CN116107267B - Numerical control machine tool control parameter optimization method and device - Google Patents
Numerical control machine tool control parameter optimization method and device Download PDFInfo
- Publication number
- CN116107267B CN116107267B CN202310211230.1A CN202310211230A CN116107267B CN 116107267 B CN116107267 B CN 116107267B CN 202310211230 A CN202310211230 A CN 202310211230A CN 116107267 B CN116107267 B CN 116107267B
- Authority
- CN
- China
- Prior art keywords
- parameters
- control
- main shaft
- vibration
- control parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/408—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by data handling or data format, e.g. reading, buffering or conversion of data
- G05B19/4083—Adapting programme, configuration
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/35—Nc in input of data, input till input file format
- G05B2219/35356—Data handling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a method and a device for optimizing control parameters of a numerical control machine tool, wherein the method comprises the steps of establishing a model based on an active disturbance rejection controller, determining control parameters to be set, acquiring vibration signals of a feeding system and a main shaft system, and extracting characteristic parameters of the vibration signals; and carrying out fusion setting on the control parameters of the main shaft system and the feeding system based on the characteristic parameters of the vibration signals and the control parameters to be set through the neural network. And a neural network is adopted to realize the fusion setting of control parameters of the feeding system and the main shaft system, and the coupling relation of vibration signals of the feeding system and the main shaft system is determined based on the correlation of the vibration signals of the two motion systems, so that the setting parameters are adjusted. Based on the method for adjusting the control parameters, the invention realizes that the motion stability is improved in the motion control of the machine tool which is sensitive to vibration, and the vibration caused by improper selection of the setting parameters is reduced.
Description
Technical Field
The invention relates to the field of numerical control machine tools, in particular to a method and a device for optimizing control parameters of a numerical control machine tool.
Background
The numerical control machine tool is used as main production equipment and plays a non-negligible role in machining. However, since machining is a dynamic transformation process, severe chatter is generated in the time-varying cutting process due to the influence of factors such as damage to internal parts, thermal deformation, and uneven hardness of materials.
In the prior art, a common method for vibrating a numerical control machine tool is to adjust the machine tool structure or adjust the movement working condition of the machine tool so as to reduce the influence of vibration on the machining process, and generally, a single movement system is considered, but vibration interference coupling among a plurality of movement systems is not considered.
By analyzing the operation principle of the machine tool, when the movement of the main shaft of the machine tool and the feeding movement are performed simultaneously, the vibration generated by the movement of the main shaft of the machine tool and the feeding movement can be overlapped and mutually influenced. Therefore, it is necessary to perform optimization of the motion parameters in combination with the vibration signals of the two motions.
Disclosure of Invention
(one) solving the technical problems
In order to solve the technical problems, the invention provides a method and a device for optimizing control parameters of a numerical control machine tool, wherein the method combines machine tool spindle motion and feeding motion vibration signals to optimize the control parameters of the motion, so that the stability of the motion control is improved in the motion control of a machine tool sensitive to vibration, the vibration caused by improper selection of setting parameters is reduced, and the machining precision is improved.
(II) technical scheme
In order to solve the technical problems and achieve the aim of the invention, the invention is realized by the following technical scheme:
a control parameter optimization method of a numerical control machine tool comprises the following steps:
s1: establishing a controller model, wherein the controller model is established based on an active disturbance rejection controller and comprises a differential tracker, a nonlinear state observer and a nonlinear state error feedback controller;
s2: determining control parameters to be set, wherein the control parameters to be set comprise parameters of an active disturbance rejection controller of a feeding system and a main shaft system;
s3, obtaining vibration signals of the feeding system and the main shaft system, and extracting characteristic parameters of the vibration signals;
s4: and (3) carrying out fusion setting on the control parameters of the main shaft system and the feeding system based on the characteristic parameters of the vibration signals obtained in the step (S3) and the to-be-set control parameters obtained in the step (S2) through a neural network.
Further, the state equation of the nonlinear expansion state observer in the step S1 is as follows:
wherein: e is the control error, and is the control error, y for system output, d is a nonlinear parameter, lambda 1 、λ 2 、λ 3 Parameters to be optimized are observation coefficients; a, a 1 、a 2 、a 3 Is a exponent value of a power function, b is empirically determined 0 To control the gain, z 1 、z 2 、z 3 Is the current state quantity of the system;is the output of the extended state observer, namely the observed estimated value
Nonlinear state error feedback controller:
the error signal obtained by the interaction of the differential tracker and the nonlinear expansion state observer is taken as the input, and the control quantity u is obtained through calculation o ；
Wherein: k (k) 1 、k 2 Parameters to be optimized are observer coefficients; a, a 4 、a 5 Exponent value for power function; b 0 For controlling gain, u is the control quantity; e, e 1 For tracking signal x 1 Disturbance value z estimated by non-linear expansion state observer 1 A state error signal, e, constituting a system 2 As differential signal x 2 Disturbance value z estimated with ESO 2 The state error, z, of the constituent system 3 Disturbance values estimated for the non-linear expansion state observer.
Further, the fal (e, a, d) function value expression is as follows:
wherein k, p, q are coefficients.
Further, the control parameters to be set in step S2 include a speed factor R of tracking speed of the differential tracker 1 The method comprises the steps of carrying out a first treatment on the surface of the Nonlinear state error feedback controller observer coefficient k 1 、k 2 The method comprises the steps of carrying out a first treatment on the surface of the Observation coefficient lambda of non-linear expansion state observer 1 、λ 2 、λ 3 Control gain b 0 。
Further, the step S3 further includes:
s31: collecting vibration signals;
s32: processing the acquired signals;
s33: extracting signal characteristics, including time domain characteristics, energy entropy and correlation characteristics;
the correlation characteristic is a correlation coefficient of vibration signals of the feeding system and the main shaft system, and specifically comprises the following steps:
wherein s is i 、s j Vibration signals of the feeding system and the main shaft system are respectively; e(s) is the expected value of the signal.
Further, the vibration signal acquisition comprises a plurality of acceleration sensors respectively arranged on the side surface of the lathe bed, and a plurality of acceleration sensors respectively arranged on the workbench and the guide rail; the vibration of the spindle is measured at a position on the workpiece that is close to the tool but does not affect the machining process.
Further, the signal processing of the collected signal includes performing wavelet packet decomposition reconstruction on the collected vibration sensor signal, including the following steps:
(1) J layers of wavelet packet decomposition is carried out on the signal to be detected, and a series of sub-signal sequences with different frequency bands are obtained after the decomposition;
(2) Extracting wavelet packet coefficients D from low frequency to high frequency for each frequency band m，k ；
(3) Calculating the energy entropy of each frequency band;
energy value E of each band of the mth layer m，k Is that
Ｅ m，k ＝∫|D m，k (t)| 2 dt
Wherein D is m，k (t) is a wavelet packet reconstruction coefficient; t is the time of the corresponding band signal;
according to the definition of entropy, the energy entropy H of each band of the m layer m，k The method comprises the following steps:
wherein, the liquid crystal display device comprises a liquid crystal display device,
wherein: p is p m，k The specific weight of the mth layer k frequency band in the mth layer total energy is calculated; e is the total energy:
8. the method for optimizing control parameters of a numerically controlled machine tool according to claim 1, wherein said step S4 further comprises:
s41: building a neural network model:
the network adopts a three-layer neural network comprising an input layer, an hidden layer and an output layer
S42: determining input and output parameters and an objective function:
the input parameters comprise time domain features, frequency domain features and correlation features of vibration signals of the feeding system and the main shaft system;
the output parameters are control parameters of the feeding system and the main shaft system respectivelyObserver coefficientsObservation coefficient->
Wherein, the parameter marked a is a feeding system parameter, and the parameter marked b is a main shaft system parameter;
the objective function is:
wherein y (k) is the actual output of the network; y is d (k) For expected output of the network, correcting the weight between the input layer and the hidden layer and the weight between the hidden layer and the output layer and parameters in the basis function by using a gradient descent method;
s43: training a network and determining network parameters;
s44: the control parameters of the feed system and the spindle system are optimized according to the designed network.
The invention also provides a device for optimizing the control parameters of the numerical control machine tool, which comprises:
the controller model building module: the method is used for establishing an active disturbance rejection controller model and comprises a differential tracker, a nonlinear state observer and a nonlinear state error feedback controller;
the control parameter determining module is used for determining control parameters to be set, wherein the control parameters include a speed factor R1 for tracking speed; observer coefficient k 1 、k 2 The method comprises the steps of carrying out a first treatment on the surface of the Observation coefficient lambda 1 、λ 2 、λ 3 The method comprises the steps of carrying out a first treatment on the surface of the Coefficient b 0 ；
The vibration signal acquisition and processing module is used for acquiring vibration signals of the feeding system and the main shaft system and extracting characteristic parameters of the vibration signals; the vibration signal characteristic parameters comprise time domain characteristics, energy entropy and correlation characteristics, wherein the correlation characteristics are correlation coefficients of vibration signals of the feeding system and the main shaft system;
and the optimized control parameter module is used for carrying out fusion setting on the control parameters of the main shaft system and the feeding system through the characteristics of the vibration signals and the control parameters to be set based on a neural network algorithm.
In addition, in order to achieve the above object, the present invention further provides a computer readable storage medium, on which data encryption program instructions of a numerically controlled machine control parameter optimization method are stored, the data protection program instructions of the numerically controlled machine control parameter optimization being executable by one or more processors to implement the steps of the numerically controlled machine control parameter optimization method as described above.
(III) beneficial effects
Compared with the prior art, the invention realizes the on-line setting of the control parameters of the feeding system and the main shaft system by acquiring the vibration signal characteristics of the feeding system and the main shaft system. Furthermore, a neural network is adopted to realize the fusion setting of the control parameters of the feeding system and the main shaft system, and the coupling relation of the vibration signals of the feeding system and the main shaft system is determined based on the correlation of the vibration signals of the two motion systems, so that the setting parameters are adjusted. Based on the method for adjusting the control parameters, the motion stability is improved in the motion control of the machine tool which is sensitive to vibration, and vibration caused by improper selection of the setting parameters is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a flow chart of a method for optimizing control parameters of a numerical control machine according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a vibration signal acquisition sensor setup position according to an embodiment of the present application;
fig. 3 is a schematic diagram of a neural network structure according to an embodiment of the present application.
Reference numerals: 1-workpiece, 2-cutter, 3-headstock, 4-stand, 5-lathe bed, 6-workstation, 7-acceleration sensor.
Detailed Description
Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
Other advantages and effects of the present disclosure will become readily apparent to those skilled in the art from the following disclosure, which describes embodiments of the present disclosure by way of specific examples. It will be apparent that the described embodiments are merely some, but not all embodiments of the present disclosure. The disclosure may be embodied or practiced in other different specific embodiments, and details within the subject specification may be modified or changed from various points of view and applications without departing from the spirit of the disclosure. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict. All other embodiments, which can be made by one of ordinary skill in the art without inventive effort, based on the embodiments in this disclosure are intended to be within the scope of this disclosure.
It should also be noted that the illustrations provided in the following embodiments merely illustrate the basic concepts of the disclosure by way of illustration, and only the components related to the disclosure are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
Referring to fig. 1, a method for optimizing control parameters of a numerical control machine tool includes the following steps:
s1: establishing a controller model
The invention is based on an active disturbance rejection controller model, which comprises a differential tracker, a nonlinear state observer and a nonlinear state error feedback controller. The three important constituent modules of the active disturbance rejection controller can be designed into the following form according to the uncertain nonlinear object:
(1) The differential tracker can extract smooth and continuous input signals and generalized differential signals, realizes quick tracking of instructions and prevents overshoot, thereby solving the contradiction between quick and overshoot in the system. The differential tracker state equation is as follows:
the definition of the g-function is as follows:
wherein: v is the input signal of TD; v 1 A tracking signal of v; v 2 Extracting a signal for the differentiation of v; t is a sampling period; r is R 1 A speed factor for tracking speed;is a filtering effect factor.
(2) The nonlinear expansion state observer is used for expanding disturbance affecting system output into a new state variable to perform real-time estimation and compensation, the performance of the nonlinear expansion state observer directly affects the control quality of the active disturbance rejection controller, and the state equation is as follows:
wherein: e is the control error, and is the control error, y for system output, d is a nonlinear parameter, lambda 1 、λ 2 、λ 3 Parameters to be optimized are observation coefficients; a, a 1 、a 2 、a 3 Is a exponent value of a power function, b is empirically determined 0 To control the gain, z 1 、z 2 、z 3 Is the current state quantity of the system;the output of the extended state observer is the observation estimated value;
in order to improve the stability and convergence speed of the fal (e, a, d) function, the invention improves the fal (e, a, d) function.
The functional value expression of fal (e, a, d) is as follows:
in the formula, a sin function and a tan function are adopted to replace a primary term and a tertiary term in the traditional function, the stability of the sin function is better than that of the primary function, and the convergence rate of the tan function is better than that of the tertiary function, so that the stability and the convergence rate of the improved fal function word are better than those of the traditional fal function.
To ensure that the function is continuously conductive within the full definition domain, the following conditions are satisfied:
the bring-in fal function definition is available:
substituting the values of k, p and q into the above formula to obtain a nonlinear function fa ]:
it was found that the nonlinear function fa does not contain a quadratic term but only two terms sin and tan, which means that the quadratic term affects the smoothness and the conductivity of the function, resulting in a deterioration of the system performance. Therefore, the effect of the sin function and the tan function adopted by the invention is better than that of polynomial interpolation.
(3) Nonlinear state error feedback controller
The error signal obtained by the interaction of the differential tracker and the nonlinear expansion state observer is taken as the input, and the control quantity u is obtained through calculation o 。
Wherein: k (k) 1 、k 2 Parameters to be optimized are observer coefficients; a, a 4 、a 5 Exponent value for power function; b 0 For controlling gain, u is the control quantity; e, e 1 For tracking signal x 1 Disturbance value z estimated by non-linear expansion state observer 1 A state error signal, e, constituting a system 2 As differential signal x 2 Disturbance value z estimated with ESO 2 The state error, z, of the constituent system 3 Disturbance values estimated for the non-linear expansion state observer.
S2: determining control parameters to be set
At present, the requirements on the machining precision and complexity of machined parts of a machine tool are higher and higher, but with the development of technologies such as superhard high-speed cutting, dry cutting and the like, novel cutters made of ceramics, cubic boron nitride and the like are widely applied, but the cutters are fragile due to the characteristics of the materials, and are easy to crack even when subjected to tiny impact; meanwhile, along with the great improvement of the processing speed of numerical control processing, the possibility of vibration is increased, and in the processing such as cutting and the like, even tiny vibration can cause the deviation of the size or the surface roughness of a processed part, so the invention provides a method for realizing the control of the vibration of a numerical control machine tool by an intelligent algorithm on-line controller parameter adjustment method.
The controller model in step S1 can determine that the control parameters to be set include:
speed factor R for tracking speed 1 The method comprises the steps of carrying out a first treatment on the surface of the Observer coefficient k 1 、k 2 The method comprises the steps of carrying out a first treatment on the surface of the Observation coefficient lambda 1 、λ 2 、λ 3 The method comprises the steps of carrying out a first treatment on the surface of the Control gain b 0 。
b 0 Not only related to the object under investigation, but also the common parameters of ESO and NLSEF, different b 0 The values determine the variation of the disturbance over different ranges.
S3: and obtaining a vibration signal and extracting characteristic parameters of the vibration signal.
The invention combines the monitoring of vibrations of the feed system and the spindle system.
The feeding system is a connecting link of the numerical control device and the machine tool movement mechanism, and the servo motor drives the transmission mechanism to realize the movement of the workbench, the tool bit main shaft and other parts. Vibrations of the feed system include friction self-excited vibrations and feed residual vibrations.
Wherein the feed residual vibration is a mechanical structure resonance caused by acceleration and deceleration at the end of the movement of the moving part. Based on this, the vibration influence of this part can be reduced by an improvement of the control parameter.
The high-speed spindle is a core part of a machine tool, and requires a high rotation speed, high precision, and the like. Along with the continuous increase of the rotating speed of the main shaft of the machine tool, the acting force between the rotor and the bearing is continuously increased, and meanwhile, the main shaft vibrates due to intermittent cutting, unbalanced moving parts, self-excited cutting vibration and the like.
In the prior art, a common method for controlling the vibration of the main shaft adopts a self-balancing mechanism to perform balance control, but the self-balancing mechanism has a complex structural design and is difficult to use; another common way is by adjusting the bearing pre-tightening force, but this way has the problem of selecting different bearing pre-tightening forces at high and low speeds, which cannot be effectively adjusted on line.
Therefore, the flutter control can be better realized through adjusting the control parameters.
The acquisition of the vibration signal and the extraction of the signal characteristics comprise the following steps:
s31: vibration signal acquisition:
vibration signal acquisition includes acceleration-based sensors and force sensors.
The acceleration sensor is used for measuring the vibration of the feeding system, and the concrete setting mode is shown in fig. 2: a plurality of acceleration sensors 7 are respectively arranged on the side surface of the lathe bed 5, and a plurality of acceleration sensors 7 are respectively arranged on the workbench 6 and the guide rail; if the machine tool is of a gantry structure, a plurality of acceleration sensors 7 are further arranged on the gantry support.
Optionally, a plurality of acceleration sensors are respectively arranged on the spindle box 3 and the upright post 4.
Respectively obtaining detection values { p } of a plurality of acceleration sensors 7 1 p 2 … p n }。
The force sensor is used for measuring vibration of the spindle system. The forces generated by machining such as cutting forces during machining are the main sources of vibration that produce chatter. The present invention places the force sensor on the workpiece 1 close to the tool 2 without affecting the machining process.
The sensor can be mounted in a sticking or magnetic attraction mode.
S32: and processing the acquired signals.
The method comprises the steps of carrying out wavelet packet decomposition and reconstruction on the acquired vibration sensor signals, and comprises the following steps:
(1) J layers of wavelet packet decomposition is carried out on the signal to be detected, and a series of sub-signal sequences with different frequency bands are obtained after the decomposition;
(2) Extracting wavelet packet coefficients D from low frequency to high frequency for each frequency band m,k ；
(3) Calculating the energy entropy of each frequency band:
energy value E of each band of the mth layer m,k Is that
E m,k ＝∫｜Ｄ m,k (t)| 2 dt
Wherein D is m,k (t) is a wavelet packet reconstruction coefficient; t is the time of the corresponding band signal.
According to the definition of entropy, the energy entropy H of each band of the m layer m,k The method comprises the following steps:
wherein, the liquid crystal display device comprises a liquid crystal display device,
wherein: p is p m,k The specific weight of the mth layer k frequency band in the mth layer total energy is calculated; e is total energyThe amount is as follows:
s33: signal feature extraction is performed, including time domain features, energy entropy, and correlation features.
(1) The time domain features include mean, root mean square, mean square error, peak value, and kurtosis factor.
(2) The energy entropy feature includes the top 4 bands of energy entropy duty cycle rank.
(3) The correlation characteristic is a correlation coefficient of vibration signals of the feeding system and the main shaft system, and specifically comprises the following steps:
wherein s is i 、s i Vibration signals of the feeding system and the main shaft system are respectively; e(s) is the expected value of the signal.
The correlation coefficient satisfies |ρ ij |≤1。
As is known from the vibration generation principle, the vibrations of the feed system and the spindle system affect each other, and the vibration signals are in a coupling relationship, so that the correlation coefficient of the vibration signals of the feed system and the spindle system is also used as one of the characteristics of the vibration signals as an influencing factor for determining the motion control parameter.
Under different processing working conditions, the vibration of the main shaft system and the vibration of the feeding system have different vibration signals and vibration characteristic parameters, and the motion control parameters of the main shaft system and the feeding system are set by identifying the fusion of the different vibration characteristic parameters.
S4: optimizing control parameters based on a neural network:
and (3) carrying out fusion setting on the control parameters of the main shaft system and the feeding system based on the characteristics of the vibration signals obtained in the step (S3) and the control parameters to be set obtained in the step (S2). The specific method for fusion setting of control parameters based on the neural network algorithm is shown in fig. 3, and comprises the following steps:
s41: building a neural network model:
the network adopts a three-layer neural network comprising an input layer, an hidden layer and an output layer
S42: determining input and output parameters and an objective function:
the input parameters comprise time domain features, frequency domain features and correlation features of vibration signals of the feeding system and the main shaft system;
the output parameters are control parameters of the feeding system and the main shaft system respectivelyObserver coefficientsObservation coefficient->
Wherein, the parameter marked a is the feeding system parameter, and the parameter marked b is the main shaft system parameter.
The objective function is:
wherein y (k) is the actual output of the network; y is d (k) Output is expected for the network. And then correcting the parameters in the weight and the basis function between the input layer and the hidden layer and between the hidden layer and the output layer by using a gradient descent method.
S43: training the network and determining network parameters.
S44: the control parameters of the feed system and the spindle system are optimized according to the designed network.
In this embodiment, the on-line tuning of the control parameters of the feed system and the spindle system is achieved by acquiring the vibration signal characteristics of the feed system and the spindle system. Furthermore, a neural network is adopted to realize the fusion setting of the control parameters of the feeding system and the main shaft system, and the coupling relation of the vibration signals of the feeding system and the main shaft system is determined based on the correlation of the vibration signals of the two motion systems, so that the setting parameters are adjusted. Based on the method for adjusting the control parameters, the motion stability is improved in the motion control of the machine tool which is sensitive to vibration, and vibration caused by improper selection of the setting parameters is reduced.
The embodiment of the invention also provides a device for optimizing the control parameters of the numerical control machine tool, which comprises the following steps:
the controller model building module: the method is used for establishing an active disturbance rejection controller model and comprises a differential tracker, a nonlinear state observer and a nonlinear state error feedback controller;
the control parameter determining module is used for determining control parameters to be set, wherein the control parameters include a speed factor R1 for tracking speed; observer coefficient k 1 、k 2 The method comprises the steps of carrying out a first treatment on the surface of the Observation coefficient lambda 1 、λ 2 、λ 3 The method comprises the steps of carrying out a first treatment on the surface of the Coefficient b 0 。
The vibration signal acquisition and processing module is used for acquiring vibration signals of the feeding system and the main shaft system and extracting characteristic parameters of the vibration signals; the vibration signal characteristic parameters comprise time domain characteristics, energy entropy and correlation characteristics, wherein the correlation characteristics are correlation coefficients of vibration signals of the feeding system and the main shaft system;
and the optimized control parameter module is used for carrying out fusion setting on the control parameters of the main shaft system and the feeding system through the characteristics of the vibration signals and the control parameters to be set based on a neural network algorithm.
In addition, the embodiment of the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores data encryption program instructions of the numerical control machine control parameter optimization method, and the numerical control machine control parameter optimization program instructions can be executed by one or more processors to realize the steps of the numerical control machine control parameter optimization method.
The above examples are only illustrative of the preferred embodiments of the present invention and are not intended to limit the scope of the present invention, and various modifications and improvements made by those skilled in the art to the technical solution of the present invention should fall within the scope of protection defined by the claims of the present invention without departing from the spirit of the present invention.
Claims (8)
1. The numerical control machine tool control parameter optimization method is characterized by comprising the following steps of:
s1: establishing a controller model, wherein the controller model is established based on an active disturbance rejection controller and comprises a differential tracker, a nonlinear state observer and a nonlinear state error feedback controller;
s2: determining control parameters to be set, wherein the control parameters to be set comprise parameters of an active disturbance rejection controller of a feeding system and a main shaft system;
s3, obtaining vibration signals of the feeding system and the main shaft system, and extracting characteristic parameters of the vibration signals;
s4: fusing and setting control parameters of a main shaft system and a feeding system based on the characteristic parameters of the vibration signals obtained in the step S3 and the to-be-set control parameters obtained in the step S2 through a neural network;
the step S3 further includes:
s31: collecting vibration signals;
s32: processing the acquired signals;
s33: extracting signal characteristics, including time domain characteristics, energy entropy and correlation characteristics;
the correlation characteristic is a correlation coefficient of vibration signals of the feeding system and the main shaft system, and specifically comprises the following steps:
wherein (1)>、/>Vibration signals of the feeding system and the main shaft system are respectively; e(s) is a signal expectation;
the step S4 further includes:
s41: building a neural network model:
the network adopts a three-layer neural network comprising an input layer, an hidden layer and an output layer
S42: determining input and output parameters and an objective function:
the input parameters comprise time domain features, frequency domain features and correlation features of vibration signals of the feeding system and the main shaft system;
the output parameters are control parameters of the feeding system and the main shaft system respectively、/>The method comprises the steps of carrying out a first treatment on the surface of the Observer coefficient->、/>、/>、/>The method comprises the steps of carrying out a first treatment on the surface of the Observation coefficient->、/>、/>、/>；/>、/>；
Wherein, the parameter marked a is a feeding system parameter, and the parameter marked b is a main shaft system parameter;
the objective function is:
in (1) the->The actual output is the network; />For expected output of the network, correcting the weight between the input layer and the hidden layer and the weight between the hidden layer and the output layer and parameters in the basis function by using a gradient descent method;
s43: training a network and determining network parameters;
s44: the control parameters of the feed system and the spindle system are optimized according to the designed network.
2. The method according to claim 1, wherein the state equation of the nonlinear expansion state observer in the step S1 is as follows:
wherein: e is the control error, y is the system output, d is the nonlinear parameter, ++>、/>、/>Parameters to be optimized are observation coefficients; />、/>、/>Is a exponent value of a power function, empirically determined, < >>To control the gain +.>、/>、/>Is the current state quantity of the system; />、/>、/>The output of the extended state observer is the observation estimated value;
nonlinear state error feedback controller:
the error signal obtained by the interaction of the differential tracker and the nonlinear expansion state observer is taken as the input, and the error feedback control quantity is obtained through calculation；/>Wherein: />、/>Parameters to be optimized are observer coefficients; />、/>Exponent value for power function; />To control the gain +.>Is a control amount; />For tracking signal->Disturbance value estimated by non-linear expansion state observer +.>Form a status error signal of the system,/->For differentiating signal +.>Disturbance value estimated from ESO +.>Status errors of the constituent systems>Disturbance values estimated for the non-linear expansion state observer.
3. The method for optimizing control parameters of a numerical control machine according to claim 2, wherein the following is performedThe function value expression is as follows:
wherein k, p, q are coefficients.
4. The method according to claim 3, wherein the control parameters to be set in step S2 include a speed factor of tracking speed of a differential trackerThe method comprises the steps of carrying out a first treatment on the surface of the Nonlinear state error feedback controller observer coefficient +.>、/>The method comprises the steps of carrying out a first treatment on the surface of the Observation coefficient of non-linear expansion state observer +.>、/>、/>Control gain +.>。
5. The method for optimizing control parameters of a numerically-controlled machine tool according to claim 1, wherein the vibration signal acquisition comprises arranging a plurality of acceleration sensors on the side surface of the machine tool body respectively, and arranging a plurality of acceleration sensors on the workbench and the guide rail respectively; the vibration of the spindle is measured at a position on the workpiece that is close to the tool but does not affect the machining process.
6. The method for optimizing control parameters of a numerically controlled machine tool according to claim 1, wherein the signal processing of the acquired signals includes wavelet packet decomposition reconstruction of the acquired vibration sensor signals, comprising the steps of:
(1) J layers of wavelet packet decomposition is carried out on the signal to be detected, and a series of sub-signal sequences with different frequency bands are obtained after the decomposition;
(2) Extracting wavelet packet coefficients from low frequency to high frequency for each frequency band；
(3) Calculating the energy entropy of each frequency band;
energy value of each band of the mth layerIs->In (1) the->Reconstructing coefficients for the wavelet packet; />Time for the corresponding band signal;
according to the definition of entropy, the energy entropy of each frequency band of the m layerThe method comprises the following steps: />Wherein, the liquid crystal display device comprises a liquid crystal display device,wherein: />The specific weight of the mth layer k frequency band in the mth layer total energy is calculated; e is the total energy:。
7. an apparatus based on the numerical control machine tool control parameter optimization method according to any one of claims 1 to 6, comprising:
the controller model building module: the method is used for establishing an active disturbance rejection controller model and comprises a differential tracker, a nonlinear state observer and a nonlinear state error feedback controller;
a module for determining the control parameters to be set, which is used for determining the control parameters to be set, wherein the control parameters include a speed factor for tracking speedThe method comprises the steps of carrying out a first treatment on the surface of the Observer coefficient->、/>The method comprises the steps of carrying out a first treatment on the surface of the Observation coefficient->、/>、/>The method comprises the steps of carrying out a first treatment on the surface of the Coefficient->；
The vibration signal acquisition and processing module is used for acquiring vibration signals of the feeding system and the main shaft system and extracting characteristic parameters of the vibration signals; the vibration signal characteristic parameters comprise time domain characteristics, energy entropy and correlation characteristics, wherein the correlation characteristics are correlation coefficients of vibration signals of the feeding system and the main shaft system;
and the optimized control parameter module is used for carrying out fusion setting on the control parameters of the main shaft system and the feeding system through the characteristics of the vibration signals and the control parameters to be set based on a neural network algorithm.
8. A computer readable storage medium, wherein data encryption program instructions of a numerically controlled machine control parameter optimization method are stored on the computer readable storage medium, and the data protection program instructions of the numerically controlled machine control parameter optimization are executable by one or more processors to implement the steps of the numerically controlled machine control parameter optimization method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310211230.1A CN116107267B (en) | 2023-03-07 | 2023-03-07 | Numerical control machine tool control parameter optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310211230.1A CN116107267B (en) | 2023-03-07 | 2023-03-07 | Numerical control machine tool control parameter optimization method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116107267A CN116107267A (en) | 2023-05-12 |
| CN116107267B true CN116107267B (en) | 2023-07-18 |
Family
ID=86261649
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310211230.1A Active CN116107267B (en) | 2023-03-07 | 2023-03-07 | Numerical control machine tool control parameter optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116107267B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207070A (en) * | 2013-04-09 | 2013-07-17 | 苏州经贸职业技术学院 | Method for diagnosing failure of rotary machine by fusing oil and vibration |
| CN108646572A (en) * | 2018-07-16 | 2018-10-12 | 广西师范大学 | A kind of control method for three axis holder servo motors being combined with automatic disturbance rejection controller based on BP neural network |
| CN108716471A (en) * | 2018-04-03 | 2018-10-30 | 北京航空航天大学 | A kind of rotor of magnetic suspension molecular pump infinitesimal displacement Active Control Method |
| CN109639194A (en) * | 2019-01-21 | 2019-04-16 | 广西师范大学 | A kind of neural network of three axis holder servo motor and the composite control method of active disturbance rejection |
| CN110131312A (en) * | 2019-04-03 | 2019-08-16 | 江苏大学 | Five-degree-of-freedom alternating active magnetic bearings active disturbance rejection decoupling controller and building method |
| CN110488754A (en) * | 2019-08-09 | 2019-11-22 | 大连理工大学 | A kind of lathe self-adaptation control method based on GA-BP neural network algorithm |
| CN111694320A (en) * | 2020-06-10 | 2020-09-22 | 大连理工大学 | Machine tool self-adaptive control method considering flutter suppression |
| CN113031433A (en) * | 2021-02-02 | 2021-06-25 | 星展测控科技股份有限公司 | Method and device for controlling communication-in-motion servo system |
| CN113110290A (en) * | 2021-04-06 | 2021-07-13 | 大连理工大学 | Large-scale thin-wall part mirror image machining method based on force feedback control |
| CN113919217A (en) * | 2021-10-08 | 2022-01-11 | 南开大学 | Self-adaptive parameter setting method and device for active disturbance rejection controller |
| CN114696700A (en) * | 2022-01-14 | 2022-07-01 | 西安理工大学 | Neural network for online setting parameters of active disturbance rejection controller of permanent magnet synchronous motor |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10061275B2 (en) * | 2014-07-29 | 2018-08-28 | Linestream Technologies | Optimized parameterization of active disturbance rejection control |
| CN104571990A (en) * | 2014-12-22 | 2015-04-29 | 广东欧珀移动通信有限公司 | Method and system for adjusting operating state of display screen |
| CN106200872A (en) * | 2016-06-30 | 2016-12-07 | 维沃移动通信有限公司 | A kind of terminal and the management method of power consumption thereof |
| US11626815B2 (en) * | 2019-10-23 | 2023-04-11 | Guangdong University Of Technology | High-precision rigid-flexible coupling rotating platform and control method thereof |
-
2023
- 2023-03-07 CN CN202310211230.1A patent/CN116107267B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103207070A (en) * | 2013-04-09 | 2013-07-17 | 苏州经贸职业技术学院 | Method for diagnosing failure of rotary machine by fusing oil and vibration |
| CN108716471A (en) * | 2018-04-03 | 2018-10-30 | 北京航空航天大学 | A kind of rotor of magnetic suspension molecular pump infinitesimal displacement Active Control Method |
| CN108646572A (en) * | 2018-07-16 | 2018-10-12 | 广西师范大学 | A kind of control method for three axis holder servo motors being combined with automatic disturbance rejection controller based on BP neural network |
| CN109639194A (en) * | 2019-01-21 | 2019-04-16 | 广西师范大学 | A kind of neural network of three axis holder servo motor and the composite control method of active disturbance rejection |
| CN110131312A (en) * | 2019-04-03 | 2019-08-16 | 江苏大学 | Five-degree-of-freedom alternating active magnetic bearings active disturbance rejection decoupling controller and building method |
| CN110488754A (en) * | 2019-08-09 | 2019-11-22 | 大连理工大学 | A kind of lathe self-adaptation control method based on GA-BP neural network algorithm |
| CN111694320A (en) * | 2020-06-10 | 2020-09-22 | 大连理工大学 | Machine tool self-adaptive control method considering flutter suppression |
| CN113031433A (en) * | 2021-02-02 | 2021-06-25 | 星展测控科技股份有限公司 | Method and device for controlling communication-in-motion servo system |
| CN113110290A (en) * | 2021-04-06 | 2021-07-13 | 大连理工大学 | Large-scale thin-wall part mirror image machining method based on force feedback control |
| CN113919217A (en) * | 2021-10-08 | 2022-01-11 | 南开大学 | Self-adaptive parameter setting method and device for active disturbance rejection controller |
| CN114696700A (en) * | 2022-01-14 | 2022-07-01 | 西安理工大学 | Neural network for online setting parameters of active disturbance rejection controller of permanent magnet synchronous motor |
Non-Patent Citations (5)
| Title |
|---|
| 光电稳定平台神经网络自抗扰控制方法;朱启轩等;电光与控制;第25卷(第03期);第10-14页\n * |
| 基于BP神经网络的FTS输出控制;吕雪军等;振动与冲击;第38卷(第07期);第77-85页\n * |
| 基于自抗扰控制器的永磁同步电主轴速度扰动控制研究;孙荣俊等;组合机床与自动化加工技术(第11期);第108-111页\n * |
| 某新型电液伺服系统神经网络自抗扰控制;高雨轩;;机械制造与自动化(第02期);第229-232页\n * |
| 焊锡机器人位置控制算法的研究;罗亮等;机械设计与制造(第10期);第176-179，\n183页\n * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116107267A (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Aslan et al. | Prediction of cutting forces in five-axis milling using feed drive current measurements | |
| CN203894596U (en) | Multi-parameter online active monitoring system for machining states of numerical control machine bed | |
| Gordon et al. | Accurate control of ball screw drives using pole-placement vibration damping and a novel trajectory prefilter | |
| CN104166372B (en) | A kind of disturbance rejection control device of feed system Double position loop feedback | |
| CN103823409A (en) | Numerical machine tool machining state multi-parameter online active monitoring system and implement method thereof | |
| CN106002489A (en) | Automatic compensation device and method for eliminating cutting chatter of numerical control machine tool | |
| CN102929210A (en) | Control and optimization system for feature-based numerical control machining process and control and optimization method therefor | |
| DE102012014324A1 (en) | Control device that drives a driven object by two motors | |
| CN103192292B (en) | Numerical control machine error identification and separation method based on processing workpiece curved surface morphology information | |
| CN109746762B (en) | Online monitoring and inhibiting method for deep hole boring machining chatter | |
| CN113126564B (en) | Digital twin driven numerical control milling cutter abrasion on-line monitoring method | |
| CN106970593A (en) | It is a kind of that the method that processing flutter suppresses online is realized by speed of mainshaft intelligent control | |
| CN104950806A (en) | Machine tool feed system feedforward control method based on GMDH (Group Method of Data Handling) data mining algorithm | |
| CN109376440A (en) | A kind of processing control method of high-efficient milling weak separation part | |
| CN103268430A (en) | Milling technological parameter optimizing method based on machine tool dynamic stiffness measurement | |
| CN108732995B (en) | The fast acquiring method of milling process workpiece kinetic parameter | |
| Zhou et al. | Prediction of cutting force in milling process using vibration signals of machine tool | |
| CN112475410A (en) | Correlation analysis system and method for milling temperature and multivariate influence factors | |
| JP2021057030A (en) | Control system | |
| CN116107267B (en) | Numerical control machine tool control parameter optimization method and device | |
| El-Sinawi et al. | Improving surface roughness in turning using optimal control of tool's radial position | |
| Mandal | Applicability of tool condition monitoring methods used for conventional milling in micromilling: A comparative review | |
| Ogedengbe et al. | Feasibility of tool condition monitoring on micro-milling using current signals | |
| CN113946922B (en) | Dynamics integrated modeling and machining precision prediction method for five-axis linkage milling process | |
| Jee et al. | Real-time inertia compensation for multi-axis CNC machine tools |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |