional solution has the defects of slow response speed and low control accuracy, and it is difficult to meet the requirements of high-speed and high-precision machining. At the same time, the airbag or hydraulic device has a large volume and occupies a lot of space, which is not conducive to the miniaturization and integration of numerical control machine tools.

[0004] Therefore, there is an urgent need for a control method and system that can monitor the force state of the working part of a numerical control machine tool in real time, dynamically adjust the parameters of elastic elements according to the actual force situation and the characteristics of elastic elements, and achieve the force balance of the working part.

[0005] In view of this, the present invention proposes a control system and method for a dynamic balancing device. Summary of the Invention

[0006] To achieve the above object, the present invention provides a control system and method for a dynamic balancing device, and the specific technical solutions are as follows:

[0007] A control method for a dynamic balancing device, comprising:

[0008] Obtaining displacement data of the working part of the numerical control machine tool in the vertical direction during operation, calculating the force data of the working part of the numerical control machine tool according to the displacement data, and applying a reaction force to the working part of the numerical control machine tool through a spring;

[0009] Adjusting the spring deformation amount by using an electric cylinder, and controlling the spring elastic force based on Hooke's law through the spring deformation amount;

[0010] Constructing a bounce threshold for the working part of the numerical control machine tool, and based on the obtained reaction force required by the working part of the numerical control machine tool in the vertical direction, constructing an adaptive spring elastic force calculation model, and inversely solving the telescopic amount of the electric cylinder;

[0011] Construct a spring elastic force loss balance model. Based on the working time, working frequency, and force-bearing conditions of the spring, calculate the elastic force loss of the spring at different times, and calculate the compensation value of the spring deformation according to the elastic force loss.

[0012] Construct and train a machine learning algorithm to calculate the spring elastic force loss factor. According to the displacement of the working part of the CNC machine tool and the spring elastic force loss factor, calculate the reaction force provided by the spring elastic force to the working part of the CNC machine tool, and achieve the force balance of the working part of the CNC machine tool in the vertical direction.

[0013] Preferably, obtain the displacement data of the working part of the CNC machine tool in the vertical direction, calculate the force data of the working part of the CNC machine tool according to the displacement data, and calculate the resultant external force received by the working part of the CNC machine tool in the vertical direction according to Newton's second law.

[0014] Apply a reaction force to the working part of the CNC machine tool through the spring. To make the working part of the CNC machine tool in force balance in the vertical direction, provide a supporting force equal in magnitude and opposite in direction to the resultant external force through the spring.

[0015] The top of the spring is connected to the top of the electric cylinder, and the bottom of the spring is connected to the working part of the CNC machine tool, and undergoes elastic deformation in the vertical direction; when the working part of the CNC machine tool is fixed, the spring controls the spring deformation through the telescoping of the electric cylinder.

[0016] Use an electric cylinder to adjust the spring deformation. By controlling the telescoping amount of the electric cylinder, change the spring deformation so that the reaction force provided by the spring meets the requirements of the force balance of the working part of the CNC machine tool.

[0017] Preferably, collect the displacement of the working part of the CNC machine tool during operation through a displacement sensor ; construct a bounce threshold for the working part of the CNC machine tool, and define the bounce threshold of the working part of the CNC machine tool in the vertical direction , when the working part of the CNC machine tool is in the displacement within the time , it is regarded as a bounce;

[0018] Let the mass of the working part of the CNC machine tool be , and the resultant external force received by the working part of the CNC machine tool in the vertical direction be , according to Newton's second law: ; where is the acceleration of the working part of the CNC machine tool in the vertical direction, which is obtained by taking the second derivative of the displacement collected by the displacement sensor with respect to time ;

[0019] Apply a reaction force to the working part of the CNC machine tool through the spring, and set the spring to provide a supporting force vertically upward , according to Hooke's law, the supporting force of the spring is proportional to the deformation : ; where is the spring stiffness coefficient;

[0020] To make the working part of the CNC machine tool in vertical force balance, a supporting force equal in magnitude and opposite in direction to the resultant external force is provided by the spring : ;

[0021] Controlling the spring deformation to achieve the force balance of the working part of the CNC machine tool. From the formula , it can be seen that by solving the deformation of the control spring, is satisfied: , achieving force balance.

[0022] Preferably, according to the displacement of the working part of the CNC machine tool in the vertical direction, the resultant external force is calculated;

[0023] Since the spring stiffness coefficient is not a constant value, an adaptive spring force calculation model is constructed, and the nonlinear stiffness coefficient function of the spring is defined. The nonlinear stiffness coefficient function is expressed as a piecewise function:

[0024]

[0025] where is preset force segmentation points, is the corresponding stiffness coefficients;

[0026] Substituting the nonlinear stiffness coefficient function into Hooke's law, an adaptive spring force calculation model is obtained: ;

[0027] Reverse-solving the telescopic amount of the electric cylinder. From the adaptive spring force calculation model , it is obtained that to provide the required reaction force , the spring deformation needs to satisfy: ;

[0028] The telescopic amount of the electric cylinder is equal to the spring deformation , that is ;

[0029] According to the calculated required spring deformation , control the telescopic amount of the electric cylinder , so that the spring can provide the required reaction force to achieve the force balance of the working part of the CNC machine tool.

[0030] Preferably, since the spring will generate elastic force loss during operation, introduce a spring elastic force loss factor to compensate for the elastic force loss during the spring operation;

[0031] Define the spring elastic force loss factor , indicating the elastic force loss ratio of the spring relative to the initial value under the conditions of the working duration , the number of working times and the force ;

[0032] Construct a spring elastic force loss balance model. On the basis of the adaptive spring elastic force calculation model , introduce the elastic force loss factor , and obtain the spring elastic force calculation model considering the elastic force loss: ; where is the actual spring elastic force after considering the elastic force loss;

[0033] Calculate the elastic force loss of the spring at different times. According to the working time , the number of working times and the force condition of the spring, substitute them into the elastic force loss factor expression to calculate the elastic force loss factor at different times; substitute the calculated elastic force loss factor into the spring elastic force calculation model considering the elastic force loss to obtain the actual spring elastic force ;

[0034] Calculate the compensation value of the spring deformation amount. It can be known from the spring elastic force calculation model considering the elastic force loss that to compensate for the elastic force loss and make the actual spring elastic force reach the required supporting force , that is , it is necessary to compensate the spring deformation amount ; Let , and obtain the compensation value of the spring deformation amount: ; The compensation value of the telescopic amount of the electric cylinder;

[0035] Add the compensation value of the telescopic amount of the electric cylinder to the telescopic amount of the electric cylinder, and substitute the compensated telescopic amount of the electric cylinder into the electric cylinder control, that is, under the condition of considering the elastic force loss, achieve the force balance of the working part of the CNC machine tool in the vertical direction.

[0036] Preferably, historical working data of the spring is collected, including the working duration of the spring , the number of working times , the force and the corresponding elastic force loss factor to form a data set;

[0037] Select the working duration , the number of working times and the force as input features, and the elastic force loss factor as the output target; randomly divide the data set into a training set and a test set;

[0038] Construct a support vector regression SVR model, select the Gaussian kernel function as the kernel function of the SVR model, introduce slack variables, and construct the optimization objective of the SVR model; transform the optimization problem into a dual problem and introduce Lagrange multipliers for solution;

[0039] Train and optimize the support vector regression SVR model, use the training set data, and obtain the optimal Lagrange multipliers and the model parameters of the SVR model by solving the dual problem of the SVR model; use the test set data to evaluate the trained SVR model, calculate the error between the predicted value and the true value, and use indicators such as mean square error, mean absolute error, and coefficient of determination to evaluate the prediction performance of the model;

[0040] According to the model evaluation results, adjust the hyperparameters of the SVR model, including the penalty coefficient, the parameters of the loss function, and the bandwidth parameter of the kernel function; use the grid search optimization method to search for the optimal combination of hyperparameters in the hyperparameter space; repeat the model training and evaluation steps until the expected prediction performance is obtained.

[0041] Preferably, use the trained model to calculate the elastic force loss factor, deploy the trained SVR model to the control system of the numerically controlled machine tool, and realize the online prediction function;

[0042] During the operation of the numerically controlled machine tool, collect the working duration , the number of working times and the force of the spring in real time, input them into the SVR model, and obtain the predicted elastic force loss factor ;

[0043] Elastic force loss compensation, substitute the predicted elastic force loss factor into the compensation formula for the spring deformation amount:

[0044]

[0045] Calculate the real-time spring deformation compensation value , and transfer the calculated spring deformation compensation value to the electric cylinder to adjust the telescopic amount of the electric cylinder to compensate for the elastic force loss of the spring.

[0046] A dynamic balance device control system for implementing the described dynamic balance device control method, including: a displacement data acquisition module, a spring deformation adjustment module, a spring deformation calculation module, a compensation value calculation module, and an elastic force loss factor calculation module;

[0047] The displacement data acquisition module is used to acquire the displacement data of the working part of the numerical control machine tool in the vertical direction during work, calculate the force data of the working part of the numerical control machine tool according to the displacement data, and apply a reaction force to the working part of the numerical control machine tool through the spring;

[0048] The spring deformation adjustment module uses an electric cylinder to adjust the spring deformation and controls the spring elastic force based on Hooke's law through the spring deformation;

[0049] The spring deformation calculation module is used to construct a bounce threshold for the working part of the numerical control machine tool, and based on the required reaction force of the working part of the numerical control machine tool in the vertical direction obtained, construct an adaptive spring elastic force calculation model and inversely solve the telescopic amount of the electric cylinder;

[0050] The compensation value calculation module is used to construct a spring elastic force loss balance model, calculate the elastic force loss of the spring at different times based on the spring working time, working times, and force conditions, and calculate the spring deformation compensation value according to the elastic force loss;

[0051] The elastic force loss factor calculation module is used to construct and train a machine learning algorithm to calculate the spring elastic force loss factor, and calculate the reaction force provided by the spring elastic force to the working part of the numerical control machine tool according to the displacement amount of the working part of the numerical control machine tool and the spring elastic force loss factor, so as to achieve the force balance of the working part of the numerical control machine tool in the vertical direction.

[0052] An electronic device includes: a processor and a memory. Among them, a computer program that can be called by the processor is stored in the memory; the processor executes the described dynamic balance device control method by calling the computer program stored in the memory.

[0053] A computer-readable storage medium stores instructions, and when the instructions run on a computer, the computer is caused to execute the described dynamic balance device control method.

[0054] Advantages of the present invention: By obtaining displacement data and calculating force data, the present invention realizes real-time monitoring of the force state of the working part of the numerically controlled machine tool, provides a data basis for subsequent dynamic balance control, and improves the pertinence and effectiveness of control.

[0055] The present invention uses an electric cylinder to adjust the spring deformation amount, controls the spring elastic force based on Hooke's law, and realizes the application of an accurately controllable reaction force to the working part of the numerically controlled machine tool, improving the flexibility and precision of force balance control.

[0056] The present invention constructs a bounce threshold and an adaptive spring elastic force calculation model, and realizes accurate control of the required reaction force of the working part of the numerically controlled machine tool by inversely solving the telescopic amount of the electric cylinder, improving the adaptive ability and control performance of the system.

[0057] The present invention constructs a spring elastic force loss balance model, considers the working time, number of times and force conditions of the spring, calculates the spring elastic force loss and compensates it, ensures the elastic force stability of the spring during long-term use, and improves the reliability of the system.

[0058] The present invention constructs and trains a machine learning algorithm, calculates the spring elastic force loss factor, combines the displacement amount and the loss factor to calculate the reaction force provided by the spring, and realizes intelligent adaptive balance control of the working part of the numerically controlled machine tool, improving the control precision and efficiency. Description of the Drawings

[0059] Figure 1 It is a flowchart of a control method for a dynamic balance device provided by the present invention;

[0060] Figure 2 It is a structural diagram of a control system for a dynamic balance device provided by the present invention. Detailed Embodiments

[0061] To better understand the present invention, more detailed descriptions will be made on various aspects of the present invention with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present invention, and do not limit the scope of the present invention in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0062] In the accompanying drawings, for ease of illustration, the sizes, dimensions and shapes of the elements have been slightly adjusted. The accompanying drawings are for illustrative purposes only and are not drawn to an exact scale. As used herein, terms such as "substantially", "about" and similar terms are used as terms of approximation and not as terms of degree, and are intended to account for the inherent deviations in measured or calculated values that would be recognized by a person of ordinary skill in the art. Additionally, in the present invention, the order of description of the various step processes does not necessarily represent the order in which these processes occur in actual operation, unless otherwise clearly specified or derivable from the context.

[0063] It should also be understood that expressions such as "comprising", "including", "having", "containing" and / or "including" are open-ended rather than closed-ended expressions in this specification, which mean that the stated features, elements and / or components exist, but do not exclude the existence of one or more other features, elements, components and / or combinations thereof. In addition, when an expression such as "at least one of..." appears after a list of listed features, it modifies the entire list of features rather than just individual elements in the list. In addition, when describing embodiments of the present invention, the use of "may" means "one or more embodiments of the present invention". And the term "exemplary" is intended to refer to an example or illustration.

[0064] Unless otherwise defined, all terms used herein (including engineering terms and scientific and technical terms) have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention pertains. It should also be understood that, unless clearly stated in the present invention, words defined in a common dictionary should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and should not be interpreted in an idealized or overly formal sense.

[0065] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0066] Embodiment 1

[0067] Referring to Figure 1 , the first embodiment of the present invention provides a method for controlling a dynamic balance device.

[0068] S1: Obtain the displacement data of the working part of the numerical control machine tool in the vertical direction during operation, calculate the force data of the working part of the numerical control machine tool according to the displacement data, and apply a reaction force to the working part of the numerical control machine tool through a spring.

[0069] Obtain the displacement data of the working part of the CNC machine tool in the vertical direction. Install a displacement sensor on the working part of the CNC machine tool to collect the displacement of the working part of the CNC machine tool in the vertical direction in real time. The displacement sensor can be selected from high-precision sensors such as inductive, capacitive, and photoelectric sensors.

[0070] Calculate the force data of the working part of the CNC machine tool according to the displacement data, and calculate the resultant external force received by the working part of the CNC machine tool in the vertical direction according to Newton's second law.

[0071] Apply a reaction force to the working part of the CNC machine tool through the spring. To make the working part of the CNC machine tool in force balance in the vertical direction, provide a supporting force through the spring that is equal in magnitude and opposite in direction to the resultant external force.

[0072] In step S1, by installing a high-precision displacement sensor on the working part of the CNC machine tool, collect the displacement data in the vertical direction in real time, calculate the force of the working part according to the displacement data, and then use the spring to apply a reaction force to realize the real-time monitoring and dynamic balance of the force state of the working part of the CNC machine tool, improve the machining accuracy and stability, and reduce vibration and noise.

[0073] S2: Use an electric cylinder to adjust the spring deformation amount. Based on Hooke's law, control the spring elastic force through the spring deformation amount.

[0074] The top of the spring is connected to the top of the electric cylinder, and the bottom of the spring is connected to the working part of the CNC machine tool, and elastic deformation occurs in the vertical direction. When the working part of the CNC machine tool is fixed and the movement of the working part of the CNC machine tool in the vertical direction is very small, the spring controls the spring deformation amount through the telescopic movement of the electric cylinder, and then controls the change of the spring elastic force.

[0075] Use an electric cylinder to adjust the spring deformation amount. By controlling the telescopic amount of the electric cylinder, change the spring deformation amount, so that the reaction force provided by the spring meets the requirements of the force balance of the working part of the CNC machine tool.

[0076] In step S2, use an electric cylinder to adjust the spring deformation amount, and accurately adjust the spring elastic force by controlling the spring deformation amount based on Hooke's law, so as to apply an accurately controllable balance reaction force to the working part of the CNC machine tool. Compared with passive elastic elements, adjusting the spring deformation amount by an electric cylinder has the advantages of fast response speed, high control accuracy, and strong adaptability, and can significantly improve the dynamic balance control performance of the working part of the CNC machine tool.

[0077] S3: Construct a bounce threshold for the working part of the CNC machine tool, and based on the required reaction force of the working part of the CNC machine tool obtained in the vertical direction, construct an adaptive spring elastic force calculation model, and inversely calculate the telescopic amount of the electric cylinder.

[0078] Collect the displacement of the working part of the CNC machine tool during operation through the displacement sensor , construct the bounce threshold of the working part of the CNC machine tool, and define the bounce threshold of the working part of the CNC machine tool in the vertical direction , when the working part of the CNC machine tool is in the displacement within the time is regarded as a bounce occurring, and the bounce threshold can be set according to factors such as the specific working conditions of the CNC machine tool and the processing accuracy requirements.

[0079] Let the mass of the working part of the CNC machine tool be , and the resultant external force acting on the working part of the CNC machine tool in the vertical direction be . According to Newton's second law, we have: ; where is the acceleration of the working part of the CNC machine tool in the vertical direction, which is obtained by taking the second derivative of the displacement collected by the displacement sensor with respect to time ;

[0080] Apply a reaction force to the working part of the CNC machine tool through a spring, and set the spring to provide a vertical upward supporting force . According to Hooke's law, the supporting force of the spring is proportional to the deformation : ; where is the spring stiffness coefficient, which is an inherent property of the spring;

[0081] To make the working part of the CNC machine tool in vertical force balance, a supporting force that is equal in magnitude and opposite in direction to the resultant external force is provided by the spring: ;

[0082] Control the spring deformation to achieve the force balance of the working part of the CNC machine tool. From the formula , it can be seen that by solving the deformation of the control spring, is made to satisfy: , thus achieving force balance.

[0083] According to the displacement of the working part of the CNC machine tool in the vertical direction, calculate the resultant external force ; to achieve force balance, a reaction force that is equal in magnitude and opposite in direction to is provided by the spring, that is .

[0084] Since the spring stiffness coefficient is not a constant value, construct an adaptive spring elastic force calculation model, and define the nonlinear stiffness coefficient function of the spring, so that the spring stiffness coefficient changes with the force on the spring, and the nonlinear stiffness coefficient function It is represented by a piecewise function:

[0085]

[0086] where is a preset force segmentation point, is a corresponding stiffness coefficient.

[0087] Substitute the non-linear stiffness coefficient function into Hooke's law to obtain an adaptive spring elastic force calculation model: .

[0088] Reverse solve the telescopic amount of the electric cylinder. From the adaptive spring elastic force calculation model it is obtained that to provide the required reaction force , the spring deformation amount needs to satisfy: .

[0089] The telescopic amount of the electric cylinder is equal to the spring deformation amount , that is .

[0090] According to the calculated required spring deformation amount , control the telescopic amount of the electric cylinder, then the spring can provide the required reaction force to achieve the force balance of the working part of the CNC machine tool.

[0091] By constructing the bounce threshold of the working part of the CNC machine tool, judge whether the working part of the CNC machine tool bounces, and obtain the required reaction force , use the adaptive spring elastic force calculation model to solve the required spring deformation amount , and control the telescopic amount of the electric cylinder, then the dynamic force balance of the working part of the CNC machine tool in the vertical direction can be achieved, avoiding or greatly reducing the bounce of the working part of the CNC machine tool during operation.

[0092] In step S3, by constructing the bounce threshold of the working part of the CNC machine tool, combining the displacement sensor data to calculate the required balance reaction force, and establishing an adaptive spring elastic force calculation model, considering the non-linear characteristics of the spring stiffness coefficient, reverse solving the telescopic amount of the electric cylinder, the adaptive dynamic balance control of the force of the working part of the CNC machine tool is realized, effectively avoiding or reducing the bounce phenomenon of the working part, and improving the processing quality and equipment reliability.

[0093] S4: Construct a spring elastic force loss balance model. Based on the working time, working frequency, and force-bearing condition of the spring, calculate the elastic force of the spring at different times, and calculate the compensation value of the spring deformation according to the elastic force loss.

[0094] Since the spring will generate elastic force loss during operation, introduce a spring elastic force loss factor to compensate for the elastic force loss during the spring operation.

[0095] Define the spring elastic force loss factor , which represents the loss ratio of the elastic force relative to the initial value under the condition that the spring has worked for a duration , working frequency and force-bearing ; the working frequency is defined as: each time the spring completes a telescopic motion, it is recorded as one working frequency.

[0096] Construct a spring elastic force loss balance model. On the basis of the adaptive spring elastic force calculation model , introduce the elastic force loss factor to obtain a spring elastic force calculation model considering elastic force loss: ; where is the actual spring elastic force considering elastic force loss.

[0097] Calculate the elastic force loss of the spring at different times. According to the working time , working frequency and force-bearing condition of the spring, substitute them into the elastic force loss factor expression to calculate the elastic force loss factor at different times; substitute the calculated elastic force loss factor into the spring elastic force calculation model considering elastic force loss to obtain the actual spring elastic force .

[0098] Calculate the compensation value of the spring deformation. It can be known from the spring elastic force calculation model considering elastic force loss that to compensate for the elastic force loss and make the actual spring elastic force reach the required supporting force , that is , it is necessary to compensate for the spring deformation .

[0099] Let , and obtain the compensation value of the spring deformation : ; the compensation value of the telescopic amount of the electric cylinder .

[0100] Add the compensation value of the telescopic amount of the electric cylinder to the telescopic amount of the electric cylinder, and the telescopic amount of the compensated electric cylinder Substitute it into the control of the electric cylinder, that is, under the consideration of elastic force loss, achieve the force balance of the working part of the CNC machine tool in the vertical direction.

[0101] In step S4, the spring elastic force loss factor is introduced, a spring elastic force loss balance model is constructed, the elastic force loss is calculated based on the working time, number of times and force condition of the spring, and by solving the spring deformation compensation value and controlling the telescopic amount of the electric cylinder, the automatic compensation of the spring elastic force loss is realized, ensuring the long-term stability and consistency of the force balance control of the working part of the CNC machine tool and extending the service life of the equipment.

[0102] S5: Construct and train a machine learning algorithm to calculate the spring elastic force loss factor, and calculate the reaction force provided by the spring elastic force to the working part of the CNC machine tool according to the displacement of the working part of the CNC machine tool and the spring elastic force loss factor, so as to achieve the force balance of the working part of the CNC machine tool in the vertical direction.

[0103] Collect the historical working data of the spring, including the working duration of the spring , the number of working times , the force and the corresponding elastic force loss factor , to form a data set.

[0104] Select the working duration , the number of working times and the force as input features, and the elastic force loss factor as the output target; randomly divide the data set into a training set and a test set, and the ratio of the training set to the test set can be set according to the actual situation.

[0105] Construct a support vector regression (SVR) model, select the Gaussian kernel function as the kernel function of the SVR model, introduce slack variables, and construct the optimization objective of the SVR model; transform the optimization problem into a dual problem and introduce Lagrange multipliers for solution.

[0106] Train and optimize the support vector regression (SVR) model, use the training set data, and by solving the dual problem of the SVR model, obtain the optimal Lagrange multipliers and the model parameters of the SVR model; use the test set data to evaluate the trained SVR model, calculate the error between the predicted value and the true value, and use the mean square error (MSE), mean absolute error (MAE), coefficient of determination ( ) index to evaluate the prediction performance of the model.

[0107] According to the model evaluation results, adjust the hyperparameters of the SVR model, including the penalty coefficient, the parameters of the loss function, and the bandwidth parameter of the kernel function, to improve the performance of the model; use grid search, random search, or Bayesian optimization methods to search for the optimal combination of hyperparameters in the hyperparameter space; repeat the model training and evaluation steps until the expected prediction performance is obtained.

[0108] Use the trained model to calculate the elastic force loss factor, deploy the trained SVR model to the control system of the numerically controlled machine tool, and realize the online prediction function.

[0109] During the operation of the numerically controlled machine tool, the working duration of the spring is collected in real time , the number of working times and the force , input them into the SVR model to obtain the predicted elastic force loss factor , substitute the predicted elastic force loss factor into the compensation formula for the spring deformation amount:

[0110]

[0111] Calculate the real-time spring deformation amount compensation value , transfer the calculated spring deformation amount compensation value to the electric cylinder to adjust the telescopic amount of the electric cylinder to compensate for the elastic force loss of the spring.

[0112] During the long-term operation of the numerically controlled machine tool, continuously collect the working data of the spring, and regularly retrain and update the SVR model to adapt to the change of the spring performance; regularly evaluate the performance of the prediction model, and adjust and optimize the model structure when necessary to maintain the prediction accuracy and reliability of the model.

[0113] In step S5, a support vector regression (SVR) model is constructed and trained using machine learning methods. Taking the spring working time, number of times, and force as inputs, predicting the elastic force loss factor, and combining with the displacement of the working part of the numerically controlled machine tool to calculate the real-time balance reaction force provided by the spring, realizing the intelligent adaptive dynamic balance control of the force on the working part of the numerically controlled machine tool. Through continuous learning and model update, the intelligent level and long-term reliability of the control system can be continuously improved.

[0114] Embodiment 2

[0115] Referring to Figure 2 , the second embodiment of the present invention provides a dynamic balance device control system.

[0116] The system includes: a displacement data acquisition module, a spring deformation amount adjustment module, a spring deformation amount calculation module, a compensation value calculation module, and an elastic force loss factor calculation module.

[0117] The displacement data acquisition module is configured to acquire the displacement data of the working part of the CNC machine tool in the vertical direction during operation, calculate the force data of the working part of the CNC machine tool according to the displacement data, and apply a reaction force to the working part of the CNC machine tool through a spring.

[0118] The spring deformation adjustment module uses an electric cylinder to adjust the spring deformation, and based on Hooke's law, controls the spring elastic force through the spring deformation.

[0119] The spring deformation calculation module is configured to construct a bounce threshold for the working part of the CNC machine tool, and based on the reaction force required by the working part of the CNC machine tool in the vertical direction obtained, construct an adaptive spring elastic force calculation model, and inversely calculate the telescopic amount of the electric cylinder.

[0120] The compensation value calculation module is configured to construct a spring elastic force loss balance model, calculate the elastic force loss of the spring at different times based on the working time, working times and force conditions of the spring, and calculate the compensation value of the spring deformation according to the elastic force loss.

[0121] The elastic force loss factor calculation module is configured to construct and train a machine learning algorithm to calculate the spring elastic force loss factor, and calculate the reaction force provided by the spring elastic force to the working part of the CNC machine tool according to the displacement amount of the working part of the CNC machine tool and the spring elastic force loss factor, so as to achieve the force balance of the working part of the CNC machine tool in the vertical direction.

[0122] Embodiment 3

[0123] The present invention also provides an electronic device. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute a control method for a dynamic balance device as described above.

[0124] The method or system according to the embodiment of the present invention can also be implemented by means of the architecture of the electronic device of the present invention.

[0125] The electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, input / output components, a hard disk, etc.

[0126] The storage device in the electronic device, such as ROM or hard disk, can store a control method for a dynamic balance device provided by the present invention.

[0127] A control method for a dynamic balance device, comprising: obtaining displacement data of a working part of a numerically controlled machine tool in the vertical direction during operation, calculating force data of the working part of the numerically controlled machine tool according to the displacement data, and applying a reaction force to the working part of the numerically controlled machine tool through a spring; adjusting the spring deformation amount by an electric cylinder, and controlling the spring elastic force based on Hooke's law through the spring deformation amount; constructing a bounce threshold of the working part of the numerically controlled machine tool, and constructing an adaptive spring elastic force calculation model based on the obtained reaction force required by the working part of the numerically controlled machine tool in the vertical direction, and inversely solving the telescopic amount of the electric cylinder; constructing a spring elastic force loss balance model, calculating the elastic force loss of the spring at different times based on the working time, working times and force conditions of the spring, and calculating a compensation value of the spring deformation amount according to the elastic force loss; constructing and training a machine learning algorithm to calculate a spring elastic force loss factor, and calculating the reaction force provided by the spring elastic force to the working part of the numerically controlled machine tool according to the displacement amount of the working part of the numerically controlled machine tool and the spring elastic force loss factor, so as to achieve the force balance of the working part of the numerically controlled machine tool in the vertical direction.

[0128] Further, the electronic device may further include a user interface. Of course, the architecture of the present invention is only exemplary, and when implementing different devices, one or more components of the electronic device disclosed in the present invention may be omitted according to actual needs.

[0129] Embodiment 4

[0130] The present invention also discloses a computer-readable storage medium.

[0131] Computer-readable instructions are stored on the computer-readable storage medium.

[0132] When the computer-readable instructions are run by a processor, a control method for a dynamic balance device according to an embodiment of the present invention described with reference to the above drawings can be executed.

[0133] The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. Additionally, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program.

[0134] For example, the present invention provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by the present invention. For example: obtaining displacement data of the working part of a numerically controlled machine tool in the vertical direction during operation, calculating the force data of the working part of the numerically controlled machine tool based on the displacement data, and applying a reaction force to the working part of the numerically controlled machine tool through a spring; adjusting the spring deformation amount by using an electric cylinder, and controlling the spring elastic force based on Hooke's law through the spring deformation amount; constructing a bounce threshold of the working part of the numerically controlled machine tool, and constructing an adaptive spring elastic force calculation model based on the obtained reaction force required by the working part of the numerically controlled machine tool in the vertical direction, and inversely solving the telescopic amount of the electric cylinder; constructing a spring elastic force loss balance model, calculating the elastic force loss of the spring at different times based on the working time, working times and force conditions of the spring, and calculating the compensation value of the spring deformation amount according to the elastic force loss; constructing and training a machine learning algorithm, calculating the spring elastic force loss factor, and calculating the reaction force provided by the spring elastic force to the working part of the numerically controlled machine tool according to the displacement amount of the working part of the numerically controlled machine tool and the spring elastic force loss factor, so as to achieve the force balance of the working part of the numerically controlled machine tool in the vertical direction.

[0135] When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present invention are executed. The method, apparatus and device of the present invention can be implemented in many ways. For example, the method, apparatus and device of the present invention can be implemented by software, hardware, firmware or any combination of software, hardware and firmware.

[0136] The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the above specific described order unless otherwise specifically stated.

[0137] In addition, in some embodiments, the present invention can also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0138] In addition, parts of the above technical solutions provided in the embodiments of the present invention that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0139] As described above in the specific embodiments, the purpose, technical solutions and beneficial effects of the present invention are further described in detail. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for controlling a dynamic balancing device, characterized in that: include: Obtaining the displacement data of the working part of the CNC machine tool in the vertical direction during operation, calculating the force data of the working part of the CNC machine tool according to the displacement data, and applying a reaction force to the working part of the CNC machine tool through a spring; The spring deformation is adjusted by an electric cylinder, and the spring force is controlled by the spring deformation based on Hooke's law. Construct the bouncing threshold of the working part of the CNC machine tool, and based on the acquired reaction force required by the working part of the CNC machine tool in the vertical direction, construct an adaptive spring force calculation model to reversely solve the extension and contraction amount of the electric cylinder; Construct a spring force loss balance model, calculate the spring force loss at different times based on the spring working time, working times and force conditions, and calculate the compensation value of the spring deformation according to the spring force loss; Build and train a machine learning algorithm to calculate the spring force loss factor. Based on the displacement of the working part of the CNC machine tool and the spring force loss factor, calculate the reaction force provided by the spring force on the working part of the CNC machine tool to achieve the force balance of the working part of the CNC machine tool in the vertical direction.

2. A dynamic balancing device control method according to claim 1, characterized in that: Obtain the displacement data of the working part of the CNC machine tool in the vertical direction, calculate the force data of the working part of the CNC machine tool according to the displacement data, and calculate the resultant external force of the working part of the CNC machine tool in the vertical direction according to Newton's second law; A reaction force is applied to the working part of the CNC machine tool through a spring. In order to balance the force on the working part of the CNC machine tool in the vertical direction, a supporting force equal to the resultant external force and opposite in direction is provided through the spring; The top of the spring is connected to the top of the electric cylinder, and the bottom of the spring is connected to the working part of the CNC machine tool, and elastically deforms in the vertical direction; when the working part of the CNC machine tool is fixed, the spring controls the spring deformation through the expansion and contraction of the electric cylinder; The electric cylinder is used to adjust the spring deformation. By controlling the expansion and contraction of the electric cylinder, the spring deformation is changed so that the reaction force provided by the spring meets the force balance requirement of the working part of the CNC machine tool.

3. A dynamic balancing device control method according to claim 2, characterized in that: The displacement sensor is used to collect the displacement of the working part of the CNC machine tool during operation. ; Construct the bounce threshold of the working part of the CNC machine tool and define the bounce threshold of the working part of the CNC machine tool in the vertical direction , when the CNC machine tool working part is Displacement in time When , it is considered that a bounce occurs; Assume that the mass of the working part of the CNC machine tool is , the total external force on the working part of the CNC machine tool in the vertical direction is , according to Newton's second law: ;in is the acceleration of the working part of the CNC machine tool in the vertical direction, and the displacement collected by the displacement sensor About Time The second derivative of is obtained; Apply reaction force to the working part of the CNC machine tool through the spring, and set the spring to provide vertical upward support force According to Hooke's law, the spring force and deformation Proportional to: ;in is the spring stiffness coefficient; In order to balance the vertical force on the working part of the CNC machine tool, a spring is used to provide a force that is equal to the combined external force. Equal and opposite supporting forces : ; Control the spring deformation to achieve force balance of the working part of the CNC machine tool. It can be seen that by solving the deformation of the control spring ,make satisfy: , achieving force balance.

4. A dynamic balancing device control method according to claim 3, characterized in that: According to the displacement of the working part of the CNC machine tool in the vertical direction , calculate the total external force ; Construct an adaptive spring force calculation model and define the nonlinear stiffness coefficient function of the spring , the nonlinear stiffness coefficient function Expressed as a piecewise function: ； in for Preset force segmentation points, for The corresponding stiffness coefficients; The nonlinear stiffness coefficient function Substituting into Hooke's law, we get the adaptive spring force calculation model: ; Reverse solution of the electric cylinder extension and contraction amount, using the adaptive spring force calculation model To provide the required reaction force , spring deformation Need to meet: ; Extension and retraction of electric cylinder Spring deformation Equal, that is ; The required spring deformation calculated , control the extension and retraction of the electric cylinder , so that the spring provides the required reaction force to achieve force balance in the working part of the CNC machine tool.

5. A dynamic balancing device control method according to claim 4, characterized in that: Introduce spring force loss factor to compensate for the spring force loss when working; Define the spring loss factor , indicating the length of time the spring has worked , Number of work And the force In the case of , the loss ratio of elastic force relative to the initial value; Construct a spring force loss balance model and use it in the adaptive spring force calculation model Based on this, the elastic loss factor is introduced , and the spring force calculation model considering the elastic force loss is obtained: ;in is the actual spring force after considering the elastic force loss; Calculate the elastic force loss of the spring at different times, according to the working time of the spring , Number of work And the stress , substitute into the elastic loss factor expression, calculate the elastic loss factor at different times; Substitute the spring force calculation model that takes into account the elastic force loss to obtain the actual spring force ; Calculate the compensation value of the spring deformation using the spring force calculation model that takes into account the spring force loss It can be seen that in order to compensate for the elastic force loss, the actual spring force Achieve the required support ,Right now , the spring deformation to make compensation; , get the compensation value of the spring deformation : ; Compensation value of electric cylinder extension ; The extension and contraction amount of the electric cylinder Increase the compensation value of the electric cylinder extension amount , the expansion and contraction amount of the electric cylinder after compensation Substitute it into the electric cylinder control, that is, take the elastic force loss into consideration, and realize the force balance of the working part of the CNC machine tool in the vertical direction.

6. A dynamic balancing device control method according to claim 5, characterized in that: Collect historical working data of springs, including the working time of springs , Number of work , force and the corresponding elastic loss factor , forming a data set; Select the working time , Number of work and force As input features, elastic loss factor As the output target; randomly divide the data set into training set and test set; Construct a support vector regression SVR model, select the Gaussian kernel function as the kernel function of the SVR model, introduce relaxation variables, and construct the optimization target of the SVR model; The optimization problem is transformed into a dual problem and Lagrange multipliers are introduced to solve it; Train and optimize the support vector regression (SVR) model. Use the training set data to solve the dual problem of the SVR model to obtain the optimal Lagrange multiplier and model parameters of the SVR model. Use the test set data to evaluate the trained SVR model, calculate the error between the predicted value and the true value, and use the mean square error, mean absolute error, and determination coefficient indicators to evaluate the model's prediction performance. According to the model evaluation results, adjust the hyperparameters of the SVR model, including the penalty coefficient, the parameters of the loss function, and the bandwidth parameter of the kernel function; use the grid search optimization method to search for the optimal hyperparameter combination in the hyperparameter space; repeat the model training and evaluation steps until the expected prediction performance is obtained.

7. A dynamic balancing device control method according to claim 6, characterized in that: The trained model is used to calculate the elastic loss factor, and the trained SVR model is deployed to the control system of the CNC machine tool to realize the online prediction function; During the operation of the CNC machine tool, the working time of the spring is collected in real time , Number of work and force , which is input into the SVR model to obtain the predicted elastic loss factor ; Elasticity loss compensation, the predicted elasticity loss factor Substitute the spring deformation into the compensation formula: ； Calculate the real-time spring deformation compensation value , the calculated spring deformation compensation value The force is transmitted to the electric cylinder to adjust the extension and contraction of the electric cylinder to compensate for the loss of spring force.

8. A dynamic balancing device control system, used to implement a dynamic balancing device control method according to any one of claims 1 to 7, characterized in that: include: Displacement data acquisition module, spring deformation adjustment module, spring deformation calculation module, compensation value calculation module and elastic force loss factor calculation module; The displacement data acquisition module is used to acquire the displacement data of the working part of the CNC machine tool in the vertical direction when the CNC machine tool is working, calculate the force data of the working part of the CNC machine tool according to the displacement data, and apply a reaction force to the working part of the CNC machine tool through a spring; The spring deformation adjustment module uses an electric cylinder to adjust the spring deformation, and controls the spring force through the spring deformation based on Hooke's law; The spring deformation calculation module is used to construct a bouncing threshold of the CNC machine tool working part, and based on the acquired reaction force required by the CNC machine tool working part in the vertical direction, construct an adaptive spring elastic force calculation model to reversely solve the extension and contraction amount of the electric cylinder; The compensation value calculation module is used to construct a spring elastic force loss balance model, calculate the elastic force loss of the spring at different times based on the spring working time, working times and force conditions, and calculate the compensation value of the spring deformation according to the elastic force loss; The elastic force loss factor calculation module is used to construct and train a machine learning algorithm, calculate the spring elastic force loss factor, and calculate the reaction force provided by the spring elastic force on the working part of the CNC machine tool based on the displacement of the working part of the CNC machine tool and the spring elastic force loss factor, so as to achieve the force balance of the working part of the CNC machine tool in the vertical direction.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes a dynamic balancing device control method as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes a dynamic balancing device control method as claimed in any one of claims 1 to 7.

Images