Numerical control machining cutting force self-adaptive control method and device and storage medium

Abstract

The invention provides a numerical control machining cutting force adaptive control method, which comprises the following steps of: generating cutting force distribution along a machining tool path according to cutting force, feeding speed and machining line numbers acquired in a preprocessing process, performing feature segment identification on the cutting force distribution, generating corresponding CF codes as initial identifiers of different feature segments, and performing feature segment identification on the CF codes; compiling into a corresponding line number of the G code to obtain an NC program; the method comprises the following steps: actually machining a workpiece according to an NC program, taking an online collected actual cutting force at the current moment as a feedback cutting force, and taking a deviation between the feedback cutting force and a target cutting force and a CF code of a next machining line number in the NC program as input of a cutting force adaptive control system; and the feedback cutting force in the machining process is close to the target cutting force by adjusting the feeding speed of the numerical control machine tool on line. According to the method, the CF codes distributed along the machining tool path are introduced to serve as constraints of cutting force control, the robustness of self-adaptive control and the uniformity of cutting force distribution in the machining process are improved, and therefore the machining efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of numerical control machining, and in particular to a numerical control machining cutting force adaptive control method and device and a storage medium. BACKGROUND

[0002] In numerical control machining, in order to ensure the safety and reliability of the machining process and ensure the service life of the tool, conservative machining parameters are often used in machining programming, which sacrifices the machining efficiency and does not easily bring out the best machining capacity of the numerical control machine tool. Moreover, for a complex curved surface structure workpiece, the structural characteristics of the machining area are quite different, the tool frequently cuts in and out and the cutting amount is different, which leads to uneven distribution of cutting force in the machining process or even mutation, and the machining process is prone to vibration, which affects the surface quality of the workpiece and aggravates tool wear. Therefore, adaptive control of the cutting force is needed.

[0003] The adaptive control technology of cutting force adjusts the feed speed online, so that the numerical control machine tool can process with the target cutting force, which can improve the machining capacity and efficiency of the numerical control machine tool. The theory and application of generalized predictive control are very mature, and it has been verified that it can be effectively applied to the control of cutting force in numerical control machining. However, the existing technology only considers adaptive control with constant feed speed under constant machining conditions. In the actual machining process, due to the hysteresis of adaptive control, the mutation of cutting force will occur at the mutation of machining conditions (such as tool cutting in and cutting out), and for the acceleration and deceleration section in speed control, adjusting the feed speed according to the target cutting force will cause a large machining error.

[0004] For example, the prior art solution one (Chinese patent 202010930080.6, control method and device for adaptive machining of numerical control machine tool): the effective current of the cutting machining state is used to obtain the theoretical identification cutting force of the numerical control machine tool at the current time, the reinforcement learning model is used to obtain the predicted cutting force, the feed rate target optimum is autonomously found through the predicted cutting force, and adaptive machining of the numerical control machine tool according to the predicted cutting force is realized. However, this solution uses the kinematics equation of the machine tool spindle to obtain the theoretical cutting force as the feedback of adaptive control, without considering the influence of torque transmission process disturbance, and the error with the actual cutting force is large; and the neural network model used for cutting force prediction has a large amount of calculation, which is not suitable for online control.

[0005] Prior art solution two (paper, Li Qiang. Research on milling force control method based on generalized predictive control[D]. Harbin Engineering University, 2013.): A piezoelectric sensor is used for measuring the cutting force in the machining process, and a generalized predictive control algorithm is used for adaptive control of the feed speed. Since this scheme uses a piezoelectric sensor to obtain the actual machining cutting force, the cost is high, and the installation of the sensor may affect the machining; and in adaptive control, the actual machining cutting force distribution is not combined, and when the cutting condition changes too much, the cutting force may not be effectively controlled. SUMMARY

[0006] The present application aims to at least solve one of the technical problems existing in the prior art.

[0007] To this end, the present application provides a numerical control machining cutting force adaptive control method, device and storage medium, in the cutting force adaptive control process, the cutting force characteristic CF (Cutting Force) code distributed along the machining tool path is introduced as the constraint of cutting force control, the robustness of adaptive control and the uniformity of cutting force distribution in the machining process are improved, thereby improving the machining efficiency.

[0008] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0009] The first aspect of the present application provides a numerical control machining cutting force adaptive control method, comprising:

[0010] According to the machining tool path in the G code, the workpiece is pre-machined, the cutting force, the feed speed and the machining line number collected in the pre-machining process are used to generate the cutting force distribution along the machining tool path, the characteristic section of the cutting force distribution is identified, the corresponding CF code is generated as the identifier of the start of different characteristic sections, and the CF code is compiled into the corresponding line number of the G code to obtain the NC program; The information contained in the CF code is the cutting force characteristic value of the corresponding machining line number and the characteristic section to which it belongs;

[0011] According to the NC program, the workpiece is actually machined, the actual cutting force at the current time collected online in the actual machining process is taken as the feedback cutting force, the deviation between the feedback cutting force and the target cutting force and the CF code of the next machining line number in the NC program are taken as the input of the cutting force adaptive control system, and the feed speed of the numerical control machine tool is adjusted online to make the feedback cutting force in the machining process close to the target cutting force.

[0012] In some embodiments, the cutting force distribution along the machining tool path is generated according to the cutting force, the feed speed and the machining line number collected in the pre-machining process, comprising:

[0013] In the pre-processing process, data of cutting force, feed speed and machining line number corresponding timestamp are synchronously collected, the cutting force is obtained by direct acquisition or indirect acquisition;

[0014] According to the timestamp and the mutation feature point of cutting force and feed speed at the start of machining, the cutting force and feed speed with different sampling frequencies are aligned with the machining line number, and the average cutting force between each machining line number is taken as the cutting force feature value of the machining line number, and the cutting force distribution along the machining tool path is obtained.

[0015] In some embodiments, the cutting force distribution is subjected to feature segment recognition, and the recognized feature segments include idle cutting segments, feed-in segments, feed-out segments, cutting segments, acceleration segments and deceleration segments, wherein the idle cutting segments, feed-in segments, feed-out segments and cutting segments are recognized according to the k-nearest neighbor classification method and taking the cutting force of the tool position as the evaluation index, and the acceleration segments and deceleration segments are recognized according to the k-nearest neighbor classification method and taking the feed speed of the tool position as the evaluation index.

[0016] In some embodiments, the feature segment recognition process includes:

[0017] The recognition of the idle cutting segments, feed-in segments, feed-out segments and cutting segments:

[0018] First, according to the k-nearest neighbor classification method and taking the cutting force as the evaluation index, the rising segment IS, the stable segment SS and the falling segment DS in the cutting force distribution are preliminarily distinguished, including:

[0019] Let the mth tool position D m to be evaluated be [N m , Force m ], N m is the machining line number corresponding to the tool position D m , Force m is the cutting force corresponding to the tool position D m , and K tool positions adjacent to the tool position D m are selected as the neighborhood set D; all tool positions in the neighborhood set D are traversed, and the cutting force corresponding to a tool position in the neighborhood set D and the cutting force corresponding to any subsequent tool position are taken as a comparison pair, and a total of N = K(K-1) / 2 comparison pairs are obtained.

[0020] The fluctuation amount R is introduced, and the state judgment condition between adjacent tool positions is set as:

[0021] Stable segment SS: Force k-1 ×(1+R)≥Force k ≥Force k-1 ×(1-R)

[0022] Rising segment IS: Force k ≥ Force k-1 × (1 + R)

[0023] Descending segment DS: Force k ≥ Force k-1 × (1 - R)

[0024] wherein, Force k-1 and Force k are the cutting forces corresponding to the two tool positions in any comparison pair obtained for the adjacent set D respectively;

[0025] Traverse all the comparison pairs obtained for the adjacent set D, count the number of each state, and take the state with the largest number as the tool position D based on the evaluation of the cutting force; m Cutting load state ans:

[0026] ans = max (Count of IS, Count of SS, Count of DS)

[0027] wherein, Count of IS, Count of SS, Count of DS are the numbers of the rising segment IS, the stable segment SS and the descending segment DS respectively;

[0028] Subsequently, according to the rising segment IS, the stable segment SS and the descending segment DS identified by the above method, and in combination with the following several cases, the idle cutting segment, the feeding segment, the unloading segment, the cutting heavy load segment and the cutting light load segment are identified:

[0029] (1) Feeding segment: the cutting force increases, corresponding to the rising segment IS;

[0030] (2) Unloading segment: the cutting force decreases, corresponding to the descending segment DS;

[0031] (3) Idle cutting segment: the cutting force is almost 0 and shows stability, the starting point is the inflection point between the descending segment DS and the stable segment SS, and the end point is the inflection point between the stable segment SS and the rising segment IS;

[0032] (4) Cutting segment: the cutting force is large and shows stability, the starting point is the inflection point between the rising segment IS and the stable segment SS, and the end point is the inflection point between the stable segment SS and the descending segment DS; set a cutting force threshold value, and determine the cutting heavy load segment as the cutting segment with the average cutting force of the whole tool path greater than or equal to the cutting force threshold value, and determine the cutting light load segment as the cutting segment with the average cutting force of the whole tool path less than the cutting force threshold value;

[0033] The identification of the acceleration segment and the deceleration segment: take the feed speed of the tool position as the evaluation index and refer to the identification process of the feeding segment, the unloading segment and the idle cutting segment.

[0034] In some embodiments, the cutting force distribution is subjected to feature segment recognition by using a pre-trained feature segment recognition model, the feature segment recognition model is constructed by using LSTM neural network and trained by taking as training data set the empty cutting segment, the feed-in segment, the feed-out segment and the cutting segment recognized according to the k-nearest neighbor classification method and taking the cutting force of the tool position as the evaluation index, and the acceleration and deceleration segment recognized according to the k-nearest neighbor classification method and taking the feed rate of the tool position as the evaluation index.

[0035] In some embodiments, the actual cutting force is obtained by direct acquisition or indirect acquisition.

[0036] In some embodiments, the direct acquisition is direct acquisition of the cutting force by using a cutting force sensor installed on the numerical control machine tool, and the indirect acquisition is indirect acquisition of the cutting force based on a Kalman filter by online acquisition of spindle power.

[0037] In some embodiments, the cutting force adaptive control system performs cutting force adaptive control based on a generalized predictive control algorithm, reads the CF code of the next machining line number in advance, and adjusts the feedback cutting force according to the feature segment to which the next line number belongs:

[0038] ① For the feed-in segment, the cutting light load segment and the cutting heavy load segment, the feedback cutting force F m (q) = max(F a (q), F cf (q)), so as to reduce the feed rate in advance; F a (q) is the actual cutting force at the current time q in the actual machining process, and F cf (q) is the cutting force feature value corresponding to the machining line number at the current time q;

[0039] ② For the acceleration segment and the deceleration segment, the feedback cutting force F m (q) is taken as the target cutting force F d , the return feed rate is 100%, and the original acceleration and deceleration features are retained;

[0040] ③ For the feed-out segment, the actual cutting force F a (q) is taken as the feedback cutting force F m (q), and the feed rate is increased when entering the empty cutting segment.

[0041] The second aspect of the present application provides a numerical control machining cutting force adaptive control device, comprising:

[0042] The first module is configured to pre-process a workpiece according to a machining tool path in G code, generate a cutting force distribution along the machining tool path according to the cutting force, the feed speed and the machining line number collected in the pre-processing process, perform feature segment identification on the cutting force distribution, generate a corresponding CF code as an identifier of the start of different feature segments, compile the corresponding line number in the G code, and obtain an NC program; the CF code contains information of a cutting force feature value of the corresponding machining line number and a feature segment to which the cutting force feature value belongs;

[0043] The second module is configured to actually process the workpiece according to the NC program, take an actual cutting force of a current time collected online in the actual processing process as a feedback cutting force, take a deviation between the feedback cutting force and a target cutting force and a CF code of a next machining line number in the NC program as inputs of a cutting force adaptive control system, and make the feed speed of the numerical control machine tool online adjustment to make the feedback cutting force in the processing process close to the target cutting force.

[0044] The third aspect of the present application provides a computer readable storage medium, the computer readable storage medium stores computer instructions, the computer instructions are used for making the computer execute the numerical control machining cutting force adaptive control method according to any one of the embodiments of the third aspect of the present application.

[0045] Compared with the prior art, the present application has the following characteristics and beneficial effects:

[0046] In the cutting force adaptive control of numerical control machining, the present application obtains the cutting force features distributed along the machining tool path in the pre-processing mode, and correspondingly obtains the CF code, which is compiled into the NC program by CAM, and is used for real-time linkage adaptive control with the G code to guide the numerical control machining, thereby improving the accuracy and robustness of the cutting force adaptive control, effectively improving the machining efficiency, avoiding the cutting force mutation in the processing process, and improving the stability of the processing process. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 It is a flow chart of the numerical control machining cutting force adaptive control method provided by the first aspect of the present application;

[0048] Figure 2 It is a whole algorithm flow chart of the adaptive controller using the generalized predictive control algorithm as the embodiment of the present application;

[0049] Figure 3 It is a cutting force distribution extraction process schematic diagram along the machining tool path provided by the embodiment of the present application;

[0050] Figure 4 It is a cutting force feature segment identification result schematic diagram provided by the embodiment of the present application;

[0051] Figure 5A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical scheme and advantages of the present application more clear, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. The following schemes are only used to explain the inventive idea, and the specific schemes are not limited thereto. In addition, in order to facilitate the description, only the parts related to the present application are shown in the drawings, rather than all the processes.

[0053] On the contrary, the present application covers any alternative, modification, equivalent method and scheme defined by the claims on the essence and scope of the present application. Further, in order to make the public better understand the present application, in the following detailed description of the present application, some specific details are described in detail. The present application can also be completely understood without the description of these details by those skilled in the art.

[0054] Referring to Figure 1 The first aspect embodiment of the present application provides a numerical control machining cutting force adaptive control method, comprising the following steps:

[0055] Step S100, pre-machining the workpiece according to the machining tool path in the G code, generating the cutting force distribution along the machining tool path according to the cutting force, feed speed and machining line number collected in the pre-machining process, identifying the feature section of the cutting force distribution, generating the corresponding CF code as the identifier of the start of different feature sections, compiling into the corresponding line number of the G code, obtaining the NC program; the information contained in the CF code is the cutting force characteristic value of the corresponding machining line number and the corresponding feature section;

[0056] Step S200, actual machining the workpiece according to the NC program, taking the actual cutting force of the current time collected online in the actual machining process as the feedback cutting force, taking the deviation of the feedback cutting force and the target cutting force and the CF code of the next machining line number in the NC program as the input of the cutting force adaptive control system, and adjusting the feed speed of the numerical control machine tool online to make the feedback cutting force in the machining process close to the target cutting force.

[0057] The first aspect of the present application provides a cutting force adaptive control method based on CF (Cutting Force) code. In the pre-machining stage, the cutting force, feed speed and machining line number data of the pre-machining process are collected to generate the cutting force characteristics along the machining tool path. The cutting force adaptive control strategy is identified by recognizing the air cutting segment, feed cutting segment, tool-out segment, acceleration segment and deceleration segment. The CF code is generated and integrated into the cutting force adaptive control process to improve the accuracy and robustness of the cutting force adaptive control process under varying machining conditions.

[0058] In some embodiments, the purpose of generating the CF code is that the cutting force adaptive control system can identify the feed cutting segment, tool-out segment, acceleration segment and deceleration segment according to the CF code to modify the feed speed adjustment strategy, thereby improving the accuracy and stability of the cutting force adaptive control. Referring to Figure 2 , step S100 comprises the following steps:

[0059] Step S110: Pre-machining the workpiece according to the machining tool path in the G code. In the pre-machining process, the cutting force, feed speed and machining line number corresponding time stamp data are collected synchronously. The cutting force can be obtained by direct acquisition or indirect acquisition. The direct acquisition is to directly collect the cutting force by using the cutting force sensor installed on the numerical control machine tool. The indirect acquisition is to indirectly obtain the cutting force based on the Kalman filter by online collecting the spindle power. Considering the high cost of the cutting force sensor and the influence of installing the cutting force sensor on the machining process, the indirect acquisition of the cutting force is preferred in the present application.

[0060] Further, the cutting force is indirectly obtained based on the Kalman filter by online collecting the spindle power. The specific steps comprise:

[0061] Step S111: According to the collected spindle power of the numerical control machine tool, the total torque generated by the driving motor is obtained according to the following formula:

[0062]

[0063] Wherein, τ m is the total torque generated by the driving motor, which is used to overcome all loads generated in the machining process, including the inertia torque τ J , the friction torque τ f and the cutting torque τ c ; J e is the equivalent inertia of the driving motor; t is the time; Ω (rad / s) is the angular velocity of the driving motor; P is the spindle power of the numerical control machine tool.

[0064] Step S112: Removing the total torque τ mInertial torque τ J and friction torque τ f , to obtain the cutting torque τ c , the friction torque τ f can be obtained by the following Stribeck friction model:

[0065]

[0066] wherein τ coul is the Coulomb friction force; τ start is the maximum static friction force; v f is the driving shaft speed; v s is the Stribeck speed; +, - represent direction; C v is the viscous friction coefficient;

[0067] Step S113: using Kalman filtering to eliminate the dynamic disturbance of the cutting torque τ c transmitted, to obtain the estimated value F a of the actual cutting force in the pre-machining process. The data of the cutting force is the estimated value obtained by using the Kalman filtering method on the collected spindle power.

[0068] Step S120: according to the time stamp and the characteristic point of the sudden change of the cutting force and the feed speed at the start of machining, the cutting force and the feed speed of different sampling frequencies are aligned with the machining row number, and the average cutting force between each machining row number is taken as the cutting force characteristic value of the machining row number, and the cutting force distribution along the machining tool path is obtained, as shown in Figure 3 .

[0069] Step S130: feature segment recognition is performed on the cutting force distribution obtained in step S120, and the recognized feature segments include idle cutting segments, feed-in segments, tool-out segments, cutting segments, acceleration segments and deceleration segments, wherein the idle cutting segments, the feed-in segments and the tool-out segments take the cutting force of the tool position as the evaluation index, and the acceleration segments and the deceleration segments take the feed speed of the tool position as the evaluation index, and the specific steps include:

[0070] Step S131, identification of idle cutting segments, feed-in segments, tool-out segments and cutting segments:

[0071] Firstly, according to the k-nearest neighbor classification method and taking the cutting force as the evaluation index, the rising segment IS, the stable segment SS and the falling segment DS in the cutting force distribution are preliminarily distinguished, and the specific steps are as follows:

[0072] Let the mth tool position D m to be evaluated be [N m , Force m ], N m is the machining row number corresponding to the tool position D m , and Force m is the cutting force of the tool position Dm The corresponding cutting force, with tool position D m Select K adjacent knife points for the center to construct a neighboring set D, that is, D = {D m-(K-1) / 2 ,…,D m-1 ,D m ,D m+1 ,…,D m+(K-1) / 2}; traverse all the tool positions in the neighboring set D, and take the cutting force corresponding to a tool position in the neighboring set D and the cutting force corresponding to any subsequent tool position as a comparison pair, and obtain a total of M = K (K-1) / 2 comparison pairs; in a specific embodiment of the present invention, take K = 5, then the constructed neighboring set D = {D m-2 ,D m-1 ,D m ,D m+1 ,D m+2}, a total of M = 10 comparison pairs are obtained:

[0073] (D m-2 ,D m-1 )、(D m-2 ,D m )、(D m-2 ,D m+1 )、(D m-2 ,D m+2 )

[0074] (D m-1 ,D m )、(D m-1 ,D m+1 )、(D m-1 ,D m+2 )

[0075] (D m ,D m+1 )、(D m ,D m+2 )

[0076] (D m+1 ,D m+2 )

[0077] The fluctuation value R is introduced, and its value range is 0-1. For areas with large data fluctuations, a larger R should be taken, and the state judgment condition between two adjacent cutting positions is set as follows:

[0078] Stationary section SS: Force k-1 ×(1+R)≥Force k ≥Force k-1 ×(1-R)

[0079] Ascending IS: Force k ≥Forcek-1 x(1+R)

[0080] Rising segment IS: Force k ≥ Force k-1 x(1-R)

[0081] wherein, Force k-1 and Force k are the cutting forces corresponding to the two tool positions in any comparison pair obtained for the adjacent set D;

[0082] Traverse all the comparison pairs obtained for the adjacent set D, count the number of each state, and take the state with the largest number as the tool position D based on the evaluation of the cutting force m Cutting load state ans:

[0083] ans = max(Count of IS, Count of SS, Count of DS)

[0084] wherein, Count of IS, Count of SS, Count of DS are the numbers of the rising segment IS, the stable segment SS and the falling segment DS counted respectively;

[0085] Subsequently, since the cutting forces of the idle cutting segment and the cutting segment are relatively stable in the machining process, and the cutting force of the idle cutting segment is almost 0 and smaller than that of the cutting segment, the rising segment IS, the stable segment SS and the falling segment DS identified according to the above method can identify the idle cutting segment, the feed-in segment, the feed-out segment, the cutting heavy load segment and the cutting light load segment in the following several cases:

[0086] (1) Feed-in segment: the cutting force increases, corresponding to the rising segment IS;

[0087] (2) Feed-out segment: the cutting force decreases, corresponding to the falling segment DS;

[0088] (3) Idle cutting segment: the cutting force is almost 0 and relatively stable, the starting point is the inflection point between the falling segment DS and the stable segment SS, and the end point is the inflection point between the stable segment SS and the rising segment IS;

[0089] (4) Cutting segment: the cutting force is relatively large and stable, the starting point is the inflection point between the rising segment IS and the stable segment SS, and the end point is the inflection point between the stable segment SS and the falling segment DS; set a cutting force threshold, and determine the cutting heavy load segment as the cutting segment with the average cutting force of the entire tool path greater than or equal to the cutting force threshold, and determine the cutting light load segment as the cutting segment with the average cutting force of the entire tool path less than the cutting force threshold.

[0090] Step S132, identification of acceleration segment and deceleration segment:

[0091] The acceleration and deceleration section can be identified by using the same method as step S131 with the feed speed as the evaluation index, and specifically includes:

[0092] First, the rising section IS', the stable section SS', and the falling section DS' in the cutting force distribution are distinguished according to the k-nearest neighbor classification method and with the feed speed as the evaluation index, and specifically includes:

[0093] Suppose the n-th tool position D n to be evaluated is [N n , FS n ], N n is the machining row number corresponding to the tool position D n , and FS n is the feed speed corresponding to the tool position D n . The K' (which can be equal to or different from K, and in this embodiment K' = K) adjacent tool positions are selected around the tool position D n to form an adjacent set D', i.e. D' = {D n-(K-1) / 2 ,…,D n-1 ,D n ,D n+1 ,…,D n+(K-1) / 2}; all tool positions in the adjacent set D' are traversed, and the feed speed corresponding to a tool position in the adjacent set D' and the feed speed corresponding to any subsequent tool position are taken as a comparison pair, and a total of N = K'(K'-1) / 2 comparison pairs are obtained;

[0094] The fluctuation amount R' is introduced, and the value range is 0-1. For a region with large data fluctuation, a larger R' should be taken, and the state judgment condition between adjacent tool positions is set as:

[0095] The stable section SS': FS l-1 ×(1+R') ≥ FS l ≥ FS l-1 ×(1-R')

[0096] The rising section IS': FS l ≥ FS l-1 ×(1+R')

[0097] The falling section DS': FS l ≥ FS l-1 ×(1-R')

[0098] Wherein, FS l-1 and FS l are the feed speeds corresponding to the two tool positions in any comparison pair obtained from the adjacent set D';

[0099] Traverse all the comparison pairs obtained for the neighboring set D', count the number of each state, and take the state with the largest number as the tool position D based on cutting force evaluation n Low speed state ans':

[0100] ans'=max(Count ofIS',Count ofSS',Count ofDS')

[0101] Among them, Count of IS', Count of SS', and Count of DS' are the number of rising segments IS', stable segments SS', and falling segments DS' respectively;

[0102] Then, based on the rising segment IS', steady segment SS' and descending segment DS' identified by the above method, the acceleration segment, deceleration segment and uniform speed segment are identified:

[0103] (1) Acceleration stage: the feed speed increases, corresponding to the rising stage IS';

[0104] (2) Deceleration stage: emergency speed is reduced, corresponding to the descending stage DS';

[0105] (3) Uniform speed section: The feed speed is relatively stable. The starting point is the inflection point between the descending section DS' and the stable section SS', and the end point is the inflection point between the stable section SS' and the ascending section IS'.

[0106] Furthermore, since the k-nearest neighbor classification method needs to be reclassified for different machining processes, it is inefficient and has certain limitations. Considering that the characteristics of the cutting force distribution of different workpieces are similar, step S130 also includes: using the classification results obtained in steps S131 and S132 as a training data set, constructing an LSTM neural network for training, and obtaining a more general feature segment recognition model.

[0107] Step S140: Generate corresponding CF codes as identifiers of the start of different characteristic segments for the air cutting segment, feed segment, exit segment, cutting segment, acceleration segment, and deceleration segment identified in step S130, and compile them into the corresponding line number of the G code as a constraint for the adaptive control of the cutting force. The information contained in the CF code is the cutting force characteristic value F of the corresponding processing line number. cf and the feature segment to which it belongs.

[0108] In some embodiments, in step S200, the cutting force adaptive control system performs cutting force adaptive control based on the generalized predictive control algorithm. In the cutting force adaptive control, the CF code in the NC program obtained by reading step S100 is used together with the cutting force collected online as a constraint reference for the cutting force adaptive control. Figure 2 The specific steps of step S200 are as follows:

[0109] Step S210: actual machining is performed on the workpiece according to the NC program obtained in step S100, and the cutting force and the feed speed in the actual machining process are collected online, wherein the cutting force can be obtained in the manner defined in step S110, and in this embodiment, the cutting force in the actual machining process is indirectly obtained by online collection of the spindle power based on a Kalman filter, and the actual cutting force at the current time q in the actual machining process is denoted as F a (q), and the actual cutting force F a (q) is taken as the feedback cutting force F m (q).

[0110] Step S220: the CF code of the next machining line number is pre-read, and the feedback cutting force is adjusted according to the feature section to which the next line number belongs:

[0111] ① For the feed-in section, the cutting light load section and the cutting heavy load section, the feedback cutting force F m (q) = max(F a (q), F cf (q)), so as to reduce the feed speed in advance to avoid the sudden change caused by the cutting tool cutting in, and F cf (q) is the cutting force feature value corresponding to the machining line number at the current time q;

[0112] ② For the acceleration section and the deceleration section, the feedback cutting force F m (q) is taken as the target cutting force F d , and the feed ratio is returned to 100%, and the original acceleration and deceleration features are retained;

[0113] ③ For the tool-out section, the feedback cutting force F a (q) does not need to be adjusted, that is, the actual cutting force F a (q) is still taken as the feedback cutting force F m (q), and the feed speed is increased in the air cutting section.

[0114] Step S230: the feed drive and the milling machining system are approximated as a three-order discrete transfer function, and the transfer function is taken as a cutting force adaptive control model G c (q):

[0115]

[0116] Wherein z is a complex frequency variable, F m (q) is the feedback cutting force at time q, f c (q) is the feed speed at time q, and the parameter θ(q) of the cutting force adaptive control model is [a 1q ,a 2q ,b 0q ,b 1q ,b 2qThe recursive least square method with a forgetting factor is used for identification, and the performance index J of the recursive least square method is expressed as follows:

[0117]

[0118] Wherein, λ is the forgetting factor; L is the number of groups of input historical data; is the qth group of input historical data, F p is the predicted cutting force of the adaptive cutting force control system, f c is the feed speed of the adaptive cutting force control system.

[0119] The recursive formula of the above recursive least square method is obtained as follows:

[0120]

[0121] Wherein, K(q) is the gain matrix, and P(q) is the covariance matrix.

[0122] Step S240: In order to realize online adjustment of the machining process feed speed, the actual cutting force of the machining process is close to the target cutting force, a rolling optimization problem is defined, and the objective function of the optimization problem is J GPC min, J GPC The expression of J

[0123]

[0124] Wherein, F d is the target cutting force, F p is the predicted cutting force under the to-be-adjusted feed speed f c obtained by using the generalized prediction model, Г is the weighting coefficient matrix, and Δf c is the difference between the feed speed at the current time and the feed speed at the last time, is the expectation operator.

[0125] Then the optimal control quantity f c (q) at the qth time is obtained as follows:

[0126]

[0127] G(z -1 )=B(z -1 )E(z -1 )

[0128]

[0129] f c (q)=f c(q-1) + [1, 0,..., 0] Af c

[0130] wherein f i,j and e i,j are the elements of the i-th row and j-th column of the F matrix and E matrix respectively; a1, a2 are the coefficients [a 1q , a 2q ] in θ(q), B(z -1 ) is the coefficient [b 0q , b 1q , b 2q ] in θ(q), F r is the target cutting force, G1, G2 describe the dynamic characteristics and delay of the cutting force adaptive control system, E represents the bias matrix of the generalized prediction system, and F represents the feedback gain of the controller.

[0131] Step S250: obtaining the feed rate adjustment value at the q-th moment is set as f c (q) / f c (q-1), and the feed rate adjustment value is sent to the numerical control system in a PLC communication manner to realize online adjustment of the machining process feed speed.

[0132] The second aspect embodiment of the present application provides a numerical control machining cutting force adaptive control device, which comprises:

[0133] A first module is configured to pre-machining a workpiece according to a machining tool path in a G code, generating a cutting force distribution along the machining tool path according to the cutting force, the feed speed and the machining line number collected in the pre-machining process, identifying the cutting force distribution according to a feature section, generating a corresponding CF code as an identifier of the start of different feature sections, compiling the corresponding line number in the G code to obtain an NC program; the information contained in the CF code is the cutting force characteristic value of the corresponding machining line number and the feature section to which it belongs.

[0134] A second module is configured to actually machining the workpiece according to the NC program, taking the actual cutting force at the current moment collected online in the actual machining process as a feedback cutting force, taking the deviation between the feedback cutting force and the target cutting force and the CF code of the next machining line number in the NC program as the input of the cutting force adaptive control system, and adjusting the feed speed of the numerical control machine tool online to make the feedback cutting force in the machining process close to the target cutting force.

[0135] It should be noted that the above-mentioned embodiment of the numerical control machining cutting force adaptive control method is also applicable to the numerical control machining cutting force adaptive control device of the present embodiment, and will not be repeated here.

[0136] To achieve the above-mentioned embodiments, the embodiments of the present application further provide a computer readable storage medium, having stored thereon a computer program, which is executed by a processor to perform the numerical control machining cutting force adaptive control method of the above-mentioned embodiments.

[0137] Reference will now be made to the drawings, in which Figure 5 a structural diagram of an electronic device suitable for use in implementing embodiments of the present application is shown. It should be noted that the electronic device in the embodiments of the present application can include, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Multimedia Players), car terminals (e.g., car navigation terminals), and the like, as well as fixed terminals such as digital TVs, desktop computers, servers, and the like. Figure 5 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application.

[0138] As shown in Figure 5 , the electronic device can include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 101 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 102 or loaded into a random access memory (RAM) 103 from a storage device 108. Various programs and data required for the operation of the electronic device are also stored in the RAM 103. The processing device 101, the ROM 102, and the RAM 103 are connected to each other through a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0139] In general, the following devices can be connected to the I / O interface 105: input devices 106 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, and the like; output devices 107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; storage devices 108 including, for example, a magnetic tape, a hard disk, and the like; and communication devices 109. The communication devices 109 can allow the electronic device to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 An electronic device having various devices is shown, but it should be understood that all of the devices shown are not required to be implemented or possessed. More or fewer devices can be alternatively implemented or possessed.

[0140] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, an embodiment includes a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network by the communication device 109, or installed from the storage device 108, or installed from the ROM 102. When the computer program is executed by the processing device 101, the above-mentioned functions defined in the methods of the embodiments of the present application are performed.

[0141] It should be noted that the computer readable medium described above in the present application can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium may, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device or apparatus. In the present application, the computer readable signal medium can include a data signal carried in a baseband or as a part of a carrier wave, which carries computer readable program code. Such a propagated data signal can take on many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can transmit, propagate or transport program for use by or in connection with an instruction execution system, device or apparatus. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to a wire, cable, optical fiber, RF (radio frequency), or any suitable combination thereof.

[0142] The computer readable medium described above can be included in the electronic device described above; or can exist separately from the electronic device and be not assembled into the electronic device.

[0143] The computer readable medium described above carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the numerical control machining cutting force self-adaptive control method described above.

[0144] Computer program code for carrying out operations of the present application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++, Python, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0145] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In the specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Also, the specific features, structures, materials or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples, without contradiction.

[0146] In addition, the terms "first", "second", etc. are used only for the purpose of description and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality of" is at least two, for example, two, three, etc., unless otherwise specifically limited.

[0147] Any process or method descriptions or descriptions of the flow diagrams in the specification or elsewhere in this document, can be understood as representing the steps of the code of the modules, segments or portions of the code for implementing specific logic functions or steps in the process, and the scope of the preferred embodiments of the present application includes additional implementation in which the steps are performed in different order, including an essentially simultaneous performance of the functions according to the involved functions, or in reverse order, which should be understood by those skilled in the art of the embodiments of the present application.

[0148] The logic and / or steps represented in the flowcharts and / or described herein, for example, can be considered as a sequence of instructions to implement logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, apparatus, or device, such as a computer-based system, processor- based system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable medium can be a computer- readable storage medium or a computer-readable signal medium. The computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires (electrical connections), a portable computer diskette (a magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, for example, via optical scanning of the paper or other medium, then compiled, interpreted, or otherwise processed in a suitable manner, if necessary, and stored in a computer memory.

[0149] It should be understood that aspects of the application can be implemented in hardware, software, firmware or combinations thereof. In the above embodiments, the various steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following technologies, known in the art, or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and the like.

[0150] Those skilled in the art can understand that all or part of the steps carried out by the above-mentioned embodiments can be completed by programs instructing related hardware, and the developed programs can be stored in a computer-readable storage medium. When the programs are executed, they include one or a combination of the steps of the method embodiments.

[0151] In addition, each of the functional units in the various embodiments of the present application can be integrated in one processing module, or each of the units can be physically present separately, or two or more units can be integrated in one module. The integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer readable storage medium.

[0152] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements and variations to the above embodiments within the scope of the present application.

Claims

1. A method for adaptively controlling cutting force in numerical control machining, characterized in that: include: Pre-machining the workpiece according to the machining tool path in the G code, generating a cutting force distribution along the machining tool path based on the cutting force, feed speed, and machining line number collected during the pre-machining process, performing feature segment identification on the cutting force distribution, generating corresponding CF codes as identifiers for the start of different feature segments, and compiling them into the corresponding line numbers of the G code to obtain an NC program; the CF codes contain information such as the cutting force characteristic value corresponding to the machining line number and the corresponding feature segment; The workpiece is actually processed according to the NC program, and the actual cutting force at the current moment collected online during the actual processing is used as the feedback cutting force. The deviation between the feedback cutting force and the target cutting force and the CF code of the next processing line number in the NC program are used as the input of the cutting force adaptive control system. The feed speed of the CNC machine tool is adjusted online to make the feedback cutting force during the processing close to the target cutting force.

2. The CNC machining cutting force adaptive control method according to claim 1, characterized in that: Generating the cutting force distribution along the machining tool path according to the cutting force, feed speed and machining line number collected during the pre-machining process includes: During the pre-machining process, data of cutting force, feed speed and time stamp corresponding to the machining line number are synchronously collected, wherein the cutting force is obtained by direct acquisition or indirect acquisition; According to the timestamp and the mutation characteristic points of the cutting force and feed speed at the start of processing, the cutting force and feed speed of different sampling frequencies are aligned with the processing line number. The average cutting force between each processing line number is used as the cutting force characteristic value of the processing line number, and the cutting force distribution along the processing tool path is obtained at the same time.

3. The CNC machining cutting force adaptive control method according to claim 2, characterized in that: The cutting force distribution is subjected to characteristic segment identification, and the identified characteristic segments include an air cutting segment, a tool feed segment, a tool exit segment, a cutting segment, an acceleration segment, and a deceleration segment. The air cutting segment, the tool feed segment, the tool exit segment, and the cutting segment are identified according to a k-nearest neighbor classification method with the cutting force of the tool position as an evaluation index. The acceleration segment and the deceleration segment are identified according to a k-nearest neighbor classification method with the feed rate of the tool position as an evaluation index.

4. The CNC machining cutting force adaptive control method according to claim 3, characterized in that: The identification process of the feature segment includes: Identification of the air cutting section, the feed section, the exit section and the cutting section: First, based on the k-nearest neighbor classification method and using cutting force as an evaluation index, the rising segment IS, the stable segment SS, and the falling segment DS in the cutting force distribution are preliminarily distinguished, including: Suppose the mth knife point D to be evaluated m =[N m ,Force m ],N m The knife point D m Corresponding processing line number, Force m The knife point D m The corresponding cutting force, with tool position D m Select K adjacent tool locations for the center to construct a neighboring set D; traverse all tool locations in the neighboring set D, and use the cutting force corresponding to a tool location in the neighboring set D and the cutting force corresponding to any subsequent tool location as a comparison pair, obtaining a total of N = K (K-1) / 2 comparison pairs; The fluctuation R is introduced, and the state judgment condition between two adjacent cutting positions is set as follows: Stationary section SS: Force k-1 ×(1+R)≥Force k ≥Force k-1 ×(1-R) Ascending IS: Force k ≥Force k-1 ×(1+R) Descending section DS:Force k ≥Force k-1 ×(1-R) Among them, Force k-1 and Force k are the cutting forces corresponding to two tool positions in any comparison pair obtained for the adjacent set D; Traverse all comparison pairs obtained for the neighboring set D, count the number of each state, and take the state with the largest number as the tool position D based on cutting force evaluation m Cutting load state ans: ans=max(CountofIS,CountofSS,CountofDS) Among them, CountofIS, CountofSS, and CountofDS are the numbers of rising segments IS, stable segments SS, and falling segments DS respectively; Then, based on the rising section IS, stable section SS and descending section DS identified by the above method, the air cutting section, feed section, exit section, heavy-load cutting section and light-load cutting section are identified in combination with the following situations: (1) Feed stage: cutting force increases, corresponding to the rising stage IS; (2) Cutting out stage: cutting force decreases, corresponding to the descending stage DS; (3) Empty cutting section: The cutting force is almost 0 and is stable. The starting point is the inflection point between the descending section DS and the stable section SS, and the end point is the inflection point between the stable section SS and the ascending section IS. (4) Cutting segment: The cutting force is large and the trend is stable. The starting point is the inflection point between the rising segment IS and the stable segment SS, and the end point is the inflection point between the stable segment SS and the descending segment DS. A cutting force threshold is set. The cutting segment with an average cutting force of the entire tool path greater than or equal to the cutting force threshold is determined as a heavy-load cutting segment, and the cutting segment with an average cutting force of the entire tool path less than the cutting force threshold is determined as a light-load cutting segment. The identification of the acceleration section and the deceleration section is performed by taking the feed rate of the tool position point as an evaluation index and referring to the identification process of the tool feed section, tool exit section and air cutting section.

5. The CNC machining cutting force adaptive control method according to claim 3, characterized in that: A pre-trained feature segment identification model is used to identify the feature segments of the cutting force distribution. The feature segment identification model is obtained by constructing an LSTM neural network for training using the air cutting segment, feed segment, exit segment and cutting segment identified by the k-nearest neighbor classification method with the cutting force at the tool position as the evaluation index, and the acceleration and deceleration segments identified by the k-nearest neighbor classification method with the supply speed at the tool position as the evaluation index as the training data set.

6. The CNC machining cutting force adaptive control method according to claim 1, characterized in that: The actual cutting force is obtained by direct acquisition or indirect acquisition.

7. The CNC machining cutting force adaptive control method according to claim 2 or 6, characterized in that: The direct acquisition method is to directly acquire the cutting force using a cutting force sensor installed on a CNC machine tool; the indirect acquisition method is to indirectly obtain the cutting force by online acquisition of the spindle power based on a Kalman filter.

8. The CNC machining cutting force adaptive control method according to claim 1, characterized in that: The cutting force adaptive control system performs cutting force adaptive control based on the generalized predictive control algorithm, pre-reads the CF code of the next processing line number, and adjusts the feedback cutting force according to the feature segment of the next line number: ① For the feed section, light-load cutting section, and heavy-load cutting section, take the feedback cutting force F m (q)=max(F a (q),F cf (q)), thereby reducing the feed speed in advance; F a (q) is the actual cutting force at the current moment q during the actual machining process, F cf (q) is the cutting force characteristic value corresponding to the processing line number at the current moment q; ② For the acceleration and deceleration sections, feedback cutting force F m (q) are taken as the target cutting force F d , the return feed rate is 100%, retaining the original acceleration and deceleration characteristics; ③ For the cutting section, the actual cutting force F a (q) as the feedback cutting force F m (q), enter the air cutting section and increase the feed speed.

9. A CNC machining cutting force adaptive control device, characterized in that: include: The first module is configured to pre-process a workpiece according to a machining tool path in the G code, generate a cutting force distribution along the machining tool path based on the cutting force, feed rate, and machining line number collected during the pre-processing process, perform feature segment identification on the cutting force distribution, generate corresponding CF codes as identifiers for the start of different feature segments, compile them into the corresponding line number of the G code, and obtain an NC program; the CF codes contain information such as the cutting force characteristic value and the corresponding feature segment corresponding to the machining line number; The second module is configured to perform actual processing on the workpiece according to the NC program, and use the actual cutting force at the current moment collected online during the actual processing as the feedback cutting force, and use the deviation between the feedback cutting force and the target cutting force and the CF code of the next processing line number in the NC program as the input of the cutting force adaptive control system. By adjusting the feed speed of the CNC machine tool online, the feedback cutting force during the processing process is made close to the target cutting force.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the CNC machining cutting force adaptive control method according to any one of claims 1 to 8.

Images